[Gluster-users] [Gluster 3.2.1] Réplication issues on a two bricks volume

[Julien Groselle]

First of all, we have milions of this lines :
[2011-08-01 10:30:30.155065] W [inode.c:1035:inode_path]
0-/storage/backup/inode: no dentry for non-root inode 392601459:
ef33731f-7c5c-435e-b300-2ffe2ab1c155
[2011-08-01 10:30:30.155767] W [inode.c:1035:inode_path]
0-/storage/backup/inode: no dentry for non-root inode 392601459:
ef33731f-7c5c-435e-b300-2ffe2ab1c155
[2011-08-01 10:30:30.156144] W [inode.c:1035:inode_path]
0-/storage/backup/inode: no dentry for non-root inode 392601459:
ef33731f-7c5c-435e-b300-2ffe2ab1c155
[2011-08-01 10:30:30.156641] W [inode.c:1035:inode_path]
0-/storage/backup/inode: no dentry for non-root inode 392601459:
ef33731f-7c5c-435e-b300-2ffe2ab1c155
[2011-08-01 10:30:30.159850] W [inode.c:1035:inode_path]
0-/storage/backup/inode: no dentry for non-root inode 392601459:
ef33731f-7c5c-435e-b300-2ffe2ab1c155
[2011-08-01 10:30:30.160271] W [inode.c:1035:inode_path]
0-/storage/backup/inode: no dentry for non-root inode 392601459:
ef33731f-7c5c-435e-b300-2ffe2ab1c155

What does it means ?

And we have many errors "No such file or directory" like this one :
[2011-08-01 10:37:23.342608] E [posix.c:1085:posix_readlink]
0-REP_SVG-posix: readlink on /Sauvegarde/
vulcano.coe.int/usrshare/20110729/terminfo/v/vt102 failed: No such file or
directory

I hope i've helped.

*Julien Groselle*


2011/8/1 Julien Groselle <julien.groselle at gmail.com>

> I'm sorry, someone of my team has flushed the logs, and restart
> rebalance...
> I will give you logs as soon as possible, when the problem will come again.
>
> You want me to create a distributed / replicated<http://www.gluster.com/community/documentation/index.php/Gluster_3.2:_Creating_Distributed_Replicated_Volumes>volume, right ?
> I had used this command to create my volume :
> # gluster volume create REP_SVG replica 2 transport tcp
> server1:/storage/backup server2:/storage/backup
>
> What is the command to create distributed / replicated volume ?
>
> Thank you very much for your quick answer !
>
> *Julien Groselle*
>
>
> 2011/8/1 Anand Avati <anand.avati at gmail.com>
>
>> Can you please provide logs for the errors you are facing? Also, rebalance
>> was not the right operation to be done in  your situation. You don't seem to
>> have a distributed setup (but a pure replicate instead) in which case
>> rebalance is really not achieving anything for you.
>>
>> Avati
>>
>> On Mon, Aug 1, 2011 at 12:30 PM, Julien Groselle <
>> julien.groselle at gmail.com> wrote:
>>
>>> Hello,
>>>
>>> I have installed GlusterFS one month ago, and replication have many
>>> issues :
>>> First of all, our infrastructure, 2 storage array of 8Tb in replication
>>> mode... We have our backups file on this arrays, so 6Tb of datas.
>>>
>>> I want replicate datas on the second storrage array, so, i use this
>>> command :
>>> # gluster volume rebalance REP_SVG migrate-data start
>>> And gluster start to replicate, in 2 weeks we had 2.6Yb of datas
>>> replicated.
>>> But now, replication fail after about one day of replication.... with
>>> many errors.
>>>
>>> So i have two questions, are there any option or command to boost
>>> replication ?
>>> We have to continue to backup our servers... so during the réplication,
>>> many files are rotated/moved/added.
>>> Is it a problem for gluster to replicatde datas during a backup session ?
>>>
>>> For now, we can't replicate any datas more ! We need help.
>>>
>>> FYI :
>>> # gluster --version
>>> glusterfs 3.2.1 built on Jun 12 2011 12:29:36
>>> Repository revision: v3.2.1
>>> Copyright (c) 2006-2010 Gluster Inc. <http://www.gluster.com>
>>> GlusterFS comes with ABSOLUTELY NO WARRANTY.
>>> You may redistribute copies of GlusterFS under the terms of the GNU
>>> Affero General Public License.
>>>
>>> # uname -a
>>> Linux toomba 2.6.32-5-amd64 #1 SMP Wed Jan 12 03:40:32 UTC 2011 x86_64
>>> GNU/Linux
>>>
>>> # cat /etc/debian_version
>>> 6.0.2
>>>
>>> # gluster peer status
>>> Number of Peers: 1
>>>
>>> Hostname: kaiserstuhl-svg.coe.int
>>> Uuid: 5b79b4bc-c8d2-48d4-bd43-37991197ab47
>>> State: Peer in Cluster (Connected)
>>>
>>> # gluster volume info all
>>>
>>> Volume Name: REP_SVG
>>> Type: Replicate
>>> Status: Started
>>> Number of Bricks: 2
>>> Transport-type: tcp
>>> Bricks:
>>> Brick1: toomba-svg.coe.int:/storage/backup
>>> Brick2: kaiserstuhl-svg.coe.int:/storage/backup
>>> Options Reconfigured:
>>> performance.write-behind-window-size: 16MB
>>> performance.cache-size: 256MB
>>> diagnostics.brick-log-level: WARNING
>>>
>>> *Julien Groselle*
>>>
>>> _______________________________________________
>>> Gluster-users mailing list
>>> Gluster-users at gluster.org
>>> http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
>>>
>>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20110801/b84f73e4/attachment.html>