glusterfs.git/xlators/storage/posix/src, branch v3.3.0qa30

storage/posix: don't allow rmdir()/lookup() on HIDDEN_DIRECTORY

2012-03-14T10:21:03+00:00

so that we won't even have a GFID set on the GFID dir itself.

Change-Id: I65be7d675a308f51f4c62a86499341412b20c47f
Signed-off-by: Amar Tumballi 
BUG: 802726
Reviewed-on: http://review.gluster.com/2936
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

posix_fill_readdir: Using strcmp to compare GF_HIDDEN_PATH with entry->d_name instead of strncmp.

2012-03-12T06:00:05+00:00

Change-Id: I29b6fc81213e52a697ed96559c3216c5512799ed
BUG: 802005
Signed-off-by: M S Vishwanath Bhat 
Reviewed-on: http://review.gluster.com/2910
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi

glusterd/rebalance: Bring in support for parallel rebalance

2012-03-08T05:14:27+00:00

This patch, enables rebalance processes to be started on all
nodes where the volume is spread across (1 process per node)

node-uuid xattr identifies which node takes ownership of the
task to migrate the file. The model employed is push (src pushes
to dst)

Change-Id: Ieacd46a6216cf6ded841bbaebd10cfaea51c16d6
BUG: 763844
Signed-off-by: shishirng 
Reviewed-on: http://review.gluster.com/2873
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi 
Reviewed-by: Vijay Bellur

storage/posix: In lookup check for buf->gfid being NULL

2012-02-29T10:09:59+00:00

There are few cases where create and lookup race.
Lookup ends up getting a valid struct iatt, but with no gfid set.
We need to check for gfid being 0, and handle it as an error.

Signed-off-by: shishir gowda 
Change-Id: I36ae1978b325aff964cbc3b24730c1e993666267
BUG: 797167
Reviewed-on: http://review.gluster.com/2832
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi 
Reviewed-by: Vijay Bellur

glusterfsd: unref the dict and free the memory to avoid memleak

2012-02-27T10:17:34+00:00

Change-Id: Ib7a1f8cbab039fefb73dc35560a035d5688b0e32
BUG: 796186
Signed-off-by: Raghavendra Bhat 
Reviewed-on: http://review.gluster.com/2808
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi 
Reviewed-by: Vijay Bellur

Introduce new extended attribute: node-uuid

2012-02-23T07:19:44+00:00

Request for trusted.glusterfs.node-uuid returns pathinfo
like string but containing the UUID of glusterd instead
of the backend path for the requested file. This info
is benificial for tasks like parallel rebalance that will
make use of the UUID for data locality.

Change-Id: I766a09cc4a5f63aebd11c73107924a1b29242dcf
BUG: 772610
Signed-off-by: Venky Shankar 
Reviewed-on: http://review.gluster.com/2614
Tested-by: Gluster Build System 
Reviewed-by: Shishir Gowda 
Reviewed-by: Vijay Bellur

storage/posix: Add xattr for gfid2path

2012-02-20T18:05:38+00:00

Change-Id: I1fe987d255bf50e8433043749b482b67554a0ac3
BUG: 763820
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.com/2774
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

cluster/dht: Support for hardlink rebalance when decommissioning

2012-02-19T12:47:50+00:00

The support for hardlink rebalance is only available for decommissioning
of a node. this can be triggered in two ways
1. remove-brick start
2. if decommission node value is set in vol file, then a normal rebalance
   command

The way we handle it is-
if (nlink > 1)
do
       * if src file doesnt have linkto xattr
                * mark src's linkto to the dst
       * else
                * perform a link on the dst
                * do a look up
                * if nlinks = dst.nlinks
                        * migrate data
                * else
                        * continue crawling
done
Signed-off-by: shishir gowda 
Change-Id: If43b5524b872fd1413e9f7aa7f436cb244e30d8d
BUG: 763844
Reviewed-on: http://review.gluster.com/2737
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi

posix: handle some internal behavior in posix_mknod()

2012-02-17T06:48:57+00:00

assume a case of link() systemcall, which is handled in distribute by
creating a 'linkfile' in hashed subvolume, if the 'oldloc' is present
in different subvolume. we have same 'gfid' for the linkfile as that
of file for consistency. Now, a file with multiple hardlinks, we may
end up with 'hardlinked' linkfiles. dht create linkfile using 'mknod()'
fop, and as now posix_mknod() is not equipped to handle this situation.

this patch fixes the situation by looking at the 'internal' key set in
the dictionary to differentiate the call which originates from inside
with regular system calls.

Change-Id: Ibff7c31f8e0c8bdae035c705c93a295f080ff985
BUG: 763844
Signed-off-by: Amar Tumballi 
Reviewed-on: http://review.gluster.com/2755
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

storage/posix: reset op_ret to -1 after call to MAKE_INODE_HANDLE

2012-02-17T05:56:30+00:00

MAKE_INODE_HANDLE uses op_ret. We do not reset it to -1, and in few
instances we jump to label out, where we unwind with op_ret.

Change-Id: Iac4d9f250f5253b3ce0cd91cc385168247efd4a8
BUG: 788998
Signed-off-by: shishir gowda 
Reviewed-on: http://review.gluster.com/2759
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi