summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorRaghavendra G <raghavendra@gluster.com>2010-08-18 14:23:02 +0000
committerAnand V. Avati <avati@dev.gluster.com>2010-08-18 13:00:23 -0700
commitf51252fa0d89556542fdfd190e8a94b28b013c36 (patch)
tree43ac09fe154daeefcf9de45be6e79a5d0a1e9a85
parent03df0871493d111116f168ec5331bffe99f6470f (diff)
rpcsvc: check for listener on default port used by mgmt (6969) while registering programs.v3.1.0prealpha3
- If programs have not provided a default port, rpcsvc tries to allocate a listener bound to default port. While registering programs, if programs have not given any port information, programs will be associated with either default listener or the one provided in options provided during rpcsvc_init, with latter given more precedence. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875
-rw-r--r--rpc/rpc-lib/src/rpcsvc.c5
-rw-r--r--xlators/mgmt/glusterd/src/glusterd.c1
2 files changed, 5 insertions, 1 deletions
diff --git a/rpc/rpc-lib/src/rpcsvc.c b/rpc/rpc-lib/src/rpcsvc.c
index e12403e20..c4c9fcaa2 100644
--- a/rpc/rpc-lib/src/rpcsvc.c
+++ b/rpc/rpc-lib/src/rpcsvc.c
@@ -1704,6 +1704,10 @@ rpcsvc_program_register (rpcsvc_t *svc, rpcsvc_program_t program)
}
listener = rpcsvc_get_listener (svc, listen_port, NULL);
+ if ((listener == NULL) && (listen_port == RPCSVC_DEFAULT_LISTEN_PORT)) {
+ listener = rpcsvc_get_listener (svc, 6969, NULL);
+ }
+
if ((listener == NULL) || (listener->trans == NULL)) {
if ((listener != NULL) && (listener->trans == NULL)) {
gf_log (GF_RPCSVC, GF_LOG_DEBUG,
@@ -1741,6 +1745,7 @@ rpcsvc_program_register (rpcsvc_t *svc, rpcsvc_program_t program)
listener = rpcsvc_create_listener (svc, program.options,
program.progname);
if (listener == NULL) {
+ ret = -1;
gf_log (GF_RPCSVC, GF_LOG_DEBUG,
"creation of listener for program (%s) failed",
program.progname);
diff --git a/xlators/mgmt/glusterd/src/glusterd.c b/xlators/mgmt/glusterd/src/glusterd.c
index 1997a31e5..a9f790bd3 100644
--- a/xlators/mgmt/glusterd/src/glusterd.c
+++ b/xlators/mgmt/glusterd/src/glusterd.c
@@ -148,7 +148,6 @@ glusterd_rpcsvc_notify (rpcsvc_t *rpc, void *xl, rpcsvc_event_t event,
switch (event) {
case RPCSVC_EVENT_ACCEPT:
{
- xprt->mydata = this;
break;
}
case RPCSVC_EVENT_DISCONNECT:
d>xlators/cluster/afr/src/afr-lk-common.c2143
-rw-r--r--xlators/cluster/afr/src/afr-mem-types.h54
-rw-r--r--xlators/cluster/afr/src/afr-messages.h473
-rw-r--r--xlators/cluster/afr/src/afr-open.c533
-rw-r--r--xlators/cluster/afr/src/afr-read-txn.c586
-rw-r--r--xlators/cluster/afr/src/afr-self-heal-common.c3564
-rw-r--r--xlators/cluster/afr/src/afr-self-heal-data.c1410
-rw-r--r--xlators/cluster/afr/src/afr-self-heal-entry.c1873
-rw-r--r--xlators/cluster/afr/src/afr-self-heal-metadata.c824
-rw-r--r--xlators/cluster/afr/src/afr-self-heal-name.c1097
-rw-r--r--xlators/cluster/afr/src/afr-self-heal.h441
-rw-r--r--xlators/cluster/afr/src/afr-self-heald.c2381
-rw-r--r--xlators/cluster/afr/src/afr-self-heald.h82
-rw-r--r--xlators/cluster/afr/src/afr-transaction.c4042
-rw-r--r--xlators/cluster/afr/src/afr-transaction.h63
-rw-r--r--xlators/cluster/afr/src/afr.c1874
-rw-r--r--xlators/cluster/afr/src/afr.h1894
-rw-r--r--xlators/cluster/afr/src/pump.c2475
-rw-r--r--xlators/cluster/afr/src/pump.h81
-rw-r--r--xlators/cluster/dht/src/Makefile.am26
-rw-r--r--xlators/cluster/dht/src/dht-common.c15498
-rw-r--r--xlators/cluster/dht/src/dht-common.h2002
-rw-r--r--xlators/cluster/dht/src/dht-diskusage.c794
-rw-r--r--xlators/cluster/dht/src/dht-hashfn.c151
-rw-r--r--xlators/cluster/dht/src/dht-helper.c3298
-rw-r--r--xlators/cluster/dht/src/dht-inode-read.c2172
-rw-r--r--xlators/cluster/dht/src/dht-inode-write.c1995
-rw-r--r--xlators/cluster/dht/src/dht-layout.c1260
-rw-r--r--xlators/cluster/dht/src/dht-linkfile.c526
-rw-r--r--xlators/cluster/dht/src/dht-lock.c1392
-rw-r--r--xlators/cluster/dht/src/dht-lock.h91
-rw-r--r--xlators/cluster/dht/src/dht-mem-types.h43
-rw-r--r--xlators/cluster/dht/src/dht-messages.h825
-rw-r--r--xlators/cluster/dht/src/dht-rebalance.c6620
-rw-r--r--xlators/cluster/dht/src/dht-rename.c2828
-rw-r--r--xlators/cluster/dht/src/dht-selfheal.c4036
-rw-r--r--xlators/cluster/dht/src/dht-shared.c1709
-rw-r--r--xlators/cluster/dht/src/dht.c165
-rw-r--r--xlators/cluster/dht/src/nufa.c1096
-rw-r--r--xlators/cluster/dht/src/switch.c1477
-rw-r--r--xlators/cluster/dht/src/tier.c1273
-rw-r--r--xlators/cluster/dht/src/tier.h72
-rw-r--r--xlators/cluster/dht/src/unittest/dht_layout_mock.c44
-rw-r--r--xlators/cluster/dht/src/unittest/dht_layout_unittest.c26
-rw-r--r--xlators/cluster/ec/src/Makefile.am38
-rw-r--r--xlators/cluster/ec/src/ec-code-avx.c109
-rw-r--r--xlators/cluster/ec/src/ec-code-avx.h (renamed from xlators/cluster/dht/src/dht-helper.h)15
-rw-r--r--xlators/cluster/ec/src/ec-code-c.c11679
-rw-r--r--xlators/cluster/ec/src/ec-code-c.h27
-rw-r--r--xlators/cluster/ec/src/ec-code-intel.c594
-rw-r--r--xlators/cluster/ec/src/ec-code-intel.h191
-rw-r--r--xlators/cluster/ec/src/ec-code-sse.c101
-rw-r--r--xlators/cluster/ec/src/ec-code-sse.h18
-rw-r--r--xlators/cluster/ec/src/ec-code-x64.c144
-rw-r--r--xlators/cluster/ec/src/ec-code-x64.h18
-rw-r--r--xlators/cluster/ec/src/ec-code.c1060
-rw-r--r--xlators/cluster/ec/src/ec-code.h44
-rw-r--r--xlators/cluster/ec/src/ec-combine.c910
-rw-r--r--xlators/cluster/ec/src/ec-combine.h38
-rw-r--r--xlators/cluster/ec/src/ec-common.c2602
-rw-r--r--xlators/cluster/ec/src/ec-common.h300
-rw-r--r--xlators/cluster/ec/src/ec-data.c220
-rw-r--r--xlators/cluster/ec/src/ec-data.h318
-rw-r--r--xlators/cluster/ec/src/ec-dir-read.c521
-rw-r--r--xlators/cluster/ec/src/ec-dir-write.c1295
-rw-r--r--xlators/cluster/ec/src/ec-fops.h416
-rw-r--r--xlators/cluster/ec/src/ec-galois.c183
-rw-r--r--xlators/cluster/ec/src/ec-galois.h32
-rw-r--r--xlators/cluster/ec/src/ec-generic.c1435
-rw-r--r--xlators/cluster/ec/src/ec-gf.c11635
-rw-r--r--xlators/cluster/ec/src/ec-gf8.c5882
-rw-r--r--xlators/cluster/ec/src/ec-gf8.h (renamed from xlators/cluster/ec/src/ec-gf.h)11
-rw-r--r--xlators/cluster/ec/src/ec-heal.c4653
-rw-r--r--xlators/cluster/ec/src/ec-heald.c974
-rw-r--r--xlators/cluster/ec/src/ec-heald.h41
-rw-r--r--xlators/cluster/ec/src/ec-helpers.c634
-rw-r--r--xlators/cluster/ec/src/ec-helpers.h223
-rw-r--r--xlators/cluster/ec/src/ec-inode-read.c1753
-rw-r--r--xlators/cluster/ec/src/ec-inode-write.c2444
-rw-r--r--xlators/cluster/ec/src/ec-locks.c920
-rw-r--r--xlators/cluster/ec/src/ec-mem-types.h11
-rw-r--r--xlators/cluster/ec/src/ec-messages.h550
-rw-r--r--xlators/cluster/ec/src/ec-method.c488
-rw-r--r--xlators/cluster/ec/src/ec-method.h34
-rw-r--r--xlators/cluster/ec/src/ec-types.h690
-rw-r--r--xlators/cluster/ec/src/ec.c1914
-rw-r--r--xlators/cluster/ec/src/ec.h61
-rw-r--r--xlators/cluster/ha/src/Makefile.am16
-rw-r--r--xlators/cluster/ha/src/ha-helpers.c194
-rw-r--r--xlators/cluster/ha/src/ha-mem-types.h26
-rw-r--r--xlators/cluster/ha/src/ha.c4013
-rw-r--r--xlators/cluster/ha/src/ha.h53
-rw-r--r--xlators/cluster/map/src/Makefile.am16
-rw-r--r--xlators/cluster/map/src/map-helper.c348
-rw-r--r--xlators/cluster/map/src/map-mem-types.h24
-rw-r--r--xlators/cluster/map/src/map.c2566
-rw-r--r--xlators/cluster/map/src/map.h67
-rw-r--r--xlators/cluster/stripe/src/Makefile.am19
-rw-r--r--xlators/cluster/stripe/src/stripe-helpers.c677
-rw-r--r--xlators/cluster/stripe/src/stripe-mem-types.h31
-rw-r--r--xlators/cluster/stripe/src/stripe.c5758
-rw-r--r--xlators/cluster/stripe/src/stripe.h286
-rw-r--r--xlators/debug/Makefile.am2
-rw-r--r--xlators/debug/delay-gen/Makefile.am (renamed from xlators/features/changetimerecorder/Makefile.am)0
-rw-r--r--xlators/debug/delay-gen/src/Makefile.am11
-rw-r--r--xlators/debug/delay-gen/src/delay-gen-mem-types.h21
-rw-r--r--xlators/debug/delay-gen/src/delay-gen-messages.h26
-rw-r--r--xlators/debug/delay-gen/src/delay-gen.c697
-rw-r--r--xlators/debug/delay-gen/src/delay-gen.h27
-rw-r--r--xlators/debug/error-gen/src/Makefile.am5
-rw-r--r--xlators/debug/error-gen/src/error-gen-mem-types.h6
-rw-r--r--xlators/debug/error-gen/src/error-gen.c2997
-rw-r--r--xlators/debug/error-gen/src/error-gen.h31
-rw-r--r--xlators/debug/io-stats/src/Makefile.am7
-rw-r--r--xlators/debug/io-stats/src/io-stats-mem-types.h17
-rw-r--r--xlators/debug/io-stats/src/io-stats.c6165
-rw-r--r--xlators/debug/sink/Makefile.am (renamed from xlators/features/qemu-block/Makefile.am)1
-rw-r--r--xlators/debug/sink/src/Makefile.am14
-rw-r--r--xlators/debug/sink/src/sink.c94
-rw-r--r--xlators/debug/trace/src/Makefile.am5
-rw-r--r--xlators/debug/trace/src/trace-mem-types.h7
-rw-r--r--xlators/debug/trace/src/trace.c5412
-rw-r--r--xlators/debug/trace/src/trace.h70
-rw-r--r--xlators/encryption/Makefile.am3
-rw-r--r--xlators/encryption/crypt/src/Makefile.am24
-rw-r--r--xlators/encryption/crypt/src/atom.c962
-rw-r--r--xlators/encryption/crypt/src/crypt-common.h141
-rw-r--r--xlators/encryption/crypt/src/crypt-mem-types.h45
-rw-r--r--xlators/encryption/crypt/src/crypt.c4526
-rw-r--r--xlators/encryption/crypt/src/crypt.h904
-rw-r--r--xlators/encryption/crypt/src/data.c769
-rw-r--r--xlators/encryption/crypt/src/keys.c302
-rw-r--r--xlators/encryption/crypt/src/metadata.c619
-rw-r--r--xlators/encryption/crypt/src/metadata.h74
-rw-r--r--xlators/encryption/rot-13/src/rot-13.c201
-rw-r--r--xlators/features/Makefile.am15
-rw-r--r--xlators/features/arbiter/src/Makefile.am8
-rw-r--r--xlators/features/arbiter/src/arbiter-mem-types.h7
-rw-r--r--xlators/features/arbiter/src/arbiter.c508
-rw-r--r--xlators/features/arbiter/src/arbiter.h11
-rw-r--r--xlators/features/barrier/src/Makefile.am5
-rw-r--r--xlators/features/barrier/src/barrier-mem-types.h6
-rw-r--r--xlators/features/barrier/src/barrier.c1081
-rw-r--r--xlators/features/barrier/src/barrier.h129
-rw-r--r--xlators/features/bit-rot/src/bitd/Makefile.am21
-rw-r--r--xlators/features/bit-rot/src/bitd/bit-rot-bitd-messages.h452
-rw-r--r--xlators/features/bit-rot/src/bitd/bit-rot-scrub-status.c78
-rw-r--r--xlators/features/bit-rot/src/bitd/bit-rot-scrub-status.h50
-rw-r--r--xlators/features/bit-rot/src/bitd/bit-rot-scrub.c2645
-rw-r--r--xlators/features/bit-rot/src/bitd/bit-rot-scrub.h37
-rw-r--r--xlators/features/bit-rot/src/bitd/bit-rot-ssm.c124
-rw-r--r--xlators/features/bit-rot/src/bitd/bit-rot-ssm.h38
-rw-r--r--xlators/features/bit-rot/src/bitd/bit-rot-tbf.c306
-rw-r--r--xlators/features/bit-rot/src/bitd/bit-rot-tbf.h70
-rw-r--r--xlators/features/bit-rot/src/bitd/bit-rot.c3133
-rw-r--r--xlators/features/bit-rot/src/bitd/bit-rot.h345
-rw-r--r--xlators/features/bit-rot/src/stub/Makefile.am12
-rw-r--r--xlators/features/bit-rot/src/stub/bit-rot-common.h175
-rw-r--r--xlators/features/bit-rot/src/stub/bit-rot-object-version.h12
-rw-r--r--xlators/features/bit-rot/src/stub/bit-rot-stub-helpers.c796
-rw-r--r--xlators/features/bit-rot/src/stub/bit-rot-stub-mem-types.h37
-rw-r--r--xlators/features/bit-rot/src/stub/bit-rot-stub-messages.h239
-rw-r--r--xlators/features/bit-rot/src/stub/bit-rot-stub.c4583
-rw-r--r--xlators/features/bit-rot/src/stub/bit-rot-stub.h646
-rw-r--r--xlators/features/changelog/lib/examples/c/get-changes-multi.c80
-rw-r--r--xlators/features/changelog/lib/examples/c/get-changes.c96
-rw-r--r--xlators/features/changelog/lib/examples/c/get-history.c144
-rwxr-xr-x[-rw-r--r--]xlators/features/changelog/lib/examples/python/changes.py16
-rw-r--r--xlators/features/changelog/lib/examples/python/libgfchangelog.py9
-rw-r--r--xlators/features/changelog/lib/src/Makefile.am34
-rw-r--r--xlators/features/changelog/lib/src/changelog-lib-messages.h74
-rw-r--r--xlators/features/changelog/lib/src/gf-changelog-api.c318
-rw-r--r--xlators/features/changelog/lib/src/gf-changelog-helpers.c250
-rw-r--r--xlators/features/changelog/lib/src/gf-changelog-helpers.h244
-rw-r--r--xlators/features/changelog/lib/src/gf-changelog-journal-handler.c1615
-rw-r--r--xlators/features/changelog/lib/src/gf-changelog-journal.h94
-rw-r--r--xlators/features/changelog/lib/src/gf-changelog-reborp.c622
-rw-r--r--xlators/features/changelog/lib/src/gf-changelog-rpc.c93
-rw-r--r--xlators/features/changelog/lib/src/gf-changelog-rpc.h10
-rw-r--r--xlators/features/changelog/lib/src/gf-changelog.c872
-rw-r--r--xlators/features/changelog/lib/src/gf-history-changelog.c1476
-rw-r--r--xlators/features/changelog/src/Makefile.am26
-rw-r--r--xlators/features/changelog/src/changelog-barrier.c138
-rw-r--r--xlators/features/changelog/src/changelog-encoders.c305
-rw-r--r--xlators/features/changelog/src/changelog-encoders.h42
-rw-r--r--xlators/features/changelog/src/changelog-ev-handle.c578
-rw-r--r--xlators/features/changelog/src/changelog-ev-handle.h110
-rw-r--r--xlators/features/changelog/src/changelog-helpers.c2866
-rw-r--r--xlators/features/changelog/src/changelog-helpers.h890
-rw-r--r--xlators/features/changelog/src/changelog-mem-types.h33
-rw-r--r--xlators/features/changelog/src/changelog-messages.h172
-rw-r--r--xlators/features/changelog/src/changelog-misc.h164
-rw-r--r--xlators/features/changelog/src/changelog-rpc-common.c499
-rw-r--r--xlators/features/changelog/src/changelog-rpc-common.h59
-rw-r--r--xlators/features/changelog/src/changelog-rpc.c588
-rw-r--r--xlators/features/changelog/src/changelog-rpc.h10
-rw-r--r--xlators/features/changelog/src/changelog-rt.c68
-rw-r--r--xlators/features/changelog/src/changelog-rt.h14
-rw-r--r--xlators/features/changelog/src/changelog.c4507
-rw-r--r--xlators/features/changetimerecorder/src/Makefile.am23
-rw-r--r--xlators/features/changetimerecorder/src/changetimerecorder.c1691
-rw-r--r--xlators/features/changetimerecorder/src/changetimerecorder.h26
-rw-r--r--xlators/features/changetimerecorder/src/ctr-helper.c300
-rw-r--r--xlators/features/changetimerecorder/src/ctr-helper.h735
-rw-r--r--xlators/features/changetimerecorder/src/ctr-xlator-ctx.c409
-rw-r--r--xlators/features/changetimerecorder/src/ctr-xlator-ctx.h90
-rw-r--r--xlators/features/cloudsync/Makefile.am (renamed from xlators/features/ganesha/Makefile.am)0
-rw-r--r--xlators/features/cloudsync/src/Makefile.am46
-rw-r--r--xlators/features/cloudsync/src/cloudsync-autogen-fops-tmpl.c30
-rw-r--r--xlators/features/cloudsync/src/cloudsync-autogen-fops-tmpl.h (renamed from xlators/features/changetimerecorder/src/ctr_mem_types.h)20
-rw-r--r--xlators/features/cloudsync/src/cloudsync-common.c60
-rw-r--r--xlators/features/cloudsync/src/cloudsync-common.h134
-rwxr-xr-xxlators/features/cloudsync/src/cloudsync-fops-c.py324
-rwxr-xr-xxlators/features/cloudsync/src/cloudsync-fops-h.py31
-rw-r--r--xlators/features/cloudsync/src/cloudsync-mem-types.h22
-rw-r--r--xlators/features/cloudsync/src/cloudsync-messages.h16
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/Makefile.am (renamed from xlators/storage/bd/Makefile.am)0
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/Makefile.am11
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cloudsyncs3/Makefile.am (renamed from xlators/encryption/rot-13/Makefile.am)2
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cloudsyncs3/src/Makefile.am12
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cloudsyncs3/src/libcloudsyncs3-mem-types.h19
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cloudsyncs3/src/libcloudsyncs3.c584
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cloudsyncs3/src/libcloudsyncs3.h50
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cloudsyncs3/src/libcloudsyncs3.sym1
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cvlt/Makefile.am (renamed from xlators/cluster/map/Makefile.am)2
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cvlt/src/Makefile.am12
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cvlt/src/archivestore.h203
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cvlt/src/cvlt-messages.h30
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cvlt/src/libcloudsynccvlt.sym1
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cvlt/src/libcvlt-mem-types.h19
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cvlt/src/libcvlt.c842
-rw-r--r--xlators/features/cloudsync/src/cloudsync-plugins/src/cvlt/src/libcvlt.h84
-rw-r--r--xlators/features/cloudsync/src/cloudsync.c2076
-rw-r--r--xlators/features/cloudsync/src/cloudsync.h123
-rw-r--r--xlators/features/compress/src/Makefile.am8
-rw-r--r--xlators/features/compress/src/cdc-helper.c766
-rw-r--r--xlators/features/compress/src/cdc-mem-types.h10
-rw-r--r--xlators/features/compress/src/cdc.c583
-rw-r--r--xlators/features/compress/src/cdc.h76
-rw-r--r--xlators/features/filter/Makefile.am3
-rw-r--r--xlators/features/filter/src/Makefile.am16
-rw-r--r--xlators/features/filter/src/filter.c1734
-rw-r--r--xlators/features/ganesha/src/Makefile.am18
-rw-r--r--xlators/features/ganesha/src/ganesha-mem-types.h21
-rw-r--r--xlators/features/ganesha/src/ganesha.c95
-rw-r--r--xlators/features/gfid-access/src/Makefile.am5
-rw-r--r--xlators/features/gfid-access/src/gfid-access-mem-types.h9
-rw-r--r--xlators/features/gfid-access/src/gfid-access.c2206
-rw-r--r--xlators/features/gfid-access/src/gfid-access.h137
-rw-r--r--xlators/features/glupy/Makefile.am3
-rw-r--r--xlators/features/glupy/doc/README.md44
-rw-r--r--xlators/features/glupy/doc/TESTING9
-rw-r--r--xlators/features/glupy/doc/test.vol10
-rw-r--r--xlators/features/glupy/examples/Makefile.am5
-rw-r--r--xlators/features/glupy/examples/debug-trace.py775
-rw-r--r--xlators/features/glupy/examples/helloworld.py19
-rw-r--r--xlators/features/glupy/examples/negative.py91
-rw-r--r--xlators/features/glupy/src/Makefile.am24
-rw-r--r--xlators/features/glupy/src/__init__.py.in2
-rw-r--r--xlators/features/glupy/src/glupy.c2501
-rw-r--r--xlators/features/glupy/src/glupy.h60
-rw-r--r--xlators/features/glupy/src/glupy/Makefile.am5
-rw-r--r--xlators/features/glupy/src/glupy/__init__.py852
-rw-r--r--xlators/features/glupy/src/setup.py.in24
-rw-r--r--xlators/features/index/src/Makefile.am10
-rw-r--r--xlators/features/index/src/index-mem-types.h15
-rw-r--r--xlators/features/index/src/index-messages.h33
-rw-r--r--xlators/features/index/src/index.c3427
-rw-r--r--xlators/features/index/src/index.h89
-rw-r--r--xlators/features/leases/Makefile.am (renamed from xlators/encryption/crypt/Makefile.am)2
-rw-r--r--xlators/features/leases/src/Makefile.am20
-rw-r--r--xlators/features/leases/src/leases-internal.c1412
-rw-r--r--xlators/features/leases/src/leases-mem-types.h27
-rw-r--r--xlators/features/leases/src/leases-messages.h33
-rw-r--r--xlators/features/leases/src/leases.c1168
-rw-r--r--xlators/features/leases/src/leases.h259
-rw-r--r--xlators/features/locks/src/Makefile.am14
-rw-r--r--xlators/features/locks/src/clear.c689
-rw-r--r--xlators/features/locks/src/clear.h71
-rw-r--r--xlators/features/locks/src/common.c1953
-rw-r--r--xlators/features/locks/src/common.h258
-rw-r--r--xlators/features/locks/src/entrylk.c1498
-rw-r--r--xlators/features/locks/src/inodelk.c1597
-rw-r--r--xlators/features/locks/src/locks-mem-types.h23
-rw-r--r--xlators/features/locks/src/locks.h332
-rw-r--r--xlators/features/locks/src/pl-messages.h29
-rw-r--r--xlators/features/locks/src/posix.c6356
-rw-r--r--xlators/features/locks/src/reservelk.c587
-rw-r--r--xlators/features/locks/tests/unit-test.c96
-rw-r--r--xlators/features/mac-compat/Makefile.am3
-rw-r--r--xlators/features/mac-compat/src/Makefile.am15
-rw-r--r--xlators/features/mac-compat/src/mac-compat.c349
-rw-r--r--xlators/features/mac-compat/src/mac-compat.h41
-rw-r--r--xlators/features/marker/src/Makefile.am13
-rw-r--r--xlators/features/marker/src/marker-common.c78
-rw-r--r--xlators/features/marker/src/marker-common.h12
-rw-r--r--xlators/features/marker/src/marker-mem-types.h23
-rw-r--r--xlators/features/marker/src/marker-quota-helper.c610
-rw-r--r--xlators/features/marker/src/marker-quota-helper.h86
-rw-r--r--xlators/features/marker/src/marker-quota.c5546
-rw-r--r--xlators/features/marker/src/marker-quota.h208
-rw-r--r--xlators/features/marker/src/marker.c4832
-rw-r--r--xlators/features/marker/src/marker.h218
-rw-r--r--xlators/features/metadisp/Makefile.am (renamed from xlators/cluster/stripe/Makefile.am)2
-rw-r--r--xlators/features/metadisp/src/Makefile.am38
-rw-r--r--xlators/features/metadisp/src/backend.c45
-rw-r--r--xlators/features/metadisp/src/fops-tmpl.c10
-rw-r--r--xlators/features/metadisp/src/gen-fops.py160
-rw-r--r--xlators/features/metadisp/src/metadisp-create.c101
-rw-r--r--xlators/features/metadisp/src/metadisp-fops.h51
-rw-r--r--xlators/features/metadisp/src/metadisp-fsync.c54
-rw-r--r--xlators/features/metadisp/src/metadisp-lookup.c90
-rw-r--r--xlators/features/metadisp/src/metadisp-open.c70
-rw-r--r--xlators/features/metadisp/src/metadisp-readdir.c65
-rw-r--r--xlators/features/metadisp/src/metadisp-setattr.c90
-rw-r--r--xlators/features/metadisp/src/metadisp-stat.c124
-rw-r--r--xlators/features/metadisp/src/metadisp-unlink.c160
-rw-r--r--xlators/features/metadisp/src/metadisp.c46
-rw-r--r--xlators/features/metadisp/src/metadisp.h45
-rw-r--r--xlators/features/namespace/Makefile.am3
-rw-r--r--xlators/features/namespace/src/Makefile.am17
-rw-r--r--xlators/features/namespace/src/namespace.c1344
-rw-r--r--xlators/features/namespace/src/namespace.h23
-rw-r--r--xlators/features/path-convertor/Makefile.am3
-rw-r--r--xlators/features/path-convertor/src/Makefile.am15
-rw-r--r--xlators/features/path-convertor/src/path-mem-types.h22
-rw-r--r--xlators/features/path-convertor/src/path.c1228
-rw-r--r--xlators/features/protect/Makefile.am3
-rw-r--r--xlators/features/protect/src/Makefile.am21
-rw-r--r--xlators/features/protect/src/prot_client.c218
-rw-r--r--xlators/features/protect/src/prot_dht.c168
-rw-r--r--xlators/features/protect/src/prot_server.c51
-rw-r--r--xlators/features/qemu-block/src/Makefile.am156
-rw-r--r--xlators/features/qemu-block/src/bdrv-xlator.c391
-rw-r--r--xlators/features/qemu-block/src/bh-syncop.c48
-rw-r--r--xlators/features/qemu-block/src/clock-timer.c60
-rw-r--r--xlators/features/qemu-block/src/coroutine-synctask.c116
-rw-r--r--xlators/features/qemu-block/src/monitor-logging.c50
-rw-r--r--xlators/features/qemu-block/src/qb-coroutines.c667
-rw-r--r--xlators/features/qemu-block/src/qb-coroutines.h30
-rw-r--r--xlators/features/qemu-block/src/qemu-block-memory-types.h25
-rw-r--r--xlators/features/qemu-block/src/qemu-block.c1139
-rw-r--r--xlators/features/qemu-block/src/qemu-block.h109
-rw-r--r--xlators/features/quiesce/src/Makefile.am7
-rw-r--r--xlators/features/quiesce/src/quiesce-mem-types.h7
-rw-r--r--xlators/features/quiesce/src/quiesce-messages.h28
-rw-r--r--xlators/features/quiesce/src/quiesce.c3370
-rw-r--r--xlators/features/quiesce/src/quiesce.h68
-rw-r--r--xlators/features/quota/src/Makefile.am22
-rw-r--r--xlators/features/quota/src/quota-enforcer-client.c729
-rw-r--r--xlators/features/quota/src/quota-mem-types.h28
-rw-r--r--xlators/features/quota/src/quota-messages.h252
-rw-r--r--xlators/features/quota/src/quota.c8151
-rw-r--r--xlators/features/quota/src/quota.h424
-rw-r--r--xlators/features/quota/src/quotad-aggregator.c749
-rw-r--r--xlators/features/quota/src/quotad-aggregator.h29
-rw-r--r--xlators/features/quota/src/quotad-helpers.c116
-rw-r--r--xlators/features/quota/src/quotad-helpers.h4
-rw-r--r--xlators/features/quota/src/quotad.c313
-rw-r--r--xlators/features/read-only/src/Makefile.am11
-rw-r--r--xlators/features/read-only/src/read-only-common.c550
-rw-r--r--xlators/features/read-only/src/read-only-common.h117
-rw-r--r--xlators/features/read-only/src/read-only-mem-types.h6
-rw-r--r--xlators/features/read-only/src/read-only.c181
-rw-r--r--xlators/features/read-only/src/read-only.h22
-rw-r--r--xlators/features/read-only/src/worm-helper.c395
-rw-r--r--xlators/features/read-only/src/worm-helper.h44
-rw-r--r--xlators/features/read-only/src/worm.c751
-rw-r--r--xlators/features/sdfs/Makefile.am3
-rw-r--r--xlators/features/sdfs/src/Makefile.am19
-rw-r--r--xlators/features/sdfs/src/sdfs-messages.h67
-rw-r--r--xlators/features/sdfs/src/sdfs.c1479
-rw-r--r--xlators/features/sdfs/src/sdfs.h49
-rw-r--r--xlators/features/selinux/Makefile.am3
-rw-r--r--xlators/features/selinux/src/Makefile.am20
-rw-r--r--xlators/features/selinux/src/selinux-mem-types.h (renamed from xlators/features/filter/src/filter-mem-types.h)15
-rw-r--r--xlators/features/selinux/src/selinux-messages.h30
-rw-r--r--xlators/features/selinux/src/selinux.c323
-rw-r--r--xlators/features/selinux/src/selinux.h24
-rw-r--r--xlators/features/shard/src/Makefile.am7
-rw-r--r--xlators/features/shard/src/shard-mem-types.h15
-rw-r--r--xlators/features/shard/src/shard-messages.h39
-rw-r--r--xlators/features/shard/src/shard.c9208
-rw-r--r--xlators/features/shard/src/shard.h488
-rw-r--r--xlators/features/snapview-client/src/Makefile.am7
-rw-r--r--xlators/features/snapview-client/src/snapview-client-mem-types.h12
-rw-r--r--xlators/features/snapview-client/src/snapview-client-messages.h71
-rw-r--r--xlators/features/snapview-client/src/snapview-client.c4129
-rw-r--r--xlators/features/snapview-client/src/snapview-client.h181
-rw-r--r--xlators/features/snapview-server/src/Makefile.am25
-rw-r--r--xlators/features/snapview-server/src/snapview-server-helpers.c905
-rw-r--r--xlators/features/snapview-server/src/snapview-server-mem-types.h15
-rw-r--r--xlators/features/snapview-server/src/snapview-server-messages.h54
-rw-r--r--xlators/features/snapview-server/src/snapview-server-mgmt.c845
-rw-r--r--xlators/features/snapview-server/src/snapview-server.c4140
-rw-r--r--xlators/features/snapview-server/src/snapview-server.h299
-rw-r--r--xlators/features/thin-arbiter/Makefile.am3
-rw-r--r--xlators/features/thin-arbiter/src/Makefile.am22
-rw-r--r--xlators/features/thin-arbiter/src/thin-arbiter-mem-types.h19
-rw-r--r--xlators/features/thin-arbiter/src/thin-arbiter-messages.h28
-rw-r--r--xlators/features/thin-arbiter/src/thin-arbiter.c661
-rw-r--r--xlators/features/thin-arbiter/src/thin-arbiter.h59
-rw-r--r--xlators/features/trash/src/Makefile.am7
-rw-r--r--xlators/features/trash/src/trash-mem-types.h13
-rw-r--r--xlators/features/trash/src/trash.c4296
-rw-r--r--xlators/features/trash/src/trash.h105
-rw-r--r--xlators/features/upcall/src/Makefile.am12
-rw-r--r--xlators/features/upcall/src/upcall-cache-invalidation.h43
-rw-r--r--xlators/features/upcall/src/upcall-internal.c1031
-rw-r--r--xlators/features/upcall/src/upcall-mem-types.h13
-rw-r--r--xlators/features/upcall/src/upcall-messages.h59
-rw-r--r--xlators/features/upcall/src/upcall.c3084
-rw-r--r--xlators/features/upcall/src/upcall.h206
-rw-r--r--xlators/features/utime/Makefile.am3
-rw-r--r--xlators/features/utime/src/Makefile.am41
-rw-r--r--xlators/features/utime/src/utime-autogen-fops-tmpl.c28
-rw-r--r--xlators/features/utime/src/utime-autogen-fops-tmpl.h22
-rwxr-xr-xxlators/features/utime/src/utime-gen-fops-c.py147
-rwxr-xr-xxlators/features/utime/src/utime-gen-fops-h.py35
-rw-r--r--xlators/features/utime/src/utime-helpers.c110
-rw-r--r--xlators/features/utime/src/utime-helpers.h25
-rw-r--r--xlators/features/utime/src/utime-mem-types.h21
-rw-r--r--xlators/features/utime/src/utime-messages.h29
-rw-r--r--xlators/features/utime/src/utime.c392
-rw-r--r--xlators/features/utime/src/utime.h23
-rw-r--r--xlators/lib/src/libxlator.c796
-rw-r--r--xlators/lib/src/libxlator.h121
-rw-r--r--xlators/meta/Makefile.am2
-rw-r--r--xlators/meta/src/Makefile.am5
-rw-r--r--xlators/meta/src/active-link.c30
-rw-r--r--xlators/meta/src/cmdline-file.c37
-rw-r--r--xlators/meta/src/frames-file.c169
-rw-r--r--xlators/meta/src/graph-dir.c134
-rw-r--r--xlators/meta/src/graphs-dir.c92
-rw-r--r--xlators/meta/src/history-file.c38
-rw-r--r--xlators/meta/src/logfile-link.c30
-rw-r--r--xlators/meta/src/logging-dir.c47
-rw-r--r--xlators/meta/src/loglevel-file.c45
-rw-r--r--xlators/meta/src/mallinfo-file.c30
-rw-r--r--xlators/meta/src/measure-file.c42
-rw-r--r--xlators/meta/src/meminfo-file.c38
-rw-r--r--xlators/meta/src/meta-defaults.c780
-rw-r--r--xlators/meta/src/meta-helpers.c450
-rw-r--r--xlators/meta/src/meta-hooks.h6
-rw-r--r--xlators/meta/src/meta-mem-types.h17
-rw-r--r--xlators/meta/src/meta.c298
-rw-r--r--xlators/meta/src/meta.h186
-rw-r--r--xlators/meta/src/name-file.c39
-rw-r--r--xlators/meta/src/option-file.c41
-rw-r--r--xlators/meta/src/options-dir.c67
-rw-r--r--xlators/meta/src/private-file.c38
-rw-r--r--xlators/meta/src/process_uuid-file.c33
-rw-r--r--xlators/meta/src/profile-file.c38
-rw-r--r--xlators/meta/src/root-dir.c110
-rw-r--r--xlators/meta/src/subvolume-link.c72
-rw-r--r--xlators/meta/src/subvolumes-dir.c70
-rw-r--r--xlators/meta/src/top-link.c36
-rw-r--r--xlators/meta/src/type-file.c39
-rw-r--r--xlators/meta/src/version-file.c34
-rw-r--r--xlators/meta/src/view-dir.c32
-rw-r--r--xlators/meta/src/volfile-file.c76
-rw-r--r--xlators/meta/src/xlator-dir.c135
-rw-r--r--xlators/mgmt/glusterd/src/Makefile.am64
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-bitd-svc.c224
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-bitd-svc.h22
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-bitrot.c1240
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-brick-ops.c4634
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-conn-helper.c4
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-conn-helper.h7
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-conn-mgmt.c223
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-conn-mgmt.h43
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-errno.h33
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-ganesha.c1426
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-geo-rep.c10851
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-geo-rep.h43
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-gfproxyd-svc-helper.c235
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-gfproxyd-svc-helper.h51
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-gfproxyd-svc.c478
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-gfproxyd-svc.h47
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-handler.c10076
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-handshake.c4045
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-hooks.c990
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-hooks.h85
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-locks.c1259
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-locks.h43
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-log-ops.c459
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-mem-types.h101
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-messages.h4981
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-mgmt-handler.c1759
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-mgmt.c4717
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-mgmt.h89
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-mountbroker.c1191
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-mountbroker.h35
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-nfs-svc.c381
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-nfs-svc.h21
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-op-sm.c13159
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-op-sm.h332
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-peer-utils.c1559
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-peer-utils.h67
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-pmap.c881
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-pmap.h63
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-proc-mgmt.c181
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-proc-mgmt.h39
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-quota.c3452
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-quota.h (renamed from xlators/features/ganesha/src/ganesha.h)20
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-quotad-svc.c280
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-quotad-svc.h19
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-rcu.h8
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-rebalance.c2038
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-replace-brick.c1564
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-reset-brick.c376
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-rpc-ops.c4066
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-scrub-svc.c218
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-scrub-svc.h28
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-server-quorum.c699
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-server-quorum.h33
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-shd-svc-helper.c153
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-shd-svc-helper.h42
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-shd-svc.c848
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-shd-svc.h31
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-sm.c2472
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-sm.h258
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-snapd-svc-helper.c66
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-snapd-svc-helper.h21
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-snapd-svc.c728
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-snapd-svc.h26
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-snapshot-utils.c6712
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-snapshot-utils.h153
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-snapshot.c17234
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-statedump.c359
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-statedump.h9
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-store.c8030
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-store.h260
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-svc-helper.c1074
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-svc-helper.h58
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-svc-mgmt.c652
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-svc-mgmt.h104
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-syncop.c3296
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-syncop.h99
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-tierd-svc-helper.c207
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-utils.c21034
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-utils.h820
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-volgen.c9832
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-volgen.h344
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-volume-ops.c5136
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-volume-set.c4888
-rw-r--r--xlators/mgmt/glusterd/src/glusterd.c3616
-rw-r--r--xlators/mgmt/glusterd/src/glusterd.h1759
-rw-r--r--xlators/mount/fuse/src/Makefile.am9
-rw-r--r--xlators/mount/fuse/src/fuse-bridge.c10294
-rw-r--r--xlators/mount/fuse/src/fuse-bridge.h798
-rw-r--r--xlators/mount/fuse/src/fuse-helpers.c1008
-rw-r--r--xlators/mount/fuse/src/fuse-mem-types.h25
-rw-r--r--xlators/mount/fuse/src/fuse-resolve.c1019
-rwxr-xr-xxlators/mount/fuse/utils/mount.glusterfs.in231
-rwxr-xr-xxlators/mount/fuse/utils/mount_glusterfs.in36
-rw-r--r--xlators/nfs/server/src/Makefile.am21
-rw-r--r--xlators/nfs/server/src/acl3.c1590
-rw-r--r--xlators/nfs/server/src/acl3.h18
-rw-r--r--xlators/nfs/server/src/auth-cache.c525
-rw-r--r--xlators/nfs/server/src/auth-cache.h25
-rw-r--r--xlators/nfs/server/src/exports.c1632
-rw-r--r--xlators/nfs/server/src/exports.h69
-rw-r--r--xlators/nfs/server/src/mount3-auth.c682
-rw-r--r--xlators/nfs/server/src/mount3-auth.h28
-rw-r--r--xlators/nfs/server/src/mount3.c6344
-rw-r--r--xlators/nfs/server/src/mount3.h214
-rw-r--r--xlators/nfs/server/src/mount3udp_svc.c344
-rw-r--r--xlators/nfs/server/src/netgroups.c1012
-rw-r--r--xlators/nfs/server/src/netgroups.h31
-rw-r--r--xlators/nfs/server/src/nfs-common.c657
-rw-r--r--xlators/nfs/server/src/nfs-common.h56
-rw-r--r--xlators/nfs/server/src/nfs-fops.c2370
-rw-r--r--xlators/nfs/server/src/nfs-fops.h310
-rw-r--r--xlators/nfs/server/src/nfs-generics.c341
-rw-r--r--xlators/nfs/server/src/nfs-generics.h151
-rw-r--r--xlators/nfs/server/src/nfs-inodes.c773
-rw-r--r--xlators/nfs/server/src/nfs-inodes.h65
-rw-r--r--xlators/nfs/server/src/nfs-mem-types.h70
-rw-r--r--xlators/nfs/server/src/nfs-messages.h1748
-rw-r--r--xlators/nfs/server/src/nfs.c3405
-rw-r--r--xlators/nfs/server/src/nfs.h177
-rw-r--r--xlators/nfs/server/src/nfs3-fh.c221
-rw-r--r--xlators/nfs/server/src/nfs3-fh.h110
-rw-r--r--xlators/nfs/server/src/nfs3-helpers.c5044
-rw-r--r--xlators/nfs/server/src/nfs3-helpers.h280
-rw-r--r--xlators/nfs/server/src/nfs3.c9273
-rw-r--r--xlators/nfs/server/src/nfs3.h387
-rw-r--r--xlators/nfs/server/src/nfsserver.sym12
-rw-r--r--xlators/nfs/server/src/nlm4.c4337
-rw-r--r--xlators/nfs/server/src/nlm4.h131
-rw-r--r--xlators/nfs/server/src/nlmcbk_svc.c176
-rw-r--r--xlators/performance/Makefile.am3
-rw-r--r--xlators/performance/io-cache/src/Makefile.am5
-rw-r--r--xlators/performance/io-cache/src/io-cache-messages.h144
-rw-r--r--xlators/performance/io-cache/src/io-cache.c3112
-rw-r--r--xlators/performance/io-cache/src/io-cache.h405
-rw-r--r--xlators/performance/io-cache/src/ioc-inode.c291
-rw-r--r--xlators/performance/io-cache/src/ioc-mem-types.h24
-rw-r--r--xlators/performance/io-cache/src/page.c1460
-rw-r--r--xlators/performance/io-threads/src/Makefile.am7
-rw-r--r--xlators/performance/io-threads/src/io-threads-messages.h108
-rw-r--r--xlators/performance/io-threads/src/io-threads.c1973
-rw-r--r--xlators/performance/io-threads/src/io-threads.h120
-rw-r--r--xlators/performance/io-threads/src/iot-mem-types.h9
-rw-r--r--xlators/performance/md-cache/src/Makefile.am3
-rw-r--r--xlators/performance/md-cache/src/md-cache-mem-types.h13
-rw-r--r--xlators/performance/md-cache/src/md-cache-messages.h57
-rw-r--r--xlators/performance/md-cache/src/md-cache.c4710
-rw-r--r--xlators/performance/nl-cache/Makefile.am3
-rw-r--r--xlators/performance/nl-cache/src/Makefile.am12
-rw-r--r--xlators/performance/nl-cache/src/nl-cache-helper.c1201
-rw-r--r--xlators/performance/nl-cache/src/nl-cache-mem-types.h27
-rw-r--r--xlators/performance/nl-cache/src/nl-cache-messages.h29
-rw-r--r--xlators/performance/nl-cache/src/nl-cache.c840
-rw-r--r--xlators/performance/nl-cache/src/nl-cache.h175
-rw-r--r--xlators/performance/open-behind/src/Makefile.am5
-rw-r--r--xlators/performance/open-behind/src/open-behind-mem-types.h9
-rw-r--r--xlators/performance/open-behind/src/open-behind-messages.h77
-rw-r--r--xlators/performance/open-behind/src/open-behind.c1622
-rw-r--r--xlators/performance/quick-read/src/Makefile.am7
-rw-r--r--xlators/performance/quick-read/src/quick-read-mem-types.h16
-rw-r--r--xlators/performance/quick-read/src/quick-read-messages.h112
-rw-r--r--xlators/performance/quick-read/src/quick-read.c2138
-rw-r--r--xlators/performance/quick-read/src/quick-read.h88
-rw-r--r--xlators/performance/read-ahead/src/Makefile.am7
-rw-r--r--xlators/performance/read-ahead/src/page.c852
-rw-r--r--xlators/performance/read-ahead/src/read-ahead-mem-types.h17
-rw-r--r--xlators/performance/read-ahead/src/read-ahead-messages.h87
-rw-r--r--xlators/performance/read-ahead/src/read-ahead.c1841
-rw-r--r--xlators/performance/read-ahead/src/read-ahead.h183
-rw-r--r--xlators/performance/readdir-ahead/src/Makefile.am9
-rw-r--r--xlators/performance/readdir-ahead/src/readdir-ahead-mem-types.h12
-rw-r--r--xlators/performance/readdir-ahead/src/readdir-ahead-messages.h97
-rw-r--r--xlators/performance/readdir-ahead/src/readdir-ahead.c1586
-rw-r--r--xlators/performance/readdir-ahead/src/readdir-ahead.h94
-rw-r--r--xlators/performance/symlink-cache/Makefile.am3
-rw-r--r--xlators/performance/symlink-cache/src/Makefile.am15
-rw-r--r--xlators/performance/symlink-cache/src/symlink-cache-messages.h93
-rw-r--r--xlators/performance/symlink-cache/src/symlink-cache.c406
-rw-r--r--xlators/performance/write-behind/src/Makefile.am7
-rw-r--r--xlators/performance/write-behind/src/write-behind-mem-types.h16
-rw-r--r--xlators/performance/write-behind/src/write-behind-messages.h114
-rw-r--r--xlators/performance/write-behind/src/write-behind.c4210
-rw-r--r--xlators/playground/rot-13/Makefile.am (renamed from xlators/cluster/ha/Makefile.am)0
-rw-r--r--xlators/playground/rot-13/src/Makefile.am (renamed from xlators/encryption/rot-13/src/Makefile.am)5
-rw-r--r--xlators/playground/rot-13/src/rot-13.c166
-rw-r--r--xlators/playground/rot-13/src/rot-13.h (renamed from xlators/encryption/rot-13/src/rot-13.h)9
-rw-r--r--xlators/playground/template/src/Makefile.am7
-rw-r--r--xlators/playground/template/src/template.c187
-rw-r--r--xlators/playground/template/src/template.h39
-rw-r--r--xlators/protocol/auth/addr/src/Makefile.am6
-rw-r--r--xlators/protocol/auth/addr/src/addr.c475
-rw-r--r--xlators/protocol/auth/login/src/Makefile.am5
-rw-r--r--xlators/protocol/auth/login/src/login.c323
-rw-r--r--xlators/protocol/client/src/Makefile.am13
-rw-r--r--xlators/protocol/client/src/client-callback.c333
-rw-r--r--xlators/protocol/client/src/client-common.c3589
-rw-r--r--xlators/protocol/client/src/client-common.h630
-rw-r--r--xlators/protocol/client/src/client-handshake.c2655
-rw-r--r--xlators/protocol/client/src/client-helpers.c1034
-rw-r--r--xlators/protocol/client/src/client-lk.c755
-rw-r--r--xlators/protocol/client/src/client-mem-types.h17
-rw-r--r--xlators/protocol/client/src/client-messages.h776
-rw-r--r--xlators/protocol/client/src/client-rpc-fops.c10484
-rw-r--r--xlators/protocol/client/src/client-rpc-fops_v2.c6177
-rw-r--r--xlators/protocol/client/src/client.c4329
-rw-r--r--xlators/protocol/client/src/client.h571
-rw-r--r--xlators/protocol/server/src/Makefile.am22
-rw-r--r--xlators/protocol/server/src/authenticate.c358
-rw-r--r--xlators/protocol/server/src/authenticate.h39
-rw-r--r--xlators/protocol/server/src/server-common.c842
-rw-r--r--xlators/protocol/server/src/server-common.h199
-rw-r--r--xlators/protocol/server/src/server-handshake.c1439
-rw-r--r--xlators/protocol/server/src/server-helpers.c2155
-rw-r--r--xlators/protocol/server/src/server-helpers.h94
-rw-r--r--xlators/protocol/server/src/server-mem-types.h23
-rw-r--r--xlators/protocol/server/src/server-messages.h942
-rw-r--r--xlators/protocol/server/src/server-resolve.c939
-rw-r--r--xlators/protocol/server/src/server-rpc-fops.c9178
-rw-r--r--xlators/protocol/server/src/server-rpc-fops_v2.c6031
-rw-r--r--xlators/protocol/server/src/server.c2795
-rw-r--r--xlators/protocol/server/src/server.h275
-rw-r--r--xlators/storage/Makefile.am4
-rw-r--r--xlators/storage/bd/src/Makefile.am20
-rw-r--r--xlators/storage/bd/src/bd-aio.c528
-rw-r--r--xlators/storage/bd/src/bd-aio.h41
-rw-r--r--xlators/storage/bd/src/bd-helper.c1023
-rw-r--r--xlators/storage/bd/src/bd-mem-types.h27
-rw-r--r--xlators/storage/bd/src/bd.c2452
-rw-r--r--xlators/storage/bd/src/bd.h173
-rw-r--r--xlators/storage/posix/src/Makefile.am20
-rw-r--r--xlators/storage/posix/src/posix-aio.c959
-rw-r--r--xlators/storage/posix/src/posix-aio.h27
-rw-r--r--xlators/storage/posix/src/posix-common.c1524
-rw-r--r--xlators/storage/posix/src/posix-entry-ops.c2496
-rw-r--r--xlators/storage/posix/src/posix-gfid-path.c243
-rw-r--r--xlators/storage/posix/src/posix-gfid-path.h28
-rw-r--r--xlators/storage/posix/src/posix-handle.c1566
-rw-r--r--xlators/storage/posix/src/posix-handle.h432
-rw-r--r--xlators/storage/posix/src/posix-helpers.c4814
-rw-r--r--xlators/storage/posix/src/posix-inode-fd-ops.c6004
-rw-r--r--xlators/storage/posix/src/posix-inode-handle.h118
-rw-r--r--xlators/storage/posix/src/posix-mem-types.h20
-rw-r--r--xlators/storage/posix/src/posix-messages.h951
-rw-r--r--xlators/storage/posix/src/posix-metadata-disk.h31
-rw-r--r--xlators/storage/posix/src/posix-metadata.c916
-rw-r--r--xlators/storage/posix/src/posix-metadata.h71
-rw-r--r--xlators/storage/posix/src/posix.c6708
-rw-r--r--xlators/storage/posix/src/posix.h739
-rw-r--r--xlators/system/posix-acl/src/Makefile.am8
-rw-r--r--xlators/system/posix-acl/src/posix-acl-mem-types.h13
-rw-r--r--xlators/system/posix-acl/src/posix-acl-messages.h28
-rw-r--r--xlators/system/posix-acl/src/posix-acl-xattr.c229
-rw-r--r--xlators/system/posix-acl/src/posix-acl-xattr.h17
-rw-r--r--xlators/system/posix-acl/src/posix-acl.c3306
-rw-r--r--xlators/system/posix-acl/src/posix-acl.h33
-rw-r--r--xlators/xlator.sym1
730 files changed, 368941 insertions, 310356 deletions
diff --git a/xlators/Makefile.am b/xlators/Makefile.am
index 2a03f905b6d..ef20cbb64fa 100644
--- a/xlators/Makefile.am
+++ b/xlators/Makefile.am
@@ -1,4 +1,13 @@
-SUBDIRS = cluster storage protocol performance debug features encryption mount nfs mgmt system \
- playground meta
+if BUILD_GNFS
+ GNFS_DIR = nfs
+endif
+
+DIST_SUBDIRS = cluster storage protocol performance debug features \
+ mount nfs mgmt system playground meta
+
+SUBDIRS = cluster storage protocol performance debug features \
+ mount ${GNFS_DIR} mgmt system playground meta
+
+EXTRA_DIST = xlator.sym
CLEANFILES =
diff --git a/xlators/cluster/Makefile.am b/xlators/cluster/Makefile.am
index 903fbb39f12..8e067d5ab58 100644
--- a/xlators/cluster/Makefile.am
+++ b/xlators/cluster/Makefile.am
@@ -1,3 +1,3 @@
-SUBDIRS = stripe afr dht ec
+SUBDIRS = afr dht ec
CLEANFILES =
diff --git a/xlators/cluster/afr/src/Makefile.am b/xlators/cluster/afr/src/Makefile.am
index ac66bf3bb11..610819b28fc 100644
--- a/xlators/cluster/afr/src/Makefile.am
+++ b/xlators/cluster/afr/src/Makefile.am
@@ -1,4 +1,4 @@
-xlator_LTLIBRARIES = afr.la pump.la
+xlator_LTLIBRARIES = afr.la
xlatordir = $(libdir)/glusterfs/$(PACKAGE_VERSION)/xlator/cluster
afr_common_source = afr-dir-read.c afr-dir-write.c afr-inode-read.c \
@@ -10,22 +10,19 @@ AFR_SELFHEAL_SOURCES = afr-self-heal-common.c afr-self-heal-data.c \
afr-self-heal-entry.c afr-self-heal-metadata.c afr-self-heald.c \
afr-self-heal-name.c
-afr_la_LDFLAGS = -module -avoid-version
+afr_la_LDFLAGS = -module $(GF_XLATOR_DEFAULT_LDFLAGS)
afr_la_SOURCES = $(afr_common_source) $(AFR_SELFHEAL_SOURCES) afr.c
afr_la_LIBADD = $(top_builddir)/libglusterfs/src/libglusterfs.la
-pump_la_LDFLAGS = -module -avoid-version
-pump_la_SOURCES = $(afr_common_source) $(AFR_SELFHEAL_SOURCES) pump.c
-pump_la_LIBADD = $(top_builddir)/libglusterfs/src/libglusterfs.la
-
noinst_HEADERS = afr.h afr-transaction.h afr-inode-write.h afr-inode-read.h \
afr-dir-read.h afr-dir-write.h afr-self-heal.h afr-mem-types.h \
- afr-common.c afr-self-heald.h pump.h \
+ afr-common.c afr-self-heald.h \
$(top_builddir)/xlators/lib/src/libxlator.h afr-messages.h
AM_CPPFLAGS = $(GF_CPPFLAGS) \
-I$(top_srcdir)/libglusterfs/src -I$(top_srcdir)/xlators/lib/src \
- -I$(top_srcdir)/rpc/rpc-lib/src
+ -I$(top_srcdir)/rpc/rpc-lib/src \
+ -I$(top_srcdir)/rpc/xdr/src -I$(top_builddir)/rpc/xdr/src
AM_CFLAGS = -Wall $(GF_CFLAGS)
diff --git a/xlators/cluster/afr/src/afr-common.c b/xlators/cluster/afr/src/afr-common.c
index 31c6eff1fa8..032ab5c8001 100644
--- a/xlators/cluster/afr/src/afr-common.c
+++ b/xlators/cluster/afr/src/afr-common.c
@@ -15,29 +15,20 @@
#include <stdlib.h>
#include <signal.h>
-#ifndef _CONFIG_H
-#define _CONFIG_H
-#include "config.h"
-#endif
-
-#include "glusterfs.h"
+#include <glusterfs/glusterfs.h>
#include "afr.h"
-#include "dict.h"
-#include "xlator.h"
-#include "hashfn.h"
-#include "logging.h"
-#include "stack.h"
-#include "list.h"
-#include "call-stub.h"
-#include "defaults.h"
-#include "common-utils.h"
-#include "compat-errno.h"
-#include "compat.h"
-#include "byte-order.h"
-#include "statedump.h"
-#include "inode.h"
-
-#include "fd.h"
+#include <glusterfs/dict.h>
+#include <glusterfs/hashfn.h>
+#include <glusterfs/list.h>
+#include <glusterfs/call-stub.h>
+#include <glusterfs/defaults.h>
+#include <glusterfs/common-utils.h>
+#include <glusterfs/compat-errno.h>
+#include <glusterfs/compat.h>
+#include <glusterfs/byte-order.h>
+#include <glusterfs/statedump.h>
+#include <glusterfs/events.h>
+#include <glusterfs/upcall-utils.h>
#include "afr-inode-read.h"
#include "afr-inode-write.h"
@@ -48,56 +39,799 @@
#include "afr-self-heald.h"
#include "afr-messages.h"
-call_frame_t *
-afr_copy_frame (call_frame_t *base)
+int32_t
+afr_quorum_errno(afr_private_t *priv)
+{
+ return ENOTCONN;
+}
+
+gf_boolean_t
+afr_is_private_directory(afr_private_t *priv, uuid_t pargfid, const char *name,
+ pid_t pid)
{
- afr_local_t *local = NULL;
- call_frame_t *frame = NULL;
- int op_errno = 0;
+ if (!__is_root_gfid(pargfid)) {
+ return _gf_false;
+ }
- frame = copy_frame (base);
- if (!frame)
- return NULL;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local) {
- AFR_STACK_DESTROY (frame);
- return NULL;
- }
+ if (strcmp(name, GF_REPLICATE_TRASH_DIR) == 0) {
+ /*For backward compatibility /.landfill is private*/
+ return _gf_true;
+ }
+
+ if (pid == GF_CLIENT_PID_GSYNCD) {
+ /*geo-rep needs to create/sync private directory on slave because
+ * it appears in changelog*/
+ return _gf_false;
+ }
- return frame;
+ if (pid == GF_CLIENT_PID_GLFS_HEAL || pid == GF_CLIENT_PID_SELF_HEALD) {
+ if (strcmp(name, priv->anon_inode_name) == 0) {
+ /* anonymous-inode dir is private*/
+ return _gf_true;
+ }
+ } else {
+ if (strncmp(name, AFR_ANON_DIR_PREFIX, strlen(AFR_ANON_DIR_PREFIX)) ==
+ 0) {
+ /* anonymous-inode dir prefix is private for geo-rep to work*/
+ return _gf_true;
+ }
+ }
+
+ return _gf_false;
}
-int
-__afr_inode_ctx_get (xlator_t *this, inode_t *inode, afr_inode_ctx_t **ctx)
+void
+afr_fill_success_replies(afr_local_t *local, afr_private_t *priv,
+ unsigned char *replies)
{
- uint64_t ctx_int = 0;
- int ret = -1;
- afr_inode_ctx_t *tmp_ctx = NULL;
+ int i = 0;
- ret = __inode_ctx_get (inode, this, &ctx_int);
- if (ret) {
- tmp_ctx = GF_CALLOC (1, sizeof (afr_inode_ctx_t),
- gf_afr_mt_inode_ctx_t);
- if (!tmp_ctx)
- goto out;
-
- ctx_int = (long) tmp_ctx;
- ret = __inode_ctx_set (inode, this, &ctx_int);
- if (ret) {
- GF_FREE (tmp_ctx);
- goto out;
- }
- tmp_ctx->spb_choice = -1;
- tmp_ctx->read_subvol = 0;
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->replies[i].valid && local->replies[i].op_ret == 0) {
+ replies[i] = 1;
} else {
- tmp_ctx = (afr_inode_ctx_t *) ctx_int;
+ replies[i] = 0;
}
+ }
+}
- *ctx = tmp_ctx;
- ret = 0;
+int
+afr_fav_child_reset_sink_xattrs(void *opaque);
+
+int
+afr_fav_child_reset_sink_xattrs_cbk(int ret, call_frame_t *frame, void *opaque);
+
+static void
+afr_discover_done(call_frame_t *frame, xlator_t *this);
+
+int
+afr_dom_lock_acquire_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int op_ret, int op_errno, dict_t *xdata)
+{
+ afr_local_t *local = frame->local;
+ afr_private_t *priv = this->private;
+ int i = (long)cookie;
+
+ local->cont.lk.dom_lock_op_ret[i] = op_ret;
+ local->cont.lk.dom_lock_op_errno[i] = op_errno;
+ if (op_ret < 0) {
+ gf_msg(this->name, GF_LOG_ERROR, op_errno, AFR_MSG_LK_HEAL_DOM,
+ "%s: Failed to acquire %s on %s",
+ uuid_utoa(local->fd->inode->gfid), AFR_LK_HEAL_DOM,
+ priv->children[i]->name);
+ } else {
+ local->cont.lk.dom_locked_nodes[i] = 1;
+ }
+
+ syncbarrier_wake(&local->barrier);
+
+ return 0;
+}
+
+int
+afr_dom_lock_acquire(call_frame_t *frame)
+{
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ struct gf_flock flock = {
+ 0,
+ };
+ int i = 0;
+
+ priv = frame->this->private;
+ local = frame->local;
+ local->cont.lk.dom_locked_nodes = GF_CALLOC(
+ priv->child_count, sizeof(*local->cont.lk.locked_nodes),
+ gf_afr_mt_char);
+ if (!local->cont.lk.dom_locked_nodes) {
+ return -ENOMEM;
+ }
+ local->cont.lk.dom_lock_op_ret = GF_CALLOC(
+ priv->child_count, sizeof(*local->cont.lk.dom_lock_op_ret),
+ gf_afr_mt_int32_t);
+ if (!local->cont.lk.dom_lock_op_ret) {
+ return -ENOMEM; /* CALLOC'd members are freed in afr_local_cleanup. */
+ }
+ local->cont.lk.dom_lock_op_errno = GF_CALLOC(
+ priv->child_count, sizeof(*local->cont.lk.dom_lock_op_errno),
+ gf_afr_mt_int32_t);
+ if (!local->cont.lk.dom_lock_op_errno) {
+ return -ENOMEM; /* CALLOC'd members are freed in afr_local_cleanup. */
+ }
+ flock.l_type = F_WRLCK;
+
+ AFR_ONALL(frame, afr_dom_lock_acquire_cbk, finodelk, AFR_LK_HEAL_DOM,
+ local->fd, F_SETLK, &flock, NULL);
+
+ if (!afr_has_quorum(local->cont.lk.dom_locked_nodes, frame->this, NULL))
+ goto blocking_lock;
+
+ /*If any of the bricks returned EAGAIN, we still need blocking locks.*/
+ if (AFR_COUNT(local->cont.lk.dom_locked_nodes, priv->child_count) !=
+ priv->child_count) {
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->cont.lk.dom_lock_op_ret[i] == -1 &&
+ local->cont.lk.dom_lock_op_errno[i] == EAGAIN)
+ goto blocking_lock;
+ }
+ }
+
+ return 0;
+
+blocking_lock:
+ afr_dom_lock_release(frame);
+ AFR_ONALL(frame, afr_dom_lock_acquire_cbk, finodelk, AFR_LK_HEAL_DOM,
+ local->fd, F_SETLKW, &flock, NULL);
+ if (!afr_has_quorum(local->cont.lk.dom_locked_nodes, frame->this, NULL)) {
+ afr_dom_lock_release(frame);
+ return -afr_quorum_errno(priv);
+ }
+
+ return 0;
+}
+
+int
+afr_dom_lock_release_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int op_ret, int op_errno, dict_t *xdata)
+{
+ afr_local_t *local = frame->local;
+ afr_private_t *priv = this->private;
+ int i = (long)cookie;
+
+ if (op_ret < 0) {
+ gf_msg(this->name, GF_LOG_ERROR, op_errno, AFR_MSG_LK_HEAL_DOM,
+ "%s: Failed to release %s on %s", local->loc.path,
+ AFR_LK_HEAL_DOM, priv->children[i]->name);
+ }
+ local->cont.lk.dom_locked_nodes[i] = 0;
+
+ syncbarrier_wake(&local->barrier);
+
+ return 0;
+}
+
+void
+afr_dom_lock_release(call_frame_t *frame)
+{
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ unsigned char *locked_on = NULL;
+ struct gf_flock flock = {
+ 0,
+ };
+
+ local = frame->local;
+ priv = frame->this->private;
+ locked_on = local->cont.lk.dom_locked_nodes;
+ if (AFR_COUNT(locked_on, priv->child_count) == 0)
+ return;
+ flock.l_type = F_UNLCK;
+
+ AFR_ONLIST(locked_on, frame, afr_dom_lock_release_cbk, finodelk,
+ AFR_LK_HEAL_DOM, local->fd, F_SETLK, &flock, NULL);
+
+ return;
+}
+
+static void
+afr_lk_heal_info_cleanup(afr_lk_heal_info_t *info)
+{
+ if (!info)
+ return;
+ if (info->xdata_req)
+ dict_unref(info->xdata_req);
+ if (info->fd)
+ fd_unref(info->fd);
+ GF_FREE(info->locked_nodes);
+ GF_FREE(info->child_up_event_gen);
+ GF_FREE(info->child_down_event_gen);
+ GF_FREE(info);
+}
+
+static int
+afr_add_lock_to_saved_locks(call_frame_t *frame, xlator_t *this)
+{
+ afr_private_t *priv = this->private;
+ afr_local_t *local = frame->local;
+ afr_lk_heal_info_t *info = NULL;
+ afr_fd_ctx_t *fd_ctx = NULL;
+ int ret = -ENOMEM;
+
+ info = GF_CALLOC(sizeof(*info), 1, gf_afr_mt_lk_heal_info_t);
+ if (!info) {
+ goto cleanup;
+ }
+ INIT_LIST_HEAD(&info->pos);
+ info->fd = fd_ref(local->fd);
+ info->cmd = local->cont.lk.cmd;
+ info->pid = frame->root->pid;
+ info->flock = local->cont.lk.user_flock;
+ info->xdata_req = dict_copy_with_ref(local->xdata_req, NULL);
+ if (!info->xdata_req) {
+ goto cleanup;
+ }
+ info->lk_owner = frame->root->lk_owner;
+ info->locked_nodes = GF_MALLOC(
+ sizeof(*info->locked_nodes) * priv->child_count, gf_afr_mt_char);
+ if (!info->locked_nodes) {
+ goto cleanup;
+ }
+ memcpy(info->locked_nodes, local->cont.lk.locked_nodes,
+ sizeof(*info->locked_nodes) * priv->child_count);
+ info->child_up_event_gen = GF_CALLOC(sizeof(*info->child_up_event_gen),
+ priv->child_count, gf_afr_mt_int32_t);
+ if (!info->child_up_event_gen) {
+ goto cleanup;
+ }
+ info->child_down_event_gen = GF_CALLOC(sizeof(*info->child_down_event_gen),
+ priv->child_count,
+ gf_afr_mt_int32_t);
+ if (!info->child_down_event_gen) {
+ goto cleanup;
+ }
+
+ LOCK(&local->fd->lock);
+ {
+ fd_ctx = __afr_fd_ctx_get(local->fd, this);
+ if (fd_ctx)
+ fd_ctx->lk_heal_info = info;
+ }
+ UNLOCK(&local->fd->lock);
+ if (!fd_ctx) {
+ goto cleanup;
+ }
+
+ LOCK(&priv->lock);
+ {
+ list_add_tail(&info->pos, &priv->saved_locks);
+ }
+ UNLOCK(&priv->lock);
+
+ return 0;
+cleanup:
+ gf_msg(this->name, GF_LOG_ERROR, -ret, AFR_MSG_LK_HEAL_DOM,
+ "%s: Failed to add lock to healq",
+ uuid_utoa(local->fd->inode->gfid));
+ if (info) {
+ afr_lk_heal_info_cleanup(info);
+ if (fd_ctx) {
+ LOCK(&local->fd->lock);
+ {
+ fd_ctx->lk_heal_info = NULL;
+ }
+ UNLOCK(&local->fd->lock);
+ }
+ }
+ return ret;
+}
+
+static int
+afr_remove_lock_from_saved_locks(afr_local_t *local, xlator_t *this)
+{
+ afr_private_t *priv = this->private;
+ struct gf_flock flock = local->cont.lk.user_flock;
+ afr_lk_heal_info_t *info = NULL;
+ afr_fd_ctx_t *fd_ctx = NULL;
+ int ret = -EINVAL;
+
+ fd_ctx = afr_fd_ctx_get(local->fd, this);
+ if (!fd_ctx || !fd_ctx->lk_heal_info) {
+ goto out;
+ }
+
+ info = fd_ctx->lk_heal_info;
+ if ((info->flock.l_start != flock.l_start) ||
+ (info->flock.l_whence != flock.l_whence) ||
+ (info->flock.l_len != flock.l_len)) {
+ /*TODO: Compare lkowners too.*/
+ goto out;
+ }
+
+ LOCK(&priv->lock);
+ {
+ list_del(&fd_ctx->lk_heal_info->pos);
+ }
+ UNLOCK(&priv->lock);
+
+ afr_lk_heal_info_cleanup(info);
+ fd_ctx->lk_heal_info = NULL;
+ ret = 0;
out:
- return ret;
+ if (ret)
+ gf_msg(this->name, GF_LOG_ERROR, -ret, AFR_MSG_LK_HEAL_DOM,
+ "%s: Failed to remove lock from healq",
+ uuid_utoa(local->fd->inode->gfid));
+ return ret;
+}
+
+int
+afr_lock_heal_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, struct gf_flock *lock,
+ dict_t *xdata)
+{
+ afr_local_t *local = frame->local;
+ int i = (long)cookie;
+
+ local->replies[i].valid = 1;
+ local->replies[i].op_ret = op_ret;
+ local->replies[i].op_errno = op_errno;
+ if (op_ret != 0) {
+ gf_msg(this->name, GF_LOG_ERROR, op_errno, AFR_MSG_LK_HEAL_DOM,
+ "Failed to heal lock on child %d for %s", i,
+ uuid_utoa(local->fd->inode->gfid));
+ }
+ syncbarrier_wake(&local->barrier);
+ return 0;
+}
+
+int
+afr_getlk_cbk(call_frame_t *frame, void *cookie, xlator_t *this, int32_t op_ret,
+ int32_t op_errno, struct gf_flock *lock, dict_t *xdata)
+{
+ afr_local_t *local = frame->local;
+ int i = (long)cookie;
+
+ local->replies[i].valid = 1;
+ local->replies[i].op_ret = op_ret;
+ local->replies[i].op_errno = op_errno;
+ if (op_ret != 0) {
+ gf_msg(this->name, GF_LOG_ERROR, op_errno, AFR_MSG_LK_HEAL_DOM,
+ "Failed getlk for %s", uuid_utoa(local->fd->inode->gfid));
+ } else {
+ local->cont.lk.getlk_rsp[i] = *lock;
+ }
+
+ syncbarrier_wake(&local->barrier);
+ return 0;
}
+
+static gf_boolean_t
+afr_does_lk_owner_match(call_frame_t *frame, afr_private_t *priv,
+ afr_lk_heal_info_t *info)
+{
+ int i = 0;
+ afr_local_t *local = frame->local;
+ struct gf_flock flock = {
+ 0,
+ };
+ gf_boolean_t ret = _gf_true;
+ char *wind_on = alloca0(priv->child_count);
+ unsigned char *success_replies = alloca0(priv->child_count);
+ local->cont.lk.getlk_rsp = GF_CALLOC(sizeof(*local->cont.lk.getlk_rsp),
+ priv->child_count, gf_afr_mt_gf_lock);
+
+ flock = info->flock;
+ for (i = 0; i < priv->child_count; i++) {
+ if (info->locked_nodes[i])
+ wind_on[i] = 1;
+ }
+
+ AFR_ONLIST(wind_on, frame, afr_getlk_cbk, lk, info->fd, F_GETLK, &flock,
+ info->xdata_req);
+
+ afr_fill_success_replies(local, priv, success_replies);
+ if (AFR_COUNT(success_replies, priv->child_count) == 0) {
+ ret = _gf_false;
+ goto out;
+ }
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->replies[i].valid || local->replies[i].op_ret != 0)
+ continue;
+ if (local->cont.lk.getlk_rsp[i].l_type == F_UNLCK)
+ continue;
+ /*TODO: Do we really need to compare lkowner if F_UNLCK is true?*/
+ if (!is_same_lkowner(&local->cont.lk.getlk_rsp[i].l_owner,
+ &info->lk_owner)) {
+ ret = _gf_false;
+ break;
+ }
+ }
+out:
+ afr_local_replies_wipe(local, priv);
+ GF_FREE(local->cont.lk.getlk_rsp);
+ local->cont.lk.getlk_rsp = NULL;
+ return ret;
+}
+
+static void
+afr_mark_fd_bad(fd_t *fd, xlator_t *this)
+{
+ afr_fd_ctx_t *fd_ctx = NULL;
+
+ if (!fd)
+ return;
+ LOCK(&fd->lock);
+ {
+ fd_ctx = __afr_fd_ctx_get(fd, this);
+ if (fd_ctx) {
+ fd_ctx->is_fd_bad = _gf_true;
+ fd_ctx->lk_heal_info = NULL;
+ }
+ }
+ UNLOCK(&fd->lock);
+}
+
+static void
+afr_add_lock_to_lkhealq(afr_private_t *priv, afr_lk_heal_info_t *info)
+{
+ LOCK(&priv->lock);
+ {
+ list_del(&info->pos);
+ list_add_tail(&info->pos, &priv->lk_healq);
+ }
+ UNLOCK(&priv->lock);
+}
+
+static void
+afr_lock_heal_do(call_frame_t *frame, afr_private_t *priv,
+ afr_lk_heal_info_t *info)
+{
+ int i = 0;
+ int op_errno = 0;
+ int32_t *current_event_gen = NULL;
+ afr_local_t *local = frame->local;
+ xlator_t *this = frame->this;
+ char *wind_on = alloca0(priv->child_count);
+ gf_boolean_t retry = _gf_true;
+
+ frame->root->pid = info->pid;
+ lk_owner_copy(&frame->root->lk_owner, &info->lk_owner);
+
+ op_errno = -afr_dom_lock_acquire(frame);
+ if ((op_errno != 0)) {
+ goto release;
+ }
+
+ if (!afr_does_lk_owner_match(frame, priv, info)) {
+ gf_msg(this->name, GF_LOG_WARNING, 0, AFR_MSG_LK_HEAL_DOM,
+ "Ignoring lock heal for %s since lk-onwers mismatch. "
+ "Lock possibly pre-empted by another client.",
+ uuid_utoa(info->fd->inode->gfid));
+ goto release;
+ }
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (info->locked_nodes[i])
+ continue;
+ wind_on[i] = 1;
+ }
+
+ current_event_gen = alloca(priv->child_count);
+ memcpy(current_event_gen, info->child_up_event_gen,
+ priv->child_count * sizeof *current_event_gen);
+ AFR_ONLIST(wind_on, frame, afr_lock_heal_cbk, lk, info->fd, info->cmd,
+ &info->flock, info->xdata_req);
+
+ LOCK(&priv->lock);
+ {
+ for (i = 0; i < priv->child_count; i++) {
+ if (!wind_on[i])
+ continue;
+ if ((!local->replies[i].valid) || (local->replies[i].op_ret != 0)) {
+ continue;
+ }
+
+ if ((current_event_gen[i] == info->child_up_event_gen[i]) &&
+ (current_event_gen[i] > info->child_down_event_gen[i])) {
+ info->locked_nodes[i] = 1;
+ retry = _gf_false;
+ list_del_init(&info->pos);
+ list_add_tail(&info->pos, &priv->saved_locks);
+ } else {
+ /*We received subsequent child up/down events while heal was in
+ * progress; don't mark child as healed. Attempt again on the
+ * new child up*/
+ gf_msg(this->name, GF_LOG_ERROR, 0, AFR_MSG_LK_HEAL_DOM,
+ "Event gen mismatch: skipped healing lock on child %d "
+ "for %s.",
+ i, uuid_utoa(info->fd->inode->gfid));
+ }
+ }
+ }
+ UNLOCK(&priv->lock);
+
+release:
+ afr_dom_lock_release(frame);
+ if (retry)
+ afr_add_lock_to_lkhealq(priv, info);
+ return;
+}
+
+static int
+afr_lock_heal_done(int ret, call_frame_t *frame, void *opaque)
+{
+ STACK_DESTROY(frame->root);
+ return 0;
+}
+
+static int
+afr_lock_heal(void *opaque)
+{
+ call_frame_t *frame = (call_frame_t *)opaque;
+ call_frame_t *iter_frame = NULL;
+ xlator_t *this = frame->this;
+ afr_private_t *priv = this->private;
+ afr_lk_heal_info_t *info = NULL;
+ afr_lk_heal_info_t *tmp = NULL;
+ struct list_head healq = {
+ 0,
+ };
+ int ret = 0;
+
+ iter_frame = afr_copy_frame(frame);
+ if (!iter_frame) {
+ return ENOMEM;
+ }
+
+ INIT_LIST_HEAD(&healq);
+ LOCK(&priv->lock);
+ {
+ list_splice_init(&priv->lk_healq, &healq);
+ }
+ UNLOCK(&priv->lock);
+
+ list_for_each_entry_safe(info, tmp, &healq, pos)
+ {
+ GF_ASSERT((AFR_COUNT(info->locked_nodes, priv->child_count) <
+ priv->child_count));
+ ((afr_local_t *)(iter_frame->local))->fd = fd_ref(info->fd);
+ afr_lock_heal_do(iter_frame, priv, info);
+ AFR_STACK_RESET(iter_frame);
+ if (iter_frame->local == NULL) {
+ ret = ENOTCONN;
+ gf_msg(frame->this->name, GF_LOG_ERROR, ENOTCONN,
+ AFR_MSG_LK_HEAL_DOM,
+ "Aborting processing of lk_healq."
+ "Healing will be reattempted on next child up for locks "
+ "that are still in quorum.");
+ LOCK(&priv->lock);
+ {
+ list_add_tail(&healq, &priv->lk_healq);
+ }
+ UNLOCK(&priv->lock);
+ break;
+ }
+ }
+
+ AFR_STACK_DESTROY(iter_frame);
+ return ret;
+}
+
+static int
+__afr_lock_heal_synctask(xlator_t *this, afr_private_t *priv, int child)
+{
+ int ret = 0;
+ call_frame_t *frame = NULL;
+ afr_lk_heal_info_t *info = NULL;
+ afr_lk_heal_info_t *tmp = NULL;
+
+ if (priv->shd.iamshd)
+ return 0;
+
+ list_for_each_entry_safe(info, tmp, &priv->saved_locks, pos)
+ {
+ info->child_up_event_gen[child] = priv->event_generation;
+ list_del_init(&info->pos);
+ list_add_tail(&info->pos, &priv->lk_healq);
+ }
+
+ frame = create_frame(this, this->ctx->pool);
+ if (!frame)
+ return -1;
+
+ ret = synctask_new(this->ctx->env, afr_lock_heal, afr_lock_heal_done, frame,
+ frame);
+ if (ret)
+ gf_msg(this->name, GF_LOG_ERROR, ENOMEM, AFR_MSG_LK_HEAL_DOM,
+ "Failed to launch lock heal synctask");
+
+ return ret;
+}
+
+static int
+__afr_mark_pending_lk_heal(xlator_t *this, afr_private_t *priv, int child)
+{
+ afr_lk_heal_info_t *info = NULL;
+ afr_lk_heal_info_t *tmp = NULL;
+
+ if (priv->shd.iamshd)
+ return 0;
+ list_for_each_entry_safe(info, tmp, &priv->saved_locks, pos)
+ {
+ info->child_down_event_gen[child] = priv->event_generation;
+ if (info->locked_nodes[child] == 1)
+ info->locked_nodes[child] = 0;
+ if (!afr_has_quorum(info->locked_nodes, this, NULL)) {
+ /* Since the lock was lost on quorum no. of nodes, we should
+ * not attempt to heal it anymore. Some other client could have
+ * acquired the lock, modified data and released it and this
+ * client wouldn't know about it if we heal it.*/
+ afr_mark_fd_bad(info->fd, this);
+ list_del(&info->pos);
+ afr_lk_heal_info_cleanup(info);
+ /* We're not winding an unlock on the node where the lock is still
+ * present because when fencing logic switches over to the new
+ * client (since we marked the fd bad), it should preempt any
+ * existing lock. */
+ }
+ }
+ return 0;
+}
+
+gf_boolean_t
+afr_is_consistent_io_possible(afr_local_t *local, afr_private_t *priv,
+ int32_t *op_errno)
+{
+ if (priv->consistent_io && local->call_count != priv->child_count) {
+ gf_msg(THIS->name, GF_LOG_INFO, 0, AFR_MSG_SUBVOLS_DOWN,
+ "All subvolumes are not up");
+ if (op_errno)
+ *op_errno = ENOTCONN;
+ return _gf_false;
+ }
+ return _gf_true;
+}
+
+gf_boolean_t
+afr_is_lock_mode_mandatory(dict_t *xdata)
+{
+ int ret = 0;
+ uint32_t lk_mode = GF_LK_ADVISORY;
+
+ ret = dict_get_uint32(xdata, GF_LOCK_MODE, &lk_mode);
+ if (!ret && lk_mode == GF_LK_MANDATORY)
+ return _gf_true;
+
+ return _gf_false;
+}
+
+call_frame_t *
+afr_copy_frame(call_frame_t *base)
+{
+ afr_local_t *local = NULL;
+ call_frame_t *frame = NULL;
+ int op_errno = 0;
+
+ frame = copy_frame(base);
+ if (!frame)
+ return NULL;
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local) {
+ AFR_STACK_DESTROY(frame);
+ return NULL;
+ }
+
+ return frame;
+}
+
+/* Check if an entry or inode could be undergoing a transaction. */
+gf_boolean_t
+afr_is_possibly_under_txn(afr_transaction_type type, afr_local_t *local,
+ xlator_t *this)
+{
+ int i = 0;
+ int tmp = 0;
+ afr_private_t *priv = NULL;
+ GF_UNUSED char *key = NULL;
+ int keylen = 0;
+
+ priv = this->private;
+
+ if (type == AFR_ENTRY_TRANSACTION) {
+ key = GLUSTERFS_PARENT_ENTRYLK;
+ keylen = SLEN(GLUSTERFS_PARENT_ENTRYLK);
+ } else if (type == AFR_DATA_TRANSACTION) {
+ /*FIXME: Use GLUSTERFS_INODELK_DOM_COUNT etc. once
+ * pl_inodelk_xattr_fill supports separate keys for different
+ * domains.*/
+ key = GLUSTERFS_INODELK_COUNT;
+ keylen = SLEN(GLUSTERFS_INODELK_COUNT);
+ }
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->replies[i].xdata)
+ continue;
+ if (dict_get_int32n(local->replies[i].xdata, key, keylen, &tmp) == 0)
+ if (tmp)
+ return _gf_true;
+ }
+
+ return _gf_false;
+}
+
+static void
+afr_inode_ctx_destroy(afr_inode_ctx_t *ctx)
+{
+ int i = 0;
+
+ if (!ctx)
+ return;
+
+ for (i = 0; i < AFR_NUM_CHANGE_LOGS; i++) {
+ GF_FREE(ctx->pre_op_done[i]);
+ }
+
+ GF_FREE(ctx);
+}
+
+int
+__afr_inode_ctx_get(xlator_t *this, inode_t *inode, afr_inode_ctx_t **ctx)
+{
+ uint64_t ctx_int = 0;
+ int ret = -1;
+ int i = -1;
+ int num_locks = -1;
+ afr_inode_ctx_t *ictx = NULL;
+ afr_lock_t *lock = NULL;
+ afr_private_t *priv = this->private;
+
+ ret = __inode_ctx_get(inode, this, &ctx_int);
+ if (ret == 0) {
+ *ctx = (afr_inode_ctx_t *)(uintptr_t)ctx_int;
+ return 0;
+ }
+
+ ictx = GF_CALLOC(1, sizeof(afr_inode_ctx_t), gf_afr_mt_inode_ctx_t);
+ if (!ictx)
+ goto out;
+
+ for (i = 0; i < AFR_NUM_CHANGE_LOGS; i++) {
+ ictx->pre_op_done[i] = GF_CALLOC(sizeof *ictx->pre_op_done[i],
+ priv->child_count, gf_afr_mt_int32_t);
+ if (!ictx->pre_op_done[i]) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ }
+
+ num_locks = sizeof(ictx->lock) / sizeof(afr_lock_t);
+ for (i = 0; i < num_locks; i++) {
+ lock = &ictx->lock[i];
+ INIT_LIST_HEAD(&lock->post_op);
+ INIT_LIST_HEAD(&lock->frozen);
+ INIT_LIST_HEAD(&lock->waiting);
+ INIT_LIST_HEAD(&lock->owners);
+ }
+
+ ctx_int = (uint64_t)(uintptr_t)ictx;
+ ret = __inode_ctx_set(inode, this, &ctx_int);
+ if (ret) {
+ goto out;
+ }
+
+ ictx->spb_choice = -1;
+ ictx->read_subvol = 0;
+ ictx->write_subvol = 0;
+ ictx->lock_count = 0;
+ ret = 0;
+ *ctx = ictx;
+out:
+ if (ret) {
+ afr_inode_ctx_destroy(ictx);
+ }
+ return ret;
+}
+
/*
* INODE CTX 64-bit VALUE FORMAT FOR SMALL (<= 16) SUBVOL COUNTS:
*
@@ -129,1535 +863,2258 @@ out:
*/
int
-__afr_inode_read_subvol_get_small (inode_t *inode, xlator_t *this,
- unsigned char *data, unsigned char *metadata,
- int *event_p)
-{
- afr_private_t *priv = NULL;
- int ret = -1;
- uint16_t datamap = 0;
- uint16_t metadatamap = 0;
- uint32_t event = 0;
- uint64_t val = 0;
- int i = 0;
- afr_inode_ctx_t *ctx = NULL;
+__afr_set_in_flight_sb_status(xlator_t *this, afr_local_t *local,
+ inode_t *inode)
+{
+ int i = 0;
+ int txn_type = 0;
+ int count = 0;
+ int index = -1;
+ uint16_t datamap_old = 0;
+ uint16_t metadatamap_old = 0;
+ uint16_t datamap = 0;
+ uint16_t metadatamap = 0;
+ uint16_t tmp_map = 0;
+ uint16_t mask = 0;
+ uint32_t event = 0;
+ uint64_t val = 0;
+ afr_private_t *priv = NULL;
+
+ priv = this->private;
+ txn_type = local->transaction.type;
+
+ if (txn_type == AFR_DATA_TRANSACTION)
+ val = local->inode_ctx->write_subvol;
+ else
+ val = local->inode_ctx->read_subvol;
+
+ metadatamap_old = metadatamap = (val & 0x000000000000ffff);
+ datamap_old = datamap = (val & 0x00000000ffff0000) >> 16;
+ event = (val & 0xffffffff00000000) >> 32;
+
+ if (txn_type == AFR_DATA_TRANSACTION)
+ tmp_map = datamap;
+ else if (txn_type == AFR_METADATA_TRANSACTION)
+ tmp_map = metadatamap;
+
+ count = gf_bits_count(tmp_map);
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->transaction.failed_subvols[i])
+ continue;
+
+ mask = 1 << i;
+ if (txn_type == AFR_METADATA_TRANSACTION)
+ metadatamap &= ~mask;
+ else if (txn_type == AFR_DATA_TRANSACTION)
+ datamap &= ~mask;
+ }
+
+ switch (txn_type) {
+ case AFR_METADATA_TRANSACTION:
+ if ((metadatamap_old != 0) && (metadatamap == 0) && (count == 1)) {
+ index = gf_bits_index(tmp_map);
+ local->transaction.in_flight_sb_errno = local->replies[index]
+ .op_errno;
+ local->transaction.in_flight_sb = _gf_true;
+ metadatamap |= (1 << index);
+ }
+ if (metadatamap_old != metadatamap) {
+ __afr_inode_need_refresh_set(inode, this);
+ }
+ break;
+
+ case AFR_DATA_TRANSACTION:
+ if ((datamap_old != 0) && (datamap == 0) && (count == 1)) {
+ index = gf_bits_index(tmp_map);
+ local->transaction.in_flight_sb_errno = local->replies[index]
+ .op_errno;
+ local->transaction.in_flight_sb = _gf_true;
+ datamap |= (1 << index);
+ }
+ if (datamap_old != datamap)
+ __afr_inode_need_refresh_set(inode, this);
+ break;
- priv = this->private;
+ default:
+ break;
+ }
- ret = __afr_inode_ctx_get (this, inode, &ctx);
- if (ret < 0)
- return ret;
+ val = ((uint64_t)metadatamap) | (((uint64_t)datamap) << 16) |
+ (((uint64_t)event) << 32);
- val = ctx->read_subvol;
+ if (txn_type == AFR_DATA_TRANSACTION)
+ local->inode_ctx->write_subvol = val;
+ local->inode_ctx->read_subvol = val;
- metadatamap = (val & 0x000000000000ffff);
- datamap = (val & 0x00000000ffff0000) >> 16;
- event = (val & 0xffffffff00000000) >> 32;
+ return 0;
+}
- for (i = 0; i < priv->child_count; i++) {
- if (metadata)
- metadata[i] = (metadatamap >> i) & 1;
- if (data)
- data[i] = (datamap >> i) & 1;
- }
+gf_boolean_t
+afr_is_symmetric_error(call_frame_t *frame, xlator_t *this)
+{
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int op_errno = 0;
+ int i_errno = 0;
+ gf_boolean_t matching_errors = _gf_true;
+ int i = 0;
- if (event_p)
- *event_p = event;
- return ret;
-}
+ priv = this->private;
+ local = frame->local;
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->replies[i].valid)
+ continue;
+ if (local->replies[i].op_ret != -1) {
+ /* Operation succeeded on at least one subvol,
+ so it is not a failed-everywhere situation.
+ */
+ matching_errors = _gf_false;
+ break;
+ }
+ i_errno = local->replies[i].op_errno;
+
+ if (i_errno == ENOTCONN) {
+ /* ENOTCONN is not a symmetric error. We do not
+ know if the operation was performed on the
+ backend or not.
+ */
+ matching_errors = _gf_false;
+ break;
+ }
+
+ if (!op_errno) {
+ op_errno = i_errno;
+ } else if (op_errno != i_errno) {
+ /* Mismatching op_errno's */
+ matching_errors = _gf_false;
+ break;
+ }
+ }
+ return matching_errors;
+}
int
-__afr_inode_read_subvol_set_small (inode_t *inode, xlator_t *this,
- unsigned char *data, unsigned char *metadata,
- int event)
+afr_set_in_flight_sb_status(xlator_t *this, call_frame_t *frame, inode_t *inode)
{
- afr_private_t *priv = NULL;
- uint16_t datamap = 0;
- uint16_t metadatamap = 0;
- uint64_t val = 0;
- int i = 0;
- int ret = -1;
- afr_inode_ctx_t *ctx = NULL;
+ int ret = -1;
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
- priv = this->private;
+ priv = this->private;
+ local = frame->local;
- ret = __afr_inode_ctx_get (this, inode, &ctx);
- if (ret)
- goto out;
+ /* If this transaction saw no failures, then exit. */
+ if (AFR_COUNT(local->transaction.failed_subvols, priv->child_count) == 0)
+ return 0;
- for (i = 0; i < priv->child_count; i++) {
- if (data[i])
- datamap |= (1 << i);
- if (metadata[i])
- metadatamap |= (1 << i);
- }
+ if (afr_is_symmetric_error(frame, this))
+ return 0;
- val = ((uint64_t) metadatamap) |
- (((uint64_t) datamap) << 16) |
- (((uint64_t) event) << 32);
+ LOCK(&inode->lock);
+ {
+ ret = __afr_set_in_flight_sb_status(this, local, inode);
+ }
+ UNLOCK(&inode->lock);
- ctx->read_subvol = val;
+ return ret;
+}
- ret = 0;
-out:
+int
+__afr_inode_read_subvol_get_small(inode_t *inode, xlator_t *this,
+ unsigned char *data, unsigned char *metadata,
+ int *event_p)
+{
+ afr_private_t *priv = NULL;
+ int ret = -1;
+ uint16_t datamap = 0;
+ uint16_t metadatamap = 0;
+ uint32_t event = 0;
+ uint64_t val = 0;
+ int i = 0;
+ afr_inode_ctx_t *ctx = NULL;
+
+ priv = this->private;
+
+ ret = __afr_inode_ctx_get(this, inode, &ctx);
+ if (ret < 0)
return ret;
+
+ val = ctx->read_subvol;
+
+ metadatamap = (val & 0x000000000000ffff);
+ datamap = (val & 0x00000000ffff0000) >> 16;
+ event = (val & 0xffffffff00000000) >> 32;
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (metadata)
+ metadata[i] = (metadatamap >> i) & 1;
+ if (data)
+ data[i] = (datamap >> i) & 1;
+ }
+
+ if (event_p)
+ *event_p = event;
+ return ret;
}
int
-__afr_inode_read_subvol_reset_small (inode_t *inode, xlator_t *this)
+__afr_inode_read_subvol_set_small(inode_t *inode, xlator_t *this,
+ unsigned char *data, unsigned char *metadata,
+ int event)
{
- int ret = -1;
- uint16_t datamap = 0;
- uint16_t metadatamap = 0;
- uint32_t event = 0;
- uint64_t val = 0;
- afr_inode_ctx_t *ctx = NULL;
+ afr_private_t *priv = NULL;
+ uint16_t datamap = 0;
+ uint16_t metadatamap = 0;
+ uint64_t val = 0;
+ int i = 0;
+ int ret = -1;
+ afr_inode_ctx_t *ctx = NULL;
- ret = __afr_inode_ctx_get (this, inode, &ctx);
- if (ret)
- return ret;
+ priv = this->private;
- val = ctx->read_subvol;
+ ret = __afr_inode_ctx_get(this, inode, &ctx);
+ if (ret)
+ goto out;
- metadatamap = (val & 0x000000000000ffff) >> 0;
- datamap = (val & 0x00000000ffff0000) >> 16;
- event = 0;
+ for (i = 0; i < priv->child_count; i++) {
+ if (data[i])
+ datamap |= (1 << i);
+ if (metadata[i])
+ metadatamap |= (1 << i);
+ }
- val = ((uint64_t) metadatamap) |
- (((uint64_t) datamap) << 16) |
- (((uint64_t) event) << 32);
+ val = ((uint64_t)metadatamap) | (((uint64_t)datamap) << 16) |
+ (((uint64_t)event) << 32);
- ctx->read_subvol = val;
+ ctx->read_subvol = val;
- return ret;
+ ret = 0;
+out:
+ return ret;
}
-
int
-__afr_inode_read_subvol_get (inode_t *inode, xlator_t *this,
- unsigned char *data, unsigned char *metadata,
- int *event_p)
+__afr_inode_read_subvol_get(inode_t *inode, xlator_t *this, unsigned char *data,
+ unsigned char *metadata, int *event_p)
{
- afr_private_t *priv = NULL;
- int ret = -1;
+ afr_private_t *priv = NULL;
+ int ret = -1;
- priv = this->private;
+ priv = this->private;
- if (priv->child_count <= 16)
- ret = __afr_inode_read_subvol_get_small (inode, this, data,
- metadata, event_p);
- else
- /* TBD: allocate structure with array and read from it */
- ret = -1;
+ if (priv->child_count <= 16)
+ ret = __afr_inode_read_subvol_get_small(inode, this, data, metadata,
+ event_p);
+ else
+ /* TBD: allocate structure with array and read from it */
+ ret = -1;
- return ret;
+ return ret;
}
int
-__afr_inode_split_brain_choice_get (inode_t *inode, xlator_t *this,
- int *spb_choice)
+__afr_inode_split_brain_choice_get(inode_t *inode, xlator_t *this,
+ int *spb_choice)
{
- afr_inode_ctx_t *ctx = NULL;
- int ret = -1;
+ afr_inode_ctx_t *ctx = NULL;
+ int ret = -1;
- ret = __afr_inode_ctx_get (this, inode, &ctx);
- if (ret < 0)
- return ret;
+ ret = __afr_inode_ctx_get(this, inode, &ctx);
+ if (ret < 0)
+ return ret;
- *spb_choice = ctx->spb_choice;
- return 0;
+ *spb_choice = ctx->spb_choice;
+ return 0;
}
int
-__afr_inode_read_subvol_set (inode_t *inode, xlator_t *this, unsigned char *data,
- unsigned char *metadata, int event)
+__afr_inode_read_subvol_set(inode_t *inode, xlator_t *this, unsigned char *data,
+ unsigned char *metadata, int event)
{
- afr_private_t *priv = NULL;
- int ret = -1;
+ afr_private_t *priv = NULL;
+ int ret = -1;
- priv = this->private;
+ priv = this->private;
- if (priv->child_count <= 16)
- ret = __afr_inode_read_subvol_set_small (inode, this, data,
- metadata, event);
- else
- ret = -1;
+ if (priv->child_count <= 16)
+ ret = __afr_inode_read_subvol_set_small(inode, this, data, metadata,
+ event);
+ else
+ ret = -1;
- return ret;
+ return ret;
}
int
-__afr_inode_split_brain_choice_set (inode_t *inode, xlator_t *this,
- int spb_choice)
+__afr_inode_split_brain_choice_set(inode_t *inode, xlator_t *this,
+ int spb_choice)
{
- afr_inode_ctx_t *ctx = NULL;
- int ret = -1;
+ afr_inode_ctx_t *ctx = NULL;
+ int ret = -1;
- ret = __afr_inode_ctx_get (this, inode, &ctx);
- if (ret)
- goto out;
+ ret = __afr_inode_ctx_get(this, inode, &ctx);
+ if (ret)
+ goto out;
- ctx->spb_choice = spb_choice;
+ ctx->spb_choice = spb_choice;
- ret = 0;
+ ret = 0;
out:
- return ret;
+ return ret;
}
int
-__afr_inode_read_subvol_reset (inode_t *inode, xlator_t *this)
+afr_inode_read_subvol_get(inode_t *inode, xlator_t *this, unsigned char *data,
+ unsigned char *metadata, int *event_p)
{
- afr_private_t *priv = NULL;
- int ret = -1;
+ int ret = -1;
- priv = this->private;
+ GF_VALIDATE_OR_GOTO(this->name, inode, out);
- if (priv->child_count <= 16)
- ret = __afr_inode_read_subvol_reset_small (inode, this);
- else
- ret = -1;
-
- return ret;
+ LOCK(&inode->lock);
+ {
+ ret = __afr_inode_read_subvol_get(inode, this, data, metadata, event_p);
+ }
+ UNLOCK(&inode->lock);
+out:
+ return ret;
}
-
int
-afr_inode_read_subvol_get (inode_t *inode, xlator_t *this, unsigned char *data,
- unsigned char *metadata, int *event_p)
+afr_inode_get_readable(call_frame_t *frame, inode_t *inode, xlator_t *this,
+ unsigned char *readable, int *event_p, int type)
{
- int ret = -1;
+ afr_private_t *priv = this->private;
+ afr_local_t *local = frame->local;
+ unsigned char *data = alloca0(priv->child_count);
+ unsigned char *metadata = alloca0(priv->child_count);
+ int data_count = 0;
+ int metadata_count = 0;
+ int event_generation = 0;
+ int ret = 0;
+
+ ret = afr_inode_read_subvol_get(inode, this, data, metadata,
+ &event_generation);
+ if (ret == -1)
+ return -EIO;
+
+ data_count = AFR_COUNT(data, priv->child_count);
+ metadata_count = AFR_COUNT(metadata, priv->child_count);
+
+ if (inode->ia_type == IA_IFDIR) {
+ /* For directories, allow even if it is in data split-brain. */
+ if (type == AFR_METADATA_TRANSACTION || local->op == GF_FOP_STAT ||
+ local->op == GF_FOP_FSTAT) {
+ if (!metadata_count)
+ return -EIO;
+ }
+ } else {
+ /* For files, abort in case of data/metadata split-brain. */
+ if (!data_count || !metadata_count) {
+ return -EIO;
+ }
+ }
+
+ if (type == AFR_METADATA_TRANSACTION && readable)
+ memcpy(readable, metadata, priv->child_count * sizeof *metadata);
+ if (type == AFR_DATA_TRANSACTION && readable) {
+ if (!data_count)
+ memcpy(readable, local->child_up,
+ priv->child_count * sizeof *readable);
+ else
+ memcpy(readable, data, priv->child_count * sizeof *data);
+ }
+ if (event_p)
+ *event_p = event_generation;
+ return 0;
+}
- GF_VALIDATE_OR_GOTO (this->name, inode, out);
+static int
+afr_inode_split_brain_choice_get(inode_t *inode, xlator_t *this,
+ int *spb_choice)
+{
+ int ret = -1;
+ GF_VALIDATE_OR_GOTO(this->name, inode, out);
- LOCK(&inode->lock);
- {
- ret = __afr_inode_read_subvol_get (inode, this, data,
- metadata, event_p);
- }
- UNLOCK(&inode->lock);
+ LOCK(&inode->lock);
+ {
+ ret = __afr_inode_split_brain_choice_get(inode, this, spb_choice);
+ }
+ UNLOCK(&inode->lock);
out:
- return ret;
+ return ret;
}
+/*
+ * frame is used to get the favourite policy. Since
+ * afr_inode_split_brain_choice_get was called with afr_open, it is possible to
+ * have a frame with out local->replies. So in that case, frame is passed as
+ * null, hence this function will handle the frame NULL case.
+ */
int
-afr_inode_get_readable (call_frame_t *frame, inode_t *inode, xlator_t *this,
- unsigned char *readable, int *event_p, int type)
+afr_split_brain_read_subvol_get(inode_t *inode, xlator_t *this,
+ call_frame_t *frame, int *spb_subvol)
{
+ int ret = -1;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
- afr_private_t *priv = this->private;
- afr_local_t *local = frame->local;
- unsigned char *data = alloca0 (priv->child_count);
- unsigned char *metadata = alloca0 (priv->child_count);
- int data_count = 0;
- int metadata_count = 0;
- int event_generation = 0;
- int ret = 0;
-
- /* We don't care about split-brains for entry transactions. */
- if (type == AFR_ENTRY_TRANSACTION || type == AFR_ENTRY_RENAME_TRANSACTION)
- return 0;
+ GF_VALIDATE_OR_GOTO("afr", this, out);
+ GF_VALIDATE_OR_GOTO(this->name, this->private, out);
+ GF_VALIDATE_OR_GOTO(this->name, inode, out);
+ GF_VALIDATE_OR_GOTO(this->name, spb_subvol, out);
- ret = afr_inode_read_subvol_get (inode, this, data, metadata,
- &event_generation);
- if (ret == -1)
- return -EIO;
+ priv = this->private;
- data_count = AFR_COUNT (data, priv->child_count);
- metadata_count = AFR_COUNT (metadata, priv->child_count);
+ ret = afr_inode_split_brain_choice_get(inode, this, spb_subvol);
+ if (*spb_subvol < 0 && priv->fav_child_policy && frame && frame->local) {
+ local = frame->local;
+ *spb_subvol = afr_sh_get_fav_by_policy(this, local->replies, inode,
+ NULL);
+ if (*spb_subvol >= 0) {
+ ret = 0;
+ }
+ }
- if (inode->ia_type == IA_IFDIR) {
- /* For directories, allow even if it is in data split-brain. */
- if (type == AFR_METADATA_TRANSACTION) {
- if (!metadata_count)
- return -EIO;
- }
- } else {
- /* For files, abort in case of data/metadata split-brain. */
- if (!data_count || !metadata_count)
- return -EIO;
- }
-
- if (type == AFR_METADATA_TRANSACTION && readable)
- memcpy (readable, metadata, priv->child_count * sizeof *metadata);
- if (type == AFR_DATA_TRANSACTION && readable) {
- if (!data_count)
- memcpy (readable, local->child_up,
- priv->child_count * sizeof *readable);
- else
- memcpy (readable, data, priv->child_count * sizeof *data);
- }
- if (event_p)
- *event_p = event_generation;
- return 0;
+out:
+ return ret;
}
-
int
-afr_inode_split_brain_choice_get (inode_t *inode, xlator_t *this,
- int *spb_choice)
+afr_inode_read_subvol_set(inode_t *inode, xlator_t *this, unsigned char *data,
+ unsigned char *metadata, int event)
{
- int ret = -1;
+ int ret = -1;
- GF_VALIDATE_OR_GOTO (this->name, inode, out);
+ GF_VALIDATE_OR_GOTO(this->name, inode, out);
- LOCK(&inode->lock);
- {
- ret = __afr_inode_split_brain_choice_get (inode, this,
- spb_choice);
- }
- UNLOCK(&inode->lock);
+ LOCK(&inode->lock);
+ {
+ ret = __afr_inode_read_subvol_set(inode, this, data, metadata, event);
+ }
+ UNLOCK(&inode->lock);
out:
- return ret;
+ return ret;
}
-
int
-afr_inode_read_subvol_set (inode_t *inode, xlator_t *this, unsigned char *data,
- unsigned char *metadata, int event)
+afr_inode_split_brain_choice_set(inode_t *inode, xlator_t *this, int spb_choice)
{
- int ret = -1;
+ int ret = -1;
- GF_VALIDATE_OR_GOTO (this->name, inode, out);
+ GF_VALIDATE_OR_GOTO(this->name, inode, out);
- LOCK(&inode->lock);
- {
- ret = __afr_inode_read_subvol_set (inode, this, data, metadata,
- event);
- }
- UNLOCK(&inode->lock);
+ LOCK(&inode->lock);
+ {
+ ret = __afr_inode_split_brain_choice_set(inode, this, spb_choice);
+ }
+ UNLOCK(&inode->lock);
out:
- return ret;
+ return ret;
}
-
-int
-afr_inode_split_brain_choice_set (inode_t *inode, xlator_t *this,
- int spb_choice)
+/* The caller of this should perform afr_inode_refresh, if this function
+ * returns _gf_true
+ */
+gf_boolean_t
+afr_is_inode_refresh_reqd(inode_t *inode, xlator_t *this, int event_gen1,
+ int event_gen2)
{
- int ret = -1;
+ gf_boolean_t need_refresh = _gf_false;
+ afr_inode_ctx_t *ctx = NULL;
+ int ret = -1;
- GF_VALIDATE_OR_GOTO (this->name, inode, out);
+ GF_VALIDATE_OR_GOTO(this->name, inode, out);
- LOCK(&inode->lock);
- {
- ret = __afr_inode_split_brain_choice_set (inode, this,
- spb_choice);
- }
- UNLOCK(&inode->lock);
+ LOCK(&inode->lock);
+ {
+ ret = __afr_inode_ctx_get(this, inode, &ctx);
+ if (ret)
+ goto unlock;
+
+ need_refresh = ctx->need_refresh;
+ /* Hoping that the caller will do inode_refresh followed by
+ * this, hence setting the need_refresh to false */
+ ctx->need_refresh = _gf_false;
+ }
+unlock:
+ UNLOCK(&inode->lock);
+
+ if (event_gen1 != event_gen2)
+ need_refresh = _gf_true;
out:
- return ret;
+ return need_refresh;
}
+int
+__afr_inode_need_refresh_set(inode_t *inode, xlator_t *this)
+{
+ int ret = -1;
+ afr_inode_ctx_t *ctx = NULL;
+
+ ret = __afr_inode_ctx_get(this, inode, &ctx);
+ if (ret == 0) {
+ ctx->need_refresh = _gf_true;
+ }
+
+ return ret;
+}
int
-afr_inode_read_subvol_reset (inode_t *inode, xlator_t *this)
+afr_inode_need_refresh_set(inode_t *inode, xlator_t *this)
{
- int ret = -1;
+ int ret = -1;
- GF_VALIDATE_OR_GOTO (this->name, inode, out);
+ GF_VALIDATE_OR_GOTO(this->name, inode, out);
- LOCK(&inode->lock);
- {
- ret = __afr_inode_read_subvol_reset (inode, this);
- }
- UNLOCK(&inode->lock);
+ LOCK(&inode->lock);
+ {
+ ret = __afr_inode_need_refresh_set(inode, this);
+ }
+ UNLOCK(&inode->lock);
out:
- return ret;
+ return ret;
}
int
-afr_spb_choice_timeout_cancel (xlator_t *this, inode_t *inode)
+afr_spb_choice_timeout_cancel(xlator_t *this, inode_t *inode)
{
- afr_inode_ctx_t *ctx = NULL;
- int ret = -1;
+ afr_inode_ctx_t *ctx = NULL;
+ int ret = -1;
- if (!inode)
- return ret;
+ if (!inode)
+ return ret;
- LOCK(&inode->lock);
- {
- __afr_inode_ctx_get (this, inode, &ctx);
- if (!ctx) {
- gf_log (this->name, GF_LOG_WARNING, "Failed to cancel"
- " split-brain choice timer.");
- goto out;
- }
- ctx->spb_choice = -1;
- if (ctx->timer) {
- gf_timer_call_cancel (this->ctx, ctx->timer);
- ctx->timer = NULL;
- }
- ret = 0;
+ LOCK(&inode->lock);
+ {
+ ret = __afr_inode_ctx_get(this, inode, &ctx);
+ if (ret < 0 || !ctx) {
+ UNLOCK(&inode->lock);
+ gf_msg(this->name, GF_LOG_WARNING, 0,
+ AFR_MSG_SPLIT_BRAIN_CHOICE_ERROR,
+ "Failed to cancel split-brain choice timer.");
+ goto out;
+ }
+ ctx->spb_choice = -1;
+ if (ctx->timer) {
+ gf_timer_call_cancel(this->ctx, ctx->timer);
+ ctx->timer = NULL;
}
+ ret = 0;
+ }
+ UNLOCK(&inode->lock);
out:
- UNLOCK(&inode->lock);
- return ret;
+ return ret;
}
void
-afr_set_split_brain_choice_cbk (void *data)
+afr_set_split_brain_choice_cbk(void *data)
{
- inode_t *inode = data;
- xlator_t *this = THIS;
+ inode_t *inode = data;
+ xlator_t *this = THIS;
- afr_spb_choice_timeout_cancel (this, inode);
- inode_unref (inode);
- return;
+ afr_spb_choice_timeout_cancel(this, inode);
+ inode_invalidate(inode);
+ inode_unref(inode);
+ return;
}
-
int
-afr_set_split_brain_choice (int ret, call_frame_t *frame, void *opaque)
-{
- int op_errno = ENOMEM;
- afr_private_t *priv = NULL;
- afr_inode_ctx_t *ctx = NULL;
- inode_t *inode = NULL;
- loc_t *loc = NULL;
- xlator_t *this = NULL;
- afr_spbc_timeout_t *data = opaque;
- struct timespec delta = {0, };
-
- if (ret)
- goto out;
-
- frame = data->frame;
- loc = data->loc;
- this = frame->this;
- priv = this->private;
-
- delta.tv_sec = priv->spb_choice_timeout;
- delta.tv_nsec = 0;
-
- inode = loc->inode;
- if (!inode)
- goto out;
-
- if (!(data->d_spb || data->m_spb)) {
- gf_log (this->name, GF_LOG_WARNING, "Cannot set "
- "replica.split-brain-choice on %s. File is"
- " not in data/metadata split-brain.",
- uuid_utoa (loc->gfid));
- ret = -1;
- op_errno = EINVAL;
- goto out;
+afr_set_split_brain_choice(int ret, call_frame_t *frame, void *opaque)
+{
+ int op_errno = ENOMEM;
+ afr_private_t *priv = NULL;
+ afr_inode_ctx_t *ctx = NULL;
+ inode_t *inode = NULL;
+ loc_t *loc = NULL;
+ xlator_t *this = NULL;
+ afr_spbc_timeout_t *data = opaque;
+ struct timespec delta = {
+ 0,
+ };
+ gf_boolean_t timer_set = _gf_false;
+ gf_boolean_t timer_cancelled = _gf_false;
+ gf_boolean_t timer_reset = _gf_false;
+ int old_spb_choice = -1;
+
+ frame = data->frame;
+ loc = data->loc;
+ this = frame->this;
+ priv = this->private;
+
+ if (ret) {
+ op_errno = -ret;
+ ret = -1;
+ goto out;
+ }
+
+ delta.tv_sec = priv->spb_choice_timeout;
+ delta.tv_nsec = 0;
+
+ if (!loc->inode) {
+ ret = -1;
+ op_errno = EINVAL;
+ goto out;
+ }
+
+ if (!(data->d_spb || data->m_spb)) {
+ gf_msg(this->name, GF_LOG_WARNING, 0, AFR_MSG_SPLIT_BRAIN_CHOICE_ERROR,
+ "Cannot set "
+ "replica.split-brain-choice on %s. File is"
+ " not in data/metadata split-brain.",
+ uuid_utoa(loc->gfid));
+ ret = -1;
+ op_errno = EINVAL;
+ goto out;
+ }
+
+ /*
+ * we're ref'ing the inode before LOCK like it is done elsewhere in the
+ * code. If we ref after LOCK, coverity complains of possible deadlocks.
+ */
+ inode = inode_ref(loc->inode);
+
+ LOCK(&inode->lock);
+ {
+ ret = __afr_inode_ctx_get(this, inode, &ctx);
+ if (ret) {
+ UNLOCK(&inode->lock);
+ gf_msg(this->name, GF_LOG_ERROR, 0,
+ AFR_MSG_SPLIT_BRAIN_CHOICE_ERROR,
+ "Failed to get inode_ctx for %s", loc->name);
+ goto post_unlock;
}
- LOCK(&inode->lock);
- {
- ret = __afr_inode_ctx_get (this, inode, &ctx);
- if (ret) {
- gf_log (this->name, GF_LOG_ERROR, "Failed to get"
- "inode_ctx for %s", loc->name);
- goto unlock;
- }
-
- ctx->spb_choice = data->spb_child_index;
+ old_spb_choice = ctx->spb_choice;
+ ctx->spb_choice = data->spb_child_index;
- /* Possible changes in spb-choice :
- * -1 to valid : ref and inject timer
- *
- * valid to valid : cancel timer and inject new one
- *
- * valid to -1 : cancel timer and unref
- *
- * -1 to -1 : do not do anything
- */
+ /* Possible changes in spb-choice :
+ * valid to -1 : cancel timer and unref
+ * valid to valid : cancel timer and inject new one
+ * -1 to -1 : unref and do not do anything
+ * -1 to valid : inject timer
+ */
- /* ctx->timer is NULL iff previous value of
- * ctx->spb_choice is -1
- */
- if (ctx->timer) {
- if (ctx->spb_choice == -1) {
- gf_timer_call_cancel (this->ctx, ctx->timer);
- ctx->timer = NULL;
- inode_unref (inode);
- goto unlock;
- }
- goto reset_timer;
- } else {
- if (ctx->spb_choice == -1)
- goto unlock;
+ /* ctx->timer is NULL iff previous value of
+ * ctx->spb_choice is -1
+ */
+ if (ctx->timer) {
+ if (ctx->spb_choice == -1) {
+ if (!gf_timer_call_cancel(this->ctx, ctx->timer)) {
+ ctx->timer = NULL;
+ timer_cancelled = _gf_true;
}
-
- inode = inode_ref (loc->inode);
- goto set_timer;
-
-reset_timer:
- gf_timer_call_cancel (this->ctx, ctx->timer);
- ctx->timer = NULL;
-
-set_timer:
- ctx->timer = gf_timer_call_after (this->ctx, delta,
- afr_set_split_brain_choice_cbk,
- inode);
+ /* If timer cancel failed here it means that the
+ * previous cbk will be executed which will set
+ * spb_choice to -1. So we can consider the
+ * 'valid to -1' case to be a success
+ * (i.e. ret = 0) and goto unlock.
+ */
+ goto unlock;
+ }
+ goto reset_timer;
+ } else {
+ if (ctx->spb_choice == -1)
+ goto unlock;
+ goto set_timer;
}
+
+ reset_timer:
+ ret = gf_timer_call_cancel(this->ctx, ctx->timer);
+ if (ret != 0) {
+ /* We need to bail out now instead of launching a new
+ * timer. Otherwise the cbk of the previous timer event
+ * will cancel the new ctx->timer.
+ */
+ ctx->spb_choice = old_spb_choice;
+ ret = -1;
+ op_errno = EAGAIN;
+ goto unlock;
+ }
+ ctx->timer = NULL;
+ timer_reset = _gf_true;
+
+ set_timer:
+ ctx->timer = gf_timer_call_after(this->ctx, delta,
+ afr_set_split_brain_choice_cbk, inode);
+ if (!ctx->timer) {
+ ctx->spb_choice = old_spb_choice;
+ ret = -1;
+ op_errno = ENOMEM;
+ }
+ if (!timer_reset && ctx->timer)
+ timer_set = _gf_true;
+ if (timer_reset && !ctx->timer)
+ timer_cancelled = _gf_true;
+ }
unlock:
- UNLOCK(&inode->lock);
- inode_invalidate (inode);
+ UNLOCK(&inode->lock);
+post_unlock:
+ if (!timer_set)
+ inode_unref(inode);
+ if (timer_cancelled)
+ inode_unref(inode);
+ /*
+ * We need to invalidate the inode to prevent the kernel from serving
+ * reads from an older cached value despite a change in spb_choice to
+ * a new value.
+ */
+ inode_invalidate(inode);
out:
- if (data)
- GF_FREE (data);
- AFR_STACK_UNWIND (setxattr, frame, ret, op_errno, NULL);
- return 0;
+ GF_FREE(data);
+ AFR_STACK_UNWIND(setxattr, frame, ret, op_errno, NULL);
+ return 0;
}
int
-afr_accused_fill (xlator_t *this, dict_t *xdata, unsigned char *accused,
- afr_transaction_type type)
+afr_accused_fill(xlator_t *this, dict_t *xdata, unsigned char *accused,
+ afr_transaction_type type)
{
- afr_private_t *priv = NULL;
- int i = 0;
- int idx = afr_index_for_transaction_type (type);
- void *pending_raw = NULL;
- int pending[3];
- int ret = 0;
+ afr_private_t *priv = NULL;
+ int i = 0;
+ int idx = afr_index_for_transaction_type(type);
+ void *pending_raw = NULL;
+ int pending[3];
+ int ret = 0;
- priv = this->private;
+ priv = this->private;
- for (i = 0; i < priv->child_count; i++) {
- ret = dict_get_ptr (xdata, priv->pending_key[i],
- &pending_raw);
- if (ret) /* no pending flags */
- continue;
- memcpy (pending, pending_raw, sizeof(pending));
+ for (i = 0; i < priv->child_count; i++) {
+ ret = dict_get_ptr(xdata, priv->pending_key[i], &pending_raw);
+ if (ret) /* no pending flags */
+ continue;
+ memcpy(pending, pending_raw, sizeof(pending));
- if (ntoh32 (pending[idx]))
- accused[i] = 1;
- }
+ if (ntoh32(pending[idx]))
+ accused[i] = 1;
+ }
- return 0;
+ return 0;
}
-
int
-afr_accuse_smallfiles (xlator_t *this, struct afr_reply *replies,
- unsigned char *data_accused)
+afr_accuse_smallfiles(xlator_t *this, struct afr_reply *replies,
+ unsigned char *data_accused)
{
- int i = 0;
- afr_private_t *priv = NULL;
- uint64_t maxsize = 0;
+ int i = 0;
+ afr_private_t *priv = NULL;
+ uint64_t maxsize = 0;
- priv = this->private;
+ priv = this->private;
- for (i = 0; i < priv->child_count; i++) {
- if (data_accused[i])
- continue;
- if (replies[i].poststat.ia_size > maxsize)
- maxsize = replies[i].poststat.ia_size;
- }
+ for (i = 0; i < priv->child_count; i++) {
+ if (replies[i].valid && replies[i].xdata &&
+ dict_get_sizen(replies[i].xdata, GLUSTERFS_BAD_INODE))
+ continue;
+ if (data_accused[i])
+ continue;
+ if (replies[i].poststat.ia_size > maxsize)
+ maxsize = replies[i].poststat.ia_size;
+ }
- for (i = 0; i < priv->child_count; i++) {
- if (data_accused[i])
- continue;
- if ((priv->arbiter_count == 1) && (i == ARBITER_BRICK_INDEX))
- continue;
- if (replies[i].poststat.ia_size < maxsize)
- data_accused[i] = 1;
- }
+ for (i = 0; i < priv->child_count; i++) {
+ if (data_accused[i])
+ continue;
+ if (AFR_IS_ARBITER_BRICK(priv, i))
+ continue;
+ if (replies[i].poststat.ia_size < maxsize)
+ data_accused[i] = 1;
+ }
- return 0;
+ return 0;
}
-
int
-afr_replies_interpret (call_frame_t *frame, xlator_t *this, inode_t *inode)
-{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- struct afr_reply *replies = NULL;
- int event_generation = 0;
- int i = 0;
- unsigned char *data_accused = NULL;
- unsigned char *metadata_accused = NULL;
- unsigned char *data_readable = NULL;
- unsigned char *metadata_readable = NULL;
- int ret = 0;
-
- local = frame->local;
- priv = this->private;
- replies = local->replies;
- event_generation = local->event_generation;
-
- data_accused = alloca0 (priv->child_count);
- data_readable = alloca0 (priv->child_count);
- metadata_accused = alloca0 (priv->child_count);
- metadata_readable = alloca0 (priv->child_count);
-
- for (i = 0; i < priv->child_count; i++) {
- data_readable[i] = 1;
- metadata_readable[i] = 1;
- }
-
- for (i = 0; i < priv->child_count; i++) {
- if (!replies[i].valid) {
- data_readable[i] = 0;
- metadata_readable[i] = 0;
- continue;
- }
-
- if (replies[i].op_ret == -1) {
- data_readable[i] = 0;
- metadata_readable[i] = 0;
- continue;
- }
-
- afr_accused_fill (this, replies[i].xdata, data_accused,
- (replies[i].poststat.ia_type == IA_IFDIR) ?
- AFR_ENTRY_TRANSACTION : AFR_DATA_TRANSACTION);
-
- afr_accused_fill (this, replies[i].xdata,
- metadata_accused, AFR_METADATA_TRANSACTION);
-
- }
-
- if (inode->ia_type != IA_IFDIR)
- afr_accuse_smallfiles (this, replies, data_accused);
-
- for (i = 0; i < priv->child_count; i++) {
- if (data_accused[i]) {
- data_readable[i] = 0;
- ret = 1;
- }
- if (metadata_accused[i]) {
- metadata_readable[i] = 0;
- ret = 1;
- }
- }
-
- afr_inode_read_subvol_set (inode, this, data_readable,
- metadata_readable, event_generation);
- return ret;
+afr_readables_fill(call_frame_t *frame, xlator_t *this, inode_t *inode,
+ unsigned char *data_accused, unsigned char *metadata_accused,
+ unsigned char *data_readable,
+ unsigned char *metadata_readable, struct afr_reply *replies)
+{
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ dict_t *xdata = NULL;
+ int i = 0;
+ int ret = 0;
+ ia_type_t ia_type = IA_INVAL;
+
+ local = frame->local;
+ priv = this->private;
+
+ for (i = 0; i < priv->child_count; i++) {
+ data_readable[i] = 1;
+ metadata_readable[i] = 1;
+ }
+ if (AFR_IS_ARBITER_BRICK(priv, ARBITER_BRICK_INDEX)) {
+ data_readable[ARBITER_BRICK_INDEX] = 0;
+ metadata_readable[ARBITER_BRICK_INDEX] = 0;
+ }
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (replies) { /* Lookup */
+ if (!replies[i].valid || replies[i].op_ret == -1 ||
+ (replies[i].xdata &&
+ dict_get_sizen(replies[i].xdata, GLUSTERFS_BAD_INODE))) {
+ data_readable[i] = 0;
+ metadata_readable[i] = 0;
+ continue;
+ }
+
+ xdata = replies[i].xdata;
+ ia_type = replies[i].poststat.ia_type;
+ } else { /* pre-op xattrop */
+ xdata = local->transaction.changelog_xdata[i];
+ ia_type = inode->ia_type;
+ }
+
+ if (!xdata)
+ continue; /* mkdir_cbk sends NULL xdata_rsp. */
+ afr_accused_fill(this, xdata, data_accused,
+ (ia_type == IA_IFDIR) ? AFR_ENTRY_TRANSACTION
+ : AFR_DATA_TRANSACTION);
+
+ afr_accused_fill(this, xdata, metadata_accused,
+ AFR_METADATA_TRANSACTION);
+ }
+
+ if (replies && ia_type != IA_INVAL && ia_type != IA_IFDIR &&
+ /* We want to accuse small files only when we know for
+ * sure that there is no IO happening. Otherwise, the
+ * ia_sizes obtained in post-refresh replies may
+ * mismatch due to a race between inode-refresh and
+ * ongoing writes, causing spurious heal launches*/
+ !afr_is_possibly_under_txn(AFR_DATA_TRANSACTION, local, this)) {
+ afr_accuse_smallfiles(this, replies, data_accused);
+ }
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (data_accused[i]) {
+ data_readable[i] = 0;
+ ret = 1;
+ }
+ if (metadata_accused[i]) {
+ metadata_readable[i] = 0;
+ ret = 1;
+ }
+ }
+ return ret;
}
-
+int
+afr_replies_interpret(call_frame_t *frame, xlator_t *this, inode_t *inode,
+ gf_boolean_t *start_heal)
+{
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ struct afr_reply *replies = NULL;
+ int event_generation = 0;
+ int i = 0;
+ unsigned char *data_accused = NULL;
+ unsigned char *metadata_accused = NULL;
+ unsigned char *data_readable = NULL;
+ unsigned char *metadata_readable = NULL;
+ int ret = 0;
+
+ local = frame->local;
+ priv = this->private;
+ replies = local->replies;
+ event_generation = local->event_generation;
+
+ data_accused = alloca0(priv->child_count);
+ data_readable = alloca0(priv->child_count);
+ metadata_accused = alloca0(priv->child_count);
+ metadata_readable = alloca0(priv->child_count);
+
+ ret = afr_readables_fill(frame, this, inode, data_accused, metadata_accused,
+ data_readable, metadata_readable, replies);
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (start_heal && priv->child_up[i] &&
+ (data_accused[i] || metadata_accused[i])) {
+ *start_heal = _gf_true;
+ break;
+ }
+ }
+ afr_inode_read_subvol_set(inode, this, data_readable, metadata_readable,
+ event_generation);
+ return ret;
+}
int
-afr_refresh_selfheal_done (int ret, call_frame_t *heal, void *opaque)
+afr_refresh_selfheal_done(int ret, call_frame_t *heal, void *opaque)
{
- if (heal)
- STACK_DESTROY (heal->root);
- return 0;
+ if (heal)
+ AFR_STACK_DESTROY(heal);
+ return 0;
}
int
-afr_inode_refresh_err (call_frame_t *frame, xlator_t *this)
+afr_inode_refresh_err(call_frame_t *frame, xlator_t *this)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- int i = 0;
- int err = 0;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int i = 0;
+ int err = 0;
- local = frame->local;
- priv = this->private;
+ local = frame->local;
+ priv = this->private;
- for (i = 0; i < priv->child_count; i++) {
- if (local->replies[i].valid && !local->replies[i].op_ret) {
- err = 0;
- goto ret;
- }
- }
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->replies[i].valid && !local->replies[i].op_ret) {
+ err = 0;
+ goto ret;
+ }
+ }
- err = afr_final_errno (local, priv);
+ err = afr_final_errno(local, priv);
ret:
- return -err;
+ return err;
}
-
-int
-afr_refresh_selfheal_wrap (void *opaque)
+gf_boolean_t
+afr_selfheal_enabled(const xlator_t *this)
{
- call_frame_t *frame = opaque;
- afr_local_t *local = NULL;
- xlator_t *this = NULL;
- int err = 0;
+ const afr_private_t *priv = this->private;
- local = frame->local;
- this = frame->this;
+ return priv->data_self_heal || priv->metadata_self_heal ||
+ priv->entry_self_heal;
+}
- afr_selfheal (frame->this, local->refreshinode->gfid);
+int
+afr_txn_refresh_done(call_frame_t *frame, xlator_t *this, int err)
+{
+ call_frame_t *heal_frame = NULL;
+ afr_local_t *heal_local = NULL;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ inode_t *inode = NULL;
+ int event_generation = 0;
+ int read_subvol = -1;
+ int ret = 0;
+
+ local = frame->local;
+ inode = local->inode;
+ priv = this->private;
+
+ if (err)
+ goto refresh_done;
+
+ if (local->op == GF_FOP_LOOKUP)
+ goto refresh_done;
+
+ ret = afr_inode_get_readable(frame, inode, this, local->readable,
+ &event_generation, local->transaction.type);
+
+ if (ret == -EIO) {
+ /* No readable subvolume even after refresh ==> splitbrain.*/
+ if (!priv->fav_child_policy) {
+ err = EIO;
+ goto refresh_done;
+ }
+ read_subvol = afr_sh_get_fav_by_policy(this, local->replies, inode,
+ NULL);
+ if (read_subvol == -1) {
+ err = EIO;
+ goto refresh_done;
+ }
+
+ heal_frame = afr_frame_create(this, NULL);
+ if (!heal_frame) {
+ err = EIO;
+ goto refresh_done;
+ }
+ heal_local = heal_frame->local;
+ heal_local->xdata_req = dict_new();
+ if (!heal_local->xdata_req) {
+ err = EIO;
+ AFR_STACK_DESTROY(heal_frame);
+ goto refresh_done;
+ }
+ heal_local->heal_frame = frame;
+ ret = synctask_new(this->ctx->env, afr_fav_child_reset_sink_xattrs,
+ afr_fav_child_reset_sink_xattrs_cbk, heal_frame,
+ heal_frame);
+ return 0;
+ }
- afr_selfheal_unlocked_discover (frame, local->refreshinode,
- local->refreshinode->gfid,
- local->replies);
+refresh_done:
+ afr_local_replies_wipe(local, this->private);
+ local->refreshfn(frame, this, err);
- afr_replies_interpret (frame, this, local->refreshinode);
+ return 0;
+}
- err = afr_inode_refresh_err (frame, this);
+int
+afr_inode_refresh_done(call_frame_t *frame, xlator_t *this, int error)
+{
+ call_frame_t *heal_frame = NULL;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ gf_boolean_t start_heal = _gf_false;
+ afr_local_t *heal_local = NULL;
+ unsigned char *success_replies = NULL;
+ int ret = 0;
+
+ if (error != 0) {
+ goto refresh_done;
+ }
+
+ local = frame->local;
+ priv = this->private;
+ success_replies = alloca0(priv->child_count);
+ afr_fill_success_replies(local, priv, success_replies);
+
+ if (priv->thin_arbiter_count && local->is_read_txn &&
+ AFR_COUNT(success_replies, priv->child_count) != priv->child_count) {
+ /* We need to query the good bricks and/or thin-arbiter.*/
+ if (success_replies[0]) {
+ local->read_txn_query_child = AFR_CHILD_ZERO;
+ } else if (success_replies[1]) {
+ local->read_txn_query_child = AFR_CHILD_ONE;
+ }
+ error = EINVAL;
+ goto refresh_done;
+ }
+
+ if (!afr_has_quorum(success_replies, this, frame)) {
+ error = afr_final_errno(frame->local, this->private);
+ if (!error)
+ error = afr_quorum_errno(priv);
+ goto refresh_done;
+ }
+
+ ret = afr_replies_interpret(frame, this, local->refreshinode, &start_heal);
+
+ if (ret && afr_selfheal_enabled(this) && start_heal) {
+ heal_frame = afr_frame_create(this, NULL);
+ if (!heal_frame)
+ goto refresh_done;
+ heal_local = heal_frame->local;
+ heal_local->refreshinode = inode_ref(local->refreshinode);
+ heal_local->heal_frame = heal_frame;
+ if (!afr_throttled_selfheal(heal_frame, this)) {
+ AFR_STACK_DESTROY(heal_frame);
+ goto refresh_done;
+ }
+ }
+
+refresh_done:
+ afr_txn_refresh_done(frame, this, error);
+
+ return 0;
+}
- afr_local_replies_wipe (local, this->private);
+void
+afr_inode_refresh_subvol_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int op_ret, int op_errno, struct iatt *buf,
+ dict_t *xdata, struct iatt *par)
+{
+ afr_local_t *local = NULL;
+ int call_child = (long)cookie;
+ int8_t need_heal = 1;
+ int call_count = 0;
+ int ret = 0;
+
+ local = frame->local;
+ local->replies[call_child].valid = 1;
+ local->replies[call_child].op_ret = op_ret;
+ local->replies[call_child].op_errno = op_errno;
+ if (op_ret != -1) {
+ local->replies[call_child].poststat = *buf;
+ if (par)
+ local->replies[call_child].postparent = *par;
+ if (xdata)
+ local->replies[call_child].xdata = dict_ref(xdata);
+ }
- local->refreshfn (frame, this, err);
+ if (xdata) {
+ ret = dict_get_int8(xdata, "link-count", &need_heal);
+ if (ret) {
+ gf_msg_debug(this->name, -ret, "Unable to get link count");
+ }
+ }
- return 0;
+ local->replies[call_child].need_heal = need_heal;
+ call_count = afr_frame_return(frame);
+ if (call_count == 0) {
+ afr_set_need_heal(this, local);
+ ret = afr_inode_refresh_err(frame, this);
+ if (ret) {
+ gf_msg_debug(this->name, ret, "afr_inode_refresh_err failed");
+ }
+ afr_inode_refresh_done(frame, this, ret);
+ }
}
-
-gf_boolean_t
-afr_selfheal_enabled (xlator_t *this)
+int
+afr_inode_refresh_subvol_with_lookup_cbk(call_frame_t *frame, void *cookie,
+ xlator_t *this, int op_ret,
+ int op_errno, inode_t *inode,
+ struct iatt *buf, dict_t *xdata,
+ struct iatt *par)
{
- afr_private_t *priv = NULL;
- gf_boolean_t data = _gf_false;
- int ret = 0;
-
- priv = this->private;
-
- ret = gf_string2boolean (priv->data_self_heal, &data);
- GF_ASSERT (!ret);
-
- return data || priv->metadata_self_heal || priv->entry_self_heal;
+ afr_inode_refresh_subvol_cbk(frame, cookie, this, op_ret, op_errno, buf,
+ xdata, par);
+ return 0;
}
-
int
-afr_inode_refresh_done (call_frame_t *frame, xlator_t *this)
+afr_inode_refresh_subvol_with_lookup(call_frame_t *frame, xlator_t *this, int i,
+ inode_t *inode, uuid_t gfid, dict_t *xdata)
{
- call_frame_t *heal = NULL;
- afr_local_t *local = NULL;
- int ret = 0;
- int err = 0;
-
- local = frame->local;
+ loc_t loc = {
+ 0,
+ };
+ afr_private_t *priv = NULL;
- ret = afr_replies_interpret (frame, this, local->refreshinode);
+ priv = this->private;
- err = afr_inode_refresh_err (frame, this);
+ loc.inode = inode;
+ if (gf_uuid_is_null(inode->gfid) && gfid) {
+ /* To handle setattr/setxattr on yet to be linked inode from
+ * dht */
+ gf_uuid_copy(loc.gfid, gfid);
+ } else {
+ gf_uuid_copy(loc.gfid, inode->gfid);
+ }
- afr_local_replies_wipe (local, this->private);
-
- if (ret && afr_selfheal_enabled (this)) {
- heal = copy_frame (frame);
- if (heal)
- heal->root->pid = GF_CLIENT_PID_AFR_SELF_HEALD;
- ret = synctask_new (this->ctx->env, afr_refresh_selfheal_wrap,
- afr_refresh_selfheal_done, heal, frame);
- if (ret)
- goto refresh_done;
- } else {
- refresh_done:
- local->refreshfn (frame, this, err);
- }
-
- return 0;
+ STACK_WIND_COOKIE(frame, afr_inode_refresh_subvol_with_lookup_cbk,
+ (void *)(long)i, priv->children[i],
+ priv->children[i]->fops->lookup, &loc, xdata);
+ return 0;
}
-
int
-afr_inode_refresh_subvol_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int op_ret, int op_errno, inode_t *inode,
- struct iatt *buf, dict_t *xdata, struct iatt *par)
+afr_inode_refresh_subvol_with_fstat_cbk(call_frame_t *frame, void *cookie,
+ xlator_t *this, int32_t op_ret,
+ int32_t op_errno, struct iatt *buf,
+ dict_t *xdata)
{
- afr_local_t *local = NULL;
- int call_child = (long) cookie;
- int call_count = 0;
-
- local = frame->local;
-
- local->replies[call_child].valid = 1;
- local->replies[call_child].op_ret = op_ret;
- local->replies[call_child].op_errno = op_errno;
- if (op_ret != -1) {
- local->replies[call_child].poststat = *buf;
- local->replies[call_child].postparent = *par;
- local->replies[call_child].xdata = dict_ref (xdata);
- }
-
- call_count = afr_frame_return (frame);
-
- if (call_count == 0)
- afr_inode_refresh_done (frame, this);
-
- return 0;
+ afr_inode_refresh_subvol_cbk(frame, cookie, this, op_ret, op_errno, buf,
+ xdata, NULL);
+ return 0;
}
-
int
-afr_inode_refresh_subvol (call_frame_t *frame, xlator_t *this, int i,
- inode_t *inode, dict_t *xdata)
+afr_inode_refresh_subvol_with_fstat(call_frame_t *frame, xlator_t *this, int i,
+ dict_t *xdata)
{
- loc_t loc = {0, };
- afr_private_t *priv = NULL;
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
- priv = this->private;
+ priv = this->private;
+ local = frame->local;
- loc.inode = inode;
- gf_uuid_copy (loc.gfid, inode->gfid);
-
- STACK_WIND_COOKIE (frame, afr_inode_refresh_subvol_cbk,
- (void *) (long) i, priv->children[i],
- priv->children[i]->fops->lookup, &loc, xdata);
- return 0;
+ STACK_WIND_COOKIE(frame, afr_inode_refresh_subvol_with_fstat_cbk,
+ (void *)(long)i, priv->children[i],
+ priv->children[i]->fops->fstat, local->fd, xdata);
+ return 0;
}
-
int
-afr_inode_refresh_do (call_frame_t *frame, xlator_t *this)
+afr_inode_refresh_do(call_frame_t *frame, xlator_t *this)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- int call_count = 0;
- int i = 0;
- dict_t *xdata = NULL;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int call_count = 0;
+ int i = 0;
+ int ret = 0;
+ dict_t *xdata = NULL;
+ afr_fd_ctx_t *fd_ctx = NULL;
+ unsigned char *wind_subvols = NULL;
- priv = this->private;
- local = frame->local;
+ priv = this->private;
+ local = frame->local;
+ wind_subvols = alloca0(priv->child_count);
- afr_local_replies_wipe (local, priv);
+ afr_local_replies_wipe(local, priv);
- xdata = dict_new ();
- if (!xdata) {
- afr_inode_refresh_done (frame, this);
- return 0;
- }
+ if (local->fd) {
+ fd_ctx = afr_fd_ctx_get(local->fd, this);
+ if (!fd_ctx) {
+ afr_inode_refresh_done(frame, this, EINVAL);
+ return 0;
+ }
+ }
- if (afr_xattr_req_prepare (this, xdata) != 0) {
- dict_unref (xdata);
- afr_inode_refresh_done (frame, this);
- return 0;
- }
+ xdata = dict_new();
+ if (!xdata) {
+ afr_inode_refresh_done(frame, this, ENOMEM);
+ return 0;
+ }
- local->call_count = AFR_COUNT (local->child_up, priv->child_count);
+ ret = afr_xattr_req_prepare(this, xdata);
+ if (ret != 0) {
+ dict_unref(xdata);
+ afr_inode_refresh_done(frame, this, -ret);
+ return 0;
+ }
+
+ ret = dict_set_sizen_str_sizen(xdata, "link-count", GF_XATTROP_INDEX_COUNT);
+ if (ret) {
+ gf_msg_debug(this->name, -ret, "Unable to set link-count in dict ");
+ }
- call_count = local->call_count;
- for (i = 0; i < priv->child_count; i++) {
- if (!local->child_up[i])
- continue;
+ ret = dict_set_str_sizen(xdata, GLUSTERFS_INODELK_DOM_COUNT, this->name);
+ if (ret) {
+ gf_msg_debug(this->name, -ret,
+ "Unable to set inodelk-dom-count in dict ");
+ }
- afr_inode_refresh_subvol (frame, this, i, local->refreshinode,
- xdata);
+ if (local->fd) {
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->child_up[i] && fd_ctx->opened_on[i] == AFR_FD_OPENED)
+ wind_subvols[i] = 1;
+ }
+ } else {
+ memcpy(wind_subvols, local->child_up,
+ sizeof(*local->child_up) * priv->child_count);
+ }
+
+ local->call_count = AFR_COUNT(wind_subvols, priv->child_count);
+
+ call_count = local->call_count;
+ if (!call_count) {
+ dict_unref(xdata);
+ if (local->fd && AFR_COUNT(local->child_up, priv->child_count))
+ afr_inode_refresh_done(frame, this, EBADFD);
+ else
+ afr_inode_refresh_done(frame, this, ENOTCONN);
+ return 0;
+ }
+ for (i = 0; i < priv->child_count; i++) {
+ if (!wind_subvols[i])
+ continue;
- if (!--call_count)
- break;
- }
+ if (local->fd)
+ afr_inode_refresh_subvol_with_fstat(frame, this, i, xdata);
+ else
+ afr_inode_refresh_subvol_with_lookup(
+ frame, this, i, local->refreshinode, local->refreshgfid, xdata);
- dict_unref (xdata);
+ if (!--call_count)
+ break;
+ }
- return 0;
-}
+ dict_unref(xdata);
+ return 0;
+}
int
-afr_inode_refresh (call_frame_t *frame, xlator_t *this, inode_t *inode,
- afr_inode_refresh_cbk_t refreshfn)
+afr_inode_refresh(call_frame_t *frame, xlator_t *this, inode_t *inode,
+ uuid_t gfid, afr_inode_refresh_cbk_t refreshfn)
{
- afr_local_t *local = NULL;
+ afr_local_t *local = NULL;
- local = frame->local;
+ local = frame->local;
- local->refreshfn = refreshfn;
+ local->refreshfn = refreshfn;
- if (local->refreshinode) {
- inode_unref (local->refreshinode);
- local->refreshinode = NULL;
- }
+ if (local->refreshinode) {
+ inode_unref(local->refreshinode);
+ local->refreshinode = NULL;
+ }
- local->refreshinode = inode_ref (inode);
+ local->refreshinode = inode_ref(inode);
- afr_inode_refresh_do (frame, this);
+ if (gfid)
+ gf_uuid_copy(local->refreshgfid, gfid);
+ else
+ gf_uuid_clear(local->refreshgfid);
- return 0;
-}
+ afr_inode_refresh_do(frame, this);
+ return 0;
+}
int
-afr_xattr_req_prepare (xlator_t *this, dict_t *xattr_req)
+afr_xattr_req_prepare(xlator_t *this, dict_t *xattr_req)
{
- int i = 0;
- afr_private_t *priv = NULL;
- int ret = 0;
+ int i = 0;
+ afr_private_t *priv = NULL;
+ int ret = 0;
- priv = this->private;
+ priv = this->private;
- for (i = 0; i < priv->child_count; i++) {
- ret = dict_set_uint64 (xattr_req, priv->pending_key[i],
- AFR_NUM_CHANGE_LOGS * sizeof(int));
- if (ret < 0)
- gf_msg (this->name, GF_LOG_WARNING,
- -ret, AFR_MSG_DICT_SET_FAILED,
- "Unable to set dict value for %s",
- priv->pending_key[i]);
- /* 3 = data+metadata+entry */
- }
- ret = dict_set_uint64 (xattr_req, AFR_DIRTY,
- AFR_NUM_CHANGE_LOGS * sizeof(int));
- if (ret) {
- gf_msg_debug (this->name, -ret, "failed to set dirty "
- "query flag");
- }
-
- ret = dict_set_int32 (xattr_req, "list-xattr", 1);
- if (ret) {
- gf_msg_debug (this->name, -ret,
- "Unable to set list-xattr in dict ");
- }
+ for (i = 0; i < priv->child_count; i++) {
+ ret = dict_set_uint64(xattr_req, priv->pending_key[i],
+ AFR_NUM_CHANGE_LOGS * sizeof(int));
+ if (ret < 0)
+ gf_msg(this->name, GF_LOG_WARNING, -ret, AFR_MSG_DICT_SET_FAILED,
+ "Unable to set dict value for %s", priv->pending_key[i]);
+ /* 3 = data+metadata+entry */
+ }
+ ret = dict_set_uint64(xattr_req, AFR_DIRTY,
+ AFR_NUM_CHANGE_LOGS * sizeof(int));
+ if (ret) {
+ gf_msg_debug(this->name, -ret,
+ "failed to set dirty "
+ "query flag");
+ }
+
+ ret = dict_set_int32_sizen(xattr_req, "list-xattr", 1);
+ if (ret) {
+ gf_msg_debug(this->name, -ret, "Unable to set list-xattr in dict ");
+ }
+
+ return ret;
+}
- return ret;
+int
+afr_lookup_xattr_req_prepare(afr_local_t *local, xlator_t *this,
+ dict_t *xattr_req, loc_t *loc)
+{
+ int ret = -ENOMEM;
+
+ if (!local->xattr_req)
+ local->xattr_req = dict_new();
+
+ if (!local->xattr_req)
+ goto out;
+
+ if (xattr_req && (xattr_req != local->xattr_req))
+ dict_copy(xattr_req, local->xattr_req);
+
+ ret = afr_xattr_req_prepare(this, local->xattr_req);
+
+ ret = dict_set_uint64(local->xattr_req, GLUSTERFS_INODELK_COUNT, 0);
+ if (ret < 0) {
+ gf_msg(this->name, GF_LOG_WARNING, -ret, AFR_MSG_DICT_SET_FAILED,
+ "%s: Unable to set dict value for %s", loc->path,
+ GLUSTERFS_INODELK_COUNT);
+ }
+ ret = dict_set_uint64(local->xattr_req, GLUSTERFS_ENTRYLK_COUNT, 0);
+ if (ret < 0) {
+ gf_msg(this->name, GF_LOG_WARNING, -ret, AFR_MSG_DICT_SET_FAILED,
+ "%s: Unable to set dict value for %s", loc->path,
+ GLUSTERFS_ENTRYLK_COUNT);
+ }
+
+ ret = dict_set_uint32(local->xattr_req, GLUSTERFS_PARENT_ENTRYLK, 0);
+ if (ret < 0) {
+ gf_msg(this->name, GF_LOG_WARNING, -ret, AFR_MSG_DICT_SET_FAILED,
+ "%s: Unable to set dict value for %s", loc->path,
+ GLUSTERFS_PARENT_ENTRYLK);
+ }
+
+ ret = dict_set_sizen_str_sizen(local->xattr_req, "link-count",
+ GF_XATTROP_INDEX_COUNT);
+ if (ret) {
+ gf_msg_debug(this->name, -ret, "Unable to set link-count in dict ");
+ }
+
+ ret = 0;
+out:
+ return ret;
}
int
-afr_lookup_xattr_req_prepare (afr_local_t *local, xlator_t *this,
- dict_t *xattr_req, loc_t *loc)
+afr_least_pending_reads_child(afr_private_t *priv, unsigned char *readable)
{
- int ret = -ENOMEM;
-
- if (!local->xattr_req)
- local->xattr_req = dict_new ();
+ int i = 0;
+ int child = -1;
+ int64_t read_iter = -1;
+ int64_t pending_read = -1;
- if (!local->xattr_req)
- goto out;
+ for (i = 0; i < priv->child_count; i++) {
+ if (AFR_IS_ARBITER_BRICK(priv, i) || !readable[i])
+ continue;
+ read_iter = GF_ATOMIC_GET(priv->pending_reads[i]);
+ if (child == -1 || read_iter < pending_read) {
+ pending_read = read_iter;
+ child = i;
+ }
+ }
- if (xattr_req && (xattr_req != local->xattr_req))
- dict_copy (xattr_req, local->xattr_req);
+ return child;
+}
- ret = afr_xattr_req_prepare (this, local->xattr_req);
+static int32_t
+afr_least_latency_child(afr_private_t *priv, unsigned char *readable)
+{
+ int32_t i = 0;
+ int child = -1;
- ret = dict_set_uint64 (local->xattr_req, GLUSTERFS_INODELK_COUNT, 0);
- if (ret < 0) {
- gf_msg (this->name, GF_LOG_WARNING,
- -ret, AFR_MSG_DICT_SET_FAILED,
- "%s: Unable to set dict value for %s",
- loc->path, GLUSTERFS_INODELK_COUNT);
- }
- ret = dict_set_uint64 (local->xattr_req, GLUSTERFS_ENTRYLK_COUNT, 0);
- if (ret < 0) {
- gf_msg (this->name, GF_LOG_WARNING,
- -ret, AFR_MSG_DICT_SET_FAILED,
- "%s: Unable to set dict value for %s",
- loc->path, GLUSTERFS_ENTRYLK_COUNT);
- }
+ for (i = 0; i < priv->child_count; i++) {
+ if (AFR_IS_ARBITER_BRICK(priv, i) || !readable[i] ||
+ priv->child_latency[i] < 0)
+ continue;
- ret = dict_set_uint32 (local->xattr_req, GLUSTERFS_PARENT_ENTRYLK, 0);
- if (ret < 0) {
- gf_msg (this->name, GF_LOG_WARNING,
- -ret, AFR_MSG_DICT_SET_FAILED,
- "%s: Unable to set dict value for %s",
- loc->path, GLUSTERFS_PARENT_ENTRYLK);
+ if (child == -1 ||
+ priv->child_latency[i] < priv->child_latency[child]) {
+ child = i;
}
-
- ret = 0;
-out:
- return ret;
+ }
+ return child;
}
-
-int
-afr_hash_child (afr_read_subvol_args_t *args, int32_t child_count, int hashmode)
+static int32_t
+afr_least_latency_times_pending_reads_child(afr_private_t *priv,
+ unsigned char *readable)
{
- uuid_t gfid_copy = {0,};
- pid_t pid;
+ int32_t i = 0;
+ int child = -1;
+ int64_t pending_read = 0;
+ int64_t latency = -1;
+ int64_t least_latency = -1;
- if (!hashmode) {
- return -1;
- }
+ for (i = 0; i < priv->child_count; i++) {
+ if (AFR_IS_ARBITER_BRICK(priv, i) || !readable[i] ||
+ priv->child_latency[i] < 0)
+ continue;
- gf_uuid_copy (gfid_copy, args->gfid);
+ pending_read = GF_ATOMIC_GET(priv->pending_reads[i]);
+ latency = (pending_read + 1) * priv->child_latency[i];
- if ((hashmode > 1) && (args->ia_type != IA_IFDIR)) {
+ if (child == -1 || latency < least_latency) {
+ least_latency = latency;
+ child = i;
+ }
+ }
+ return child;
+}
+
+int
+afr_hash_child(afr_read_subvol_args_t *args, afr_private_t *priv,
+ unsigned char *readable)
+{
+ uuid_t gfid_copy = {
+ 0,
+ };
+ pid_t pid;
+ int child = -1;
+
+ switch (priv->hash_mode) {
+ case AFR_READ_POLICY_FIRST_UP:
+ break;
+ case AFR_READ_POLICY_GFID_HASH:
+ gf_uuid_copy(gfid_copy, args->gfid);
+ child = SuperFastHash((char *)gfid_copy, sizeof(gfid_copy)) %
+ priv->child_count;
+ break;
+ case AFR_READ_POLICY_GFID_PID_HASH:
+ if (args->ia_type != IA_IFDIR) {
/*
* Why getpid? Because it's one of the cheapest calls
- * available - faster than gethostname etc. - and returns a
- * constant-length value that's sure to be shorter than a UUID.
- * It's still very unlikely to be the same across clients, so
- * it still provides good mixing. We're not trying for
- * perfection here. All we need is a low probability that
- * multiple clients won't converge on the same subvolume.
+ * available - faster than gethostname etc. - and
+ * returns a constant-length value that's sure to be
+ * shorter than a UUID. It's still very unlikely to be
+ * the same across clients, so it still provides good
+ * mixing. We're not trying for perfection here. All we
+ * need is a low probability that multiple clients
+ * won't converge on the same subvolume.
*/
+ gf_uuid_copy(gfid_copy, args->gfid);
pid = getpid();
- memcpy (gfid_copy, &pid, sizeof(pid));
- }
-
- return SuperFastHash((char *)gfid_copy,
- sizeof(gfid_copy)) % child_count;
+ *(pid_t *)gfid_copy ^= pid;
+ }
+ child = SuperFastHash((char *)gfid_copy, sizeof(gfid_copy)) %
+ priv->child_count;
+ break;
+ case AFR_READ_POLICY_LESS_LOAD:
+ child = afr_least_pending_reads_child(priv, readable);
+ break;
+ case AFR_READ_POLICY_LEAST_LATENCY:
+ child = afr_least_latency_child(priv, readable);
+ break;
+ case AFR_READ_POLICY_LOAD_LATENCY_HYBRID:
+ child = afr_least_latency_times_pending_reads_child(priv, readable);
+ break;
+ }
+
+ return child;
}
-
int
-afr_read_subvol_select_by_policy (inode_t *inode, xlator_t *this,
- unsigned char *readable,
- afr_read_subvol_args_t *args)
+afr_read_subvol_select_by_policy(inode_t *inode, xlator_t *this,
+ unsigned char *readable,
+ afr_read_subvol_args_t *args)
{
- int i = 0;
- int read_subvol = -1;
- afr_private_t *priv = NULL;
- afr_read_subvol_args_t local_args = {0,};
+ int i = 0;
+ int read_subvol = -1;
+ afr_private_t *priv = NULL;
+ afr_read_subvol_args_t local_args = {
+ 0,
+ };
- priv = this->private;
+ priv = this->private;
- /* first preference - explicitly specified or local subvolume */
- if (priv->read_child >= 0 && readable[priv->read_child])
- return priv->read_child;
+ /* first preference - explicitly specified or local subvolume */
+ if (priv->read_child >= 0 && readable[priv->read_child])
+ return priv->read_child;
- if (inode_is_linked (inode)) {
- gf_uuid_copy (local_args.gfid, inode->gfid);
- local_args.ia_type = inode->ia_type;
- } else if (args) {
- local_args = *args;
- }
+ if (inode_is_linked(inode)) {
+ gf_uuid_copy(local_args.gfid, inode->gfid);
+ local_args.ia_type = inode->ia_type;
+ } else if (args) {
+ local_args = *args;
+ }
- /* second preference - use hashed mode */
- read_subvol = afr_hash_child (&local_args, priv->child_count,
- priv->hash_mode);
- if (read_subvol >= 0 && readable[read_subvol])
- return read_subvol;
+ /* second preference - use hashed mode */
+ read_subvol = afr_hash_child(&local_args, priv, readable);
+ if (read_subvol >= 0 && readable[read_subvol])
+ return read_subvol;
- for (i = 0; i < priv->child_count; i++) {
- if (readable[i])
- return i;
- }
+ for (i = 0; i < priv->child_count; i++) {
+ if (readable[i])
+ return i;
+ }
- /* no readable subvolumes, either split brain or all subvols down */
+ /* no readable subvolumes, either split brain or all subvols down */
- return -1;
+ return -1;
}
-
int
-afr_inode_read_subvol_type_get (inode_t *inode, xlator_t *this,
- unsigned char *readable, int *event_p,
- int type)
+afr_inode_read_subvol_type_get(inode_t *inode, xlator_t *this,
+ unsigned char *readable, int *event_p, int type)
{
- int ret = -1;
+ int ret = -1;
- if (type == AFR_METADATA_TRANSACTION)
- ret = afr_inode_read_subvol_get (inode, this, 0, readable,
- event_p);
- else
- ret = afr_inode_read_subvol_get (inode, this, readable, 0,
- event_p);
- return ret;
+ if (type == AFR_METADATA_TRANSACTION)
+ ret = afr_inode_read_subvol_get(inode, this, 0, readable, event_p);
+ else
+ ret = afr_inode_read_subvol_get(inode, this, readable, 0, event_p);
+ return ret;
}
+void
+afr_readables_intersect_get(inode_t *inode, xlator_t *this, int *event,
+ unsigned char *intersection)
+{
+ afr_private_t *priv = NULL;
+ unsigned char *data_readable = NULL;
+ unsigned char *metadata_readable = NULL;
+ unsigned char *intersect = NULL;
+
+ priv = this->private;
+ data_readable = alloca0(priv->child_count);
+ metadata_readable = alloca0(priv->child_count);
+ intersect = alloca0(priv->child_count);
+
+ afr_inode_read_subvol_get(inode, this, data_readable, metadata_readable,
+ event);
+
+ AFR_INTERSECT(intersect, data_readable, metadata_readable,
+ priv->child_count);
+ if (intersection)
+ memcpy(intersection, intersect,
+ sizeof(*intersection) * priv->child_count);
+}
int
-afr_read_subvol_get (inode_t *inode, xlator_t *this, int *subvol_p,
- int *event_p, afr_transaction_type type,
- afr_read_subvol_args_t *args)
+afr_read_subvol_get(inode_t *inode, xlator_t *this, int *subvol_p,
+ unsigned char *readables, int *event_p,
+ afr_transaction_type type, afr_read_subvol_args_t *args)
{
- afr_private_t *priv = NULL;
- unsigned char *data_readable = NULL;
- unsigned char *metadata_readable = NULL;
- unsigned char *readable = NULL;
- unsigned char *intersection = NULL;
- int subvol = -1;
- int event = 0;
+ afr_private_t *priv = NULL;
+ unsigned char *readable = NULL;
+ unsigned char *intersection = NULL;
+ int subvol = -1;
+ int event = 0;
- priv = this->private;
+ priv = this->private;
- readable = alloca0 (priv->child_count);
- data_readable = alloca0 (priv->child_count);
- metadata_readable = alloca0 (priv->child_count);
- intersection = alloca0 (priv->child_count);
+ readable = alloca0(priv->child_count);
+ intersection = alloca0(priv->child_count);
- afr_inode_read_subvol_type_get (inode, this, readable, &event, type);
+ afr_inode_read_subvol_type_get(inode, this, readable, &event, type);
- afr_inode_read_subvol_get (inode, this, data_readable, metadata_readable,
- &event);
+ afr_readables_intersect_get(inode, this, &event, intersection);
- AFR_INTERSECT (intersection, data_readable, metadata_readable,
- priv->child_count);
-
- if (AFR_COUNT (intersection, priv->child_count) > 0)
- subvol = afr_read_subvol_select_by_policy (inode, this,
- intersection, args);
- else
- subvol = afr_read_subvol_select_by_policy (inode, this,
- readable, args);
- if (subvol_p)
- *subvol_p = subvol;
- if (event_p)
- *event_p = event;
- return subvol;
+ if (AFR_COUNT(intersection, priv->child_count) > 0)
+ subvol = afr_read_subvol_select_by_policy(inode, this, intersection,
+ args);
+ else
+ subvol = afr_read_subvol_select_by_policy(inode, this, readable, args);
+ if (subvol_p)
+ *subvol_p = subvol;
+ if (event_p)
+ *event_p = event;
+ if (readables)
+ memcpy(readables, readable, sizeof(*readables) * priv->child_count);
+ return subvol;
}
-
void
-afr_local_transaction_cleanup (afr_local_t *local, xlator_t *this)
+afr_local_transaction_cleanup(afr_local_t *local, xlator_t *this)
{
- afr_private_t *priv = NULL;
- int i = 0;
+ afr_private_t *priv = NULL;
+ int i = 0;
- priv = this->private;
+ priv = this->private;
- afr_matrix_cleanup (local->pending, priv->child_count);
+ afr_matrix_cleanup(local->pending, priv->child_count);
- GF_FREE (local->internal_lock.locked_nodes);
+ GF_FREE(local->internal_lock.lower_locked_nodes);
- for (i = 0; local->internal_lock.inodelk[i].domain; i++) {
- GF_FREE (local->internal_lock.inodelk[i].locked_nodes);
- }
+ afr_lockees_cleanup(&local->internal_lock);
- GF_FREE (local->internal_lock.lower_locked_nodes);
+ GF_FREE(local->transaction.pre_op);
- afr_entry_lockee_cleanup (&local->internal_lock);
-
- GF_FREE (local->transaction.pre_op);
-
- GF_FREE (local->transaction.pre_op_sources);
- if (local->transaction.pre_op_xdata) {
- for (i = 0; i < priv->child_count; i++) {
- if (!local->transaction.pre_op_xdata[i])
- continue;
- dict_unref (local->transaction.pre_op_xdata[i]);
- }
- GF_FREE (local->transaction.pre_op_xdata);
+ GF_FREE(local->transaction.pre_op_sources);
+ if (local->transaction.changelog_xdata) {
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->transaction.changelog_xdata[i])
+ continue;
+ dict_unref(local->transaction.changelog_xdata[i]);
}
+ GF_FREE(local->transaction.changelog_xdata);
+ }
- GF_FREE (local->transaction.eager_lock);
- GF_FREE (local->transaction.fop_subvols);
- GF_FREE (local->transaction.failed_subvols);
-
- GF_FREE (local->transaction.basename);
- GF_FREE (local->transaction.new_basename);
+ GF_FREE(local->transaction.failed_subvols);
- loc_wipe (&local->transaction.parent_loc);
- loc_wipe (&local->transaction.new_parent_loc);
+ GF_FREE(local->transaction.basename);
+ GF_FREE(local->transaction.new_basename);
+ loc_wipe(&local->transaction.parent_loc);
+ loc_wipe(&local->transaction.new_parent_loc);
}
+void
+afr_reply_wipe(struct afr_reply *reply)
+{
+ if (reply->xdata) {
+ dict_unref(reply->xdata);
+ reply->xdata = NULL;
+ }
+
+ if (reply->xattr) {
+ dict_unref(reply->xattr);
+ reply->xattr = NULL;
+ }
+}
void
-afr_replies_wipe (struct afr_reply *replies, int count)
+afr_replies_wipe(struct afr_reply *replies, int count)
{
- int i = 0;
+ int i = 0;
- for (i = 0; i < count; i++) {
- if (replies[i].xdata) {
- dict_unref (replies[i].xdata);
- replies[i].xdata = NULL;
- }
- }
+ for (i = 0; i < count; i++) {
+ afr_reply_wipe(&replies[i]);
+ }
}
void
-afr_local_replies_wipe (afr_local_t *local, afr_private_t *priv)
+afr_local_replies_wipe(afr_local_t *local, afr_private_t *priv)
{
+ if (!local->replies)
+ return;
- if (!local->replies)
- return;
+ afr_replies_wipe(local->replies, priv->child_count);
- afr_replies_wipe (local->replies, priv->child_count);
+ memset(local->replies, 0, sizeof(*local->replies) * priv->child_count);
+}
- memset (local->replies, 0, sizeof(*local->replies) * priv->child_count);
+static gf_boolean_t
+afr_fop_lock_is_unlock(call_frame_t *frame)
+{
+ afr_local_t *local = frame->local;
+ switch (local->op) {
+ case GF_FOP_INODELK:
+ case GF_FOP_FINODELK:
+ if ((F_UNLCK == local->cont.inodelk.in_flock.l_type) &&
+ (local->cont.inodelk.in_cmd == F_SETLKW ||
+ local->cont.inodelk.in_cmd == F_SETLK))
+ return _gf_true;
+ break;
+ case GF_FOP_ENTRYLK:
+ case GF_FOP_FENTRYLK:
+ if (ENTRYLK_UNLOCK == local->cont.entrylk.in_cmd)
+ return _gf_true;
+ break;
+ default:
+ return _gf_false;
+ }
+ return _gf_false;
}
-void
-afr_remove_eager_lock_stub (afr_local_t *local)
+static gf_boolean_t
+afr_lk_is_unlock(int32_t cmd, struct gf_flock *flock)
{
- LOCK (&local->fd->lock);
- {
- list_del_init (&local->transaction.eager_locked);
- }
- UNLOCK (&local->fd->lock);
+ switch (cmd) {
+ case F_RESLK_UNLCK:
+ return _gf_true;
+ break;
+
+#if F_SETLKW != F_SETLKW64
+ case F_SETLKW64:
+#endif
+ case F_SETLKW:
+
+#if F_SETLK != F_SETLK64
+ case F_SETLK64:
+#endif
+ case F_SETLK:
+ if (F_UNLCK == flock->l_type)
+ return _gf_true;
+ break;
+ default:
+ return _gf_false;
+ }
+ return _gf_false;
}
void
-afr_local_cleanup (afr_local_t *local, xlator_t *this)
+afr_handle_inconsistent_fop(call_frame_t *frame, int32_t *op_ret,
+ int32_t *op_errno)
{
- afr_private_t * priv = NULL;
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
- if (!local)
- return;
+ if (!frame || !frame->this || !frame->local || !frame->this->private)
+ return;
- syncbarrier_destroy (&local->barrier);
+ if (*op_ret < 0)
+ return;
- if (local->transaction.eager_lock_on &&
- !list_empty (&local->transaction.eager_locked))
- afr_remove_eager_lock_stub (local);
+ /* Failing inodelk/entrylk/lk here is not a good idea because we
+ * need to cleanup the locks on the other bricks if we choose to fail
+ * the fop here. The brick may go down just after unwind happens as well
+ * so anyways the fop will fail when the next fop is sent so leaving
+ * it like this for now.*/
+ local = frame->local;
+ switch (local->op) {
+ case GF_FOP_LOOKUP:
+ case GF_FOP_INODELK:
+ case GF_FOP_FINODELK:
+ case GF_FOP_ENTRYLK:
+ case GF_FOP_FENTRYLK:
+ case GF_FOP_LK:
+ return;
+ default:
+ break;
+ }
- afr_local_transaction_cleanup (local, this);
+ priv = frame->this->private;
+ if (!priv->consistent_io)
+ return;
- priv = this->private;
+ if (local->event_generation &&
+ (local->event_generation != priv->event_generation))
+ goto inconsistent;
- loc_wipe (&local->loc);
- loc_wipe (&local->newloc);
+ return;
+inconsistent:
+ *op_ret = -1;
+ *op_errno = ENOTCONN;
+}
- if (local->fd)
- fd_unref (local->fd);
+void
+afr_local_cleanup(afr_local_t *local, xlator_t *this)
+{
+ afr_private_t *priv = NULL;
- if (local->xattr_req)
- dict_unref (local->xattr_req);
+ if (!local)
+ return;
- if (local->dict)
- dict_unref (local->dict);
+ syncbarrier_destroy(&local->barrier);
- afr_local_replies_wipe (local, priv);
- GF_FREE(local->replies);
+ afr_local_transaction_cleanup(local, this);
- GF_FREE (local->child_up);
+ priv = this->private;
- GF_FREE (local->read_attempted);
+ loc_wipe(&local->loc);
+ loc_wipe(&local->newloc);
- GF_FREE (local->readable);
+ if (local->fd)
+ fd_unref(local->fd);
- if (local->inode)
- inode_unref (local->inode);
+ if (local->xattr_req)
+ dict_unref(local->xattr_req);
- if (local->parent)
- inode_unref (local->parent);
+ if (local->xattr_rsp)
+ dict_unref(local->xattr_rsp);
- if (local->parent2)
- inode_unref (local->parent2);
+ if (local->dict)
+ dict_unref(local->dict);
- if (local->refreshinode)
- inode_unref (local->refreshinode);
+ afr_local_replies_wipe(local, priv);
+ GF_FREE(local->replies);
- { /* getxattr */
- GF_FREE (local->cont.getxattr.name);
- }
+ GF_FREE(local->child_up);
- { /* lk */
- GF_FREE (local->cont.lk.locked_nodes);
- }
+ GF_FREE(local->read_attempted);
+
+ GF_FREE(local->readable);
+ GF_FREE(local->readable2);
+
+ if (local->inode)
+ inode_unref(local->inode);
- { /* create */
- if (local->cont.create.fd)
- fd_unref (local->cont.create.fd);
- if (local->cont.create.params)
- dict_unref (local->cont.create.params);
- }
+ if (local->parent)
+ inode_unref(local->parent);
- { /* mknod */
- if (local->cont.mknod.params)
- dict_unref (local->cont.mknod.params);
- }
+ if (local->parent2)
+ inode_unref(local->parent2);
- { /* mkdir */
- if (local->cont.mkdir.params)
- dict_unref (local->cont.mkdir.params);
- }
+ if (local->refreshinode)
+ inode_unref(local->refreshinode);
- { /* symlink */
- if (local->cont.symlink.params)
- dict_unref (local->cont.symlink.params);
- }
+ { /* getxattr */
+ GF_FREE(local->cont.getxattr.name);
+ }
- { /* writev */
- GF_FREE (local->cont.writev.vector);
- if (local->cont.writev.iobref)
- iobref_unref (local->cont.writev.iobref);
- }
+ { /* lk */
+ GF_FREE(local->cont.lk.locked_nodes);
+ GF_FREE(local->cont.lk.dom_locked_nodes);
+ GF_FREE(local->cont.lk.dom_lock_op_ret);
+ GF_FREE(local->cont.lk.dom_lock_op_errno);
+ }
- { /* setxattr */
- if (local->cont.setxattr.dict)
- dict_unref (local->cont.setxattr.dict);
- }
+ { /* create */
+ if (local->cont.create.fd)
+ fd_unref(local->cont.create.fd);
+ if (local->cont.create.params)
+ dict_unref(local->cont.create.params);
+ }
- { /* fsetxattr */
- if (local->cont.fsetxattr.dict)
- dict_unref (local->cont.fsetxattr.dict);
- }
+ { /* mknod */
+ if (local->cont.mknod.params)
+ dict_unref(local->cont.mknod.params);
+ }
- { /* removexattr */
- GF_FREE (local->cont.removexattr.name);
- }
- { /* xattrop */
- if (local->cont.xattrop.xattr)
- dict_unref (local->cont.xattrop.xattr);
- }
- { /* fxattrop */
- if (local->cont.fxattrop.xattr)
- dict_unref (local->cont.fxattrop.xattr);
- }
- { /* symlink */
- GF_FREE (local->cont.symlink.linkpath);
- }
+ { /* mkdir */
+ if (local->cont.mkdir.params)
+ dict_unref(local->cont.mkdir.params);
+ }
- { /* opendir */
- GF_FREE (local->cont.opendir.checksum);
- }
+ { /* symlink */
+ if (local->cont.symlink.params)
+ dict_unref(local->cont.symlink.params);
+ }
- { /* readdirp */
- if (local->cont.readdir.dict)
- dict_unref (local->cont.readdir.dict);
- }
+ { /* writev */
+ GF_FREE(local->cont.writev.vector);
+ if (local->cont.writev.iobref)
+ iobref_unref(local->cont.writev.iobref);
+ }
- { /* inodelk */
- GF_FREE (local->cont.inodelk.volume);
- }
+ { /* setxattr */
+ if (local->cont.setxattr.dict)
+ dict_unref(local->cont.setxattr.dict);
+ }
- if (local->xdata_req)
- dict_unref (local->xdata_req);
+ { /* fsetxattr */
+ if (local->cont.fsetxattr.dict)
+ dict_unref(local->cont.fsetxattr.dict);
+ }
- if (local->xdata_rsp)
- dict_unref (local->xdata_rsp);
-}
+ { /* removexattr */
+ GF_FREE(local->cont.removexattr.name);
+ }
+ { /* xattrop */
+ if (local->cont.xattrop.xattr)
+ dict_unref(local->cont.xattrop.xattr);
+ }
+ { /* symlink */
+ GF_FREE(local->cont.symlink.linkpath);
+ }
+ { /* opendir */
+ GF_FREE(local->cont.opendir.checksum);
+ }
+
+ { /* open */
+ if (local->cont.open.fd)
+ fd_unref(local->cont.open.fd);
+ }
+
+ { /* readdirp */
+ if (local->cont.readdir.dict)
+ dict_unref(local->cont.readdir.dict);
+ }
+
+ { /* inodelk */
+ GF_FREE(local->cont.inodelk.volume);
+ if (local->cont.inodelk.xdata)
+ dict_unref(local->cont.inodelk.xdata);
+ }
+
+ { /* entrylk */
+ GF_FREE(local->cont.entrylk.volume);
+ GF_FREE(local->cont.entrylk.basename);
+ if (local->cont.entrylk.xdata)
+ dict_unref(local->cont.entrylk.xdata);
+ }
+
+ if (local->xdata_req)
+ dict_unref(local->xdata_req);
+
+ if (local->xdata_rsp)
+ dict_unref(local->xdata_rsp);
+}
int
-afr_frame_return (call_frame_t *frame)
+afr_frame_return(call_frame_t *frame)
{
- afr_local_t *local = NULL;
- int call_count = 0;
+ afr_local_t *local = NULL;
+ int call_count = 0;
- local = frame->local;
+ local = frame->local;
- LOCK (&frame->lock);
- {
- call_count = --local->call_count;
- }
- UNLOCK (&frame->lock);
+ LOCK(&frame->lock);
+ {
+ call_count = --local->call_count;
+ }
+ UNLOCK(&frame->lock);
- return call_count;
+ return call_count;
}
+static char *afr_ignore_xattrs[] = {GF_SELINUX_XATTR_KEY, QUOTA_SIZE_KEY, NULL};
gf_boolean_t
-afr_is_entry_possibly_under_txn (afr_local_t *local, xlator_t *this)
+afr_is_xattr_ignorable(char *key)
{
- int i = 0;
- int tmp = 0;
- afr_private_t *priv = NULL;
+ int i = 0;
- priv = this->private;
-
- for (i = 0; i < priv->child_count; i++) {
- if (!local->replies[i].xdata)
- continue;
- if (dict_get_int32 (local->replies[i].xdata,
- GLUSTERFS_PARENT_ENTRYLK,
- &tmp) == 0)
- if (tmp)
- return _gf_true;
- }
-
- return _gf_false;
+ if (!strncmp(key, AFR_XATTR_PREFIX, SLEN(AFR_XATTR_PREFIX)))
+ return _gf_true;
+ for (i = 0; afr_ignore_xattrs[i]; i++) {
+ if (!strcmp(key, afr_ignore_xattrs[i]))
+ return _gf_true;
+ }
+ return _gf_false;
}
+static gf_boolean_t
+afr_xattr_match_needed(dict_t *this, char *key1, data_t *value1, void *data)
+{
+ /* Ignore all non-disk (i.e. virtual) xattrs right away. */
+ if (!gf_is_valid_xattr_namespace(key1))
+ return _gf_false;
-static char *afr_ignore_xattrs[] = {
- GLUSTERFS_OPEN_FD_COUNT,
- GLUSTERFS_PARENT_ENTRYLK,
- GLUSTERFS_ENTRYLK_COUNT,
- GLUSTERFS_INODELK_COUNT,
- GF_SELINUX_XATTR_KEY,
- QUOTA_SIZE_KEY,
- NULL
-};
+ /* Ignore on-disk xattrs that AFR doesn't need to heal. */
+ if (!afr_is_xattr_ignorable(key1))
+ return _gf_true;
+
+ return _gf_false;
+}
gf_boolean_t
-afr_is_xattr_ignorable (char *key)
+afr_xattrs_are_equal(dict_t *dict1, dict_t *dict2)
{
- int i = 0;
+ return are_dicts_equal(dict1, dict2, afr_xattr_match_needed, NULL);
+}
- if (!strncmp (key, AFR_XATTR_PREFIX, strlen(AFR_XATTR_PREFIX)))
- return _gf_true;
- for (i = 0; afr_ignore_xattrs[i]; i++) {
- if (!strcmp (key, afr_ignore_xattrs[i]))
- return _gf_true;
+static int
+afr_get_parent_read_subvol(xlator_t *this, inode_t *parent,
+ struct afr_reply *replies, unsigned char *readable)
+{
+ int i = 0;
+ int par_read_subvol = -1;
+ int par_read_subvol_iter = -1;
+ afr_private_t *priv = NULL;
+
+ priv = this->private;
+
+ if (parent)
+ par_read_subvol = afr_data_subvol_get(parent, this, NULL, NULL, NULL,
+ NULL);
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (!replies[i].valid)
+ continue;
+
+ if (replies[i].op_ret < 0)
+ continue;
+
+ if (par_read_subvol_iter == -1) {
+ par_read_subvol_iter = i;
+ continue;
}
- return _gf_false;
+
+ if ((par_read_subvol_iter != par_read_subvol) && readable[i])
+ par_read_subvol_iter = i;
+
+ if (i == par_read_subvol)
+ par_read_subvol_iter = i;
+ }
+ /* At the end of the for-loop, the only reason why @par_read_subvol_iter
+ * could be -1 is when this LOOKUP has failed on all sub-volumes.
+ * So it is okay to send an arbitrary subvolume (0 in this case)
+ * as parent read subvol.
+ */
+ if (par_read_subvol_iter == -1)
+ par_read_subvol_iter = 0;
+
+ return par_read_subvol_iter;
}
-static gf_boolean_t
-afr_xattr_match (dict_t *this, char *key1, data_t *value1, void *data)
+int
+afr_read_subvol_decide(inode_t *inode, xlator_t *this,
+ afr_read_subvol_args_t *args, unsigned char *readable)
{
- if (!afr_is_xattr_ignorable (key1))
- return _gf_true;
+ int event = 0;
+ afr_private_t *priv = NULL;
+ unsigned char *intersection = NULL;
- return _gf_false;
+ priv = this->private;
+ intersection = alloca0(priv->child_count);
+
+ afr_readables_intersect_get(inode, this, &event, intersection);
+
+ if (AFR_COUNT(intersection, priv->child_count) <= 0) {
+ /* TODO: If we have one brick with valid data_readable and
+ * another with metadata_readable, try to send an iatt with
+ * valid bits from both.*/
+ return -1;
+ }
+
+ memcpy(readable, intersection, sizeof(*readable) * priv->child_count);
+
+ return afr_read_subvol_select_by_policy(inode, this, intersection, args);
}
-gf_boolean_t
-afr_xattrs_are_equal (dict_t *dict1, dict_t *dict2)
+static inline int
+afr_first_up_child(call_frame_t *frame, xlator_t *this)
{
- return are_dicts_equal (dict1, dict2, afr_xattr_match, NULL);
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ int i = 0;
+
+ local = frame->local;
+ priv = this->private;
+
+ for (i = 0; i < priv->child_count; i++)
+ if (local->replies[i].valid && local->replies[i].op_ret == 0)
+ return i;
+ return -1;
}
-static int
-afr_get_parent_read_subvol (xlator_t *this, inode_t *parent,
- struct afr_reply *replies, unsigned char *readable)
+static void
+afr_attempt_readsubvol_set(call_frame_t *frame, xlator_t *this,
+ unsigned char *success_replies,
+ unsigned char *data_readable, int *read_subvol)
{
- int i = 0;
- int par_read_subvol = -1;
- int par_read_subvol_iter = -1;
- afr_private_t *priv = NULL;
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ int spb_subvol = -1;
+ int child_count = -1;
- priv = this->private;
+ if (*read_subvol != -1)
+ return;
- if (parent)
- par_read_subvol = afr_data_subvol_get (parent, this, 0, 0,
- NULL);
+ priv = this->private;
+ local = frame->local;
+ child_count = priv->child_count;
+
+ afr_split_brain_read_subvol_get(local->inode, this, frame, &spb_subvol);
+ if ((spb_subvol >= 0) &&
+ (AFR_COUNT(success_replies, child_count) == child_count)) {
+ *read_subvol = spb_subvol;
+ } else if (!priv->quorum_count ||
+ frame->root->pid == GF_CLIENT_PID_GLFS_HEAL) {
+ *read_subvol = afr_first_up_child(frame, this);
+ } else if (priv->quorum_count &&
+ afr_has_quorum(data_readable, this, NULL)) {
+ /* read_subvol is guaranteed to be valid if we hit this path. */
+ *read_subvol = afr_first_up_child(frame, this);
+ } else {
+ /* If quorum is enabled and we do not have a
+ readable yet, it means all good copies are down.
+ */
+ local->op_ret = -1;
+ local->op_errno = ENOTCONN;
+ gf_msg(this->name, GF_LOG_WARNING, 0, AFR_MSG_READ_SUBVOL_ERROR,
+ "no read "
+ "subvols for %s",
+ local->loc.path);
+ }
+ if (*read_subvol >= 0)
+ dict_del_sizen(local->replies[*read_subvol].xdata, GF_CONTENT_KEY);
+}
- for (i = 0; i < priv->child_count; i++) {
- if (!replies[i].valid)
- continue;
+static void
+afr_lookup_done(call_frame_t *frame, xlator_t *this)
+{
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ int i = -1;
+ int op_errno = 0;
+ int read_subvol = 0;
+ int par_read_subvol = 0;
+ int ret = -1;
+ unsigned char *readable = NULL;
+ unsigned char *success_replies = NULL;
+ int event = 0;
+ struct afr_reply *replies = NULL;
+ uuid_t read_gfid = {
+ 0,
+ };
+ gf_boolean_t locked_entry = _gf_false;
+ gf_boolean_t in_flight_create = _gf_false;
+ gf_boolean_t can_interpret = _gf_true;
+ inode_t *parent = NULL;
+ ia_type_t ia_type = IA_INVAL;
+ afr_read_subvol_args_t args = {
+ 0,
+ };
+ char *gfid_heal_msg = NULL;
+
+ priv = this->private;
+ local = frame->local;
+ replies = local->replies;
+ parent = local->loc.parent;
+
+ locked_entry = afr_is_possibly_under_txn(AFR_ENTRY_TRANSACTION, local,
+ this);
+
+ readable = alloca0(priv->child_count);
+ success_replies = alloca0(priv->child_count);
+
+ afr_inode_read_subvol_get(parent, this, readable, NULL, &event);
+ par_read_subvol = afr_get_parent_read_subvol(this, parent, replies,
+ readable);
+
+ /* First, check if we have a gfid-change from somewhere,
+ If so, propagate that so that a fresh lookup can be
+ issued
+ */
+ if (local->cont.lookup.needs_fresh_lookup) {
+ local->op_ret = -1;
+ local->op_errno = ESTALE;
+ goto error;
+ }
- if (replies[i].op_ret < 0)
- continue;
+ op_errno = afr_final_errno(frame->local, this->private);
+ local->op_errno = op_errno;
- if (par_read_subvol_iter == -1) {
- par_read_subvol_iter = i;
- continue;
- }
+ read_subvol = -1;
+ afr_fill_success_replies(local, priv, success_replies);
- if ((par_read_subvol_iter != par_read_subvol) && readable[i])
- par_read_subvol_iter = i;
+ for (i = 0; i < priv->child_count; i++) {
+ if (!replies[i].valid)
+ continue;
- if (i == par_read_subvol)
- par_read_subvol_iter = i;
+ if (replies[i].op_ret == -1) {
+ if (locked_entry && replies[i].op_errno == ENOENT) {
+ in_flight_create = _gf_true;
+ }
+ continue;
}
- /* At the end of the for-loop, the only reason why @par_read_subvol_iter
- * could be -1 is when this LOOKUP has failed on all sub-volumes.
- * So it is okay to send an arbitrary subvolume (0 in this case)
- * as parent read subvol.
- */
- if (par_read_subvol_iter == -1)
- par_read_subvol_iter = 0;
- return par_read_subvol_iter;
-
-}
+ if (read_subvol == -1 || !readable[read_subvol]) {
+ read_subvol = i;
+ gf_uuid_copy(read_gfid, replies[i].poststat.ia_gfid);
+ ia_type = replies[i].poststat.ia_type;
+ local->op_ret = 0;
+ }
+ }
-static void
-afr_lookup_done (call_frame_t *frame, xlator_t *this)
-{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int i = -1;
- int op_errno = 0;
- int read_subvol = 0;
- int par_read_subvol = 0;
- unsigned char *readable = NULL;
- int event = 0;
- struct afr_reply *replies = NULL;
- uuid_t read_gfid = {0, };
- gf_boolean_t locked_entry = _gf_false;
- gf_boolean_t can_interpret = _gf_true;
- inode_t *parent = NULL;
- int spb_choice = -1;
- ia_type_t ia_type = IA_INVAL;
- afr_read_subvol_args_t args = {0,};
-
- priv = this->private;
- local = frame->local;
- replies = local->replies;
- parent = local->loc.parent;
-
- locked_entry = afr_is_entry_possibly_under_txn (local, this);
-
- readable = alloca0 (priv->child_count);
-
- afr_inode_read_subvol_get (parent, this, readable, NULL, &event);
-
- afr_inode_split_brain_choice_get (local->inode, this,
- &spb_choice);
- /* First, check if we have a gfid-change from somewhere,
- If so, propagate that so that a fresh lookup can be
- issued
- */
- if (local->cont.lookup.needs_fresh_lookup) {
- local->op_ret = -1;
- local->op_errno = ESTALE;
- goto unwind;
- }
-
- op_errno = afr_final_errno (frame->local, this->private);
- local->op_errno = op_errno;
-
- read_subvol = -1;
- for (i = 0; i < priv->child_count; i++) {
- if (!replies[i].valid)
- continue;
-
- if (locked_entry && replies[i].op_ret == -1 &&
- replies[i].op_errno == ENOENT) {
- /* Second, check entry is still
- "underway" in creation */
- local->op_ret = -1;
- local->op_errno = ENOENT;
- goto unwind;
- }
-
- if (replies[i].op_ret == -1)
- continue;
-
- if (read_subvol == -1 || !readable[read_subvol]) {
- read_subvol = i;
- gf_uuid_copy (read_gfid, replies[i].poststat.ia_gfid);
- ia_type = replies[i].poststat.ia_type;
- local->op_ret = 0;
- }
- }
-
- if (read_subvol == -1)
- goto unwind;
- /* We now have a read_subvol, which is readable[] (if there
- were any). Next we look for GFID mismatches. We don't
- consider a GFID mismatch as an error if read_subvol is
- readable[] but the mismatching GFID subvol is not.
- */
- for (i = 0; i < priv->child_count; i++) {
- if (!replies[i].valid || replies[i].op_ret == -1) {
- if (priv->child_up[i])
- can_interpret = _gf_false;
- continue;
- }
-
- if (!gf_uuid_compare (replies[i].poststat.ia_gfid, read_gfid))
- continue;
-
- can_interpret = _gf_false;
-
- if (locked_entry)
- continue;
-
- /* Now GFIDs mismatch. It's OK as long as this subvol
- is not readable[] but read_subvol is */
- if (readable[read_subvol] && !readable[i])
- continue;
-
- /* LOG ERROR */
- local->op_ret = -1;
- local->op_errno = EIO;
- goto unwind;
- }
-
- /* Forth, for the finalized GFID, pick the best subvolume
- to return stats from.
- */
- if (can_interpret) {
- /* It is safe to call afr_replies_interpret() because we have
- a response from all the UP subvolumes and all of them resolved
- to the same GFID
- */
- gf_uuid_copy (args.gfid, read_gfid);
- args.ia_type = ia_type;
- if (afr_replies_interpret (frame, this, local->inode)) {
- read_subvol = afr_data_subvol_get (local->inode, this,
- 0, 0, &args);
- afr_inode_read_subvol_reset (local->inode, this);
- goto cant_interpret;
- } else {
- read_subvol = afr_data_subvol_get (local->inode, this,
- 0, 0, &args);
- }
- } else {
- cant_interpret:
- if (read_subvol == -1) {
- if (spb_choice >= 0)
- read_subvol = spb_choice;
- else
- read_subvol = 0;
- }
- dict_del (replies[read_subvol].xdata, GF_CONTENT_KEY);
- }
+ if (in_flight_create && !afr_has_quorum(success_replies, this, NULL)) {
+ local->op_ret = -1;
+ local->op_errno = ENOENT;
+ goto error;
+ }
+
+ if (read_subvol == -1)
+ goto error;
+ /* We now have a read_subvol, which is readable[] (if there
+ were any). Next we look for GFID mismatches. We don't
+ consider a GFID mismatch as an error if read_subvol is
+ readable[] but the mismatching GFID subvol is not.
+ */
+ for (i = 0; i < priv->child_count; i++) {
+ if (!replies[i].valid || replies[i].op_ret == -1) {
+ continue;
+ }
+
+ if (!gf_uuid_compare(replies[i].poststat.ia_gfid, read_gfid))
+ continue;
+
+ can_interpret = _gf_false;
+
+ if (locked_entry)
+ continue;
+
+ /* Now GFIDs mismatch. It's OK as long as this subvol
+ is not readable[] but read_subvol is */
+ if (readable[read_subvol] && !readable[i])
+ continue;
+
+ /* If we were called from glfsheal and there is still a gfid
+ * mismatch, succeed the lookup and let glfsheal print the
+ * response via gfid-heal-msg.*/
+ if (!dict_get_str_sizen(local->xattr_req, "gfid-heal-msg",
+ &gfid_heal_msg))
+ goto cant_interpret;
+
+ /* LOG ERROR */
+ local->op_ret = -1;
+ local->op_errno = EIO;
+ goto error;
+ }
+
+ /* Forth, for the finalized GFID, pick the best subvolume
+ to return stats from.
+ */
+ read_subvol = -1;
+ memset(readable, 0, sizeof(*readable) * priv->child_count);
+ if (can_interpret) {
+ if (!afr_has_quorum(success_replies, this, NULL))
+ goto cant_interpret;
+ /* It is safe to call afr_replies_interpret() because we have
+ a response from all the UP subvolumes and all of them resolved
+ to the same GFID
+ */
+ gf_uuid_copy(args.gfid, read_gfid);
+ args.ia_type = ia_type;
+ ret = afr_replies_interpret(frame, this, local->inode, NULL);
+ read_subvol = afr_read_subvol_decide(local->inode, this, &args,
+ readable);
+ if (read_subvol == -1)
+ goto cant_interpret;
+ if (ret) {
+ afr_inode_need_refresh_set(local->inode, this);
+ dict_del_sizen(local->replies[read_subvol].xdata, GF_CONTENT_KEY);
+ }
+ } else {
+ cant_interpret:
+ afr_attempt_readsubvol_set(frame, this, success_replies, readable,
+ &read_subvol);
+ if (read_subvol == -1) {
+ goto error;
+ }
+ }
- afr_handle_quota_size (frame, this);
+ afr_handle_quota_size(frame, this);
-unwind:
- if (read_subvol == -1) {
- if (spb_choice >= 0)
- read_subvol = spb_choice;
- else
- read_subvol = 0;
+ afr_set_need_heal(this, local);
+ if (AFR_IS_ARBITER_BRICK(priv, read_subvol) && local->op_ret == 0) {
+ local->op_ret = -1;
+ local->op_errno = ENOTCONN;
+ gf_msg_debug(this->name, 0,
+ "Arbiter cannot be a read subvol "
+ "for %s",
+ local->loc.path);
+ goto error;
+ }
+
+ ret = dict_get_str_sizen(local->xattr_req, "gfid-heal-msg", &gfid_heal_msg);
+ if (!ret) {
+ ret = dict_set_str_sizen(local->replies[read_subvol].xdata,
+ "gfid-heal-msg", gfid_heal_msg);
+ if (ret) {
+ gf_msg(this->name, GF_LOG_ERROR, 0, AFR_MSG_DICT_SET_FAILED,
+ "Error setting gfid-heal-msg dict");
+ local->op_ret = -1;
+ local->op_errno = ENOMEM;
}
- par_read_subvol = afr_get_parent_read_subvol (this, parent, replies,
- readable);
+ }
+
+ AFR_STACK_UNWIND(lookup, frame, local->op_ret, local->op_errno,
+ local->inode, &local->replies[read_subvol].poststat,
+ local->replies[read_subvol].xdata,
+ &local->replies[par_read_subvol].postparent);
+ return;
- AFR_STACK_UNWIND (lookup, frame, local->op_ret, local->op_errno,
- local->inode, &local->replies[read_subvol].poststat,
- local->replies[read_subvol].xdata,
- &local->replies[par_read_subvol].postparent);
+error:
+ AFR_STACK_UNWIND(lookup, frame, local->op_ret, local->op_errno, NULL, NULL,
+ NULL, NULL);
}
/*
@@ -1665,615 +3122,845 @@ unwind:
* others in that they must be given higher priority while
* returning to the user.
*
- * The hierarchy is ENODATA > ENOENT > ESTALE > others
+ * The hierarchy is ENODATA > ENOENT > ESTALE > ENOSPC others
*/
int
-afr_higher_errno (int32_t old_errno, int32_t new_errno)
+afr_higher_errno(int32_t old_errno, int32_t new_errno)
{
- if (old_errno == ENODATA || new_errno == ENODATA)
- return ENODATA;
- if (old_errno == ENOENT || new_errno == ENOENT)
- return ENOENT;
- if (old_errno == ESTALE || new_errno == ESTALE)
- return ESTALE;
+ if (old_errno == ENODATA || new_errno == ENODATA)
+ return ENODATA;
+ if (old_errno == ENOENT || new_errno == ENOENT)
+ return ENOENT;
+ if (old_errno == ESTALE || new_errno == ESTALE)
+ return ESTALE;
+ if (old_errno == ENOSPC || new_errno == ENOSPC)
+ return ENOSPC;
- return new_errno;
+ return new_errno;
}
-
int
-afr_final_errno (afr_local_t *local, afr_private_t *priv)
+afr_final_errno(afr_local_t *local, afr_private_t *priv)
{
- int i = 0;
- int op_errno = 0;
- int tmp_errno = 0;
+ int i = 0;
+ int op_errno = 0;
+ int tmp_errno = 0;
- for (i = 0; i < priv->child_count; i++) {
- if (!local->replies[i].valid)
- continue;
- if (local->replies[i].op_ret >= 0)
- continue;
- tmp_errno = local->replies[i].op_errno;
- op_errno = afr_higher_errno (op_errno, tmp_errno);
- }
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->replies[i].valid)
+ continue;
+ if (local->replies[i].op_ret >= 0)
+ continue;
+ tmp_errno = local->replies[i].op_errno;
+ op_errno = afr_higher_errno(op_errno, tmp_errno);
+ }
- return op_errno;
+ return op_errno;
}
static int32_t
-afr_local_discovery_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, dict_t *dict,
- dict_t *xdata)
-{
- int ret = 0;
- char *pathinfo = NULL;
- gf_boolean_t is_local = _gf_false;
- afr_private_t *priv = NULL;
- int32_t child_index = -1;
-
- if (op_ret != 0) {
- goto out;
- }
-
- priv = this->private;
- child_index = (int32_t)(long)cookie;
-
- ret = dict_get_str (dict, GF_XATTR_PATHINFO_KEY, &pathinfo);
- if (ret != 0) {
- goto out;
- }
-
- ret = glusterfs_is_local_pathinfo (pathinfo, &is_local);
- if (ret) {
- goto out;
- }
-
- /*
- * Note that one local subvolume will override another here. The only
- * way to avoid that would be to retain extra information about whether
- * the previous read_child is local, and it's just not worth it. Even
- * the slowest local subvolume is far preferable to a remote one.
- */
- if (is_local) {
- /* Don't set arbiter as read child. */
- if ((priv->arbiter_count == 1) &&
- (child_index == ARBITER_BRICK_INDEX))
- goto out;
- gf_msg (this->name, GF_LOG_INFO, 0,
- AFR_MSG_LOCAL_CHILD, "selecting local read_child %s",
- priv->children[child_index]->name);
-
- priv->read_child = child_index;
- }
+afr_local_discovery_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *dict,
+ dict_t *xdata)
+{
+ int ret = 0;
+ char *pathinfo = NULL;
+ gf_boolean_t is_local = _gf_false;
+ afr_private_t *priv = NULL;
+ int32_t child_index = -1;
+
+ if (op_ret != 0) {
+ goto out;
+ }
+
+ priv = this->private;
+ child_index = (int32_t)(long)cookie;
+
+ ret = dict_get_str_sizen(dict, GF_XATTR_PATHINFO_KEY, &pathinfo);
+ if (ret != 0) {
+ goto out;
+ }
+
+ ret = glusterfs_is_local_pathinfo(pathinfo, &is_local);
+ if (ret) {
+ goto out;
+ }
+
+ /*
+ * Note that one local subvolume will override another here. The only
+ * way to avoid that would be to retain extra information about whether
+ * the previous read_child is local, and it's just not worth it. Even
+ * the slowest local subvolume is far preferable to a remote one.
+ */
+ if (is_local) {
+ priv->local[child_index] = 1;
+ /* Don't set arbiter as read child. */
+ if (AFR_IS_ARBITER_BRICK(priv, child_index))
+ goto out;
+ gf_msg(this->name, GF_LOG_INFO, 0, AFR_MSG_LOCAL_CHILD,
+ "selecting local read_child %s",
+ priv->children[child_index]->name);
+
+ priv->read_child = child_index;
+ }
out:
- STACK_DESTROY(frame->root);
- return 0;
+ STACK_DESTROY(frame->root);
+ return 0;
}
static void
-afr_attempt_local_discovery (xlator_t *this, int32_t child_index)
+afr_attempt_local_discovery(xlator_t *this, int32_t child_index)
{
- call_frame_t *newframe = NULL;
- loc_t tmploc = {0,};
- afr_private_t *priv = this->private;
+ call_frame_t *newframe = NULL;
+ loc_t tmploc = {
+ 0,
+ };
+ afr_private_t *priv = this->private;
- newframe = create_frame(this,this->ctx->pool);
- if (!newframe) {
- return;
- }
+ newframe = create_frame(this, this->ctx->pool);
+ if (!newframe) {
+ return;
+ }
- tmploc.gfid[sizeof(tmploc.gfid)-1] = 1;
- STACK_WIND_COOKIE (newframe, afr_local_discovery_cbk,
- (void *)(long)child_index,
- priv->children[child_index],
- priv->children[child_index]->fops->getxattr,
- &tmploc, GF_XATTR_PATHINFO_KEY, NULL);
+ tmploc.gfid[sizeof(tmploc.gfid) - 1] = 1;
+ STACK_WIND_COOKIE(newframe, afr_local_discovery_cbk,
+ (void *)(long)child_index, priv->children[child_index],
+ priv->children[child_index]->fops->getxattr, &tmploc,
+ GF_XATTR_PATHINFO_KEY, NULL);
}
int
-afr_lookup_sh_metadata_wrap (void *opaque)
+afr_lookup_sh_metadata_wrap(void *opaque)
+{
+ call_frame_t *frame = opaque;
+ afr_local_t *local = NULL;
+ xlator_t *this = NULL;
+ inode_t *inode = NULL;
+ afr_private_t *priv = NULL;
+ struct afr_reply *replies = NULL;
+ int i = 0, first = -1;
+ int ret = -1;
+ dict_t *dict = NULL;
+
+ local = frame->local;
+ this = frame->this;
+ priv = this->private;
+ replies = local->replies;
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (!replies[i].valid || replies[i].op_ret == -1)
+ continue;
+ first = i;
+ break;
+ }
+ if (first == -1)
+ goto out;
+
+ if (afr_selfheal_metadata_by_stbuf(this, &replies[first].poststat))
+ goto out;
+
+ afr_local_replies_wipe(local, this->private);
+
+ dict = dict_new();
+ if (!dict)
+ goto out;
+ if (local->xattr_req) {
+ dict_copy(local->xattr_req, dict);
+ }
+
+ ret = dict_set_sizen_str_sizen(dict, "link-count", GF_XATTROP_INDEX_COUNT);
+ if (ret) {
+ gf_msg_debug(this->name, -ret, "Unable to set link-count in dict ");
+ }
+
+ if (loc_is_nameless(&local->loc)) {
+ ret = afr_selfheal_unlocked_discover_on(frame, local->inode,
+ local->loc.gfid, local->replies,
+ local->child_up, dict);
+ } else {
+ inode = afr_selfheal_unlocked_lookup_on(frame, local->loc.parent,
+ local->loc.name, local->replies,
+ local->child_up, dict);
+ }
+ if (inode)
+ inode_unref(inode);
+out:
+ if (loc_is_nameless(&local->loc))
+ afr_discover_done(frame, this);
+ else
+ afr_lookup_done(frame, this);
+
+ if (dict)
+ dict_unref(dict);
+
+ return 0;
+}
+
+gf_boolean_t
+afr_is_pending_set(xlator_t *this, dict_t *xdata, int type)
{
- call_frame_t *frame = opaque;
- afr_local_t *local = NULL;
- xlator_t *this = NULL;
- inode_t *inode = NULL;
- afr_private_t *priv = NULL;
- struct afr_reply *replies = NULL;
- int i= 0, first = -1;
+ int idx = -1;
+ afr_private_t *priv = NULL;
+ void *pending_raw = NULL;
+ int *pending_int = NULL;
+ int i = 0;
- local = frame->local;
- this = frame->this;
- priv = this->private;
- replies = local->replies;
-
- for (i =0; i < priv->child_count; i++) {
- if(!replies[i].valid || replies[i].op_ret == -1)
- continue;
- first = i;
- break;
- }
- if (first == -1)
- goto out;
+ priv = this->private;
+ idx = afr_index_for_transaction_type(type);
- inode = afr_inode_link (local->inode,&replies[first].poststat);
- if(!inode)
- goto out;
+ if (dict_get_ptr(xdata, AFR_DIRTY, &pending_raw) == 0) {
+ if (pending_raw) {
+ pending_int = pending_raw;
- afr_selfheal_metadata (frame, this, inode);
- inode_forget (inode, 1);
- inode_unref (inode);
+ if (ntoh32(pending_int[idx]))
+ return _gf_true;
+ }
+ }
- afr_local_replies_wipe (local, this->private);
- inode = afr_selfheal_unlocked_lookup_on (frame, local->loc.parent,
- local->loc.name, local->replies,
- local->child_up, NULL);
- if (inode)
- inode_unref (inode);
-out:
- afr_lookup_done (frame, this);
+ for (i = 0; i < priv->child_count; i++) {
+ if (dict_get_ptr(xdata, priv->pending_key[i], &pending_raw))
+ continue;
+ if (!pending_raw)
+ continue;
+ pending_int = pending_raw;
- return 0;
+ if (ntoh32(pending_int[idx]))
+ return _gf_true;
+ }
+
+ return _gf_false;
}
static gf_boolean_t
afr_can_start_metadata_self_heal(call_frame_t *frame, xlator_t *this)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- struct afr_reply *replies = NULL;
- int i = 0, first = -1;
- gf_boolean_t start = _gf_false;
- struct iatt stbuf = {0, };
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ struct afr_reply *replies = NULL;
+ int i = 0, first = -1;
+ gf_boolean_t start = _gf_false;
+ struct iatt stbuf = {
+ 0,
+ };
- local = frame->local;
- replies = local->replies;
- priv = this->private;
+ local = frame->local;
+ replies = local->replies;
+ priv = this->private;
- if (!priv->metadata_self_heal)
- return _gf_false;
+ if (!priv->metadata_self_heal)
+ return _gf_false;
- for (i = 0; i < priv->child_count; i++) {
- if(!replies[i].valid || replies[i].op_ret == -1)
- continue;
- if (first == -1) {
- first = i;
- stbuf = replies[i].poststat;
- continue;
- }
+ for (i = 0; i < priv->child_count; i++) {
+ if (!replies[i].valid || replies[i].op_ret == -1)
+ continue;
+ if (first == -1) {
+ first = i;
+ stbuf = replies[i].poststat;
+ continue;
+ }
- if (gf_uuid_compare (stbuf.ia_gfid, replies[i].poststat.ia_gfid)) {
- start = _gf_false;
- break;
- }
- if (!IA_EQUAL (stbuf, replies[i].poststat, type)) {
- start = _gf_false;
- break;
- }
+ if (afr_is_pending_set(this, replies[i].xdata,
+ AFR_METADATA_TRANSACTION)) {
+ /* Let shd do the heal so that lookup is not blocked
+ * on getting metadata lock/doing the heal */
+ start = _gf_false;
+ break;
+ }
- /*Check if iattrs need heal*/
- if ((!IA_EQUAL (stbuf, replies[i].poststat, uid)) ||
- (!IA_EQUAL (stbuf, replies[i].poststat, gid)) ||
- (!IA_EQUAL (stbuf, replies[i].poststat, prot))) {
- start = _gf_true;
- continue;
- }
+ if (gf_uuid_compare(stbuf.ia_gfid, replies[i].poststat.ia_gfid)) {
+ start = _gf_false;
+ break;
+ }
+ if (!IA_EQUAL(stbuf, replies[i].poststat, type)) {
+ start = _gf_false;
+ break;
+ }
- /*Check if xattrs need heal*/
- if (!afr_xattrs_are_equal (replies[first].xdata,
- replies[i].xdata))
- start = _gf_true;
+ /*Check if iattrs need heal*/
+ if ((!IA_EQUAL(stbuf, replies[i].poststat, uid)) ||
+ (!IA_EQUAL(stbuf, replies[i].poststat, gid)) ||
+ (!IA_EQUAL(stbuf, replies[i].poststat, prot))) {
+ start = _gf_true;
+ continue;
}
- return start;
+ /*Check if xattrs need heal*/
+ if (!afr_xattrs_are_equal(replies[first].xdata, replies[i].xdata))
+ start = _gf_true;
+ }
+
+ return start;
}
int
-afr_lookup_metadata_heal_check (call_frame_t *frame, xlator_t *this)
+afr_lookup_metadata_heal_check(call_frame_t *frame, xlator_t *this)
{
- call_frame_t *heal = NULL;
- int ret = 0;
+ call_frame_t *heal = NULL;
+ afr_local_t *local = NULL;
+ int ret = 0;
- if (!afr_can_start_metadata_self_heal (frame, this))
- goto out;
+ local = frame->local;
+ if (!afr_can_start_metadata_self_heal(frame, this))
+ goto out;
- heal = copy_frame (frame);
- if (heal)
- heal->root->pid = GF_CLIENT_PID_AFR_SELF_HEALD;
- ret = synctask_new (this->ctx->env, afr_lookup_sh_metadata_wrap,
- afr_refresh_selfheal_done, heal, frame);
- if(ret)
- goto out;
- return ret;
+ heal = afr_frame_create(this, &ret);
+ if (!heal) {
+ ret = -ret;
+ goto out;
+ }
+
+ ret = synctask_new(this->ctx->env, afr_lookup_sh_metadata_wrap,
+ afr_refresh_selfheal_done, heal, frame);
+ if (ret)
+ goto out;
+ return ret;
out:
- afr_lookup_done (frame, this);
- return ret;
+ if (loc_is_nameless(&local->loc))
+ afr_discover_done(frame, this);
+ else
+ afr_lookup_done(frame, this);
+ if (heal)
+ AFR_STACK_DESTROY(heal);
+ return ret;
}
int
-afr_lookup_selfheal_wrap (void *opaque)
+afr_lookup_selfheal_wrap(void *opaque)
{
- int ret = 0;
- call_frame_t *frame = opaque;
- afr_local_t *local = NULL;
- xlator_t *this = NULL;
- inode_t *inode = NULL;
+ int ret = 0;
+ call_frame_t *frame = opaque;
+ afr_local_t *local = NULL;
+ xlator_t *this = NULL;
+ inode_t *inode = NULL;
+ uuid_t pargfid = {
+ 0,
+ };
- local = frame->local;
- this = frame->this;
+ local = frame->local;
+ this = frame->this;
+ loc_pargfid(&local->loc, pargfid);
- ret = afr_selfheal_name (frame->this, local->loc.pargfid,
- local->loc.name, &local->cont.lookup.gfid_req);
- if (ret == -EIO)
- goto unwind;
+ ret = afr_selfheal_name(frame->this, pargfid, local->loc.name,
+ &local->cont.lookup.gfid_req, local->xattr_req);
+ if (ret == -EIO)
+ goto unwind;
- afr_local_replies_wipe (local, this->private);
+ afr_local_replies_wipe(local, this->private);
- inode = afr_selfheal_unlocked_lookup_on (frame, local->loc.parent,
- local->loc.name, local->replies,
- local->child_up, NULL);
- if (inode)
- inode_unref (inode);
+ inode = afr_selfheal_unlocked_lookup_on(frame, local->loc.parent,
+ local->loc.name, local->replies,
+ local->child_up, local->xattr_req);
+ if (inode)
+ inode_unref(inode);
- afr_lookup_metadata_heal_check(frame, this);
- return 0;
+ afr_lookup_metadata_heal_check(frame, this);
+ return 0;
unwind:
- AFR_STACK_UNWIND (lookup, frame, -1, EIO, NULL, NULL, NULL, NULL);
- return 0;
+ AFR_STACK_UNWIND(lookup, frame, -1, EIO, NULL, NULL, NULL, NULL);
+ return 0;
}
-
int
-afr_lookup_entry_heal (call_frame_t *frame, xlator_t *this)
-{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- call_frame_t *heal = NULL;
- int i = 0, first = -1;
- gf_boolean_t need_heal = _gf_false;
- struct afr_reply *replies = NULL;
- int ret = 0;
-
- local = frame->local;
- replies = local->replies;
- priv = this->private;
-
- for (i = 0; i < priv->child_count; i++) {
- if (!replies[i].valid)
- continue;
-
- if ((replies[i].op_ret == -1) &&
- (replies[i].op_errno == ENODATA))
- need_heal = _gf_true;
-
- if (first == -1) {
- first = i;
- continue;
- }
-
- if (replies[i].op_ret != replies[first].op_ret) {
- need_heal = _gf_true;
- break;
- }
-
- if (gf_uuid_compare (replies[i].poststat.ia_gfid,
- replies[first].poststat.ia_gfid)) {
- need_heal = _gf_true;
- break;
- }
- }
-
- if (need_heal) {
- heal = copy_frame (frame);
- if (heal)
- heal->root->pid = GF_CLIENT_PID_AFR_SELF_HEALD;
- ret = synctask_new (this->ctx->env, afr_lookup_selfheal_wrap,
- afr_refresh_selfheal_done, heal, frame);
- if (ret)
- goto metadata_heal;
- return ret;
- }
-metadata_heal:
- ret = afr_lookup_metadata_heal_check (frame, this);
-
- return ret;
-}
-
+afr_lookup_entry_heal(call_frame_t *frame, xlator_t *this)
+{
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ call_frame_t *heal = NULL;
+ int i = 0, first = -1;
+ gf_boolean_t name_state_mismatch = _gf_false;
+ struct afr_reply *replies = NULL;
+ int ret = 0;
+ unsigned char *par_readables = NULL;
+ unsigned char *success = NULL;
+ int32_t op_errno = 0;
+ uuid_t gfid = {0};
+
+ local = frame->local;
+ replies = local->replies;
+ priv = this->private;
+ par_readables = alloca0(priv->child_count);
+ success = alloca0(priv->child_count);
+
+ ret = afr_inode_read_subvol_get(local->loc.parent, this, par_readables,
+ NULL, NULL);
+ if (ret < 0 || AFR_COUNT(par_readables, priv->child_count) == 0) {
+ /* In this case set par_readables to all 1 so that name_heal
+ * need checks at the end of this function will flag missing
+ * entry when name state mismatches*/
+ memset(par_readables, 1, priv->child_count);
+ }
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (!replies[i].valid)
+ continue;
+
+ if (replies[i].op_ret == 0) {
+ if (gf_uuid_is_null(gfid)) {
+ gf_uuid_copy(gfid, replies[i].poststat.ia_gfid);
+ }
+ success[i] = 1;
+ } else {
+ if ((replies[i].op_errno != ENOTCONN) &&
+ (replies[i].op_errno != ENOENT) &&
+ (replies[i].op_errno != ESTALE)) {
+ op_errno = replies[i].op_errno;
+ }
+ }
-int
-afr_lookup_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int op_ret, int op_errno, inode_t *inode, struct iatt *buf,
- dict_t *xdata, struct iatt *postparent)
-{
- afr_local_t * local = NULL;
- int call_count = -1;
- int child_index = -1;
+ /*gfid is missing, needs heal*/
+ if ((replies[i].op_ret == -1) && (replies[i].op_errno == ENODATA)) {
+ goto name_heal;
+ }
- child_index = (long) cookie;
+ if (first == -1) {
+ first = i;
+ continue;
+ }
- local = frame->local;
+ if (replies[i].op_ret != replies[first].op_ret) {
+ name_state_mismatch = _gf_true;
+ }
- local->replies[child_index].valid = 1;
- local->replies[child_index].op_ret = op_ret;
- local->replies[child_index].op_errno = op_errno;
- /*
- * On revalidate lookup if the gfid-changed, afr should unwind the fop
- * with ESTALE so that a fresh lookup will be sent by the top xlator.
- * So remember it.
- */
- if (xdata && dict_get (xdata, "gfid-changed"))
- local->cont.lookup.needs_fresh_lookup = _gf_true;
+ if (replies[i].op_ret == 0) {
+ /* Rename after this lookup may succeed if we don't do
+ * a name-heal and the destination may not have pending xattrs
+ * to indicate which name is good and which is bad so always do
+ * this heal*/
+ if (gf_uuid_compare(replies[i].poststat.ia_gfid, gfid)) {
+ goto name_heal;
+ }
+ }
+ }
- if (op_ret != -1) {
- local->replies[child_index].poststat = *buf;
- local->replies[child_index].postparent = *postparent;
- if (xdata)
- local->replies[child_index].xdata = dict_ref (xdata);
- }
+ if (name_state_mismatch) {
+ if (!priv->quorum_count)
+ goto name_heal;
+ if (!afr_has_quorum(success, this, NULL))
+ goto name_heal;
+ if (op_errno)
+ goto name_heal;
+ for (i = 0; i < priv->child_count; i++) {
+ if (!replies[i].valid)
+ continue;
+ if (par_readables[i] && replies[i].op_ret < 0 &&
+ replies[i].op_errno != ENOTCONN) {
+ goto name_heal;
+ }
+ }
+ }
+
+ goto metadata_heal;
+
+name_heal:
+ heal = afr_frame_create(this, NULL);
+ if (!heal)
+ goto metadata_heal;
+
+ ret = synctask_new(this->ctx->env, afr_lookup_selfheal_wrap,
+ afr_refresh_selfheal_done, heal, frame);
+ if (ret) {
+ AFR_STACK_DESTROY(heal);
+ goto metadata_heal;
+ }
+ return ret;
- call_count = afr_frame_return (frame);
- if (call_count == 0) {
- afr_lookup_entry_heal (frame, this);
- }
+metadata_heal:
+ ret = afr_lookup_metadata_heal_check(frame, this);
- return 0;
+ return ret;
}
+int
+afr_lookup_cbk(call_frame_t *frame, void *cookie, xlator_t *this, int op_ret,
+ int op_errno, inode_t *inode, struct iatt *buf, dict_t *xdata,
+ struct iatt *postparent)
+{
+ afr_local_t *local = NULL;
+ int call_count = -1;
+ int child_index = -1;
+ GF_UNUSED int ret = 0;
+ int8_t need_heal = 1;
+
+ child_index = (long)cookie;
+
+ local = frame->local;
+
+ local->replies[child_index].valid = 1;
+ local->replies[child_index].op_ret = op_ret;
+ local->replies[child_index].op_errno = op_errno;
+ /*
+ * On revalidate lookup if the gfid-changed, afr should unwind the fop
+ * with ESTALE so that a fresh lookup will be sent by the top xlator.
+ * So remember it.
+ */
+ if (xdata && dict_get_sizen(xdata, "gfid-changed"))
+ local->cont.lookup.needs_fresh_lookup = _gf_true;
+
+ if (xdata) {
+ ret = dict_get_int8(xdata, "link-count", &need_heal);
+ local->replies[child_index].need_heal = need_heal;
+ } else {
+ local->replies[child_index].need_heal = need_heal;
+ }
+ if (op_ret != -1) {
+ local->replies[child_index].poststat = *buf;
+ local->replies[child_index].postparent = *postparent;
+ if (xdata)
+ local->replies[child_index].xdata = dict_ref(xdata);
+ }
+
+ call_count = afr_frame_return(frame);
+ if (call_count == 0) {
+ afr_set_need_heal(this, local);
+ afr_lookup_entry_heal(frame, this);
+ }
+ return 0;
+}
static void
-afr_discover_done (call_frame_t *frame, xlator_t *this)
+afr_discover_unwind(call_frame_t *frame, xlator_t *this)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int i = -1;
- int op_errno = 0;
- int read_subvol = 0;
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ int read_subvol = -1;
+ int ret = 0;
+ unsigned char *data_readable = NULL;
+ unsigned char *success_replies = NULL;
- priv = this->private;
- local = frame->local;
+ priv = this->private;
+ local = frame->local;
+ data_readable = alloca0(priv->child_count);
+ success_replies = alloca0(priv->child_count);
- for (i = 0; i < priv->child_count; i++) {
- if (!local->replies[i].valid)
- continue;
- if (local->replies[i].op_ret == 0)
- local->op_ret = 0;
- }
-
- op_errno = afr_final_errno (frame->local, this->private);
-
- if (local->op_ret < 0) {
- local->op_errno = op_errno;
- local->op_ret = -1;
- goto unwind;
- }
-
- afr_replies_interpret (frame, this, local->inode);
-
- read_subvol = afr_data_subvol_get (local->inode, this, 0, 0, NULL);
- if (read_subvol == -1) {
- gf_msg (this->name, GF_LOG_WARNING, 0,
- AFR_MSG_READ_SUBVOL_ERROR, "no read subvols for %s",
- local->loc.path);
-
- for (i = 0; i < priv->child_count; i++) {
- if (!local->replies[i].valid ||
- local->replies[i].op_ret == -1)
- continue;
- read_subvol = i;
- break;
- }
- }
+ afr_fill_success_replies(local, priv, success_replies);
+ if (AFR_COUNT(success_replies, priv->child_count) > 0)
+ local->op_ret = 0;
-unwind:
- if (read_subvol == -1) {
- afr_inode_split_brain_choice_get (local->inode, this,
- &read_subvol);
- if (read_subvol == -1)
- read_subvol = 0;
- }
+ if (local->op_ret < 0) {
+ local->op_ret = -1;
+ local->op_errno = afr_final_errno(frame->local, this->private);
+ goto error;
+ }
- AFR_STACK_UNWIND (lookup, frame, local->op_ret, local->op_errno,
- local->inode, &local->replies[read_subvol].poststat,
- local->replies[read_subvol].xdata,
- &local->replies[read_subvol].postparent);
-}
+ if (!afr_has_quorum(success_replies, this, frame))
+ goto unwind;
+ ret = afr_replies_interpret(frame, this, local->inode, NULL);
+ if (ret) {
+ afr_inode_need_refresh_set(local->inode, this);
+ }
-int
-afr_discover_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int op_ret, int op_errno, inode_t *inode, struct iatt *buf,
- dict_t *xdata, struct iatt *postparent)
-{
- afr_local_t * local = NULL;
- int call_count = -1;
- int child_index = -1;
+ read_subvol = afr_read_subvol_decide(local->inode, this, NULL,
+ data_readable);
- child_index = (long) cookie;
+unwind:
+ afr_attempt_readsubvol_set(frame, this, success_replies, data_readable,
+ &read_subvol);
+ if (read_subvol == -1)
+ goto error;
- local = frame->local;
+ if (AFR_IS_ARBITER_BRICK(priv, read_subvol) && local->op_ret == 0) {
+ local->op_ret = -1;
+ local->op_errno = ENOTCONN;
+ gf_msg_debug(this->name, 0,
+ "Arbiter cannot be a read subvol "
+ "for %s",
+ local->loc.path);
+ }
- local->replies[child_index].valid = 1;
- local->replies[child_index].op_ret = op_ret;
- local->replies[child_index].op_errno = op_errno;
- if (op_ret != -1) {
- local->replies[child_index].poststat = *buf;
- local->replies[child_index].postparent = *postparent;
- if (xdata)
- local->replies[child_index].xdata = dict_ref (xdata);
- }
+ AFR_STACK_UNWIND(lookup, frame, local->op_ret, local->op_errno,
+ local->inode, &local->replies[read_subvol].poststat,
+ local->replies[read_subvol].xdata,
+ &local->replies[read_subvol].postparent);
+ return;
- if (local->do_discovery && (op_ret == 0))
- afr_attempt_local_discovery (this, child_index);
+error:
+ AFR_STACK_UNWIND(lookup, frame, local->op_ret, local->op_errno, NULL, NULL,
+ NULL, NULL);
+}
- call_count = afr_frame_return (frame);
- if (call_count == 0) {
- afr_discover_done (frame, this);
- }
+static int
+afr_ta_id_file_check(void *opaque)
+{
+ afr_private_t *priv = NULL;
+ xlator_t *this = NULL;
+ loc_t loc = {
+ 0,
+ };
+ struct iatt stbuf = {
+ 0,
+ };
+ dict_t *dict = NULL;
+ uuid_t gfid = {
+ 0,
+ };
+ fd_t *fd = NULL;
+ int ret = 0;
+
+ this = opaque;
+ priv = this->private;
+
+ ret = afr_fill_ta_loc(this, &loc, _gf_false);
+ if (ret) {
+ gf_msg(this->name, GF_LOG_ERROR, -ret, AFR_MSG_THIN_ARB,
+ "Failed to populate thin-arbiter loc for: %s.", loc.name);
+ goto out;
+ }
+
+ ret = syncop_lookup(priv->children[THIN_ARBITER_BRICK_INDEX], &loc, &stbuf,
+ 0, 0, 0);
+ if (ret == 0) {
+ goto out;
+ } else if (ret == -ENOENT) {
+ fd = fd_create(loc.inode, getpid());
+ if (!fd)
+ goto out;
+ dict = dict_new();
+ if (!dict)
+ goto out;
+ gf_uuid_generate(gfid);
+ ret = dict_set_gfuuid(dict, "gfid-req", gfid, true);
+ ret = syncop_create(priv->children[THIN_ARBITER_BRICK_INDEX], &loc,
+ O_RDWR, 0664, fd, &stbuf, dict, NULL);
+ }
- return 0;
+out:
+ if (ret == 0) {
+ gf_uuid_copy(priv->ta_gfid, stbuf.ia_gfid);
+ } else {
+ gf_msg(this->name, GF_LOG_ERROR, -ret, AFR_MSG_THIN_ARB,
+ "Failed to lookup/create thin-arbiter id file.");
+ }
+ if (dict)
+ dict_unref(dict);
+ if (fd)
+ fd_unref(fd);
+ loc_wipe(&loc);
+
+ return 0;
}
+static int
+afr_ta_id_file_check_cbk(int ret, call_frame_t *ta_frame, void *opaque)
+{
+ return 0;
+}
-int
-afr_discover_do (call_frame_t *frame, xlator_t *this, int err)
+static void
+afr_discover_done(call_frame_t *frame, xlator_t *this)
{
- int ret = 0;
- int i = 0;
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- int call_count = 0;
+ int ret = 0;
+ afr_private_t *priv = NULL;
- local = frame->local;
- priv = this->private;
+ priv = this->private;
+ if (!priv->thin_arbiter_count)
+ goto unwind;
+ if (!gf_uuid_is_null(priv->ta_gfid))
+ goto unwind;
- if (err) {
- local->op_errno = -err;
- ret = -1;
- goto out;
- }
+ ret = synctask_new(this->ctx->env, afr_ta_id_file_check,
+ afr_ta_id_file_check_cbk, NULL, this);
+ if (ret)
+ goto unwind;
+unwind:
+ afr_discover_unwind(frame, this);
+}
- call_count = local->call_count = AFR_COUNT (local->child_up,
- priv->child_count);
+int
+afr_discover_cbk(call_frame_t *frame, void *cookie, xlator_t *this, int op_ret,
+ int op_errno, inode_t *inode, struct iatt *buf, dict_t *xdata,
+ struct iatt *postparent)
+{
+ afr_local_t *local = NULL;
+ int call_count = -1;
+ int child_index = -1;
+ GF_UNUSED int ret = 0;
+ int8_t need_heal = 1;
+
+ child_index = (long)cookie;
+
+ local = frame->local;
+
+ local->replies[child_index].valid = 1;
+ local->replies[child_index].op_ret = op_ret;
+ local->replies[child_index].op_errno = op_errno;
+ if (op_ret != -1) {
+ local->replies[child_index].poststat = *buf;
+ local->replies[child_index].postparent = *postparent;
+ if (xdata)
+ local->replies[child_index].xdata = dict_ref(xdata);
+ }
+
+ if (local->do_discovery && (op_ret == 0))
+ afr_attempt_local_discovery(this, child_index);
+
+ if (xdata) {
+ ret = dict_get_int8(xdata, "link-count", &need_heal);
+ local->replies[child_index].need_heal = need_heal;
+ } else {
+ local->replies[child_index].need_heal = need_heal;
+ }
+
+ call_count = afr_frame_return(frame);
+ if (call_count == 0) {
+ afr_set_need_heal(this, local);
+ afr_lookup_metadata_heal_check(frame, this);
+ }
- ret = afr_lookup_xattr_req_prepare (local, this, local->xattr_req,
- &local->loc);
- if (ret) {
- local->op_errno = -ret;
- ret = -1;
- goto out;
- }
+ return 0;
+}
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND_COOKIE (frame, afr_discover_cbk,
- (void *) (long) i,
- priv->children[i],
- priv->children[i]->fops->lookup,
- &local->loc, local->xattr_req);
- if (!--call_count)
- break;
- }
+int
+afr_discover_do(call_frame_t *frame, xlator_t *this, int err)
+{
+ int ret = 0;
+ int i = 0;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int call_count = 0;
+
+ local = frame->local;
+ priv = this->private;
+
+ if (err) {
+ local->op_errno = err;
+ goto out;
+ }
+
+ call_count = local->call_count = AFR_COUNT(local->child_up,
+ priv->child_count);
+
+ ret = afr_lookup_xattr_req_prepare(local, this, local->xattr_req,
+ &local->loc);
+ if (ret) {
+ local->op_errno = -ret;
+ goto out;
+ }
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->child_up[i]) {
+ STACK_WIND_COOKIE(
+ frame, afr_discover_cbk, (void *)(long)i, priv->children[i],
+ priv->children[i]->fops->lookup, &local->loc, local->xattr_req);
+ if (!--call_count)
+ break;
}
+ }
- return 0;
+ return 0;
out:
- AFR_STACK_UNWIND (lookup, frame, -1, local->op_errno, 0, 0, 0, 0);
- return 0;
+ AFR_STACK_UNWIND(lookup, frame, -1, local->op_errno, 0, 0, 0, 0);
+ return 0;
}
-
int
-afr_discover (call_frame_t *frame, xlator_t *this, loc_t *loc, dict_t *xattr_req)
+afr_discover(call_frame_t *frame, xlator_t *this, loc_t *loc, dict_t *xattr_req)
{
- int op_errno = ENOMEM;
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int event = 0;
+ int op_errno = ENOMEM;
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ int event = 0;
- priv = this->private;
+ priv = this->private;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
- if (!local->call_count) {
- op_errno = ENOTCONN;
- goto out;
- }
+ if (!local->call_count) {
+ op_errno = ENOTCONN;
+ goto out;
+ }
- if (__is_root_gfid (loc->inode->gfid)) {
- if (!this->itable)
- this->itable = loc->inode->table;
- if (!priv->root_inode)
- priv->root_inode = inode_ref (loc->inode);
+ if (__is_root_gfid(loc->inode->gfid)) {
+ if (!priv->root_inode)
+ priv->root_inode = inode_ref(loc->inode);
- if (priv->choose_local && !priv->did_discovery) {
- /* Logic to detect which subvolumes of AFR are
- local, in order to prefer them for reads
- */
- local->do_discovery = _gf_true;
- priv->did_discovery = _gf_true;
- }
- }
+ if (priv->choose_local && !priv->did_discovery) {
+ /* Logic to detect which subvolumes of AFR are
+ local, in order to prefer them for reads
+ */
+ local->do_discovery = _gf_true;
+ priv->did_discovery = _gf_true;
+ }
+ }
- local->op = GF_FOP_LOOKUP;
+ local->op = GF_FOP_LOOKUP;
- loc_copy (&local->loc, loc);
+ loc_copy(&local->loc, loc);
- local->inode = inode_ref (loc->inode);
+ local->inode = inode_ref(loc->inode);
- if (xattr_req)
- /* If xattr_req was null, afr_lookup_xattr_req_prepare() will
- allocate one for us */
- local->xattr_req = dict_ref (xattr_req);
+ if (xattr_req) {
+ /* If xattr_req was null, afr_lookup_xattr_req_prepare() will
+ allocate one for us */
+ local->xattr_req = dict_copy_with_ref(xattr_req, NULL);
+ if (!local->xattr_req) {
+ op_errno = ENOMEM;
+ goto out;
+ }
+ }
- if (gf_uuid_is_null (loc->inode->gfid)) {
- afr_discover_do (frame, this, 0);
- return 0;
- }
+ if (gf_uuid_is_null(loc->inode->gfid)) {
+ afr_discover_do(frame, this, 0);
+ return 0;
+ }
- afr_read_subvol_get (loc->inode, this, NULL, &event,
- AFR_DATA_TRANSACTION, NULL);
+ afr_read_subvol_get(loc->inode, this, NULL, NULL, &event,
+ AFR_DATA_TRANSACTION, NULL);
- if (event != local->event_generation)
- afr_inode_refresh (frame, this, loc->inode, afr_discover_do);
- else
- afr_discover_do (frame, this, 0);
+ afr_discover_do(frame, this, 0);
- return 0;
+ return 0;
out:
- AFR_STACK_UNWIND (lookup, frame, -1, op_errno, NULL, NULL, NULL, NULL);
- return 0;
+ AFR_STACK_UNWIND(lookup, frame, -1, op_errno, NULL, NULL, NULL, NULL);
+ return 0;
}
-
int
-afr_lookup_do (call_frame_t *frame, xlator_t *this, int err)
-{
- int ret = 0;
- int i = 0;
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- int call_count = 0;
-
- local = frame->local;
- priv = this->private;
-
- if (err < 0) {
- local->op_errno = -err;
- ret = -1;
- goto out;
- }
-
- call_count = local->call_count = AFR_COUNT (local->child_up,
- priv->child_count);
-
- ret = afr_lookup_xattr_req_prepare (local, this, local->xattr_req,
- &local->loc);
- if (ret) {
- local->op_errno = -ret;
- ret = -1;
- goto out;
- }
-
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND_COOKIE (frame, afr_lookup_cbk,
- (void *) (long) i,
- priv->children[i],
- priv->children[i]->fops->lookup,
- &local->loc, local->xattr_req);
- if (!--call_count)
- break;
- }
+afr_lookup_do(call_frame_t *frame, xlator_t *this, int err)
+{
+ int ret = 0;
+ int i = 0;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int call_count = 0;
+
+ local = frame->local;
+ priv = this->private;
+
+ if (err < 0) {
+ local->op_errno = err;
+ goto out;
+ }
+
+ call_count = local->call_count = AFR_COUNT(local->child_up,
+ priv->child_count);
+
+ ret = afr_lookup_xattr_req_prepare(local, this, local->xattr_req,
+ &local->loc);
+ if (ret) {
+ local->op_errno = -ret;
+ goto out;
+ }
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->child_up[i]) {
+ STACK_WIND_COOKIE(
+ frame, afr_lookup_cbk, (void *)(long)i, priv->children[i],
+ priv->children[i]->fops->lookup, &local->loc, local->xattr_req);
+ if (!--call_count)
+ break;
}
- return 0;
+ }
+ return 0;
out:
- AFR_STACK_UNWIND (lookup, frame, -1, local->op_errno, 0, 0, 0, 0);
- return 0;
+ AFR_STACK_UNWIND(lookup, frame, -1, local->op_errno, 0, 0, 0, 0);
+ return 0;
}
/*
@@ -2313,2671 +4000,3879 @@ out:
*/
int
-afr_lookup (call_frame_t *frame, xlator_t *this, loc_t *loc, dict_t *xattr_req)
-{
- afr_local_t *local = NULL;
- int32_t op_errno = 0;
- int event = 0;
- void *gfid_req = NULL;
- int ret = 0;
-
- if (!loc->parent && gf_uuid_is_null (loc->pargfid)) {
- if (xattr_req)
- dict_del (xattr_req, "gfid-req");
- afr_discover (frame, this, loc, xattr_req);
- return 0;
- }
-
- if (__is_root_gfid (loc->parent->gfid)) {
- if (!strcmp (loc->name, GF_REPLICATE_TRASH_DIR)) {
- op_errno = EPERM;
- goto out;
- }
- }
-
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
-
- if (!local->call_count) {
- op_errno = ENOTCONN;
- goto out;
- }
-
- local->op = GF_FOP_LOOKUP;
-
- loc_copy (&local->loc, loc);
-
- local->inode = inode_ref (loc->inode);
-
- if (xattr_req) {
- /* If xattr_req was null, afr_lookup_xattr_req_prepare() will
- allocate one for us */
- ret = dict_get_ptr (xattr_req, "gfid-req", &gfid_req);
- if (ret == 0) {
- gf_uuid_copy (local->cont.lookup.gfid_req, gfid_req);
- dict_del (xattr_req, "gfid-req");
- }
- local->xattr_req = dict_ref (xattr_req);
- }
+afr_lookup(call_frame_t *frame, xlator_t *this, loc_t *loc, dict_t *xattr_req)
+{
+ afr_local_t *local = NULL;
+ int32_t op_errno = 0;
+ int event = 0;
+ int ret = 0;
- afr_read_subvol_get (loc->parent, this, NULL, &event,
- AFR_DATA_TRANSACTION, NULL);
+ if (loc_is_nameless(loc)) {
+ if (xattr_req)
+ dict_del_sizen(xattr_req, "gfid-req");
+ afr_discover(frame, this, loc, xattr_req);
+ return 0;
+ }
- if (event != local->event_generation)
- afr_inode_refresh (frame, this, loc->parent, afr_lookup_do);
- else
- afr_lookup_do (frame, this, 0);
+ if (afr_is_private_directory(this->private, loc->parent->gfid, loc->name,
+ frame->root->pid)) {
+ op_errno = EPERM;
+ goto out;
+ }
- return 0;
-out:
- AFR_STACK_UNWIND (lookup, frame, -1, op_errno, NULL, NULL, NULL, NULL);
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
- return 0;
-}
+ if (!local->call_count) {
+ op_errno = ENOTCONN;
+ goto out;
+ }
+ local->op = GF_FOP_LOOKUP;
-/* {{{ open */
+ loc_copy(&local->loc, loc);
-afr_fd_ctx_t *
-__afr_fd_ctx_get (fd_t *fd, xlator_t *this)
-{
- uint64_t ctx = 0;
- int ret = 0;
- afr_fd_ctx_t *fd_ctx = NULL;
+ local->inode = inode_ref(loc->inode);
- ret = __fd_ctx_get (fd, this, &ctx);
+ if (xattr_req) {
+ /* If xattr_req was null, afr_lookup_xattr_req_prepare() will
+ allocate one for us */
+ local->xattr_req = dict_copy_with_ref(xattr_req, NULL);
+ if (!local->xattr_req) {
+ op_errno = ENOMEM;
+ goto out;
+ }
+ ret = dict_get_gfuuid(local->xattr_req, "gfid-req",
+ &local->cont.lookup.gfid_req);
+ if (ret == 0) {
+ dict_del_sizen(local->xattr_req, "gfid-req");
+ }
+ }
- if (ret < 0) {
- ret = __afr_fd_ctx_set (this, fd);
- if (ret < 0)
- goto out;
+ afr_read_subvol_get(loc->parent, this, NULL, NULL, &event,
+ AFR_DATA_TRANSACTION, NULL);
- ret = __fd_ctx_get (fd, this, &ctx);
- if (ret < 0)
- goto out;
- }
+ afr_lookup_do(frame, this, 0);
- fd_ctx = (afr_fd_ctx_t *)(long) ctx;
+ return 0;
out:
- return fd_ctx;
-}
+ AFR_STACK_UNWIND(lookup, frame, -1, op_errno, NULL, NULL, NULL, NULL);
+ return 0;
+}
-afr_fd_ctx_t *
-afr_fd_ctx_get (fd_t *fd, xlator_t *this)
+void
+_afr_cleanup_fd_ctx(xlator_t *this, afr_fd_ctx_t *fd_ctx)
{
- afr_fd_ctx_t *fd_ctx = NULL;
+ afr_private_t *priv = this->private;
- LOCK(&fd->lock);
+ if (fd_ctx->lk_heal_info) {
+ LOCK(&priv->lock);
{
- fd_ctx = __afr_fd_ctx_get (fd, this);
+ list_del(&fd_ctx->lk_heal_info->pos);
}
- UNLOCK(&fd->lock);
-
- return fd_ctx;
+ afr_lk_heal_info_cleanup(fd_ctx->lk_heal_info);
+ fd_ctx->lk_heal_info = NULL;
+ }
+ GF_FREE(fd_ctx->opened_on);
+ GF_FREE(fd_ctx);
+ return;
}
-
int
-__afr_fd_ctx_set (xlator_t *this, fd_t *fd)
+afr_cleanup_fd_ctx(xlator_t *this, fd_t *fd)
{
- afr_private_t * priv = NULL;
- int ret = -1;
- uint64_t ctx = 0;
- afr_fd_ctx_t * fd_ctx = NULL;
- int i = 0;
-
- VALIDATE_OR_GOTO (this->private, out);
- VALIDATE_OR_GOTO (fd, out);
-
- priv = this->private;
-
- ret = __fd_ctx_get (fd, this, &ctx);
-
- if (ret == 0)
- goto out;
-
- fd_ctx = GF_CALLOC (1, sizeof (afr_fd_ctx_t),
- gf_afr_mt_afr_fd_ctx_t);
- if (!fd_ctx) {
- ret = -ENOMEM;
- goto out;
- }
-
- for (i = 0; i < AFR_NUM_CHANGE_LOGS; i++) {
- fd_ctx->pre_op_done[i] = GF_CALLOC (sizeof (*fd_ctx->pre_op_done[i]),
- priv->child_count,
- gf_afr_mt_int32_t);
- if (!fd_ctx->pre_op_done[i]) {
- ret = -ENOMEM;
- goto out;
- }
- }
-
- fd_ctx->opened_on = GF_CALLOC (sizeof (*fd_ctx->opened_on),
- priv->child_count,
- gf_afr_mt_int32_t);
- if (!fd_ctx->opened_on) {
- ret = -ENOMEM;
- goto out;
- }
-
- for (i = 0; i < priv->child_count; i++) {
- if (fd_is_anonymous (fd))
- fd_ctx->opened_on[i] = AFR_FD_OPENED;
- else
- fd_ctx->opened_on[i] = AFR_FD_NOT_OPENED;
- }
-
- fd_ctx->lock_piggyback = GF_CALLOC (sizeof (*fd_ctx->lock_piggyback),
- priv->child_count,
- gf_afr_mt_char);
- if (!fd_ctx->lock_piggyback) {
- ret = -ENOMEM;
- goto out;
- }
-
- fd_ctx->lock_acquired = GF_CALLOC (sizeof (*fd_ctx->lock_acquired),
- priv->child_count,
- gf_afr_mt_char);
- if (!fd_ctx->lock_acquired) {
- ret = -ENOMEM;
- goto out;
- }
+ uint64_t ctx = 0;
+ afr_fd_ctx_t *fd_ctx = NULL;
+ int ret = 0;
- fd_ctx->readdir_subvol = -1;
+ ret = fd_ctx_get(fd, this, &ctx);
+ if (ret < 0)
+ goto out;
- pthread_mutex_init (&fd_ctx->delay_lock, NULL);
+ fd_ctx = (afr_fd_ctx_t *)(long)ctx;
- INIT_LIST_HEAD (&fd_ctx->eager_locked);
+ if (fd_ctx) {
+ _afr_cleanup_fd_ctx(this, fd_ctx);
+ }
- ret = __fd_ctx_set (fd, this, (uint64_t)(long) fd_ctx);
- if (ret)
- gf_msg_debug (this->name, 0,
- "failed to set fd ctx (%p)", fd);
out:
- return ret;
+ return 0;
}
-
int
-afr_fd_ctx_set (xlator_t *this, fd_t *fd)
+afr_release(xlator_t *this, fd_t *fd)
{
- int ret = -1;
-
- LOCK (&fd->lock);
- {
- ret = __afr_fd_ctx_set (this, fd);
- }
- UNLOCK (&fd->lock);
+ afr_cleanup_fd_ctx(this, fd);
- return ret;
+ return 0;
}
-/* {{{ flush */
-
-int
-afr_flush_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, dict_t *xdata)
+afr_fd_ctx_t *
+__afr_fd_ctx_get(fd_t *fd, xlator_t *this)
{
- afr_local_t *local = NULL;
- int call_count = -1;
+ uint64_t ctx = 0;
+ int ret = 0;
+ afr_fd_ctx_t *fd_ctx = NULL;
- local = frame->local;
-
- LOCK (&frame->lock);
- {
- if (op_ret != -1) {
- local->op_ret = op_ret;
- if (!local->xdata_rsp && xdata)
- local->xdata_rsp = dict_ref (xdata);
- } else {
- local->op_errno = op_errno;
- }
- }
- UNLOCK (&frame->lock);
+ ret = __fd_ctx_get(fd, this, &ctx);
- call_count = afr_frame_return (frame);
+ if (ret < 0) {
+ ret = __afr_fd_ctx_set(this, fd);
+ if (ret < 0)
+ goto out;
- if (call_count == 0)
- AFR_STACK_UNWIND (flush, frame, local->op_ret,
- local->op_errno, local->xdata_rsp);
+ ret = __fd_ctx_get(fd, this, &ctx);
+ if (ret < 0)
+ goto out;
+ }
- return 0;
+ fd_ctx = (afr_fd_ctx_t *)(long)ctx;
+out:
+ return fd_ctx;
}
-static int
-afr_flush_wrapper (call_frame_t *frame, xlator_t *this, fd_t *fd, dict_t *xdata)
+afr_fd_ctx_t *
+afr_fd_ctx_get(fd_t *fd, xlator_t *this)
{
- int i = 0;
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- int call_count = -1;
+ afr_fd_ctx_t *fd_ctx = NULL;
- priv = this->private;
- local = frame->local;
- call_count = local->call_count;
+ LOCK(&fd->lock);
+ {
+ fd_ctx = __afr_fd_ctx_get(fd, this);
+ }
+ UNLOCK(&fd->lock);
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND_COOKIE (frame, afr_flush_cbk,
- (void *) (long) i,
- priv->children[i],
- priv->children[i]->fops->flush,
- local->fd, xdata);
- if (!--call_count)
- break;
-
- }
- }
-
- return 0;
+ return fd_ctx;
}
int
-afr_flush (call_frame_t *frame, xlator_t *this, fd_t *fd, dict_t *xdata)
+__afr_fd_ctx_set(xlator_t *this, fd_t *fd)
{
- afr_local_t *local = NULL;
- call_stub_t *stub = NULL;
- int op_errno = ENOMEM;
+ afr_private_t *priv = NULL;
+ int ret = -1;
+ uint64_t ctx = 0;
+ afr_fd_ctx_t *fd_ctx = NULL;
+ int i = 0;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ VALIDATE_OR_GOTO(this->private, out);
+ VALIDATE_OR_GOTO(fd, out);
- if (!local->call_count) {
- op_errno = ENOTCONN;
- goto out;
- }
+ priv = this->private;
- local->fd = fd_ref(fd);
+ ret = __fd_ctx_get(fd, this, &ctx);
- stub = fop_flush_stub (frame, afr_flush_wrapper, fd, xdata);
- if (!stub)
- goto out;
+ if (ret == 0)
+ goto out;
- afr_delayed_changelog_wake_resume (this, fd, stub);
+ fd_ctx = GF_CALLOC(1, sizeof(afr_fd_ctx_t), gf_afr_mt_afr_fd_ctx_t);
+ if (!fd_ctx) {
+ ret = -ENOMEM;
+ goto out;
+ }
- return 0;
+ fd_ctx->opened_on = GF_CALLOC(sizeof(*fd_ctx->opened_on), priv->child_count,
+ gf_afr_mt_int32_t);
+ if (!fd_ctx->opened_on) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (fd_is_anonymous(fd))
+ fd_ctx->opened_on[i] = AFR_FD_OPENED;
+ else
+ fd_ctx->opened_on[i] = AFR_FD_NOT_OPENED;
+ }
+
+ fd_ctx->readdir_subvol = -1;
+ fd_ctx->lk_heal_info = NULL;
+
+ ret = __fd_ctx_set(fd, this, (uint64_t)(long)fd_ctx);
+ if (ret)
+ gf_msg_debug(this->name, 0, "failed to set fd ctx (%p)", fd);
out:
- AFR_STACK_UNWIND (flush, frame, -1, op_errno, NULL);
- return 0;
+ if (ret && fd_ctx)
+ _afr_cleanup_fd_ctx(this, fd_ctx);
+ return ret;
}
-/* }}} */
-
+/* {{{ flush */
int
-afr_cleanup_fd_ctx (xlator_t *this, fd_t *fd)
+afr_flush_cbk(call_frame_t *frame, void *cookie, xlator_t *this, int32_t op_ret,
+ int32_t op_errno, dict_t *xdata)
{
- uint64_t ctx = 0;
- afr_fd_ctx_t *fd_ctx = NULL;
- int ret = 0;
- int i = 0;
-
- ret = fd_ctx_get (fd, this, &ctx);
- if (ret < 0)
- goto out;
-
- fd_ctx = (afr_fd_ctx_t *)(long) ctx;
+ afr_local_t *local = NULL;
+ int call_count = -1;
- if (fd_ctx) {
- //no need to take any locks
- if (!list_empty (&fd_ctx->eager_locked))
- gf_msg (this->name, GF_LOG_WARNING, 0,
- AFR_MSG_INVALID_DATA, "%s: Stale "
- "Eager-lock stubs found",
- uuid_utoa (fd->inode->gfid));
+ local = frame->local;
- for (i = 0; i < AFR_NUM_CHANGE_LOGS; i++)
- GF_FREE (fd_ctx->pre_op_done[i]);
-
- GF_FREE (fd_ctx->opened_on);
-
- GF_FREE (fd_ctx->lock_piggyback);
+ LOCK(&frame->lock);
+ {
+ if (op_ret != -1) {
+ local->op_ret = op_ret;
+ if (!local->xdata_rsp && xdata)
+ local->xdata_rsp = dict_ref(xdata);
+ } else {
+ local->op_errno = op_errno;
+ }
+ call_count = --local->call_count;
+ }
+ UNLOCK(&frame->lock);
- GF_FREE (fd_ctx->lock_acquired);
+ if (call_count == 0)
+ AFR_STACK_UNWIND(flush, frame, local->op_ret, local->op_errno,
+ local->xdata_rsp);
- pthread_mutex_destroy (&fd_ctx->delay_lock);
+ return 0;
+}
- GF_FREE (fd_ctx);
+static int
+afr_flush_wrapper(call_frame_t *frame, xlator_t *this, fd_t *fd, dict_t *xdata)
+{
+ int i = 0;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int call_count = -1;
+
+ priv = this->private;
+ local = frame->local;
+ call_count = local->call_count;
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->child_up[i]) {
+ STACK_WIND_COOKIE(frame, afr_flush_cbk, (void *)(long)i,
+ priv->children[i], priv->children[i]->fops->flush,
+ local->fd, xdata);
+ if (!--call_count)
+ break;
}
+ }
-out:
- return 0;
+ return 0;
}
-
-int
-afr_release (xlator_t *this, fd_t *fd)
+afr_local_t *
+afr_wakeup_same_fd_delayed_op(xlator_t *this, afr_lock_t *lock, fd_t *fd)
{
- afr_cleanup_fd_ctx (this, fd);
-
- return 0;
-}
+ afr_local_t *local = NULL;
+ if (lock->delay_timer) {
+ local = list_entry(lock->post_op.next, afr_local_t,
+ transaction.owner_list);
+ if (fd == local->fd) {
+ if (gf_timer_call_cancel(this->ctx, lock->delay_timer)) {
+ local = NULL;
+ } else {
+ lock->delay_timer = NULL;
+ }
+ } else {
+ local = NULL;
+ }
+ }
-/* {{{ fsync */
+ return local;
+}
-int
-afr_fsync_unwind_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, struct iatt *prebuf,
- struct iatt *postbuf, dict_t *xdata)
-{
- AFR_STACK_UNWIND (fsync, frame, op_ret, op_errno, prebuf, postbuf,
- xdata);
- return 0;
+void
+afr_delayed_changelog_wake_resume(xlator_t *this, inode_t *inode,
+ call_stub_t *stub)
+{
+ afr_inode_ctx_t *ctx = NULL;
+ afr_lock_t *lock = NULL;
+ afr_local_t *metadata_local = NULL;
+ afr_local_t *data_local = NULL;
+ LOCK(&inode->lock);
+ {
+ (void)__afr_inode_ctx_get(this, inode, &ctx);
+ lock = &ctx->lock[AFR_DATA_TRANSACTION];
+ data_local = afr_wakeup_same_fd_delayed_op(this, lock, stub->args.fd);
+ lock = &ctx->lock[AFR_METADATA_TRANSACTION];
+ metadata_local = afr_wakeup_same_fd_delayed_op(this, lock,
+ stub->args.fd);
+ }
+ UNLOCK(&inode->lock);
+
+ if (data_local) {
+ data_local->transaction.resume_stub = stub;
+ } else if (metadata_local) {
+ metadata_local->transaction.resume_stub = stub;
+ } else {
+ call_resume(stub);
+ }
+ if (data_local) {
+ afr_delayed_changelog_wake_up_cbk(data_local);
+ }
+ if (metadata_local) {
+ afr_delayed_changelog_wake_up_cbk(metadata_local);
+ }
}
int
-afr_fsync_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, struct iatt *prebuf,
- struct iatt *postbuf, dict_t *xdata)
+afr_flush(call_frame_t *frame, xlator_t *this, fd_t *fd, dict_t *xdata)
{
- afr_local_t *local = NULL;
- int call_count = -1;
- int child_index = (long) cookie;
- int read_subvol = 0;
- call_stub_t *stub = NULL;
+ afr_local_t *local = NULL;
+ call_stub_t *stub = NULL;
+ int op_errno = ENOMEM;
- local = frame->local;
+ AFR_ERROR_OUT_IF_FDCTX_INVALID(fd, this, op_errno, out);
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
- read_subvol = afr_data_subvol_get (local->inode, this, 0, 0, NULL);
+ local->op = GF_FOP_FLUSH;
+ if (!afr_is_consistent_io_possible(local, this->private, &op_errno))
+ goto out;
- LOCK (&frame->lock);
- {
- if (op_ret == 0) {
- if (local->op_ret == -1) {
- local->op_ret = 0;
-
- local->cont.inode_wfop.prebuf = *prebuf;
- local->cont.inode_wfop.postbuf = *postbuf;
-
- if (xdata)
- local->xdata_rsp = dict_ref (xdata);
- }
-
- if (child_index == read_subvol) {
- local->cont.inode_wfop.prebuf = *prebuf;
- local->cont.inode_wfop.postbuf = *postbuf;
- if (xdata) {
- if (local->xdata_rsp)
- dict_unref (local->xdata_rsp);
- local->xdata_rsp = dict_ref (xdata);
- }
- }
- } else {
- local->op_errno = op_errno;
- }
- }
- UNLOCK (&frame->lock);
-
- call_count = afr_frame_return (frame);
-
- if (call_count == 0) {
- /* Make a stub out of the frame, and register it
- with the waking up post-op. When the call-stub resumes,
- we are guaranteed that there was no post-op pending
- (i.e changelogs were unset in the server). This is an
- essential "guarantee", that fsync() returns only after
- completely finishing EVERYTHING, including the delayed
- post-op. This guarantee is expected by FUSE graph switching
- for example.
- */
- stub = fop_fsync_cbk_stub (frame, afr_fsync_unwind_cbk,
- local->op_ret, local->op_errno,
- &local->cont.inode_wfop.prebuf,
- &local->cont.inode_wfop.postbuf,
- local->xdata_rsp);
- if (!stub) {
- AFR_STACK_UNWIND (fsync, frame, -1, ENOMEM, 0, 0, 0);
- return 0;
- }
-
- /* If no new unstable writes happened between the
- time we cleared the unstable write witness flag in afr_fsync
- and now, calling afr_delayed_changelog_wake_up() should
- wake up and skip over the fsync phase and go straight to
- afr_changelog_post_op_now()
- */
- afr_delayed_changelog_wake_resume (this, local->fd, stub);
- }
+ local->fd = fd_ref(fd);
- return 0;
-}
+ stub = fop_flush_stub(frame, afr_flush_wrapper, fd, xdata);
+ if (!stub)
+ goto out;
+ afr_delayed_changelog_wake_resume(this, fd->inode, stub);
+
+ return 0;
+out:
+ AFR_STACK_UNWIND(flush, frame, -1, op_errno, NULL);
+ return 0;
+}
int
-afr_fsync (call_frame_t *frame, xlator_t *this, fd_t *fd, int32_t datasync,
- dict_t *xdata)
+afr_fsyncdir_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int i = 0;
- int32_t call_count = 0;
- int32_t op_errno = ENOMEM;
+ afr_local_t *local = NULL;
+ int call_count = -1;
- priv = this->private;
+ local = frame->local;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
-
- call_count = local->call_count;
- if (!call_count) {
- op_errno = ENOTCONN;
- goto out;
- }
-
- local->fd = fd_ref (fd);
+ LOCK(&frame->lock);
+ {
+ if (op_ret == 0) {
+ local->op_ret = 0;
+ if (!local->xdata_rsp && xdata)
+ local->xdata_rsp = dict_ref(xdata);
+ } else {
+ local->op_errno = op_errno;
+ }
+ call_count = --local->call_count;
+ }
+ UNLOCK(&frame->lock);
- if (afr_fd_has_witnessed_unstable_write (this, fd)) {
- /* don't care. we only wanted to CLEAR the bit */
- }
+ if (call_count == 0)
+ AFR_STACK_UNWIND(fsyncdir, frame, local->op_ret, local->op_errno,
+ local->xdata_rsp);
- local->inode = inode_ref (fd->inode);
+ return 0;
+}
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND_COOKIE (frame, afr_fsync_cbk,
- (void *) (long) i,
- priv->children[i],
- priv->children[i]->fops->fsync,
- fd, datasync, xdata);
- if (!--call_count)
- break;
- }
+int
+afr_fsyncdir(call_frame_t *frame, xlator_t *this, fd_t *fd, int32_t datasync,
+ dict_t *xdata)
+{
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ int i = 0;
+ int32_t call_count = 0;
+ int32_t op_errno = ENOMEM;
+
+ priv = this->private;
+
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
+
+ local->op = GF_FOP_FSYNCDIR;
+ if (!afr_is_consistent_io_possible(local, priv, &op_errno))
+ goto out;
+
+ call_count = local->call_count;
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->child_up[i]) {
+ STACK_WIND(frame, afr_fsyncdir_cbk, priv->children[i],
+ priv->children[i]->fops->fsyncdir, fd, datasync, xdata);
+ if (!--call_count)
+ break;
}
+ }
- return 0;
+ return 0;
out:
- AFR_STACK_UNWIND (fsync, frame, -1, op_errno, NULL, NULL, NULL);
+ AFR_STACK_UNWIND(fsyncdir, frame, -1, op_errno, NULL);
- return 0;
+ return 0;
}
/* }}} */
-/* {{{ fsync */
+static int
+afr_serialized_lock_wind(call_frame_t *frame, xlator_t *this);
-int
-afr_fsyncdir_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, dict_t *xdata)
+static gf_boolean_t
+afr_is_conflicting_lock_present(int32_t op_ret, int32_t op_errno)
{
- afr_local_t *local = NULL;
- int call_count = -1;
+ if (op_ret == -1 && op_errno == EAGAIN)
+ return _gf_true;
+ return _gf_false;
+}
- local = frame->local;
+static void
+afr_fop_lock_unwind(call_frame_t *frame, glusterfs_fop_t op, int32_t op_ret,
+ int32_t op_errno, dict_t *xdata)
+{
+ switch (op) {
+ case GF_FOP_INODELK:
+ AFR_STACK_UNWIND(inodelk, frame, op_ret, op_errno, xdata);
+ break;
+ case GF_FOP_FINODELK:
+ AFR_STACK_UNWIND(finodelk, frame, op_ret, op_errno, xdata);
+ break;
+ case GF_FOP_ENTRYLK:
+ AFR_STACK_UNWIND(entrylk, frame, op_ret, op_errno, xdata);
+ break;
+ case GF_FOP_FENTRYLK:
+ AFR_STACK_UNWIND(fentrylk, frame, op_ret, op_errno, xdata);
+ break;
+ default:
+ break;
+ }
+}
- LOCK (&frame->lock);
- {
- if (op_ret == 0) {
- local->op_ret = 0;
- if (!local->xdata_rsp && xdata)
- local->xdata_rsp = dict_ref (xdata);
- } else {
- local->op_errno = op_errno;
- }
- }
- UNLOCK (&frame->lock);
+static void
+afr_fop_lock_wind(call_frame_t *frame, xlator_t *this, int child_index,
+ int32_t (*lock_cbk)(call_frame_t *, void *, xlator_t *,
+ int32_t, int32_t, dict_t *))
+{
+ afr_local_t *local = frame->local;
+ afr_private_t *priv = this->private;
+ int i = child_index;
+
+ switch (local->op) {
+ case GF_FOP_INODELK:
+ STACK_WIND_COOKIE(
+ frame, lock_cbk, (void *)(long)i, priv->children[i],
+ priv->children[i]->fops->inodelk,
+ (const char *)local->cont.inodelk.volume, &local->loc,
+ local->cont.inodelk.cmd, &local->cont.inodelk.flock,
+ local->cont.inodelk.xdata);
+ break;
+ case GF_FOP_FINODELK:
+ STACK_WIND_COOKIE(
+ frame, lock_cbk, (void *)(long)i, priv->children[i],
+ priv->children[i]->fops->finodelk,
+ (const char *)local->cont.inodelk.volume, local->fd,
+ local->cont.inodelk.cmd, &local->cont.inodelk.flock,
+ local->cont.inodelk.xdata);
+ break;
+ case GF_FOP_ENTRYLK:
+ STACK_WIND_COOKIE(
+ frame, lock_cbk, (void *)(long)i, priv->children[i],
+ priv->children[i]->fops->entrylk, local->cont.entrylk.volume,
+ &local->loc, local->cont.entrylk.basename,
+ local->cont.entrylk.cmd, local->cont.entrylk.type,
+ local->cont.entrylk.xdata);
+ break;
+ case GF_FOP_FENTRYLK:
+ STACK_WIND_COOKIE(
+ frame, lock_cbk, (void *)(long)i, priv->children[i],
+ priv->children[i]->fops->fentrylk, local->cont.entrylk.volume,
+ local->fd, local->cont.entrylk.basename,
+ local->cont.entrylk.cmd, local->cont.entrylk.type,
+ local->cont.entrylk.xdata);
+ break;
+ default:
+ break;
+ }
+}
- call_count = afr_frame_return (frame);
+void
+afr_fop_lock_proceed(call_frame_t *frame)
+{
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
- if (call_count == 0)
- AFR_STACK_UNWIND (fsyncdir, frame, local->op_ret,
- local->op_errno, local->xdata_rsp);
+ local = frame->local;
+ priv = frame->this->private;
- return 0;
+ if (local->fop_lock_state != AFR_FOP_LOCK_PARALLEL) {
+ afr_fop_lock_unwind(frame, local->op, local->op_ret, local->op_errno,
+ local->xdata_rsp);
+ return;
+ }
+ /* At least one child is up */
+ /*
+ * Non-blocking locks also need to be serialized. Otherwise there is
+ * a chance that both the mounts which issued same non-blocking inodelk
+ * may endup not acquiring the lock on any-brick.
+ * Ex: Mount1 and Mount2
+ * request for full length lock on file f1. Mount1 afr may acquire the
+ * partial lock on brick-1 and may not acquire the lock on brick-2
+ * because Mount2 already got the lock on brick-2, vice versa. Since
+ * both the mounts only got partial locks, afr treats them as failure in
+ * gaining the locks and unwinds with EAGAIN errno.
+ */
+ local->op_ret = -1;
+ local->op_errno = EUCLEAN;
+ local->fop_lock_state = AFR_FOP_LOCK_SERIAL;
+ afr_local_replies_wipe(local, priv);
+ if (local->xdata_rsp)
+ dict_unref(local->xdata_rsp);
+ local->xdata_rsp = NULL;
+ switch (local->op) {
+ case GF_FOP_INODELK:
+ case GF_FOP_FINODELK:
+ local->cont.inodelk.cmd = local->cont.inodelk.in_cmd;
+ local->cont.inodelk.flock = local->cont.inodelk.in_flock;
+ if (local->cont.inodelk.xdata)
+ dict_unref(local->cont.inodelk.xdata);
+ local->cont.inodelk.xdata = NULL;
+ if (local->xdata_req)
+ local->cont.inodelk.xdata = dict_ref(local->xdata_req);
+ break;
+ case GF_FOP_ENTRYLK:
+ case GF_FOP_FENTRYLK:
+ local->cont.entrylk.cmd = local->cont.entrylk.in_cmd;
+ if (local->cont.entrylk.xdata)
+ dict_unref(local->cont.entrylk.xdata);
+ local->cont.entrylk.xdata = NULL;
+ if (local->xdata_req)
+ local->cont.entrylk.xdata = dict_ref(local->xdata_req);
+ break;
+ default:
+ break;
+ }
+ afr_serialized_lock_wind(frame, frame->this);
}
+static int32_t
+afr_unlock_partial_lock_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *xdata)
-int
-afr_fsyncdir (call_frame_t *frame, xlator_t *this, fd_t *fd, int32_t datasync,
- dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int i = 0;
- int32_t call_count = 0;
- int32_t op_errno = ENOMEM;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int call_count = -1;
+ int child_index = (long)cookie;
+ uuid_t gfid = {0};
- priv = this->private;
+ local = frame->local;
+ priv = this->private;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ if (op_ret < 0 && op_errno != ENOTCONN) {
+ if (local->fd)
+ gf_uuid_copy(gfid, local->fd->inode->gfid);
+ else
+ loc_gfid(&local->loc, gfid);
+ gf_msg(this->name, GF_LOG_ERROR, op_errno, AFR_MSG_UNLOCK_FAIL,
+ "%s: Failed to unlock %s on %s "
+ "with lk_owner: %s",
+ uuid_utoa(gfid), gf_fop_list[local->op],
+ priv->children[child_index]->name,
+ lkowner_utoa(&frame->root->lk_owner));
+ }
- call_count = local->call_count;
- if (!call_count) {
- op_errno = ENOTCONN;
- goto out;
- }
+ call_count = afr_frame_return(frame);
+ if (call_count == 0)
+ afr_fop_lock_proceed(frame);
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND (frame, afr_fsyncdir_cbk,
- priv->children[i],
- priv->children[i]->fops->fsyncdir,
- fd, datasync, xdata);
- if (!--call_count)
- break;
- }
- }
+ return 0;
+}
- return 0;
-out:
- AFR_STACK_UNWIND (fsyncdir, frame, -1, op_errno, NULL);
+static int32_t
+afr_unlock_locks_and_proceed(call_frame_t *frame, xlator_t *this,
+ int call_count)
+{
+ int i = 0;
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+
+ if (call_count == 0) {
+ afr_fop_lock_proceed(frame);
+ goto out;
+ }
+
+ local = frame->local;
+ priv = this->private;
+ local->call_count = call_count;
+ switch (local->op) {
+ case GF_FOP_INODELK:
+ case GF_FOP_FINODELK:
+ local->cont.inodelk.flock.l_type = F_UNLCK;
+ local->cont.inodelk.cmd = F_SETLK;
+ if (local->cont.inodelk.xdata)
+ dict_unref(local->cont.inodelk.xdata);
+ local->cont.inodelk.xdata = NULL;
+ break;
+ case GF_FOP_ENTRYLK:
+ case GF_FOP_FENTRYLK:
+ local->cont.entrylk.cmd = ENTRYLK_UNLOCK;
+ if (local->cont.entrylk.xdata)
+ dict_unref(local->cont.entrylk.xdata);
+ local->cont.entrylk.xdata = NULL;
+ break;
+ default:
+ break;
+ }
- return 0;
-}
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->replies[i].valid)
+ continue;
-/* }}} */
+ if (local->replies[i].op_ret == -1)
+ continue;
-/* {{{ xattrop */
+ afr_fop_lock_wind(frame, this, i, afr_unlock_partial_lock_cbk);
+
+ if (!--call_count)
+ break;
+ }
+
+out:
+ return 0;
+}
int32_t
-afr_xattrop_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- dict_t *xattr, dict_t *xdata)
+afr_fop_lock_done(call_frame_t *frame, xlator_t *this)
{
- afr_local_t *local = NULL;
- int call_count = -1;
+ int i = 0;
+ int lock_count = 0;
+ unsigned char *success = NULL;
- local = frame->local;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
- LOCK (&frame->lock);
- {
- if (op_ret == 0) {
- if (!local->cont.xattrop.xattr)
- local->cont.xattrop.xattr = dict_ref (xattr);
+ local = frame->local;
+ priv = this->private;
+ success = alloca0(priv->child_count);
- if (!local->xdata_rsp && xdata)
- local->xdata_rsp = dict_ref (xdata);
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->replies[i].valid)
+ continue;
- local->op_ret = 0;
- }
-
- local->op_errno = op_errno;
+ if (local->replies[i].op_ret == 0) {
+ lock_count++;
+ success[i] = 1;
}
- UNLOCK (&frame->lock);
- call_count = afr_frame_return (frame);
+ if (local->op_ret == -1 && local->op_errno == EAGAIN)
+ continue;
- if (call_count == 0)
- AFR_STACK_UNWIND (xattrop, frame, local->op_ret, local->op_errno,
- local->cont.xattrop.xattr, local->xdata_rsp);
+ if ((local->replies[i].op_ret == -1) &&
+ (local->replies[i].op_errno == EAGAIN)) {
+ local->op_ret = -1;
+ local->op_errno = EAGAIN;
+ continue;
+ }
- return 0;
-}
+ if (local->replies[i].op_ret == 0)
+ local->op_ret = 0;
+ local->op_errno = local->replies[i].op_errno;
+ }
-int32_t
-afr_xattrop (call_frame_t *frame, xlator_t *this, loc_t *loc,
- gf_xattrop_flags_t optype, dict_t *xattr, dict_t *xdata)
-{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int i = 0;
- int32_t call_count = 0;
- int32_t op_errno = ENOMEM;
+ if (afr_fop_lock_is_unlock(frame))
+ goto unwind;
- priv = this->private;
+ if (afr_is_conflicting_lock_present(local->op_ret, local->op_errno)) {
+ afr_unlock_locks_and_proceed(frame, this, lock_count);
+ } else if (priv->quorum_count && !afr_has_quorum(success, this, NULL)) {
+ local->fop_lock_state = AFR_FOP_LOCK_QUORUM_FAILED;
+ local->op_ret = -1;
+ local->op_errno = afr_final_errno(local, priv);
+ if (local->op_errno == 0)
+ local->op_errno = afr_quorum_errno(priv);
+ afr_unlock_locks_and_proceed(frame, this, lock_count);
+ } else {
+ goto unwind;
+ }
+
+ return 0;
+unwind:
+ afr_fop_lock_unwind(frame, local->op, local->op_ret, local->op_errno,
+ local->xdata_rsp);
+ return 0;
+}
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+static int
+afr_common_lock_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *xdata)
+{
+ afr_local_t *local = NULL;
+ int child_index = (long)cookie;
- call_count = local->call_count;
- if (!call_count) {
- op_errno = ENOTCONN;
- goto out;
- }
+ local = frame->local;
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND (frame, afr_xattrop_cbk,
- priv->children[i],
- priv->children[i]->fops->xattrop,
- loc, optype, xattr, xdata);
- if (!--call_count)
- break;
- }
+ local->replies[child_index].valid = 1;
+ local->replies[child_index].op_ret = op_ret;
+ local->replies[child_index].op_errno = op_errno;
+ if (op_ret == 0 && xdata) {
+ local->replies[child_index].xdata = dict_ref(xdata);
+ LOCK(&frame->lock);
+ {
+ if (!local->xdata_rsp)
+ local->xdata_rsp = dict_ref(xdata);
}
-
- return 0;
-out:
- AFR_STACK_UNWIND (xattrop, frame, -1, op_errno, NULL, NULL);
-
- return 0;
+ UNLOCK(&frame->lock);
+ }
+ return 0;
}
-/* }}} */
-
-/* {{{ fxattrop */
+static int32_t
+afr_serialized_lock_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *xdata)
-int32_t
-afr_fxattrop_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- dict_t *xattr, dict_t *xdata)
{
- afr_local_t *local = NULL;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int child_index = (long)cookie;
+ int next_child = 0;
- int call_count = -1;
+ local = frame->local;
+ priv = this->private;
- local = frame->local;
+ afr_common_lock_cbk(frame, cookie, this, op_ret, op_errno, xdata);
- LOCK (&frame->lock);
- {
- if (op_ret == 0) {
- if (!local->cont.fxattrop.xattr)
- local->cont.fxattrop.xattr = dict_ref (xattr);
+ for (next_child = child_index + 1; next_child < priv->child_count;
+ next_child++) {
+ if (local->child_up[next_child])
+ break;
+ }
- if (!local->xdata_rsp && xdata)
- local->xdata_rsp = dict_ref (xdata);
- local->op_ret = 0;
- }
+ if (afr_is_conflicting_lock_present(op_ret, op_errno) ||
+ (next_child == priv->child_count)) {
+ afr_fop_lock_done(frame, this);
+ } else {
+ afr_fop_lock_wind(frame, this, next_child, afr_serialized_lock_cbk);
+ }
- local->op_errno = op_errno;
- }
- UNLOCK (&frame->lock);
+ return 0;
+}
- call_count = afr_frame_return (frame);
+static int
+afr_serialized_lock_wind(call_frame_t *frame, xlator_t *this)
+{
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ int i = 0;
- if (call_count == 0)
- AFR_STACK_UNWIND (fxattrop, frame, local->op_ret, local->op_errno,
- local->cont.fxattrop.xattr, local->xdata_rsp);
+ priv = this->private;
+ local = frame->local;
- return 0;
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->child_up[i]) {
+ afr_fop_lock_wind(frame, this, i, afr_serialized_lock_cbk);
+ break;
+ }
+ }
+ return 0;
}
+static int32_t
+afr_parallel_lock_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *xdata)
-int32_t
-afr_fxattrop (call_frame_t *frame, xlator_t *this, fd_t *fd,
- gf_xattrop_flags_t optype, dict_t *xattr, dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int i = 0;
- int32_t call_count = 0;
- int32_t op_errno = 0;
+ int call_count = 0;
- priv = this->private;
+ afr_common_lock_cbk(frame, cookie, this, op_ret, op_errno, xdata);
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ call_count = afr_frame_return(frame);
+ if (call_count == 0)
+ afr_fop_lock_done(frame, this);
- call_count = local->call_count;
- if (!call_count) {
- op_errno = ENOTCONN;
- goto out;
- }
+ return 0;
+}
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND (frame, afr_fxattrop_cbk,
- priv->children[i],
- priv->children[i]->fops->fxattrop,
- fd, optype, xattr, xdata);
- if (!--call_count)
- break;
- }
- }
+static int
+afr_parallel_lock_wind(call_frame_t *frame, xlator_t *this)
+{
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ int call_count = 0;
+ int i = 0;
- return 0;
-out:
- AFR_STACK_UNWIND (fxattrop, frame, -1, op_errno, NULL, NULL);
+ priv = this->private;
+ local = frame->local;
+ call_count = local->call_count;
- return 0;
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->child_up[i])
+ continue;
+ afr_fop_lock_wind(frame, this, i, afr_parallel_lock_cbk);
+ if (!--call_count)
+ break;
+ }
+ return 0;
}
-/* }}} */
-
-int32_t
-afr_unlock_partial_inodelk_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret,
- int32_t op_errno, dict_t *xdata)
-
+static int
+afr_fop_handle_lock(call_frame_t *frame, xlator_t *this)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- int call_count = -1;
- int child_index = (long)cookie;
- uuid_t gfid = {0};
+ afr_local_t *local = frame->local;
+ int op_errno = 0;
- local = frame->local;
- priv = this->private;
+ if (!afr_fop_lock_is_unlock(frame)) {
+ if (!afr_is_consistent_io_possible(local, this->private, &op_errno))
+ goto out;
- if (op_ret < 0 && op_errno != ENOTCONN) {
- loc_gfid (&local->loc, gfid);
- gf_msg (this->name, GF_LOG_ERROR, 0,
- AFR_MSG_INODE_UNLOCK_FAIL,
- "%s: Failed to unlock %s "
- "with lk_owner: %s (%s)", uuid_utoa (gfid),
- priv->children[child_index]->name,
- lkowner_utoa (&frame->root->lk_owner),
- strerror (op_errno));
+ switch (local->op) {
+ case GF_FOP_INODELK:
+ case GF_FOP_FINODELK:
+ local->cont.inodelk.cmd = F_SETLK;
+ break;
+ case GF_FOP_ENTRYLK:
+ case GF_FOP_FENTRYLK:
+ local->cont.entrylk.cmd = ENTRYLK_LOCK_NB;
+ break;
+ default:
+ break;
}
+ }
- call_count = afr_frame_return (frame);
- if (call_count == 0) {
- AFR_STACK_UNWIND (inodelk, frame, local->op_ret,
- local->op_errno, local->xdata_rsp);
+ if (local->xdata_req) {
+ switch (local->op) {
+ case GF_FOP_INODELK:
+ case GF_FOP_FINODELK:
+ local->cont.inodelk.xdata = dict_ref(local->xdata_req);
+ break;
+ case GF_FOP_ENTRYLK:
+ case GF_FOP_FENTRYLK:
+ local->cont.entrylk.xdata = dict_ref(local->xdata_req);
+ break;
+ default:
+ break;
}
+ }
- return 0;
+ local->fop_lock_state = AFR_FOP_LOCK_PARALLEL;
+ afr_parallel_lock_wind(frame, this);
+out:
+ return -op_errno;
}
-int32_t
-afr_unlock_inodelks_and_unwind (call_frame_t *frame, xlator_t *this,
- int call_count)
-{
- int i = 0;
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
-
- local = frame->local;
- priv = this->private;
- local->call_count = call_count;
- local->cont.inodelk.flock.l_type = F_UNLCK;
-
- for (i = 0; i < priv->child_count; i++) {
- if (!local->replies[i].valid)
- continue;
-
- if (local->replies[i].op_ret == -1)
- continue;
-
- STACK_WIND_COOKIE (frame, afr_unlock_partial_inodelk_cbk,
- (void*) (long) i,
- priv->children[i],
- priv->children[i]->fops->inodelk,
- local->cont.inodelk.volume,
- &local->loc, local->cont.inodelk.cmd,
- &local->cont.inodelk.flock, 0);
-
- if (!--call_count)
- break;
- }
+static int32_t
+afr_handle_inodelk(call_frame_t *frame, xlator_t *this, glusterfs_fop_t fop,
+ const char *volume, loc_t *loc, fd_t *fd, int32_t cmd,
+ struct gf_flock *flock, dict_t *xdata)
+{
+ afr_local_t *local = NULL;
+ int32_t op_errno = ENOMEM;
+
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
+
+ local->op = fop;
+ if (loc)
+ loc_copy(&local->loc, loc);
+ if (fd && (flock->l_type != F_UNLCK)) {
+ AFR_ERROR_OUT_IF_FDCTX_INVALID(fd, this, op_errno, out);
+ local->fd = fd_ref(fd);
+ }
+
+ local->cont.inodelk.volume = gf_strdup(volume);
+ if (!local->cont.inodelk.volume) {
+ op_errno = ENOMEM;
+ goto out;
+ }
+
+ local->cont.inodelk.in_cmd = cmd;
+ local->cont.inodelk.cmd = cmd;
+ local->cont.inodelk.in_flock = *flock;
+ local->cont.inodelk.flock = *flock;
+ if (xdata)
+ local->xdata_req = dict_ref(xdata);
+
+ op_errno = -afr_fop_handle_lock(frame, frame->this);
+ if (op_errno)
+ goto out;
+ return 0;
+out:
+ afr_fop_lock_unwind(frame, fop, -1, op_errno, NULL);
- return 0;
+ return 0;
}
int32_t
-afr_inodelk_done (call_frame_t *frame, xlator_t *this)
+afr_inodelk(call_frame_t *frame, xlator_t *this, const char *volume, loc_t *loc,
+ int32_t cmd, struct gf_flock *flock, dict_t *xdata)
{
- int i = 0;
- int lock_count = 0;
-
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
+ afr_handle_inodelk(frame, this, GF_FOP_INODELK, volume, loc, NULL, cmd,
+ flock, xdata);
+ return 0;
+}
- local = frame->local;
- priv = this->private;
+int32_t
+afr_finodelk(call_frame_t *frame, xlator_t *this, const char *volume, fd_t *fd,
+ int32_t cmd, struct gf_flock *flock, dict_t *xdata)
+{
+ afr_handle_inodelk(frame, this, GF_FOP_FINODELK, volume, NULL, fd, cmd,
+ flock, xdata);
+ return 0;
+}
- for (i = 0; i < priv->child_count; i++) {
- if (!local->replies[i].valid)
- continue;
+static int
+afr_handle_entrylk(call_frame_t *frame, xlator_t *this, glusterfs_fop_t fop,
+ const char *volume, loc_t *loc, fd_t *fd,
+ const char *basename, entrylk_cmd cmd, entrylk_type type,
+ dict_t *xdata)
+{
+ afr_local_t *local = NULL;
+ int32_t op_errno = ENOMEM;
+
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
+
+ local->op = fop;
+ if (loc)
+ loc_copy(&local->loc, loc);
+ if (fd && (cmd != ENTRYLK_UNLOCK)) {
+ AFR_ERROR_OUT_IF_FDCTX_INVALID(fd, this, op_errno, out);
+ local->fd = fd_ref(fd);
+ }
+ local->cont.entrylk.cmd = cmd;
+ local->cont.entrylk.in_cmd = cmd;
+ local->cont.entrylk.type = type;
+ local->cont.entrylk.volume = gf_strdup(volume);
+ local->cont.entrylk.basename = gf_strdup(basename);
+ if (!local->cont.entrylk.volume || !local->cont.entrylk.basename) {
+ op_errno = ENOMEM;
+ goto out;
+ }
+ if (xdata)
+ local->xdata_req = dict_ref(xdata);
+ op_errno = -afr_fop_handle_lock(frame, frame->this);
+ if (op_errno)
+ goto out;
+
+ return 0;
+out:
+ afr_fop_lock_unwind(frame, fop, -1, op_errno, NULL);
+ return 0;
+}
- if (local->replies[i].op_ret == 0)
- lock_count++;
+int
+afr_entrylk(call_frame_t *frame, xlator_t *this, const char *volume, loc_t *loc,
+ const char *basename, entrylk_cmd cmd, entrylk_type type,
+ dict_t *xdata)
+{
+ afr_handle_entrylk(frame, this, GF_FOP_ENTRYLK, volume, loc, NULL, basename,
+ cmd, type, xdata);
+ return 0;
+}
- if (local->op_ret == -1 && local->op_errno == EAGAIN)
- continue;
+int
+afr_fentrylk(call_frame_t *frame, xlator_t *this, const char *volume, fd_t *fd,
+ const char *basename, entrylk_cmd cmd, entrylk_type type,
+ dict_t *xdata)
+{
+ afr_handle_entrylk(frame, this, GF_FOP_FENTRYLK, volume, NULL, fd, basename,
+ cmd, type, xdata);
+ return 0;
+}
- if ((local->replies[i].op_ret == -1) &&
- (local->replies[i].op_errno == EAGAIN)) {
- local->op_ret = -1;
- local->op_errno = EAGAIN;
- continue;
- }
+int
+afr_statfs_cbk(call_frame_t *frame, void *cookie, xlator_t *this, int op_ret,
+ int op_errno, struct statvfs *statvfs, dict_t *xdata)
+{
+ afr_local_t *local = NULL;
+ int call_count = 0;
+ struct statvfs *buf = NULL;
- if (local->replies[i].op_ret == 0)
- local->op_ret = 0;
+ local = frame->local;
- local->op_errno = local->replies[i].op_errno;
+ LOCK(&frame->lock);
+ {
+ if (op_ret != 0) {
+ local->op_errno = op_errno;
+ goto unlock;
}
- if (lock_count && local->cont.inodelk.flock.l_type != F_UNLCK &&
- (local->op_ret == -1 && local->op_errno == EAGAIN)) {
- afr_unlock_inodelks_and_unwind (frame, this,
- lock_count);
+ local->op_ret = op_ret;
+
+ buf = &local->cont.statfs.buf;
+ if (local->cont.statfs.buf_set) {
+ if (statvfs->f_bavail < buf->f_bavail) {
+ *buf = *statvfs;
+ if (xdata) {
+ if (local->xdata_rsp)
+ dict_unref(local->xdata_rsp);
+ local->xdata_rsp = dict_ref(xdata);
+ }
+ }
} else {
- AFR_STACK_UNWIND (inodelk, frame, local->op_ret,
- local->op_errno, local->xdata_rsp);
+ *buf = *statvfs;
+ local->cont.statfs.buf_set = 1;
+ if (xdata)
+ local->xdata_rsp = dict_ref(xdata);
}
+ }
+unlock:
+ call_count = --local->call_count;
+ UNLOCK(&frame->lock);
- return 0;
+ if (call_count == 0)
+ AFR_STACK_UNWIND(statfs, frame, local->op_ret, local->op_errno,
+ &local->cont.statfs.buf, local->xdata_rsp);
+
+ return 0;
}
int
-afr_common_inodelk_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, dict_t *xdata)
-{
- afr_local_t *local = NULL;
- int child_index = (long)cookie;
+afr_statfs(call_frame_t *frame, xlator_t *this, loc_t *loc, dict_t *xdata)
+{
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int i = 0;
+ int call_count = 0;
+ int32_t op_errno = ENOMEM;
+
+ priv = this->private;
+
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
+
+ local->op = GF_FOP_STATFS;
+ if (!afr_is_consistent_io_possible(local, priv, &op_errno))
+ goto out;
+
+ if (priv->arbiter_count == 1 && local->child_up[ARBITER_BRICK_INDEX])
+ local->call_count--;
+ call_count = local->call_count;
+ if (!call_count) {
+ op_errno = ENOTCONN;
+ goto out;
+ }
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->child_up[i]) {
+ if (AFR_IS_ARBITER_BRICK(priv, i))
+ continue;
+ STACK_WIND(frame, afr_statfs_cbk, priv->children[i],
+ priv->children[i]->fops->statfs, loc, xdata);
+ if (!--call_count)
+ break;
+ }
+ }
- local = frame->local;
+ return 0;
+out:
+ AFR_STACK_UNWIND(statfs, frame, -1, op_errno, NULL, NULL);
- local->replies[child_index].valid = 1;
- local->replies[child_index].op_ret = op_ret;
- local->replies[child_index].op_errno = op_errno;
- if (op_ret == 0 && xdata) {
- local->replies[child_index].xdata = dict_ref (xdata);
- LOCK (&frame->lock);
- {
- if (!local->xdata_rsp)
- local->xdata_rsp = dict_ref (xdata);
- }
- UNLOCK (&frame->lock);
- }
- return 0;
+ return 0;
}
-static int32_t
-afr_parallel_inodelk_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, dict_t *xdata)
-
+int32_t
+afr_lk_unlock_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, struct gf_flock *lock,
+ dict_t *xdata)
{
- int call_count = 0;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = this->private;
+ int call_count = -1;
+ int child_index = (long)cookie;
- afr_common_inodelk_cbk (frame, cookie, this, op_ret, op_errno, xdata);
+ local = frame->local;
- call_count = afr_frame_return (frame);
- if (call_count == 0)
- afr_inodelk_done (frame, this);
+ if (op_ret < 0 && op_errno != ENOTCONN && op_errno != EBADFD) {
+ gf_msg(this->name, GF_LOG_ERROR, op_errno, AFR_MSG_UNLOCK_FAIL,
+ "gfid=%s: unlock failed on subvolume %s "
+ "with lock owner %s",
+ uuid_utoa(local->fd->inode->gfid),
+ priv->children[child_index]->name,
+ lkowner_utoa(&frame->root->lk_owner));
+ }
- return 0;
+ call_count = afr_frame_return(frame);
+ if (call_count == 0) {
+ AFR_STACK_UNWIND(lk, frame, local->op_ret, local->op_errno, NULL,
+ local->xdata_rsp);
+ }
+
+ return 0;
}
-static inline gf_boolean_t
-afr_is_conflicting_lock_present (int32_t op_ret, int32_t op_errno)
+int32_t
+afr_lk_unlock(call_frame_t *frame, xlator_t *this)
{
- if (op_ret == -1 && op_errno == EAGAIN)
- return _gf_true;
- return _gf_false;
-}
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int i = 0;
+ int call_count = 0;
-static int32_t
-afr_serialized_inodelk_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, dict_t *xdata)
+ local = frame->local;
+ priv = this->private;
-{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- int child_index = (long)cookie;
- int next_child = 0;
+ call_count = afr_locked_nodes_count(local->cont.lk.locked_nodes,
+ priv->child_count);
- local = frame->local;
- priv = this->private;
+ if (call_count == 0) {
+ AFR_STACK_UNWIND(lk, frame, local->op_ret, local->op_errno, NULL,
+ local->xdata_rsp);
+ return 0;
+ }
- afr_common_inodelk_cbk (frame, cookie, this, op_ret, op_errno, xdata);
+ local->call_count = call_count;
- for (next_child = child_index + 1; next_child < priv->child_count;
- next_child++) {
- if (local->child_up[next_child])
- break;
- }
+ local->cont.lk.user_flock.l_type = F_UNLCK;
- if (afr_is_conflicting_lock_present (op_ret, op_errno) ||
- (next_child == priv->child_count)) {
- afr_inodelk_done (frame, this);
- } else {
- STACK_WIND_COOKIE (frame, afr_serialized_inodelk_cbk,
- (void *) (long) next_child,
- priv->children[next_child],
- priv->children[next_child]->fops->inodelk,
- (const char *)local->cont.inodelk.volume,
- &local->loc, local->cont.inodelk.cmd,
- &local->cont.inodelk.flock,
- local->xdata_req);
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->cont.lk.locked_nodes[i]) {
+ STACK_WIND_COOKIE(frame, afr_lk_unlock_cbk, (void *)(long)i,
+ priv->children[i], priv->children[i]->fops->lk,
+ local->fd, F_SETLK, &local->cont.lk.user_flock,
+ NULL);
+
+ if (!--call_count)
+ break;
}
+ }
- return 0;
+ return 0;
}
-static int
-afr_parallel_inodelk_wind (call_frame_t *frame, xlator_t *this)
+int32_t
+afr_lk_cbk(call_frame_t *frame, void *cookie, xlator_t *this, int32_t op_ret,
+ int32_t op_errno, struct gf_flock *lock, dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int call_count = 0;
- int i = 0;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int child_index = -1;
- priv = this->private;
- local = frame->local;
- call_count = local->call_count;
+ local = frame->local;
+ priv = this->private;
- for (i = 0; i < priv->child_count; i++) {
- if (!local->child_up[i])
- continue;
- STACK_WIND_COOKIE (frame, afr_parallel_inodelk_cbk,
- (void *) (long) i,
- priv->children[i],
- priv->children[i]->fops->inodelk,
- (const char *)local->cont.inodelk.volume,
- &local->loc, local->cont.inodelk.cmd,
- &local->cont.inodelk.flock,
- local->xdata_req);
- if (!--call_count)
- break;
- }
+ child_index = (long)cookie;
+
+ afr_common_lock_cbk(frame, cookie, this, op_ret, op_errno, xdata);
+ if (op_ret < 0 && op_errno == EAGAIN) {
+ local->op_ret = -1;
+ local->op_errno = EAGAIN;
+
+ afr_lk_unlock(frame, this);
return 0;
-}
+ }
+
+ if (op_ret == 0) {
+ local->op_ret = 0;
+ local->op_errno = 0;
+ local->cont.lk.locked_nodes[child_index] = 1;
+ local->cont.lk.ret_flock = *lock;
+ }
+
+ child_index++;
+
+ if (child_index < priv->child_count) {
+ STACK_WIND_COOKIE(frame, afr_lk_cbk, (void *)(long)child_index,
+ priv->children[child_index],
+ priv->children[child_index]->fops->lk, local->fd,
+ local->cont.lk.cmd, &local->cont.lk.user_flock,
+ local->xdata_req);
+ } else if (priv->quorum_count &&
+ !afr_has_quorum(local->cont.lk.locked_nodes, this, NULL)) {
+ local->op_ret = -1;
+ local->op_errno = afr_final_errno(local, priv);
-static int
-afr_serialized_inodelk_wind (call_frame_t *frame, xlator_t *this)
-{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int i = 0;
+ afr_lk_unlock(frame, this);
+ } else {
+ if (local->op_ret < 0)
+ local->op_errno = afr_final_errno(local, priv);
- priv = this->private;
- local = frame->local;
+ AFR_STACK_UNWIND(lk, frame, local->op_ret, local->op_errno,
+ &local->cont.lk.ret_flock, local->xdata_rsp);
+ }
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND_COOKIE (frame, afr_serialized_inodelk_cbk,
- (void *) (long) i,
- priv->children[i],
- priv->children[i]->fops->inodelk,
- (const char *)local->cont.inodelk.volume,
- &local->loc, local->cont.inodelk.cmd,
- &local->cont.inodelk.flock,
- local->xdata_req);
- break;
- }
- }
- return 0;
+ return 0;
}
-int32_t
-afr_inodelk (call_frame_t *frame, xlator_t *this,
- const char *volume, loc_t *loc, int32_t cmd,
- struct gf_flock *flock, dict_t *xdata)
+int
+afr_lk_transaction_cbk(int ret, call_frame_t *frame, void *opaque)
{
- afr_local_t *local = NULL;
- int32_t op_errno = ENOMEM;
+ return 0;
+}
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+int
+afr_lk_txn_wind_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, struct gf_flock *lock,
+ dict_t *xdata)
+{
+ afr_local_t *local = NULL;
+ int child_index = -1;
+
+ local = frame->local;
+ child_index = (long)cookie;
+ afr_common_lock_cbk(frame, cookie, this, op_ret, op_errno, xdata);
+ if (op_ret == 0) {
+ local->op_ret = 0;
+ local->op_errno = 0;
+ local->cont.lk.locked_nodes[child_index] = 1;
+ local->cont.lk.ret_flock = *lock;
+ }
+ syncbarrier_wake(&local->barrier);
+ return 0;
+}
- loc_copy (&local->loc, loc);
- local->cont.inodelk.volume = gf_strdup (volume);
- if (!local->cont.inodelk.volume) {
- op_errno = ENOMEM;
- goto out;
+int
+afr_lk_txn_unlock_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, struct gf_flock *lock,
+ dict_t *xdata)
+{
+ afr_local_t *local = frame->local;
+ afr_private_t *priv = this->private;
+ int child_index = (long)cookie;
+
+ if (op_ret < 0 && op_errno != ENOTCONN && op_errno != EBADFD) {
+ gf_msg(this->name, GF_LOG_ERROR, op_errno, AFR_MSG_UNLOCK_FAIL,
+ "gfid=%s: unlock failed on subvolume %s "
+ "with lock owner %s",
+ uuid_utoa(local->fd->inode->gfid),
+ priv->children[child_index]->name,
+ lkowner_utoa(&frame->root->lk_owner));
+ }
+ return 0;
+}
+int
+afr_lk_transaction(void *opaque)
+{
+ call_frame_t *frame = NULL;
+ xlator_t *this = NULL;
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ char *wind_on = NULL;
+ int op_errno = 0;
+ int i = 0;
+ int ret = 0;
+
+ frame = (call_frame_t *)opaque;
+ local = frame->local;
+ this = frame->this;
+ priv = this->private;
+ wind_on = alloca0(priv->child_count);
+
+ if (priv->arbiter_count || priv->child_count != 3) {
+ op_errno = ENOTSUP;
+ gf_msg(frame->this->name, GF_LOG_ERROR, op_errno, AFR_MSG_LK_HEAL_DOM,
+ "%s: Lock healing supported only for replica 3 volumes.",
+ uuid_utoa(local->fd->inode->gfid));
+ goto err;
+ }
+
+ op_errno = -afr_dom_lock_acquire(frame); // Released during
+ // AFR_STACK_UNWIND
+ if (op_errno != 0) {
+ goto err;
+ }
+ if (priv->quorum_count &&
+ !afr_has_quorum(local->cont.lk.dom_locked_nodes, this, NULL)) {
+ op_errno = afr_final_errno(local, priv);
+ goto err;
+ }
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (priv->child_up[i] && local->cont.lk.dom_locked_nodes[i])
+ wind_on[i] = 1;
+ }
+ AFR_ONLIST(wind_on, frame, afr_lk_txn_wind_cbk, lk, local->fd,
+ local->cont.lk.cmd, &local->cont.lk.user_flock,
+ local->xdata_req);
+
+ if (priv->quorum_count &&
+ !afr_has_quorum(local->cont.lk.locked_nodes, this, NULL)) {
+ local->op_ret = -1;
+ local->op_errno = afr_final_errno(local, priv);
+ goto unlock;
+ } else {
+ if (local->cont.lk.user_flock.l_type == F_UNLCK)
+ ret = afr_remove_lock_from_saved_locks(local, this);
+ else
+ ret = afr_add_lock_to_saved_locks(frame, this);
+ if (ret) {
+ local->op_ret = -1;
+ local->op_errno = -ret;
+ goto unlock;
}
+ AFR_STACK_UNWIND(lk, frame, local->op_ret, local->op_errno,
+ &local->cont.lk.ret_flock, local->xdata_rsp);
+ }
- local->cont.inodelk.cmd = cmd;
- local->cont.inodelk.flock = *flock;
- if (xdata)
- local->xdata_req = dict_ref (xdata);
-
- /* At least one child is up */
- /*
- * Non-blocking locks also need to be serialized. Otherwise there is
- * a chance that both the mounts which issued same non-blocking inodelk
- * may endup not acquiring the lock on any-brick.
- * Ex: Mount1 and Mount2
- * request for full length lock on file f1. Mount1 afr may acquire the
- * partial lock on brick-1 and may not acquire the lock on brick-2
- * because Mount2 already got the lock on brick-2, vice versa. Since
- * both the mounts only got partial locks, afr treats them as failure in
- * gaining the locks and unwinds with EAGAIN errno.
- */
- if (flock->l_type == F_UNLCK) {
- afr_parallel_inodelk_wind (frame, this);
- } else {
- afr_serialized_inodelk_wind (frame, this);
+ return 0;
+
+unlock:
+ local->cont.lk.user_flock.l_type = F_UNLCK;
+ AFR_ONLIST(local->cont.lk.locked_nodes, frame, afr_lk_txn_unlock_cbk, lk,
+ local->fd, F_SETLK, &local->cont.lk.user_flock, NULL);
+err:
+ AFR_STACK_UNWIND(lk, frame, -1, op_errno, NULL, NULL);
+ return -1;
+}
+
+int
+afr_lk(call_frame_t *frame, xlator_t *this, fd_t *fd, int32_t cmd,
+ struct gf_flock *flock, dict_t *xdata)
+{
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ int ret = 0;
+ int i = 0;
+ int32_t op_errno = ENOMEM;
+
+ priv = this->private;
+
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
+
+ local->op = GF_FOP_LK;
+ if (!afr_lk_is_unlock(cmd, flock)) {
+ AFR_ERROR_OUT_IF_FDCTX_INVALID(fd, this, op_errno, out);
+ if (!afr_is_consistent_io_possible(local, priv, &op_errno))
+ goto out;
+ }
+
+ local->cont.lk.locked_nodes = GF_CALLOC(
+ priv->child_count, sizeof(*local->cont.lk.locked_nodes),
+ gf_afr_mt_char);
+
+ if (!local->cont.lk.locked_nodes) {
+ op_errno = ENOMEM;
+ goto out;
+ }
+
+ local->fd = fd_ref(fd);
+ local->cont.lk.cmd = cmd;
+ local->cont.lk.user_flock = *flock;
+ local->cont.lk.ret_flock = *flock;
+ if (xdata)
+ local->xdata_req = dict_ref(xdata);
+
+ if (afr_is_lock_mode_mandatory(xdata)) {
+ ret = synctask_new(this->ctx->env, afr_lk_transaction,
+ afr_lk_transaction_cbk, frame, frame);
+ if (ret) {
+ op_errno = ENOMEM;
+ goto out;
}
+ return 0;
+ }
+
+ STACK_WIND_COOKIE(frame, afr_lk_cbk, (void *)(long)0, priv->children[i],
+ priv->children[i]->fops->lk, fd, cmd, flock,
+ local->xdata_req);
- return 0;
+ return 0;
out:
- AFR_STACK_UNWIND (inodelk, frame, -1, op_errno, NULL);
+ AFR_STACK_UNWIND(lk, frame, -1, op_errno, NULL, NULL);
- return 0;
+ return 0;
}
-
int32_t
-afr_finodelk_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, dict_t *xdata)
-
+afr_lease_unlock_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, struct gf_lease *lease,
+ dict_t *xdata)
{
- afr_local_t *local = NULL;
- int call_count = -1;
-
- local = frame->local;
-
- LOCK (&frame->lock);
- {
- if (op_ret == 0)
- local->op_ret = 0;
-
- local->op_errno = op_errno;
- }
- UNLOCK (&frame->lock);
+ afr_local_t *local = NULL;
+ int call_count = -1;
- call_count = afr_frame_return (frame);
+ local = frame->local;
+ call_count = afr_frame_return(frame);
- if (call_count == 0)
- AFR_STACK_UNWIND (finodelk, frame, local->op_ret,
- local->op_errno, xdata);
+ if (call_count == 0)
+ AFR_STACK_UNWIND(lease, frame, local->op_ret, local->op_errno, lease,
+ xdata);
- return 0;
+ return 0;
}
-
int32_t
-afr_finodelk (call_frame_t *frame, xlator_t *this, const char *volume, fd_t *fd,
- int32_t cmd, struct gf_flock *flock, dict_t *xdata)
+afr_lease_unlock(call_frame_t *frame, xlator_t *this)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int i = 0;
- int32_t call_count = 0;
- int32_t op_errno = ENOMEM;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int i = 0;
+ int call_count = 0;
- priv = this->private;
+ local = frame->local;
+ priv = this->private;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ call_count = afr_locked_nodes_count(local->cont.lease.locked_nodes,
+ priv->child_count);
- call_count = local->call_count;
- if (!call_count) {
- op_errno = ENOTCONN;
- goto out;
- }
+ if (call_count == 0) {
+ AFR_STACK_UNWIND(lease, frame, local->op_ret, local->op_errno,
+ &local->cont.lease.ret_lease, NULL);
+ return 0;
+ }
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND (frame, afr_finodelk_cbk,
- priv->children[i],
- priv->children[i]->fops->finodelk,
- volume, fd, cmd, flock, xdata);
-
- if (!--call_count)
- break;
- }
- }
+ local->call_count = call_count;
- return 0;
-out:
- AFR_STACK_UNWIND (finodelk, frame, -1, op_errno, NULL);
+ local->cont.lease.user_lease.cmd = GF_UNLK_LEASE;
- return 0;
-}
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->cont.lease.locked_nodes[i]) {
+ STACK_WIND(frame, afr_lease_unlock_cbk, priv->children[i],
+ priv->children[i]->fops->lease, &local->loc,
+ &local->cont.lease.user_lease, NULL);
+ if (!--call_count)
+ break;
+ }
+ }
+
+ return 0;
+}
int32_t
-afr_entrylk_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, dict_t *xdata)
+afr_lease_cbk(call_frame_t *frame, void *cookie, xlator_t *this, int32_t op_ret,
+ int32_t op_errno, struct gf_lease *lease, dict_t *xdata)
{
- afr_local_t *local = NULL;
- int call_count = -1;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int child_index = -1;
- local = frame->local;
+ local = frame->local;
+ priv = this->private;
- LOCK (&frame->lock);
- {
- if (op_ret == 0)
- local->op_ret = 0;
+ child_index = (long)cookie;
- local->op_errno = op_errno;
- }
- UNLOCK (&frame->lock);
+ afr_common_lock_cbk(frame, cookie, this, op_ret, op_errno, xdata);
+ if (op_ret < 0 && op_errno == EAGAIN) {
+ local->op_ret = -1;
+ local->op_errno = EAGAIN;
- call_count = afr_frame_return (frame);
+ afr_lease_unlock(frame, this);
+ return 0;
+ }
+
+ if (op_ret == 0) {
+ local->op_ret = 0;
+ local->op_errno = 0;
+ local->cont.lease.locked_nodes[child_index] = 1;
+ local->cont.lease.ret_lease = *lease;
+ }
+
+ child_index++;
+ if (child_index < priv->child_count) {
+ STACK_WIND_COOKIE(frame, afr_lease_cbk, (void *)(long)child_index,
+ priv->children[child_index],
+ priv->children[child_index]->fops->lease, &local->loc,
+ &local->cont.lease.user_lease, xdata);
+ } else if (priv->quorum_count &&
+ !afr_has_quorum(local->cont.lease.locked_nodes, this, NULL)) {
+ local->op_ret = -1;
+ local->op_errno = afr_final_errno(local, priv);
- if (call_count == 0)
- AFR_STACK_UNWIND (entrylk, frame, local->op_ret,
- local->op_errno, xdata);
+ afr_lease_unlock(frame, this);
+ } else {
+ if (local->op_ret < 0)
+ local->op_errno = afr_final_errno(local, priv);
+ AFR_STACK_UNWIND(lease, frame, local->op_ret, local->op_errno,
+ &local->cont.lease.ret_lease, NULL);
+ }
- return 0;
+ return 0;
}
-
int
-afr_entrylk (call_frame_t *frame, xlator_t *this, const char *volume,
- loc_t *loc, const char *basename, entrylk_cmd cmd,
- entrylk_type type, dict_t *xdata)
+afr_lease(call_frame_t *frame, xlator_t *this, loc_t *loc,
+ struct gf_lease *lease, dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int i = 0;
- int32_t call_count = 0;
- int32_t op_errno = 0;
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ int32_t op_errno = ENOMEM;
- priv = this->private;
+ priv = this->private;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
- call_count = local->call_count;
- if (!call_count) {
- op_errno = ENOTCONN;
- goto out;
- }
+ local->op = GF_FOP_LEASE;
+ local->cont.lease.locked_nodes = GF_CALLOC(
+ priv->child_count, sizeof(*local->cont.lease.locked_nodes),
+ gf_afr_mt_char);
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND (frame, afr_entrylk_cbk,
- priv->children[i],
- priv->children[i]->fops->entrylk,
- volume, loc, basename, cmd, type, xdata);
-
- if (!--call_count)
- break;
- }
- }
+ if (!local->cont.lease.locked_nodes) {
+ op_errno = ENOMEM;
+ goto out;
+ }
- return 0;
-out:
- AFR_STACK_UNWIND (entrylk, frame, -1, op_errno, NULL);
+ loc_copy(&local->loc, loc);
+ local->cont.lease.user_lease = *lease;
+ local->cont.lease.ret_lease = *lease;
- return 0;
-}
+ STACK_WIND_COOKIE(frame, afr_lease_cbk, (void *)(long)0, priv->children[0],
+ priv->children[0]->fops->lease, loc, lease, xdata);
+ return 0;
+out:
+ AFR_STACK_UNWIND(lease, frame, -1, op_errno, NULL, NULL);
+ return 0;
+}
int
-afr_fentrylk_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, dict_t *xdata)
-
-{
- afr_local_t *local = NULL;
- int call_count = -1;
-
- local = frame->local;
-
- LOCK (&frame->lock);
- {
- if (op_ret == 0)
- local->op_ret = 0;
-
- local->op_errno = op_errno;
- }
- UNLOCK (&frame->lock);
-
- call_count = afr_frame_return (frame);
+afr_ipc_cbk(call_frame_t *frame, void *cookie, xlator_t *this, int32_t op_ret,
+ int32_t op_errno, dict_t *xdata)
+{
+ afr_local_t *local = NULL;
+ int child_index = (long)cookie;
+ int call_count = 0;
+ gf_boolean_t failed = _gf_false;
+ gf_boolean_t succeeded = _gf_false;
+ int i = 0;
+ afr_private_t *priv = NULL;
+
+ local = frame->local;
+ priv = this->private;
+
+ local->replies[child_index].valid = 1;
+ local->replies[child_index].op_ret = op_ret;
+ local->replies[child_index].op_errno = op_errno;
+ if (xdata)
+ local->replies[child_index].xdata = dict_ref(xdata);
+
+ call_count = afr_frame_return(frame);
+ if (call_count)
+ goto out;
+ /* If any of the subvolumes failed with other than ENOTCONN
+ * return error else return success unless all the subvolumes
+ * failed.
+ * TODO: In case of failure, we need to unregister the xattrs
+ * from the other subvolumes where it succeeded (once upcall
+ * fixes the Bz-1371622)*/
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->replies[i].valid)
+ continue;
+ if (local->replies[i].op_ret < 0 &&
+ local->replies[i].op_errno != ENOTCONN) {
+ local->op_ret = local->replies[i].op_ret;
+ local->op_errno = local->replies[i].op_errno;
+ if (local->xdata_rsp)
+ dict_unref(local->xdata_rsp);
+ local->xdata_rsp = NULL;
+ if (local->replies[i].xdata) {
+ local->xdata_rsp = dict_ref(local->replies[i].xdata);
+ }
+ failed = _gf_true;
+ break;
+ }
+ if (local->replies[i].op_ret == 0) {
+ succeeded = _gf_true;
+ local->op_ret = 0;
+ local->op_errno = 0;
+ if (!local->xdata_rsp && local->replies[i].xdata) {
+ local->xdata_rsp = dict_ref(local->replies[i].xdata);
+ }
+ }
+ }
+
+ if (!succeeded && !failed) {
+ local->op_ret = -1;
+ local->op_errno = ENOTCONN;
+ }
- if (call_count == 0)
- AFR_STACK_UNWIND (fentrylk, frame, local->op_ret,
- local->op_errno, xdata);
+ AFR_STACK_UNWIND(ipc, frame, local->op_ret, local->op_errno,
+ local->xdata_rsp);
- return 0;
+out:
+ return 0;
}
-
int
-afr_fentrylk (call_frame_t *frame, xlator_t *this, const char *volume, fd_t *fd,
- const char *basename, entrylk_cmd cmd, entrylk_type type,
- dict_t *xdata)
+afr_ipc(call_frame_t *frame, xlator_t *this, int32_t op, dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int i = 0;
- int32_t call_count = 0;
- int32_t op_errno = ENOMEM;
+ afr_local_t *local = NULL;
+ int32_t op_errno = -1;
+ afr_private_t *priv = NULL;
+ int i = 0;
+ int call_cnt = -1;
+
+ VALIDATE_OR_GOTO(frame, err);
+ VALIDATE_OR_GOTO(this, err);
+
+ if (op != GF_IPC_TARGET_UPCALL)
+ goto wind_default;
- priv = this->private;
+ VALIDATE_OR_GOTO(this->private, err);
+ priv = this->private;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto err;
- call_count = local->call_count;
- if (!call_count) {
- op_errno = ENOTCONN;
- goto out;
- }
+ call_cnt = local->call_count;
+ if (xdata) {
for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND (frame, afr_fentrylk_cbk,
- priv->children[i],
- priv->children[i]->fops->fentrylk,
- volume, fd, basename, cmd, type, xdata);
-
- if (!--call_count)
- break;
- }
+ if (dict_set_int8(xdata, priv->pending_key[i], 0) < 0)
+ goto err;
}
+ }
- return 0;
-out:
- AFR_STACK_UNWIND (fentrylk, frame, -1, op_errno, NULL);
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->child_up[i])
+ continue;
- return 0;
-}
+ STACK_WIND_COOKIE(frame, afr_ipc_cbk, (void *)(long)i,
+ priv->children[i], priv->children[i]->fops->ipc, op,
+ xdata);
+ if (!--call_cnt)
+ break;
+ }
+ return 0;
+
+err:
+ if (op_errno == -1)
+ op_errno = errno;
+ AFR_STACK_UNWIND(ipc, frame, -1, op_errno, NULL);
+ return 0;
+
+wind_default:
+ STACK_WIND(frame, default_ipc_cbk, FIRST_CHILD(this),
+ FIRST_CHILD(this)->fops->ipc, op, xdata);
+ return 0;
+}
int
-afr_statfs_cbk (call_frame_t *frame, void *cookie, xlator_t *this, int op_ret,
- int op_errno, struct statvfs *statvfs, dict_t *xdata)
+afr_forget(xlator_t *this, inode_t *inode)
{
- afr_local_t *local = NULL;
- int call_count = 0;
- struct statvfs *buf = NULL;
+ uint64_t ctx_int = 0;
+ afr_inode_ctx_t *ctx = NULL;
- LOCK (&frame->lock);
- {
- local = frame->local;
-
- if (op_ret != 0) {
- local->op_errno = op_errno;
- goto unlock;
- }
-
- local->op_ret = op_ret;
-
- buf = &local->cont.statfs.buf;
- if (local->cont.statfs.buf_set) {
- if (statvfs->f_bavail < buf->f_bavail) {
- *buf = *statvfs;
- if (xdata) {
- if (local->xdata_rsp)
- dict_unref (local->xdata_rsp);
- local->xdata_rsp = dict_ref (xdata);
- }
- }
- } else {
- *buf = *statvfs;
- local->cont.statfs.buf_set = 1;
- if (xdata)
- local->xdata_rsp = dict_ref (xdata);
- }
- }
-unlock:
- UNLOCK (&frame->lock);
-
- call_count = afr_frame_return (frame);
+ afr_spb_choice_timeout_cancel(this, inode);
+ inode_ctx_del(inode, this, &ctx_int);
+ if (!ctx_int)
+ return 0;
- if (call_count == 0)
- AFR_STACK_UNWIND (statfs, frame, local->op_ret, local->op_errno,
- &local->cont.statfs.buf, local->xdata_rsp);
+ ctx = (afr_inode_ctx_t *)(uintptr_t)ctx_int;
+ afr_inode_ctx_destroy(ctx);
+ return 0;
+}
- return 0;
+int
+afr_priv_dump(xlator_t *this)
+{
+ afr_private_t *priv = NULL;
+ char key_prefix[GF_DUMP_MAX_BUF_LEN];
+ char key[GF_DUMP_MAX_BUF_LEN];
+ int i = 0;
+
+ GF_ASSERT(this);
+ priv = this->private;
+
+ GF_ASSERT(priv);
+ snprintf(key_prefix, GF_DUMP_MAX_BUF_LEN, "%s.%s", this->type, this->name);
+ gf_proc_dump_add_section("%s", key_prefix);
+ gf_proc_dump_write("child_count", "%u", priv->child_count);
+ for (i = 0; i < priv->child_count; i++) {
+ sprintf(key, "child_up[%d]", i);
+ gf_proc_dump_write(key, "%d", priv->child_up[i]);
+ sprintf(key, "pending_key[%d]", i);
+ gf_proc_dump_write(key, "%s", priv->pending_key[i]);
+ sprintf(key, "pending_reads[%d]", i);
+ gf_proc_dump_write(key, "%" PRId64,
+ GF_ATOMIC_GET(priv->pending_reads[i]));
+ sprintf(key, "child_latency[%d]", i);
+ gf_proc_dump_write(key, "%" PRId64, priv->child_latency[i]);
+ sprintf(key, "halo_child_up[%d]", i);
+ gf_proc_dump_write(key, "%d", priv->halo_child_up[i]);
+ }
+ gf_proc_dump_write("data_self_heal", "%d", priv->data_self_heal);
+ gf_proc_dump_write("metadata_self_heal", "%d", priv->metadata_self_heal);
+ gf_proc_dump_write("entry_self_heal", "%d", priv->entry_self_heal);
+ gf_proc_dump_write("read_child", "%d", priv->read_child);
+ gf_proc_dump_write("wait_count", "%u", priv->wait_count);
+ gf_proc_dump_write("heal-wait-queue-length", "%d", priv->heal_wait_qlen);
+ gf_proc_dump_write("heal-waiters", "%d", priv->heal_waiters);
+ gf_proc_dump_write("background-self-heal-count", "%d",
+ priv->background_self_heal_count);
+ gf_proc_dump_write("healers", "%d", priv->healers);
+ gf_proc_dump_write("read-hash-mode", "%d", priv->hash_mode);
+ gf_proc_dump_write("use-anonymous-inode", "%d", priv->use_anon_inode);
+ if (priv->quorum_count == AFR_QUORUM_AUTO) {
+ gf_proc_dump_write("quorum-type", "auto");
+ } else if (priv->quorum_count == 0) {
+ gf_proc_dump_write("quorum-type", "none");
+ } else {
+ gf_proc_dump_write("quorum-type", "fixed");
+ gf_proc_dump_write("quorum-count", "%d", priv->quorum_count);
+ }
+ gf_proc_dump_write("up", "%u", afr_has_quorum(priv->child_up, this, NULL));
+ if (priv->thin_arbiter_count) {
+ gf_proc_dump_write("ta_child_up", "%d", priv->ta_child_up);
+ gf_proc_dump_write("ta_bad_child_index", "%d",
+ priv->ta_bad_child_index);
+ gf_proc_dump_write("ta_notify_dom_lock_offset", "%" PRId64,
+ priv->ta_notify_dom_lock_offset);
+ }
+
+ return 0;
}
+/**
+ * find_child_index - find the child's index in the array of subvolumes
+ * @this: AFR
+ * @child: child
+ */
-int
-afr_statfs (call_frame_t *frame, xlator_t *this, loc_t *loc, dict_t *xdata)
+static int
+afr_find_child_index(xlator_t *this, xlator_t *child)
{
- afr_local_t * local = NULL;
- afr_private_t *priv = NULL;
- int i = 0;
- int call_count = 0;
- int32_t op_errno = ENOMEM;
+ afr_private_t *priv = NULL;
+ int child_count = -1;
+ int i = -1;
- priv = this->private;
+ priv = this->private;
+ child_count = priv->child_count;
+ if (priv->thin_arbiter_count) {
+ child_count++;
+ }
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ for (i = 0; i < child_count; i++) {
+ if ((xlator_t *)child == priv->children[i])
+ break;
+ }
- call_count = local->call_count;
- if (!call_count) {
- op_errno = ENOTCONN;
- goto out;
- }
+ return i;
+}
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND (frame, afr_statfs_cbk,
- priv->children[i],
- priv->children[i]->fops->statfs,
- loc, xdata);
- if (!--call_count)
- break;
- }
- }
+int
+__afr_get_up_children_count(afr_private_t *priv)
+{
+ int up_children = 0;
+ int i = 0;
- return 0;
-out:
- AFR_STACK_UNWIND (statfs, frame, -1, op_errno, NULL, NULL);
+ for (i = 0; i < priv->child_count; i++)
+ if (priv->child_up[i] == 1)
+ up_children++;
- return 0;
+ return up_children;
}
-
-int32_t
-afr_lk_unlock_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, struct gf_flock *lock,
- dict_t *xdata)
+static int
+__get_heard_from_all_status(xlator_t *this)
{
- afr_local_t * local = NULL;
- int call_count = -1;
-
- local = frame->local;
- call_count = afr_frame_return (frame);
-
- if (call_count == 0)
- AFR_STACK_UNWIND (lk, frame, local->op_ret, local->op_errno,
- lock, xdata);
+ afr_private_t *priv = this->private;
+ int i;
+ for (i = 0; i < priv->child_count; i++) {
+ if (!priv->last_event[i]) {
+ return 0;
+ }
+ }
+ if (priv->thin_arbiter_count && !priv->ta_child_up) {
return 0;
+ }
+ return 1;
}
-
-int32_t
-afr_lk_unlock (call_frame_t *frame, xlator_t *this)
+glusterfs_event_t
+__afr_transform_event_from_state(xlator_t *this)
{
- afr_local_t * local = NULL;
- afr_private_t * priv = NULL;
- int i = 0;
- int call_count = 0;
-
- local = frame->local;
- priv = this->private;
+ int i = 0;
+ int up_children = 0;
+ afr_private_t *priv = this->private;
- call_count = afr_locked_nodes_count (local->cont.lk.locked_nodes,
- priv->child_count);
+ if (__get_heard_from_all_status(this))
+ /* have_heard_from_all. Let afr_notify() do the propagation. */
+ return GF_EVENT_MAXVAL;
- if (call_count == 0) {
- AFR_STACK_UNWIND (lk, frame, local->op_ret, local->op_errno,
- &local->cont.lk.ret_flock, NULL);
- return 0;
- }
-
- local->call_count = call_count;
-
- local->cont.lk.user_flock.l_type = F_UNLCK;
+ up_children = __afr_get_up_children_count(priv);
+ /* Treat the children with pending notification, as having sent a
+ * GF_EVENT_CHILD_DOWN. i.e. set the event as GF_EVENT_SOME_DESCENDENT_DOWN,
+ * as done in afr_notify() */
+ for (i = 0; i < priv->child_count; i++) {
+ if (priv->last_event[i])
+ continue;
+ priv->last_event[i] = GF_EVENT_SOME_DESCENDENT_DOWN;
+ priv->child_up[i] = 0;
+ }
- for (i = 0; i < priv->child_count; i++) {
- if (local->cont.lk.locked_nodes[i]) {
- STACK_WIND (frame, afr_lk_unlock_cbk,
- priv->children[i],
- priv->children[i]->fops->lk,
- local->fd, F_SETLK,
- &local->cont.lk.user_flock, NULL);
-
- if (!--call_count)
- break;
- }
- }
+ if (up_children)
+ /* We received at least one child up */
+ return GF_EVENT_CHILD_UP;
+ else
+ return GF_EVENT_CHILD_DOWN;
- return 0;
+ return GF_EVENT_MAXVAL;
}
+static void
+afr_notify_cbk(void *data)
+{
+ xlator_t *this = data;
+ afr_private_t *priv = this->private;
+ glusterfs_event_t event = GF_EVENT_MAXVAL;
+ gf_boolean_t propagate = _gf_false;
+
+ LOCK(&priv->lock);
+ {
+ if (!priv->timer) {
+ /*
+ * Either child_up/child_down is already sent to parent.
+ * This is a spurious wake up.
+ */
+ goto unlock;
+ }
+ priv->timer = NULL;
+ event = __afr_transform_event_from_state(this);
+ if (event != GF_EVENT_MAXVAL)
+ propagate = _gf_true;
+ }
+unlock:
+ UNLOCK(&priv->lock);
+ if (propagate)
+ default_notify(this, event, NULL);
+}
-int32_t
-afr_lk_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, struct gf_flock *lock, dict_t *xdata)
+static void
+__afr_launch_notify_timer(xlator_t *this, afr_private_t *priv)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- int child_index = -1;
-/* int ret = 0; */
+ struct timespec delay = {
+ 0,
+ };
+ gf_msg_debug(this->name, 0, "Initiating child-down timer");
+ delay.tv_sec = 10;
+ delay.tv_nsec = 0;
+ priv->timer = gf_timer_call_after(this->ctx, delay, afr_notify_cbk, this);
+ if (priv->timer == NULL) {
+ gf_msg(this->name, GF_LOG_ERROR, 0, AFR_MSG_TIMER_CREATE_FAIL,
+ "Cannot create timer for delayed initialization");
+ }
+}
- local = frame->local;
- priv = this->private;
-
- child_index = (long) cookie;
-
- if (!child_went_down (op_ret, op_errno) && (op_ret == -1)) {
- local->op_ret = -1;
- local->op_errno = op_errno;
+static int
+find_best_down_child(xlator_t *this)
+{
+ afr_private_t *priv = NULL;
+ int i = -1;
+ int32_t best_child = -1;
+ int64_t best_latency = INT64_MAX;
- afr_lk_unlock (frame, this);
- return 0;
- }
+ priv = this->private;
- if (op_ret == 0) {
- local->op_ret = 0;
- local->op_errno = 0;
- local->cont.lk.locked_nodes[child_index] = 1;
- local->cont.lk.ret_flock = *lock;
+ for (i = 0; i < priv->child_count; i++) {
+ if (!priv->child_up[i] && priv->child_latency[i] >= 0 &&
+ priv->child_latency[i] < best_latency) {
+ best_child = i;
+ best_latency = priv->child_latency[i];
}
+ }
+ if (best_child >= 0) {
+ gf_msg_debug(this->name, 0,
+ "Found best down child (%d) @ %" PRId64 " ms latency",
+ best_child, best_latency);
+ }
+ return best_child;
+}
- child_index++;
+int
+find_worst_up_child(xlator_t *this)
+{
+ afr_private_t *priv = NULL;
+ int i = -1;
+ int32_t worst_child = -1;
+ int64_t worst_latency = INT64_MIN;
- if (child_index < priv->child_count) {
- STACK_WIND_COOKIE (frame, afr_lk_cbk, (void *) (long) child_index,
- priv->children[child_index],
- priv->children[child_index]->fops->lk,
- local->fd, local->cont.lk.cmd,
- &local->cont.lk.user_flock, xdata);
- } else if (local->op_ret == -1) {
- /* all nodes have gone down */
+ priv = this->private;
- AFR_STACK_UNWIND (lk, frame, -1, ENOTCONN,
- &local->cont.lk.ret_flock, NULL);
- } else {
- AFR_STACK_UNWIND (lk, frame, local->op_ret, local->op_errno,
- &local->cont.lk.ret_flock, NULL);
+ for (i = 0; i < priv->child_count; i++) {
+ if (priv->child_up[i] && priv->child_latency[i] >= 0 &&
+ priv->child_latency[i] > worst_latency) {
+ worst_child = i;
+ worst_latency = priv->child_latency[i];
}
-
- return 0;
+ }
+ if (worst_child >= 0) {
+ gf_msg_debug(this->name, 0,
+ "Found worst up child (%d) @ %" PRId64 " ms latency",
+ worst_child, worst_latency);
+ }
+ return worst_child;
}
-
-int
-afr_lk (call_frame_t *frame, xlator_t *this,
- fd_t *fd, int32_t cmd, struct gf_flock *flock, dict_t *xdata)
+void
+__afr_handle_ping_event(xlator_t *this, xlator_t *child_xlator, const int idx,
+ int64_t halo_max_latency_msec, int32_t *event,
+ int64_t child_latency_msec)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int i = 0;
- int32_t op_errno = ENOMEM;
+ afr_private_t *priv = NULL;
+ int up_children = 0;
- priv = this->private;
+ priv = this->private;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ priv->child_latency[idx] = child_latency_msec;
+ gf_msg_debug(child_xlator->name, 0, "Client ping @ %" PRId64 " ms",
+ child_latency_msec);
+ if (priv->shd.iamshd)
+ return;
- local->cont.lk.locked_nodes = GF_CALLOC (priv->child_count,
- sizeof (*local->cont.lk.locked_nodes),
- gf_afr_mt_char);
+ up_children = __afr_get_up_children_count(priv);
- if (!local->cont.lk.locked_nodes) {
- op_errno = ENOMEM;
- goto out;
+ if (child_latency_msec > halo_max_latency_msec &&
+ priv->child_up[idx] == 1 && up_children > priv->halo_min_replicas) {
+ if ((up_children - 1) < priv->halo_min_replicas) {
+ gf_log(child_xlator->name, GF_LOG_INFO,
+ "Overriding halo threshold, "
+ "min replicas: %d",
+ priv->halo_min_replicas);
+ } else {
+ gf_log(child_xlator->name, GF_LOG_INFO,
+ "Child latency (%" PRId64
+ " ms) "
+ "exceeds halo threshold (%" PRId64
+ "), "
+ "marking child down.",
+ child_latency_msec, halo_max_latency_msec);
+ if (priv->halo_child_up[idx]) {
+ *event = GF_EVENT_CHILD_DOWN;
+ }
+ }
+ } else if (child_latency_msec < halo_max_latency_msec &&
+ priv->child_up[idx] == 0) {
+ if (up_children < priv->halo_max_replicas) {
+ gf_log(child_xlator->name, GF_LOG_INFO,
+ "Child latency (%" PRId64
+ " ms) "
+ "below halo threshold (%" PRId64
+ "), "
+ "marking child up.",
+ child_latency_msec, halo_max_latency_msec);
+ if (priv->halo_child_up[idx]) {
+ *event = GF_EVENT_CHILD_UP;
+ }
+ } else {
+ gf_log(child_xlator->name, GF_LOG_INFO,
+ "Not marking child %d up, "
+ "max replicas (%d) reached.",
+ idx, priv->halo_max_replicas);
}
+ }
+}
- local->fd = fd_ref (fd);
- local->cont.lk.cmd = cmd;
- local->cont.lk.user_flock = *flock;
- local->cont.lk.ret_flock = *flock;
+static int64_t
+afr_get_halo_latency(xlator_t *this)
+{
+ afr_private_t *priv = NULL;
+ int64_t halo_max_latency_msec = 0;
- STACK_WIND_COOKIE (frame, afr_lk_cbk, (void *) (long) 0,
- priv->children[i],
- priv->children[i]->fops->lk,
- fd, cmd, flock, xdata);
+ priv = this->private;
- return 0;
+ if (priv->shd.iamshd) {
+ halo_max_latency_msec = priv->shd.halo_max_latency_msec;
+ } else if (priv->nfsd.iamnfsd) {
+ halo_max_latency_msec = priv->nfsd.halo_max_latency_msec;
+ } else {
+ halo_max_latency_msec = priv->halo_max_latency_msec;
+ }
+ gf_msg_debug(this->name, 0, "Using halo latency %" PRId64,
+ halo_max_latency_msec);
+ return halo_max_latency_msec;
+}
+
+void
+__afr_handle_child_up_event(xlator_t *this, xlator_t *child_xlator,
+ const int idx, int64_t child_latency_msec,
+ int32_t *event, int32_t *call_psh,
+ int32_t *up_child)
+{
+ afr_private_t *priv = NULL;
+ int up_children = 0;
+ int worst_up_child = -1;
+ int64_t halo_max_latency_msec = afr_get_halo_latency(this);
+
+ priv = this->private;
+
+ /*
+ * This only really counts if the child was never up
+ * (value = -1) or had been down (value = 0). See
+ * comment at GF_EVENT_CHILD_DOWN for a more detailed
+ * explanation.
+ */
+ if (priv->child_up[idx] != 1) {
+ priv->event_generation++;
+ }
+ priv->child_up[idx] = 1;
+
+ *call_psh = 1;
+ *up_child = idx;
+ up_children = __afr_get_up_children_count(priv);
+ /*
+ * If this is an _actual_ CHILD_UP event, we
+ * want to set the child_latency to MAX to indicate
+ * the child needs ping data to be available before doing child-up
+ */
+ if (!priv->halo_enabled)
+ goto out;
+
+ if (child_latency_msec < 0) {
+ /*set to INT64_MAX-1 so that it is found for best_down_child*/
+ priv->halo_child_up[idx] = 1;
+ if (priv->child_latency[idx] < 0) {
+ priv->child_latency[idx] = AFR_HALO_MAX_LATENCY;
+ }
+ }
+
+ /*
+ * Handle the edge case where we exceed
+ * halo_min_replicas and we've got a child which is
+ * marked up as it was helping to satisfy the
+ * halo_min_replicas even though it's latency exceeds
+ * halo_max_latency_msec.
+ */
+ if (up_children > priv->halo_min_replicas) {
+ worst_up_child = find_worst_up_child(this);
+ if (worst_up_child >= 0 &&
+ priv->child_latency[worst_up_child] > halo_max_latency_msec) {
+ gf_msg_debug(this->name, 0,
+ "Marking child %d down, "
+ "doesn't meet halo threshold (%" PRId64
+ "), and > "
+ "halo_min_replicas (%d)",
+ worst_up_child, halo_max_latency_msec,
+ priv->halo_min_replicas);
+ priv->child_up[worst_up_child] = 0;
+ up_children--;
+ }
+ }
+
+ if (up_children > priv->halo_max_replicas && !priv->shd.iamshd) {
+ worst_up_child = find_worst_up_child(this);
+ if (worst_up_child < 0) {
+ worst_up_child = idx;
+ }
+ priv->child_up[worst_up_child] = 0;
+ up_children--;
+ gf_msg_debug(this->name, 0,
+ "Marking child %d down, "
+ "up_children (%d) > halo_max_replicas (%d)",
+ worst_up_child, up_children, priv->halo_max_replicas);
+ }
out:
- AFR_STACK_UNWIND (lk, frame, -1, op_errno, NULL, NULL);
+ if (up_children == 1) {
+ gf_msg(this->name, GF_LOG_INFO, 0, AFR_MSG_SUBVOL_UP,
+ "Subvolume '%s' came back up; "
+ "going online.",
+ child_xlator->name);
+ gf_event(EVENT_AFR_SUBVOL_UP, "client-pid=%d; subvol=%s",
+ this->ctx->cmd_args.client_pid, this->name);
+ } else {
+ *event = GF_EVENT_SOME_DESCENDENT_UP;
+ }
- return 0;
+ priv->last_event[idx] = *event;
}
-int
-afr_forget (xlator_t *this, inode_t *inode)
+void
+__afr_handle_child_down_event(xlator_t *this, xlator_t *child_xlator, int idx,
+ int64_t child_latency_msec, int32_t *event,
+ int32_t *call_psh, int32_t *up_child)
+{
+ afr_private_t *priv = NULL;
+ int i = 0;
+ int up_children = 0;
+ int down_children = 0;
+ int best_down_child = -1;
+
+ priv = this->private;
+
+ /*
+ * If a brick is down when we start, we'll get a
+ * CHILD_DOWN to indicate its initial state. There
+ * was never a CHILD_UP in this case, so if we
+ * increment "down_count" the difference between than
+ * and "up_count" will no longer be the number of
+ * children that are currently up. This has serious
+ * implications e.g. for quorum enforcement, so we
+ * don't increment these values unless the event
+ * represents an actual state transition between "up"
+ * (value = 1) and anything else.
+ */
+ if (priv->child_up[idx] == 1) {
+ priv->event_generation++;
+ }
+
+ /*
+ * If this is an _actual_ CHILD_DOWN event, we
+ * want to set the child_latency to < 0 to indicate
+ * the child is really disconnected.
+ */
+ if (child_latency_msec < 0) {
+ priv->child_latency[idx] = child_latency_msec;
+ priv->halo_child_up[idx] = 0;
+ }
+ priv->child_up[idx] = 0;
+
+ up_children = __afr_get_up_children_count(priv);
+ /*
+ * Handle the edge case where we need to find the
+ * next best child (to mark up) as marking this child
+ * down would cause us to fall below halo_min_replicas.
+ * We will also force the SHD to heal this child _now_
+ * as we want it to be up to date if we are going to
+ * begin using it synchronously.
+ */
+ if (priv->halo_enabled && up_children < priv->halo_min_replicas) {
+ best_down_child = find_best_down_child(this);
+ if (best_down_child >= 0) {
+ gf_msg_debug(this->name, 0,
+ "Swapping out child %d for "
+ "child %d to satisfy halo_min_replicas (%d).",
+ idx, best_down_child, priv->halo_min_replicas);
+ priv->child_up[best_down_child] = 1;
+ *call_psh = 1;
+ *up_child = best_down_child;
+ }
+ }
+ for (i = 0; i < priv->child_count; i++)
+ if (priv->child_up[i] == 0)
+ down_children++;
+ if (down_children == priv->child_count) {
+ gf_msg(this->name, GF_LOG_ERROR, 0, AFR_MSG_SUBVOLS_DOWN,
+ "All subvolumes are down. Going "
+ "offline until at least one of them "
+ "comes back up.");
+ gf_event(EVENT_AFR_SUBVOLS_DOWN, "client-pid=%d; subvol=%s",
+ this->ctx->cmd_args.client_pid, this->name);
+ } else {
+ *event = GF_EVENT_SOME_DESCENDENT_DOWN;
+ }
+ priv->last_event[idx] = *event;
+}
+
+void
+afr_ta_lock_release_synctask(xlator_t *this)
{
- uint64_t ctx_int = 0;
- afr_inode_ctx_t *ctx = NULL;
+ call_frame_t *ta_frame = NULL;
+ int ret = 0;
- afr_spb_choice_timeout_cancel (this, inode);
- inode_ctx_del (inode, this, &ctx_int);
- if (!ctx_int)
- return 0;
+ ta_frame = afr_ta_frame_create(this);
+ if (!ta_frame) {
+ gf_msg(this->name, GF_LOG_ERROR, ENOMEM, AFR_MSG_THIN_ARB,
+ "Failed to create ta_frame");
+ return;
+ }
- ctx = (afr_inode_ctx_t *)ctx_int;
- GF_FREE (ctx);
- return 0;
+ ret = synctask_new(this->ctx->env, afr_release_notify_lock_for_ta,
+ afr_ta_lock_release_done, ta_frame, this);
+ if (ret) {
+ STACK_DESTROY(ta_frame->root);
+ gf_msg(this->name, GF_LOG_ERROR, ENOMEM, AFR_MSG_THIN_ARB,
+ "Failed to release "
+ "AFR_TA_DOM_NOTIFY lock.");
+ }
}
-int
-afr_priv_dump (xlator_t *this)
+static void
+afr_handle_inodelk_contention(xlator_t *this, struct gf_upcall *upcall)
{
- afr_private_t *priv = NULL;
- char key_prefix[GF_DUMP_MAX_BUF_LEN];
- char key[GF_DUMP_MAX_BUF_LEN];
- int i = 0;
+ struct gf_upcall_inodelk_contention *lc = NULL;
+ unsigned int inmem_count = 0;
+ unsigned int onwire_count = 0;
+ afr_private_t *priv = this->private;
+ lc = upcall->data;
- GF_ASSERT (this);
- priv = this->private;
+ if (strcmp(lc->domain, AFR_TA_DOM_NOTIFY) != 0)
+ return;
- GF_ASSERT (priv);
- snprintf(key_prefix, GF_DUMP_MAX_BUF_LEN, "%s.%s", this->type, this->name);
- gf_proc_dump_add_section(key_prefix);
- gf_proc_dump_write("child_count", "%u", priv->child_count);
- for (i = 0; i < priv->child_count; i++) {
- sprintf (key, "child_up[%d]", i);
- gf_proc_dump_write(key, "%d", priv->child_up[i]);
- sprintf (key, "pending_key[%d]", i);
- gf_proc_dump_write(key, "%s", priv->pending_key[i]);
- }
- gf_proc_dump_write("data_self_heal", "%s", priv->data_self_heal);
- gf_proc_dump_write("metadata_self_heal", "%d", priv->metadata_self_heal);
- gf_proc_dump_write("entry_self_heal", "%d", priv->entry_self_heal);
- gf_proc_dump_write("data_change_log", "%d", priv->data_change_log);
- gf_proc_dump_write("metadata_change_log", "%d", priv->metadata_change_log);
- gf_proc_dump_write("entry-change_log", "%d", priv->entry_change_log);
- gf_proc_dump_write("read_child", "%d", priv->read_child);
- gf_proc_dump_write("favorite_child", "%d", priv->favorite_child);
- gf_proc_dump_write("wait_count", "%u", priv->wait_count);
- gf_proc_dump_write("quorum-reads", "%d", priv->quorum_reads);
+ if (priv->shd.iamshd) {
+ /* shd should ignore AFR_TA_DOM_NOTIFY release requests. */
+ return;
+ }
+ LOCK(&priv->lock);
+ {
+ if (priv->release_ta_notify_dom_lock == _gf_true) {
+ /* Ignore multiple release requests from shds.*/
+ UNLOCK(&priv->lock);
+ return;
+ }
+ priv->release_ta_notify_dom_lock = _gf_true;
+ inmem_count = priv->ta_in_mem_txn_count;
+ onwire_count = priv->ta_on_wire_txn_count;
+ }
+ UNLOCK(&priv->lock);
+ if (inmem_count || onwire_count)
+ /* lock release will happen in txn code path after
+ * in-memory or on-wire txns are over.*/
+ return;
- return 0;
+ afr_ta_lock_release_synctask(this);
}
+static void
+afr_handle_upcall_event(xlator_t *this, struct gf_upcall *upcall)
+{
+ struct gf_upcall_cache_invalidation *up_ci = NULL;
+ afr_private_t *priv = this->private;
+ inode_t *inode = NULL;
+ inode_table_t *itable = NULL;
+ int i = 0;
+
+ switch (upcall->event_type) {
+ case GF_UPCALL_INODELK_CONTENTION:
+ afr_handle_inodelk_contention(this, upcall);
+ break;
+ case GF_UPCALL_CACHE_INVALIDATION:
+ up_ci = (struct gf_upcall_cache_invalidation *)upcall->data;
+
+ /* Since md-cache will be aggressively filtering
+ * lookups, the stale read issue will be more
+ * pronounced. Hence when a pending xattr is set notify
+ * all the md-cache clients to invalidate the existing
+ * stat cache and send the lookup next time */
+ if (!up_ci->dict)
+ break;
+ for (i = 0; i < priv->child_count; i++) {
+ if (!dict_get(up_ci->dict, priv->pending_key[i]))
+ continue;
+ up_ci->flags |= UP_INVAL_ATTR;
+ itable = ((xlator_t *)this->graph->top)->itable;
+ /*Internal processes may not have itable for
+ *top xlator*/
+ if (itable)
+ inode = inode_find(itable, upcall->gfid);
+ if (inode)
+ afr_inode_need_refresh_set(inode, this);
+ break;
+ }
+ break;
+ default:
+ break;
+ }
+}
-/**
- * find_child_index - find the child's index in the array of subvolumes
- * @this: AFR
- * @child: child
- */
-
-static int
-find_child_index (xlator_t *this, xlator_t *child)
-{
- afr_private_t *priv = NULL;
- int i = -1;
-
- priv = this->private;
+int32_t
+afr_notify(xlator_t *this, int32_t event, void *data, void *data2)
+{
+ afr_private_t *priv = NULL;
+ xlator_t *child_xlator = NULL;
+ int i = -1;
+ int propagate = 0;
+ int had_heard_from_all = 0;
+ int have_heard_from_all = 0;
+ int idx = -1;
+ int ret = -1;
+ int call_psh = 0;
+ int up_child = -1;
+ dict_t *input = NULL;
+ dict_t *output = NULL;
+ gf_boolean_t had_quorum = _gf_false;
+ gf_boolean_t has_quorum = _gf_false;
+ int64_t halo_max_latency_msec = 0;
+ int64_t child_latency_msec = -1;
+
+ child_xlator = (xlator_t *)data;
+
+ priv = this->private;
+
+ if (!priv)
+ return 0;
- for (i = 0; i < priv->child_count; i++) {
- if ((xlator_t *) child == priv->children[i])
- break;
+ /*
+ * We need to reset this in case children come up in "staggered"
+ * fashion, so that we discover a late-arriving local subvolume. Note
+ * that we could end up issuing N lookups to the first subvolume, and
+ * O(N^2) overall, but N is small for AFR so it shouldn't be an issue.
+ */
+ priv->did_discovery = _gf_false;
+
+ /* parent xlators don't need to know about every child_up, child_down
+ * because of afr ha. If all subvolumes go down, child_down has
+ * to be triggered. In that state when 1 subvolume comes up child_up
+ * needs to be triggered. dht optimizes revalidate lookup by sending
+ * it only to one of its subvolumes. When child up/down happens
+ * for afr's subvolumes dht should be notified by child_modified. The
+ * subsequent revalidate lookup happens on all the dht's subvolumes
+ * which triggers afr self-heals if any.
+ */
+ idx = afr_find_child_index(this, child_xlator);
+ if (idx < 0) {
+ gf_msg(this->name, GF_LOG_ERROR, 0, AFR_MSG_INVALID_CHILD_UP,
+ "Received child_up from invalid subvolume");
+ goto out;
+ }
+
+ had_quorum = priv->quorum_count &&
+ afr_has_quorum(priv->child_up, this, NULL);
+ if (event == GF_EVENT_CHILD_PING) {
+ child_latency_msec = (int64_t)(uintptr_t)data2;
+ if (priv->halo_enabled) {
+ halo_max_latency_msec = afr_get_halo_latency(this);
+
+ /* Calculates the child latency and sets event
+ */
+ LOCK(&priv->lock);
+ {
+ __afr_handle_ping_event(this, child_xlator, idx,
+ halo_max_latency_msec, &event,
+ child_latency_msec);
+ }
+ UNLOCK(&priv->lock);
+ } else {
+ LOCK(&priv->lock);
+ {
+ priv->child_latency[idx] = child_latency_msec;
+ }
+ UNLOCK(&priv->lock);
}
+ }
- return i;
-}
-
-int32_t
-afr_notify (xlator_t *this, int32_t event,
- void *data, void *data2)
-{
- afr_private_t *priv = NULL;
- int i = -1;
- int up_children = 0;
- int down_children = 0;
- int propagate = 0;
- int had_heard_from_all = 0;
- int have_heard_from_all = 0;
- int idx = -1;
- int ret = -1;
- int call_psh = 0;
- int up_child = -1;
- dict_t *input = NULL;
- dict_t *output = NULL;
- gf_boolean_t had_quorum = _gf_false;
- gf_boolean_t has_quorum = _gf_false;
-
- priv = this->private;
-
- if (!priv)
- return 0;
-
- /*
- * We need to reset this in case children come up in "staggered"
- * fashion, so that we discover a late-arriving local subvolume. Note
- * that we could end up issuing N lookups to the first subvolume, and
- * O(N^2) overall, but N is small for AFR so it shouldn't be an issue.
+ if (event == GF_EVENT_CHILD_PING) {
+ /* This is the only xlator that handles PING, no reason to
+ * propagate.
*/
- priv->did_discovery = _gf_false;
+ goto out;
+ }
- had_heard_from_all = 1;
- for (i = 0; i < priv->child_count; i++) {
- if (!priv->last_event[i]) {
- had_heard_from_all = 0;
- }
+ if (event == GF_EVENT_TRANSLATOR_OP) {
+ LOCK(&priv->lock);
+ {
+ had_heard_from_all = __get_heard_from_all_status(this);
}
+ UNLOCK(&priv->lock);
- /* parent xlators dont need to know about every child_up, child_down
- * because of afr ha. If all subvolumes go down, child_down has
- * to be triggered. In that state when 1 subvolume comes up child_up
- * needs to be triggered. dht optimizes revalidate lookup by sending
- * it only to one of its subvolumes. When child up/down happens
- * for afr's subvolumes dht should be notified by child_modified. The
- * subsequent revalidate lookup happens on all the dht's subvolumes
- * which triggers afr self-heals if any.
- */
- idx = find_child_index (this, data);
- if (idx < 0) {
- gf_msg (this->name, GF_LOG_ERROR, 0, AFR_MSG_INVALID_CHILD_UP,
- "Received child_up from invalid subvolume");
- goto out;
+ if (!had_heard_from_all) {
+ ret = -1;
+ } else {
+ input = data;
+ output = data2;
+ ret = afr_xl_op(this, input, output);
}
+ goto out;
+ }
+
+ if (event == GF_EVENT_UPCALL) {
+ afr_handle_upcall_event(this, data);
+ }
- had_quorum = priv->quorum_count && afr_has_quorum (priv->child_up,
- this);
+ LOCK(&priv->lock);
+ {
+ had_heard_from_all = __get_heard_from_all_status(this);
switch (event) {
- case GF_EVENT_CHILD_UP:
- LOCK (&priv->lock);
- {
- /*
- * This only really counts if the child was never up
- * (value = -1) or had been down (value = 0). See
- * comment at GF_EVENT_CHILD_DOWN for a more detailed
- * explanation.
- */
- if (priv->child_up[idx] != 1) {
- priv->up_count++;
- priv->event_generation++;
- }
- priv->child_up[idx] = 1;
-
- call_psh = 1;
- up_child = idx;
- for (i = 0; i < priv->child_count; i++)
- if (priv->child_up[i] == 1)
- up_children++;
- if (up_children == 1) {
- gf_msg (this->name, GF_LOG_INFO, 0,
- AFR_MSG_SUBVOL_UP,
- "Subvolume '%s' came back up; "
- "going online.", ((xlator_t *)data)->name);
- } else {
- event = GF_EVENT_CHILD_MODIFIED;
- }
-
- priv->last_event[idx] = event;
+ case GF_EVENT_PARENT_UP:
+ __afr_launch_notify_timer(this, priv);
+ propagate = 1;
+ break;
+ case GF_EVENT_CHILD_UP:
+ if (priv->thin_arbiter_count &&
+ (idx == AFR_CHILD_THIN_ARBITER)) {
+ priv->ta_child_up = 1;
+ priv->ta_event_gen++;
+ break;
}
- UNLOCK (&priv->lock);
-
+ __afr_handle_child_up_event(this, child_xlator, idx,
+ child_latency_msec, &event,
+ &call_psh, &up_child);
+ __afr_lock_heal_synctask(this, priv, idx);
break;
- case GF_EVENT_CHILD_DOWN:
- LOCK (&priv->lock);
- {
- /*
- * If a brick is down when we start, we'll get a
- * CHILD_DOWN to indicate its initial state. There
- * was never a CHILD_UP in this case, so if we
- * increment "down_count" the difference between than
- * and "up_count" will no longer be the number of
- * children that are currently up. This has serious
- * implications e.g. for quorum enforcement, so we
- * don't increment these values unless the event
- * represents an actual state transition between "up"
- * (value = 1) and anything else.
- */
- if (priv->child_up[idx] == 1) {
- priv->down_count++;
- priv->event_generation++;
- }
- priv->child_up[idx] = 0;
-
- for (i = 0; i < priv->child_count; i++)
- if (priv->child_up[i] == 0)
- down_children++;
- if (down_children == priv->child_count) {
- gf_msg (this->name, GF_LOG_ERROR, 0,
- AFR_MSG_ALL_SUBVOLS_DOWN,
- "All subvolumes are down. Going offline "
- "until atleast one of them comes back up.");
- } else {
- event = GF_EVENT_CHILD_MODIFIED;
- }
-
- priv->last_event[idx] = event;
+ case GF_EVENT_CHILD_DOWN:
+ if (priv->thin_arbiter_count &&
+ (idx == AFR_CHILD_THIN_ARBITER)) {
+ priv->ta_child_up = 0;
+ priv->ta_event_gen++;
+ afr_ta_locked_priv_invalidate(priv);
+ break;
}
- UNLOCK (&priv->lock);
-
+ __afr_handle_child_down_event(this, child_xlator, idx,
+ child_latency_msec, &event,
+ &call_psh, &up_child);
+ __afr_mark_pending_lk_heal(this, priv, idx);
break;
- case GF_EVENT_CHILD_CONNECTING:
- LOCK (&priv->lock);
- {
- priv->last_event[idx] = event;
- }
- UNLOCK (&priv->lock);
+ case GF_EVENT_CHILD_CONNECTING:
+ priv->last_event[idx] = event;
break;
- case GF_EVENT_TRANSLATOR_OP:
- input = data;
- output = data2;
- if (!had_heard_from_all) {
- ret = -1;
- goto out;
- }
- ret = afr_xl_op (this, input, output);
- goto out;
+ case GF_EVENT_SOME_DESCENDENT_DOWN:
+ priv->last_event[idx] = event;
break;
-
- default:
+ default:
propagate = 1;
break;
}
-
- if (priv->quorum_count) {
- has_quorum = afr_has_quorum (priv->child_up, this);
- if (!had_quorum && has_quorum)
- gf_msg (this->name, GF_LOG_INFO, 0, AFR_MSG_QUORUM_MET,
- "Client-quorum is met");
- if (had_quorum && !has_quorum)
- gf_msg (this->name, GF_LOG_WARNING, 0,
- AFR_MSG_QUORUM_FAIL,
- "Client-quorum is not met");
- }
-
- /* have all subvolumes reported status once by now? */
- have_heard_from_all = 1;
- for (i = 0; i < priv->child_count; i++) {
- if (!priv->last_event[i])
- have_heard_from_all = 0;
- }
-
- /* if all subvols have reported status, no need to hide anything
- or wait for anything else. Just propagate blindly */
- if (have_heard_from_all)
- propagate = 1;
-
+ have_heard_from_all = __get_heard_from_all_status(this);
if (!had_heard_from_all && have_heard_from_all) {
- /* This is the first event which completes aggregation
- of events from all subvolumes. If at least one subvol
- had come up, propagate CHILD_UP, but only this time
- */
- event = GF_EVENT_CHILD_DOWN;
-
- LOCK (&priv->lock);
- {
- up_children = AFR_COUNT (priv->child_up, priv->child_count);
- for (i = 0; i < priv->child_count; i++) {
- if (priv->last_event[i] == GF_EVENT_CHILD_UP) {
- event = GF_EVENT_CHILD_UP;
- break;
- }
-
- if (priv->last_event[i] ==
- GF_EVENT_CHILD_CONNECTING) {
- event = GF_EVENT_CHILD_CONNECTING;
- /* continue to check other events for CHILD_UP */
- }
- }
+ if (priv->timer) {
+ gf_timer_call_cancel(this->ctx, priv->timer);
+ priv->timer = NULL;
+ }
+ /* This is the first event which completes aggregation
+ of events from all subvolumes. If at least one subvol
+ had come up, propagate CHILD_UP, but only this time
+ */
+ event = GF_EVENT_CHILD_DOWN;
+ for (i = 0; i < priv->child_count; i++) {
+ if (priv->last_event[i] == GF_EVENT_CHILD_UP) {
+ event = GF_EVENT_CHILD_UP;
+ break;
}
- UNLOCK (&priv->lock);
- }
- ret = 0;
- if (propagate)
- ret = default_notify (this, event, data);
-
- if (!had_heard_from_all && have_heard_from_all && priv->shd.iamshd) {
- /*
- * Since self-heal is supposed to be launched only after
- * the responses from all the bricks are collected,
- * launch self-heals now on all up subvols.
- */
- for (i = 0; i < priv->child_count; i++)
- if (priv->child_up[i])
- afr_selfheal_childup (this, i);
- } else if (have_heard_from_all && call_psh && priv->shd.iamshd) {
- /*
- * Already heard from everyone. Just launch heal on now up
- * subvolume.
- */
- afr_selfheal_childup (this, up_child);
- }
+ if (priv->last_event[i] == GF_EVENT_CHILD_CONNECTING) {
+ event = GF_EVENT_CHILD_CONNECTING;
+ /* continue to check other events for CHILD_UP */
+ }
+ }
+ }
+ }
+ UNLOCK(&priv->lock);
+
+ if (priv->quorum_count) {
+ has_quorum = afr_has_quorum(priv->child_up, this, NULL);
+ if (!had_quorum && has_quorum) {
+ gf_msg(this->name, GF_LOG_INFO, 0, AFR_MSG_QUORUM_MET,
+ "Client-quorum is met");
+ gf_event(EVENT_AFR_QUORUM_MET, "client-pid=%d; subvol=%s",
+ this->ctx->cmd_args.client_pid, this->name);
+ }
+ if (had_quorum && !has_quorum) {
+ gf_msg(this->name, GF_LOG_WARNING, 0, AFR_MSG_QUORUM_FAIL,
+ "Client-quorum is not met");
+ gf_event(EVENT_AFR_QUORUM_FAIL, "client-pid=%d; subvol=%s",
+ this->ctx->cmd_args.client_pid, this->name);
+ }
+ }
+
+ /* if all subvols have reported status, no need to hide anything
+ or wait for anything else. Just propagate blindly */
+ if (have_heard_from_all)
+ propagate = 1;
+
+ ret = 0;
+ if (propagate)
+ ret = default_notify(this, event, data);
+
+ if ((!had_heard_from_all) || call_psh) {
+ /* Launch self-heal on all local subvolumes if:
+ * a) We have_heard_from_all for the first time
+ * b) Already heard from everyone, but we now got a child-up
+ * event.
+ */
+ if (have_heard_from_all) {
+ afr_selfheal_childup(this, priv);
+ }
+ }
out:
- return ret;
+ return ret;
}
+int
+afr_local_init(afr_local_t *local, afr_private_t *priv, int32_t *op_errno)
+{
+ int __ret = -1;
+ local->op_ret = -1;
+ local->op_errno = EUCLEAN;
+
+ __ret = syncbarrier_init(&local->barrier);
+ if (__ret) {
+ if (op_errno)
+ *op_errno = __ret;
+ goto out;
+ }
+
+ local->child_up = GF_MALLOC(priv->child_count * sizeof(*local->child_up),
+ gf_afr_mt_char);
+ if (!local->child_up) {
+ if (op_errno)
+ *op_errno = ENOMEM;
+ goto out;
+ }
+
+ memcpy(local->child_up, priv->child_up,
+ sizeof(*local->child_up) * priv->child_count);
+ local->call_count = AFR_COUNT(local->child_up, priv->child_count);
+ if (local->call_count == 0) {
+ gf_msg(THIS->name, GF_LOG_INFO, 0, AFR_MSG_SUBVOLS_DOWN,
+ "no subvolumes up");
+ if (op_errno)
+ *op_errno = ENOTCONN;
+ goto out;
+ }
+
+ local->event_generation = priv->event_generation;
+
+ local->read_attempted = GF_CALLOC(priv->child_count, sizeof(char),
+ gf_afr_mt_char);
+ if (!local->read_attempted) {
+ if (op_errno)
+ *op_errno = ENOMEM;
+ goto out;
+ }
+
+ local->readable = GF_CALLOC(priv->child_count, sizeof(char),
+ gf_afr_mt_char);
+ if (!local->readable) {
+ if (op_errno)
+ *op_errno = ENOMEM;
+ goto out;
+ }
+
+ local->readable2 = GF_CALLOC(priv->child_count, sizeof(char),
+ gf_afr_mt_char);
+ if (!local->readable2) {
+ if (op_errno)
+ *op_errno = ENOMEM;
+ goto out;
+ }
+
+ local->read_subvol = -1;
+
+ local->replies = GF_CALLOC(priv->child_count, sizeof(*local->replies),
+ gf_afr_mt_reply_t);
+ if (!local->replies) {
+ if (op_errno)
+ *op_errno = ENOMEM;
+ goto out;
+ }
+
+ local->need_full_crawl = _gf_false;
+ if (priv->thin_arbiter_count) {
+ local->ta_child_up = priv->ta_child_up;
+ local->ta_failed_subvol = AFR_CHILD_UNKNOWN;
+ local->read_txn_query_child = AFR_CHILD_UNKNOWN;
+ local->ta_event_gen = priv->ta_event_gen;
+ local->fop_state = TA_SUCCESS;
+ }
+ local->is_new_entry = _gf_false;
+
+ INIT_LIST_HEAD(&local->healer);
+ return 0;
+out:
+ return -1;
+}
int
-afr_local_init (afr_local_t *local, afr_private_t *priv, int32_t *op_errno)
+afr_internal_lock_init(afr_internal_lock_t *lk, size_t child_count)
{
- local->op_ret = -1;
- local->op_errno = EUCLEAN;
+ int ret = -ENOMEM;
- syncbarrier_init (&local->barrier);
+ lk->lower_locked_nodes = GF_CALLOC(sizeof(*lk->lower_locked_nodes),
+ child_count, gf_afr_mt_char);
+ if (NULL == lk->lower_locked_nodes)
+ goto out;
- local->child_up = GF_CALLOC (priv->child_count,
- sizeof (*local->child_up),
- gf_afr_mt_char);
- if (!local->child_up) {
- if (op_errno)
- *op_errno = ENOMEM;
- goto out;
- }
+ lk->lock_op_ret = -1;
+ lk->lock_op_errno = EUCLEAN;
- memcpy (local->child_up, priv->child_up,
- sizeof (*local->child_up) * priv->child_count);
- local->call_count = AFR_COUNT (local->child_up, priv->child_count);
- if (local->call_count == 0) {
- gf_msg (THIS->name, GF_LOG_INFO, 0,
- AFR_MSG_ALL_SUBVOLS_DOWN, "no subvolumes up");
- if (op_errno)
- *op_errno = ENOTCONN;
- goto out;
- }
- local->event_generation = priv->event_generation;
-
- local->read_attempted = GF_CALLOC (priv->child_count, sizeof (char),
- gf_afr_mt_char);
- if (!local->read_attempted) {
- if (op_errno)
- *op_errno = ENOMEM;
- goto out;
- }
-
- local->readable = GF_CALLOC (priv->child_count, sizeof (char),
- gf_afr_mt_char);
- if (!local->readable) {
- if (op_errno)
- *op_errno = ENOMEM;
- goto out;
- }
-
- local->replies = GF_CALLOC(priv->child_count, sizeof(*local->replies),
- gf_afr_mt_reply_t);
- if (!local->replies) {
- if (op_errno)
- *op_errno = ENOMEM;
- goto out;
- }
-
- return 0;
+ ret = 0;
out:
- return -1;
+ return ret;
}
-int
-afr_internal_lock_init (afr_internal_lock_t *lk, size_t child_count,
- transaction_lk_type_t lk_type)
+void
+afr_matrix_cleanup(int32_t **matrix, unsigned int m)
{
- int ret = -ENOMEM;
+ int i = 0;
- lk->locked_nodes = GF_CALLOC (sizeof (*lk->locked_nodes),
- child_count, gf_afr_mt_char);
- if (NULL == lk->locked_nodes)
- goto out;
+ if (!matrix)
+ goto out;
+ for (i = 0; i < m; i++) {
+ GF_FREE(matrix[i]);
+ }
- lk->lower_locked_nodes = GF_CALLOC (sizeof (*lk->lower_locked_nodes),
- child_count, gf_afr_mt_char);
- if (NULL == lk->lower_locked_nodes)
- goto out;
+ GF_FREE(matrix);
+out:
+ return;
+}
- lk->lock_op_ret = -1;
- lk->lock_op_errno = EUCLEAN;
- lk->transaction_lk_type = lk_type;
+int32_t **
+afr_matrix_create(unsigned int m, unsigned int n)
+{
+ int32_t **matrix = NULL;
+ int i = 0;
- ret = 0;
+ matrix = GF_CALLOC(sizeof(*matrix), m, gf_afr_mt_int32_t);
+ if (!matrix)
+ goto out;
+
+ for (i = 0; i < m; i++) {
+ matrix[i] = GF_CALLOC(sizeof(*matrix[i]), n, gf_afr_mt_int32_t);
+ if (!matrix[i])
+ goto out;
+ }
+ return matrix;
out:
- return ret;
+ afr_matrix_cleanup(matrix, m);
+ return NULL;
+}
+
+int
+afr_transaction_local_init(afr_local_t *local, xlator_t *this)
+{
+ int ret = -ENOMEM;
+ afr_private_t *priv = NULL;
+
+ priv = this->private;
+ INIT_LIST_HEAD(&local->transaction.wait_list);
+ INIT_LIST_HEAD(&local->transaction.owner_list);
+ INIT_LIST_HEAD(&local->ta_waitq);
+ INIT_LIST_HEAD(&local->ta_onwireq);
+ ret = afr_internal_lock_init(&local->internal_lock, priv->child_count);
+ if (ret < 0)
+ goto out;
+
+ ret = -ENOMEM;
+ local->pre_op_compat = priv->pre_op_compat;
+
+ local->transaction.pre_op = GF_CALLOC(sizeof(*local->transaction.pre_op),
+ priv->child_count, gf_afr_mt_char);
+ if (!local->transaction.pre_op)
+ goto out;
+
+ local->transaction.changelog_xdata = GF_CALLOC(
+ sizeof(*local->transaction.changelog_xdata), priv->child_count,
+ gf_afr_mt_dict_t);
+ if (!local->transaction.changelog_xdata)
+ goto out;
+
+ if (priv->arbiter_count == 1) {
+ local->transaction.pre_op_sources = GF_CALLOC(
+ sizeof(*local->transaction.pre_op_sources), priv->child_count,
+ gf_afr_mt_char);
+ if (!local->transaction.pre_op_sources)
+ goto out;
+ }
+
+ local->transaction.failed_subvols = GF_CALLOC(
+ sizeof(*local->transaction.failed_subvols), priv->child_count,
+ gf_afr_mt_char);
+ if (!local->transaction.failed_subvols)
+ goto out;
+
+ local->pending = afr_matrix_create(priv->child_count, AFR_NUM_CHANGE_LOGS);
+ if (!local->pending)
+ goto out;
+
+ ret = 0;
+out:
+ return ret;
}
void
-afr_matrix_cleanup (int32_t **matrix, unsigned int m)
+afr_set_low_priority(call_frame_t *frame)
{
- int i = 0;
-
- if (!matrix)
- goto out;
- for (i = 0; i < m; i++) {
- GF_FREE (matrix[i]);
- }
+ frame->root->pid = LOW_PRIO_PROC_PID;
+}
- GF_FREE (matrix);
+void
+afr_priv_destroy(afr_private_t *priv)
+{
+ int i = 0;
+ int child_count = -1;
+
+ if (!priv)
+ goto out;
+
+ GF_FREE(priv->sh_domain);
+ GF_FREE(priv->last_event);
+
+ child_count = priv->child_count;
+ if (priv->thin_arbiter_count) {
+ child_count++;
+ }
+ if (priv->pending_key) {
+ for (i = 0; i < child_count; i++)
+ GF_FREE(priv->pending_key[i]);
+ }
+
+ GF_FREE(priv->pending_reads);
+ GF_FREE(priv->local);
+ GF_FREE(priv->pending_key);
+ GF_FREE(priv->children);
+ GF_FREE(priv->anon_inode);
+ GF_FREE(priv->child_up);
+ GF_FREE(priv->halo_child_up);
+ GF_FREE(priv->child_latency);
+ LOCK_DESTROY(&priv->lock);
+
+ GF_FREE(priv);
out:
- return;
+ return;
}
-int32_t**
-afr_matrix_create (unsigned int m, unsigned int n)
+int **
+afr_mark_pending_changelog(afr_private_t *priv, unsigned char *pending,
+ dict_t *xattr, ia_type_t iat)
{
- int32_t **matrix = NULL;
- int i = 0;
+ int i = 0;
+ int **changelog = NULL;
+ int idx = -1;
+ int m_idx = 0;
+ int d_idx = 0;
+ int ret = 0;
- matrix = GF_CALLOC (sizeof (*matrix), m, gf_afr_mt_int32_t);
- if (!matrix)
- goto out;
+ m_idx = afr_index_for_transaction_type(AFR_METADATA_TRANSACTION);
+ d_idx = afr_index_for_transaction_type(AFR_DATA_TRANSACTION);
- for (i = 0; i < m; i++) {
- matrix[i] = GF_CALLOC (sizeof (*matrix[i]), n,
- gf_afr_mt_int32_t);
- if (!matrix[i])
- goto out;
- }
- return matrix;
-out:
- afr_matrix_cleanup (matrix, m);
+ idx = afr_index_from_ia_type(iat);
+
+ changelog = afr_matrix_create(priv->child_count, AFR_NUM_CHANGE_LOGS);
+ if (!changelog)
+ goto out;
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (!pending[i])
+ continue;
+
+ changelog[i][m_idx] = hton32(1);
+ if (idx != -1)
+ changelog[i][idx] = hton32(1);
+ /* If the newentry marking is on a newly created directory,
+ * then mark it with the full-heal indicator.
+ */
+ if ((IA_ISDIR(iat)) && (priv->esh_granular))
+ changelog[i][d_idx] = hton32(1);
+ }
+ ret = afr_set_pending_dict(priv, xattr, changelog);
+ if (ret < 0) {
+ afr_matrix_cleanup(changelog, priv->child_count);
return NULL;
+ }
+out:
+ return changelog;
}
-int
-afr_inodelk_init (afr_inodelk_t *lk, char *dom, size_t child_count)
+static dict_t *
+afr_set_heal_info(char *status)
{
- int ret = -ENOMEM;
+ dict_t *dict = NULL;
+ int ret = -1;
- lk->domain = dom;
- lk->locked_nodes = GF_CALLOC (sizeof (*lk->locked_nodes),
- child_count, gf_afr_mt_char);
- if (NULL == lk->locked_nodes)
- goto out;
- ret = 0;
+ dict = dict_new();
+ if (!dict) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = dict_set_dynstr_sizen(dict, "heal-info", status);
+ if (ret)
+ gf_msg("", GF_LOG_WARNING, -ret, AFR_MSG_DICT_SET_FAILED,
+ "Failed to set heal-info key to "
+ "%s",
+ status);
out:
- return ret;
+ /* Any error other than EINVAL, dict_set_dynstr frees status */
+ if (ret == -ENOMEM || ret == -EINVAL) {
+ GF_FREE(status);
+ }
+
+ if (ret && dict) {
+ dict_unref(dict);
+ dict = NULL;
+ }
+ return dict;
}
-int
-afr_transaction_local_init (afr_local_t *local, xlator_t *this)
+static gf_boolean_t
+afr_is_dirty_count_non_unary_for_txn(xlator_t *this, struct afr_reply *replies,
+ afr_transaction_type type)
{
- int child_up_count = 0;
- int ret = -ENOMEM;
- afr_private_t *priv = NULL;
+ afr_private_t *priv = this->private;
+ int *dirty = alloca0(priv->child_count * sizeof(int));
+ int i = 0;
- priv = this->private;
- ret = afr_internal_lock_init (&local->internal_lock, priv->child_count,
- AFR_TRANSACTION_LK);
- if (ret < 0)
- goto out;
+ afr_selfheal_extract_xattr(this, replies, type, dirty, NULL);
+ for (i = 0; i < priv->child_count; i++) {
+ if (dirty[i] > 1)
+ return _gf_true;
+ }
- if ((local->transaction.type == AFR_DATA_TRANSACTION) ||
- (local->transaction.type == AFR_METADATA_TRANSACTION)) {
- ret = afr_inodelk_init (&local->internal_lock.inodelk[0],
- this->name, priv->child_count);
- if (ret < 0)
- goto out;
- }
+ return _gf_false;
+}
- ret = -ENOMEM;
- child_up_count = AFR_COUNT (local->child_up, priv->child_count);
- if (priv->optimistic_change_log && child_up_count == priv->child_count)
- local->optimistic_change_log = 1;
+static gf_boolean_t
+afr_is_dirty_count_non_unary(xlator_t *this, struct afr_reply *replies,
+ ia_type_t ia_type)
+{
+ gf_boolean_t data_chk = _gf_false;
+ gf_boolean_t mdata_chk = _gf_false;
+ gf_boolean_t entry_chk = _gf_false;
+
+ switch (ia_type) {
+ case IA_IFDIR:
+ mdata_chk = _gf_true;
+ entry_chk = _gf_true;
+ break;
+ case IA_IFREG:
+ mdata_chk = _gf_true;
+ data_chk = _gf_true;
+ break;
+ default:
+ /*IA_IFBLK, IA_IFCHR, IA_IFLNK, IA_IFIFO, IA_IFSOCK*/
+ mdata_chk = _gf_true;
+ break;
+ }
- local->pre_op_compat = priv->pre_op_compat;
+ if (data_chk && afr_is_dirty_count_non_unary_for_txn(
+ this, replies, AFR_DATA_TRANSACTION)) {
+ return _gf_true;
+ } else if (mdata_chk && afr_is_dirty_count_non_unary_for_txn(
+ this, replies, AFR_METADATA_TRANSACTION)) {
+ return _gf_true;
+ } else if (entry_chk && afr_is_dirty_count_non_unary_for_txn(
+ this, replies, AFR_ENTRY_TRANSACTION)) {
+ return _gf_true;
+ }
- local->transaction.eager_lock =
- GF_CALLOC (sizeof (*local->transaction.eager_lock),
- priv->child_count,
- gf_afr_mt_int32_t);
+ return _gf_false;
+}
- if (!local->transaction.eager_lock)
- goto out;
+static int
+afr_update_heal_status(xlator_t *this, struct afr_reply *replies,
+ ia_type_t ia_type, gf_boolean_t *esh, gf_boolean_t *dsh,
+ gf_boolean_t *msh, unsigned char pending)
+{
+ int ret = -1;
+ GF_UNUSED int ret1 = 0;
+ int i = 0;
+ int io_domain_lk_count = 0;
+ int shd_domain_lk_count = 0;
+ afr_private_t *priv = NULL;
+ char *key1 = NULL;
+ char *key2 = NULL;
+
+ priv = this->private;
+ key1 = alloca0(strlen(GLUSTERFS_INODELK_DOM_PREFIX) + 2 +
+ strlen(this->name));
+ key2 = alloca0(strlen(GLUSTERFS_INODELK_DOM_PREFIX) + 2 +
+ strlen(priv->sh_domain));
+ sprintf(key1, "%s:%s", GLUSTERFS_INODELK_DOM_PREFIX, this->name);
+ sprintf(key2, "%s:%s", GLUSTERFS_INODELK_DOM_PREFIX, priv->sh_domain);
+
+ for (i = 0; i < priv->child_count; i++) {
+ if ((replies[i].valid != 1) || (replies[i].op_ret != 0))
+ continue;
+ if (!io_domain_lk_count) {
+ ret1 = dict_get_int32(replies[i].xdata, key1, &io_domain_lk_count);
+ }
+ if (!shd_domain_lk_count) {
+ ret1 = dict_get_int32(replies[i].xdata, key2, &shd_domain_lk_count);
+ }
+ }
+
+ if (!pending) {
+ if ((afr_is_dirty_count_non_unary(this, replies, ia_type)) ||
+ (!io_domain_lk_count)) {
+ /* Needs heal. */
+ ret = 0;
+ } else {
+ /* No heal needed. */
+ *dsh = *esh = *msh = 0;
+ }
+ } else {
+ if (shd_domain_lk_count) {
+ ret = -EAGAIN; /*For 'possibly-healing'. */
+ } else {
+ ret = 0; /*needs heal. Just set a non -ve value so that it is
+ assumed as the source index.*/
+ }
+ }
+ return ret;
+}
- local->transaction.pre_op = GF_CALLOC (sizeof (*local->transaction.pre_op),
- priv->child_count,
- gf_afr_mt_char);
- if (!local->transaction.pre_op)
- goto out;
+/*return EIO, EAGAIN or pending*/
+int
+afr_lockless_inspect(call_frame_t *frame, xlator_t *this, uuid_t gfid,
+ inode_t **inode, gf_boolean_t *entry_selfheal,
+ gf_boolean_t *data_selfheal,
+ gf_boolean_t *metadata_selfheal, unsigned char *pending)
+{
+ int ret = -1;
+ int i = 0;
+ afr_private_t *priv = NULL;
+ struct afr_reply *replies = NULL;
+ gf_boolean_t dsh = _gf_false;
+ gf_boolean_t msh = _gf_false;
+ gf_boolean_t esh = _gf_false;
+ unsigned char *sources = NULL;
+ unsigned char *sinks = NULL;
+ unsigned char *valid_on = NULL;
+ uint64_t *witness = NULL;
+
+ priv = this->private;
+ replies = alloca0(sizeof(*replies) * priv->child_count);
+ sources = alloca0(sizeof(*sources) * priv->child_count);
+ sinks = alloca0(sizeof(*sinks) * priv->child_count);
+ witness = alloca0(sizeof(*witness) * priv->child_count);
+ valid_on = alloca0(sizeof(*valid_on) * priv->child_count);
+
+ ret = afr_selfheal_unlocked_inspect(frame, this, gfid, inode, &dsh, &msh,
+ &esh, replies);
+ if (ret)
+ goto out;
+ for (i = 0; i < priv->child_count; i++) {
+ if (replies[i].valid && replies[i].op_ret == 0) {
+ valid_on[i] = 1;
+ }
+ }
+ if (msh) {
+ ret = afr_selfheal_find_direction(frame, this, replies,
+ AFR_METADATA_TRANSACTION, valid_on,
+ sources, sinks, witness, pending);
+ if (*pending & PFLAG_SBRAIN)
+ ret = -EIO;
+ if (ret)
+ goto out;
+ }
+ if (dsh) {
+ ret = afr_selfheal_find_direction(frame, this, replies,
+ AFR_DATA_TRANSACTION, valid_on,
+ sources, sinks, witness, pending);
+ if (*pending & PFLAG_SBRAIN)
+ ret = -EIO;
+ if (ret)
+ goto out;
+ }
+ if (esh) {
+ ret = afr_selfheal_find_direction(frame, this, replies,
+ AFR_ENTRY_TRANSACTION, valid_on,
+ sources, sinks, witness, pending);
+ if (*pending & PFLAG_SBRAIN)
+ ret = -EIO;
+ if (ret)
+ goto out;
+ }
- if (priv->arbiter_count == 1) {
- local->transaction.pre_op_xdata =
- GF_CALLOC (sizeof (*local->transaction.pre_op_xdata),
- priv->child_count, gf_afr_mt_dict_t);
- if (!local->transaction.pre_op_xdata)
- goto out;
+ ret = afr_update_heal_status(this, replies, (*inode)->ia_type, &esh, &dsh,
+ &msh, *pending);
+out:
+ *data_selfheal = dsh;
+ *entry_selfheal = esh;
+ *metadata_selfheal = msh;
+ if (replies)
+ afr_replies_wipe(replies, priv->child_count);
+ return ret;
+}
- local->transaction.pre_op_sources =
- GF_CALLOC (sizeof (*local->transaction.pre_op_sources),
- priv->child_count, gf_afr_mt_char);
- if (!local->transaction.pre_op_sources)
- goto out;
+int
+afr_get_heal_info(call_frame_t *frame, xlator_t *this, loc_t *loc)
+{
+ gf_boolean_t data_selfheal = _gf_false;
+ gf_boolean_t metadata_selfheal = _gf_false;
+ gf_boolean_t entry_selfheal = _gf_false;
+ unsigned char pending = 0;
+ dict_t *dict = NULL;
+ int ret = -1;
+ int op_errno = ENOMEM;
+ inode_t *inode = NULL;
+ char *substr = NULL;
+ char *status = NULL;
+ call_frame_t *heal_frame = NULL;
+ afr_local_t *heal_local = NULL;
+
+ /*Use frame with lk-owner set*/
+ heal_frame = afr_frame_create(frame->this, &op_errno);
+ if (!heal_frame) {
+ ret = -1;
+ goto out;
+ }
+ heal_local = heal_frame->local;
+ heal_frame->local = frame->local;
+
+ ret = afr_lockless_inspect(heal_frame, this, loc->gfid, &inode,
+ &entry_selfheal, &data_selfheal,
+ &metadata_selfheal, &pending);
+
+ if (ret == -ENOMEM) {
+ ret = -1;
+ goto out;
+ }
+
+ if (pending & PFLAG_PENDING) {
+ gf_asprintf(&substr, "-pending");
+ if (!substr)
+ goto out;
+ }
+
+ if (ret == -EIO) {
+ ret = gf_asprintf(&status, "split-brain%s", substr ? substr : "");
+ if (ret < 0) {
+ goto out;
}
-
- local->transaction.fop_subvols = GF_CALLOC (sizeof (*local->transaction.fop_subvols),
- priv->child_count,
- gf_afr_mt_char);
- if (!local->transaction.fop_subvols)
+ dict = afr_set_heal_info(status);
+ if (!dict) {
+ ret = -1;
+ goto out;
+ }
+ } else if (ret == -EAGAIN) {
+ ret = gf_asprintf(&status, "possibly-healing%s", substr ? substr : "");
+ if (ret < 0) {
+ goto out;
+ }
+ dict = afr_set_heal_info(status);
+ if (!dict) {
+ ret = -1;
+ goto out;
+ }
+ } else if (ret >= 0) {
+ /* value of ret = source index
+ * so ret >= 0 and at least one of the 3 booleans set to
+ * true means a source is identified; heal is required.
+ */
+ if (!data_selfheal && !entry_selfheal && !metadata_selfheal) {
+ status = gf_strdup("no-heal");
+ if (!status) {
+ ret = -1;
goto out;
-
- local->transaction.failed_subvols = GF_CALLOC (sizeof (*local->transaction.failed_subvols),
- priv->child_count,
- gf_afr_mt_char);
- if (!local->transaction.failed_subvols)
+ }
+ dict = afr_set_heal_info(status);
+ if (!dict) {
+ ret = -1;
goto out;
-
- local->pending = afr_matrix_create (priv->child_count,
- AFR_NUM_CHANGE_LOGS);
- if (!local->pending)
+ }
+ } else {
+ ret = gf_asprintf(&status, "heal%s", substr ? substr : "");
+ if (ret < 0) {
+ goto out;
+ }
+ dict = afr_set_heal_info(status);
+ if (!dict) {
+ ret = -1;
+ goto out;
+ }
+ }
+ } else if (ret < 0) {
+ /* Apart from above checked -ve ret values, there are
+ * other possible ret values like ENOTCONN
+ * (returned when number of valid replies received are
+ * less than 2)
+ * in which case heal is required when one of the
+ * selfheal booleans is set.
+ */
+ if (data_selfheal || entry_selfheal || metadata_selfheal) {
+ ret = gf_asprintf(&status, "heal%s", substr ? substr : "");
+ if (ret < 0) {
goto out;
+ }
+ dict = afr_set_heal_info(status);
+ if (!dict) {
+ ret = -1;
+ goto out;
+ }
+ }
+ }
- INIT_LIST_HEAD (&local->transaction.eager_locked);
+ ret = 0;
+ op_errno = 0;
- ret = 0;
out:
- return ret;
+ if (heal_frame) {
+ heal_frame->local = heal_local;
+ AFR_STACK_DESTROY(heal_frame);
+ }
+ AFR_STACK_UNWIND(getxattr, frame, ret, op_errno, dict, NULL);
+ if (dict)
+ dict_unref(dict);
+ if (inode)
+ inode_unref(inode);
+ GF_FREE(substr);
+ return ret;
}
+int
+_afr_is_split_brain(call_frame_t *frame, xlator_t *this,
+ struct afr_reply *replies, afr_transaction_type type,
+ gf_boolean_t *spb)
+{
+ afr_private_t *priv = NULL;
+ uint64_t *witness = NULL;
+ unsigned char *sources = NULL;
+ unsigned char *sinks = NULL;
+ int sources_count = 0;
+ int ret = 0;
+
+ priv = this->private;
+
+ sources = alloca0(priv->child_count);
+ sinks = alloca0(priv->child_count);
+ witness = alloca0(priv->child_count * sizeof(*witness));
+
+ ret = afr_selfheal_find_direction(frame, this, replies, type,
+ priv->child_up, sources, sinks, witness,
+ NULL);
+ if (ret)
+ return ret;
-void
-afr_set_low_priority (call_frame_t *frame)
-{
- frame->root->pid = LOW_PRIO_PROC_PID;
-}
+ sources_count = AFR_COUNT(sources, priv->child_count);
+ if (!sources_count)
+ *spb = _gf_true;
+ return ret;
+}
-gf_boolean_t
-afr_have_quorum (char *logname, afr_private_t *priv)
+int
+afr_is_split_brain(call_frame_t *frame, xlator_t *this, inode_t *inode,
+ uuid_t gfid, gf_boolean_t *d_spb, gf_boolean_t *m_spb)
{
- unsigned int quorum = 0;
+ int ret = -1;
+ afr_private_t *priv = NULL;
+ struct afr_reply *replies = NULL;
- GF_VALIDATE_OR_GOTO(logname,priv,out);
+ priv = this->private;
- quorum = priv->quorum_count;
- if (quorum != AFR_QUORUM_AUTO) {
- return (priv->up_count >= (priv->down_count + quorum));
- }
+ replies = alloca0(sizeof(*replies) * priv->child_count);
- quorum = priv->child_count / 2 + 1;
- if (priv->up_count >= (priv->down_count + quorum)) {
- return _gf_true;
- }
+ ret = afr_selfheal_unlocked_discover(frame, inode, gfid, replies);
+ if (ret)
+ goto out;
- /*
- * Special case for even numbers of nodes: if we have exactly half
- * and that includes the first ("senior-most") node, then that counts
- * as quorum even if it wouldn't otherwise. This supports e.g. N=2
- * while preserving the critical property that there can only be one
- * such group.
- */
- if ((priv->child_count % 2) == 0) {
- quorum = priv->child_count / 2;
- if (priv->up_count >= (priv->down_count + quorum)) {
- if (priv->child_up[0]) {
- return _gf_true;
- }
- }
- }
+ if (!afr_can_decide_split_brain_source_sinks(replies, priv->child_count)) {
+ ret = -EAGAIN;
+ goto out;
+ }
+
+ ret = _afr_is_split_brain(frame, this, replies, AFR_DATA_TRANSACTION,
+ d_spb);
+ if (ret)
+ goto out;
+ ret = _afr_is_split_brain(frame, this, replies, AFR_METADATA_TRANSACTION,
+ m_spb);
out:
- return _gf_false;
+ if (replies) {
+ afr_replies_wipe(replies, priv->child_count);
+ replies = NULL;
+ }
+ return ret;
}
-void
-afr_priv_destroy (afr_private_t *priv)
+int
+afr_get_split_brain_status_cbk(int ret, call_frame_t *frame, void *opaque)
{
- int i = 0;
+ GF_FREE(opaque);
+ return 0;
+}
- if (!priv)
- goto out;
- GF_FREE (priv->last_event);
- if (priv->pending_key) {
- for (i = 0; i < priv->child_count; i++)
- GF_FREE (priv->pending_key[i]);
+int
+afr_get_split_brain_status(void *opaque)
+{
+ gf_boolean_t d_spb = _gf_false;
+ gf_boolean_t m_spb = _gf_false;
+ int ret = -1;
+ int op_errno = 0;
+ int i = 0;
+ char *choices = NULL;
+ char *status = NULL;
+ dict_t *dict = NULL;
+ inode_t *inode = NULL;
+ afr_private_t *priv = NULL;
+ xlator_t **children = NULL;
+ call_frame_t *frame = NULL;
+ xlator_t *this = NULL;
+ loc_t *loc = NULL;
+ afr_spb_status_t *data = NULL;
+
+ data = opaque;
+ frame = data->frame;
+ this = frame->this;
+ loc = data->loc;
+ priv = this->private;
+ children = priv->children;
+
+ inode = afr_inode_find(this, loc->gfid);
+ if (!inode)
+ goto out;
+
+ dict = dict_new();
+ if (!dict) {
+ op_errno = ENOMEM;
+ ret = -1;
+ goto out;
+ }
+
+ /* Calculation for string length :
+ * (child_count X length of child-name) + SLEN(" Choices :")
+ * child-name consists of :
+ * a) 251 = max characters for volname according to GD_VOLUME_NAME_MAX
+ * b) strlen("-client-00,") assuming 16 replicas
+ */
+ choices = alloca0(priv->child_count * (256 + SLEN("-client-00,")) +
+ SLEN(" Choices:"));
+
+ ret = afr_is_split_brain(frame, this, inode, loc->gfid, &d_spb, &m_spb);
+ if (ret) {
+ op_errno = -ret;
+ if (ret == -EAGAIN) {
+ ret = dict_set_sizen_str_sizen(dict, GF_AFR_SBRAIN_STATUS,
+ SBRAIN_HEAL_NO_GO_MSG);
+ if (ret) {
+ gf_msg(this->name, GF_LOG_WARNING, -ret,
+ AFR_MSG_DICT_SET_FAILED,
+ "Failed to set GF_AFR_SBRAIN_STATUS in dict");
+ }
+ }
+ ret = -1;
+ goto out;
+ }
+
+ if (d_spb || m_spb) {
+ sprintf(choices, " Choices:");
+ for (i = 0; i < priv->child_count; i++) {
+ strcat(choices, children[i]->name);
+ strcat(choices, ",");
+ }
+ choices[strlen(choices) - 1] = '\0';
+
+ ret = gf_asprintf(&status,
+ "data-split-brain:%s "
+ "metadata-split-brain:%s%s",
+ (d_spb) ? "yes" : "no", (m_spb) ? "yes" : "no",
+ choices);
+
+ if (-1 == ret) {
+ op_errno = ENOMEM;
+ goto out;
+ }
+ ret = dict_set_dynstr_sizen(dict, GF_AFR_SBRAIN_STATUS, status);
+ if (ret) {
+ op_errno = -ret;
+ ret = -1;
+ goto out;
+ }
+ } else {
+ ret = dict_set_sizen_str_sizen(dict, GF_AFR_SBRAIN_STATUS,
+ SFILE_NOT_UNDER_DATA);
+ if (ret) {
+ op_errno = -ret;
+ ret = -1;
+ goto out;
}
- GF_FREE (priv->pending_key);
- GF_FREE (priv->children);
- GF_FREE (priv->child_up);
- LOCK_DESTROY (&priv->lock);
+ }
- GF_FREE (priv);
+ ret = 0;
out:
- return;
+ AFR_STACK_UNWIND(getxattr, frame, ret, op_errno, dict, NULL);
+ if (dict)
+ dict_unref(dict);
+ if (inode)
+ inode_unref(inode);
+ return ret;
}
-void
-afr_handle_open_fd_count (call_frame_t *frame, xlator_t *this)
+int32_t
+afr_heal_splitbrain_file(call_frame_t *frame, xlator_t *this, loc_t *loc)
{
- afr_local_t *local = NULL;
- afr_fd_ctx_t *fd_ctx = NULL;
-
- local = frame->local;
-
- if (!local->fd)
- return;
-
- fd_ctx = afr_fd_ctx_get (local->fd, this);
- if (!fd_ctx)
- return;
+ int ret = 0;
+ int op_errno = 0;
+ dict_t *dict = NULL;
+ afr_local_t *local = NULL;
+ afr_local_t *heal_local = NULL;
+ call_frame_t *heal_frame = NULL;
+
+ local = frame->local;
+ dict = dict_new();
+ if (!dict) {
+ op_errno = ENOMEM;
+ ret = -1;
+ goto out;
+ }
+
+ heal_frame = afr_frame_create(this, &op_errno);
+ if (!heal_frame) {
+ ret = -1;
+ goto out;
+ }
+ heal_local = heal_frame->local;
+ heal_frame->local = frame->local;
+ /*Initiate heal with heal_frame with lk-owner set so that inodelk/entrylk
+ * work correctly*/
+ ret = afr_selfheal_do(heal_frame, this, loc->gfid);
+
+ if (ret == 1 || ret == 2) {
+ ret = dict_set_sizen_str_sizen(dict, "sh-fail-msg",
+ SFILE_NOT_IN_SPLIT_BRAIN);
+ if (ret)
+ gf_msg(this->name, GF_LOG_WARNING, -ret, AFR_MSG_DICT_SET_FAILED,
+ "Failed to set sh-fail-msg in dict");
+ ret = 0;
+ goto out;
+ } else {
+ if (local->xdata_rsp) {
+ /* 'sh-fail-msg' has been set in the dict during self-heal.*/
+ dict_copy(local->xdata_rsp, dict);
+ ret = 0;
+ } else if (ret < 0) {
+ op_errno = -ret;
+ ret = -1;
+ }
+ }
- fd_ctx->open_fd_count = local->open_fd_count;
+out:
+ if (heal_frame) {
+ heal_frame->local = heal_local;
+ AFR_STACK_DESTROY(heal_frame);
+ }
+ if (local->op == GF_FOP_GETXATTR)
+ AFR_STACK_UNWIND(getxattr, frame, ret, op_errno, dict, NULL);
+ else if (local->op == GF_FOP_SETXATTR)
+ AFR_STACK_UNWIND(setxattr, frame, ret, op_errno, NULL);
+ if (dict)
+ dict_unref(dict);
+ return ret;
}
-int**
-afr_mark_pending_changelog (afr_private_t *priv, unsigned char *pending,
- dict_t *xattr, ia_type_t iat)
+int
+afr_get_child_index_from_name(xlator_t *this, char *name)
{
- int i = 0;
- int **changelog = NULL;
- int idx = -1;
- int m_idx = 0;
- int ret = 0;
+ afr_private_t *priv = this->private;
+ int index = -1;
- m_idx = afr_index_for_transaction_type (AFR_METADATA_TRANSACTION);
+ for (index = 0; index < priv->child_count; index++) {
+ if (!strcmp(priv->children[index]->name, name))
+ goto out;
+ }
+ index = -1;
+out:
+ return index;
+}
- idx = afr_index_from_ia_type (iat);
+void
+afr_priv_need_heal_set(afr_private_t *priv, gf_boolean_t need_heal)
+{
+ LOCK(&priv->lock);
+ {
+ priv->need_heal = need_heal;
+ }
+ UNLOCK(&priv->lock);
+}
- changelog = afr_matrix_create (priv->child_count, AFR_NUM_CHANGE_LOGS);
- if (!changelog)
- goto out;
+void
+afr_set_need_heal(xlator_t *this, afr_local_t *local)
+{
+ int i = 0;
+ afr_private_t *priv = this->private;
+ gf_boolean_t need_heal = _gf_false;
- for (i = 0; i < priv->child_count; i++) {
- if (!pending[i])
- continue;
-
- changelog[i][m_idx] = hton32(1);
- if (idx != -1)
- changelog[i][idx] = hton32(1);
- }
- ret = afr_set_pending_dict (priv, xattr, changelog);
- if (ret < 0) {
- afr_matrix_cleanup (changelog, priv->child_count);
- return NULL;
- }
-out:
- return changelog;
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->replies[i].valid && local->replies[i].need_heal) {
+ need_heal = _gf_true;
+ break;
+ }
+ }
+ afr_priv_need_heal_set(priv, need_heal);
+ return;
}
gf_boolean_t
-afr_decide_heal_info (afr_private_t *priv, unsigned char *sources, int ret)
+afr_get_need_heal(xlator_t *this)
{
- int sources_count = 0;
+ afr_private_t *priv = this->private;
+ gf_boolean_t need_heal = _gf_true;
- if (ret)
- goto out;
+ LOCK(&priv->lock);
+ {
+ need_heal = priv->need_heal;
+ }
+ UNLOCK(&priv->lock);
+ return need_heal;
+}
- sources_count = AFR_COUNT (sources, priv->child_count);
- if (sources_count == priv->child_count)
- return _gf_false;
-out:
- return _gf_true;
+int
+afr_get_msg_id(char *op_type)
+{
+ if (!strcmp(op_type, GF_AFR_REPLACE_BRICK))
+ return AFR_MSG_REPLACE_BRICK_STATUS;
+ else if (!strcmp(op_type, GF_AFR_ADD_BRICK))
+ return AFR_MSG_ADD_BRICK_STATUS;
+ return -1;
}
int
-afr_selfheal_locked_metadata_inspect (call_frame_t *frame, xlator_t *this,
- inode_t *inode, gf_boolean_t *msh)
+afr_fav_child_reset_sink_xattrs_cbk(int ret, call_frame_t *heal_frame,
+ void *opaque)
{
- int ret = -1;
- unsigned char *locked_on = NULL;
- unsigned char *sources = NULL;
- unsigned char *sinks = NULL;
- unsigned char *healed_sinks = NULL;
- struct afr_reply *locked_replies = NULL;
+ call_frame_t *txn_frame = NULL;
+ afr_local_t *local = NULL;
+ afr_local_t *heal_local = NULL;
+ xlator_t *this = NULL;
- afr_private_t *priv = this->private;
+ heal_local = heal_frame->local;
+ txn_frame = heal_local->heal_frame;
+ local = txn_frame->local;
+ this = txn_frame->this;
- locked_on = alloca0 (priv->child_count);
- sources = alloca0 (priv->child_count);
- sinks = alloca0 (priv->child_count);
- healed_sinks = alloca0 (priv->child_count);
+ /* Refresh the inode agan and proceed with the transaction.*/
+ afr_inode_refresh(txn_frame, this, local->inode, NULL, local->refreshfn);
- locked_replies = alloca0 (sizeof (*locked_replies) * priv->child_count);
+ AFR_STACK_DESTROY(heal_frame);
- ret = afr_selfheal_inodelk (frame, this, inode, this->name,
- LLONG_MAX - 1, 0, locked_on);
- {
- if (ret == 0) {
- /* Not a single lock */
- ret = -afr_final_errno (frame->local, priv);
- if (ret == 0)
- ret = -ENOTCONN;/* all invalid responses */
- goto out;
- }
- ret = __afr_selfheal_metadata_prepare (frame, this, inode,
- locked_on, sources,
- sinks, healed_sinks,
- locked_replies);
- *msh = afr_decide_heal_info (priv, sources, ret);
- }
- afr_selfheal_uninodelk (frame, this, inode, this->name,
- LLONG_MAX - 1, 0, locked_on);
-out:
- if (locked_replies)
- afr_replies_wipe (locked_replies, priv->child_count);
- return ret;
+ return 0;
}
int
-afr_selfheal_locked_data_inspect (call_frame_t *frame, xlator_t *this,
- inode_t *inode, gf_boolean_t *dsh)
-{
- int ret = -1;
- afr_private_t *priv = NULL;
- unsigned char *locked_on = NULL;
- unsigned char *data_lock = NULL;
- unsigned char *sources = NULL;
- unsigned char *sinks = NULL;
- unsigned char *healed_sinks = NULL;
- struct afr_reply *locked_replies = NULL;
-
- priv = this->private;
- locked_on = alloca0 (priv->child_count);
- data_lock = alloca0 (priv->child_count);
- sources = alloca0 (priv->child_count);
- sinks = alloca0 (priv->child_count);
- healed_sinks = alloca0 (priv->child_count);
-
- locked_replies = alloca0 (sizeof (*locked_replies) * priv->child_count);
-
- ret = afr_selfheal_tryinodelk (frame, this, inode, priv->sh_domain,
- 0, 0, locked_on);
+afr_fav_child_reset_sink_xattrs(void *opaque)
+{
+ call_frame_t *heal_frame = NULL;
+ call_frame_t *txn_frame = NULL;
+ xlator_t *this = NULL;
+ gf_boolean_t d_spb = _gf_false;
+ gf_boolean_t m_spb = _gf_false;
+ afr_local_t *heal_local = NULL;
+ afr_local_t *txn_local = NULL;
+ afr_private_t *priv = NULL;
+ inode_t *inode = NULL;
+ unsigned char *locked_on = NULL;
+ unsigned char *sources = NULL;
+ unsigned char *sinks = NULL;
+ unsigned char *healed_sinks = NULL;
+ unsigned char *undid_pending = NULL;
+ struct afr_reply *locked_replies = NULL;
+ int ret = 0;
+
+ heal_frame = (call_frame_t *)opaque;
+ heal_local = heal_frame->local;
+ txn_frame = heal_local->heal_frame;
+ txn_local = txn_frame->local;
+ this = txn_frame->this;
+ inode = txn_local->inode;
+ priv = this->private;
+ locked_on = alloca0(priv->child_count);
+ sources = alloca0(priv->child_count);
+ sinks = alloca0(priv->child_count);
+ healed_sinks = alloca0(priv->child_count);
+ undid_pending = alloca0(priv->child_count);
+ locked_replies = alloca0(sizeof(*locked_replies) * priv->child_count);
+
+ ret = _afr_is_split_brain(txn_frame, this, txn_local->replies,
+ AFR_DATA_TRANSACTION, &d_spb);
+
+ ret = _afr_is_split_brain(txn_frame, this, txn_local->replies,
+ AFR_METADATA_TRANSACTION, &m_spb);
+
+ /* Take appropriate locks and reset sink xattrs. */
+ if (d_spb) {
+ ret = afr_selfheal_inodelk(heal_frame, this, inode, this->name, 0, 0,
+ locked_on);
{
- if (ret == 0) {
- ret = -afr_final_errno (frame->local, priv);
- if (ret == 0)
- ret = -ENOTCONN;/* all invalid responses */
- goto out;
- }
- ret = afr_selfheal_inodelk (frame, this, inode, this->name,
- 0, 0, data_lock);
- {
- if (ret == 0) {
- ret = -afr_final_errno (frame->local, priv);
- if (ret == 0)
- ret = -ENOTCONN;
- /* all invalid responses */
- goto unlock;
- }
- ret = __afr_selfheal_data_prepare (frame, this, inode,
- data_lock, sources,
- sinks, healed_sinks,
- locked_replies);
- *dsh = afr_decide_heal_info (priv, sources, ret);
- }
- afr_selfheal_uninodelk (frame, this, inode, this->name, 0, 0,
- data_lock);
+ if (ret < priv->child_count)
+ goto data_unlock;
+ ret = __afr_selfheal_data_prepare(
+ heal_frame, this, inode, locked_on, sources, sinks,
+ healed_sinks, undid_pending, locked_replies, NULL);
+ }
+ data_unlock:
+ afr_selfheal_uninodelk(heal_frame, this, inode, this->name, 0, 0,
+ locked_on);
+ }
+
+ if (m_spb) {
+ memset(locked_on, 0, sizeof(*locked_on) * priv->child_count);
+ memset(undid_pending, 0, sizeof(*undid_pending) * priv->child_count);
+ ret = afr_selfheal_inodelk(heal_frame, this, inode, this->name,
+ LLONG_MAX - 1, 0, locked_on);
+ {
+ if (ret < priv->child_count)
+ goto mdata_unlock;
+ ret = __afr_selfheal_metadata_prepare(
+ heal_frame, this, inode, locked_on, sources, sinks,
+ healed_sinks, undid_pending, locked_replies, NULL);
}
-unlock:
- afr_selfheal_uninodelk (frame, this, inode, priv->sh_domain, 0, 0,
- locked_on);
-out:
- if (locked_replies)
- afr_replies_wipe (locked_replies, priv->child_count);
- return ret;
+ mdata_unlock:
+ afr_selfheal_uninodelk(heal_frame, this, inode, this->name,
+ LLONG_MAX - 1, 0, locked_on);
+ }
+
+ return ret;
}
+/*
+ * Concatenates the xattrs in local->replies separated by a delimiter.
+ */
int
-afr_selfheal_locked_entry_inspect (call_frame_t *frame, xlator_t *this,
- inode_t *inode,
- gf_boolean_t *esh)
-{
- int ret = -1;
- int source = -1;
- afr_private_t *priv = NULL;
- unsigned char *locked_on = NULL;
- unsigned char *data_lock = NULL;
- unsigned char *sources = NULL;
- unsigned char *sinks = NULL;
- unsigned char *healed_sinks = NULL;
- struct afr_reply *locked_replies = NULL;
-
- priv = this->private;
- locked_on = alloca0 (priv->child_count);
- data_lock = alloca0 (priv->child_count);
- sources = alloca0 (priv->child_count);
- sinks = alloca0 (priv->child_count);
- healed_sinks = alloca0 (priv->child_count);
-
- locked_replies = alloca0 (sizeof (*locked_replies) * priv->child_count);
-
- ret = afr_selfheal_tryentrylk (frame, this, inode, priv->sh_domain,
- NULL, locked_on);
- {
- if (ret == 0) {
- ret = -afr_final_errno (frame->local, priv);
- if (ret == 0)
- ret = -ENOTCONN;/* all invalid responses */
- goto out;
- }
+afr_serialize_xattrs_with_delimiter(call_frame_t *frame, xlator_t *this,
+ char *buf, const char *default_str,
+ int32_t *serz_len, char delimiter)
+{
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ char *xattr = NULL;
+ int i = 0;
+ int len = 0;
+ int keylen = 0;
+ size_t str_len = 0;
+ int ret = -1;
+
+ priv = this->private;
+ local = frame->local;
+
+ keylen = strlen(local->cont.getxattr.name);
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->replies[i].valid || local->replies[i].op_ret) {
+ str_len = strlen(default_str);
+ buf = strncat(buf, default_str, str_len);
+ len += str_len;
+ buf[len++] = delimiter;
+ buf[len] = '\0';
+ } else {
+ ret = dict_get_strn(local->replies[i].xattr,
+ local->cont.getxattr.name, keylen, &xattr);
+ if (ret) {
+ gf_msg("TEST", GF_LOG_ERROR, -ret, AFR_MSG_DICT_GET_FAILED,
+ "Failed to get the node_uuid of brick "
+ "%d",
+ i);
+ goto out;
+ }
+ str_len = strlen(xattr);
+ buf = strncat(buf, xattr, str_len);
+ len += str_len;
+ buf[len++] = delimiter;
+ buf[len] = '\0';
+ }
+ }
+ buf[--len] = '\0'; /*remove the last delimiter*/
+ if (serz_len)
+ *serz_len = ++len;
+ ret = 0;
- ret = afr_selfheal_entrylk (frame, this, inode, this->name,
- NULL, data_lock);
- {
- if (ret == 0) {
- ret = -afr_final_errno (frame->local, priv);
- if (ret == 0)
- ret = -ENOTCONN;
- /* all invalid responses */
- goto unlock;
- }
- ret = __afr_selfheal_entry_prepare (frame, this, inode,
- data_lock, sources,
- sinks, healed_sinks,
- locked_replies,
- &source);
- if ((ret == 0) && source < 0)
- ret = -EIO;
- *esh = afr_decide_heal_info (priv, sources, ret);
- }
- afr_selfheal_unentrylk (frame, this, inode, this->name, NULL,
- data_lock);
- }
-unlock:
- afr_selfheal_unentrylk (frame, this, inode, priv->sh_domain, NULL,
- locked_on);
out:
- if (locked_replies)
- afr_replies_wipe (locked_replies, priv->child_count);
- return ret;
+ return ret;
}
-int
-afr_selfheal_locked_inspect (call_frame_t *frame, xlator_t *this, uuid_t gfid,
- inode_t **inode,
- gf_boolean_t *entry_selfheal,
- gf_boolean_t *data_selfheal,
- gf_boolean_t *metadata_selfheal)
-
+uint64_t
+afr_write_subvol_get(call_frame_t *frame, xlator_t *this)
{
- int ret = -1;
- gf_boolean_t dsh = _gf_false;
- gf_boolean_t msh = _gf_false;
- gf_boolean_t esh = _gf_false;
+ afr_local_t *local = NULL;
+ uint64_t write_subvol = 0;
- ret = afr_selfheal_unlocked_inspect (frame, this, gfid, inode,
- &dsh, &msh, &esh);
- if (ret)
- goto out;
+ local = frame->local;
+ LOCK(&local->inode->lock);
+ write_subvol = local->inode_ctx->write_subvol;
+ UNLOCK(&local->inode->lock);
- /* For every heal type hold locks and check if it indeed needs heal */
+ return write_subvol;
+}
- if (msh) {
- ret = afr_selfheal_locked_metadata_inspect (frame, this,
- *inode, &msh);
- if (ret == -EIO)
- goto out;
- }
+int
+afr_write_subvol_set(call_frame_t *frame, xlator_t *this)
+{
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ unsigned char *data_accused = NULL;
+ unsigned char *metadata_accused = NULL;
+ unsigned char *data_readable = NULL;
+ unsigned char *metadata_readable = NULL;
+ uint16_t datamap = 0;
+ uint16_t metadatamap = 0;
+ uint64_t val = 0;
+ int event = 0;
+ int i = 0;
+
+ local = frame->local;
+ priv = this->private;
+ data_accused = alloca0(priv->child_count);
+ metadata_accused = alloca0(priv->child_count);
+ data_readable = alloca0(priv->child_count);
+ metadata_readable = alloca0(priv->child_count);
+ event = local->event_generation;
+
+ afr_readables_fill(frame, this, local->inode, data_accused,
+ metadata_accused, data_readable, metadata_readable,
+ NULL);
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (data_readable[i])
+ datamap |= (1 << i);
+ if (metadata_readable[i])
+ metadatamap |= (1 << i);
+ }
+
+ val = ((uint64_t)metadatamap) | (((uint64_t)datamap) << 16) |
+ (((uint64_t)event) << 32);
+
+ LOCK(&local->inode->lock);
+ {
+ if (local->inode_ctx->write_subvol == 0 &&
+ local->transaction.type == AFR_DATA_TRANSACTION) {
+ local->inode_ctx->write_subvol = val;
+ }
+ }
+ UNLOCK(&local->inode->lock);
+
+ return 0;
+}
- if (dsh) {
- ret = afr_selfheal_locked_data_inspect (frame, this, *inode,
- &dsh);
- if (ret == -EIO || (ret == -EAGAIN))
- goto out;
- }
+int
+afr_write_subvol_reset(call_frame_t *frame, xlator_t *this)
+{
+ afr_local_t *local = NULL;
- if (esh) {
- ret = afr_selfheal_locked_entry_inspect (frame, this, *inode,
- &esh);
- }
+ local = frame->local;
+ LOCK(&local->inode->lock);
+ {
+ GF_ASSERT(local->inode_ctx->lock_count > 0);
+ local->inode_ctx->lock_count--;
-out:
- *data_selfheal = dsh;
- *entry_selfheal = esh;
- *metadata_selfheal = msh;
- return ret;
+ if (!local->inode_ctx->lock_count)
+ local->inode_ctx->write_subvol = 0;
+ }
+ UNLOCK(&local->inode->lock);
+
+ return 0;
}
-dict_t*
-afr_set_heal_info (char *status)
+int
+afr_set_inode_local(xlator_t *this, afr_local_t *local, inode_t *inode)
{
- dict_t *dict = NULL;
- int ret = -1;
+ int ret = 0;
- dict = dict_new ();
- if (!dict) {
- ret = -ENOMEM;
- goto out;
- }
-
- if (!strcmp (status, "heal")) {
- ret = dict_set_str (dict, "heal-info", "heal");
- if (ret)
- gf_msg ("", GF_LOG_WARNING, -ret,
- AFR_MSG_DICT_SET_FAILED,
- "Failed to set heal-info key to "
- "heal");
- } else if (!strcmp (status, "split-brain")) {
- ret = dict_set_str (dict, "heal-info", "split-brain");
- if (ret)
- gf_msg ("", GF_LOG_WARNING, -ret,
- AFR_MSG_DICT_SET_FAILED,
- "Failed to set heal-info key to "
- "split-brain");
- } else if (!strcmp (status, "possibly-healing")) {
- ret = dict_set_str (dict, "heal-info", "possibly-healing");
- if (ret)
- gf_msg ("", GF_LOG_WARNING, -ret,
- AFR_MSG_DICT_SET_FAILED,
- "Failed to set heal-info key to "
- "possibly-healing");
- }
-out:
- return dict;
+ local->inode = inode_ref(inode);
+ LOCK(&local->inode->lock);
+ {
+ ret = __afr_inode_ctx_get(this, local->inode, &local->inode_ctx);
+ }
+ UNLOCK(&local->inode->lock);
+ if (ret < 0) {
+ gf_msg_callingfn(
+ this->name, GF_LOG_ERROR, ENOMEM, AFR_MSG_INODE_CTX_GET_FAILED,
+ "Error getting inode ctx %s", uuid_utoa(local->inode->gfid));
+ }
+ return ret;
}
-int
-afr_get_heal_info (call_frame_t *frame, xlator_t *this, loc_t *loc,
- dict_t *xdata)
+gf_boolean_t
+afr_ta_is_fop_called_from_synctask(xlator_t *this)
{
- gf_boolean_t data_selfheal = _gf_false;
- gf_boolean_t metadata_selfheal = _gf_false;
- gf_boolean_t entry_selfheal = _gf_false;
- dict_t *dict = NULL;
- int ret = -1;
- int op_errno = 0;
- inode_t *inode = NULL;
+ struct synctask *task = NULL;
+ gf_lkowner_t tmp_owner = {
+ 0,
+ };
- ret = afr_selfheal_locked_inspect (frame, this, loc->gfid, &inode,
- &entry_selfheal,
- &data_selfheal, &metadata_selfheal);
+ task = synctask_get();
+ if (!task)
+ return _gf_false;
- if (ret == -ENOMEM) {
- op_errno = -ret;
- ret = -1;
- goto out;
- }
+ set_lk_owner_from_ptr(&tmp_owner, (void *)this);
- if (ret == -EIO) {
- dict = afr_set_heal_info ("split-brain");
- } else if (ret == -EAGAIN) {
- dict = afr_set_heal_info ("possibly-healing");
- } else if (ret >= 0) {
- /* value of ret = source index
- * so ret >= 0 and at least one of the 3 booleans set to
- * true means a source is identified; heal is required.
- */
- if (!data_selfheal && !entry_selfheal &&
- !metadata_selfheal) {
- dict = afr_set_heal_info ("no-heal");
- } else {
- dict = afr_set_heal_info ("heal");
- }
- } else if (ret < 0) {
- /* Apart from above checked -ve ret values, there are
- * other possible ret values like ENOTCONN
- * (returned when number of valid replies received are
- * less than 2)
- * in which case heal is required when one of the
- * selfheal booleans is set.
- */
- if (data_selfheal || entry_selfheal ||
- metadata_selfheal) {
- dict = afr_set_heal_info ("heal");
- }
- }
- ret = 0;
+ if (!is_same_lkowner(&tmp_owner, &task->frame->root->lk_owner))
+ return _gf_false;
-out:
- AFR_STACK_UNWIND (getxattr, frame, ret, op_errno, dict, NULL);
- if (dict)
- dict_unref (dict);
- if (inode) {
- inode_forget (inode, 1);
- inode_unref (inode);
- }
- return ret;
+ return _gf_true;
}
int
-_afr_is_split_brain (call_frame_t *frame, xlator_t *this,
- struct afr_reply *replies,
- afr_transaction_type type,
- gf_boolean_t *spb)
-{
- afr_private_t *priv = NULL;
- uint64_t *witness = NULL;
- unsigned char *sources = NULL;
- unsigned char *sinks = NULL;
- int sources_count = 0;
- int ret = 0;
-
- priv = this->private;
-
- sources = alloca0 (priv->child_count);
- sinks = alloca0 (priv->child_count);
- witness = alloca0(priv->child_count * sizeof (*witness));
-
- ret = afr_selfheal_find_direction (frame, this, replies,
- type, priv->child_up, sources,
- sinks, witness);
- if (ret)
- return ret;
-
- sources_count = AFR_COUNT (sources, priv->child_count);
- if (!sources_count)
- *spb = _gf_true;
-
- return ret;
+afr_ta_post_op_lock(xlator_t *this, loc_t *loc)
+{
+ int ret = 0;
+ uuid_t gfid = {
+ 0,
+ };
+ afr_private_t *priv = this->private;
+ gf_boolean_t locked = _gf_false;
+ struct gf_flock flock1 = {
+ 0,
+ };
+ struct gf_flock flock2 = {
+ 0,
+ };
+ int32_t cmd = 0;
+
+ /* Clients must take AFR_TA_DOM_NOTIFY lock only when the previous lock
+ * has been released in afr_notify due to upcall notification from shd.
+ */
+ GF_ASSERT(priv->ta_notify_dom_lock_offset == 0);
+
+ if (!priv->shd.iamshd)
+ GF_ASSERT(afr_ta_is_fop_called_from_synctask(this));
+ flock1.l_type = F_WRLCK;
+
+ while (!locked) {
+ if (priv->shd.iamshd) {
+ cmd = F_SETLKW;
+ flock1.l_start = 0;
+ flock1.l_len = 0;
+ } else {
+ cmd = F_SETLK;
+ gf_uuid_generate(gfid);
+ flock1.l_start = gfid_to_ino(gfid);
+ if (flock1.l_start < 0)
+ flock1.l_start = -flock1.l_start;
+ flock1.l_len = 1;
+ }
+ ret = syncop_inodelk(priv->children[THIN_ARBITER_BRICK_INDEX],
+ AFR_TA_DOM_NOTIFY, loc, cmd, &flock1, NULL, NULL);
+ if (!ret) {
+ locked = _gf_true;
+ priv->ta_notify_dom_lock_offset = flock1.l_start;
+ } else if (ret == -EAGAIN) {
+ continue;
+ } else {
+ gf_msg(this->name, GF_LOG_ERROR, -ret, AFR_MSG_THIN_ARB,
+ "Failed to get "
+ "AFR_TA_DOM_NOTIFY lock on %s.",
+ loc->name);
+ goto out;
+ }
+ }
+
+ flock2.l_type = F_WRLCK;
+ flock2.l_start = 0;
+ flock2.l_len = 0;
+ ret = syncop_inodelk(priv->children[THIN_ARBITER_BRICK_INDEX],
+ AFR_TA_DOM_MODIFY, loc, F_SETLKW, &flock2, NULL, NULL);
+ if (ret) {
+ gf_msg(this->name, GF_LOG_ERROR, -ret, AFR_MSG_THIN_ARB,
+ "Failed to get AFR_TA_DOM_MODIFY lock on %s.", loc->name);
+ flock1.l_type = F_UNLCK;
+ ret = syncop_inodelk(priv->children[THIN_ARBITER_BRICK_INDEX],
+ AFR_TA_DOM_NOTIFY, loc, F_SETLK, &flock1, NULL,
+ NULL);
+ }
+out:
+ return ret;
}
int
-afr_is_split_brain (call_frame_t *frame, xlator_t *this, inode_t *inode,
- uuid_t gfid, gf_boolean_t *d_spb, gf_boolean_t *m_spb)
-{
- int ret = -1;
- afr_private_t *priv = NULL;
- struct afr_reply *replies = NULL;
+afr_ta_post_op_unlock(xlator_t *this, loc_t *loc)
+{
+ afr_private_t *priv = this->private;
+ struct gf_flock flock = {
+ 0,
+ };
+ int ret = 0;
+
+ if (!priv->shd.iamshd)
+ GF_ASSERT(afr_ta_is_fop_called_from_synctask(this));
+ flock.l_type = F_UNLCK;
+ flock.l_start = 0;
+ flock.l_len = 0;
+
+ ret = syncop_inodelk(priv->children[THIN_ARBITER_BRICK_INDEX],
+ AFR_TA_DOM_MODIFY, loc, F_SETLK, &flock, NULL, NULL);
+ if (ret) {
+ gf_msg(this->name, GF_LOG_ERROR, -ret, AFR_MSG_THIN_ARB,
+ "Failed to unlock AFR_TA_DOM_MODIFY lock.");
+ goto out;
+ }
+
+ if (!priv->shd.iamshd)
+ /* Mounts (clients) will not release the AFR_TA_DOM_NOTIFY lock
+ * in post-op as they use it as a notification mechanism. When
+ * shd sends a lock request on TA during heal, the clients will
+ * receive a lock-contention upcall notification upon which they
+ * will release the AFR_TA_DOM_NOTIFY lock after completing the
+ * in flight I/O.*/
+ goto out;
+
+ ret = syncop_inodelk(priv->children[THIN_ARBITER_BRICK_INDEX],
+ AFR_TA_DOM_NOTIFY, loc, F_SETLK, &flock, NULL, NULL);
+ if (ret) {
+ gf_msg(this->name, GF_LOG_ERROR, -ret, AFR_MSG_THIN_ARB,
+ "Failed to unlock AFR_TA_DOM_NOTIFY lock.");
+ }
+out:
+ return ret;
+}
- priv = this->private;
+call_frame_t *
+afr_ta_frame_create(xlator_t *this)
+{
+ call_frame_t *frame = NULL;
+ void *lk_owner = NULL;
- replies = alloca0 (sizeof (*replies) * priv->child_count);
+ frame = create_frame(this, this->ctx->pool);
+ if (!frame)
+ return NULL;
+ lk_owner = (void *)this;
+ afr_set_lk_owner(frame, this, lk_owner);
+ return frame;
+}
- ret = afr_selfheal_unlocked_discover (frame, inode, gfid, replies);
- if (ret)
- goto out;
+gf_boolean_t
+afr_ta_has_quorum(afr_private_t *priv, afr_local_t *local)
+{
+ int data_count = 0;
- ret = _afr_is_split_brain (frame, this, replies,
- AFR_DATA_TRANSACTION, d_spb);
- if (ret)
- goto out;
+ data_count = AFR_COUNT(local->child_up, priv->child_count);
+ if (data_count == 2) {
+ return _gf_true;
+ } else if (data_count == 1 && local->ta_child_up) {
+ return _gf_true;
+ }
- ret = _afr_is_split_brain (frame, this, replies,
- AFR_METADATA_TRANSACTION, m_spb);
-out:
- if (replies) {
- afr_replies_wipe (replies, priv->child_count);
- replies = NULL;
- }
- return ret;
+ return _gf_false;
}
-int
-afr_get_split_brain_status (call_frame_t *frame, xlator_t *this, loc_t *loc)
-{
- gf_boolean_t d_spb = _gf_false;
- gf_boolean_t m_spb = _gf_false;
- int ret = -1;
- int op_errno = 0;
- int i = 0;
- char *choices = NULL;
- char *status = NULL;
- dict_t *dict = NULL;
- inode_t *inode = NULL;
- afr_private_t *priv = NULL;
- xlator_t **children = NULL;
-
- priv = this->private;
- children = priv->children;
-
- inode = afr_inode_find (this, loc->gfid);
- if (!inode)
- goto out;
-
- /* Calculation for string length :
- * (child_count X length of child-name) + strlen (" Choices :")
- * child-name consists of :
- * a) 256 = max characters for volname according to GD_VOLUME_NAME_MAX
- * b) strlen ("-client-00,") assuming 16 replicas
- */
- choices = alloca0 (priv->child_count * (256 + strlen ("-client-00,")) +
- strlen (" Choices:"));
+static gf_boolean_t
+afr_is_add_replica_mount_lookup_on_root(call_frame_t *frame)
+{
+ afr_local_t *local = NULL;
- ret = afr_is_split_brain (frame, this, inode, loc->gfid, &d_spb,
- &m_spb);
- if (ret) {
- op_errno = -ret;
- ret = -1;
- goto out;
- }
+ if (frame->root->pid != GF_CLIENT_PID_ADD_REPLICA_MOUNT)
+ return _gf_false;
- dict = dict_new ();
- if (!dict) {
- op_errno = ENOMEM;
- ret = -1;
- goto out;
- }
+ local = frame->local;
- if (d_spb || m_spb) {
- sprintf (choices, " Choices:");
- for (i = 0; i < priv->child_count; i++) {
- strcat (choices, children[i]->name);
- strcat (choices, ",");
- }
- choices[strlen (choices) - 1] = '\0';
+ if (local->op != GF_FOP_LOOKUP)
+ /* TODO:If the replica count is being increased on a plain distribute
+ * volume that was never mounted, we need to allow setxattr on '/' with
+ * GF_CLIENT_PID_NO_ROOT_SQUASH to accomodate for DHT layout setting */
+ return _gf_false;
- ret = gf_asprintf (&status, "data-split-brain:%s "
- "metadata-split-brain:%s%s",
- (d_spb) ? "yes" : "no",
- (m_spb) ? "yes" : "no", choices);
+ if (local->inode == NULL)
+ return _gf_false;
- if (-1 == ret) {
- op_errno = ENOMEM;
- goto out;
- }
- ret = dict_set_dynstr (dict, GF_AFR_SBRAIN_STATUS, status);
- if (ret)
- goto out;
- } else {
- ret = dict_set_str (dict, GF_AFR_SBRAIN_STATUS,
- "The file is not under data or"
- " metadata split-brain");
- if (ret)
- goto out;
- }
+ if (!__is_root_gfid(local->inode->gfid))
+ return _gf_false;
- ret = 0;
-out:
- AFR_STACK_UNWIND (getxattr, frame, ret, op_errno, dict, NULL);
- if (dict)
- dict_unref (dict);
- if (inode)
- inode_unref (inode);
- return ret;
+ return _gf_true;
}
-int32_t
-afr_heal_splitbrain_file(call_frame_t *frame, xlator_t *this, loc_t *loc)
+gf_boolean_t
+afr_lookup_has_quorum(call_frame_t *frame, const unsigned int up_children_count)
{
- int ret = 0;
- int op_errno = 0;
- dict_t *dict = NULL;
- afr_local_t *local = NULL;
+ if (frame && (up_children_count > 0) &&
+ afr_is_add_replica_mount_lookup_on_root(frame))
+ return _gf_true;
- local = frame->local;
- dict = dict_new ();
- if (!dict) {
- op_errno = ENOMEM;
- ret = -1;
- goto out;
- }
+ return _gf_false;
+}
- ret = afr_selfheal_do (frame, this, loc->gfid);
+void
+afr_handle_replies_quorum(call_frame_t *frame, xlator_t *this)
+{
+ afr_local_t *local = frame->local;
+ afr_private_t *priv = this->private;
+ unsigned char *success_replies = NULL;
- if (ret == 1 || ret == 2) {
- ret = dict_set_str (dict, "sh-fail-msg",
- "File not in split-brain");
- if (ret)
- gf_msg (this->name, GF_LOG_WARNING,
- -ret, AFR_MSG_DICT_SET_FAILED,
- "Failed to set sh-fail-msg in dict");
- ret = 0;
- goto out;
- } else {
- if (local->xdata_rsp) {
- /* 'sh-fail-msg' has been set in the dict during self-heal.*/
- dict_copy (local->xdata_rsp, dict);
- ret = 0;
- } else if (ret < 0) {
- op_errno = -ret;
- ret = -1;
- }
- }
+ success_replies = alloca0(priv->child_count);
+ afr_fill_success_replies(local, priv, success_replies);
-out:
- if (local->op == GF_FOP_GETXATTR)
- AFR_STACK_UNWIND (getxattr, frame, ret, op_errno, dict, NULL);
- else if (local->op == GF_FOP_SETXATTR)
- AFR_STACK_UNWIND (setxattr, frame, ret, op_errno, NULL);
- if (dict)
- dict_unref(dict);
- return ret;
+ if (priv->quorum_count && !afr_has_quorum(success_replies, this, NULL)) {
+ local->op_errno = afr_final_errno(local, priv);
+ if (!local->op_errno)
+ local->op_errno = afr_quorum_errno(priv);
+ local->op_ret = -1;
+ }
}
-int
-afr_get_child_index_from_name (xlator_t *this, char *name)
-{
- afr_private_t *priv = this->private;
- int index = -1;
-
- for (index = 0; index < priv->child_count; index++) {
- if (!strcmp (priv->children[index]->name, name))
- goto out;
+gf_boolean_t
+afr_ta_dict_contains_pending_xattr(dict_t *dict, afr_private_t *priv, int child)
+{
+ int *pending = NULL;
+ int ret = 0;
+ int i = 0;
+
+ ret = dict_get_ptr(dict, priv->pending_key[child], (void *)&pending);
+ if (ret == 0) {
+ for (i = 0; i < AFR_NUM_CHANGE_LOGS; i++) {
+ /* Not doing a ntoh32(pending) as we just want to check
+ * if it is non-zero or not. */
+ if (pending[i]) {
+ return _gf_true;
+ }
}
- index = -1;
-out:
- return index;
+ }
+
+ return _gf_false;
}
diff --git a/xlators/cluster/afr/src/afr-dir-read.c b/xlators/cluster/afr/src/afr-dir-read.c
index 11f583e42f1..f8bf8340dab 100644
--- a/xlators/cluster/afr/src/afr-dir-read.c
+++ b/xlators/cluster/afr/src/afr-dir-read.c
@@ -8,339 +8,339 @@
cases as published by the Free Software Foundation.
*/
-
#include <libgen.h>
#include <unistd.h>
-#include <fnmatch.h>
#include <sys/time.h>
#include <stdlib.h>
#include <signal.h>
#include <string.h>
-#ifndef _CONFIG_H
-#define _CONFIG_H
-#include "config.h"
-#endif
-
-#include "glusterfs.h"
-#include "dict.h"
-#include "xlator.h"
-#include "hashfn.h"
-#include "logging.h"
-#include "stack.h"
-#include "list.h"
-#include "call-stub.h"
-#include "defaults.h"
-#include "common-utils.h"
-#include "compat-errno.h"
-#include "compat.h"
-#include "checksum.h"
+#include <glusterfs/glusterfs.h>
+#include <glusterfs/dict.h>
+#include <glusterfs/list.h>
+#include <glusterfs/common-utils.h>
+#include <glusterfs/compat-errno.h>
+#include <glusterfs/compat.h>
#include "afr.h"
#include "afr-transaction.h"
-
int32_t
-afr_opendir_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- fd_t *fd, dict_t *xdata)
+afr_opendir_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, fd_t *fd, dict_t *xdata)
{
- afr_local_t *local = NULL;
- int call_count = -1;
- int32_t child_index = 0;
- afr_fd_ctx_t *fd_ctx = NULL;
-
- local = frame->local;
- fd_ctx = local->fd_ctx;
- child_index = (long) cookie;
-
- LOCK (&frame->lock);
- {
- if (op_ret == -1) {
- local->op_errno = op_errno;
- fd_ctx->opened_on[child_index] = AFR_FD_NOT_OPENED;
- } else {
- local->op_ret = op_ret;
- fd_ctx->opened_on[child_index] = AFR_FD_OPENED;
- if (!local->xdata_rsp && xdata)
- local->xdata_rsp = dict_ref (xdata);
- }
+ afr_local_t *local = NULL;
+ int call_count = -1;
+ int32_t child_index = 0;
+ afr_fd_ctx_t *fd_ctx = NULL;
+
+ local = frame->local;
+ fd_ctx = local->fd_ctx;
+ child_index = (long)cookie;
+
+ local->replies[child_index].valid = 1;
+ local->replies[child_index].op_ret = op_ret;
+ local->replies[child_index].op_errno = op_errno;
+
+ LOCK(&frame->lock);
+ {
+ if (op_ret == -1) {
+ local->op_errno = op_errno;
+ fd_ctx->opened_on[child_index] = AFR_FD_NOT_OPENED;
+ } else {
+ local->op_ret = op_ret;
+ fd_ctx->opened_on[child_index] = AFR_FD_OPENED;
+ if (!local->xdata_rsp && xdata)
+ local->xdata_rsp = dict_ref(xdata);
}
- UNLOCK (&frame->lock);
+ call_count = --local->call_count;
+ }
+ UNLOCK(&frame->lock);
- call_count = afr_frame_return (frame);
+ if (call_count == 0) {
+ afr_handle_replies_quorum(frame, this);
+ AFR_STACK_UNWIND(opendir, frame, local->op_ret, local->op_errno,
+ local->fd, NULL);
+ }
- if (call_count == 0)
- AFR_STACK_UNWIND (opendir, frame, local->op_ret,
- local->op_errno, local->fd, NULL);
- return 0;
+ return 0;
}
-
int
-afr_opendir (call_frame_t *frame, xlator_t *this, loc_t *loc, fd_t *fd)
+afr_opendir(call_frame_t *frame, xlator_t *this, loc_t *loc, fd_t *fd,
+ dict_t *xdata)
{
- afr_private_t * priv = NULL;
- afr_local_t * local = NULL;
- int i = 0;
- int call_count = -1;
- int32_t op_errno = ENOMEM;
- afr_fd_ctx_t *fd_ctx = NULL;
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ int i = 0;
+ int call_count = -1;
+ int32_t op_errno = ENOMEM;
+ afr_fd_ctx_t *fd_ctx = NULL;
- priv = this->private;
+ priv = this->private;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
- fd_ctx = afr_fd_ctx_get (fd, this);
- if (!fd_ctx)
- goto out;
+ local->op = GF_FOP_OPENDIR;
- loc_copy (&local->loc, loc);
+ if (priv->quorum_count && !afr_has_quorum(local->child_up, this, NULL)) {
+ op_errno = afr_quorum_errno(priv);
+ goto out;
+ }
- local->fd = fd_ref (fd);
- local->fd_ctx = fd_ctx;
+ if (!afr_is_consistent_io_possible(local, priv, &op_errno))
+ goto out;
- call_count = local->call_count;
+ fd_ctx = afr_fd_ctx_get(fd, this);
+ if (!fd_ctx)
+ goto out;
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND_COOKIE (frame, afr_opendir_cbk,
- (void*) (long) i,
- priv->children[i],
- priv->children[i]->fops->opendir,
- loc, fd, NULL);
+ loc_copy(&local->loc, loc);
- if (!--call_count)
- break;
- }
+ local->fd = fd_ref(fd);
+ local->fd_ctx = fd_ctx;
+
+ call_count = local->call_count;
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->child_up[i]) {
+ STACK_WIND_COOKIE(frame, afr_opendir_cbk, (void *)(long)i,
+ priv->children[i],
+ priv->children[i]->fops->opendir, loc, fd, NULL);
+
+ if (!--call_count)
+ break;
}
+ }
- return 0;
+ return 0;
out:
- AFR_STACK_UNWIND (opendir, frame, -1, op_errno, fd, NULL);
- return 0;
+ AFR_STACK_UNWIND(opendir, frame, -1, op_errno, fd, NULL);
+ return 0;
}
static int
-afr_validate_read_subvol (inode_t *inode, xlator_t *this, int par_read_subvol)
+afr_validate_read_subvol(inode_t *inode, xlator_t *this, int par_read_subvol)
{
- int gen = 0;
- int entry_read_subvol = 0;
- unsigned char *data_readable = NULL;
- unsigned char *metadata_readable = NULL;
- afr_private_t *priv = NULL;
-
- priv = this->private;
- data_readable = alloca0 (priv->child_count);
- metadata_readable = alloca0 (priv->child_count);
-
- afr_inode_read_subvol_get (inode, this, data_readable,
- metadata_readable, &gen);
-
- if (gen != priv->event_generation ||
- !data_readable[par_read_subvol] ||
- !metadata_readable[par_read_subvol])
- return -1;
-
- /* Once the control reaches the following statement, it means that the
- * parent's read subvol is perfectly readable. So calling
- * either afr_data_subvol_get() or afr_metadata_subvol_get() would
- * yield the same result. Hence, choosing afr_data_subvol_get() below.
- */
-
- if (!priv->consistent_metadata)
- return 0;
-
- /* For an inode fetched through readdirp which is yet to be linked,
- * inode ctx would not be initialised (yet). So this function returns
- * -1 above due to gen being 0, which is why it is OK to pass NULL for
- * read_subvol_args here.
- */
- entry_read_subvol = afr_data_subvol_get (inode, this, 0, 0, NULL);
- if (entry_read_subvol != par_read_subvol)
- return -1;
-
+ int gen = 0;
+ int entry_read_subvol = 0;
+ unsigned char *data_readable = NULL;
+ unsigned char *metadata_readable = NULL;
+ afr_private_t *priv = NULL;
+
+ priv = this->private;
+ data_readable = alloca0(priv->child_count);
+ metadata_readable = alloca0(priv->child_count);
+
+ afr_inode_read_subvol_get(inode, this, data_readable, metadata_readable,
+ &gen);
+
+ if (gen != priv->event_generation || !data_readable[par_read_subvol] ||
+ !metadata_readable[par_read_subvol])
+ return -1;
+
+ /* Once the control reaches the following statement, it means that the
+ * parent's read subvol is perfectly readable. So calling
+ * either afr_data_subvol_get() or afr_metadata_subvol_get() would
+ * yield the same result. Hence, choosing afr_data_subvol_get() below.
+ */
+
+ if (!priv->consistent_metadata)
return 0;
+ /* For an inode fetched through readdirp which is yet to be linked,
+ * inode ctx would not be initialised (yet). So this function returns
+ * -1 above due to gen being 0, which is why it is OK to pass NULL for
+ * read_subvol_args here.
+ */
+ entry_read_subvol = afr_data_subvol_get(inode, this, NULL, NULL, NULL,
+ NULL);
+ if (entry_read_subvol != par_read_subvol)
+ return -1;
+
+ return 0;
}
static void
-afr_readdir_transform_entries (gf_dirent_t *subvol_entries, int subvol,
- gf_dirent_t *entries, fd_t *fd)
+afr_readdir_transform_entries(call_frame_t *frame, gf_dirent_t *subvol_entries,
+ int subvol, gf_dirent_t *entries, fd_t *fd)
{
- int ret = -1;
- gf_dirent_t *entry = NULL;
- gf_dirent_t *tmp = NULL;
- xlator_t *this = NULL;
-
- this = THIS;
-
- list_for_each_entry_safe (entry, tmp, &subvol_entries->list, list) {
- if (__is_root_gfid (fd->inode->gfid) &&
- !strcmp (entry->d_name, GF_REPLICATE_TRASH_DIR)) {
- continue;
- }
-
- list_del_init (&entry->list);
- list_add_tail (&entry->list, &entries->list);
-
- if (entry->inode) {
- ret = afr_validate_read_subvol (entry->inode, this,
- subvol);
- if (ret == -1) {
- inode_unref (entry->inode);
- entry->inode = NULL;
- continue;
- }
- }
+ int ret = -1;
+ gf_dirent_t *entry = NULL;
+ gf_dirent_t *tmp = NULL;
+ xlator_t *this = NULL;
+ afr_private_t *priv = NULL;
+ gf_boolean_t need_heal = _gf_false;
+ gf_boolean_t validate_subvol = _gf_false;
+
+ this = THIS;
+ priv = this->private;
+
+ need_heal = afr_get_need_heal(this);
+ validate_subvol = need_heal | priv->consistent_metadata;
+
+ list_for_each_entry_safe(entry, tmp, &subvol_entries->list, list)
+ {
+ if (afr_is_private_directory(priv, fd->inode->gfid, entry->d_name,
+ frame->root->pid)) {
+ continue;
}
-}
+ list_del_init(&entry->list);
+ list_add_tail(&entry->list, &entries->list);
+
+ if (!validate_subvol)
+ continue;
+
+ if (entry->inode) {
+ ret = afr_validate_read_subvol(entry->inode, this, subvol);
+ if (ret == -1) {
+ inode_unref(entry->inode);
+ entry->inode = NULL;
+ continue;
+ }
+ }
+ }
+}
int32_t
-afr_readdir_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, gf_dirent_t *subvol_entries,
- dict_t *xdata)
+afr_readdir_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, gf_dirent_t *subvol_entries,
+ dict_t *xdata)
{
- afr_local_t *local = NULL;
- gf_dirent_t entries;
+ afr_local_t *local = NULL;
+ gf_dirent_t entries;
- INIT_LIST_HEAD (&entries.list);
+ INIT_LIST_HEAD(&entries.list);
- local = frame->local;
+ local = frame->local;
- if (op_ret < 0 && !local->cont.readdir.offset) {
- /* failover only if this was first readdir, detected
- by offset == 0 */
- local->op_ret = op_ret;
- local->op_errno = op_errno;
+ if (op_ret < 0 && !local->cont.readdir.offset) {
+ /* failover only if this was first readdir, detected
+ by offset == 0 */
+ local->op_ret = op_ret;
+ local->op_errno = op_errno;
- afr_read_txn_continue (frame, this, (long) cookie);
- return 0;
- }
+ afr_read_txn_continue(frame, this, (long)cookie);
+ return 0;
+ }
- if (op_ret >= 0)
- afr_readdir_transform_entries (subvol_entries, (long) cookie,
- &entries, local->fd);
+ if (op_ret >= 0)
+ afr_readdir_transform_entries(frame, subvol_entries, (long)cookie,
+ &entries, local->fd);
- AFR_STACK_UNWIND (readdir, frame, op_ret, op_errno, &entries, xdata);
+ AFR_STACK_UNWIND(readdir, frame, op_ret, op_errno, &entries, xdata);
- gf_dirent_free (&entries);
+ gf_dirent_free(&entries);
- return 0;
+ return 0;
}
-
int
-afr_readdir_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_readdir_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- afr_fd_ctx_t *fd_ctx = NULL;
-
- priv = this->private;
- local = frame->local;
- fd_ctx = afr_fd_ctx_get (local->fd, this);
-
- if (subvol == -1) {
- AFR_STACK_UNWIND (readdir, frame, local->op_ret,
- local->op_errno, 0, 0);
- return 0;
- }
-
- fd_ctx->readdir_subvol = subvol;
-
- if (local->op == GF_FOP_READDIR)
- STACK_WIND_COOKIE (frame, afr_readdir_cbk,
- (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->readdir,
- local->fd, local->cont.readdir.size,
- local->cont.readdir.offset,
- local->xdata_req);
- else
- STACK_WIND_COOKIE (frame, afr_readdir_cbk,
- (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->readdirp,
- local->fd, local->cont.readdir.size,
- local->cont.readdir.offset,
- local->xdata_req);
- return 0;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ afr_fd_ctx_t *fd_ctx = NULL;
+
+ priv = this->private;
+ local = frame->local;
+ fd_ctx = afr_fd_ctx_get(local->fd, this);
+ if (!fd_ctx) {
+ local->op_errno = EINVAL;
+ local->op_ret = -1;
+ }
+
+ if (subvol == -1 || !fd_ctx) {
+ AFR_STACK_UNWIND(readdir, frame, local->op_ret, local->op_errno, 0, 0);
+ return 0;
+ }
+
+ fd_ctx->readdir_subvol = subvol;
+
+ if (local->op == GF_FOP_READDIR)
+ STACK_WIND_COOKIE(frame, afr_readdir_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->readdir, local->fd,
+ local->cont.readdir.size, local->cont.readdir.offset,
+ local->xdata_req);
+ else
+ STACK_WIND_COOKIE(frame, afr_readdir_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->readdirp, local->fd,
+ local->cont.readdir.size, local->cont.readdir.offset,
+ local->xdata_req);
+ return 0;
}
-
int
-afr_do_readdir (call_frame_t *frame, xlator_t *this, fd_t *fd, size_t size,
- off_t offset, int whichop, dict_t *dict)
+afr_do_readdir(call_frame_t *frame, xlator_t *this, fd_t *fd, size_t size,
+ off_t offset, int whichop, dict_t *dict)
{
- afr_local_t *local = NULL;
- int32_t op_errno = 0;
- int subvol = -1;
- afr_fd_ctx_t *fd_ctx = NULL;
-
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
-
- fd_ctx = afr_fd_ctx_get (fd, this);
- if (!fd_ctx) {
- op_errno = EINVAL;
- goto out;
- }
-
- local->op = whichop;
- local->fd = fd_ref (fd);
- local->cont.readdir.size = size;
- local->cont.readdir.offset = offset;
- local->xdata_req = (dict)? dict_ref (dict) : NULL;
-
- subvol = fd_ctx->readdir_subvol;
-
- if (offset == 0 || subvol == -1) {
- /* First readdir has option of failing over and selecting
- an appropriate read subvolume */
- afr_read_txn (frame, this, fd->inode, afr_readdir_wind,
- AFR_DATA_TRANSACTION);
- } else {
- /* But continued readdirs MUST stick to the same subvolume
- without an option to failover */
- afr_readdir_wind (frame, this, subvol);
- }
-
- return 0;
+ afr_local_t *local = NULL;
+ int32_t op_errno = 0;
+ int subvol = -1;
+ afr_fd_ctx_t *fd_ctx = NULL;
+
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
+
+ fd_ctx = afr_fd_ctx_get(fd, this);
+ if (!fd_ctx) {
+ op_errno = EINVAL;
+ goto out;
+ }
+
+ local->op = whichop;
+ local->fd = fd_ref(fd);
+ local->cont.readdir.size = size;
+ local->cont.readdir.offset = offset;
+ local->xdata_req = (dict) ? dict_ref(dict) : NULL;
+
+ subvol = fd_ctx->readdir_subvol;
+
+ if (offset == 0 || subvol == -1) {
+ /* First readdir has option of failing over and selecting
+ an appropriate read subvolume */
+ afr_read_txn(frame, this, fd->inode, afr_readdir_wind,
+ AFR_DATA_TRANSACTION);
+ } else {
+ /* But continued readdirs MUST stick to the same subvolume
+ without an option to failover */
+ afr_readdir_wind(frame, this, subvol);
+ }
+
+ return 0;
out:
- AFR_STACK_UNWIND (readdir, frame, -1, op_errno, NULL, NULL);
- return 0;
+ AFR_STACK_UNWIND(readdir, frame, -1, op_errno, NULL, NULL);
+ return 0;
}
-
int32_t
-afr_readdir (call_frame_t *frame, xlator_t *this, fd_t *fd, size_t size,
- off_t offset, dict_t *xdata)
+afr_readdir(call_frame_t *frame, xlator_t *this, fd_t *fd, size_t size,
+ off_t offset, dict_t *xdata)
{
- afr_do_readdir (frame, this, fd, size, offset, GF_FOP_READDIR, xdata);
+ afr_do_readdir(frame, this, fd, size, offset, GF_FOP_READDIR, xdata);
- return 0;
+ return 0;
}
-
int32_t
-afr_readdirp (call_frame_t *frame, xlator_t *this, fd_t *fd, size_t size,
- off_t offset, dict_t *dict)
+afr_readdirp(call_frame_t *frame, xlator_t *this, fd_t *fd, size_t size,
+ off_t offset, dict_t *dict)
{
- afr_do_readdir (frame, this, fd, size, offset, GF_FOP_READDIRP, dict);
+ afr_do_readdir(frame, this, fd, size, offset, GF_FOP_READDIRP, dict);
- return 0;
+ return 0;
}
-
int32_t
-afr_releasedir (xlator_t *this, fd_t *fd)
+afr_releasedir(xlator_t *this, fd_t *fd)
{
- afr_cleanup_fd_ctx (this, fd);
+ afr_cleanup_fd_ctx(this, fd);
- return 0;
+ return 0;
}
diff --git a/xlators/cluster/afr/src/afr-dir-read.h b/xlators/cluster/afr/src/afr-dir-read.h
index 09456d15949..773e925ec6c 100644
--- a/xlators/cluster/afr/src/afr-dir-read.h
+++ b/xlators/cluster/afr/src/afr-dir-read.h
@@ -11,26 +11,23 @@
#ifndef __DIR_READ_H__
#define __DIR_READ_H__
-
int32_t
-afr_opendir (call_frame_t *frame, xlator_t *this,
- loc_t *loc, fd_t *fd, dict_t *xdata);
+afr_opendir(call_frame_t *frame, xlator_t *this, loc_t *loc, fd_t *fd,
+ dict_t *xdata);
int32_t
-afr_releasedir (xlator_t *this, fd_t *fd);
+afr_releasedir(xlator_t *this, fd_t *fd);
int32_t
-afr_readdir (call_frame_t *frame, xlator_t *this,
- fd_t *fd, size_t size, off_t offset, dict_t *xdata);
-
+afr_readdir(call_frame_t *frame, xlator_t *this, fd_t *fd, size_t size,
+ off_t offset, dict_t *xdata);
int32_t
-afr_readdirp (call_frame_t *frame, xlator_t *this,
- fd_t *fd, size_t size, off_t offset, dict_t *dict);
+afr_readdirp(call_frame_t *frame, xlator_t *this, fd_t *fd, size_t size,
+ off_t offset, dict_t *dict);
int32_t
-afr_checksum (call_frame_t *frame, xlator_t *this,
- loc_t *loc, int32_t flags, dict_t *xdata);
-
+afr_checksum(call_frame_t *frame, xlator_t *this, loc_t *loc, int32_t flags,
+ dict_t *xdata);
#endif /* __DIR_READ_H__ */
diff --git a/xlators/cluster/afr/src/afr-dir-write.c b/xlators/cluster/afr/src/afr-dir-write.c
index 2891f362298..b7cceb79158 100644
--- a/xlators/cluster/afr/src/afr-dir-write.c
+++ b/xlators/cluster/afr/src/afr-dir-write.c
@@ -8,508 +8,493 @@
cases as published by the Free Software Foundation.
*/
-
#include <libgen.h>
#include <unistd.h>
-#include <fnmatch.h>
#include <sys/time.h>
#include <stdlib.h>
#include <signal.h>
-#ifndef _CONFIG_H
-#define _CONFIG_H
-#include "config.h"
-#endif
-
-#include "glusterfs.h"
+#include <glusterfs/glusterfs.h>
#include "afr.h"
-#include "dict.h"
-#include "xlator.h"
-#include "hashfn.h"
-#include "logging.h"
-#include "stack.h"
-#include "list.h"
-#include "call-stub.h"
-#include "defaults.h"
-#include "common-utils.h"
-#include "compat-errno.h"
-#include "compat.h"
-#include "byte-order.h"
+#include <glusterfs/dict.h>
+#include <glusterfs/logging.h>
+#include <glusterfs/list.h>
+#include <glusterfs/defaults.h>
+#include <glusterfs/common-utils.h>
+#include <glusterfs/compat-errno.h>
+#include <glusterfs/compat.h>
+#include <glusterfs/byte-order.h>
#include "afr.h"
#include "afr-transaction.h"
void
-afr_mark_entry_pending_changelog (call_frame_t *frame, xlator_t *this);
+afr_mark_entry_pending_changelog(call_frame_t *frame, xlator_t *this);
int
-afr_build_parent_loc (loc_t *parent, loc_t *child, int32_t *op_errno)
+afr_build_parent_loc(loc_t *parent, loc_t *child, int32_t *op_errno)
{
- int ret = -1;
- char *child_path = NULL;
+ int ret = -1;
+ char *child_path = NULL;
+
+ if (!child->parent) {
+ if (op_errno)
+ *op_errno = EINVAL;
+ goto out;
+ }
+
+ child_path = gf_strdup(child->path);
+ if (!child_path) {
+ if (op_errno)
+ *op_errno = ENOMEM;
+ goto out;
+ }
+
+ parent->path = gf_strdup(dirname(child_path));
+ if (!parent->path) {
+ if (op_errno)
+ *op_errno = ENOMEM;
+ goto out;
+ }
+
+ parent->inode = inode_ref(child->parent);
+ gf_uuid_copy(parent->gfid, child->pargfid);
+
+ ret = 0;
+out:
+ GF_FREE(child_path);
- if (!child->parent) {
- if (op_errno)
- *op_errno = EINVAL;
- goto out;
- }
+ return ret;
+}
- child_path = gf_strdup (child->path);
- if (!child_path) {
- if (op_errno)
- *op_errno = ENOMEM;
- goto out;
+static void
+__afr_dir_write_finalize(call_frame_t *frame, xlator_t *this)
+{
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int inode_read_subvol = -1;
+ int parent_read_subvol = -1;
+ int parent2_read_subvol = -1;
+ int i = 0;
+ afr_read_subvol_args_t args = {
+ 0,
+ };
+
+ local = frame->local;
+ priv = this->private;
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->replies[i].valid)
+ continue;
+ if (local->replies[i].op_ret == -1)
+ continue;
+ gf_uuid_copy(args.gfid, local->replies[i].poststat.ia_gfid);
+ args.ia_type = local->replies[i].poststat.ia_type;
+ break;
+ }
+
+ if (local->inode) {
+ if (local->op != GF_FOP_RENAME && local->op != GF_FOP_LINK)
+ afr_replies_interpret(frame, this, local->inode, NULL);
+
+ inode_read_subvol = afr_data_subvol_get(local->inode, this, NULL, NULL,
+ NULL, &args);
+ }
+
+ if (local->parent)
+ parent_read_subvol = afr_data_subvol_get(local->parent, this, NULL,
+ local->readable, NULL, NULL);
+
+ if (local->parent2)
+ parent2_read_subvol = afr_data_subvol_get(local->parent2, this, NULL,
+ local->readable2, NULL, NULL);
+
+ local->op_ret = -1;
+ local->op_errno = afr_final_errno(local, priv);
+ afr_pick_error_xdata(local, priv, local->parent, local->readable,
+ local->parent2, local->readable2);
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->replies[i].valid)
+ continue;
+ if (local->replies[i].op_ret < 0) {
+ if (local->inode)
+ afr_inode_need_refresh_set(local->inode, this);
+ if (local->parent)
+ afr_inode_need_refresh_set(local->parent, this);
+ if (local->parent2)
+ afr_inode_need_refresh_set(local->parent2, this);
+ continue;
}
- parent->path = gf_strdup (dirname (child_path));
- if (!parent->path) {
- if (op_errno)
- *op_errno = ENOMEM;
- goto out;
+ if (local->op_ret == -1) {
+ local->op_ret = local->replies[i].op_ret;
+ local->op_errno = local->replies[i].op_errno;
+
+ local->cont.dir_fop.buf = local->replies[i].poststat;
+ local->cont.dir_fop.preparent = local->replies[i].preparent;
+ local->cont.dir_fop.postparent = local->replies[i].postparent;
+ local->cont.dir_fop.prenewparent = local->replies[i].preparent2;
+ local->cont.dir_fop.postnewparent = local->replies[i].postparent2;
+ if (local->xdata_rsp) {
+ dict_unref(local->xdata_rsp);
+ local->xdata_rsp = NULL;
+ }
+
+ if (local->replies[i].xdata)
+ local->xdata_rsp = dict_ref(local->replies[i].xdata);
+ continue;
}
- parent->inode = inode_ref (child->parent);
- gf_uuid_copy (parent->gfid, child->pargfid);
-
- ret = 0;
-out:
- GF_FREE (child_path);
-
- return ret;
-}
+ if (i == inode_read_subvol) {
+ local->cont.dir_fop.buf = local->replies[i].poststat;
+ if (local->replies[i].xdata) {
+ if (local->xdata_rsp)
+ dict_unref(local->xdata_rsp);
+ local->xdata_rsp = dict_ref(local->replies[i].xdata);
+ }
+ }
+ if (i == parent_read_subvol) {
+ local->cont.dir_fop.preparent = local->replies[i].preparent;
+ local->cont.dir_fop.postparent = local->replies[i].postparent;
+ }
-static void
-__afr_dir_write_finalize (call_frame_t *frame, xlator_t *this)
-{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- int inode_read_subvol = -1;
- int parent_read_subvol = -1;
- int parent2_read_subvol = -1;
- int i = 0;
-
- local = frame->local;
- priv = this->private;
-
- if (local->inode) {
- afr_replies_interpret (frame, this, local->inode);
- inode_read_subvol = afr_data_subvol_get (local->inode, this,
- NULL, NULL, NULL);
- }
- if (local->parent)
- parent_read_subvol = afr_data_subvol_get (local->parent, this,
- NULL, NULL, NULL);
- if (local->parent2)
- parent2_read_subvol = afr_data_subvol_get (local->parent2, this,
- NULL, NULL, NULL);
-
- local->op_ret = -1;
- local->op_errno = afr_final_errno (local, priv);
-
- for (i = 0; i < priv->child_count; i++) {
- if (!local->replies[i].valid)
- continue;
- if (local->replies[i].op_ret < 0) {
- if (local->inode)
- afr_inode_read_subvol_reset (local->inode,
- this);
- if (local->parent)
- afr_inode_read_subvol_reset (local->parent,
- this);
- if (local->parent2)
- afr_inode_read_subvol_reset (local->parent2,
- this);
- continue;
- }
-
- if (local->op_ret == -1) {
- local->op_ret = local->replies[i].op_ret;
- local->op_errno = local->replies[i].op_errno;
-
- local->cont.dir_fop.buf =
- local->replies[i].poststat;
- local->cont.dir_fop.preparent =
- local->replies[i].preparent;
- local->cont.dir_fop.postparent =
- local->replies[i].postparent;
- local->cont.dir_fop.prenewparent =
- local->replies[i].preparent2;
- local->cont.dir_fop.postnewparent =
- local->replies[i].postparent2;
- if (local->replies[i].xdata)
- local->xdata_rsp =
- dict_ref (local->replies[i].xdata);
- continue;
- }
-
- if (i == inode_read_subvol) {
- local->cont.dir_fop.buf =
- local->replies[i].poststat;
- if (local->replies[i].xdata) {
- if (local->xdata_rsp)
- dict_unref (local->xdata_rsp);
- local->xdata_rsp =
- dict_ref (local->replies[i].xdata);
- }
- }
-
- if (i == parent_read_subvol) {
- local->cont.dir_fop.preparent =
- local->replies[i].preparent;
- local->cont.dir_fop.postparent =
- local->replies[i].postparent;
- }
-
- if (i == parent2_read_subvol) {
- local->cont.dir_fop.prenewparent =
- local->replies[i].preparent2;
- local->cont.dir_fop.postnewparent =
- local->replies[i].postparent2;
- }
- }
-
- afr_txn_arbitrate_fop_cbk (frame, this);
+ if (i == parent2_read_subvol) {
+ local->cont.dir_fop.prenewparent = local->replies[i].preparent2;
+ local->cont.dir_fop.postnewparent = local->replies[i].postparent2;
+ }
+ }
}
-
static void
-__afr_dir_write_fill (call_frame_t *frame, xlator_t *this, int child_index,
- int op_ret, int op_errno, struct iatt *poststat,
- struct iatt *preparent, struct iatt *postparent,
- struct iatt *preparent2, struct iatt *postparent2,
- dict_t *xdata)
+__afr_dir_write_fill(call_frame_t *frame, xlator_t *this, int child_index,
+ int op_ret, int op_errno, struct iatt *poststat,
+ struct iatt *preparent, struct iatt *postparent,
+ struct iatt *preparent2, struct iatt *postparent2,
+ dict_t *xdata)
{
- afr_local_t *local = NULL;
- afr_fd_ctx_t *fd_ctx = NULL;
-
- local = frame->local;
- fd_ctx = local->fd_ctx;
-
- local->replies[child_index].valid = 1;
- local->replies[child_index].op_ret = op_ret;
- local->replies[child_index].op_errno = op_errno;
-
- if (op_ret >= 0) {
- if (poststat)
- local->replies[child_index].poststat = *poststat;
- if (preparent)
- local->replies[child_index].preparent = *preparent;
- if (postparent)
- local->replies[child_index].postparent = *postparent;
- if (preparent2)
- local->replies[child_index].preparent2 = *preparent2;
- if (postparent2)
- local->replies[child_index].postparent2 = *postparent2;
- if (xdata)
- local->replies[child_index].xdata = dict_ref (xdata);
-
- if (fd_ctx)
- fd_ctx->opened_on[child_index] = AFR_FD_OPENED;
- } else {
- if (op_errno != ENOTEMPTY)
- afr_transaction_fop_failed (frame, this, child_index);
- if (fd_ctx)
- fd_ctx->opened_on[child_index] = AFR_FD_NOT_OPENED;
- }
-
- return;
+ afr_local_t *local = NULL;
+ afr_fd_ctx_t *fd_ctx = NULL;
+
+ local = frame->local;
+ fd_ctx = local->fd_ctx;
+
+ local->replies[child_index].valid = 1;
+ local->replies[child_index].op_ret = op_ret;
+ local->replies[child_index].op_errno = op_errno;
+ if (xdata)
+ local->replies[child_index].xdata = dict_ref(xdata);
+
+ if (op_ret >= 0) {
+ if (poststat)
+ local->replies[child_index].poststat = *poststat;
+ if (preparent)
+ local->replies[child_index].preparent = *preparent;
+ if (postparent)
+ local->replies[child_index].postparent = *postparent;
+ if (preparent2)
+ local->replies[child_index].preparent2 = *preparent2;
+ if (postparent2)
+ local->replies[child_index].postparent2 = *postparent2;
+ if (fd_ctx)
+ fd_ctx->opened_on[child_index] = AFR_FD_OPENED;
+ } else {
+ if (op_errno != ENOTEMPTY)
+ afr_transaction_fop_failed(frame, this, child_index);
+ if (fd_ctx)
+ fd_ctx->opened_on[child_index] = AFR_FD_NOT_OPENED;
+ }
+
+ return;
}
-
static int
-__afr_dir_write_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int op_ret, int op_errno, struct iatt *buf,
- struct iatt *preparent, struct iatt *postparent,
- struct iatt *preparent2, struct iatt *postparent2,
- dict_t *xdata)
+__afr_dir_write_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int op_ret, int op_errno, struct iatt *buf,
+ struct iatt *preparent, struct iatt *postparent,
+ struct iatt *preparent2, struct iatt *postparent2,
+ dict_t *xdata)
{
- afr_local_t *local = NULL;
- int child_index = (long) cookie;
- int call_count = -1;
-
- local = frame->local;
-
- LOCK (&frame->lock);
- {
- __afr_dir_write_fill (frame, this, child_index, op_ret,
- op_errno, buf, preparent, postparent,
- preparent2, postparent2, xdata);
- }
- UNLOCK (&frame->lock);
- call_count = afr_frame_return (frame);
-
- if (call_count == 0) {
- __afr_dir_write_finalize (frame, this);
-
- if (afr_txn_nothing_failed (frame, this))
- local->transaction.unwind (frame, this);
+ afr_local_t *local = NULL;
+ int child_index = (long)cookie;
+ int call_count = -1;
+ afr_private_t *priv = NULL;
+
+ priv = this->private;
+ local = frame->local;
+
+ LOCK(&frame->lock);
+ {
+ __afr_dir_write_fill(frame, this, child_index, op_ret, op_errno, buf,
+ preparent, postparent, preparent2, postparent2,
+ xdata);
+ call_count = --local->call_count;
+ }
+ UNLOCK(&frame->lock);
+
+ if (call_count == 0) {
+ __afr_dir_write_finalize(frame, this);
+
+ if (afr_txn_nothing_failed(frame, this)) {
+ /*if it did pre-op, it will do post-op changing ctime*/
+ if (priv->consistent_metadata && afr_needs_changelog_update(local))
+ afr_zero_fill_stat(local);
+ local->transaction.unwind(frame, this);
+ }
- afr_mark_entry_pending_changelog (frame, this);
+ afr_mark_entry_pending_changelog(frame, this);
- local->transaction.resume (frame, this);
- }
+ afr_transaction_resume(frame, this);
+ }
- return 0;
+ return 0;
}
-
int
-afr_mark_new_entry_changelog_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int op_ret, int op_errno,
- dict_t *xattr, dict_t *xdata)
+afr_mark_new_entry_changelog_cbk(call_frame_t *frame, void *cookie,
+ xlator_t *this, int op_ret, int op_errno,
+ dict_t *xattr, dict_t *xdata)
{
- int call_count = 0;
+ int call_count = 0;
- call_count = afr_frame_return (frame);
+ call_count = afr_frame_return(frame);
- if (call_count == 0)
- AFR_STACK_DESTROY (frame);
+ if (call_count == 0)
+ AFR_STACK_DESTROY(frame);
- return 0;
+ return 0;
}
-
void
-afr_mark_new_entry_changelog (call_frame_t *frame, xlator_t *this)
+afr_mark_new_entry_changelog(call_frame_t *frame, xlator_t *this)
{
- call_frame_t *new_frame = NULL;
- afr_local_t *local = NULL;
- afr_local_t *new_local = NULL;
- afr_private_t *priv = NULL;
- dict_t *xattr = NULL;
- int32_t **changelog = NULL;
- int i = 0;
- int op_errno = ENOMEM;
- unsigned char *pending = NULL;
- int call_count = 0;
-
- local = frame->local;
- priv = this->private;
-
- new_frame = copy_frame (frame);
- if (!new_frame)
- goto out;
-
- new_local = AFR_FRAME_INIT (new_frame, op_errno);
- if (!new_local)
- goto out;
-
- xattr = dict_new ();
- if (!xattr)
- goto out;
-
- pending = alloca0 (priv->child_count);
-
- for (i = 0; i < priv->child_count; i++) {
- if (local->transaction.pre_op[i] &&
- !local->transaction.failed_subvols[i]) {
- call_count ++;
- continue;
- }
- pending[i] = 1;
- }
-
- changelog = afr_mark_pending_changelog (priv, pending, xattr,
- local->cont.dir_fop.buf.ia_type);
- if (!changelog)
- goto out;
-
- new_local->pending = changelog;
- gf_uuid_copy (new_local->loc.gfid, local->cont.dir_fop.buf.ia_gfid);
- new_local->loc.inode = inode_ref (local->inode);
-
- new_local->call_count = call_count;
-
- for (i = 0; i < priv->child_count; i++) {
- if (pending[i])
- continue;
-
- STACK_WIND_COOKIE (new_frame, afr_mark_new_entry_changelog_cbk,
- (void *) (long) i, priv->children[i],
- priv->children[i]->fops->xattrop,
- &new_local->loc, GF_XATTROP_ADD_ARRAY,
- xattr, NULL);
- if (!--call_count)
- break;
+ call_frame_t *new_frame = NULL;
+ afr_local_t *local = NULL;
+ afr_local_t *new_local = NULL;
+ afr_private_t *priv = NULL;
+ dict_t *xattr = NULL;
+ int32_t **changelog = NULL;
+ int i = 0;
+ int op_errno = ENOMEM;
+ unsigned char *pending = NULL;
+ int call_count = 0;
+
+ local = frame->local;
+ priv = this->private;
+
+ new_frame = copy_frame(frame);
+ if (!new_frame)
+ goto out;
+
+ new_local = AFR_FRAME_INIT(new_frame, op_errno);
+ if (!new_local)
+ goto out;
+
+ xattr = dict_new();
+ if (!xattr)
+ goto out;
+
+ pending = alloca0(priv->child_count);
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->transaction.pre_op[i] &&
+ !local->transaction.failed_subvols[i]) {
+ call_count++;
+ continue;
}
+ pending[i] = 1;
+ }
+
+ changelog = afr_mark_pending_changelog(priv, pending, xattr,
+ local->cont.dir_fop.buf.ia_type);
+ if (!changelog)
+ goto out;
+
+ new_local->pending = changelog;
+ gf_uuid_copy(new_local->loc.gfid, local->cont.dir_fop.buf.ia_gfid);
+ new_local->loc.inode = inode_ref(local->inode);
+
+ new_local->call_count = call_count;
- new_frame = NULL;
+ for (i = 0; i < priv->child_count; i++) {
+ if (pending[i])
+ continue;
+
+ STACK_WIND_COOKIE(new_frame, afr_mark_new_entry_changelog_cbk,
+ (void *)(long)i, priv->children[i],
+ priv->children[i]->fops->xattrop, &new_local->loc,
+ GF_XATTROP_ADD_ARRAY, xattr, NULL);
+ if (!--call_count)
+ break;
+ }
+
+ new_frame = NULL;
out:
- if (new_frame)
- AFR_STACK_DESTROY (new_frame);
- if (xattr)
- dict_unref (xattr);
- return;
+ if (new_frame)
+ AFR_STACK_DESTROY(new_frame);
+ if (xattr)
+ dict_unref(xattr);
+ return;
}
-
void
-afr_mark_entry_pending_changelog (call_frame_t *frame, xlator_t *this)
+afr_mark_entry_pending_changelog(call_frame_t *frame, xlator_t *this)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- int pre_op_count = 0;
- int failed_count = 0;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int pre_op_count = 0;
+ int failed_count = 0;
+ unsigned char *success_replies = NULL;
- local = frame->local;
- priv = this->private;
+ local = frame->local;
+ priv = this->private;
- if (local->op_ret < 0)
- return;
+ if (local->op_ret < 0)
+ return;
- if (local->op != GF_FOP_CREATE && local->op != GF_FOP_MKNOD)
- return;
+ if (local->op != GF_FOP_CREATE && local->op != GF_FOP_MKNOD &&
+ local->op != GF_FOP_MKDIR)
+ return;
- pre_op_count = AFR_COUNT (local->transaction.pre_op, priv->child_count);
- failed_count = AFR_COUNT (local->transaction.failed_subvols,
- priv->child_count);
+ pre_op_count = AFR_COUNT(local->transaction.pre_op, priv->child_count);
+ failed_count = AFR_COUNT(local->transaction.failed_subvols,
+ priv->child_count);
- if (pre_op_count == priv->child_count && !failed_count)
- return;
+ /* FOP succeeded on all bricks. */
+ if (pre_op_count == priv->child_count && !failed_count)
+ return;
- afr_mark_new_entry_changelog (frame, this);
+ /* FOP did not suceed on quorum no. of bricks. */
+ success_replies = alloca0(priv->child_count);
+ afr_fill_success_replies(local, priv, success_replies);
+ if (!afr_has_quorum(success_replies, this, NULL))
+ return;
+ if (priv->thin_arbiter_count) {
+ /*Mark new entry using ta file*/
+ local->is_new_entry = _gf_true;
return;
-}
+ }
+
+ afr_mark_new_entry_changelog(frame, this);
+ return;
+}
/* {{{ create */
int
-afr_create_unwind (call_frame_t *frame, xlator_t *this)
+afr_create_unwind(call_frame_t *frame, xlator_t *this)
{
- call_frame_t *main_frame = NULL;
- afr_local_t *local = NULL;
-
- local = frame->local;
+ call_frame_t *main_frame = NULL;
+ afr_local_t *local = NULL;
- main_frame = afr_transaction_detach_fop_frame (frame);
+ local = frame->local;
- if (!main_frame)
- return 0;
+ main_frame = afr_transaction_detach_fop_frame(frame);
- AFR_STACK_UNWIND (create, main_frame, local->op_ret, local->op_errno,
- local->cont.create.fd, local->inode,
- &local->cont.dir_fop.buf,
- &local->cont.dir_fop.preparent,
- &local->cont.dir_fop.postparent, local->xdata_rsp);
+ if (!main_frame)
return 0;
-}
+ AFR_STACK_UNWIND(create, main_frame, local->op_ret, local->op_errno,
+ local->cont.create.fd, local->inode,
+ &local->cont.dir_fop.buf, &local->cont.dir_fop.preparent,
+ &local->cont.dir_fop.postparent, local->xdata_rsp);
+ return 0;
+}
int
-afr_create_wind_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno,
- fd_t *fd, inode_t *inode, struct iatt *buf,
- struct iatt *preparent, struct iatt *postparent,
- dict_t *xdata)
+afr_create_wind_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, fd_t *fd, inode_t *inode,
+ struct iatt *buf, struct iatt *preparent,
+ struct iatt *postparent, dict_t *xdata)
{
- return __afr_dir_write_cbk (frame, cookie, this, op_ret, op_errno, buf,
- preparent, postparent, NULL, NULL, xdata);
+ return __afr_dir_write_cbk(frame, cookie, this, op_ret, op_errno, buf,
+ preparent, postparent, NULL, NULL, xdata);
}
-
int
-afr_create_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_create_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
-
- local = frame->local;
- priv = this->private;
-
- STACK_WIND_COOKIE (frame, afr_create_wind_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->create,
- &local->loc, local->cont.create.flags,
- local->cont.create.mode, local->umask,
- local->cont.create.fd, local->xdata_req);
- return 0;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+
+ local = frame->local;
+ priv = this->private;
+
+ STACK_WIND_COOKIE(frame, afr_create_wind_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->create, &local->loc,
+ local->cont.create.flags, local->cont.create.mode,
+ local->umask, local->cont.create.fd, local->xdata_req);
+ return 0;
}
-
int
-afr_create (call_frame_t *frame, xlator_t *this, loc_t *loc, int32_t flags,
- mode_t mode, mode_t umask, fd_t *fd, dict_t *xdata)
+afr_create(call_frame_t *frame, xlator_t *this, loc_t *loc, int32_t flags,
+ mode_t mode, mode_t umask, fd_t *fd, dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- afr_internal_lock_t *int_lock = NULL;
- call_frame_t *transaction_frame = NULL;
- int ret = -1;
- int op_errno = ENOMEM;
-
- priv = this->private;
-
- transaction_frame = copy_frame (frame);
- if (!transaction_frame)
- goto out;
-
- local = AFR_FRAME_INIT (transaction_frame, op_errno);
- if (!local)
- goto out;
-
- loc_copy (&local->loc, loc);
-
- local->fd_ctx = afr_fd_ctx_get (fd, this);
- if (!local->fd_ctx)
- goto out;
-
- local->inode = inode_ref (loc->inode);
- local->parent = inode_ref (loc->parent);
-
- local->op = GF_FOP_CREATE;
- local->cont.create.flags = flags;
- local->cont.create.mode = mode;
- local->cont.create.fd = fd_ref (fd);
- local->umask = umask;
-
- if (xdata)
- local->xdata_req = dict_copy_with_ref (xdata, NULL);
- else
- local->xdata_req = dict_new ();
-
- if (!local->xdata_req)
- goto out;
-
- local->transaction.wind = afr_create_wind;
- local->transaction.fop = __afr_txn_write_fop;
- local->transaction.done = __afr_txn_write_done;
- local->transaction.unwind = afr_create_unwind;
-
- ret = afr_build_parent_loc (&local->transaction.parent_loc, loc,
- &op_errno);
- if (ret)
- goto out;
-
- local->transaction.main_frame = frame;
- local->transaction.basename = AFR_BASENAME (loc->path);
- int_lock = &local->internal_lock;
-
- int_lock->lockee_count = 0;
- ret = afr_init_entry_lockee (&int_lock->lockee[0], local,
- &local->transaction.parent_loc,
- local->transaction.basename,
- priv->child_count);
- if (ret)
- goto out;
-
- int_lock->lockee_count++;
- ret = afr_transaction (transaction_frame, this, AFR_ENTRY_TRANSACTION);
- if (ret < 0) {
- op_errno = -ret;
- goto out;
- }
-
- return 0;
+ afr_local_t *local = NULL;
+ call_frame_t *transaction_frame = NULL;
+ int ret = -1;
+ int op_errno = ENOMEM;
+
+ transaction_frame = copy_frame(frame);
+ if (!transaction_frame)
+ goto out;
+
+ local = AFR_FRAME_INIT(transaction_frame, op_errno);
+ if (!local)
+ goto out;
+
+ loc_copy(&local->loc, loc);
+
+ local->fd_ctx = afr_fd_ctx_get(fd, this);
+ if (!local->fd_ctx)
+ goto out;
+
+ local->inode = inode_ref(loc->inode);
+ local->parent = inode_ref(loc->parent);
+
+ local->op = GF_FOP_CREATE;
+ local->cont.create.flags = flags;
+ local->fd_ctx->flags = flags;
+ local->cont.create.mode = mode;
+ local->cont.create.fd = fd_ref(fd);
+ local->umask = umask;
+
+ if (xdata)
+ local->xdata_req = dict_copy_with_ref(xdata, NULL);
+ else
+ local->xdata_req = dict_new();
+
+ if (!local->xdata_req)
+ goto out;
+
+ local->transaction.wind = afr_create_wind;
+ local->transaction.unwind = afr_create_unwind;
+
+ ret = afr_build_parent_loc(&local->transaction.parent_loc, loc, &op_errno);
+ if (ret)
+ goto out;
+
+ local->transaction.main_frame = frame;
+ local->transaction.basename = AFR_BASENAME(loc->path);
+ ret = afr_transaction(transaction_frame, this, AFR_ENTRY_TRANSACTION);
+ if (ret < 0) {
+ op_errno = -ret;
+ goto out;
+ }
+
+ return 0;
out:
- if (transaction_frame)
- AFR_STACK_DESTROY (transaction_frame);
+ if (transaction_frame)
+ AFR_STACK_DESTROY(transaction_frame);
- AFR_STACK_UNWIND (create, frame, -1, op_errno, NULL, NULL, NULL, NULL,
- NULL, NULL);
- return 0;
+ AFR_STACK_UNWIND(create, frame, -1, op_errno, NULL, NULL, NULL, NULL, NULL,
+ NULL);
+ return 0;
}
/* }}} */
@@ -517,518 +502,436 @@ out:
/* {{{ mknod */
int
-afr_mknod_unwind (call_frame_t *frame, xlator_t *this)
+afr_mknod_unwind(call_frame_t *frame, xlator_t *this)
{
- call_frame_t *main_frame = NULL;
- afr_local_t *local = NULL;
-
- local = frame->local;
+ call_frame_t *main_frame = NULL;
+ afr_local_t *local = NULL;
- main_frame = afr_transaction_detach_fop_frame (frame);
- if (!main_frame)
- return 0;
+ local = frame->local;
- AFR_STACK_UNWIND (mknod, main_frame, local->op_ret, local->op_errno,
- local->inode, &local->cont.dir_fop.buf,
- &local->cont.dir_fop.preparent,
- &local->cont.dir_fop.postparent, local->xdata_rsp);
+ main_frame = afr_transaction_detach_fop_frame(frame);
+ if (!main_frame)
return 0;
-}
+ AFR_STACK_UNWIND(mknod, main_frame, local->op_ret, local->op_errno,
+ local->inode, &local->cont.dir_fop.buf,
+ &local->cont.dir_fop.preparent,
+ &local->cont.dir_fop.postparent, local->xdata_rsp);
+ return 0;
+}
int
-afr_mknod_wind_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, inode_t *inode,
- struct iatt *buf, struct iatt *preparent,
- struct iatt *postparent, dict_t *xdata)
+afr_mknod_wind_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, inode_t *inode,
+ struct iatt *buf, struct iatt *preparent,
+ struct iatt *postparent, dict_t *xdata)
{
- return __afr_dir_write_cbk (frame, cookie, this, op_ret, op_errno, buf,
- preparent, postparent, NULL, NULL, xdata);
+ return __afr_dir_write_cbk(frame, cookie, this, op_ret, op_errno, buf,
+ preparent, postparent, NULL, NULL, xdata);
}
-
int
-afr_mknod_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_mknod_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
-
- local = frame->local;
- priv = this->private;
-
- STACK_WIND_COOKIE (frame, afr_mknod_wind_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->mknod,
- &local->loc, local->cont.mknod.mode,
- local->cont.mknod.dev, local->umask,
- local->xdata_req);
- return 0;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+
+ local = frame->local;
+ priv = this->private;
+
+ STACK_WIND_COOKIE(frame, afr_mknod_wind_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->mknod, &local->loc,
+ local->cont.mknod.mode, local->cont.mknod.dev,
+ local->umask, local->xdata_req);
+ return 0;
}
int
-afr_mknod (call_frame_t *frame, xlator_t *this, loc_t *loc, mode_t mode,
- dev_t dev, mode_t umask, dict_t *xdata)
+afr_mknod(call_frame_t *frame, xlator_t *this, loc_t *loc, mode_t mode,
+ dev_t dev, mode_t umask, dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- afr_internal_lock_t *int_lock = NULL;
- call_frame_t *transaction_frame = NULL;
- int ret = -1;
- int op_errno = ENOMEM;
-
- priv = this->private;
-
- transaction_frame = copy_frame (frame);
- if (!transaction_frame)
- goto out;
-
- local = AFR_FRAME_INIT (transaction_frame, op_errno);
- if (!local)
- goto out;
-
- loc_copy (&local->loc, loc);
- local->inode = inode_ref (loc->inode);
- local->parent = inode_ref (loc->parent);
-
- local->op = GF_FOP_MKNOD;
- local->cont.mknod.mode = mode;
- local->cont.mknod.dev = dev;
- local->umask = umask;
-
- if (xdata)
- local->xdata_req = dict_copy_with_ref (xdata, NULL);
- else
- local->xdata_req = dict_new ();
-
- if (!local->xdata_req)
- goto out;
-
- local->transaction.wind = afr_mknod_wind;
- local->transaction.fop = __afr_txn_write_fop;
- local->transaction.done = __afr_txn_write_done;
- local->transaction.unwind = afr_mknod_unwind;
-
- ret = afr_build_parent_loc (&local->transaction.parent_loc, loc,
- &op_errno);
- if (ret)
- goto out;
-
- local->transaction.main_frame = frame;
- local->transaction.basename = AFR_BASENAME (loc->path);
- int_lock = &local->internal_lock;
-
- int_lock->lockee_count = 0;
- ret = afr_init_entry_lockee (&int_lock->lockee[0], local,
- &local->transaction.parent_loc,
- local->transaction.basename,
- priv->child_count);
- if (ret)
- goto out;
-
- int_lock->lockee_count++;
- ret = afr_transaction (transaction_frame, this, AFR_ENTRY_TRANSACTION);
- if (ret < 0) {
- op_errno = -ret;
- goto out;
- }
-
- return 0;
+ afr_local_t *local = NULL;
+ call_frame_t *transaction_frame = NULL;
+ int ret = -1;
+ int op_errno = ENOMEM;
+
+ transaction_frame = copy_frame(frame);
+ if (!transaction_frame)
+ goto out;
+
+ local = AFR_FRAME_INIT(transaction_frame, op_errno);
+ if (!local)
+ goto out;
+
+ loc_copy(&local->loc, loc);
+ local->inode = inode_ref(loc->inode);
+ local->parent = inode_ref(loc->parent);
+
+ local->op = GF_FOP_MKNOD;
+ local->cont.mknod.mode = mode;
+ local->cont.mknod.dev = dev;
+ local->umask = umask;
+
+ if (xdata)
+ local->xdata_req = dict_copy_with_ref(xdata, NULL);
+ else
+ local->xdata_req = dict_new();
+
+ if (!local->xdata_req)
+ goto out;
+
+ local->transaction.wind = afr_mknod_wind;
+ local->transaction.unwind = afr_mknod_unwind;
+
+ ret = afr_build_parent_loc(&local->transaction.parent_loc, loc, &op_errno);
+ if (ret)
+ goto out;
+
+ local->transaction.main_frame = frame;
+ local->transaction.basename = AFR_BASENAME(loc->path);
+ ret = afr_transaction(transaction_frame, this, AFR_ENTRY_TRANSACTION);
+ if (ret < 0) {
+ op_errno = -ret;
+ goto out;
+ }
+
+ return 0;
out:
- if (transaction_frame)
- AFR_STACK_DESTROY (transaction_frame);
+ if (transaction_frame)
+ AFR_STACK_DESTROY(transaction_frame);
- AFR_STACK_UNWIND (mknod, frame, -1, op_errno, NULL, NULL, NULL, NULL,
- NULL);
- return 0;
+ AFR_STACK_UNWIND(mknod, frame, -1, op_errno, NULL, NULL, NULL, NULL, NULL);
+ return 0;
}
/* }}} */
/* {{{ mkdir */
-
int
-afr_mkdir_unwind (call_frame_t *frame, xlator_t *this)
+afr_mkdir_unwind(call_frame_t *frame, xlator_t *this)
{
- call_frame_t *main_frame = NULL;
- afr_local_t *local = NULL;
+ call_frame_t *main_frame = NULL;
+ afr_local_t *local = NULL;
- local = frame->local;
+ local = frame->local;
- main_frame = afr_transaction_detach_fop_frame (frame);
- if (!main_frame)
- return 0;
-
- AFR_STACK_UNWIND (mkdir, main_frame, local->op_ret, local->op_errno,
- local->inode, &local->cont.dir_fop.buf,
- &local->cont.dir_fop.preparent,
- &local->cont.dir_fop.postparent, local->xdata_rsp);
+ main_frame = afr_transaction_detach_fop_frame(frame);
+ if (!main_frame)
return 0;
-}
+ AFR_STACK_UNWIND(mkdir, main_frame, local->op_ret, local->op_errno,
+ local->inode, &local->cont.dir_fop.buf,
+ &local->cont.dir_fop.preparent,
+ &local->cont.dir_fop.postparent, local->xdata_rsp);
+ return 0;
+}
int
-afr_mkdir_wind_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, inode_t *inode,
- struct iatt *buf, struct iatt *preparent,
- struct iatt *postparent, dict_t *xdata)
+afr_mkdir_wind_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, inode_t *inode,
+ struct iatt *buf, struct iatt *preparent,
+ struct iatt *postparent, dict_t *xdata)
{
- return __afr_dir_write_cbk (frame, cookie, this, op_ret, op_errno, buf,
- preparent, postparent, NULL, NULL, xdata);
+ return __afr_dir_write_cbk(frame, cookie, this, op_ret, op_errno, buf,
+ preparent, postparent, NULL, NULL, xdata);
}
-
int
-afr_mkdir_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_mkdir_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
- local = frame->local;
- priv = this->private;
+ local = frame->local;
+ priv = this->private;
- STACK_WIND_COOKIE (frame, afr_mkdir_wind_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->mkdir, &local->loc,
- local->cont.mkdir.mode, local->umask,
- local->xdata_req);
- return 0;
+ STACK_WIND_COOKIE(frame, afr_mkdir_wind_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->mkdir, &local->loc,
+ local->cont.mkdir.mode, local->umask, local->xdata_req);
+ return 0;
}
-
int
-afr_mkdir (call_frame_t *frame, xlator_t *this, loc_t *loc, mode_t mode,
- mode_t umask, dict_t *xdata)
+afr_mkdir(call_frame_t *frame, xlator_t *this, loc_t *loc, mode_t mode,
+ mode_t umask, dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- afr_internal_lock_t *int_lock = NULL;
- call_frame_t *transaction_frame = NULL;
- int ret = -1;
- int op_errno = ENOMEM;
-
- priv = this->private;
-
- transaction_frame = copy_frame (frame);
- if (!transaction_frame)
- goto out;
-
- local = AFR_FRAME_INIT (transaction_frame, op_errno);
- if (!local)
- goto out;
-
- loc_copy (&local->loc, loc);
- local->inode = inode_ref (loc->inode);
- local->parent = inode_ref (loc->parent);
-
- local->cont.mkdir.mode = mode;
- local->umask = umask;
-
- if (xdata)
- local->xdata_req = dict_copy_with_ref (xdata, NULL);
- else
- local->xdata_req = dict_new ();
-
- if (!local->xdata_req)
- goto out;
-
- local->op = GF_FOP_MKDIR;
- local->transaction.wind = afr_mkdir_wind;
- local->transaction.fop = __afr_txn_write_fop;
- local->transaction.done = __afr_txn_write_done;
- local->transaction.unwind = afr_mkdir_unwind;
-
- ret = afr_build_parent_loc (&local->transaction.parent_loc, loc,
- &op_errno);
- if (ret)
- goto out;
-
- local->transaction.main_frame = frame;
- local->transaction.basename = AFR_BASENAME (loc->path);
- int_lock = &local->internal_lock;
-
- int_lock->lockee_count = 0;
- ret = afr_init_entry_lockee (&int_lock->lockee[0], local,
- &local->transaction.parent_loc,
- local->transaction.basename,
- priv->child_count);
- if (ret)
- goto out;
-
- int_lock->lockee_count++;
- ret = afr_transaction (transaction_frame, this, AFR_ENTRY_TRANSACTION);
- if (ret < 0) {
- op_errno = -ret;
- goto out;
- }
-
- return 0;
+ afr_local_t *local = NULL;
+ call_frame_t *transaction_frame = NULL;
+ int ret = -1;
+ int op_errno = ENOMEM;
+
+ transaction_frame = copy_frame(frame);
+ if (!transaction_frame)
+ goto out;
+
+ local = AFR_FRAME_INIT(transaction_frame, op_errno);
+ if (!local)
+ goto out;
+
+ loc_copy(&local->loc, loc);
+ local->inode = inode_ref(loc->inode);
+ local->parent = inode_ref(loc->parent);
+
+ local->cont.mkdir.mode = mode;
+ local->umask = umask;
+
+ if (!xdata || !dict_get_sizen(xdata, "gfid-req")) {
+ op_errno = EPERM;
+ gf_msg_callingfn(this->name, GF_LOG_WARNING, op_errno,
+ AFR_MSG_GFID_NULL,
+ "mkdir: %s is received "
+ "without gfid-req %p",
+ loc->path, xdata);
+ goto out;
+ }
+
+ local->xdata_req = dict_copy_with_ref(xdata, NULL);
+ if (!local->xdata_req) {
+ op_errno = ENOMEM;
+ goto out;
+ }
+
+ local->op = GF_FOP_MKDIR;
+ local->transaction.wind = afr_mkdir_wind;
+ local->transaction.unwind = afr_mkdir_unwind;
+
+ ret = afr_build_parent_loc(&local->transaction.parent_loc, loc, &op_errno);
+ if (ret)
+ goto out;
+
+ local->transaction.main_frame = frame;
+ local->transaction.basename = AFR_BASENAME(loc->path);
+ ret = afr_transaction(transaction_frame, this, AFR_ENTRY_TRANSACTION);
+ if (ret < 0) {
+ op_errno = -ret;
+ goto out;
+ }
+
+ return 0;
out:
- if (transaction_frame)
- AFR_STACK_DESTROY (transaction_frame);
+ if (transaction_frame)
+ AFR_STACK_DESTROY(transaction_frame);
- AFR_STACK_UNWIND (mkdir, frame, -1, op_errno, NULL, NULL, NULL, NULL,
- NULL);
- return 0;
+ AFR_STACK_UNWIND(mkdir, frame, -1, op_errno, NULL, NULL, NULL, NULL, NULL);
+ return 0;
}
/* }}} */
/* {{{ link */
-
int
-afr_link_unwind (call_frame_t *frame, xlator_t *this)
+afr_link_unwind(call_frame_t *frame, xlator_t *this)
{
- call_frame_t *main_frame = NULL;
- afr_local_t *local = NULL;
-
- local = frame->local;
+ call_frame_t *main_frame = NULL;
+ afr_local_t *local = NULL;
- main_frame = afr_transaction_detach_fop_frame (frame);
- if (!main_frame)
- return 0;
+ local = frame->local;
- AFR_STACK_UNWIND (link, main_frame, local->op_ret, local->op_errno,
- local->inode, &local->cont.dir_fop.buf,
- &local->cont.dir_fop.preparent,
- &local->cont.dir_fop.postparent, local->xdata_rsp);
+ main_frame = afr_transaction_detach_fop_frame(frame);
+ if (!main_frame)
return 0;
-}
+ AFR_STACK_UNWIND(link, main_frame, local->op_ret, local->op_errno,
+ local->inode, &local->cont.dir_fop.buf,
+ &local->cont.dir_fop.preparent,
+ &local->cont.dir_fop.postparent, local->xdata_rsp);
+ return 0;
+}
int
-afr_link_wind_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, inode_t *inode,
- struct iatt *buf, struct iatt *preparent,
- struct iatt *postparent, dict_t *xdata)
+afr_link_wind_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, inode_t *inode,
+ struct iatt *buf, struct iatt *preparent,
+ struct iatt *postparent, dict_t *xdata)
{
- return __afr_dir_write_cbk (frame, cookie, this, op_ret, op_errno, buf,
- preparent, postparent, NULL, NULL, xdata);
+ return __afr_dir_write_cbk(frame, cookie, this, op_ret, op_errno, buf,
+ preparent, postparent, NULL, NULL, xdata);
}
-
int
-afr_link_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_link_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
- local = frame->local;
- priv = this->private;
+ local = frame->local;
+ priv = this->private;
- STACK_WIND_COOKIE (frame, afr_link_wind_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->link,
- &local->loc, &local->newloc, local->xdata_req);
- return 0;
+ STACK_WIND_COOKIE(frame, afr_link_wind_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->link, &local->loc,
+ &local->newloc, local->xdata_req);
+ return 0;
}
-
int
-afr_link (call_frame_t *frame, xlator_t *this, loc_t *oldloc, loc_t *newloc,
- dict_t *xdata)
+afr_link(call_frame_t *frame, xlator_t *this, loc_t *oldloc, loc_t *newloc,
+ dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- afr_internal_lock_t *int_lock = NULL;
- call_frame_t *transaction_frame = NULL;
- int ret = -1;
- int op_errno = ENOMEM;
-
- priv = this->private;
-
- transaction_frame = copy_frame (frame);
- if (!transaction_frame)
- goto out;
-
- local = AFR_FRAME_INIT (transaction_frame, op_errno);
- if (!local)
- goto out;
-
- loc_copy (&local->loc, oldloc);
- loc_copy (&local->newloc, newloc);
-
- local->inode = inode_ref (oldloc->inode);
- local->parent = inode_ref (newloc->parent);
-
- if (xdata)
- local->xdata_req = dict_copy_with_ref (xdata, NULL);
- else
- local->xdata_req = dict_new ();
-
- if (!local->xdata_req)
- goto out;
-
- local->op = GF_FOP_LINK;
-
- local->transaction.wind = afr_link_wind;
- local->transaction.fop = __afr_txn_write_fop;
- local->transaction.done = __afr_txn_write_done;
- local->transaction.unwind = afr_link_unwind;
-
- ret = afr_build_parent_loc (&local->transaction.parent_loc, newloc,
- &op_errno);
- if (ret)
- goto out;
-
- local->transaction.main_frame = frame;
- local->transaction.basename = AFR_BASENAME (newloc->path);
- int_lock = &local->internal_lock;
-
- int_lock->lockee_count = 0;
- ret = afr_init_entry_lockee (&int_lock->lockee[0], local,
- &local->transaction.parent_loc,
- local->transaction.basename,
- priv->child_count);
- if (ret)
- goto out;
-
- int_lock->lockee_count++;
- ret = afr_transaction (transaction_frame, this, AFR_ENTRY_TRANSACTION);
- if (ret < 0) {
- op_errno = -ret;
- goto out;
- }
+ afr_local_t *local = NULL;
+ call_frame_t *transaction_frame = NULL;
+ int ret = -1;
+ int op_errno = ENOMEM;
+
+ transaction_frame = copy_frame(frame);
+ if (!transaction_frame)
+ goto out;
+
+ local = AFR_FRAME_INIT(transaction_frame, op_errno);
+ if (!local)
+ goto out;
+
+ loc_copy(&local->loc, oldloc);
+ loc_copy(&local->newloc, newloc);
- return 0;
+ local->inode = inode_ref(oldloc->inode);
+ local->parent = inode_ref(newloc->parent);
+
+ if (xdata)
+ local->xdata_req = dict_copy_with_ref(xdata, NULL);
+ else
+ local->xdata_req = dict_new();
+
+ if (!local->xdata_req)
+ goto out;
+
+ local->op = GF_FOP_LINK;
+
+ local->transaction.wind = afr_link_wind;
+ local->transaction.unwind = afr_link_unwind;
+
+ ret = afr_build_parent_loc(&local->transaction.parent_loc, newloc,
+ &op_errno);
+ if (ret)
+ goto out;
+
+ local->transaction.main_frame = frame;
+ local->transaction.basename = AFR_BASENAME(newloc->path);
+ ret = afr_transaction(transaction_frame, this, AFR_ENTRY_TRANSACTION);
+ if (ret < 0) {
+ op_errno = -ret;
+ goto out;
+ }
+
+ return 0;
out:
- if (transaction_frame)
- AFR_STACK_DESTROY (transaction_frame);
+ if (transaction_frame)
+ AFR_STACK_DESTROY(transaction_frame);
- AFR_STACK_UNWIND (link, frame, -1, op_errno, NULL, NULL, NULL, NULL,
- NULL);
- return 0;
+ AFR_STACK_UNWIND(link, frame, -1, op_errno, NULL, NULL, NULL, NULL, NULL);
+ return 0;
}
/* }}} */
/* {{{ symlink */
-
int
-afr_symlink_unwind (call_frame_t *frame, xlator_t *this)
+afr_symlink_unwind(call_frame_t *frame, xlator_t *this)
{
- call_frame_t *main_frame = NULL;
- afr_local_t *local = NULL;
-
- local = frame->local;
+ call_frame_t *main_frame = NULL;
+ afr_local_t *local = NULL;
- main_frame = afr_transaction_detach_fop_frame (frame);
- if (!main_frame)
- return 0;
+ local = frame->local;
- AFR_STACK_UNWIND (symlink, main_frame, local->op_ret, local->op_errno,
- local->inode, &local->cont.dir_fop.buf,
- &local->cont.dir_fop.preparent,
- &local->cont.dir_fop.postparent, local->xdata_rsp);
+ main_frame = afr_transaction_detach_fop_frame(frame);
+ if (!main_frame)
return 0;
-}
+ AFR_STACK_UNWIND(symlink, main_frame, local->op_ret, local->op_errno,
+ local->inode, &local->cont.dir_fop.buf,
+ &local->cont.dir_fop.preparent,
+ &local->cont.dir_fop.postparent, local->xdata_rsp);
+ return 0;
+}
int
-afr_symlink_wind_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, inode_t *inode,
- struct iatt *buf, struct iatt *preparent,
- struct iatt *postparent, dict_t *xdata)
+afr_symlink_wind_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, inode_t *inode,
+ struct iatt *buf, struct iatt *preparent,
+ struct iatt *postparent, dict_t *xdata)
{
- return __afr_dir_write_cbk (frame, cookie, this, op_ret, op_errno, buf,
- preparent, postparent, NULL, NULL, xdata);
+ return __afr_dir_write_cbk(frame, cookie, this, op_ret, op_errno, buf,
+ preparent, postparent, NULL, NULL, xdata);
}
-
int
-afr_symlink_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_symlink_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
-
- local = frame->local;
- priv = this->private;
-
- STACK_WIND_COOKIE (frame, afr_symlink_wind_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->symlink,
- local->cont.symlink.linkpath, &local->loc,
- local->umask, local->xdata_req);
- return 0;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+
+ local = frame->local;
+ priv = this->private;
+
+ STACK_WIND_COOKIE(frame, afr_symlink_wind_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->symlink,
+ local->cont.symlink.linkpath, &local->loc, local->umask,
+ local->xdata_req);
+ return 0;
}
-
int
-afr_symlink (call_frame_t *frame, xlator_t *this, const char *linkpath,
- loc_t *loc, mode_t umask, dict_t *xdata)
+afr_symlink(call_frame_t *frame, xlator_t *this, const char *linkpath,
+ loc_t *loc, mode_t umask, dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- afr_internal_lock_t *int_lock = NULL;
- call_frame_t *transaction_frame = NULL;
- int ret = -1;
- int op_errno = ENOMEM;
-
- priv = this->private;
-
- transaction_frame = copy_frame (frame);
- if (!transaction_frame)
- goto out;
-
- local = AFR_FRAME_INIT (transaction_frame, op_errno);
- if (!local)
- goto out;
-
- loc_copy (&local->loc, loc);
- local->inode = inode_ref (loc->inode);
- local->parent = inode_ref (loc->parent);
-
- local->cont.symlink.linkpath = gf_strdup (linkpath);
- local->umask = umask;
-
- if (xdata)
- local->xdata_req = dict_copy_with_ref (xdata, NULL);
- else
- local->xdata_req = dict_new ();
-
- if (!local->xdata_req)
- goto out;
-
- local->op = GF_FOP_SYMLINK;
- local->transaction.wind = afr_symlink_wind;
- local->transaction.fop = __afr_txn_write_fop;
- local->transaction.done = __afr_txn_write_done;
- local->transaction.unwind = afr_symlink_unwind;
-
- ret = afr_build_parent_loc (&local->transaction.parent_loc, loc,
- &op_errno);
- if (ret)
- goto out;
-
- local->transaction.main_frame = frame;
- local->transaction.basename = AFR_BASENAME (loc->path);
- int_lock = &local->internal_lock;
-
- int_lock->lockee_count = 0;
- ret = afr_init_entry_lockee (&int_lock->lockee[0], local,
- &local->transaction.parent_loc,
- local->transaction.basename,
- priv->child_count);
- if (ret)
- goto out;
-
- int_lock->lockee_count++;
- ret = afr_transaction (transaction_frame, this, AFR_ENTRY_TRANSACTION);
- if (ret < 0) {
- op_errno = -ret;
- goto out;
- }
-
- return 0;
+ afr_local_t *local = NULL;
+ call_frame_t *transaction_frame = NULL;
+ int ret = -1;
+ int op_errno = ENOMEM;
+
+ transaction_frame = copy_frame(frame);
+ if (!transaction_frame)
+ goto out;
+
+ local = AFR_FRAME_INIT(transaction_frame, op_errno);
+ if (!local)
+ goto out;
+
+ loc_copy(&local->loc, loc);
+ local->inode = inode_ref(loc->inode);
+ local->parent = inode_ref(loc->parent);
+
+ local->cont.symlink.linkpath = gf_strdup(linkpath);
+ local->umask = umask;
+
+ if (xdata)
+ local->xdata_req = dict_copy_with_ref(xdata, NULL);
+ else
+ local->xdata_req = dict_new();
+
+ if (!local->xdata_req)
+ goto out;
+
+ local->op = GF_FOP_SYMLINK;
+ local->transaction.wind = afr_symlink_wind;
+ local->transaction.unwind = afr_symlink_unwind;
+
+ ret = afr_build_parent_loc(&local->transaction.parent_loc, loc, &op_errno);
+ if (ret)
+ goto out;
+
+ local->transaction.main_frame = frame;
+ local->transaction.basename = AFR_BASENAME(loc->path);
+ ret = afr_transaction(transaction_frame, this, AFR_ENTRY_TRANSACTION);
+ if (ret < 0) {
+ op_errno = -ret;
+ goto out;
+ }
+
+ return 0;
out:
- if (transaction_frame)
- AFR_STACK_DESTROY (transaction_frame);
+ if (transaction_frame)
+ AFR_STACK_DESTROY(transaction_frame);
- AFR_STACK_UNWIND (symlink, frame, -1, op_errno, NULL, NULL, NULL,
- NULL, NULL);
- return 0;
+ AFR_STACK_UNWIND(symlink, frame, -1, op_errno, NULL, NULL, NULL, NULL,
+ NULL);
+ return 0;
}
/* }}} */
@@ -1036,161 +939,118 @@ out:
/* {{{ rename */
int
-afr_rename_unwind (call_frame_t *frame, xlator_t *this)
+afr_rename_unwind(call_frame_t *frame, xlator_t *this)
{
- call_frame_t *main_frame = NULL;
- afr_local_t *local = NULL;
-
- local = frame->local;
+ call_frame_t *main_frame = NULL;
+ afr_local_t *local = NULL;
- main_frame = afr_transaction_detach_fop_frame (frame);
- if (!main_frame)
- return 0;
+ local = frame->local;
- AFR_STACK_UNWIND (rename, main_frame, local->op_ret, local->op_errno,
- &local->cont.dir_fop.buf,
- &local->cont.dir_fop.preparent,
- &local->cont.dir_fop.postparent,
- &local->cont.dir_fop.prenewparent,
- &local->cont.dir_fop.postnewparent, local->xdata_rsp);
+ main_frame = afr_transaction_detach_fop_frame(frame);
+ if (!main_frame)
return 0;
-}
+ AFR_STACK_UNWIND(rename, main_frame, local->op_ret, local->op_errno,
+ &local->cont.dir_fop.buf, &local->cont.dir_fop.preparent,
+ &local->cont.dir_fop.postparent,
+ &local->cont.dir_fop.prenewparent,
+ &local->cont.dir_fop.postnewparent, local->xdata_rsp);
+ return 0;
+}
int
-afr_rename_wind_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, struct iatt *buf,
- struct iatt *preoldparent, struct iatt *postoldparent,
- struct iatt *prenewparent, struct iatt *postnewparent,
- dict_t *xdata)
+afr_rename_wind_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, struct iatt *buf,
+ struct iatt *preoldparent, struct iatt *postoldparent,
+ struct iatt *prenewparent, struct iatt *postnewparent,
+ dict_t *xdata)
{
- return __afr_dir_write_cbk (frame, cookie, this, op_ret, op_errno, buf,
- preoldparent, postoldparent, prenewparent,
- postnewparent, xdata);
+ return __afr_dir_write_cbk(frame, cookie, this, op_ret, op_errno, buf,
+ preoldparent, postoldparent, prenewparent,
+ postnewparent, xdata);
}
-
int
-afr_rename_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_rename_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
- local = frame->local;
- priv = this->private;
+ local = frame->local;
+ priv = this->private;
- STACK_WIND_COOKIE (frame, afr_rename_wind_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->rename,
- &local->loc, &local->newloc, local->xdata_req);
- return 0;
+ STACK_WIND_COOKIE(frame, afr_rename_wind_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->rename, &local->loc,
+ &local->newloc, local->xdata_req);
+ return 0;
}
-
int
-afr_rename (call_frame_t *frame, xlator_t *this, loc_t *oldloc, loc_t *newloc,
- dict_t *xdata)
+afr_rename(call_frame_t *frame, xlator_t *this, loc_t *oldloc, loc_t *newloc,
+ dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- afr_internal_lock_t *int_lock = NULL;
- call_frame_t *transaction_frame = NULL;
- int ret = -1;
- int op_errno = ENOMEM;
- int nlockee = 0;
-
- priv = this->private;
-
- transaction_frame = copy_frame (frame);
- if (!transaction_frame) {
- op_errno = ENOMEM;
- goto out;
- }
-
- local = AFR_FRAME_INIT (transaction_frame, op_errno);
- if (!local)
- goto out;
-
- loc_copy (&local->loc, oldloc);
- loc_copy (&local->newloc, newloc);
-
- local->inode = inode_ref (oldloc->inode);
- local->parent = inode_ref (oldloc->parent);
- local->parent2 = inode_ref (newloc->parent);
-
- if (xdata)
- local->xdata_req = dict_copy_with_ref (xdata, NULL);
- else
- local->xdata_req = dict_new ();
-
- if (!local->xdata_req)
- goto out;
-
- local->op = GF_FOP_RENAME;
- local->transaction.wind = afr_rename_wind;
- local->transaction.fop = __afr_txn_write_fop;
- local->transaction.done = __afr_txn_write_done;
- local->transaction.unwind = afr_rename_unwind;
-
- ret = afr_build_parent_loc (&local->transaction.parent_loc, oldloc,
- &op_errno);
- if (ret)
- goto out;
- ret = afr_build_parent_loc (&local->transaction.new_parent_loc, newloc,
- &op_errno);
- if (ret)
- goto out;
-
- local->transaction.main_frame = frame;
- local->transaction.basename = AFR_BASENAME (oldloc->path);
- local->transaction.new_basename = AFR_BASENAME (newloc->path);
- int_lock = &local->internal_lock;
-
- int_lock->lockee_count = nlockee = 0;
- ret = afr_init_entry_lockee (&int_lock->lockee[nlockee], local,
- &local->transaction.new_parent_loc,
- local->transaction.new_basename,
- priv->child_count);
- if (ret)
- goto out;
-
- nlockee++;
- ret = afr_init_entry_lockee (&int_lock->lockee[nlockee], local,
- &local->transaction.parent_loc,
- local->transaction.basename,
- priv->child_count);
- if (ret)
- goto out;
-
- nlockee++;
- if (local->newloc.inode && IA_ISDIR (local->newloc.inode->ia_type)) {
- ret = afr_init_entry_lockee (&int_lock->lockee[nlockee], local,
- &local->newloc,
- NULL,
- priv->child_count);
- if (ret)
- goto out;
-
- nlockee++;
- }
- qsort (int_lock->lockee, nlockee, sizeof (*int_lock->lockee),
- afr_entry_lockee_cmp);
- int_lock->lockee_count = nlockee;
-
- ret = afr_transaction (transaction_frame, this, AFR_ENTRY_RENAME_TRANSACTION);
- if (ret < 0) {
- op_errno = -ret;
- goto out;
- }
-
- return 0;
+ afr_local_t *local = NULL;
+ call_frame_t *transaction_frame = NULL;
+ int ret = -1;
+ int op_errno = ENOMEM;
+
+ transaction_frame = copy_frame(frame);
+ if (!transaction_frame) {
+ op_errno = ENOMEM;
+ goto out;
+ }
+
+ local = AFR_FRAME_INIT(transaction_frame, op_errno);
+ if (!local)
+ goto out;
+
+ loc_copy(&local->loc, oldloc);
+ loc_copy(&local->newloc, newloc);
+
+ local->inode = inode_ref(oldloc->inode);
+ local->parent = inode_ref(oldloc->parent);
+ local->parent2 = inode_ref(newloc->parent);
+
+ if (xdata)
+ local->xdata_req = dict_copy_with_ref(xdata, NULL);
+ else
+ local->xdata_req = dict_new();
+
+ if (!local->xdata_req)
+ goto out;
+
+ local->op = GF_FOP_RENAME;
+ local->transaction.wind = afr_rename_wind;
+ local->transaction.unwind = afr_rename_unwind;
+
+ ret = afr_build_parent_loc(&local->transaction.parent_loc, oldloc,
+ &op_errno);
+ if (ret)
+ goto out;
+ ret = afr_build_parent_loc(&local->transaction.new_parent_loc, newloc,
+ &op_errno);
+ if (ret)
+ goto out;
+
+ local->transaction.main_frame = frame;
+ local->transaction.basename = AFR_BASENAME(oldloc->path);
+ local->transaction.new_basename = AFR_BASENAME(newloc->path);
+ ret = afr_transaction(transaction_frame, this,
+ AFR_ENTRY_RENAME_TRANSACTION);
+ if (ret < 0) {
+ op_errno = -ret;
+ goto out;
+ }
+
+ return 0;
out:
- if (transaction_frame)
- AFR_STACK_DESTROY (transaction_frame);
+ if (transaction_frame)
+ AFR_STACK_DESTROY(transaction_frame);
- AFR_STACK_UNWIND (rename, frame, -1, op_errno, NULL, NULL, NULL, NULL,
- NULL, NULL);
- return 0;
+ AFR_STACK_UNWIND(rename, frame, -1, op_errno, NULL, NULL, NULL, NULL, NULL,
+ NULL);
+ return 0;
}
/* }}} */
@@ -1198,263 +1058,205 @@ out:
/* {{{ unlink */
int
-afr_unlink_unwind (call_frame_t *frame, xlator_t *this)
+afr_unlink_unwind(call_frame_t *frame, xlator_t *this)
{
- call_frame_t *main_frame = NULL;
- afr_local_t *local = NULL;
-
- local = frame->local;
+ call_frame_t *main_frame = NULL;
+ afr_local_t *local = NULL;
- main_frame = afr_transaction_detach_fop_frame (frame);
- if (!main_frame)
- return 0;
+ local = frame->local;
- AFR_STACK_UNWIND (unlink, main_frame, local->op_ret, local->op_errno,
- &local->cont.dir_fop.preparent,
- &local->cont.dir_fop.postparent, local->xdata_rsp);
+ main_frame = afr_transaction_detach_fop_frame(frame);
+ if (!main_frame)
return 0;
-}
+ AFR_STACK_UNWIND(unlink, main_frame, local->op_ret, local->op_errno,
+ &local->cont.dir_fop.preparent,
+ &local->cont.dir_fop.postparent, local->xdata_rsp);
+ return 0;
+}
int
-afr_unlink_wind_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, struct iatt *preparent,
- struct iatt *postparent, dict_t *xdata)
+afr_unlink_wind_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, struct iatt *preparent,
+ struct iatt *postparent, dict_t *xdata)
{
- return __afr_dir_write_cbk (frame, cookie, this, op_ret, op_errno, NULL,
- preparent, postparent, NULL, NULL, xdata);
+ return __afr_dir_write_cbk(frame, cookie, this, op_ret, op_errno, NULL,
+ preparent, postparent, NULL, NULL, xdata);
}
-
int
-afr_unlink_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_unlink_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
- local = frame->local;
- priv = this->private;
+ local = frame->local;
+ priv = this->private;
- STACK_WIND_COOKIE (frame, afr_unlink_wind_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->unlink,
- &local->loc, local->xflag, local->xdata_req);
- return 0;
+ STACK_WIND_COOKIE(frame, afr_unlink_wind_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->unlink, &local->loc,
+ local->xflag, local->xdata_req);
+ return 0;
}
-
int
-afr_unlink (call_frame_t *frame, xlator_t *this, loc_t *loc, int xflag,
- dict_t *xdata)
+afr_unlink(call_frame_t *frame, xlator_t *this, loc_t *loc, int xflag,
+ dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- afr_internal_lock_t *int_lock = NULL;
- call_frame_t *transaction_frame = NULL;
- int ret = -1;
- int op_errno = ENOMEM;
-
- priv = this->private;
-
- transaction_frame = copy_frame (frame);
- if (!transaction_frame)
- goto out;
-
- local = AFR_FRAME_INIT (transaction_frame, op_errno);
- if (!local)
- goto out;
-
- loc_copy (&local->loc, loc);
- local->xflag = xflag;
-
- local->inode = inode_ref (loc->inode);
- local->parent = inode_ref (loc->parent);
-
- if (xdata)
- local->xdata_req = dict_copy_with_ref (xdata, NULL);
- else
- local->xdata_req = dict_new ();
-
- if (!local->xdata_req)
- goto out;
-
- local->op = GF_FOP_UNLINK;
- local->transaction.wind = afr_unlink_wind;
- local->transaction.fop = __afr_txn_write_fop;
- local->transaction.done = __afr_txn_write_done;
- local->transaction.unwind = afr_unlink_unwind;
-
- ret = afr_build_parent_loc (&local->transaction.parent_loc, loc,
- &op_errno);
- if (ret)
- goto out;
-
- local->transaction.main_frame = frame;
- local->transaction.basename = AFR_BASENAME (loc->path);
- int_lock = &local->internal_lock;
-
- int_lock->lockee_count = 0;
- ret = afr_init_entry_lockee (&int_lock->lockee[0], local,
- &local->transaction.parent_loc,
- local->transaction.basename,
- priv->child_count);
- if (ret)
- goto out;
-
- int_lock->lockee_count++;
- ret = afr_transaction (transaction_frame, this, AFR_ENTRY_TRANSACTION);
- if (ret < 0) {
- op_errno = -ret;
- goto out;
- }
-
- return 0;
+ afr_local_t *local = NULL;
+ call_frame_t *transaction_frame = NULL;
+ int ret = -1;
+ int op_errno = ENOMEM;
+
+ transaction_frame = copy_frame(frame);
+ if (!transaction_frame)
+ goto out;
+
+ local = AFR_FRAME_INIT(transaction_frame, op_errno);
+ if (!local)
+ goto out;
+
+ loc_copy(&local->loc, loc);
+ local->xflag = xflag;
+
+ local->inode = inode_ref(loc->inode);
+ local->parent = inode_ref(loc->parent);
+
+ if (xdata)
+ local->xdata_req = dict_copy_with_ref(xdata, NULL);
+ else
+ local->xdata_req = dict_new();
+
+ if (!local->xdata_req)
+ goto out;
+
+ local->op = GF_FOP_UNLINK;
+ local->transaction.wind = afr_unlink_wind;
+ local->transaction.unwind = afr_unlink_unwind;
+
+ ret = afr_build_parent_loc(&local->transaction.parent_loc, loc, &op_errno);
+ if (ret)
+ goto out;
+
+ local->transaction.main_frame = frame;
+ local->transaction.basename = AFR_BASENAME(loc->path);
+ ret = afr_transaction(transaction_frame, this, AFR_ENTRY_TRANSACTION);
+ if (ret < 0) {
+ op_errno = -ret;
+ goto out;
+ }
+
+ return 0;
out:
- if (transaction_frame)
- AFR_STACK_DESTROY (transaction_frame);
+ if (transaction_frame)
+ AFR_STACK_DESTROY(transaction_frame);
- AFR_STACK_UNWIND (unlink, frame, -1, op_errno, NULL, NULL, NULL);
- return 0;
+ AFR_STACK_UNWIND(unlink, frame, -1, op_errno, NULL, NULL, NULL);
+ return 0;
}
/* }}} */
/* {{{ rmdir */
-
-
int
-afr_rmdir_unwind (call_frame_t *frame, xlator_t *this)
+afr_rmdir_unwind(call_frame_t *frame, xlator_t *this)
{
- call_frame_t *main_frame = NULL;
- afr_local_t *local = NULL;
+ call_frame_t *main_frame = NULL;
+ afr_local_t *local = NULL;
- local = frame->local;
+ local = frame->local;
- main_frame = afr_transaction_detach_fop_frame (frame);
- if (!main_frame)
- return 0;
-
- AFR_STACK_UNWIND (rmdir, main_frame, local->op_ret, local->op_errno,
- &local->cont.dir_fop.preparent,
- &local->cont.dir_fop.postparent, local->xdata_rsp);
+ main_frame = afr_transaction_detach_fop_frame(frame);
+ if (!main_frame)
return 0;
-}
+ AFR_STACK_UNWIND(rmdir, main_frame, local->op_ret, local->op_errno,
+ &local->cont.dir_fop.preparent,
+ &local->cont.dir_fop.postparent, local->xdata_rsp);
+ return 0;
+}
int
-afr_rmdir_wind_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, struct iatt *preparent,
- struct iatt *postparent, dict_t *xdata)
+afr_rmdir_wind_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, struct iatt *preparent,
+ struct iatt *postparent, dict_t *xdata)
{
- return __afr_dir_write_cbk (frame, cookie, this, op_ret, op_errno, NULL,
- preparent, postparent, NULL, NULL, xdata);
+ return __afr_dir_write_cbk(frame, cookie, this, op_ret, op_errno, NULL,
+ preparent, postparent, NULL, NULL, xdata);
}
-
int
-afr_rmdir_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_rmdir_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
- local = frame->local;
- priv = this->private;
+ local = frame->local;
+ priv = this->private;
- STACK_WIND_COOKIE (frame, afr_rmdir_wind_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->rmdir,
- &local->loc, local->cont.rmdir.flags, local->xdata_req);
- return 0;
+ STACK_WIND_COOKIE(frame, afr_rmdir_wind_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->rmdir, &local->loc,
+ local->cont.rmdir.flags, local->xdata_req);
+ return 0;
}
-
int
-afr_rmdir (call_frame_t *frame, xlator_t *this, loc_t *loc, int flags,
- dict_t *xdata)
+afr_rmdir(call_frame_t *frame, xlator_t *this, loc_t *loc, int flags,
+ dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- afr_internal_lock_t *int_lock = NULL;
- call_frame_t *transaction_frame = NULL;
- int ret = -1;
- int op_errno = ENOMEM;
- int nlockee = 0;
-
- priv = this->private;
-
- transaction_frame = copy_frame (frame);
- if (!transaction_frame)
- goto out;
-
- local = AFR_FRAME_INIT (transaction_frame, op_errno);
- if (!local)
- goto out;
-
-
- loc_copy (&local->loc, loc);
- local->inode = inode_ref (loc->inode);
- local->parent = inode_ref (loc->parent);
-
- local->cont.rmdir.flags = flags;
-
- if (xdata)
- local->xdata_req = dict_copy_with_ref (xdata, NULL);
- else
- local->xdata_req = dict_new ();
-
- if (!local->xdata_req)
- goto out;
-
- local->op = GF_FOP_RMDIR;
- local->transaction.wind = afr_rmdir_wind;
- local->transaction.fop = __afr_txn_write_fop;
- local->transaction.done = __afr_txn_write_done;
- local->transaction.unwind = afr_rmdir_unwind;
-
- ret = afr_build_parent_loc (&local->transaction.parent_loc, loc,
- &op_errno);
- if (ret)
- goto out;
-
- local->transaction.main_frame = frame;
- local->transaction.basename = AFR_BASENAME (loc->path);
- int_lock = &local->internal_lock;
-
- int_lock->lockee_count = nlockee = 0;
- ret = afr_init_entry_lockee (&int_lock->lockee[nlockee], local,
- &local->transaction.parent_loc,
- local->transaction.basename,
- priv->child_count);
- if (ret)
- goto out;
-
- nlockee++;
- ret = afr_init_entry_lockee (&int_lock->lockee[nlockee], local,
- &local->loc,
- NULL,
- priv->child_count);
- if (ret)
- goto out;
-
- nlockee++;
- qsort (int_lock->lockee, nlockee, sizeof (*int_lock->lockee),
- afr_entry_lockee_cmp);
- int_lock->lockee_count = nlockee;
-
- ret = afr_transaction (transaction_frame, this, AFR_ENTRY_TRANSACTION);
- if (ret < 0) {
- op_errno = -ret;
- goto out;
- }
-
- return 0;
+ afr_local_t *local = NULL;
+ call_frame_t *transaction_frame = NULL;
+ int ret = -1;
+ int op_errno = ENOMEM;
+
+ transaction_frame = copy_frame(frame);
+ if (!transaction_frame)
+ goto out;
+
+ local = AFR_FRAME_INIT(transaction_frame, op_errno);
+ if (!local)
+ goto out;
+
+ loc_copy(&local->loc, loc);
+ local->inode = inode_ref(loc->inode);
+ local->parent = inode_ref(loc->parent);
+
+ local->cont.rmdir.flags = flags;
+
+ if (xdata)
+ local->xdata_req = dict_copy_with_ref(xdata, NULL);
+ else
+ local->xdata_req = dict_new();
+
+ if (!local->xdata_req)
+ goto out;
+
+ local->op = GF_FOP_RMDIR;
+ local->transaction.wind = afr_rmdir_wind;
+ local->transaction.unwind = afr_rmdir_unwind;
+
+ ret = afr_build_parent_loc(&local->transaction.parent_loc, loc, &op_errno);
+ if (ret)
+ goto out;
+
+ local->transaction.main_frame = frame;
+ local->transaction.basename = AFR_BASENAME(loc->path);
+ ret = afr_transaction(transaction_frame, this, AFR_ENTRY_TRANSACTION);
+ if (ret < 0) {
+ op_errno = -ret;
+ goto out;
+ }
+
+ return 0;
out:
- if (transaction_frame)
- AFR_STACK_DESTROY (transaction_frame);
+ if (transaction_frame)
+ AFR_STACK_DESTROY(transaction_frame);
- AFR_STACK_UNWIND (rmdir, frame, -1, op_errno, NULL, NULL, NULL);
- return 0;
+ AFR_STACK_UNWIND(rmdir, frame, -1, op_errno, NULL, NULL, NULL);
+ return 0;
}
/* }}} */
diff --git a/xlators/cluster/afr/src/afr-dir-write.h b/xlators/cluster/afr/src/afr-dir-write.h
index 02f0a3682d9..1d88c3b9b26 100644
--- a/xlators/cluster/afr/src/afr-dir-write.h
+++ b/xlators/cluster/afr/src/afr-dir-write.h
@@ -12,36 +12,35 @@
#define __DIR_WRITE_H__
int32_t
-afr_create (call_frame_t *frame, xlator_t *this,
- loc_t *loc, int32_t flags, mode_t mode,
- mode_t umask, fd_t *fd, dict_t *xdata);
+afr_create(call_frame_t *frame, xlator_t *this, loc_t *loc, int32_t flags,
+ mode_t mode, mode_t umask, fd_t *fd, dict_t *xdata);
int32_t
-afr_mknod (call_frame_t *frame, xlator_t *this,
- loc_t *loc, mode_t mode, dev_t dev, mode_t umask, dict_t *xdata);
+afr_mknod(call_frame_t *frame, xlator_t *this, loc_t *loc, mode_t mode,
+ dev_t dev, mode_t umask, dict_t *xdata);
int32_t
-afr_mkdir (call_frame_t *frame, xlator_t *this,
- loc_t *loc, mode_t mode, mode_t umask, dict_t *xdata);
+afr_mkdir(call_frame_t *frame, xlator_t *this, loc_t *loc, mode_t mode,
+ mode_t umask, dict_t *xdata);
int32_t
-afr_unlink (call_frame_t *frame, xlator_t *this,
- loc_t *loc, int xflag, dict_t *xdata);
+afr_unlink(call_frame_t *frame, xlator_t *this, loc_t *loc, int xflag,
+ dict_t *xdata);
int32_t
-afr_rmdir (call_frame_t *frame, xlator_t *this,
- loc_t *loc, int flags, dict_t *xdata);
+afr_rmdir(call_frame_t *frame, xlator_t *this, loc_t *loc, int flags,
+ dict_t *xdata);
int32_t
-afr_link (call_frame_t *frame, xlator_t *this,
- loc_t *oldloc, loc_t *newloc, dict_t *xdata);
+afr_link(call_frame_t *frame, xlator_t *this, loc_t *oldloc, loc_t *newloc,
+ dict_t *xdata);
int32_t
-afr_rename (call_frame_t *frame, xlator_t *this,
- loc_t *oldloc, loc_t *newloc, dict_t *xdata);
+afr_rename(call_frame_t *frame, xlator_t *this, loc_t *oldloc, loc_t *newloc,
+ dict_t *xdata);
int
-afr_symlink (call_frame_t *frame, xlator_t *this,
- const char *linkpath, loc_t *oldloc, mode_t umask, dict_t *params);
+afr_symlink(call_frame_t *frame, xlator_t *this, const char *linkpath,
+ loc_t *oldloc, mode_t umask, dict_t *params);
#endif /* __DIR_WRITE_H__ */
diff --git a/xlators/cluster/afr/src/afr-inode-read.c b/xlators/cluster/afr/src/afr-inode-read.c
index 1ebe5e5caf8..c5521704de2 100644
--- a/xlators/cluster/afr/src/afr-inode-read.c
+++ b/xlators/cluster/afr/src/afr-inode-read.c
@@ -8,7 +8,6 @@
cases as published by the Free Software Foundation.
*/
-
#include <libgen.h>
#include <unistd.h>
#include <fnmatch.h>
@@ -16,26 +15,17 @@
#include <stdlib.h>
#include <signal.h>
-#ifndef _CONFIG_H
-#define _CONFIG_H
-#include "config.h"
-#endif
-
-#include "glusterfs.h"
+#include <glusterfs/glusterfs.h>
#include "afr.h"
-#include "dict.h"
-#include "xlator.h"
-#include "hashfn.h"
-#include "logging.h"
-#include "stack.h"
-#include "list.h"
-#include "call-stub.h"
-#include "byte-order.h"
-#include "defaults.h"
-#include "common-utils.h"
-#include "compat-errno.h"
-#include "compat.h"
-#include "quota-common-utils.h"
+#include <glusterfs/dict.h>
+#include <glusterfs/logging.h>
+#include <glusterfs/list.h>
+#include <glusterfs/byte-order.h>
+#include <glusterfs/defaults.h>
+#include <glusterfs/common-utils.h>
+#include <glusterfs/compat-errno.h>
+#include <glusterfs/compat.h>
+#include <glusterfs/quota-common-utils.h>
#include "afr-transaction.h"
#include "afr-messages.h"
@@ -50,146 +40,146 @@
* */
int
-afr_handle_quota_size (call_frame_t *frame, xlator_t *this)
+afr_handle_quota_size(call_frame_t *frame, xlator_t *this)
{
- unsigned char *readable = NULL;
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- struct afr_reply *replies = NULL;
- int i = 0;
- int ret = 0;
- quota_meta_t size = {0, };
- quota_meta_t max_size = {0, };
- int readable_cnt = 0;
- int read_subvol = -1;
-
- local = frame->local;
- priv = this->private;
- replies = local->replies;
-
- readable = alloca0 (priv->child_count);
-
- afr_inode_read_subvol_get (local->inode, this, readable, 0, 0);
-
- readable_cnt = AFR_COUNT (readable, priv->child_count);
-
- for (i = 0; i < priv->child_count; i++) {
- if (!replies[i].valid || replies[i].op_ret == -1)
- continue;
- if (readable_cnt && !readable[i])
- continue;
- if (!replies[i].xdata)
- continue;
- ret = quota_dict_get_meta (replies[i].xdata, QUOTA_SIZE_KEY,
- &size);
- if (ret == -1)
- continue;
- if (read_subvol == -1)
- read_subvol = i;
- if (size.size > max_size.size ||
- (size.file_count + size.dir_count) >
- (max_size.file_count + max_size.dir_count))
- read_subvol = i;
-
- if (size.size > max_size.size)
- max_size.size = size.size;
- if (size.file_count > max_size.file_count)
- max_size.file_count = size.file_count;
- if (size.dir_count > max_size.dir_count)
- max_size.dir_count = size.dir_count;
- }
-
- if (max_size.size == 0 && max_size.file_count == 0 &&
- max_size.dir_count == 0)
- return read_subvol;
-
- for (i = 0; i < priv->child_count; i++) {
- if (!replies[i].valid || replies[i].op_ret == -1)
- continue;
- if (readable_cnt && !readable[i])
- continue;
- if (!replies[i].xdata)
- continue;
- quota_dict_set_meta (replies[i].xdata, QUOTA_SIZE_KEY,
- &max_size, IA_IFDIR);
- }
-
+ unsigned char *readable = NULL;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ struct afr_reply *replies = NULL;
+ int i = 0;
+ int ret = 0;
+ quota_meta_t size = {
+ 0,
+ };
+ quota_meta_t max_size = {
+ 0,
+ };
+ int readable_cnt = 0;
+ int read_subvol = -1;
+
+ local = frame->local;
+ priv = this->private;
+ replies = local->replies;
+
+ readable = alloca0(priv->child_count);
+
+ afr_inode_read_subvol_get(local->inode, this, readable, 0, 0);
+
+ readable_cnt = AFR_COUNT(readable, priv->child_count);
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (!replies[i].valid || replies[i].op_ret == -1)
+ continue;
+ if (readable_cnt && !readable[i])
+ continue;
+ if (!replies[i].xdata)
+ continue;
+ ret = quota_dict_get_meta(replies[i].xdata, QUOTA_SIZE_KEY,
+ SLEN(QUOTA_SIZE_KEY), &size);
+ if (ret == -1)
+ continue;
+ if (read_subvol == -1)
+ read_subvol = i;
+ if (size.size > max_size.size ||
+ (size.file_count + size.dir_count) >
+ (max_size.file_count + max_size.dir_count))
+ read_subvol = i;
+
+ if (size.size > max_size.size)
+ max_size.size = size.size;
+ if (size.file_count > max_size.file_count)
+ max_size.file_count = size.file_count;
+ if (size.dir_count > max_size.dir_count)
+ max_size.dir_count = size.dir_count;
+ }
+
+ if (max_size.size == 0 && max_size.file_count == 0 &&
+ max_size.dir_count == 0)
return read_subvol;
-}
+ for (i = 0; i < priv->child_count; i++) {
+ if (!replies[i].valid || replies[i].op_ret == -1)
+ continue;
+ if (readable_cnt && !readable[i])
+ continue;
+ if (!replies[i].xdata)
+ continue;
+ quota_dict_set_meta(replies[i].xdata, QUOTA_SIZE_KEY, &max_size,
+ IA_IFDIR);
+ }
+
+ return read_subvol;
+}
/* {{{ access */
int
-afr_access_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int op_ret, int op_errno, dict_t *xdata)
+afr_access_cbk(call_frame_t *frame, void *cookie, xlator_t *this, int op_ret,
+ int op_errno, dict_t *xdata)
{
- afr_local_t *local = NULL;
+ afr_local_t *local = NULL;
- local = frame->local;
+ local = frame->local;
- if (op_ret < 0) {
- local->op_ret = op_ret;
- local->op_errno = op_errno;
+ if (op_ret < 0) {
+ local->op_ret = op_ret;
+ local->op_errno = op_errno;
- afr_read_txn_continue (frame, this, (long) cookie);
- return 0;
- }
+ afr_read_txn_continue(frame, this, (long)cookie);
+ return 0;
+ }
- AFR_STACK_UNWIND (access, frame, op_ret, op_errno, xdata);
+ AFR_STACK_UNWIND(access, frame, op_ret, op_errno, xdata);
- return 0;
+ return 0;
}
-
int
-afr_access_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_access_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
-
- priv = this->private;
- local = frame->local;
-
- if (subvol == -1) {
- AFR_STACK_UNWIND (access, frame, local->op_ret,
- local->op_errno, 0);
- return 0;
- }
-
- STACK_WIND_COOKIE (frame, afr_access_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->access,
- &local->loc, local->cont.access.mask,
- local->xdata_req);
- return 0;
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+
+ priv = this->private;
+ local = frame->local;
+
+ if (subvol == -1) {
+ AFR_STACK_UNWIND(access, frame, local->op_ret, local->op_errno, 0);
+ return 0;
+ }
+
+ STACK_WIND_COOKIE(frame, afr_access_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->access, &local->loc,
+ local->cont.access.mask, local->xdata_req);
+ return 0;
}
int
-afr_access (call_frame_t *frame, xlator_t *this, loc_t *loc,
- int mask, dict_t *xdata)
+afr_access(call_frame_t *frame, xlator_t *this, loc_t *loc, int mask,
+ dict_t *xdata)
{
- afr_local_t *local = NULL;
- int op_errno = 0;
+ afr_local_t *local = NULL;
+ int op_errno = 0;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
- local->op = GF_FOP_ACCESS;
- loc_copy (&local->loc, loc);
- local->cont.access.mask = mask;
- if (xdata)
- local->xdata_req = dict_ref (xdata);
+ local->op = GF_FOP_ACCESS;
+ loc_copy(&local->loc, loc);
+ local->cont.access.mask = mask;
+ if (xdata)
+ local->xdata_req = dict_ref(xdata);
- afr_read_txn (frame, this, loc->inode, afr_access_wind,
- AFR_METADATA_TRANSACTION);
+ afr_read_txn(frame, this, loc->inode, afr_access_wind,
+ AFR_METADATA_TRANSACTION);
- return 0;
+ return 0;
out:
- AFR_STACK_UNWIND (access, frame, -1, op_errno, NULL);
+ AFR_STACK_UNWIND(access, frame, -1, op_errno, NULL);
- return 0;
+ return 0;
}
/* }}} */
@@ -197,152 +187,140 @@ out:
/* {{{ stat */
int
-afr_stat_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- struct iatt *buf, dict_t *xdata)
+afr_stat_cbk(call_frame_t *frame, void *cookie, xlator_t *this, int32_t op_ret,
+ int32_t op_errno, struct iatt *buf, dict_t *xdata)
{
- afr_local_t *local = NULL;
+ afr_local_t *local = NULL;
- local = frame->local;
+ local = frame->local;
- if (op_ret < 0) {
- local->op_ret = op_ret;
- local->op_errno = op_errno;
+ if (op_ret < 0) {
+ local->op_ret = op_ret;
+ local->op_errno = op_errno;
- afr_read_txn_continue (frame, this, (long) cookie);
- return 0;
- }
+ afr_read_txn_continue(frame, this, (long)cookie);
+ return 0;
+ }
- AFR_STACK_UNWIND (stat, frame, op_ret, op_errno, buf, xdata);
+ AFR_STACK_UNWIND(stat, frame, op_ret, op_errno, buf, xdata);
- return 0;
+ return 0;
}
-
int
-afr_stat_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_stat_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
-
- priv = this->private;
- local = frame->local;
-
- if (subvol == -1) {
- AFR_STACK_UNWIND (stat, frame, local->op_ret, local->op_errno,
- 0, 0);
- return 0;
- }
-
- STACK_WIND_COOKIE (frame, afr_stat_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->stat,
- &local->loc, local->xdata_req);
- return 0;
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+
+ priv = this->private;
+ local = frame->local;
+
+ if (subvol == -1) {
+ AFR_STACK_UNWIND(stat, frame, local->op_ret, local->op_errno, 0, 0);
+ return 0;
+ }
+
+ STACK_WIND_COOKIE(
+ frame, afr_stat_cbk, (void *)(long)subvol, priv->children[subvol],
+ priv->children[subvol]->fops->stat, &local->loc, local->xdata_req);
+ return 0;
}
int
-afr_stat (call_frame_t *frame, xlator_t *this, loc_t *loc, dict_t *xdata)
+afr_stat(call_frame_t *frame, xlator_t *this, loc_t *loc, dict_t *xdata)
{
- afr_local_t *local = NULL;
- int op_errno = 0;
+ afr_local_t *local = NULL;
+ int op_errno = 0;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
- local->op = GF_FOP_STAT;
- loc_copy (&local->loc, loc);
- if (xdata)
- local->xdata_req = dict_ref (xdata);
+ local->op = GF_FOP_STAT;
+ loc_copy(&local->loc, loc);
+ if (xdata)
+ local->xdata_req = dict_ref(xdata);
- afr_read_txn (frame, this, loc->inode, afr_stat_wind,
- AFR_DATA_TRANSACTION);
+ afr_read_txn(frame, this, loc->inode, afr_stat_wind, AFR_DATA_TRANSACTION);
- return 0;
+ return 0;
out:
- AFR_STACK_UNWIND (stat, frame, -1, op_errno, NULL, NULL);
+ AFR_STACK_UNWIND(stat, frame, -1, op_errno, NULL, NULL);
- return 0;
+ return 0;
}
-
/* }}} */
/* {{{ fstat */
int
-afr_fstat_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
- int32_t op_ret, int32_t op_errno, struct iatt *buf,
- dict_t *xdata)
+afr_fstat_cbk(call_frame_t *frame, void *cookie, xlator_t *this, int32_t op_ret,
+ int32_t op_errno, struct iatt *buf, dict_t *xdata)
{
- afr_local_t *local = NULL;
+ afr_local_t *local = NULL;
- local = frame->local;
+ local = frame->local;
- if (op_ret < 0) {
- local->op_ret = op_ret;
- local->op_errno = op_errno;
+ if (op_ret < 0) {
+ local->op_ret = op_ret;
+ local->op_errno = op_errno;
- afr_read_txn_continue (frame, this, (long) cookie);
- return 0;
- }
+ afr_read_txn_continue(frame, this, (long)cookie);
+ return 0;
+ }
- AFR_STACK_UNWIND (fstat, frame, op_ret, op_errno, buf, xdata);
+ AFR_STACK_UNWIND(fstat, frame, op_ret, op_errno, buf, xdata);
- return 0;
+ return 0;
}
-
int
-afr_fstat_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_fstat_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
-
- priv = this->private;
- local = frame->local;
-
- if (subvol == -1) {
- AFR_STACK_UNWIND (fstat, frame, local->op_ret, local->op_errno,
- 0, 0);
- return 0;
- }
-
- STACK_WIND_COOKIE (frame, afr_fstat_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->fstat,
- local->fd, local->xdata_req);
- return 0;
-}
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+
+ priv = this->private;
+ local = frame->local;
+
+ if (subvol == -1) {
+ AFR_STACK_UNWIND(fstat, frame, local->op_ret, local->op_errno, 0, 0);
+ return 0;
+ }
+ STACK_WIND_COOKIE(
+ frame, afr_fstat_cbk, (void *)(long)subvol, priv->children[subvol],
+ priv->children[subvol]->fops->fstat, local->fd, local->xdata_req);
+ return 0;
+}
int32_t
-afr_fstat (call_frame_t *frame, xlator_t *this,
- fd_t *fd, dict_t *xdata)
+afr_fstat(call_frame_t *frame, xlator_t *this, fd_t *fd, dict_t *xdata)
{
- afr_local_t *local = NULL;
- int op_errno = 0;
+ afr_local_t *local = NULL;
+ int op_errno = 0;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ AFR_ERROR_OUT_IF_FDCTX_INVALID(fd, this, op_errno, out);
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
- local->op = GF_FOP_FSTAT;
- local->fd = fd_ref (fd);
- if (xdata)
- local->xdata_req = dict_ref (xdata);
+ local->op = GF_FOP_FSTAT;
+ local->fd = fd_ref(fd);
+ if (xdata)
+ local->xdata_req = dict_ref(xdata);
- afr_fix_open (fd, this);
+ afr_fix_open(fd, this);
- afr_read_txn (frame, this, fd->inode, afr_fstat_wind,
- AFR_DATA_TRANSACTION);
+ afr_read_txn(frame, this, fd->inode, afr_fstat_wind, AFR_DATA_TRANSACTION);
- return 0;
+ return 0;
out:
- AFR_STACK_UNWIND (fstat, frame, -1, op_errno, NULL, NULL);
+ AFR_STACK_UNWIND(fstat, frame, -1, op_errno, NULL, NULL);
- return 0;
+ return 0;
}
/* }}} */
@@ -350,1394 +328,1567 @@ out:
/* {{{ readlink */
int
-afr_readlink_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- const char *buf, struct iatt *sbuf, dict_t *xdata)
+afr_readlink_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, const char *buf,
+ struct iatt *sbuf, dict_t *xdata)
{
- afr_local_t *local = NULL;
+ afr_local_t *local = NULL;
- local = frame->local;
+ local = frame->local;
- if (op_ret < 0) {
- local->op_ret = -1;
- local->op_errno = op_errno;
+ if (op_ret < 0) {
+ local->op_ret = -1;
+ local->op_errno = op_errno;
- afr_read_txn_continue (frame, this, (long) cookie);
- return 0;
- }
+ afr_read_txn_continue(frame, this, (long)cookie);
+ return 0;
+ }
- AFR_STACK_UNWIND (readlink, frame, op_ret, op_errno,
- buf, sbuf, xdata);
- return 0;
+ AFR_STACK_UNWIND(readlink, frame, op_ret, op_errno, buf, sbuf, xdata);
+ return 0;
}
int
-afr_readlink_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_readlink_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
-
- local = frame->local;
- priv = this->private;
-
- if (subvol == -1) {
- AFR_STACK_UNWIND (readlink, frame, local->op_ret,
- local->op_errno, 0, 0, 0);
- return 0;
- }
-
- STACK_WIND_COOKIE (frame, afr_readlink_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->readlink,
- &local->loc, local->cont.readlink.size,
- local->xdata_req);
- return 0;
-}
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ local = frame->local;
+ priv = this->private;
+
+ if (subvol == -1) {
+ AFR_STACK_UNWIND(readlink, frame, local->op_ret, local->op_errno, 0, 0,
+ 0);
+ return 0;
+ }
+
+ STACK_WIND_COOKIE(frame, afr_readlink_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->readlink, &local->loc,
+ local->cont.readlink.size, local->xdata_req);
+ return 0;
+}
int
-afr_readlink (call_frame_t *frame, xlator_t *this,
- loc_t *loc, size_t size, dict_t *xdata)
+afr_readlink(call_frame_t *frame, xlator_t *this, loc_t *loc, size_t size,
+ dict_t *xdata)
{
- afr_local_t * local = NULL;
- int32_t op_errno = 0;
+ afr_local_t *local = NULL;
+ int32_t op_errno = 0;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
- local->op = GF_FOP_READLINK;
- loc_copy (&local->loc, loc);
- local->cont.readlink.size = size;
- if (xdata)
- local->xdata_req = dict_ref (xdata);
+ local->op = GF_FOP_READLINK;
+ loc_copy(&local->loc, loc);
+ local->cont.readlink.size = size;
+ if (xdata)
+ local->xdata_req = dict_ref(xdata);
- afr_read_txn (frame, this, loc->inode, afr_readlink_wind,
- AFR_DATA_TRANSACTION);
+ afr_read_txn(frame, this, loc->inode, afr_readlink_wind,
+ AFR_DATA_TRANSACTION);
- return 0;
+ return 0;
out:
- AFR_STACK_UNWIND(readlink, frame, -1, op_errno, 0, 0, 0);
+ AFR_STACK_UNWIND(readlink, frame, -1, op_errno, 0, 0, 0);
- return 0;
+ return 0;
}
-
/* }}} */
/* {{{ getxattr */
struct _xattr_key {
- char *key;
- struct list_head list;
+ char *key;
+ struct list_head list;
};
-
int
-__gather_xattr_keys (dict_t *dict, char *key, data_t *value,
- void *data)
+__gather_xattr_keys(dict_t *dict, char *key, data_t *value, void *data)
{
- struct list_head * list = data;
- struct _xattr_key * xkey = NULL;
+ struct list_head *list = data;
+ struct _xattr_key *xkey = NULL;
- if (!strncmp (key, AFR_XATTR_PREFIX,
- strlen (AFR_XATTR_PREFIX))) {
+ if (!strncmp(key, AFR_XATTR_PREFIX, SLEN(AFR_XATTR_PREFIX))) {
+ xkey = GF_MALLOC(sizeof(*xkey), gf_afr_mt_xattr_key);
+ if (!xkey)
+ return -1;
- xkey = GF_CALLOC (1, sizeof (*xkey), gf_afr_mt_xattr_key);
- if (!xkey)
- return -1;
+ xkey->key = key;
+ INIT_LIST_HEAD(&xkey->list);
- xkey->key = key;
- INIT_LIST_HEAD (&xkey->list);
-
- list_add_tail (&xkey->list, list);
- }
- return 0;
+ list_add_tail(&xkey->list, list);
+ }
+ return 0;
}
-
void
-afr_filter_xattrs (dict_t *dict)
+afr_filter_xattrs(dict_t *dict)
{
- struct list_head keys = {0,};
- struct _xattr_key *key = NULL;
- struct _xattr_key *tmp = NULL;
+ struct list_head keys = {
+ 0,
+ };
+ struct _xattr_key *key = NULL;
+ struct _xattr_key *tmp = NULL;
- INIT_LIST_HEAD (&keys);
+ INIT_LIST_HEAD(&keys);
- dict_foreach (dict, __gather_xattr_keys,
- (void *) &keys);
+ dict_foreach(dict, __gather_xattr_keys, (void *)&keys);
- list_for_each_entry_safe (key, tmp, &keys, list) {
- dict_del (dict, key->key);
+ list_for_each_entry_safe(key, tmp, &keys, list)
+ {
+ dict_del(dict, key->key);
- list_del_init (&key->list);
+ list_del_init(&key->list);
- GF_FREE (key);
- }
+ GF_FREE(key);
+ }
}
+static gf_boolean_t
+afr_getxattr_ignorable_errnos(int32_t op_errno)
+{
+ if (op_errno == ENODATA || op_errno == ENOTSUP || op_errno == ERANGE ||
+ op_errno == ENAMETOOLONG)
+ return _gf_true;
+ return _gf_false;
+}
int
-afr_getxattr_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- dict_t *dict, dict_t *xdata)
+afr_getxattr_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *dict, dict_t *xdata)
{
- afr_local_t *local = NULL;
+ afr_local_t *local = NULL;
- local = frame->local;
+ local = frame->local;
- if (op_ret < 0) {
- local->op_ret = op_ret;
- local->op_errno = op_errno;
+ if (op_ret < 0 && !afr_getxattr_ignorable_errnos(op_errno)) {
+ local->op_ret = op_ret;
+ local->op_errno = op_errno;
- afr_read_txn_continue (frame, this, (long) cookie);
- return 0;
- }
+ afr_read_txn_continue(frame, this, (long)cookie);
+ return 0;
+ }
- if (dict)
- afr_filter_xattrs (dict);
+ if (dict)
+ afr_filter_xattrs(dict);
- AFR_STACK_UNWIND (getxattr, frame, op_ret, op_errno, dict, xdata);
+ AFR_STACK_UNWIND(getxattr, frame, op_ret, op_errno, dict, xdata);
- return 0;
+ return 0;
}
-
int
-afr_getxattr_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_getxattr_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
-
- local = frame->local;
- priv = this->private;
-
- if (subvol == -1) {
- AFR_STACK_UNWIND (getxattr, frame, local->op_ret,
- local->op_errno, NULL, NULL);
- return 0;
- }
-
- STACK_WIND_COOKIE (frame, afr_getxattr_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->getxattr,
- &local->loc, local->cont.getxattr.name,
- local->xdata_req);
- return 0;
-}
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+
+ local = frame->local;
+ priv = this->private;
+
+ if (subvol == -1) {
+ AFR_STACK_UNWIND(getxattr, frame, local->op_ret, local->op_errno, NULL,
+ NULL);
+ return 0;
+ }
+ STACK_WIND_COOKIE(frame, afr_getxattr_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->getxattr, &local->loc,
+ local->cont.getxattr.name, local->xdata_req);
+ return 0;
+}
int32_t
-afr_getxattr_unwind (call_frame_t *frame, int op_ret, int op_errno,
- dict_t *dict, dict_t *xdata)
+afr_getxattr_unwind(call_frame_t *frame, int op_ret, int op_errno, dict_t *dict,
+ dict_t *xdata)
{
- AFR_STACK_UNWIND (getxattr, frame, op_ret, op_errno, dict, xdata);
- return 0;
+ AFR_STACK_UNWIND(getxattr, frame, op_ret, op_errno, dict, xdata);
+ return 0;
}
int32_t
-afr_fgetxattr_clrlk_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- dict_t *dict, dict_t *xdata)
+afr_fgetxattr_clrlk_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *dict,
+ dict_t *xdata)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- xlator_t **children = NULL;
- dict_t *xattr = NULL;
- char *tmp_report = NULL;
- char lk_summary[1024] = {0,};
- int serz_len = 0;
- int32_t callcnt = 0;
- long int cky = 0;
- int ret = 0;
-
- priv = this->private;
- children = priv->children;
-
- local = frame->local;
- cky = (long) cookie;
-
- LOCK (&frame->lock);
- {
- callcnt = --local->call_count;
- if (op_ret == -1)
- local->replies[cky].op_errno = op_errno;
-
- if (!local->dict)
- local->dict = dict_new ();
- if (local->dict) {
- ret = dict_get_str (dict, local->cont.getxattr.name,
- &tmp_report);
- if (ret)
- goto unlock;
- ret = dict_set_dynstr (local->dict,
- children[cky]->name,
- gf_strdup (tmp_report));
- if (ret)
- goto unlock;
- }
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ xlator_t **children = NULL;
+ dict_t *xattr = NULL;
+ char *tmp_report = NULL;
+ char lk_summary[1024] = {
+ 0,
+ };
+ int serz_len = 0;
+ int32_t callcnt = 0;
+ long int cky = 0;
+ int ret = 0;
+ int keylen = 0;
+ int children_keylen = 0;
+
+ priv = this->private;
+ children = priv->children;
+
+ local = frame->local;
+ cky = (long)cookie;
+ keylen = strlen(local->cont.getxattr.name);
+ children_keylen = strlen(children[cky]->name);
+
+ LOCK(&frame->lock);
+ {
+ callcnt = --local->call_count;
+ if (op_ret == -1)
+ local->replies[cky].op_errno = op_errno;
+
+ if (!local->dict)
+ local->dict = dict_new();
+ if (local->dict) {
+ ret = dict_get_strn(dict, local->cont.getxattr.name, keylen,
+ &tmp_report);
+ if (ret)
+ goto unlock;
+ ret = dict_set_dynstrn(local->dict, children[cky]->name,
+ children_keylen, gf_strdup(tmp_report));
+ if (ret)
+ goto unlock;
}
+ }
unlock:
- UNLOCK (&frame->lock);
-
- if (!callcnt) {
- xattr = dict_new ();
- if (!xattr) {
- op_ret = -1;
- op_errno = ENOMEM;
- goto unwind;
- }
- ret = dict_serialize_value_with_delim (local->dict,
- lk_summary,
- &serz_len, '\n');
- if (ret) {
- op_ret = -1;
- op_errno = ENOMEM;
- goto unwind;
- }
- if (serz_len == -1)
- snprintf (lk_summary, sizeof (lk_summary),
- "No locks cleared.");
- ret = dict_set_dynstr (xattr, local->cont.getxattr.name,
- gf_strdup (lk_summary));
- if (ret) {
- op_ret = -1;
- op_errno = ENOMEM;
- gf_msg (this->name, GF_LOG_ERROR,
- ENOMEM, AFR_MSG_DICT_SET_FAILED,
- "Error setting dictionary");
- goto unwind;
- }
+ UNLOCK(&frame->lock);
+
+ if (!callcnt) {
+ xattr = dict_new();
+ if (!xattr) {
+ op_ret = -1;
+ op_errno = ENOMEM;
+ goto unwind;
+ }
+ ret = dict_serialize_value_with_delim(local->dict, lk_summary,
+ &serz_len, '\n');
+ if (ret) {
+ op_ret = -1;
+ op_errno = ENOMEM;
+ goto unwind;
+ }
+ if (serz_len == -1)
+ snprintf(lk_summary, sizeof(lk_summary), "No locks cleared.");
+ ret = dict_set_dynstrn(xattr, local->cont.getxattr.name, keylen,
+ gf_strdup(lk_summary));
+ if (ret) {
+ op_ret = -1;
+ op_errno = ENOMEM;
+ gf_msg(this->name, GF_LOG_ERROR, ENOMEM, AFR_MSG_DICT_SET_FAILED,
+ "Error setting dictionary");
+ goto unwind;
+ }
- unwind:
- // Updating child_errno with more recent 'events'
- op_errno = afr_final_errno (local, priv);
+ op_errno = afr_final_errno(local, priv);
- AFR_STACK_UNWIND (fgetxattr, frame, op_ret, op_errno, xattr,
- xdata);
- if (xattr)
- dict_unref (xattr);
- }
+ unwind:
+ AFR_STACK_UNWIND(fgetxattr, frame, op_ret, op_errno, xattr, xdata);
+ if (xattr)
+ dict_unref(xattr);
+ }
- return ret;
+ return ret;
}
int32_t
-afr_getxattr_clrlk_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- dict_t *dict, dict_t *xdata)
+afr_getxattr_clrlk_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *dict,
+ dict_t *xdata)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- xlator_t **children = NULL;
- dict_t *xattr = NULL;
- char *tmp_report = NULL;
- char lk_summary[1024] = {0,};
- int serz_len = 0;
- int32_t callcnt = 0;
- long int cky = 0;
- int ret = 0;
-
- priv = this->private;
- children = priv->children;
-
- local = frame->local;
- cky = (long) cookie;
-
- LOCK (&frame->lock);
- {
- callcnt = --local->call_count;
- if (op_ret == -1)
- local->replies[cky].op_errno = op_errno;
-
- if (!local->dict)
- local->dict = dict_new ();
- if (local->dict) {
- ret = dict_get_str (dict, local->cont.getxattr.name,
- &tmp_report);
- if (ret)
- goto unlock;
- ret = dict_set_dynstr (local->dict,
- children[cky]->name,
- gf_strdup (tmp_report));
- if (ret)
- goto unlock;
- }
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ xlator_t **children = NULL;
+ dict_t *xattr = NULL;
+ char *tmp_report = NULL;
+ char lk_summary[1024] = {
+ 0,
+ };
+ int serz_len = 0;
+ int32_t callcnt = 0;
+ long int cky = 0;
+ int ret = 0;
+ int keylen = 0;
+ int children_keylen = 0;
+
+ priv = this->private;
+ children = priv->children;
+
+ local = frame->local;
+ cky = (long)cookie;
+
+ keylen = strlen(local->cont.getxattr.name);
+ children_keylen = strlen(children[cky]->name);
+
+ LOCK(&frame->lock);
+ {
+ callcnt = --local->call_count;
+ if (op_ret == -1)
+ local->replies[cky].op_errno = op_errno;
+
+ if (!local->dict)
+ local->dict = dict_new();
+ if (local->dict) {
+ ret = dict_get_strn(dict, local->cont.getxattr.name, keylen,
+ &tmp_report);
+ if (ret)
+ goto unlock;
+ ret = dict_set_dynstrn(local->dict, children[cky]->name,
+ children_keylen, gf_strdup(tmp_report));
+ if (ret)
+ goto unlock;
}
+ }
unlock:
- UNLOCK (&frame->lock);
-
- if (!callcnt) {
- xattr = dict_new ();
- if (!xattr) {
- op_ret = -1;
- op_errno = ENOMEM;
- goto unwind;
- }
- ret = dict_serialize_value_with_delim (local->dict,
- lk_summary,
- &serz_len, '\n');
- if (ret) {
- op_ret = -1;
- op_errno = ENOMEM;
- goto unwind;
- }
- if (serz_len == -1)
- snprintf (lk_summary, sizeof (lk_summary),
- "No locks cleared.");
- ret = dict_set_dynstr (xattr, local->cont.getxattr.name,
- gf_strdup (lk_summary));
- if (ret) {
- op_ret = -1;
- op_errno = ENOMEM;
- gf_msg (this->name, GF_LOG_ERROR,
- ENOMEM, AFR_MSG_DICT_SET_FAILED,
- "Error setting dictionary");
- goto unwind;
- }
+ UNLOCK(&frame->lock);
+
+ if (!callcnt) {
+ xattr = dict_new();
+ if (!xattr) {
+ op_ret = -1;
+ op_errno = ENOMEM;
+ goto unwind;
+ }
+ ret = dict_serialize_value_with_delim(local->dict, lk_summary,
+ &serz_len, '\n');
+ if (ret) {
+ op_ret = -1;
+ op_errno = ENOMEM;
+ goto unwind;
+ }
+ if (serz_len == -1)
+ snprintf(lk_summary, sizeof(lk_summary), "No locks cleared.");
+ ret = dict_set_dynstrn(xattr, local->cont.getxattr.name, keylen,
+ gf_strdup(lk_summary));
+ if (ret) {
+ op_ret = -1;
+ op_errno = ENOMEM;
+ gf_msg(this->name, GF_LOG_ERROR, ENOMEM, AFR_MSG_DICT_SET_FAILED,
+ "Error setting dictionary");
+ goto unwind;
+ }
- unwind:
- // Updating child_errno with more recent 'events'
- op_errno = afr_final_errno (local, priv);
+ op_errno = afr_final_errno(local, priv);
- AFR_STACK_UNWIND (getxattr, frame, op_ret, op_errno, xattr, xdata);
+ unwind:
+ AFR_STACK_UNWIND(getxattr, frame, op_ret, op_errno, xattr, xdata);
- if (xattr)
- dict_unref (xattr);
- }
+ if (xattr)
+ dict_unref(xattr);
+ }
- return ret;
+ return ret;
}
/**
* node-uuid cbk uses next child querying mechanism
*/
int32_t
-afr_getxattr_node_uuid_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- dict_t *dict, dict_t *xdata)
+afr_getxattr_node_uuid_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *dict,
+ dict_t *xdata)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- xlator_t **children = NULL;
- int unwind = 1;
- int curr_call_child = 0;
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ xlator_t **children = NULL;
+ int unwind = 1;
+ int curr_call_child = 0;
- priv = this->private;
- children = priv->children;
+ priv = this->private;
+ children = priv->children;
- local = frame->local;
+ local = frame->local;
+
+ if (op_ret == -1) { /** query the _next_ child */
+
+ /**
+ * _current_ becomes _next_
+ * If done with all children and yet no success; give up !
+ */
+ curr_call_child = (int)((long)cookie);
+ if (++curr_call_child == priv->child_count)
+ goto unwind;
+
+ gf_msg_debug(this->name, op_errno,
+ "op_ret (-1): Re-querying afr-child (%d/%d)",
+ curr_call_child, priv->child_count);
+
+ unwind = 0;
+ STACK_WIND_COOKIE(
+ frame, afr_getxattr_node_uuid_cbk, (void *)(long)curr_call_child,
+ children[curr_call_child],
+ children[curr_call_child]->fops->getxattr, &local->loc,
+ local->cont.getxattr.name, local->xdata_req);
+ }
+
+unwind:
+ if (unwind)
+ AFR_STACK_UNWIND(getxattr, frame, op_ret, op_errno, dict, xdata);
+
+ return 0;
+}
+
+/**
+ * list-node-uuids cbk returns the list of node_uuids for the subvolume.
+ */
+int32_t
+afr_getxattr_list_node_uuids_cbk(call_frame_t *frame, void *cookie,
+ xlator_t *this, int32_t op_ret,
+ int32_t op_errno, dict_t *dict, dict_t *xdata)
+{
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ int32_t callcnt = 0;
+ int ret = 0;
+ char *xattr_serz = NULL;
+ long cky = 0;
+ int32_t tlen = 0;
+
+ local = frame->local;
+ priv = this->private;
+ cky = (long)cookie;
+
+ LOCK(&frame->lock);
+ {
+ callcnt = --local->call_count;
+ local->replies[cky].valid = 1;
+ local->replies[cky].op_ret = op_ret;
+ local->replies[cky].op_errno = op_errno;
+
+ if (op_ret < 0)
+ goto unlock;
+
+ local->op_ret = 0;
+
+ if (!local->xdata_rsp && xdata)
+ local->xdata_rsp = dict_ref(xdata);
+ local->replies[cky].xattr = dict_ref(dict);
+ }
+
+unlock:
+ UNLOCK(&frame->lock);
+
+ if (!callcnt) {
+ if (local->op_ret != 0) {
+ /* All bricks gave an error. */
+ local->op_errno = afr_final_errno(local, priv);
+ goto unwind;
+ }
- if (op_ret == -1) { /** query the _next_ child */
-
- /**
- * _current_ becomes _next_
- * If done with all childs and yet no success; give up !
- */
- curr_call_child = (int) ((long)cookie);
- if (++curr_call_child == priv->child_count)
- goto unwind;
-
- gf_log (this->name, GF_LOG_WARNING,
- "op_ret (-1): Re-querying afr-child (%d/%d)",
- curr_call_child, priv->child_count);
-
- unwind = 0;
- STACK_WIND_COOKIE (frame, afr_getxattr_node_uuid_cbk,
- (void *) (long) curr_call_child,
- children[curr_call_child],
- children[curr_call_child]->fops->getxattr,
- &local->loc,
- local->cont.getxattr.name,
- NULL);
+ /*Since we store the UUID0_STR as node uuid for down bricks and
+ *for non zero op_ret, assigning length to priv->child_count
+ *number of uuids*/
+ local->cont.getxattr.xattr_len = (SLEN(UUID0_STR) + 2) *
+ priv->child_count;
+
+ if (!local->dict)
+ local->dict = dict_new();
+ if (!local->dict) {
+ local->op_ret = -1;
+ local->op_errno = ENOMEM;
+ goto unwind;
}
- unwind:
- if (unwind)
- AFR_STACK_UNWIND (getxattr, frame, op_ret, op_errno, dict,
- NULL);
+ xattr_serz = GF_CALLOC(local->cont.getxattr.xattr_len, sizeof(char),
+ gf_common_mt_char);
- return 0;
+ if (!xattr_serz) {
+ local->op_ret = -1;
+ local->op_errno = ENOMEM;
+ goto unwind;
+ }
+
+ ret = afr_serialize_xattrs_with_delimiter(frame, this, xattr_serz,
+ UUID0_STR, &tlen, ' ');
+ if (ret) {
+ local->op_ret = -1;
+ local->op_errno = ENOMEM;
+ GF_FREE(xattr_serz);
+ goto unwind;
+ }
+ ret = dict_set_dynstr_sizen(local->dict, GF_XATTR_LIST_NODE_UUIDS_KEY,
+ xattr_serz);
+ if (ret) {
+ gf_msg(this->name, GF_LOG_ERROR, -ret, AFR_MSG_DICT_SET_FAILED,
+ "Cannot set node_uuid key in dict");
+ local->op_ret = -1;
+ local->op_errno = ENOMEM;
+ if (ret == -EINVAL)
+ GF_FREE(xattr_serz);
+ } else {
+ local->op_ret = local->cont.getxattr.xattr_len - 1;
+ local->op_errno = 0;
+ }
+
+ unwind:
+ AFR_STACK_UNWIND(getxattr, frame, local->op_ret, local->op_errno,
+ local->dict, local->xdata_rsp);
+ }
+
+ return ret;
}
int32_t
-afr_getxattr_quota_size_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- dict_t *dict, dict_t *xdata)
+afr_getxattr_quota_size_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *dict,
+ dict_t *xdata)
{
- int idx = (long) cookie;
- int call_count = 0;
- afr_local_t *local = frame->local;
- int read_subvol = -1;
-
- local->replies[idx].valid = 1;
- local->replies[idx].op_ret = op_ret;
- local->replies[idx].op_errno = op_errno;
- if (dict)
- local->replies[idx].xdata = dict_ref (dict);
- call_count = afr_frame_return (frame);
- if (call_count == 0) {
- local->inode = inode_ref (local->loc.inode);
- read_subvol = afr_handle_quota_size (frame, this);
- if (read_subvol != -1) {
- op_ret = local->replies[read_subvol].op_ret;
- op_errno = local->replies[read_subvol].op_errno;
- dict = local->replies[read_subvol].xdata;
- }
- AFR_STACK_UNWIND (getxattr, frame, op_ret, op_errno, dict,
- xdata);
+ int idx = (long)cookie;
+ int call_count = 0;
+ afr_local_t *local = frame->local;
+ int read_subvol = -1;
+
+ local->replies[idx].valid = 1;
+ local->replies[idx].op_ret = op_ret;
+ local->replies[idx].op_errno = op_errno;
+ if (dict)
+ local->replies[idx].xdata = dict_ref(dict);
+ call_count = afr_frame_return(frame);
+ if (call_count == 0) {
+ local->inode = inode_ref(local->loc.inode);
+ read_subvol = afr_handle_quota_size(frame, this);
+ if (read_subvol != -1) {
+ op_ret = local->replies[read_subvol].op_ret;
+ op_errno = local->replies[read_subvol].op_errno;
+ dict = local->replies[read_subvol].xdata;
}
+ AFR_STACK_UNWIND(getxattr, frame, op_ret, op_errno, dict, xdata);
+ }
- return 0;
+ return 0;
}
int32_t
-afr_getxattr_lockinfo_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- dict_t *dict, dict_t *xdata)
+afr_getxattr_lockinfo_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *dict,
+ dict_t *xdata)
{
- int call_cnt = 0, len = 0;
- char *lockinfo_buf = NULL;
- dict_t *lockinfo = NULL, *newdict = NULL;
- afr_local_t *local = NULL;
-
- LOCK (&frame->lock);
- {
- local = frame->local;
+ int call_cnt = 0, len = 0;
+ char *lockinfo_buf = NULL;
+ dict_t *lockinfo = NULL, *newdict = NULL;
+ afr_local_t *local = NULL;
- call_cnt = --local->call_count;
+ LOCK(&frame->lock);
+ {
+ local = frame->local;
- if ((op_ret < 0) || (!dict && !xdata)) {
- goto unlock;
- }
+ call_cnt = --local->call_count;
- if (xdata) {
- if (!local->xdata_rsp) {
- local->xdata_rsp = dict_new ();
- if (!local->xdata_rsp) {
- local->op_ret = -1;
- local->op_errno = ENOMEM;
- goto unlock;
- }
- }
- }
+ if ((op_ret < 0) || (!dict && !xdata)) {
+ goto unlock;
+ }
- if (!dict) {
- goto unlock;
+ if (xdata) {
+ if (!local->xdata_rsp) {
+ local->xdata_rsp = dict_new();
+ if (!local->xdata_rsp) {
+ local->op_ret = -1;
+ local->op_errno = ENOMEM;
+ goto unlock;
}
+ }
+ }
- op_ret = dict_get_ptr_and_len (dict, GF_XATTR_LOCKINFO_KEY,
- (void **)&lockinfo_buf, &len);
+ if (!dict) {
+ goto unlock;
+ }
- if (!lockinfo_buf) {
- goto unlock;
- }
+ op_ret = dict_get_ptr_and_len(dict, GF_XATTR_LOCKINFO_KEY,
+ (void **)&lockinfo_buf, &len);
- if (!local->dict) {
- local->dict = dict_new ();
- if (!local->dict) {
- local->op_ret = -1;
- local->op_errno = ENOMEM;
- goto unlock;
- }
- }
- }
-unlock:
- UNLOCK (&frame->lock);
-
- if (lockinfo_buf != NULL) {
- lockinfo = dict_new ();
- if (lockinfo == NULL) {
- local->op_ret = -1;
- local->op_errno = ENOMEM;
- } else {
- op_ret = dict_unserialize (lockinfo_buf, len,
- &lockinfo);
-
- if (lockinfo && local->dict) {
- dict_copy (lockinfo, local->dict);
- }
- }
+ if (!lockinfo_buf) {
+ goto unlock;
}
- if (xdata && local->xdata_rsp) {
- dict_copy (xdata, local->xdata_rsp);
+ if (!local->dict) {
+ local->dict = dict_new();
+ if (!local->dict) {
+ local->op_ret = -1;
+ local->op_errno = ENOMEM;
+ goto unlock;
+ }
}
+ }
+unlock:
+ UNLOCK(&frame->lock);
- if (!call_cnt) {
- newdict = dict_new ();
- if (!newdict) {
- local->op_ret = -1;
- local->op_errno = ENOMEM;
- goto unwind;
- }
-
- len = dict_serialized_length (local->dict);
- if (len <= 0) {
- goto unwind;
- }
-
- lockinfo_buf = GF_CALLOC (1, len, gf_common_mt_char);
- if (!lockinfo_buf) {
- local->op_ret = -1;
- local->op_errno = ENOMEM;
- goto unwind;
- }
+ if (lockinfo_buf != NULL) {
+ lockinfo = dict_new();
+ if (lockinfo == NULL) {
+ local->op_ret = -1;
+ local->op_errno = ENOMEM;
+ } else {
+ op_ret = dict_unserialize(lockinfo_buf, len, &lockinfo);
- op_ret = dict_serialize (local->dict, lockinfo_buf);
- if (op_ret < 0) {
- local->op_ret = -1;
- local->op_errno = -op_ret;
- }
+ if (lockinfo && local->dict) {
+ dict_copy(lockinfo, local->dict);
+ }
+ }
+ }
+
+ if (xdata && local->xdata_rsp) {
+ dict_copy(xdata, local->xdata_rsp);
+ }
+
+ if (!call_cnt) {
+ newdict = dict_new();
+ if (!newdict) {
+ local->op_ret = -1;
+ local->op_errno = ENOMEM;
+ goto unwind;
+ }
- op_ret = dict_set_dynptr (newdict, GF_XATTR_LOCKINFO_KEY,
- (void *)lockinfo_buf, len);
- if (op_ret < 0) {
- local->op_ret = -1;
- local->op_errno = -op_ret;
- goto unwind;
- }
+ op_ret = dict_allocate_and_serialize(
+ local->dict, (char **)&lockinfo_buf, (unsigned int *)&len);
+ if (op_ret != 0) {
+ local->op_ret = -1;
+ goto unwind;
+ }
- unwind:
- AFR_STACK_UNWIND (getxattr, frame, op_ret,
- op_errno, newdict,
- local->xdata_rsp);
+ op_ret = dict_set_dynptr(newdict, GF_XATTR_LOCKINFO_KEY,
+ (void *)lockinfo_buf, len);
+ if (op_ret < 0) {
+ local->op_ret = -1;
+ local->op_errno = -op_ret;
+ goto unwind;
}
- dict_unref (lockinfo);
+ unwind:
+ AFR_STACK_UNWIND(getxattr, frame, op_ret, op_errno, newdict,
+ local->xdata_rsp);
+ }
- return 0;
+ dict_unref(lockinfo);
+
+ return 0;
}
int32_t
-afr_fgetxattr_lockinfo_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- dict_t *dict, dict_t *xdata)
+afr_fgetxattr_lockinfo_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *dict,
+ dict_t *xdata)
{
- int call_cnt = 0, len = 0;
- char *lockinfo_buf = NULL;
- dict_t *lockinfo = NULL, *newdict = NULL;
- afr_local_t *local = NULL;
+ int call_cnt = 0, len = 0;
+ char *lockinfo_buf = NULL;
+ dict_t *lockinfo = NULL, *newdict = NULL;
+ afr_local_t *local = NULL;
- LOCK (&frame->lock);
- {
- local = frame->local;
+ LOCK(&frame->lock);
+ {
+ local = frame->local;
- call_cnt = --local->call_count;
+ call_cnt = --local->call_count;
- if ((op_ret < 0) || (!dict && !xdata)) {
- goto unlock;
- }
-
- if (xdata) {
- if (!local->xdata_rsp) {
- local->xdata_rsp = dict_new ();
- if (!local->xdata_rsp) {
- local->op_ret = -1;
- local->op_errno = ENOMEM;
- goto unlock;
- }
- }
- }
+ if ((op_ret < 0) || (!dict && !xdata)) {
+ goto unlock;
+ }
- if (!dict) {
- goto unlock;
+ if (xdata) {
+ if (!local->xdata_rsp) {
+ local->xdata_rsp = dict_new();
+ if (!local->xdata_rsp) {
+ local->op_ret = -1;
+ local->op_errno = ENOMEM;
+ goto unlock;
}
+ }
+ }
- op_ret = dict_get_ptr_and_len (dict, GF_XATTR_LOCKINFO_KEY,
- (void **)&lockinfo_buf, &len);
+ if (!dict) {
+ goto unlock;
+ }
- if (!lockinfo_buf) {
- goto unlock;
- }
+ op_ret = dict_get_ptr_and_len(dict, GF_XATTR_LOCKINFO_KEY,
+ (void **)&lockinfo_buf, &len);
- if (!local->dict) {
- local->dict = dict_new ();
- if (!local->dict) {
- local->op_ret = -1;
- local->op_errno = ENOMEM;
- goto unlock;
- }
- }
- }
-unlock:
- UNLOCK (&frame->lock);
-
- if (lockinfo_buf != NULL) {
- lockinfo = dict_new ();
- if (lockinfo == NULL) {
- local->op_ret = -1;
- local->op_errno = ENOMEM;
- } else {
- op_ret = dict_unserialize (lockinfo_buf, len,
- &lockinfo);
-
- if (lockinfo && local->dict) {
- dict_copy (lockinfo, local->dict);
- }
- }
+ if (!lockinfo_buf) {
+ goto unlock;
}
- if (xdata && local->xdata_rsp) {
- dict_copy (xdata, local->xdata_rsp);
+ if (!local->dict) {
+ local->dict = dict_new();
+ if (!local->dict) {
+ local->op_ret = -1;
+ local->op_errno = ENOMEM;
+ goto unlock;
+ }
}
+ }
+unlock:
+ UNLOCK(&frame->lock);
- if (!call_cnt) {
- newdict = dict_new ();
- if (!newdict) {
- local->op_ret = -1;
- local->op_errno = ENOMEM;
- goto unwind;
- }
-
- len = dict_serialized_length (local->dict);
- if (len <= 0) {
- goto unwind;
- }
-
- lockinfo_buf = GF_CALLOC (1, len, gf_common_mt_char);
- if (!lockinfo_buf) {
- local->op_ret = -1;
- local->op_errno = ENOMEM;
- goto unwind;
- }
+ if (lockinfo_buf != NULL) {
+ lockinfo = dict_new();
+ if (lockinfo == NULL) {
+ local->op_ret = -1;
+ local->op_errno = ENOMEM;
+ } else {
+ op_ret = dict_unserialize(lockinfo_buf, len, &lockinfo);
- op_ret = dict_serialize (local->dict, lockinfo_buf);
- if (op_ret < 0) {
- local->op_ret = -1;
- local->op_errno = -op_ret;
- }
+ if (lockinfo && local->dict) {
+ dict_copy(lockinfo, local->dict);
+ }
+ }
+ }
+
+ if (xdata && local->xdata_rsp) {
+ dict_copy(xdata, local->xdata_rsp);
+ }
+
+ if (!call_cnt) {
+ newdict = dict_new();
+ if (!newdict) {
+ local->op_ret = -1;
+ local->op_errno = ENOMEM;
+ goto unwind;
+ }
- op_ret = dict_set_dynptr (newdict, GF_XATTR_LOCKINFO_KEY,
- (void *)lockinfo_buf, len);
- if (op_ret < 0) {
- local->op_ret = -1;
- local->op_errno = -op_ret;
- goto unwind;
- }
+ op_ret = dict_allocate_and_serialize(
+ local->dict, (char **)&lockinfo_buf, (unsigned int *)&len);
+ if (op_ret != 0) {
+ local->op_ret = -1;
+ goto unwind;
+ }
- unwind:
- AFR_STACK_UNWIND (fgetxattr, frame, op_ret,
- op_errno, newdict,
- local->xdata_rsp);
+ op_ret = dict_set_dynptr(newdict, GF_XATTR_LOCKINFO_KEY,
+ (void *)lockinfo_buf, len);
+ if (op_ret < 0) {
+ local->op_ret = -1;
+ local->op_errno = -op_ret;
+ goto unwind;
}
- dict_unref (lockinfo);
+ unwind:
+ AFR_STACK_UNWIND(fgetxattr, frame, op_ret, op_errno, newdict,
+ local->xdata_rsp);
+ }
- return 0;
+ dict_unref(lockinfo);
+
+ return 0;
}
int32_t
-afr_fgetxattr_pathinfo_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- dict_t *dict, dict_t *xdata)
+afr_fgetxattr_pathinfo_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *dict,
+ dict_t *xdata)
{
- afr_local_t *local = NULL;
- int32_t callcnt = 0;
- int ret = 0;
- char *xattr = NULL;
- char *xattr_serz = NULL;
- char xattr_cky[1024] = {0,};
- dict_t *nxattr = NULL;
- long cky = 0;
- int32_t padding = 0;
- int32_t tlen = 0;
-
- if (!frame || !frame->local || !this) {
- gf_msg ("", GF_LOG_ERROR, 0,
- AFR_MSG_INVALID_ARG, "possible NULL deref");
- goto out;
+ afr_local_t *local = NULL;
+ int32_t callcnt = 0;
+ int ret = 0;
+ char *xattr = NULL;
+ char *xattr_serz = NULL;
+ int keylen = 0;
+ char xattr_cky[1024] = {
+ 0,
+ };
+ int xattr_cky_len = 0;
+ dict_t *nxattr = NULL;
+ long cky = 0;
+ int32_t padding = 0;
+ int32_t tlen = 0;
+
+ if (!frame || !frame->local || !this) {
+ gf_msg("", GF_LOG_ERROR, 0, AFR_MSG_INVALID_ARG, "possible NULL deref");
+ goto out;
+ }
+
+ local = frame->local;
+ cky = (long)cookie;
+ keylen = strlen(local->cont.getxattr.name);
+ xattr_cky_len = snprintf(xattr_cky, sizeof(xattr_cky), "%s-%ld",
+ local->cont.getxattr.name, cky);
+ LOCK(&frame->lock);
+ {
+ callcnt = --local->call_count;
+
+ if (op_ret < 0) {
+ local->op_errno = op_errno;
+ } else {
+ local->op_ret = op_ret;
+ if (!local->xdata_rsp && xdata)
+ local->xdata_rsp = dict_ref(xdata);
}
- local = frame->local;
- cky = (long) cookie;
-
- LOCK (&frame->lock);
- {
- callcnt = --local->call_count;
-
- if (op_ret < 0) {
- local->op_errno = op_errno;
- } else {
- local->op_ret = op_ret;
- if (!local->xdata_rsp && xdata)
- local->xdata_rsp = dict_ref (xdata);
- }
+ if (!dict || (op_ret < 0))
+ goto unlock;
- if (!dict || (op_ret < 0))
- goto unlock;
-
- if (!local->dict)
- local->dict = dict_new ();
-
- if (local->dict) {
- ret = dict_get_str (dict,
- local->cont.getxattr.name,
- &xattr);
- if (ret)
- goto unlock;
-
- xattr = gf_strdup (xattr);
-
- (void)snprintf (xattr_cky, 1024, "%s-%ld",
- local->cont.getxattr.name, cky);
- ret = dict_set_dynstr (local->dict,
- xattr_cky, xattr);
- if (ret) {
- gf_msg (this->name, GF_LOG_ERROR,
- -ret, AFR_MSG_DICT_SET_FAILED,
- "Cannot set xattr cookie key");
- goto unlock;
- }
-
- local->cont.getxattr.xattr_len
- += strlen (xattr) + 1;
- }
+ if (!local->dict) {
+ local->dict = dict_new();
+ if (!local->dict)
+ goto unlock;
+ }
+ ret = dict_get_strn(dict, local->cont.getxattr.name, keylen, &xattr);
+ if (ret)
+ goto unlock;
+
+ xattr = gf_strdup(xattr);
+
+ ret = dict_set_dynstrn(local->dict, xattr_cky, xattr_cky_len, xattr);
+ if (ret) {
+ UNLOCK(&frame->lock);
+ gf_msg(this->name, GF_LOG_ERROR, -ret, AFR_MSG_DICT_SET_FAILED,
+ "Cannot set xattr cookie key");
+ goto post_unlock;
}
-unlock:
- UNLOCK (&frame->lock);
-
- if (!callcnt) {
- if (!local->cont.getxattr.xattr_len)
- goto unwind;
-
- nxattr = dict_new ();
- if (!nxattr)
- goto unwind;
-
- /* extra bytes for decorations (brackets and <>'s) */
- padding += strlen (this->name)
- + strlen (AFR_PATHINFO_HEADER) + 4;
- local->cont.getxattr.xattr_len += (padding + 2);
-
- xattr_serz = GF_CALLOC (local->cont.getxattr.xattr_len,
- sizeof (char), gf_common_mt_char);
-
- if (!xattr_serz)
- goto unwind;
-
- /* the xlator info */
- (void) sprintf (xattr_serz, "(<"AFR_PATHINFO_HEADER"%s> ",
- this->name);
-
- /* actual series of pathinfo */
- ret = dict_serialize_value_with_delim (local->dict,
- xattr_serz
- + strlen (xattr_serz),
- &tlen, ' ');
- if (ret) {
- goto unwind;
- }
- /* closing part */
- *(xattr_serz + padding + tlen) = ')';
- *(xattr_serz + padding + tlen + 1) = '\0';
+ local->cont.getxattr.xattr_len += strlen(xattr) + 1;
+ }
+unlock:
+ UNLOCK(&frame->lock);
+post_unlock:
+ if (!callcnt) {
+ if (!local->cont.getxattr.xattr_len)
+ goto unwind;
+
+ nxattr = dict_new();
+ if (!nxattr)
+ goto unwind;
+
+ /* extra bytes for decorations (brackets and <>'s) */
+ padding += strlen(this->name) + SLEN(AFR_PATHINFO_HEADER) + 4;
+ local->cont.getxattr.xattr_len += (padding + 2);
+
+ xattr_serz = GF_MALLOC(local->cont.getxattr.xattr_len,
+ gf_common_mt_char);
+
+ if (!xattr_serz)
+ goto unwind;
+
+ /* the xlator info */
+ int xattr_serz_len = sprintf(
+ xattr_serz, "(<" AFR_PATHINFO_HEADER "%s> ", this->name);
+
+ /* actual series of pathinfo */
+ ret = dict_serialize_value_with_delim(
+ local->dict, xattr_serz + xattr_serz_len, &tlen, ' ');
+ if (ret) {
+ GF_FREE(xattr_serz);
+ goto unwind;
+ }
- ret = dict_set_dynstr (nxattr, local->cont.getxattr.name,
- xattr_serz);
- if (ret)
- gf_msg (this->name, GF_LOG_ERROR,
- -ret, AFR_MSG_DICT_SET_FAILED,
- "Cannot set pathinfo key in dict");
+ /* closing part */
+ *(xattr_serz + padding + tlen) = ')';
+ *(xattr_serz + padding + tlen + 1) = '\0';
+
+ ret = dict_set_dynstrn(nxattr, local->cont.getxattr.name, keylen,
+ xattr_serz);
+ if (ret) {
+ gf_msg(this->name, GF_LOG_ERROR, -ret, AFR_MSG_DICT_SET_FAILED,
+ "Cannot set pathinfo key in dict");
+ if (ret == -EINVAL)
+ GF_FREE(xattr_serz);
+ }
- unwind:
- AFR_STACK_UNWIND (fgetxattr, frame, local->op_ret,
- local->op_errno, nxattr, local->xdata_rsp);
+ unwind:
+ AFR_STACK_UNWIND(fgetxattr, frame, local->op_ret, local->op_errno,
+ nxattr, local->xdata_rsp);
- if (nxattr)
- dict_unref (nxattr);
- }
+ if (nxattr)
+ dict_unref(nxattr);
+ }
out:
- return ret;
+ return ret;
}
int32_t
-afr_getxattr_pathinfo_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- dict_t *dict, dict_t *xdata)
+afr_getxattr_pathinfo_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *dict,
+ dict_t *xdata)
{
- afr_local_t *local = NULL;
- int32_t callcnt = 0;
- int ret = 0;
- char *xattr = NULL;
- char *xattr_serz = NULL;
- char xattr_cky[1024] = {0,};
- dict_t *nxattr = NULL;
- long cky = 0;
- int32_t padding = 0;
- int32_t tlen = 0;
-
- if (!frame || !frame->local || !this) {
- gf_msg ("", GF_LOG_ERROR, 0,
- AFR_MSG_INVALID_ARG, "possible NULL deref");
- goto out;
+ afr_local_t *local = NULL;
+ int32_t callcnt = 0;
+ int ret = 0;
+ char *xattr = NULL;
+ char *xattr_serz = NULL;
+ char xattr_cky[1024] = {
+ 0,
+ };
+ int keylen = 0;
+ int xattr_cky_len = 0;
+ dict_t *nxattr = NULL;
+ long cky = 0;
+ int32_t padding = 0;
+ int32_t tlen = 0;
+
+ if (!frame || !frame->local || !this) {
+ gf_msg("", GF_LOG_ERROR, 0, AFR_MSG_INVALID_ARG, "possible NULL deref");
+ goto out;
+ }
+
+ local = frame->local;
+ cky = (long)cookie;
+ keylen = strlen(local->cont.getxattr.name);
+ xattr_cky_len = snprintf(xattr_cky, sizeof(xattr_cky), "%s-%ld",
+ local->cont.getxattr.name, cky);
+ LOCK(&frame->lock);
+ {
+ callcnt = --local->call_count;
+
+ if (op_ret < 0) {
+ local->op_errno = op_errno;
+ } else {
+ local->op_ret = op_ret;
+ if (!local->xdata_rsp && xdata)
+ local->xdata_rsp = dict_ref(xdata);
}
- local = frame->local;
- cky = (long) cookie;
-
- LOCK (&frame->lock);
- {
- callcnt = --local->call_count;
-
- if (op_ret < 0) {
- local->op_errno = op_errno;
- } else {
- local->op_ret = op_ret;
- if (!local->xdata_rsp && xdata)
- local->xdata_rsp = dict_ref (xdata);
- }
-
- if (!dict || (op_ret < 0))
- goto unlock;
-
- if (!local->dict)
- local->dict = dict_new ();
-
- if (local->dict) {
- ret = dict_get_str (dict,
- local->cont.getxattr.name,
- &xattr);
- if (ret)
- goto unlock;
-
- xattr = gf_strdup (xattr);
-
- (void)snprintf (xattr_cky, 1024, "%s-%ld",
- local->cont.getxattr.name, cky);
- ret = dict_set_dynstr (local->dict,
- xattr_cky, xattr);
- if (ret) {
- gf_msg (this->name, GF_LOG_ERROR,
- -ret,
- AFR_MSG_DICT_SET_FAILED,
- "Cannot set xattr "
- "cookie key");
- goto unlock;
- }
-
- local->cont.getxattr.xattr_len += strlen (xattr) + 1;
- }
- }
-unlock:
- UNLOCK (&frame->lock);
-
- if (!callcnt) {
- if (!local->cont.getxattr.xattr_len)
- goto unwind;
-
- nxattr = dict_new ();
- if (!nxattr)
- goto unwind;
-
- /* extra bytes for decorations (brackets and <>'s) */
- padding += strlen (this->name) + strlen (AFR_PATHINFO_HEADER) + 4;
- local->cont.getxattr.xattr_len += (padding + 2);
+ if (!dict || (op_ret < 0))
+ goto unlock;
- xattr_serz = GF_CALLOC (local->cont.getxattr.xattr_len,
- sizeof (char), gf_common_mt_char);
-
- if (!xattr_serz)
- goto unwind;
-
- /* the xlator info */
- (void) sprintf (xattr_serz, "(<"AFR_PATHINFO_HEADER"%s> ",
- this->name);
-
- /* actual series of pathinfo */
- ret = dict_serialize_value_with_delim (local->dict,
- xattr_serz + strlen (xattr_serz),
- &tlen, ' ');
- if (ret) {
- goto unwind;
- }
+ if (!local->dict) {
+ local->dict = dict_new();
+ if (!local->dict)
+ goto unlock;
+ }
+ ret = dict_get_strn(dict, local->cont.getxattr.name, keylen, &xattr);
+ if (ret)
+ goto unlock;
+
+ xattr = gf_strdup(xattr);
+
+ ret = dict_set_dynstrn(local->dict, xattr_cky, xattr_cky_len, xattr);
+ if (ret) {
+ UNLOCK(&frame->lock);
+ gf_msg(this->name, GF_LOG_ERROR, -ret, AFR_MSG_DICT_SET_FAILED,
+ "Cannot set xattr cookie key");
+ goto post_unlock;
+ }
- /* closing part */
- *(xattr_serz + padding + tlen) = ')';
- *(xattr_serz + padding + tlen + 1) = '\0';
+ local->cont.getxattr.xattr_len += strlen(xattr) + 1;
+ }
+unlock:
+ UNLOCK(&frame->lock);
+post_unlock:
+ if (!callcnt) {
+ if (!local->cont.getxattr.xattr_len)
+ goto unwind;
+
+ nxattr = dict_new();
+ if (!nxattr)
+ goto unwind;
+
+ /* extra bytes for decorations (brackets and <>'s) */
+ padding += strlen(this->name) + SLEN(AFR_PATHINFO_HEADER) + 4;
+ local->cont.getxattr.xattr_len += (padding + 2);
+
+ xattr_serz = GF_MALLOC(local->cont.getxattr.xattr_len,
+ gf_common_mt_char);
+
+ if (!xattr_serz)
+ goto unwind;
+
+ /* the xlator info */
+ int xattr_serz_len = sprintf(
+ xattr_serz, "(<" AFR_PATHINFO_HEADER "%s> ", this->name);
+
+ /* actual series of pathinfo */
+ ret = dict_serialize_value_with_delim(
+ local->dict, xattr_serz + xattr_serz_len, &tlen, ' ');
+ if (ret) {
+ GF_FREE(xattr_serz);
+ goto unwind;
+ }
- ret = dict_set_dynstr (nxattr, local->cont.getxattr.name,
- xattr_serz);
- if (ret)
- gf_msg (this->name, GF_LOG_ERROR,
- -ret, AFR_MSG_DICT_SET_FAILED,
- "Cannot set pathinfo key in dict");
+ /* closing part */
+ *(xattr_serz + padding + tlen) = ')';
+ *(xattr_serz + padding + tlen + 1) = '\0';
+
+ ret = dict_set_dynstrn(nxattr, local->cont.getxattr.name, keylen,
+ xattr_serz);
+ if (ret) {
+ gf_msg(this->name, GF_LOG_ERROR, -ret, AFR_MSG_DICT_SET_FAILED,
+ "Cannot set pathinfo key in dict");
+ if (ret == -EINVAL)
+ GF_FREE(xattr_serz);
+ }
- unwind:
- AFR_STACK_UNWIND (getxattr, frame, local->op_ret,
- local->op_errno, nxattr, local->xdata_rsp);
+ unwind:
+ AFR_STACK_UNWIND(getxattr, frame, local->op_ret, local->op_errno,
+ nxattr, local->xdata_rsp);
- if (nxattr)
- dict_unref (nxattr);
- }
+ if (nxattr)
+ dict_unref(nxattr);
+ }
out:
- return ret;
+ return ret;
}
static int
-afr_aggregate_stime_xattr (dict_t *this, char *key, data_t *value, void *data)
+afr_aggregate_stime_xattr(dict_t *this, char *key, data_t *value, void *data)
{
- int ret = 0;
+ int ret = 0;
- if (fnmatch (GF_XATTR_STIME_PATTERN, key, FNM_NOESCAPE) == 0)
- ret = gf_get_max_stime (THIS, data, key, value);
+ if (fnmatch(GF_XATTR_STIME_PATTERN, key, FNM_NOESCAPE) == 0)
+ ret = gf_get_max_stime(THIS, data, key, value);
- return ret;
+ return ret;
}
int32_t
-afr_common_getxattr_stime_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- dict_t *dict, dict_t *xdata)
+afr_common_getxattr_stime_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *dict,
+ dict_t *xdata)
{
- afr_local_t *local = NULL;
- int32_t callcnt = 0;
+ afr_local_t *local = NULL;
+ int32_t callcnt = 0;
- if (!frame || !frame->local || !this) {
- gf_msg ("", GF_LOG_ERROR, 0,
- AFR_MSG_INVALID_ARG, "possible NULL deref");
- goto out;
- }
+ if (!frame || !frame->local || !this) {
+ gf_msg("", GF_LOG_ERROR, 0, AFR_MSG_INVALID_ARG, "possible NULL deref");
+ goto out;
+ }
- local = frame->local;
+ local = frame->local;
- LOCK (&frame->lock);
- {
- callcnt = --local->call_count;
-
- if (!dict || (op_ret < 0)) {
- local->op_errno = op_errno;
- goto cleanup;
- }
+ LOCK(&frame->lock);
+ {
+ callcnt = --local->call_count;
- if (!local->dict)
- local->dict = dict_copy_with_ref (dict, NULL);
- else
- dict_foreach (dict, afr_aggregate_stime_xattr,
- local->dict);
- local->op_ret = 0;
+ if (!dict || (op_ret < 0)) {
+ local->op_errno = op_errno;
+ goto cleanup;
}
+ if (!local->dict)
+ local->dict = dict_copy_with_ref(dict, NULL);
+ else
+ dict_foreach(dict, afr_aggregate_stime_xattr, local->dict);
+ local->op_ret = 0;
+ }
+
cleanup:
- UNLOCK (&frame->lock);
+ UNLOCK(&frame->lock);
- if (!callcnt) {
- AFR_STACK_UNWIND (getxattr, frame, local->op_ret,
- local->op_errno, local->dict, xdata);
- }
+ if (!callcnt) {
+ AFR_STACK_UNWIND(getxattr, frame, local->op_ret, local->op_errno,
+ local->dict, xdata);
+ }
out:
- return 0;
+ return 0;
}
-
static gf_boolean_t
-afr_is_special_xattr (const char *name, fop_getxattr_cbk_t *cbk,
- gf_boolean_t is_fgetxattr)
+afr_is_special_xattr(const char *name, fop_getxattr_cbk_t *cbk,
+ gf_boolean_t is_fgetxattr)
{
- gf_boolean_t is_spl = _gf_true;
-
- GF_ASSERT (cbk);
- if (!cbk || !name) {
- is_spl = _gf_false;
- goto out;
+ gf_boolean_t is_spl = _gf_true;
+
+ GF_ASSERT(cbk);
+ if (!cbk || !name) {
+ is_spl = _gf_false;
+ goto out;
+ }
+
+ if (!strcmp(name, GF_XATTR_PATHINFO_KEY) ||
+ !strcmp(name, GF_XATTR_USER_PATHINFO_KEY)) {
+ if (is_fgetxattr) {
+ *cbk = afr_fgetxattr_pathinfo_cbk;
+ } else {
+ *cbk = afr_getxattr_pathinfo_cbk;
}
-
- if (!strcmp (name, GF_XATTR_PATHINFO_KEY) ||
- !strcmp (name, GF_XATTR_USER_PATHINFO_KEY)) {
- if (is_fgetxattr) {
- *cbk = afr_fgetxattr_pathinfo_cbk;
- } else {
- *cbk = afr_getxattr_pathinfo_cbk;
- }
- } else if (!strncmp (name, GF_XATTR_CLRLK_CMD,
- strlen (GF_XATTR_CLRLK_CMD))) {
- if (is_fgetxattr) {
- *cbk = afr_fgetxattr_clrlk_cbk;
- } else {
- *cbk = afr_getxattr_clrlk_cbk;
- }
- } else if (!strncmp (name, GF_XATTR_LOCKINFO_KEY,
- strlen (GF_XATTR_LOCKINFO_KEY))) {
- if (is_fgetxattr) {
- *cbk = afr_fgetxattr_lockinfo_cbk;
- } else {
- *cbk = afr_getxattr_lockinfo_cbk;
- }
- } else if (fnmatch (GF_XATTR_STIME_PATTERN, name, FNM_NOESCAPE) == 0) {
- *cbk = afr_common_getxattr_stime_cbk;
- } else if (strcmp (name, QUOTA_SIZE_KEY) == 0) {
- *cbk = afr_getxattr_quota_size_cbk;
+ } else if (!strncmp(name, GF_XATTR_CLRLK_CMD, SLEN(GF_XATTR_CLRLK_CMD))) {
+ if (is_fgetxattr) {
+ *cbk = afr_fgetxattr_clrlk_cbk;
+ } else {
+ *cbk = afr_getxattr_clrlk_cbk;
+ }
+ } else if (!strncmp(name, GF_XATTR_LOCKINFO_KEY,
+ SLEN(GF_XATTR_LOCKINFO_KEY))) {
+ if (is_fgetxattr) {
+ *cbk = afr_fgetxattr_lockinfo_cbk;
} else {
- is_spl = _gf_false;
+ *cbk = afr_getxattr_lockinfo_cbk;
}
+ } else if (fnmatch(GF_XATTR_STIME_PATTERN, name, FNM_NOESCAPE) == 0) {
+ *cbk = afr_common_getxattr_stime_cbk;
+ } else if (strcmp(name, QUOTA_SIZE_KEY) == 0) {
+ *cbk = afr_getxattr_quota_size_cbk;
+ } else if (!strcmp(name, GF_XATTR_LIST_NODE_UUIDS_KEY)) {
+ *cbk = afr_getxattr_list_node_uuids_cbk;
+ } else {
+ is_spl = _gf_false;
+ }
out:
- return is_spl;
+ return is_spl;
}
static void
-afr_getxattr_all_subvols (xlator_t *this, call_frame_t *frame,
- const char *name, loc_t *loc,
- fop_getxattr_cbk_t cbk)
+afr_getxattr_all_subvols(xlator_t *this, call_frame_t *frame, const char *name,
+ loc_t *loc, fop_getxattr_cbk_t cbk)
{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int i = 0;
- int call_count = 0;
-
- priv = this->private;
-
- local = frame->local;
- //local->call_count set in afr_local_init
- call_count = local->call_count;
-
- //If up-children count is 0, afr_local_init would have failed already
- //and the call would have unwound so not handling it here.
-
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND_COOKIE (frame, cbk,
- (void *) (long) i, priv->children[i],
- priv->children[i]->fops->getxattr,
- loc, name, NULL);
- if (!--call_count)
- break;
- }
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ int i = 0;
+ int call_count = 0;
+
+ priv = this->private;
+
+ local = frame->local;
+ // local->call_count set in afr_local_init
+ call_count = local->call_count;
+
+ if (!strcmp(name, GF_XATTR_LIST_NODE_UUIDS_KEY)) {
+ GF_FREE(local->cont.getxattr.name);
+ local->cont.getxattr.name = gf_strdup(GF_XATTR_NODE_UUID_KEY);
+ }
+
+ // If up-children count is 0, afr_local_init would have failed already
+ // and the call would have unwound so not handling it here.
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->child_up[i]) {
+ STACK_WIND_COOKIE(frame, cbk, (void *)(long)i, priv->children[i],
+ priv->children[i]->fops->getxattr, loc,
+ local->cont.getxattr.name, NULL);
+ if (!--call_count)
+ break;
}
- return;
+ }
+ return;
}
int
-afr_marker_populate_args (call_frame_t *frame, int type, int *gauge,
- xlator_t **subvols)
+afr_marker_populate_args(call_frame_t *frame, int type, int *gauge,
+ xlator_t **subvols)
{
- xlator_t *this = frame->this;
- afr_private_t *priv = this->private;
+ xlator_t *this = frame->this;
+ afr_private_t *priv = this->private;
- memcpy (subvols, priv->children, sizeof (*subvols) * priv->child_count);
+ memcpy(subvols, priv->children, sizeof(*subvols) * priv->child_count);
- if (type == MARKER_XTIME_TYPE) {
- /*Don't error out on ENOENT/ENOTCONN */
- gauge[MCNT_NOTFOUND] = 0;
- gauge[MCNT_ENOTCONN] = 0;
- }
- return priv->child_count;
+ if (type == MARKER_XTIME_TYPE) {
+ /*Don't error out on ENOENT/ENOTCONN */
+ gauge[MCNT_NOTFOUND] = 0;
+ gauge[MCNT_ENOTCONN] = 0;
+ }
+ return priv->child_count;
}
-int32_t
-afr_getxattr (call_frame_t *frame, xlator_t *this,
- loc_t *loc, const char *name, dict_t *xdata)
+static int
+afr_handle_heal_xattrs(call_frame_t *frame, xlator_t *this, loc_t *loc,
+ const char *heal_op)
{
- afr_private_t *priv = NULL;
- xlator_t **children = NULL;
- afr_local_t *local = NULL;
- int i = 0;
- int32_t op_errno = 0;
- int ret = -1;
- fop_getxattr_cbk_t cbk = NULL;
+ int ret = -1;
+ afr_spb_status_t *data = NULL;
+ if (!strcmp(heal_op, GF_HEAL_INFO)) {
+ afr_get_heal_info(frame, this, loc);
+ ret = 0;
+ goto out;
+ }
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ if (!strcmp(heal_op, GF_AFR_HEAL_SBRAIN)) {
+ afr_heal_splitbrain_file(frame, this, loc);
+ ret = 0;
+ goto out;
+ }
+
+ if (!strcmp(heal_op, GF_AFR_SBRAIN_STATUS)) {
+ data = GF_CALLOC(1, sizeof(*data), gf_afr_mt_spb_status_t);
+ if (!data) {
+ ret = 1;
+ goto out;
+ }
+ data->frame = frame;
+ data->loc = loc;
+ ret = synctask_new(this->ctx->env, afr_get_split_brain_status,
+ afr_get_split_brain_status_cbk, NULL, data);
+ if (ret) {
+ gf_msg(this->name, GF_LOG_ERROR, 0, AFR_MSG_SPLIT_BRAIN_STATUS,
+ "Failed to create"
+ " synctask. Unable to fetch split-brain status"
+ " for %s.",
+ loc->name);
+ ret = 1;
+ goto out;
+ }
+ goto out;
+ }
- priv = this->private;
+out:
+ if (ret == 1) {
+ AFR_STACK_UNWIND(getxattr, frame, -1, ENOMEM, NULL, NULL);
+ if (data)
+ GF_FREE(data);
+ ret = 0;
+ }
+ return ret;
+}
- children = priv->children;
+int32_t
+afr_getxattr(call_frame_t *frame, xlator_t *this, loc_t *loc, const char *name,
+ dict_t *xdata)
+{
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ xlator_t **children = NULL;
+ int i = 0;
+ int32_t op_errno = 0;
+ int ret = -1;
+ fop_getxattr_cbk_t cbk = NULL;
- loc_copy (&local->loc, loc);
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
- local->op = GF_FOP_GETXATTR;
+ priv = this->private;
- if (xdata)
- local->xdata_req = dict_ref (xdata);
+ children = priv->children;
- if (!name)
- goto no_name;
+ loc_copy(&local->loc, loc);
- local->cont.getxattr.name = gf_strdup (name);
+ local->op = GF_FOP_GETXATTR;
- if (!local->cont.getxattr.name) {
- op_errno = ENOMEM;
- goto out;
- }
+ if (xdata)
+ local->xdata_req = dict_ref(xdata);
- if (!strncmp (name, AFR_XATTR_PREFIX,
- strlen (AFR_XATTR_PREFIX))) {
- op_errno = ENODATA;
- goto out;
- }
+ if (!name)
+ goto no_name;
- if (cluster_handle_marker_getxattr (frame, loc, name, priv->vol_uuid,
- afr_getxattr_unwind,
- afr_marker_populate_args) == 0)
- return 0;
+ local->cont.getxattr.name = gf_strdup(name);
- if (!strcmp (name, GF_HEAL_INFO)) {
- afr_get_heal_info (frame, this, loc, xdata);
- return 0;
- }
+ if (!local->cont.getxattr.name) {
+ op_errno = ENOMEM;
+ goto out;
+ }
- if (!strcmp (name, GF_AFR_HEAL_SBRAIN)) {
- afr_heal_splitbrain_file (frame, this, loc);
- return 0;
- }
+ if (!strncmp(name, AFR_XATTR_PREFIX, SLEN(AFR_XATTR_PREFIX))) {
+ op_errno = ENODATA;
+ goto out;
+ }
- if (!strcmp (name, GF_AFR_SBRAIN_STATUS)) {
- afr_get_split_brain_status (frame, this, loc);
- return 0;
- }
- /*
- * Special xattrs which need responses from all subvols
- */
- if (afr_is_special_xattr (name, &cbk, 0)) {
- afr_getxattr_all_subvols (this, frame, name, loc, cbk);
- return 0;
- }
+ if (cluster_handle_marker_getxattr(frame, loc, name, priv->vol_uuid,
+ afr_getxattr_unwind,
+ afr_marker_populate_args) == 0)
+ return 0;
- if (XATTR_IS_NODE_UUID (name)) {
- i = 0;
- STACK_WIND_COOKIE (frame, afr_getxattr_node_uuid_cbk,
- (void *) (long) i,
- children[i],
- children[i]->fops->getxattr,
- loc, name, xdata);
- return 0;
- }
+ ret = afr_handle_heal_xattrs(frame, this, &local->loc, name);
+ if (ret == 0)
+ return 0;
+
+ /*
+ * Heal daemons don't have IO threads ... and as a result they
+ * send this getxattr down and eventually crash :(
+ */
+ op_errno = -1;
+ GF_CHECK_XATTR_KEY_AND_GOTO(name, IO_THREADS_QUEUE_SIZE_KEY, op_errno, out);
+
+ /*
+ * Special xattrs which need responses from all subvols
+ */
+ if (afr_is_special_xattr(name, &cbk, 0)) {
+ afr_getxattr_all_subvols(this, frame, name, loc, cbk);
+ return 0;
+ }
+
+ if (XATTR_IS_NODE_UUID(name)) {
+ i = 0;
+ STACK_WIND_COOKIE(frame, afr_getxattr_node_uuid_cbk, (void *)(long)i,
+ children[i], children[i]->fops->getxattr, loc, name,
+ xdata);
+ return 0;
+ }
no_name:
- afr_read_txn (frame, this, local->loc.inode, afr_getxattr_wind,
- AFR_METADATA_TRANSACTION);
+ afr_read_txn(frame, this, local->loc.inode, afr_getxattr_wind,
+ AFR_METADATA_TRANSACTION);
- ret = 0;
+ ret = 0;
out:
- if (ret < 0)
- AFR_STACK_UNWIND (getxattr, frame, -1, op_errno, NULL, NULL);
- return 0;
+ if (ret < 0)
+ AFR_STACK_UNWIND(getxattr, frame, -1, op_errno, NULL, NULL);
+ return 0;
}
/* {{{ fgetxattr */
-
int32_t
-afr_fgetxattr_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- dict_t *dict, dict_t *xdata)
+afr_fgetxattr_cbk(call_frame_t *frame, void *cookie, xlator_t *this,
+ int32_t op_ret, int32_t op_errno, dict_t *dict, dict_t *xdata)
{
- afr_local_t *local = NULL;
+ afr_local_t *local = NULL;
- local = frame->local;
+ local = frame->local;
- if (op_ret < 0) {
- local->op_ret = -1;
- local->op_errno = op_errno;
+ if (op_ret < 0) {
+ local->op_ret = -1;
+ local->op_errno = op_errno;
- afr_read_txn_continue (frame, this, (long) cookie);
- return 0;
- }
+ afr_read_txn_continue(frame, this, (long)cookie);
+ return 0;
+ }
- if (dict)
- afr_filter_xattrs (dict);
+ if (dict)
+ afr_filter_xattrs(dict);
- AFR_STACK_UNWIND (fgetxattr, frame, op_ret, op_errno, dict, xdata);
+ AFR_STACK_UNWIND(fgetxattr, frame, op_ret, op_errno, dict, xdata);
- return 0;
+ return 0;
}
int
-afr_fgetxattr_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_fgetxattr_wind(call_frame_t *frame, xlator_t *this, int subvol)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
-
- local = frame->local;
- priv = this->private;
-
- if (subvol == -1) {
- AFR_STACK_UNWIND (fgetxattr, frame, local->op_ret,
- local->op_errno, NULL, NULL);
- return 0;
- }
-
- STACK_WIND_COOKIE (frame, afr_fgetxattr_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->fgetxattr,
- local->fd, local->cont.getxattr.name,
- local->xdata_req);
- return 0;
-}
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ local = frame->local;
+ priv = this->private;
-static void
-afr_fgetxattr_all_subvols (xlator_t *this, call_frame_t *frame,
- fop_fgetxattr_cbk_t cbk)
-{
- afr_private_t *priv = NULL;
- afr_local_t *local = NULL;
- int i = 0;
- int call_count = 0;
+ if (subvol == -1) {
+ AFR_STACK_UNWIND(fgetxattr, frame, local->op_ret, local->op_errno, NULL,
+ NULL);
+ return 0;
+ }
- priv = this->private;
+ STACK_WIND_COOKIE(frame, afr_fgetxattr_cbk, (void *)(long)subvol,
+ priv->children[subvol],
+ priv->children[subvol]->fops->fgetxattr, local->fd,
+ local->cont.getxattr.name, local->xdata_req);
+ return 0;
+}
- local = frame->local;
- //local->call_count set in afr_local_init
- call_count = local->call_count;
-
- //If up-children count is 0, afr_local_init would have failed already
- //and the call would have unwound so not handling it here.
-
- for (i = 0; i < priv->child_count; i++) {
- if (local->child_up[i]) {
- STACK_WIND_COOKIE (frame, cbk,
- (void *) (long) i,
- priv->children[i],
- priv->children[i]->fops->fgetxattr,
- local->fd, local->cont.getxattr.name,
- NULL);
- if (!--call_count)
- break;
- }
+static void
+afr_fgetxattr_all_subvols(xlator_t *this, call_frame_t *frame,
+ fop_fgetxattr_cbk_t cbk)
+{
+ afr_private_t *priv = NULL;
+ afr_local_t *local = NULL;
+ int i = 0;
+ int call_count = 0;
+
+ priv = this->private;
+
+ local = frame->local;
+ // local->call_count set in afr_local_init
+ call_count = local->call_count;
+
+ // If up-children count is 0, afr_local_init would have failed already
+ // and the call would have unwound so not handling it here.
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (local->child_up[i]) {
+ STACK_WIND_COOKIE(frame, cbk, (void *)(long)i, priv->children[i],
+ priv->children[i]->fops->fgetxattr, local->fd,
+ local->cont.getxattr.name, NULL);
+ if (!--call_count)
+ break;
}
+ }
- return;
+ return;
}
-
int
-afr_fgetxattr (call_frame_t *frame, xlator_t *this,
- fd_t *fd, const char *name, dict_t *xdata)
+afr_fgetxattr(call_frame_t *frame, xlator_t *this, fd_t *fd, const char *name,
+ dict_t *xdata)
{
- afr_local_t *local = NULL;
- int32_t op_errno = 0;
- fop_fgetxattr_cbk_t cbk = NULL;
-
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
-
- local->op = GF_FOP_FGETXATTR;
- local->fd = fd_ref (fd);
- if (name) {
- local->cont.getxattr.name = gf_strdup (name);
- if (!local->cont.getxattr.name) {
- op_errno = ENOMEM;
- goto out;
- }
- }
- if (xdata)
- local->xdata_req = dict_ref (xdata);
-
- /* pathinfo gets handled only in getxattr(), but we need to handle
- * lockinfo.
- * If we are doing fgetxattr with lockinfo as the key then we
- * collect information from all children.
- */
- if (afr_is_special_xattr (name, &cbk, 1)) {
- afr_fgetxattr_all_subvols (this, frame, cbk);
- return 0;
+ afr_local_t *local = NULL;
+ int32_t op_errno = 0;
+ fop_fgetxattr_cbk_t cbk = NULL;
+
+ AFR_ERROR_OUT_IF_FDCTX_INVALID(fd, this, op_errno, out);
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
+
+ local->op = GF_FOP_FGETXATTR;
+ local->fd = fd_ref(fd);
+ if (name) {
+ local->cont.getxattr.name = gf_strdup(name);
+ if (!local->cont.getxattr.name) {
+ op_errno = ENOMEM;
+ goto out;
}
+ }
+ if (xdata)
+ local->xdata_req = dict_ref(xdata);
+
+ /* pathinfo gets handled only in getxattr(), but we need to handle
+ * lockinfo.
+ * If we are doing fgetxattr with lockinfo as the key then we
+ * collect information from all children.
+ */
+ if (afr_is_special_xattr(name, &cbk, 1)) {
+ afr_fgetxattr_all_subvols(this, frame, cbk);
+ return 0;
+ }
- afr_fix_open (fd, this);
+ afr_fix_open(fd, this);
- afr_read_txn (frame, this, fd->inode, afr_fgetxattr_wind,
- AFR_METADATA_TRANSACTION);
+ afr_read_txn(frame, this, fd->inode, afr_fgetxattr_wind,
+ AFR_METADATA_TRANSACTION);
- return 0;
+ return 0;
out:
- AFR_STACK_UNWIND (fgetxattr, frame, -1, op_errno, NULL, NULL);
+ AFR_STACK_UNWIND(fgetxattr, frame, -1, op_errno, NULL, NULL);
- return 0;
+ return 0;
}
-
/* }}} */
/* {{{ readv */
int
-afr_readv_cbk (call_frame_t *frame, void *cookie,
- xlator_t *this, int32_t op_ret, int32_t op_errno,
- struct iovec *vector, int32_t count, struct iatt *buf,
- struct iobref *iobref, dict_t *xdata)
+afr_readv_cbk(call_frame_t *frame, void *cookie, xlator_t *this, int32_t op_ret,
+ int32_t op_errno, struct iovec *vector, int32_t count,
+ struct iatt *buf, struct iobref *iobref, dict_t *xdata)
{
- afr_local_t *local = NULL;
+ afr_local_t *local = NULL;
- local = frame->local;
+ local = frame->local;
- if (op_ret < 0) {
- local->op_ret = -1;
- local->op_errno = op_errno;
+ if (op_ret < 0) {
+ local->op_ret = -1;
+ local->op_errno = op_errno;
- afr_read_txn_continue (frame, this, (long) cookie);
- return 0;
- }
+ afr_read_txn_continue(frame, this, (long)cookie);
+ return 0;
+ }
- AFR_STACK_UNWIND (readv, frame, op_ret, op_errno,
- vector, count, buf, iobref, xdata);
- return 0;
+ AFR_STACK_UNWIND(readv, frame, op_ret, op_errno, vector, count, buf, iobref,
+ xdata);
+ return 0;
}
+int
+afr_readv_wind(call_frame_t *frame, xlator_t *this, int subvol)
+{
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+
+ local = frame->local;
+ priv = this->private;
+
+ if (subvol == -1) {
+ AFR_STACK_UNWIND(readv, frame, local->op_ret, local->op_errno, 0, 0, 0,
+ 0, 0);
+ return 0;
+ }
+
+ STACK_WIND_COOKIE(
+ frame, afr_readv_cbk, (void *)(long)subvol, priv->children[subvol],
+ priv->children[subvol]->fops->readv, local->fd, local->cont.readv.size,
+ local->cont.readv.offset, local->cont.readv.flags, local->xdata_req);
+ return 0;
+}
int
-afr_readv_wind (call_frame_t *frame, xlator_t *this, int subvol)
+afr_readv(call_frame_t *frame, xlator_t *this, fd_t *fd, size_t size,
+ off_t offset, uint32_t flags, dict_t *xdata)
{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
-
- local = frame->local;
- priv = this->private;
-
- if (subvol == -1) {
- AFR_STACK_UNWIND (readv, frame, local->op_ret, local->op_errno,
- 0, 0, 0, 0, 0);
- return 0;
- }
-
- STACK_WIND_COOKIE (frame, afr_readv_cbk, (void *) (long) subvol,
- priv->children[subvol],
- priv->children[subvol]->fops->readv,
- local->fd, local->cont.readv.size,
- local->cont.readv.offset, local->cont.readv.flags,
- local->xdata_req);
- return 0;
+ afr_local_t *local = NULL;
+ int32_t op_errno = 0;
+
+ AFR_ERROR_OUT_IF_FDCTX_INVALID(fd, this, op_errno, out);
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
+
+ local->op = GF_FOP_READ;
+ local->fd = fd_ref(fd);
+ local->cont.readv.size = size;
+ local->cont.readv.offset = offset;
+ local->cont.readv.flags = flags;
+ if (xdata)
+ local->xdata_req = dict_ref(xdata);
+
+ afr_fix_open(fd, this);
+
+ afr_read_txn(frame, this, fd->inode, afr_readv_wind, AFR_DATA_TRANSACTION);
+
+ return 0;
+out:
+ AFR_STACK_UNWIND(readv, frame, -1, op_errno, 0, 0, 0, 0, 0);
+
+ return 0;
}
+/* }}} */
+
+/* {{{ seek */
int
-afr_readv (call_frame_t *frame, xlator_t *this, fd_t *fd, size_t size,
- off_t offset, uint32_t flags, dict_t *xdata)
+afr_seek_cbk(call_frame_t *frame, void *cookie, xlator_t *this, int32_t op_ret,
+ int32_t op_errno, off_t offset, dict_t *xdata)
{
- afr_local_t * local = NULL;
- int32_t op_errno = 0;
+ afr_local_t *local = NULL;
- local = AFR_FRAME_INIT (frame, op_errno);
- if (!local)
- goto out;
+ local = frame->local;
- local->op = GF_FOP_READ;
- local->fd = fd_ref (fd);
- local->cont.readv.size = size;
- local->cont.readv.offset = offset;
- local->cont.readv.flags = flags;
- if (xdata)
- local->xdata_req = dict_ref (xdata);
+ if (op_ret < 0) {
+ local->op_ret = -1;
+ local->op_errno = op_errno;
- afr_fix_open (fd, this);
+ afr_read_txn_continue(frame, this, (long)cookie);
+ return 0;
+ }
+
+ AFR_STACK_UNWIND(seek, frame, op_ret, op_errno, offset, xdata);
+ return 0;
+}
- afr_read_txn (frame, this, fd->inode, afr_readv_wind,
- AFR_DATA_TRANSACTION);
+int
+afr_seek_wind(call_frame_t *frame, xlator_t *this, int subvol)
+{
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ local = frame->local;
+ priv = this->private;
+
+ if (subvol == -1) {
+ AFR_STACK_UNWIND(seek, frame, local->op_ret, local->op_errno, 0, NULL);
return 0;
-out:
- AFR_STACK_UNWIND(readv, frame, -1, op_errno, 0, 0, 0, 0, 0);
+ }
- return 0;
+ STACK_WIND_COOKIE(
+ frame, afr_seek_cbk, (void *)(long)subvol, priv->children[subvol],
+ priv->children[subvol]->fops->seek, local->fd, local->cont.seek.offset,
+ local->cont.seek.what, local->xdata_req);
+ return 0;
}
+int
+afr_seek(call_frame_t *frame, xlator_t *this, fd_t *fd, off_t offset,
+ gf_seek_what_t what, dict_t *xdata)
+{
+ afr_local_t *local = NULL;
+ int32_t op_errno = 0;
+
+ AFR_ERROR_OUT_IF_FDCTX_INVALID(fd, this, op_errno, out);
+ local = AFR_FRAME_INIT(frame, op_errno);
+ if (!local)
+ goto out;
+
+ local->op = GF_FOP_SEEK;
+ local->fd = fd_ref(fd);
+ local->cont.seek.offset = offset;
+ local->cont.seek.what = what;
+ if (xdata)
+ local->xdata_req = dict_ref(xdata);
+
+ afr_fix_open(fd, this);
+
+ afr_read_txn(frame, this, fd->inode, afr_seek_wind, AFR_DATA_TRANSACTION);
+
+ return 0;
+out:
+ AFR_STACK_UNWIND(seek, frame, -1, op_errno, 0, NULL);
+
+ return 0;
+}
/* }}} */
diff --git a/xlators/cluster/afr/src/afr-inode-read.h b/xlators/cluster/afr/src/afr-inode-read.h
index d128134ef2a..8c982bc7e6f 100644
--- a/xlators/cluster/afr/src/afr-inode-read.h
+++ b/xlators/cluster/afr/src/afr-inode-read.h
@@ -12,34 +12,34 @@
#define __INODE_READ_H__
int32_t
-afr_access (call_frame_t *frame, xlator_t *this,
- loc_t *loc, int32_t mask, dict_t *xdata);
+afr_access(call_frame_t *frame, xlator_t *this, loc_t *loc, int32_t mask,
+ dict_t *xdata);
int32_t
-afr_stat (call_frame_t *frame, xlator_t *this,
- loc_t *loc, dict_t *xdata);
+afr_stat(call_frame_t *frame, xlator_t *this, loc_t *loc, dict_t *xdata);
int32_t
-afr_fstat (call_frame_t *frame, xlator_t *this,
- fd_t *fd, dict_t *xdata);
+afr_fstat(call_frame_t *frame, xlator_t *this, fd_t *fd, dict_t *xdata);
int32_t
-afr_readlink (call_frame_t *frame, xlator_t *this,
- loc_t *loc, size_t size, dict_t *xdata);
+afr_readlink(call_frame_t *frame, xlator_t *this, loc_t *loc, size_t size,
+ dict_t *xdata);
int32_t
-afr_readv (call_frame_t *frame, xlator_t *this,
- fd_t *fd, size_t size, off_t offset, uint32_t flags, dict_t *xdata);
+afr_readv(call_frame_t *frame, xlator_t *this, fd_t *fd, size_t size,
+ off_t offset, uint32_t flags, dict_t *xdata);
int32_t
-afr_getxattr (call_frame_t *frame, xlator_t *this,
- loc_t *loc, const char *name, dict_t *xdata);
+afr_getxattr(call_frame_t *frame, xlator_t *this, loc_t *loc, const char *name,
+ dict_t *xdata);
int32_t
-afr_fgetxattr (call_frame_t *frame, xlator_t *this,
- fd_t *fd, const char *name, dict_t *xdata);
-
+afr_fgetxattr(call_frame_t *frame, xlator_t *this, fd_t *fd, const char *name,
+ dict_t *xdata);
int
-afr_handle_quota_size (call_frame_t *frame, xlator_t *this);
+afr_seek(call_frame_t *frame, xlator_t *this, fd_t *fd, off_t offset,
+ gf_seek_what_t what, dict_t *xdata);
+int
+afr_handle_quota_size(call_frame_t *frame, xlator_t *this);
#endif /* __INODE_READ_H__ */
diff --git a/xlators/cluster/afr/src/afr-inode-write.c b/xlators/cluster/afr/src/afr-inode-write.c
index be83781f3f1..1d6e4f3570a 100644
--- a/xlators/cluster/afr/src/afr-inode-write.c
+++ b/xlators/cluster/afr/src/afr-inode-write.c
@@ -8,706 +8,779 @@
cases as published by the Free Software Foundation.
*/
-
-#include <libgen.h>
#include <unistd.h>
-#include <fnmatch.h>
#include <sys/time.h>
#include <stdlib.h>
#include <signal.h>
-#ifndef _CONFIG_H
-#define _CONFIG_H
-#include "config.h"
-#endif
-
-#include "glusterfs.h"
+#include <glusterfs/glusterfs.h>
#include "afr.h"
-#include "dict.h"
-#include "xlator.h"
-#include "hashfn.h"
-#include "logging.h"
-#include "stack.h"
-#include "list.h"
-#include "call-stub.h"
-#include "defaults.h"
-#include "common-utils.h"
-#include "compat-errno.h"
-#include "compat.h"
+#include <glusterfs/dict.h>
+#include <glusterfs/logging.h>
+#include <glusterfs/defaults.h>
+#include <glusterfs/common-utils.h>
+#include <glusterfs/compat-errno.h>
+#include <glusterfs/compat.h>
#include "protocol-common.h"
-#include "byte-order.h"
+#include <glusterfs/byte-order.h>
#include "afr-transaction.h"
#include "afr-self-heal.h"
#include "afr-messages.h"
static void
-__afr_inode_write_finalize (call_frame_t *frame, xlator_t *this)
-{
- afr_local_t *local = NULL;
- afr_private_t *priv = NULL;
- int read_subvol = 0;
- int i = 0;
-
- local = frame->local;
- priv = this->private;
-
- if (local->inode) {
- if (local->transaction.type == AFR_METADATA_TRANSACTION)
- read_subvol = afr_metadata_subvol_get (local->inode, this,
- NULL, NULL,
- NULL);
- else
- read_subvol = afr_data_subvol_get (local->inode, this,
- NULL, NULL, NULL);
- }
-
- local->op_ret = -1;
- local->op_errno = afr_final_errno (local, priv);
-
- for (i = 0; i < priv->child_count; i++) {
- if (!local->replies[i].valid)
- continue;
- if (local->replies[i].op_ret < 0) {
- afr_inode_read_subvol_reset (local->inode, this);
- continue;
- }
-
- /* Order of checks in the compound conditional
- below is important.
-
- - Highest precedence: largest op_ret
- - Next precendence: if all op_rets are equal, read subvol
- - Least precedence: any succeeded subvol
- */
- if ((local->op_ret < local->replies[i].op_ret) ||
- ((local->op_ret == local->replies[i].op_ret) &&
- (i == read_subvol))) {
-
- local->op_ret = local->replies[i].op_ret;
- local->op_errno = local->replies[i].op_errno;
-
- local->cont.inode_wfop.prebuf =
- local->replies[i].prestat;
- local->cont.inode_wfop.postbuf =
- local->replies[i].poststat;
-
- if (local->replies[i].xdata) {
- if (local->xdata_rsp)
- dict_unref (local->xdata_rsp);
- local->xdata_rsp =
- dict_ref (local->replies[i].xdata);
- }
- }
- }
-
- afr_txn_arbitrate_fop_cbk (frame, this);
-}
+__afr_inode_write_finalize(call_frame_t *frame, xlator_t *this)
+{
+ int i = 0;
+ int ret = 0;
+ int read_subvol = 0;
+ struct iatt *stbuf = NULL;
+ afr_local_t *local = NULL;
+ afr_private_t *priv = NULL;
+ afr_read_subvol_args_t args = {
+ 0,
+ };
+
+ local = frame->local;
+ priv = this->private;
+ GF_VALIDATE_OR_GOTO(this->name, local->inode, out);
+
+ /*This code needs to stay till DHT sends fops on linked
+ * inodes*/
+ if (!inode_is_linked(local->inode)) {
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->replies[i].valid)
+ continue;
+ if (local->replies[i].op_ret == -1)
+ continue;
+ if (!gf_uuid_is_null(local->replies[i].poststat.ia_gfid)) {
+ gf_uuid_copy(args.gfid, local->replies[i].poststat.ia_gfid);
+ args.ia_type = local->replies[i].poststat.ia_type;
+ break;
+ } else {
+ ret = dict_get_bin(local->replies[i].xdata,
+ DHT_IATT_IN_XDATA_KEY, (void **)&stbuf);
+ if (ret)
+ continue;
+ gf_uuid_copy(args.gfid, stbuf->ia_gfid);
+ args.ia_type = stbuf->ia_type;
+ break;
+ }
+ }
+ }
+
+ if (local->transaction.type == AFR_METADATA_TRANSACTION) {
+ read_subvol = afr_metadata_subvol_get(local->inode, this, NULL,
+ local->readable, NULL, &args);
+ } else {
+ read_subvol = afr_data_subvol_get(local->inode, this, NULL,
+ local->readable, NULL, &args);
+ }
+
+ local->op_ret = -1;
+ local->op_errno = afr_final_errno(local, priv);
+ afr_pick_error_xdata(local, priv, local->inode, local->readable, NULL,
+ NULL);
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (!local->replies[i].valid)
+ continue;
+ if (local->replies[i].op_ret < 0)
+ continue;
+
+ /* Order of checks in the compound conditional
+ below is important.
+
+ - Highest precedence: largest op_ret
+ - Next precedence: if all op_rets are equal, read subvol
+ - Least precedence: any succeeded subvol
+ */
+ if ((local->op_ret < local->replies[i].op_ret) ||
+ ((local->op_ret == local->replies[i].op_ret) &&
+ (i == read_subvol))) {
+ local->op_ret = local->replies[i].op_ret;
+ local->op_errno = local->replies[i].op_errno;
+
+ local->cont.inode_wfop.prebuf = local->replies[i].prestat;
+ local->cont.inode_wfop.postbuf = local->replies[i].poststat;
+
+ if (local->replies[i].xdata) {
+ if (local->xdata_rsp)
+ dict_unref(local->xdata_rsp);
+ local->xdata_rsp = dict_ref(local->replies[i].xdata);
+ }
+ if (local->replies[i].xattr) {
+ if (local->xattr_rsp)
+ dict_unref(local->xattr_rsp);
+ local->xattr_rsp = dict_ref(local->replies[i].xattr);
+ }
+ }
+ }
+ afr_set_in_flight_sb_status(this, frame, local->inode);
+out