glusterfs.git/xlators, branch release-2.0

fix memory leak in mkdir, mknod, symlink by freeing local

2010-05-13T19:12:23+00:00

Signed-off-by: Raghavendra Bhat 
Signed-off-by: Anand V. Avati 

BUG: 920 (memory leak in stat-prefetch)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=920

unref dict by destroying stub in server_stub_resume to avoid leak in lookup and xattrop

2010-05-11T17:10:06+00:00

Signed-off-by: Raghavendra Bhat 
Signed-off-by: Anand V. Avati 

BUG: 915 (memory leak in server protocol)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=915

Unwind lk using struct flock from a successful server

2010-05-11T17:10:02+00:00

Signed-off-by: Raghavendra Bhat 
Signed-off-by: Anand V. Avati 

BUG: 882 (directory traversing problem (client crash))
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=882

performance/read-ahead: don't set ra_file in fd->ctx unless all memebers of ra_file is initialized

2010-05-04T10:32:10+00:00

- If ptr to ra_file is set in fd->ctx even before initializing all its
    members, A race condition may occur b/w a thread executing ra_fstat,
    ra_readv etc (where all files open on the same inode are flushed) and
    the thread doing initialization of ra_file (in ra_open_cbk or
    ra_create_cbk). Because of this race-condition, flush_region might be
    called on an uninitialized ra_file, thereby causing crash.

Signed-off-by: Raghavendra G 
Signed-off-by: Anand V. Avati 

BUG: 868 (crash in ra_fstat)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=868

fix memory leak in stat-prefetch.

2010-05-04T06:40:20+00:00

Signed-off-by: Raghavendra G 
Signed-off-by: Anand V. Avati 

BUG: 878 (Memory leak in stat-prefetch)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=878

cluster/afr: Send the struct flock returned by the server to the user only in the UNWIND path.

2010-04-27T13:32:03+00:00

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

BUG: 521 (SPECFS validation fails over distribute + replicate)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=521

performance/quick-read: don't try to validate again if qr_readv is called just after validation.

2010-04-27T09:38:15+00:00

Signed-off-by: Raghavendra G 
Signed-off-by: Anand V. Avati 

BUG: 852 (QR cache-timeout 0 causes high CPU usage and app hangs)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=852

cluster/afr: Check for call_count in ENTRY_RENAME_TRANSACTION.

2010-04-20T08:51:14+00:00

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

BUG: 824 (Crash in afr rename transaction)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=824

performance/quick-read: read directly from backend for fds opened with O_DIRECT flag.

2010-04-08T10:08:50+00:00

Signed-off-by: Raghavendra G 
Signed-off-by: Anand V. Avati 

BUG: 723 (enhancements to quick read)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=723

performance/quick-read: make use of nanosecond resolution of mtime to decide whether to keep cache or not.

2010-04-08T10:08:46+00:00

Signed-off-by: Raghavendra G 
Signed-off-by: Anand V. Avati 

BUG: 801 (Direct io-mode support and related changes in caching translators.)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=801