Re: one node change uuid in the night

[Pierre Léonard <pleonard@xxxxxxxxxxxx>]

Title: Signature electronique

Hi  Atin and all,

On 04/09/2015 06:21 PM, Pierre Léonard wrote:

Hi all,

I have a 14 node cluster with two volume on replica 7 one strip 7.
This night the node 10 add a peers files and stop.
I have corrected with the data in glusterd.info and suppress the bad peers file.

Could you clarify what steps did you perform here. Also could you try to
start glusterd with -LDEBUG and share the glusterd log file with us.
Also do you see any delta in glusterd.info file between node 10 and the
other nodes?

~Atin

Ok I will  describe all the fact of the week concerning that glusterfs volumes :

• First I bond the two ethernet port. The glusterfs volume continue to work, the IP addresse and name don't change ;
• then in the night from wednesday to thursday a lot of computing run on the cluster and at Two hours some gluster node failed ;
• thursday, I found a new peers file for the node 10, I suppress it and restore all the peers files;
• the test I do that morning is of the node 10 alone, the other was not up ;

The log file is join and compressed.

I hope that it wil help you. At the end I see an error concerning a "volfile".

Many thank's.

sincerely.

--

Pierre Léonard

Senior IT Manager

MetaGenoPolis

Pierre.Leonard@xxxxxxxxxxxx

Tél. : +33 (0)1 34 65 29 78

Centre de recherche INRA

Domaine de Vilvert – Bât. 325 R+1

78 352 Jouy-en-Josas CEDEX

France

www.mgps.eu

<<attachment: etc-glusterfs-glusterd.vol.zip>>

_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
http://www.gluster.org/mailman/listinfo/gluster-users