glusterfs.git/xlators/performance, branch v3.0.7qa2

write-behind: fixes in flush

2010-07-02T16:39:23+00:00

old code was resulting in duplicate flushes and spurious dangling flush frames

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

BUG: 1042 (Use correct flock structures in lk fops)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1042

performance/io-cache: free table->mem_pool in fini.

2010-06-23T06:16:23+00:00

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

BUG: 995 (memory leak in io-cache)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=995

free local->loc structure by using SP_STACK_UNWIND instead of STACK_UNWIND

2010-06-14T11:32:14+00:00

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

BUG: 993 (memory leak-in stat-prefetch)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=993

performance/quick-read: fix the size-to-be pruned.

2010-06-03T10:31:02+00:00

- size-to-be pruned used to be a negative number because of cache-used being
    subtracted from configured cache-limit (with cache-used > cache-limit).

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

BUG: 980 (quick read - fetching from backend issue)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=980

performance/quick-read: set default cache-size value to 128MB.

2010-06-03T09:15:13+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

Revert "performance/write-behind: explicitly enforce ordering of overlapping writes."

2010-05-28T10:41:13+00:00

This reverts commit 6d9b11dba63d86c48450aa956281114962289ef5.

performance/write-behind: explicitly enforce ordering of overlapping writes.

2010-05-26T11:49:00+00:00

- If there are non-contiguous offsets (offsets which do not start where
    previous write ended), wait for completion of previous writes to server,
    before sending new ones.
  - Send flush call to server only when all writes are completed.
  - If a file is opened with O_APPEND, at any point of time a maximum only one
    write call to server should be in transit. This is to avoid reordering of
    writes in the presence of afr which can result in data corruption.
    See bug #934 for more details.

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

BUG: 934 (md5sum mismatch when files are transferred using vsftpd)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=934

performance/quick-read: implement an upper size limit for the cache.

2010-05-26T07:13:48+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

stat-prefetch: Remove checks for loc->parent

2010-05-26T06:31:41+00:00

..because loc->parent can be NULL for the root inode.
Having this check makes sp return EINVAL on perfectly valid
fops.

Signed-off-by: Shehjar Tikoo 
Signed-off-by: Anand V. Avati 

BUG: 854 (nfs server didn't start)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=854

write-behind: update default values for better small file performance

2010-05-13T19:12:35+00:00

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

BUG: 898 (small file performance enhancements)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=898