From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756770Ab3CERPg (ORCPT ); Tue, 5 Mar 2013 12:15:36 -0500 Received: from mga14.intel.com ([143.182.124.37]:13223 "EHLO mga14.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752580Ab3CERPf (ORCPT ); Tue, 5 Mar 2013 12:15:35 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.84,787,1355126400"; d="scan'208";a="209126275" Message-ID: <5136282E.9080307@linux.intel.com> Date: Tue, 05 Mar 2013 19:15:26 +0200 From: Eliezer Tamir User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:17.0) Gecko/20130215 Thunderbird/17.0.3 MIME-Version: 1.0 To: Ben Hutchings CC: Eliezer Tamir , linux-kernel@vger.kernel.org, netdev@vger.kernel.org, Dave Miller , Jesse Brandeburg , e1000-devel@lists.sourceforge.net, Willem de Bruijn , Andi Kleen , HPA , Eliezer Tamir Subject: Re: [RFC PATCH 1/5] net: implement support for low latency socket polling References: <20130227175549.10611.82188.stgit@gitlad.jf.intel.com> <20130227175555.10611.42794.stgit@gitlad.jf.intel.com> <1362501781.2791.19.camel@bwh-desktop.uk.solarflarecom.com> In-Reply-To: <1362501781.2791.19.camel@bwh-desktop.uk.solarflarecom.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 05/03/2013 18:43, Ben Hutchings wrote: > On Wed, 2013-02-27 at 09:55 -0800, Eliezer Tamir wrote: > > Should the units really be cycles or, say, microseconds? I assume that > a sysctl setter can do a conversion to cycles so that there's no need to > multiply every time the value is used. (If the CPU doesn't have > constant_tsc or equivalent then this conversion doesn't quite work, but > then low-latency tunng usually includes disabling frequency scaling.) We are not very sensitive to this setting, anything on the order of your half round time trip plus a few standard deviations works well. We are busy waiting, so setting a higher value does not change the results much. It does make sense to have this in ms, and it might not matter if the dynamic cycles mess with the value too much. BTW on my machines enabling frequency scaling improves performance in many cases. > Also, this should be a per-device (or even per-NAPI-context?) setting. Again, I would expect this to depend more on your workload than on the NIC, so I would keep this global. User knobs should be as simple as possible. >>+int sysctl_net_ll_poll __read_mostly = 150000; > Nicely tuned for your specific test system, no doubt. :-) why don't you try this on your NIC and see ;-) Thanks for the input, Eliezer