glusterfs-afrv1.git, branch v3.1.2

nfs3: Handle root resolution failures

2011-01-13T17:46:51+00:00

..to prevent a second reply to the client which results in accessing
a call state structure that gets freed on the first reply.

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

BUG: 2286 ([glusterfs 3.1.2qa3]: Crash due to corruption in gf_dirent_free)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2286

performance/quick-read: Fix unwinding of same frame twice when qr_loc_fill fails.

2011-01-12T07:58:42+00:00

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

BUG: 2274 (crash in fd_unref)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2274

mgmt/Glusterd: make nfs.mem-factor settable through CLI

2011-01-12T07:58:37+00:00

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

BUG: 2277 (Regression in Gluster NFS re-read performance)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2277

nfs: Introduce tunable for memory consumption

2011-01-12T07:58:33+00:00

NFS has used a common define called the mem-factor to determine
how much memory is allocated for the following items:

o inode table
o local structures used by nfs for storing fop state
o local structures used by nfs3 for storing nfs op state

These are all allocated through the mem-pool. The factor is multiplied by
a multiple that is specific to each data structure. For eg.

define GF_NFS_CONCURRENT_OPS_MULT     15
define GF_NFS_INODE_LRU_MULT          6000

The first value is used for allocating a mem-pool for storing
state for each fop or nfs op that is currently being handled. Knowing that linux
allows at most 128 in-flight requests, this multiple combined with the default
mem-factor of 15 gives us 225 slots in the mem-pool for the local structures.

Similarly, 6000*15 gives us a space of 90k inodes in the lru.

That means, increasing the common mem-factor will allow increasing the perf
under some conditions. This patch introduces the mem-factor as a configurable
option.

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

BUG: 2277 (Regression in Gluster NFS re-read performance)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2277

exit if the key or the value is null while retrieving the peer information in glusterd_restore

2011-01-12T07:58:27+00:00

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

BUG: 2271 ([glusterfs-3.1.2qa3]: entry->hostname in glusterd_friend_find_by_hostname is 0x0)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2271

Add corresponding va_end.

2011-01-08T01:58:49+00:00

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

BUG: 2247 (Add corresponding va_end)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2247

cluster/replicate: update st_nlink count of stat sent to application after completion of entry-self-heal.

2011-01-08T01:58:44+00:00

- certain applications like 'find' use st_nlink count to optimize searches.
    Hence an incorrect hard link count can result in non-healing of some of
    the newly created subdirectories.

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

BUG: 2187 (Self heal errors)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2187

nfs3: Ignore requests for volumes without a single CHILD-UP

2011-01-08T01:43:56+00:00

NFS ignores the requests for subvolumes on which child-up has never been
received.

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

BUG: 2200 (cp dies with "Invalid argument" after failover)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2200

check the value of op_ret pointer not the address

2011-01-08T01:43:50+00:00

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

BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221

storage/posix: in opendir, allocate proper size for fd ctx pointer

2011-01-08T01:43:45+00:00

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

BUG: 2280 (wrong size allocated for posix_fd in posix.c:posix_opendir())
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2280