From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753232AbaEWQA4 (ORCPT ); Fri, 23 May 2014 12:00:56 -0400 Received: from mail-pa0-f45.google.com ([209.85.220.45]:41997 "EHLO mail-pa0-f45.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753035AbaEWQAx (ORCPT ); Fri, 23 May 2014 12:00:53 -0400 Message-ID: <1400860851.5367.210.camel@edumazet-glaptop2.roam.corp.google.com> Subject: Re: skbuff truesize incorrect. From: Eric Dumazet To: Rick Jones Cc: =?ISO-8859-1?Q?Bj=F8rn?= Mork , Jim Baxter , David Miller , linux-usb@vger.kernel.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, kamal@canonical.com, edumazet@google.com, mszeredi@suse.cz, fw@strlen.de Date: Fri, 23 May 2014 09:00:51 -0700 In-Reply-To: <537F6CC1.2000503@hp.com> References: <537E4AFD.20304@mentor.com> <1400792295.5367.174.camel@edumazet-glaptop2.roam.corp.google.com> <1400792601.5367.176.camel@edumazet-glaptop2.roam.corp.google.com> <20140522.171033.1040508444998374401.davem@davemloft.net> <87ppj5vupf.fsf@nemi.mork.no> <537F0DCA.6030901@mentor.com> <87vbsw4z5x.fsf@nemi.mork.no> <537F6CC1.2000503@hp.com> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.2.3-0ubuntu6 Content-Transfer-Encoding: 7bit Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2014-05-23 at 08:44 -0700, Rick Jones wrote: > If you are measuring performance with the likes of netperf, you should > be able to get an idea of the performance effect from the change in > service demand (CPU consumed per unit of work) even if the maximum > throughput remains capped. This wont be enough to truly get an idea of the gains this patch brings. Add some random drops in the equation, and instead of dropping packets, we gently add them in the out of order queue, gently coalesce them, gently allow SACK enabled flows to recover thanks to fast retransmits, with no latency effect (No expensive collapse/prunes) # nstat -az|egrep "TCPRcvCoalesce|TCPOFOQueue|TCPRcvCollapsed|Prune" TcpExtPruneCalled 118 0.0 TcpExtRcvPruned 0 0.0 TcpExtOfoPruned 0 0.0 TcpExtTCPRcvCollapsed 1009 0.0 TcpExtTCPRcvCoalesce 857806 0.0 TcpExtTCPOFOQueue 201246 0.0 Yep, we _might_ consume some cpu cycles in the perfect case where no packet was dropped, but this is kind of an utopia.