<div dir="ltr">Hello,<div><br></div><div>As you are in replicate mode, all write will be send synchronously to all bricks, and in your case to a single hdd.</div><div><br></div><div>Writes: you are going to have same perf as 1 single hdd (best case possible, you will have less)</div><div>read: all brick will be queried for metadata, one will send the file (if I am correct)</div><div><br></div><div>For sure I wouldn't go for 60+ users with this setup, maybe except if these hdd are ssd</div><div><br></div><div>just my 2 cents</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">2015-08-03 23:29 GMT+02:00 Florian Oppermann <span dir="ltr"><<a href="mailto:gluster-users@flopwelt.de" target="_blank">gluster-users@flopwelt.de</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">> If starting setup right now, you should start with current version (3.7.X)<br>
<br>
</span>Is 3.7 stable? I have 60+ potential users and dont want to risk too<br>
much. ;-)<br>
<br>
> Filesystem<br>
<br>
XFS partitions on all bricks<br>
<br>
> network type (lan, VM...)<br>
<br>
Gigabit LAN<br>
<span class=""><br>
> where is client (same lan?)<br>
<br>
</span>Yep<br>
<br>
> MTU<br>
<br>
1500<br>
<span class=""><br>
> storage (raid, # of disks...)<br>
<br>
</span>The bricks are all on separate servers. On each is a XFS partition on a<br>
single HDD (together with other partitions for system etc.). All in all<br>
there are currently seven machines involved.<br>
<br>
I just noticed that on all servers the<br>
/var/log/glusterfs/etc-glusterfs-glusterd.vol.log is full of messages like<br>
<br>
> [2015-08-03 21:24:59.879820] W [socket.c:620:__socket_rwv] 0-management: readv on /var/run/a91fc43b47272ffaace2a6989e7b5e85.socket failed (Invalid argument)<br>
<br>
I assume this to be part of the problem…<br>
<br>
Regards :-)<br>
Florian<br>
<span class=""><br>
On <a href="tel:03.08.2015%2022" value="+33308201522">03.08.2015 22</a>:41, Mathieu Chateau wrote:<br>
> Hello,<br>
><br>
> If starting setup right now, you should start with current version (3.7.X)<br>
><br>
> We need more data/context as you were able to feed 150GB before having<br>
> issue.<br>
><br>
> Info:<br>
> Filesystem<br>
> network type (lan, VM...)<br>
> where is client (same lan?)<br>
> MTU<br>
> storage (raid, # of disks...)<br>
><br>
> Cordialement,<br>
> Mathieu CHATEAU<br>
> <a href="http://www.lotp.fr" rel="noreferrer" target="_blank">http://www.lotp.fr</a><br>
><br>
> 2015-08-03 21:44 GMT+02:00 Florian Oppermann <<a href="mailto:gluster-users@flopwelt.de">gluster-users@flopwelt.de</a><br>
</span>> <mailto:<a href="mailto:gluster-users@flopwelt.de">gluster-users@flopwelt.de</a>>>:<br>
<span class="">><br>
> Dear Gluster users,<br>
><br>
> after setting up a distributed replicated volume (3x2 bricks) on gluster<br>
> 3.6.4 on Ubuntu systems and populating it with some data (about 150 GB<br>
> in 20k files) I experience extreme delay when navigating through<br>
> directories or trying to ls the contents (actually the process seems to<br>
> hang completely now until I kill the /usr/sbin/glusterfs process on the<br>
> mounting machine).<br>
><br>
> Is there some common misconfiguration or any performance tuning option<br>
> that I could try?<br>
><br>
> I mount via automount with fstype=glusterfs option (using the native<br>
> fuse mount).<br>
><br>
> Any tips?<br>
><br>
> Best regards,<br>
> Florian Oppermann<br>
> _______________________________________________<br>
> Gluster-users mailing list<br>
</span>> <a href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a> <mailto:<a href="mailto:Gluster-users@gluster.org">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>
><br>
><br>
</blockquote></div><br></div>