glusterfs.git/xlators/cluster/afr/src/afr-common.c, branch v3.2.1qa1

cluster/afr: Send the first child up/down after all its children notify

2011-05-31T16:12:17+00:00

Signed-off-by: Pranith Kumar K 
Signed-off-by: Anand Avati 

BUG: 2870 (Inconsistent xattr values when creating bricks)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2870

removed reference to GF_LOG_NORMAL

2011-04-07T18:40:25+00:00

instead used GF_LOG_INFO, which is more standard log level.

Signed-off-by: Amar Tumballi 
Signed-off-by: Vijay Bellur 

BUG: 2669 (RuntimeError: cannot recognize log level "normal")
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2669

log gfid mismatches for the same file in cluster xlator lookup

2011-04-06T17:50:22+00:00

This can help in pin pointing some of the issues resulted in gfid
mismatch for the same file, which is harder to find through basic
debugging/logging of current codebase.

Signed-off-by: Amar Tumballi 
Signed-off-by: Vijay Bellur 

BUG: 2346 ()
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346

cluster/afr: log enhancement - part 3

2011-04-01T13:08:30+00:00

Signed-off-by: Amar Tumballi 
Signed-off-by: Vijay Bellur 

BUG: 2346 (Log message enhancements in GlusterFS - phase 1)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346

cluster/afr: white-space cleanup - part 2

2011-03-31T11:19:47+00:00

Signed-off-by: Amar Tumballi 
Signed-off-by: Vijay Bellur 

BUG: 2346 (Log message enhancements in GlusterFS - phase 1)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346

core: have framework for GF_EVENT_CHILD_MODIFIED notifcation event

2011-02-22T10:11:53+00:00

If anything changes anywhere in the graph, all xlators know that
something has changed. Previously dht and afr would mask certain
events from propagating up. Now they forward GF_EVENT_CHILD_MODIFIED
event in those situations

Signed-off-by: Anand Avati 
Signed-off-by: Anand V. Avati 

BUG: 2450 (scalability enhancements)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2450

replicate: set read-child to the subvolume which replied first (fastest)

2011-02-22T10:11:20+00:00

In the old logic read-child was set to the last subvolume which replied.
Now it is updated to the first subvolume. This way we can ensure that local
servers are preferred for reads _most_ of the times.

Signed-off-by: Anand Avati 
Signed-off-by: Anand V. Avati 

BUG: 1172 (ls -lh on NFS mount of 2-mirror replicate gives incorrect file size)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1172

afr_lookup_done: Propogate the same inode number as sent in first lookup

2010-12-29T18:20:32+00:00

If only one subvolume was up, we used to unwind, without updating the ino
Signed-off-by: shishir gowda 
Signed-off-by: Anand V. Avati 

BUG: 2144 (errors removing directories when one subvolume is down)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2144

set the return value to -1 intitially which may be returned as success in validate_or_goto

2010-12-13T04:07:33+00:00

Signed-off-by: Raghavendra Bhat 
Signed-off-by: Anand V. Avati 

BUG: 1235 (Bug for all pump/migrate commits)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1235

replicate: propagate CHILD_DOWN upwards properly

2010-12-08T16:45:31+00:00

During initialization if one subvolume returns CHILD_DOWN, then
do not consider the other subvolume as down if we still haven't
heard from it yet

This causes DHT (on top) to prematurely (and wrongly) send
CHILD_UP/DOWN upwards

Signed-off-by: Anand V. Avati 
Signed-off-by: Anand V. Avati 

BUG: 2200 (cp dies with "Invalid argument" after failover)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2200