From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Michael S. Tsirkin" Subject: Re: [v3 RFC PATCH 0/4] Implement multiqueue virtio-net Date: Fri, 29 Oct 2010 13:26:03 +0200 Message-ID: <20101029112603.GA24577@redhat.com> References: <20101020085452.15579.76002.sendpatchset@krkumar2.in.ibm.com> <20101025161718.GA19559@redhat.com> <20101026093846.GA6766@redhat.com> <20101026110913.GC7922@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: anthony@codemonkey.ws, arnd@arndb.de, avi@redhat.com, davem@davemloft.net, eric.dumazet@gmail.com, kvm@vger.kernel.org, netdev@vger.kernel.org, rusty@rustcorp.com.au To: Krishna Kumar2 Return-path: Content-Disposition: inline In-Reply-To: Sender: kvm-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Thu, Oct 28, 2010 at 12:48:57PM +0530, Krishna Kumar2 wrote: > > Krishna Kumar2/India/IBM wrote on 10/28/2010 10:44:14 AM: > > > > > > > > Results for UDP BW tests (unidirectional, sum across > > > > > > 3 iterations, each iteration of 45 seconds, default > > > > > > netperf, vhosts bound to cpus 0-3; no other tuning): > > > > > > > > > > Is binding vhost threads to CPUs really required? > > > > > What happens if we let the scheduler do its job? > > > > > > > > Nothing drastic, I remember BW% and SD% both improved a > > > > bit as a result of binding. > > > > > > If there's a significant improvement this would mean that > > > we need to rethink the vhost-net interaction with the scheduler. > > > > I will get a test run with and without binding and post the > > results later today. > > Correction: The result with binding is is much better for > SD/CPU compared to without-binding: Can you pls ty finding out why that is? Is some thread bouncing between CPUs? Does a wrong numa node get picked up? In practice users are very unlikely to pin threads to CPUs. -- MST