glusterfs.git/xlators, branch v3.4.0beta3

cluster/afr: Perform delayed changelog wakeups for anon fd

2013-06-10T20:04:21+00:00

Problem:
Nfs xlator never does open on a file for performing writes,
afr does not perform changelog wakeup for this fd so operations
which do metadata operations as soon as the data operations are
completed perceive a delay od 'post-op-delay-secs'.

Fix:
Perform changelog wakeup on anon-fd if the fd with same pid is
not present in inode-list.

Note:
This approach is a short-term fix. A proper fix needs a new domain
for taking metadata locks so that data/metadata locks don't compete
with each other.

BUG: 966018
Change-Id: Ia9188a253e7943801b665e1b9205e2f551952d87
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/5067
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

Fix crash in dht_migration_complete_check_task because of NULL fd

2013-06-08T21:56:08+00:00

This is a backport of Ia5a5d40bcea7bfb320ef7096af1e035b8847d4ff

BUG: 960055
Change-Id: Ibf3547a775d7ca2f3a097c880cdf38ffafb322da
Signed-off-by: Emmanuel Dreyfus 
Reviewed-on: http://review.gluster.org/5139
Tested-by: Gluster Build System 
Reviewed-by: Jeff Darcy

dht,posix: support for case discovery

2013-06-08T21:51:22+00:00

This is support for discovering a filename in a given directory
which has a case insensitive match of a given name. It is implemented
as a virtual extended attribute on the directory where the required
filename is specified in the key.

E.g:

  sh# getfattr -e "text" -n user.glusterfs.get_real_filename:FiLe-B /mnt/samba/patchy
  getfattr: Removing leading '/' from absolute path names
  # file: mnt/samba/patchy
  user.glusterfs.get_real_filename:FiLe-B="file-b"

In reality, there can be multiple "answers" as the backend filesystem is
case sensitive and there can be multiple files which can strcasecamp()
successfully. In this case we pick the first matched file from the first
responding server.

If a matching file does not exist, we return ENOENT (and NOT ENODATA).
This way the caller can differentiate between "unsupported" glusterfs
API and file not existing.

This API is used by Samba VFS to perform efficient discovery of the real
filename without doing a full scan at the Samba level.

Change-Id: I53054c4067cba69e585fd0bbce004495bc6e39e8
BUG: 953694
Signed-off-by: Anand Avati 
Reviewed-on: http://review.gluster.org/5163
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

gfapi: link inodes in relevant entry FOPs

2013-06-08T21:51:04+00:00

Do not let inode linking to happen only in lookup(). While
that works, it is inefficient.

Change-Id: I51bbfb6255ec4324ab17ff00566375f49d120c06
BUG: 953694
Signed-off-by: Anand Avati 
Reviewed-on: http://review.gluster.org/5162
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

md-cache: support negative xattr entries

2013-06-08T21:50:34+00:00

Add support for negative xattr caching. For this, we need
to fetch xattrs in every opportunity (including readdirplus)
in order to treat missing key in cached dict as negative entry.

This is crucial to detect missing ACL xattrs in Samba workload.

Change-Id: I918a2ef4ab804724256f7546b15e808332ed518d
BUG: 953694
Signed-off-by: Anand Avati 
Reviewed-on: http://review.gluster.org/5160
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

quick-read: prune cache on write/[f]truncate

2013-06-08T21:49:59+00:00

Cache needs to be pruned on write and [f]truncate. The lack of this
is causing Samba ping-pong test to return wierd 'data increment' values
during startup.

Change-Id: I9cd6a839bcd02de738d78638211b78f382f58e0a
BUG: 953694
Signed-off-by: Anand Avati 
Reviewed-on: http://review.gluster.org/5158
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

posix-acl: fetch ACLs in readdirplus

2013-06-08T21:49:27+00:00

Not fetching ACLs in readdirplus can potentially result in spurious
wrong ACL decisions (which magically go away on a lookup() which
populates the ACLs)

Change-Id: Ided38b4d868fab482b477ce51b4878289ef9eed0
BUG: 953694
Signed-off-by: Anand Avati 
Reviewed-on: http://review.gluster.org/5156
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

cluster/afr: Avoid order mismatch in blocking entrylks

2013-06-06T18:53:39+00:00

Problem:
When taking blocking entrylks, afr orders the entrylks based on
uuid_compare of gfids of parent dirs, if they are equal then it orders
them based on the basenames. While this approach works fine, the
implementation assumes loc->gfids to be populated at the time of
the comparison, but loc may have gfid in loc->inode->gfid instead
of loc->gfid which was leading to order mismatches and dead-locks.

Fix:
Implemented loc_gfid which gives gfid by checking both loc->gfid,
loc->inode->gfid. Used this for ordering the blocking entrylks.

Change-Id: I2743fcaff3d670fbeb6b8e0a496f106a3585dde1
BUG: 965987
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/5063
Reviewed-by: Krishnan Parthasarathi 
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

glusterd-volgen: Improve volume op-versions calculation

2013-06-05T12:27:10+00:00

Backport of patch on master branch, under review at
        http://review.gluster.org/4952

Volume op-versions calculations now take into account if an option,
 a. enables/disables an xlator, or
 b. is a boolean option.

This prevents op-versions from being updated when a feature is disabled.

BUG: 954256
Change-Id: Ic68032b9e55a3f0191f8fc3ecd6b5ced385ad943
Signed-off-by: Kaushal M 
Reviewed-on: http://review.gluster.org/5094
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

glusterd-volgen: Enable open-behind based on op-version

2013-06-05T12:26:55+00:00

Backport of patch on master branch, under review at
        http://review.gluster.org/4866

This patch enables the open-behind by default only when the op-version
allows it. Also the volume op-version calculations take account of this
enablement.

BUG: 954256
Change-Id: Ie739bc23ba90ec2f009feecef28187912a37487c
Signed-off-by: Kaushal M 
Reviewed-on: http://review.gluster.org/5095
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur