glusterfs.git/xlators/cluster, branch v3.4.0qa3

cluster/dht: send ACCESS call on dir to first_up_subvol if cached is down

2012-11-29T10:26:18+00:00

Change-Id: I4f518a969bbe3a11075e7c9ae10bd21bf059d5f3
BUG: 867253
Signed-off-by: shishir gowda 
Reviewed-on: http://review.gluster.org/4240
Reviewed-by: Jeff Darcy 
Tested-by: Gluster Build System

cluster/stripe: handle GF_XATTR_LOCKINFO_KEY in f(get)(set)xattr

2012-11-28T06:44:40+00:00

Change-Id: I4463006a7f54c05e757d877c56e1330fd91aec45
BUG: 808400
Signed-off-by: Raghavendra 
Reviewed-on: http://review.gluster.org/4125
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

cluster/distribute: send getxattr on LOCKINFO to only cached subvolumes.

2012-11-28T06:43:57+00:00

lk is sent to only cached subvolume. Hence there is no point in
sending LOCKINFO to other children (even in case of directories).

Change-Id: Ia20fc358dfa84cee9a52d1f613564ff6f25aa0c9
BUG: 808400
Signed-off-by: Raghavendra 
Reviewed-on: http://review.gluster.org/4123
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

cluster/afr: handle GF_XATTR_LOCKINFO_KEY appropriately.

2012-11-28T06:43:18+00:00

values from all children need to be aggregated into a dictionary
and serialized buffer of this aggregated dictionary has to be
the value of GF_XATTR_LOCKINFO_KEY in the dict sent as a result of
fgetxattr.

Change-Id: Ie877f7c637c07feaee4c44d7ef86aa967a17b7e7
BUG: 808400
Signed-off-by: Raghavendra G 
Reviewed-on: http://review.gluster.org/4121
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

replicate: don't stop checking xattrs because one was absent

2012-11-27T05:34:33+00:00

The functional issue is described by the subject line.  This patch also
addresses several efficiency/structure issues, such as...

* Calling dict_set_ptr once for each txn type, instead of once overall.

* Calling afr_index_for_transaction_type once per iteration instead of
  once per call (or better yet zero since the conversion is unnecessary).

* Implementation of inner functions in a different file than their one
  caller, creating a spurious header-file dependency.

Change-Id: I29e0df906a820533b66b9ced73e015dfe77267d2
BUG: 865825
Signed-off-by: Jeff Darcy 
Reviewed-on: http://review.gluster.org/4070
Tested-by: Gluster Build System 
Reviewed-by: Pranith Kumar Karampuri 
Reviewed-by: Anand Avati

Cluster/afr: Fix output for gluster volume heal vn info healed

2012-11-26T09:04:52+00:00

Problem:
Whenever gluster volume heal vol full command is executed, the entries
stored in the circual buffer for sh->healed are added in the dictionary
in the _crawl_post_sh_action function irrespective of whether actual self heal
(due to non-zero values in chage log) takes place or not.

Fix:
Value of key (actual-sh-done) will be set to 1 whenever self heal takes place
due to non-zero change log values and if for some FOP self heal daemon finds
that no self heal required after examining the pending matrix, the value will
be 0.

Change-Id: I11fd0b9ee76759af17c5bca6bfafbaf66bcaacbc
BUG: 863068
Signed-off-by: Venkatesh Somyajula 
Reviewed-on: http://review.gluster.org/4181
Reviewed-by: Pranith Kumar Karampuri 
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

libglusterfs: Implement float percentage

2012-11-24T07:13:39+00:00

Change-Id: Ia7ea63471f0bbd74686873f5f6f183475880f1a0
BUG: 839595
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/4162
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

cluster/afr: check transaction type for eager-lock after it is set

2012-11-21T20:03:37+00:00

Problem:
Eager locking lk-owner decision is taken before transaction
type is set. Default transaction type is DATA so all transactions
are treated as DATA transactions at the time of eager-locking
decision.

Fix:
Move the code that takes lk-owner decision after the transaction
type is set.

Test:
Checked that the transaction type is set properly in gdb at
the time of the lk-owner decision.

Change-Id: I7607c7ff4f88c7ced5416a1cddb6586cf45d88f9
BUG: 861335
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.org/4220
Tested-by: Gluster Build System 
Reviewed-by: Anand Avati

cluster/dht: dump the layout information of directories only

2012-11-19T10:58:06+00:00

testcase:
The changes are for removing gf_log from statedump related sections in dht and
using pthread_mutex_trylock in statedump sections. Changes are internal. So
tests were done by attaching gdb to the process and executing by manually
changing the values of some of the pointers.

Change-Id: I41fa76c1812b462cb76f5bbf2fd14de080e73895
BUG: 843822
Signed-off-by: Raghavendra Bhat 
Reviewed-on: http://review.gluster.org/4117
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

cluster/dht: ignore empty ->hashed_subvol during lookup

2012-10-17T07:16:05+00:00

->hashed_subvol is not valid (== NULL) when the subvolume
the entity hashes to is down. For directories, we need not
rely on ->hashed_subvol as we aggregate information from all
subvolumes. So, during lookup, NULL ->hashed_subvol is ingored
but logged.

Change-Id: I306e4e274fe29d60ff028add4a6c3bcd67b2f314
Signed-off-by: Venky Shankar 
BUG: 856459
Reviewed-on: http://review.gluster.org/4046
Reviewed-by: Anand Avati 
Tested-by: Anand Avati