On Wed, Oct 31, 2012 at 4:50 PM, George-Cristian Bîrzan <span dir="ltr"><<a href="mailto:gc@birzan.org" target="_blank">gc@birzan.org</a>></span> wrote:<br><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"> <div class="im">on 0.10.2:</div><div class="gmail_quote"><div><br></div><div><div>[root@host34 libvirt]# virsh nodeinfo</div><div class="im"><div>CPU model: x86_64</div><div>CPU(s): 24</div><div>CPU frequency: 2200 MHz</div> </div><div>CPU socket(s): 1</div><div>Core(s) per socket: 6</div><div class="im"><div>Thread(s) per core: 1</div><div>NUMA cell(s): 4</div></div><div>Memory size: 131971020 KiB</div></div><div><br> </div><div>and <a href="http://birzan.org/capabilities4-newlibvirt.txt" target="_blank">http://birzan.org/capabilities4-newlibvirt.txt</a> </div> <div><br></div><div>This has made the problem even worse, as we now can only use 6 cores out of 24 by default (libvirt pins qemus to the CPUs is sees available, so we have to manually taskset them after starting).</div><div class="im"> <div><br></div></div></div></blockquote><div><br></div><div>I should check before I let my mouth run. This actually fixed the problem, we now get all 24 CPUs:</div><div><br></div><div><div>virsh # vcpuinfo 08867271-d458-43dc-8a03-807e83d107b4</div> <div>VCPU: 0</div><div>CPU: 9</div><div>State: running</div><div>CPU time: 1.3s</div><div>CPU Affinity: yyyyyyyyyyyyyyyyyyyyyyyy</div></div><div><br></div><div><br></div><div>To give you an example from the 'broken' host (still with 0.10.2):</div> <div><br></div><div><div>[root@host29 ~]# virsh vcpuinfo 17db9ebb-691b-47e1-bbf4-c9e3c1388d4f</div><div>VCPU: 0</div><div>CPU: 3</div><div>State: running</div><div>CPU time: 3103.2s</div> <div>CPU Affinity: yyyyyyyyyyyy</div><div><br></div><div>VCPU: 1</div><div>CPU: 1</div><div>State: running</div><div>CPU time: 3460.4s</div><div>CPU Affinity: yyyyyyyyyyyy</div></div> <div> </div></div><div><br></div>-- <br>George-Cristian Bîrzan<br>