<div dir="ltr">Ok, so we found a "solution" that I thought I'll share in case this thread pops up in a future search.<div><br></div><div>The problem was that our Redhat 5.x guests still run with a kernel that lacks the "tickeless" feature, meaning that they are poking the host a 1000 times per second even if they haven't anything to do.</div><div><br></div><div>Disabling hyperthreading and most importantly, adding the parameter "divider=10" to the kernel boot line in grub does indeed lower the cpu utilization in the hosts almost to 0% when idling.</div><div><br></div><div>In our case we use the command </div><div><br></div><div>sudo /sbin/grubby --update-kernel=ALL --args="divider=10"<br></div><div><br></div><div>To upgrade the /boot/grub/grub.conf file and then we restart the vm.</div><div><br></div><div>Thank you everyone for the help.</div><div><br></div><div>Xavier</div></div><div class="gmail_extra"><br><div class="gmail_quote">On Mon, Nov 10, 2014 at 8:32 AM, Xavier Naveira <span dir="ltr"><<a href="mailto:xnaveira@gmail.com" target="_blank">xnaveira@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">We tried a minimal installation from CD of RedHat 5.10 and it is the same.<div><br></div><div>This should be fairly easy to reproduce:</div><div><br></div><div>- Install a RedHat 6.5 hypervisor</div><div>- Install a RedHat 5.10 guest in it</div><div>- Enjoy your overused CPU</div><div><br></div><div>Is there someone with a similar setup out there?</div><span class="HOEnZb"><font color="#888888"><div><br></div><div>Xavier</div></font></span></div><div class="HOEnZb"><div class="h5"><div class="gmail_extra"><br><div class="gmail_quote">On Fri, Nov 7, 2014 at 12:30 PM, Gianluca Cecchi <span dir="ltr"><<a href="mailto:gianluca.cecchi@gmail.com" target="_blank">gianluca.cecchi@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><div class="gmail_quote"><span>On Fri, Nov 7, 2014 at 10:48 AM, Xavier Naveira <span dir="ltr"><<a href="mailto:xnaveira@gmail.com" target="_blank">xnaveira@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Hi,<div><br></div><div>We have installed and added a new hypervisor into the ovirt cluster but this time with disabled HT.</div><div><br></div><div>I migrated a RedHat 5.10 machine to it and immediately the qemu-kvm process running the vm (freshly installed, just basic packages) began to consume 20-40% CPU as showed running top on the hypervisor.</div><div><br></div><div>Now that I have a hypervisor to run tests in, what would you suggest the next step is?</div><div><br></div><div>Thank you.</div><span><font color="#888888"><div><br></div><div>Xavier</div></font></span></div><div><div><div class="gmail_extra"><br><div class="gmail_quote"><br></div></div></div></div></blockquote><div><br></div></span><div>If I remember correctly you had to test plain Qemu/KVM on CentOS 6.5 and see if the difference is made by oVirt itself or by the OS changed from 5.x to 6.y...</div><div>And also compare command line (eventually both in 5.x and 6.x) between plain Qemu/KVM and oVirt spawned VMs</div><span><font color="#888888"><div>Gianluca</div></font></span></div></div></div>
</blockquote></div><br></div>
</div></div></blockquote></div><br></div>