glusterfs-afrv1.git, branch v3.3.0qa22

features/marker: copy the gfid to loc from oplocal->loc.inode

2012-02-15T06:20:07+00:00

Change-Id: I8cfb70c163a3c4a0bd682678f71b38b5bae20ab4
BUG: 790393
Signed-off-by: Raghavendra Bhat 
Reviewed-on: http://review.gluster.com/2750
Reviewed-by: Vijay Bellur 
Tested-by: Gluster Build System

mgmt/glusterd: changes to run nfs server and self-heal daemon with valgrind

2012-02-15T03:18:25+00:00

Currently glusterd can start only the brick processes in the valgrind mode.
This patch ensures that nfs server and self-heal daemon are also started
with valgrind along with the bricks.

Change-Id: I3136deb58d54075627cdd204002eb26fdfdde462
BUG: 773600
Signed-off-by: Raghavendra Bhat 
Reviewed-on: http://review.gluster.com/2638
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi 
Reviewed-by: Vijay Bellur

nfs: avoid logging invalid fdctx in case of anonymous fds

2012-02-14T18:25:30+00:00

if get_fd_ctx fails (as in case of anonymous fds), overwhelming
amount of entries are seen in the nfs log, causing dd and other
heavy i/o operations to become unresponsive. this patch logs an
invalid fdctx only if it is not an anonymous fd.

Change-Id: I4e917d150d6a053af77d47a94a2f1c2633acadb5
BUG: 787365
Signed-off-by: Rajesh Amaravathi 
Reviewed-on: http://review.gluster.com/2747
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi

Allows Successful log rotation when no bricks are specified.

2012-02-14T18:24:24+00:00

log rotate must happen for all the bricks if no specific
brick path is given as an argument for the command.

Change-Id: I39e55883fd301bedffae996384a8284119011951
BUG: 765578
Signed-off-by: Rahul C S 
Reviewed-on: http://review.gluster.com/2748
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi

glusterd: Fail volume 'modify' operations when rb is ongoing

2012-02-14T18:22:09+00:00

* add-brick, stop-volume, remove-brick are the operations that are explicitly
 'failed' when attempted while replace-brick is in progress.
* we attach the volume-id to the dst_brick volfile ensuring that the replace-brick
  operation holds 'claim' on it.

Change-Id: If60b2af566ca940b2add600b473c99730e06ab47
BUG: 765470
Signed-off-by: Krishnan Parthasarathi 
Reviewed-on: http://review.gluster.com/2740
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi 
Reviewed-by: Vijay Bellur

protocol xdr: remove 'path<>'

2012-02-14T12:34:06+00:00

client was sending 'path' on wire, which gets ignored on server
side, and also doesn't get freed up, which causes memory leak.

also with not having path on wire, the xdr size on wire most of the
time can remain constant, which helps in allocating RDMA buffers.

Change-Id: Ie0d36a670be60b02fd1e925c6f977b1a71def5cd
BUG: 790298
Signed-off-by: Amar Tumballi 
Reviewed-on: http://review.gluster.com/2744
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

rpc : fix the leak with glusterfs v2 auth structure conversion

2012-02-14T12:27:29+00:00

both 'groups' and 'lkowner' were getting leaked after the conversion

Change-Id: Iab7cc1cf5afdad18ead9f33e6ccf98e0a934a09a
BUG: 790298
Signed-off-by: Amar Tumballi 
Reviewed-on: http://review.gluster.com/2746
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

locks: Added a getxattr interface to clear locks on a given inode.

2012-02-14T10:48:59+00:00

getxattr returns a summary of no. of inodelks/entrylks cleared.
cmd_structure: trusted.glusterfs.clrlk.t.k[.{range|basename}]
where,
type = "inode"| "entry"| "posix"
kind = "granted"| "blocked" | "all"
range = off,a-b, where a, b = 'start', 'len' from offset 'off'

Change-Id: I8a771530531030a9d4268643bc6823786ccb51f2
BUG: 789858
Signed-off-by: Krishnan Parthasarathi 
Reviewed-on: http://review.gluster.com/2551
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

features/quota: fix a crash in fgetxattr() by checking for NULL arg

2012-02-14T10:43:26+00:00

'name' can be NULL in getxattr() as it is overloaded in glusterfs
code to support listxattr() too.

Change-Id: I70ccee027828e9b2b08da770f513c4edc5c7a46b
BUG: 772601
Signed-off-by: Amar Tumballi 
Reviewed-on: http://review.gluster.com/2743
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

cluster/stripe: Support for NFS anonymous fd's

2012-02-14T09:57:47+00:00

Moving storing of all ctx info to inode ctx. anonymous fd's do not
have the ctx stored in them, hence readv/writev can fail.
Open call does not need the additional lookup calls, as all the
required fctx info will be available in the inode ctx populated
any one of the following create/mknod/lookup

Change-Id: I94ca69ff821d46ac8ed3ba1b87b97a3d1c736566
BUG: 786095
Signed-off-by: shishir gowda 
Reviewed-on: http://review.gluster.com/2726
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi