glusterfs.git/xlators/cluster/afr/src/afr-dir-read.c, branch v3.0.8qa1

fixes for spurious entry self-heal in afr

2010-08-13T18:25:33+00:00

Signed-off-by: Pranith Kumar K 
Signed-off-by: Anand V. Avati 

BUG: 974 (Spurious self-heal?)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=974

cluster/afr: Don't dereference fd ptr - it might be NULL due to a failed call.

2010-05-21T07:32:19+00:00

Signed-off-by: Pavan Vilas Sondur 
Signed-off-by: Anand V. Avati 

BUG: 914 ([3.0.4] Crash in afr_opendir_cbk)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=914

cluster/afr: Cleanup fd ctx in releasedir cbk

2010-04-07T09:41:08+00:00

Signed-off-by: Vijay Bellur 
Signed-off-by: Anand V. Avati 

BUG: 805 (memory leak in afr)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=805

cluster/afr: UNWIND if opendir returns an error.

2010-03-25T12:49:15+00:00

Signed-off-by: Vijay Bellur 
Signed-off-by: Anand V. Avati 

BUG: 756 (simaltaneous rm -rf hangs the clients)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=756

cluster/afr: Fix possible NULL dereference in readdirp_cbk

2010-03-17T10:19:42+00:00

Signed-off-by: Vikas Gorur 
Signed-off-by: Anand V. Avati 

BUG: 722 (Segfault in glusterfs 3.0.3 replicate/afr_readdirp_cbk)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=722

cluster/afr: Failover readdir calls.

2010-03-04T10:04:20+00:00

This patch makes the replicate readdir call fail over to the next
subvolume if the first call fails. It takes care to ensure that
entries are not duplicated.

The failover behavior of readdir only comes into effect if
the option 'strict-readdir' is on.

Signed-off-by: Vikas Gorur 
Signed-off-by: root 
Signed-off-by: Anand V. Avati 

BUG: 453 (afr_readdir does not fail over)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=453

storage/posix: Added janitor thread.

2009-12-02T18:29:23+00:00

The janitor thread deletes all files and directories in
the "/" GF_REPLICATE_TRASH_DIR directory. This directory
is used by replicate self-heal to dump files and
directories it deletes.

This is needed because letting replicate walk the directory
tree and delete a directory and all its children is too racy.
Instead, replicate self-heal only does an atomic rename(),
and the janitor thread takes care of actually deleting them.

Signed-off-by: Vikas Gorur 
Signed-off-by: Anand V. Avati 

BUG: 227 (replicate selfheal does not remove directory with contents in it)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=227

cluster/afr: Don't do memcpy of afr_local_t in afr_local_copy.

2009-12-01T14:30:07+00:00

For the background self-heal frame's local_t, copy only
required members --- not a wholesale memcpy. The memcpy
lead to pointers being copied and then double free'd.

Signed-off-by: Vikas Gorur 
Signed-off-by: Anand V. Avati 

BUG: 320 (Improve self-heal performance)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=320

cluster/afr: Refactored the self-heal interface.

2009-11-24T14:40:12+00:00

Cleaned up the self-heal interface to callers.

Signed-off-by: Vikas Gorur 
Signed-off-by: Anand V. Avati 

BUG: 170 (Auto-heal fails on files that are open()-ed/mmap()-ed)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=170

cluster/afr: Do self-heal on reopened fds.

2009-11-24T14:40:08+00:00

This patch brings in partial support for self-heal of open
fds. The precondition is that the fd should have been opened
successfully during the initial open() (or create()), and we
assume that protocol/client has successfully reopened the fd
when the subvolume comes back up.

It works by doing an "up/down flush" (a dummy flush transaction
to do post-op wherever necessary) and then triggering
data self-heal on the file in the post-post-op hook of the
dummy flush transaction. This ensures that any writes
that come in during self-heal will wait until self-heal completes.

The up/down flush is also done when a subvolume goes down,
so that post-op is done on all subvolumes where pre-op was done.

Signed-off-by: Vikas Gorur 
Signed-off-by: Anand V. Avati 

BUG: 170 (Auto-heal fails on files that are open()-ed/mmap()-ed)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=170