From mboxrd@z Thu Jan 1 00:00:00 1970 From: Paolo Bonzini Subject: Re: CPU Overcommitting question Date: Fri, 18 Jul 2014 17:30:37 +0200 Message-ID: <53C93D9D.3010503@redhat.com> References: <53C91BF3.6030507@dnshosting.it> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit To: Riccardo Brunetti , kvm@vger.kernel.org Return-path: Received: from mail-wg0-f41.google.com ([74.125.82.41]:58814 "EHLO mail-wg0-f41.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1762020AbaGRPap (ORCPT ); Fri, 18 Jul 2014 11:30:45 -0400 Received: by mail-wg0-f41.google.com with SMTP id z12so3716570wgg.24 for ; Fri, 18 Jul 2014 08:30:42 -0700 (PDT) In-Reply-To: <53C91BF3.6030507@dnshosting.it> Sender: kvm-owner@vger.kernel.org List-ID: Il 18/07/2014 15:06, Riccardo Brunetti ha scritto: > > > 1) Assign vCPUs so that vCPU(VM1) + vCPU(VM2) = total number of physical > cores (12) (both VMs have < 12 vCPUs) (ie. 8+4) > 2) Assign vCPUs so that vCPU(VM1) + vCPU(VM2) > total number of physical > cores (12) (both VMs have <= 12 vCPUs) (ie. 12+8) > 3) Assign vCPUs so that vCPU(VM1) + vCPU(VM2) > total number of physical > cores (12) (one VM has > 12 vCPUs) (ie. 16+8) > 4) Assign vCPUs so that vCPU(VM1) + vCPU(VM2) > total number of physical > cores (12) (both VMs have > 12 vCPUs) (ie. 16+16) The last two are usually bad ideas. The first two should be okay. Overcommitting works best if the VM are I/O bound (disk or network). If you're overcommitting, hyperthreading should in general be enabled. Answers for very specific scenarios are hard to give though, so you should also benchmark your deployment with realistic workloads. Paolo