<html><head><meta http-equiv="content-type" content="text/html; charset=utf-8"></head><body dir="auto"><div>Hi!</div><div><br></div><div>Well, it was worth a try I think... Sorry to hear it didn't help.<br><br>Do the drops increase? What kernel is the machine running?<br><br>-of (mobile)</div><div><br>Am 15.04.2015 um 18:16 schrieb Kevin Fenzi <<a href="mailto:kevin@scrye.com">kevin@scrye.com</a>>:<br><br></div><blockquote type="cite"><div>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<meta name="Generator" content="Zarafa HTML builder 1.0">
<title></title>
<!-- Converted from text/plain format -->
<p><font style="font-family: courier" size="2">
On Tue, 14 Apr 2015 20:49:28 +0200<br>
Oliver Falk <<a href="mailto:oliver@linux-kernel.at">oliver@linux-kernel.at</a>> wrote:<br>
<br>
> Hi!<br>
> <br>
> I had some similar issue some time ago on VMware. Try turning off the<br>
> hardware offloading in the VM with ethtool - no outage. Maybe it<br>
> helps... I think something like ethtool -k and then rx/tx/gso.<br>
<br>
I tried playing with this a bit yesterday, but it didn't seem to matter<br>
much. ;( <br>
<br>
There is actually not all that much i/o going on. It's mostly cpu and<br>
lots of context switches, etc. <br>
<br>
I guess I will fire off a vacuum analyze (since that shouldn't hurt<br>
anything or cause any problems) and just wait until we are out of<br>
freeze to schedule an outage and try a bunch of the more invasive<br>
things. <br>
<br>
kevin<br>
_______________________________________________<br>
infrastructure mailing list<br>
<a href="mailto:infrastructure@lists.fedoraproject.org">infrastructure@lists.fedoraproject.org</a><br>
<a href="https://admin.fedoraproject.org/mailman/listinfo/infrastructure">https://admin.fedoraproject.org/mailman/listinfo/infrastructure</a></font>
</p>
</div></blockquote><blockquote type="cite"><div><inline.txt></div></blockquote></body></html>