<html><head/><body><html><head></head><body>Pve-2.2 was working but pve-2.3 also perfoms horribly here.<br><br><div class="gmail_quote">Keith Osborne <keith@tdrnetworks.com> wrote:<blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
<pre style="white-space: pre-wrap; word-wrap:break-word; font-family: sans-serif; margin-top: 0px">Hi,<br /><br />Is anyone aware of major performance problems in the latest OpenVZ <br />kernels - I just posted a bugzilla report here with a ton of graphs:<br /><br /><a href="https://bugzilla.openvz.org/show_bug.cgi?id=2556">https://bugzilla.openvz.org/show_bug.cgi?id=2556</a><br /><br />I went from Debian 6 (excellent performance) stock kernel to Centos 6.4 <br />(terrible with ksoftirqd bug also report - <br /><a href="https://bugzilla.openvz.org/show_bug.cgi?id=2554">https://bugzilla.openvz.org/show_bug.cgi?id=2554</a>) latest VZ kernel to <br />Debian 6 Proxmox kernel (also contains ksoftirqd bug) - both latest VZ <br />kernels for CentOS and Proxmox were awful in performance - something was <br />eating up all the CPU in user, but top show only small CPU usage inside <br />the containers. Back to Debian 6 stock with a kernal circa 2011 and <br />performance is flying again.<br
/><br />I checked all the usual suspects, RAID configuration, deadline <br />scheduler, blockdev size - over just a major lag - perhaps people don't <br />notice it or perhaps it's a known problem? Does anyone else have this <br />experience of coming from the older Debian 6 vanilla kernel?<br /><br />Keith<br /><br /><hr /><br />pve-user mailing list<br />pve-user@pve.proxmox.com<br /><a href="http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-user">http://pve.proxmox.com/cgi-bin/mailman/listinfo/pve-user</a><br /><br />!DSPAM:5163f20b134248923290609!<br /><br /><br /></pre></blockquote></div><br>
-- <br>
Sent from my Android phone with K-9 Mail. Please excuse my brevity.</body></html></body></html>