glusterfs.git/xlators/cluster/afr, branch v3.1.1qa10 error out if the data-self-heal-window-size is less than 1 2010-11-18T13:56:01+00:00 Raghavendra Bhat raghavendrabhat@gluster.com 2010-11-18T02:32:38+00:00 001a44f7dc6cec6fb5ce555ce583af4428cc471d Signed-off-by: Raghavendra Bhat <raghavendrabhat@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 2120 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2120 
Signed-off-by: Raghavendra Bhat <raghavendrabhat@gluster.com>
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

BUG: 2120 ()
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2120
cluster/pump: send PARENT_UP to dst_child after init is successful 2010-11-18T13:55:51+00:00 Amar Tumballi amar@gluster.com 2010-11-18T06:31:01+00:00 f0cdfd03051cee8d25f03103ed467438c6479e47 Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 2122 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2122 
Signed-off-by: Amar Tumballi <amar@gluster.com>
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

BUG: 2122 ()
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2122
cluster/replicate: Fix memory leak in afr_fd_ctx_cleanup. 2010-11-15T12:03:46+00:00 Raghavendra G raghavendra@gluster.com 2010-11-15T04:02:45+00:00 7d48999c13b885d034528cfca61a8b63ade8a365 Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 1438 (memory leaks) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1438 
Signed-off-by: Raghavendra G <raghavendra@gluster.com>
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

BUG: 1438 (memory leaks)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1438
cluster/pump: Reset saved path upon pump completion 2010-11-14T18:26:44+00:00 Vijay Bellur vijay@gluster.com 2010-11-14T12:07:30+00:00 479393858a1744adf7c9f56216ca228b188a7398 Signed-off-by: Vijay Bellur <vijay@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 2084 ([3.1.1qa5] : replace-brick fails to migrate data when migration from same hostname) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2084 
Signed-off-by: Vijay Bellur <vijay@gluster.com>
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

BUG: 2084 ([3.1.1qa5] : replace-brick fails to migrate data when migration from same hostname)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2084
replicate: optimistic changelog 2010-11-09T11:07:07+00:00 Anand Avati avati@gluster.com 2010-11-09T05:27:02+00:00 6fb49f18a9bbfd1266b4773e757e459519c6719c The standard way of maintaining changelog in replicate has been to write out pending flags and to unset the pending flag post the actual operation. This new optimization kicks in only when all subvolumes are up. The optimization is that, during pre-op, no changelog is written for METADATA and ENTRY/RENAME operations. If during the operation nothing failed, no changelog is updated in post-op either. If however, something does fail during an operation, then, pending flags get written during post op pointing only towards the failed nodes. DATA transactions continue to work the way they are. If one subvolume is down, pending flags are written in pre-op changelog itself as before. The impact of this optimization is only in the case when both servers die or the client dies while the 'FOP' stage of the transaction is in progress. By nature of METADATA and ENTRY operations, detecting a mismatch later is not dependent on the presence of changelog. Changelog only determines the direction in which self-heal happens for these types of transactions. For the direction too this optimization does not have a major impact because in the cases of failure (both servers dieing or client dieing) the final state (direction of self-heal) would be arbitrary anyways as the syscall wouldn't have completed. Signed-off-by: Anand V. Avati <avati@blackhole.gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 2068 (performance enhancements) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2068 
The standard way of maintaining changelog in replicate has been to
write out pending flags and to unset the pending flag post the
actual operation.

This new optimization kicks in only when all subvolumes are up.

The optimization is that, during pre-op, no changelog is written for
METADATA and ENTRY/RENAME operations. If during the operation nothing
failed, no changelog is updated in post-op either. If however,
something does fail during an operation, then, pending flags get
written during post op pointing only towards the failed nodes.

DATA transactions continue to work the way they are.

If one subvolume is down, pending flags are written in pre-op changelog
itself as before.

The impact of this optimization is only in the case when both servers
die or the client dies while the 'FOP' stage of the transaction is
in progress. By nature of METADATA and ENTRY operations, detecting a
mismatch later is not dependent on the presence of changelog. Changelog
only determines the direction in which self-heal happens for these types
of transactions. For the direction too this optimization does not have
a major impact because in the cases of failure (both servers dieing or
client dieing) the final state (direction of self-heal) would be
arbitrary anyways as the syscall wouldn't have completed.

Signed-off-by: Anand V. Avati <avati@blackhole.gluster.com>
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

BUG: 2068 (performance enhancements)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2068
replicate: attempt re-open of files before performing openfd selfheal 2010-10-28T06:37:42+00:00 Anand Avati avati@gluster.com 2010-10-28T00:52:50+00:00 d615015ef4707d0df476547cbf7b6f83a29d804b in cases where subvolume state gets swapped between open and write opening file on the remaining subvolumes is necessary before attempting a self-heal. previously files were opened after self heal. Signed-off-by: Anand V. Avati <avati@blackhole.gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 918 (AFR write fails when subvolumes' state is swapped) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=918 
in cases where subvolume state gets swapped between open and write
opening file on the remaining subvolumes is necessary before attempting
a self-heal. previously files were opened after self heal.

Signed-off-by: Anand V. Avati <avati@blackhole.gluster.com>
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

BUG: 918 (AFR write fails when subvolumes' state is swapped)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=918
replicate: fix hang/missing frame during locking 2010-10-28T06:37:36+00:00 Anand Avati avati@gluster.com 2010-10-28T00:52:30+00:00 00b0a53bae2a5e39f197359581a3850a32970e54 nonblocking style locking would result in a missing frame when all subvolumes are down or when no subvolume on which fd was opened is up. Check for this condition and unlock gracefully Signed-off-by: Anand V. Avati <avati@blackhole.gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 918 (AFR write fails when subvolumes' state is swapped) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=918 
nonblocking style locking would result in a missing frame when all
subvolumes are down or when no subvolume on which fd was opened
is up. Check for this condition and unlock gracefully

Signed-off-by: Anand V. Avati <avati@blackhole.gluster.com>
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

BUG: 918 (AFR write fails when subvolumes' state is swapped)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=918
Change assert to GF_ASSERT 2010-10-12T09:39:01+00:00 Vijay Bellur vijay@gluster.com 2010-10-12T03:06:30+00:00 9bad9d59f0f19fe20f90c6ed80e25c7db08b3371 Signed-off-by: Vijay Bellur <vijay@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 
Signed-off-by: Vijay Bellur <vijay@gluster.com>
Signed-off-by: Vijay Bellur <vijay@dev.gluster.com>

BUG: 971 (dynamic volume management)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971
Copyright changes 2010-10-11T14:31:12+00:00 Vijay Bellur vijay@gluster.com 2010-10-11T08:38:19+00:00 2854c559340d33473750fac65aace58506951276 Signed-off-by: Vijay Bellur <vijay@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 971 (dynamic volume management) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971 
Signed-off-by: Vijay Bellur <vijay@gluster.com>
Signed-off-by: Vijay Bellur <vijay@dev.gluster.com>

BUG: 971 (dynamic volume management)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=971
mgmt/glusterd: Fix replace brick to pass src-brick and dst-brick port nos properly. 2010-10-08T13:05:10+00:00 Pavan Sondur pavan@gluster.com 2010-10-08T07:06:57+00:00 cd5c9df4b67073089a5502d5e4c2e2e7d2141e4a Fix also contains patch from shishir ng for maintaining replace-brick states in glusterd. Signed-off-by: Pavan Vilas Sondur <pavan@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1235 (Bug for all pump/migrate commits) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235 
Fix also contains patch from shishir ng for maintaining replace-brick
states in glusterd.
Signed-off-by: Pavan Vilas Sondur <pavan@gluster.com>
Signed-off-by: Vijay Bellur <vijay@dev.gluster.com>

BUG: 1235 (Bug for all pump/migrate commits)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235