Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754825AbbG0VH3 (ORCPT ); Mon, 27 Jul 2015 17:07:29 -0400 Received: from mx1.redhat.com ([209.132.183.28]:35864 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754791AbbG0VHX (ORCPT ); Mon, 27 Jul 2015 17:07:23 -0400 Date: Tue, 28 Jul 2015 00:07:19 +0300 From: "Michael S. Tsirkin" To: Bandan Das Cc: Eyal Moscovici , cgroups@vger.kernel.org, jasowang@redhat.com, kvm@vger.kernel.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, Razya Ladelsky Subject: Re: [RFC PATCH 0/4] Shared vhost design Message-ID: <20150728000221-mutt-send-email-mst@redhat.com> References: <1436760455-5686-1-git-send-email-bsd@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1661 Lines: 39 On Mon, Jul 27, 2015 at 03:48:19PM -0400, Bandan Das wrote: > Eyal Moscovici writes: > > > Hi, > > > > The test showed the same relative numbers as we got in our internal > > testing. I was wondering about the configuration in regards to NUMA. From > Thanks for confirming. > > > our testing we saw that if the VMs are spread across 2 NUMA nodes then > > having a shared vhost thread per node performs better then having the two > > threads in the same core. > > IIUC, this is similar to my test setup and observations i.e > > 14* 1173.8 1216.9 > > In this case, there's a shared vhost thread on CPU 14 for numa node 0 > and another on CPU 15 for numa node 1. Guests running on CPUs 0,2,4,6,8,10,12 > are serviced by vhost-0 that runs on CPU 14 and guests running on CPUs 1,3,5,7,9,11,13 > get serviced by vhost-1 (Numa node 1). I tried some other configurations but > this configuration gave me the best results. > > > Eyal, I think it makes sense to add polling on top of these patches and > get numbers for them too. Thoughts ? > > Bandan So simple polling by vhost is kind of ok for some guests, but I think to really make it work for a reasonably wide selection of guests/workloads you need to combine it with 1. polling the NIC - it makes no sense to me to only poll one side of the equation; and probably 2. - polling in guest. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/