<div dir="ltr">Hi,<div><br></div><div>I had some issues with files generated from /dev/zero also. try real files or /dev/urandom :)</div><div>I don't know, if there is a real issue/bug with files generated from /dev/zero ? Devs should check them out /me thinks.</div>
</div><div class="gmail_extra"><br><br><div class="gmail_quote">2014-09-03 16:11 GMT+03:00 Milos Kozak <span dir="ltr"><<a href="mailto:milos.kozak@lejmr.com" target="_blank">milos.kozak@lejmr.com</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Hi,<br>
<br>
I am facing a quite strange problem when I do have two servers with the same configuration and the same hardware. Servers are connected by bonded 1GE. I have one volume:<br>
<br>
[root@nodef02i 103]# gluster volume info<br>
<br>
Volume Name: ph-fs-0<br>
Type: Replicate<br>
Volume ID: f8f569ea-e30c-43d0-bb94-<u></u>b2f1164a7c9a<br>
Status: Started<br>
Number of Bricks: 1 x 2 = 2<br>
Transport-type: tcp<br>
Bricks:<br>
Brick1: 10.11.100.1:/gfs/s3-sata-10k/<u></u>fs<br>
Brick2: 10.11.100.2:/gfs/s3-sata-10k/<u></u>fs<br>
Options Reconfigured:<br>
storage.owner-gid: 498<br>
storage.owner-uid: 498<br>
network.ping-timeout: 2<br>
performance.io-thread-count: 3<br>
cluster.server-quorum-type: server<br>
network.remote-dio: enable<br>
cluster.eager-lock: enable<br>
performance.stat-prefetch: off<br>
performance.io-cache: off<br>
performance.read-ahead: off<br>
performance.quick-read: off<br>
<br>
Intended to host virtual servers (KVM), the configuration is according to the gluster blog.<br>
<br>
<br>
Currently I have got only one virtual server deployed on top of this volume in order to see effects of my stress tests. During the tests I write to the volume mounted through FUSE by dd (currently on one writing at a moment):<br>
<br>
dd if=/dev/zero of=test2.img bs=1M count=20000 conv=fdatasync<br>
<br>
<br>
Test 1) I run dd on nodef02i. Load on nodef02i is max 1erl but on the nodef01i around 14erl (I do have 12threads CPU). After the write is done the load on nodef02i goes down, but the load goes up to 28erl on nodef01i. 20minutes it stays the same. In the mean time I can see:<br>
<br>
[root@nodef01i 103]# gluster volume heal ph-fs-0 info<br>
Volume ph-fs-0 is not started (Or) All the bricks are not running.<br>
Volume heal failed<br>
<br>
[root@nodef02i 103]# gluster volume heal ph-fs-0 info<br>
Brick nodef01i.czprg:/gfs/s3-sata-<u></u>10k/fs/<br>
/<u></u>3706a2cb0bb27ba5787b3c12388f4e<u></u>bb - Possibly undergoing heal<br>
/test.img - Possibly undergoing heal<br>
Number of entries: 2<br>
<br>
Brick nodef02i.czprg:/gfs/s3-sata-<u></u>10k/fs/<br>
/<u></u>3706a2cb0bb27ba5787b3c12388f4e<u></u>bb - Possibly undergoing heal<br>
/test.img - Possibly undergoing heal<br>
Number of entries: 2<br>
<br>
<br>
[root@nodef01i 103]# gluster volume status<br>
Status of volume: ph-fs-0<br>
Gluster process Port Online Pid<br>
------------------------------<u></u>------------------------------<u></u>------------------<br>
Brick 10.11.100.1:/gfs/s3-sata-10k/<u></u>fs 49152 Y 56631<br>
Brick 10.11.100.2:/gfs/s3-sata-10k/<u></u>fs 49152 Y 3372<br>
NFS Server on localhost 2049 Y 56645<br>
Self-heal Daemon on localhost N/A Y 56649<br>
NFS Server on 10.11.100.2 2049 Y 3386<br>
Self-heal Daemon on 10.11.100.2 N/A Y 3387<br>
<br>
Task Status of Volume ph-fs-0<br>
------------------------------<u></u>------------------------------<u></u>------------------<br>
There are no active volume tasks<br>
<br>
This very high load takes another 20-30minutes. During the first test I restarted glusterd service after 10minutes because everything seemed to me that the service does not work, but I could see very high load on the nodef01i.<br>
Consequently, the virtual server yields errors about problems with EXT4 filesystem - MySQL stops.<br>
<br>
<br>
<br>
When the load culminated I tried to run the same test but from opposite direction. I wrote (dd) from nodef01i - test2. Happened more or less the same. I gained extremely high load on nodef01i and minimal load on nodef02i. Outputs from heal were more or less the same..<br>
<br>
<br>
I would like to tweak this but I don´t know what I should focus on. Thank you for help.<span class="HOEnZb"><font color="#888888"><br>
<br>
Milos<br>
<br>
<br>
</font></span><br>_______________________________________________<br>
Gluster-users mailing list<br>
<a href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a><br>
<a href="http://supercolony.gluster.org/mailman/listinfo/gluster-users" target="_blank">http://supercolony.gluster.org/mailman/listinfo/gluster-users</a><br></blockquote></div><br><br clear="all"><div><br></div>-- <br>Best regards,<br>
Roman.
</div>