From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753631AbcE0ORT (ORCPT ); Fri, 27 May 2016 10:17:19 -0400 Received: from mail-yw0-f171.google.com ([209.85.161.171]:33784 "EHLO mail-yw0-f171.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751222AbcE0ORR (ORCPT ); Fri, 27 May 2016 10:17:17 -0400 Date: Fri, 27 May 2016 10:17:15 -0400 From: Tejun Heo To: Michael Rapoport Cc: Bandan Das , linux-kernel@vger.kernel.org, kvm@vger.kernel.org, mst@redhat.com, jiangshanlai@gmail.com Subject: Re: [RFC PATCH 0/4] cgroup aware workqueues Message-ID: <20160527141715.GI23194@mtj.duckdns.org> References: <1458339291-4093-1-git-send-email-bsd@redhat.com> <201603210758.u2L7wiY9003907@d06av07.portsmouth.uk.ibm.com> <20160330170419.GG7822@mtj.duckdns.org> <201603310617.u2V6HIkt008006@d06av12.portsmouth.uk.ibm.com> <20160331171435.GD24661@htj.duckdns.org> <201605270822.u4R8MRoB027943@d06av10.portsmouth.uk.ibm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <201605270822.u4R8MRoB027943@d06av10.portsmouth.uk.ibm.com> User-Agent: Mutt/1.6.1 (2016-04-27) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, May 27, 2016 at 12:22:19PM +0300, Michael Rapoport wrote: > I've run two guests without any CPU pinning and without any actual > interaction with cgroups > Here's the results (in MBits/sec): > > size | 64 | 256 | 1024 | 4096 | 16384 > -----+-------+---------+---------+---------+--------- > (1) | 496.8 | 1346.31 | 6058.49 | 13736.2 | 13541.4 > (2) | 493.3 | 1604.03 | 5723.68 | 10181.4 | 15572.4 > (3) | 489.7 | 1437.86 | 6251.12 | 12774.2 | 12867.9 > > > From what I see, for different packet sizes there's different approach > that outperforms the others. > Moreover, I'd expect that in case when vhost completely takes over the > worker thread there would no be difference vs. current state. > > Tejun, can you help explaining these results? Heh, the only thing I can tell is the tests seem noisy and weren't run enough times to draw any conclusion. Even if the numbers were consistent, I don't think anybody would be able to tell a lot from just the results. If the results can be made stable, perf would be a good place to start. Thanks. -- tejun