<div dir="ltr">Hello,<div><br></div><div>I also experience high memory usage on my gluster clients. Sample :</div><div><img src="cid:ii_152348a663d36902" alt="Images intégrées 1" width="562" height="57"><br></div><div><br></div><div>Can I help in testing/debugging ?</div><div><br></div><div><br></div></div><div class="gmail_extra"><br clear="all"><div><div class="gmail_signature">Cordialement,<br>Mathieu CHATEAU<br><a href="http://www.lotp.fr" target="_blank">http://www.lotp.fr</a></div></div>
<br><div class="gmail_quote">2016-01-12 7:24 GMT+01:00 Soumya Koduri <span dir="ltr"><<a href="mailto:skoduri@redhat.com" target="_blank">skoduri@redhat.com</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class=""><br>
<br>
On 01/11/2016 05:11 PM, Oleksandr Natalenko wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Brief test shows that Ganesha stopped leaking and crashing, so it seems<br>
to be good for me.<br>
<br>
</blockquote></span>
Thanks for checking.<span class=""><br>
<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Nevertheless, back to my original question: what about FUSE client? It<br>
is still leaking despite all the fixes applied. Should it be considered<br>
another issue?<br>
</blockquote>
<br></span>
For fuse client, I tried vfs drop_caches as suggested by Vijay in an earlier mail. Though all the inodes get purged, I still doesn't see much difference in the memory footprint drop. Need to investigate what else is consuming so much memory here.<br>
<br>
Thanks,<br>
Soumya<div class="HOEnZb"><div class="h5"><br>
<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<br>
11.01.2016 12:26, Soumya Koduri написав:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
I have made changes to fix the lookup leak in a different way (as<br>
discussed with Pranith) and uploaded them in the latest patch set #4<br>
- <a href="http://review.gluster.org/#/c/13096/" rel="noreferrer" target="_blank">http://review.gluster.org/#/c/13096/</a><br>
<br>
Please check if it resolves the mem leak and hopefully doesn't result<br>
in any assertion :)<br>
<br>
Thanks,<br>
Soumya<br>
<br>
On 01/08/2016 05:04 PM, Soumya Koduri wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
I could reproduce while testing deep directories with in the mount<br>
point. I root caus'ed the issue & had discussion with Pranith to<br>
understand the purpose and recommended way of taking nlookup on inodes.<br>
<br>
I shall make changes to my existing fix and post the patch soon.<br>
Thanks for your patience!<br>
<br>
-Soumya<br>
<br>
On 01/07/2016 07:34 PM, Oleksandr Natalenko wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
OK, I've patched GlusterFS v3.7.6 with 43570a01 and 5cffb56b (the most<br>
recent<br>
revisions) and NFS-Ganesha v2.3.0 with 8685abfc (most recent revision<br>
too).<br>
<br>
On traversing GlusterFS volume with many files in one folder via NFS<br>
mount I<br>
get an assertion:<br>
<br>
===<br>
ganesha.nfsd: inode.c:716: __inode_forget: Assertion `inode->nlookup >=<br>
nlookup' failed.<br>
===<br>
<br>
I used GDB on NFS-Ganesha process to get appropriate stacktraces:<br>
<br>
1. short stacktrace of failed thread:<br>
<br>
<a href="https://gist.github.com/7f63bb99c530d26ded18" rel="noreferrer" target="_blank">https://gist.github.com/7f63bb99c530d26ded18</a><br>
<br>
2. full stacktrace of failed thread:<br>
<br>
<a href="https://gist.github.com/d9bc7bc8f6a0bbff9e86" rel="noreferrer" target="_blank">https://gist.github.com/d9bc7bc8f6a0bbff9e86</a><br>
<br>
3. short stacktrace of all threads:<br>
<br>
<a href="https://gist.github.com/f31da7725306854c719f" rel="noreferrer" target="_blank">https://gist.github.com/f31da7725306854c719f</a><br>
<br>
4. full stacktrace of all threads:<br>
<br>
<a href="https://gist.github.com/65cbc562b01211ea5612" rel="noreferrer" target="_blank">https://gist.github.com/65cbc562b01211ea5612</a><br>
<br>
GlusterFS volume configuration:<br>
<br>
<a href="https://gist.github.com/30f0129d16e25d4a5a52" rel="noreferrer" target="_blank">https://gist.github.com/30f0129d16e25d4a5a52</a><br>
<br>
ganesha.conf:<br>
<br>
<a href="https://gist.github.com/9b5e59b8d6d8cb84c85d" rel="noreferrer" target="_blank">https://gist.github.com/9b5e59b8d6d8cb84c85d</a><br>
<br>
How I mount NFS share:<br>
<br>
===<br>
mount -t nfs4 127.0.0.1:/mail_boxes /mnt/tmp -o<br>
defaults,_netdev,minorversion=2,noac,noacl,lookupcache=none,timeo=100<br>
===<br>
<br>
On четвер, 7 січня 2016 р. 12:06:42 EET Soumya Koduri wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Entries_HWMark = 500;<br>
</blockquote>
<br>
<br>
</blockquote>
_______________________________________________<br>
Gluster-users mailing list<br>
<a href="mailto:Gluster-users@gluster.org" target="_blank">Gluster-users@gluster.org</a><br>
<a href="http://www.gluster.org/mailman/listinfo/gluster-users" rel="noreferrer" target="_blank">http://www.gluster.org/mailman/listinfo/gluster-users</a><br>
</blockquote></blockquote></blockquote>
_______________________________________________<br>
Gluster-users mailing list<br>
<a href="mailto:Gluster-users@gluster.org" target="_blank">Gluster-users@gluster.org</a><br>
<a href="http://www.gluster.org/mailman/listinfo/gluster-users" rel="noreferrer" target="_blank">http://www.gluster.org/mailman/listinfo/gluster-users</a></div></div></blockquote></div><br></div>