[Gluster-devel] Glusterfs distributed volume stops a long time with bailing out frame type(GlusterFS 3.2.7) op(INODELK(29)

Song gluster at 163.com
Thu Jan 24 01:46:59 UTC 2013


Yes, bricks are ext4 and OS is centos6.2, kernel is
2.6.32-220.23.1.el6.x86_64

 

 

From: gluster-devel-bounces+gluster=163.com at nongnu.org
[mailto:gluster-devel-bounces+gluster=163.com at nongnu.org] On Behalf Of Joe
Julian
Sent: Wednesday, January 23, 2013 2:57 PM
To: gluster-devel at nongnu.org
Subject: Re: [Gluster-devel] Glusterfs distributed volume stops a long time
with bailing out frame type(GlusterFS 3.2.7) op(INODELK(29)

 

On 01/22/2013 07:03 PM, Song wrote:



Hi, 

 

When application access a directory of glusterfs volume, glusterfs client
spend about 1 hour, from 19:44:05 to 20:44:25.

The gluster volume is DHT + AFR, native mount to /xmail/gfs1

 

Access(/xmail/gfs1/xmail_dedup/gfs1_000/011/204/)

 

 

The following message is displayed in client log:

 

 

Are your bricks ext4?
http://joejulian.name/blog/glusterfs-bit-by-ext4-structure-change/

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-devel/attachments/20130124/3e2b9f29/attachment-0001.html>


More information about the Gluster-devel mailing list