glusterfs.git/xlators/features/locks/src, branch v3.8.2

posix/lock: implement meta-lock/unlock functionality

2016-06-06T06:33:53+00:00

problem : The lock state needs to be protected when rebalance is reading the
lock state on the source. Otherwise there will be locks left unmigrated.
Hence, to synchronize incoming lock requests with lock-migration, meta lock
is needed. Any new lock request will be queued if there is an active meta-lock
and with sucessful lock migration, will be unwound with EREMOTE, so that
dht module can wind the request to the correct destination.

On a successful lock migration, "pl_inode->migrated" flag is enabled. Hence,
any further request would be unwound with EREMOTE and will be redirected to
new destination.

More details can be found here:
https://github.com/gluster/glusterfs-specs/blob/master/accepted/Lock-Migration.md

design discussion:
https://www.gluster.org/pipermail/gluster-devel/2016-January/048088.html

Change-Id: Ief033d5652b5ca4ba6f499110a521cae283d6aba
BUG: 1338501
Signed-off-by: Susant Palai 
Reviewed-on: http://review.gluster.org/14462
Tested-by: Kotresh HR 
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Raghavendra G 
CentOS-regression: Gluster Build System

core: Honour mandatory lock flags during lock migration

2016-05-27T14:50:37+00:00

lk_flags from posix_lock_t structure is the primary key used to
differentiate locks as either advisory and mandatory type. During
lock migration this field is not read in getactivelk() call path.
So in order to copy the exact lock state from source to destination
it is necessary to include lk_flags within lock_migration_info_t
structure to maintain accurate state. This change also includes
minor modifications to setactivelk() call to consider lk_flags
during lock migration.

> Reviewed-on: http://review.gluster.org/14189
> Smoke: Gluster Build System 
> Reviewed-by: Susant Palai 
> Reviewed-by: Poornima G 
> NetBSD-regression: NetBSD Build System 
> CentOS-regression: Gluster Build System 
> Reviewed-by: Pranith Kumar Karampuri 

(cherry picked from commit deaf8439fc42435988aae6a7b9ab681cc0d36b09)

Change-Id: I20a7b6b6a0f3bdac5734cce8a2cd2349eceff195
BUG: 1337805
Signed-off-by: Anoop C S 
Reviewed-on: http://review.gluster.org/14457
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Pranith Kumar Karampuri

features/locks: Implement mandatory locks

2016-05-03T09:24:58+00:00

Initial change to fix/enable the mandatory locking support in GlusterFS
as per the following design:

https://review.gluster.org/#/c/12014/

Accordingly 'locks.mandatory-locking' option is available as part of this
change which will accept one among the following values:

* off
* file
* forced
* optimal

See design doc for more details

> Reviewed-on: http://review.gluster.org/9768
> Smoke: Gluster Build System 
> CentOS-regression: Gluster Build System 
> NetBSD-regression: NetBSD Build System 
> Reviewed-by: Poornima G 
> Reviewed-by: Raghavendra Talur 
> Reviewed-by: Rajesh Joseph 
> Reviewed-by: Pranith Kumar Karampuri 

(cherry picked from commit 4517bf8dd6de310950cc5a612955aa3a2fddb57e)

Change-Id: I14c489b3f8af5ebcbfa155a03f0c175e9558ac46
BUG: 1332162
Signed-off-by: Anoop C S 
Reviewed-on: http://review.gluster.org/14149
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Niels de Vos 
CentOS-regression: Gluster Build System

cluster/dht: handle EREMOTE in dht lk/flush

2016-05-02T01:05:08+00:00

With lock-migration, we need to send requests to destination
brick post migration. Once, the source brick marks the lock
structure to be already migrated, the requests will be redirected
to destination brick by dht_lk2/flush2.

Change-Id: I50b14011c5ab68c34826fb7ba7f8c8d42a68ad97
BUG: 1326085
Signed-off-by: Susant Palai 
Reviewed-on: http://review.gluster.org/13493
Smoke: Gluster Build System 
Reviewed-by: Niels de Vos 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System

posix/lock: add setactivelk () fop

2016-05-02T01:04:58+00:00

Change-Id: Ic7ad7362ac0e8bb0f8861698767c9ab7da539403
BUG: 1326085
Signed-off-by: Susant Palai 
Reviewed-on: http://review.gluster.org/14014
Smoke: Gluster Build System 
Reviewed-by: Niels de Vos 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System

posix/lock: add getactivelk () fop

2016-05-02T01:04:36+00:00

Change-Id: I99e41a80854d6f90572df755e14757099ae1236f
BUG: 1326085
Signed-off-by: Susant Palai 
Reviewed-on: http://review.gluster.org/13995
Reviewed-by: Niels de Vos 
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System

locks: fix build breakage from missing pl-messages.h

2016-04-01T14:19:41+00:00

Change-Id: I0f8af57dd96226b1e7a8a39237a82ce1cdd48be6
Signed-off-by: Jeff Darcy 
Reviewed-on: http://review.gluster.org/13876
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System

cluster/ec: Rebalance hangs during rename

2016-03-30T08:51:11+00:00

Problem:
During the rename of a particular file (ec
is holding blocking inodelk on the parent
directory), if the rename of another file
under the same directory comes. EC does not
release the lock and goes ahead and renames
the "new" file with the "already held lock".

That causes rebalance process to be blocked
on a lock which has been acquired by rename.

Solution:
While rename fop comes, ec takes blocking inodelk
on old and new parent of the file. Before releasing,
every lock held by ec, it waits for some "time" to
see if that lock can be reused by the next fop.
If within this "time" some other request comes,
it releases this lock based on condition
"lock count > 1"

To get this "lock count" for rename fop, we have
implemented "pl_rename" in feature/lock. Also,
on ec side, changed the condition to release the lock
based on the type of fop and old and new parent
directories.

Change-Id: I979dbab1185df962e8f305a6074ae1186ffe7db0
Bug: 1304988
Signed-off-by: Ashish Pandey 
Reviewed-on: http://review.gluster.org/13460
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Pranith Kumar Karampuri 
Reviewed-by: Krutika Dhananjay

features/locks: Remove unneeded function parameter

2016-03-22T19:38:00+00:00

We use list_del_init() inside __delete_lock()
to remove a lock from inode's lock list where
pl_inode_t is not required at all. This patch
removes pl_inode_t from list of parameters
required for __delete_lock().

Change-Id: Ic5701bcae231172d4fd7feda1b25752343ee81cf
BUG: 1293227
Signed-off-by: Anoop C S 
Reviewed-on: http://review.gluster.org/13033
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Jeff Darcy

afr: misc performance improvements

2016-03-08T14:13:46+00:00

1. In afr_getxattr_cbk, consider the errno value before blindly
launching an inode refresh and a subsequent retry on other children.

2. We want to accuse small files only when we know for sure that there is no
IO happening on that inode. Otherwise, the ia_sizes obtained in the
post-inode-refresh replies may mismatch due to a race between
inode-refresh and ongoing writes, causing spurious heal launches.

Change-Id: Ife180f4fa5e584808c1077aacdc2423897675d33
BUG: 1309462
Signed-off-by: Ravishankar N 
Reviewed-on: http://review.gluster.org/13595
Smoke: Gluster Build System 
Tested-by: Pranith Kumar Karampuri 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Krutika Dhananjay 
Reviewed-by: Pranith Kumar Karampuri