From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jarek Poplawski Subject: Re: [PATCH] tcp: splice as many packets as possible at once Date: Tue, 20 Jan 2009 14:06:11 +0000 Message-ID: <20090120140611.GC17004@ff.dom.local> References: <20090115.153449.204259387.davem@davemloft.net> <20090115234255.GE1123@1wt.eu> <20090115234408.GA1693@1wt.eu> <20090115.155434.206643894.davem@davemloft.net> <20090119004206.GA10396@1wt.eu> <4975BD09.3020103@zeus.com> <20090120121115.GA17277@ioremap.net> <4975D518.1000800@zeus.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Evgeniy Polyakov , Willy Tarreau , David Miller , herbert@gondor.apana.org.au, dada1@cosmosbay.com, mingo@elte.hu, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, jens.axboe@oracle.com To: Ben Mansell Return-path: Received: from mail-ew0-f20.google.com ([209.85.219.20]:53695 "EHLO mail-ew0-f20.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752718AbZATOGS (ORCPT ); Tue, 20 Jan 2009 09:06:18 -0500 Content-Disposition: inline In-Reply-To: <4975D518.1000800@zeus.com> Sender: netdev-owner@vger.kernel.org List-ID: On Tue, Jan 20, 2009 at 01:43:52PM +0000, Ben Mansell wrote: ... > With an unpatched kernel, the splice performance was worse (due to the > one packet per-splice issues). With the small patch to fix that, I was > getting around 2 Gbps performance, although oddly enough, I could only > get 2 Gbps with read()/write() then as well... > > I'll try and do some tests on a machine that hopefully doesn't have the > bottlenecks (and one that uses different NICs) I guess you should especially check if SG and checksums are on, and it could depend on a chip within those NICs as well. Jarek P.