From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754199AbdLTEJq convert rfc822-to-8bit (ORCPT ); Tue, 19 Dec 2017 23:09:46 -0500 Received: from mout.gmx.net ([212.227.17.21]:56126 "EHLO mout.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753632AbdLTEJn (ORCPT ); Tue, 19 Dec 2017 23:09:43 -0500 Message-ID: <1513742961.6863.21.camel@gmx.de> Subject: Re: [PATCH 3/4] sched: Comment on why sync wakeups try to run on the current CPU From: Mike Galbraith To: Peter Zijlstra , Mel Gorman Cc: Ingo Molnar , Matt Fleming , LKML Date: Wed, 20 Dec 2017 05:09:21 +0100 In-Reply-To: <20171219190644.3neuaenffj6tcxci@hirez.programming.kicks-ass.net> References: <20171218094327.19562-1-mgorman@techsingularity.net> <20171218094327.19562-4-mgorman@techsingularity.net> <20171219190644.3neuaenffj6tcxci@hirez.programming.kicks-ass.net> Content-Type: text/plain; charset="ISO-8859-15" X-Mailer: Evolution 3.20.5 Mime-Version: 1.0 Content-Transfer-Encoding: 8BIT X-Provags-ID: V03:K0:JTU4Ts9rQeVGKU6nkWmyzUOer44UFvD7OETnkKpn2Sz6Y+a8Mn3 17dwfppaiPBcbzVLLjqsJm2WkemVsTT4DEnJMmpE269t8C2Pjt3MfMyEnoybj9NGcl8leU3 z9hr4CoAAcahLKRmIt+vi4OZ/jwjicx0bP/xpi0egsVZgp9E3UE2KK4VJmRFzQB6KhrHdp8 r1Xbe3YU+zpdnDPyA2u2A== X-UI-Out-Filterresults: notjunk:1;V01:K0:yKpqnI1RJ/o=:XPw9x6p0hiCWPmL0aK25C9 vL8dgsv+qo2kqcKa/TCk52W6yVTXchjls5drjdHGjv5BVZd9m9gCqwM+BmtncBB/Y8hZhxard UyMEsk3P6AFVeWJgM76UwYexLcBFBNXOr7BqPNzltWz12Z12OudpK9cHlRTAMK+FSIYup+WxR DTMXJrdwca7+N5mpnR5BqLMXI1a+A5H1N6cXIgCsdo/jnB+PyDeYHDuK1RW1ilsr0BlNYqvvo MRWCiVaT6WnsuJ+zNPqf1VG8fjnLEAnkCkvnFpejhy++tImVHSQMpcLUU/MeajXRHzEFHLwUJ LYd5I0XY18zQDV/4h6Xjy05uOTOpRrA3hw/pUhswOpdM+HnSRpUJ5vDrOozKIGaOIdofh9tOT Xp4WxXjecyYShCoBJYG0a2Uh02SDUsPw3HeXEUuP8yvrF2GBxXGeNXSwEf+NBOSzQTvWBfp3x HgXdXoWGVBA4R8CWoFIWS+tsrvh7b3ouMo6PeE8OEQ5bNFzk3Fq7k8Ylwn7HKF9XrhgaSQDHD i9CB+kz8fiTw/RGwDhpVSo0As4chePOE7OtNW08FaTiSw0lWju2F+4f4EOgH3RDKYED2S5ZY7 e5n6cSWE3XjVSFrlvsokBappY0IIrll02uFBsJUdvQ5xFvj2uXPDZF6fPvOg/0EWPQo0Wd5ob KR6dQ6ZGR0PvSf+Vtmvq/3z+ew7+LXyNbE0ZixZV/fyH7Won4YEbqgI87D4Q249Bq0hmn7o3F AvUhDnel3CEsX0fgIEPVoaBShlVWPfP46lAyuqnbnaVaVg3GR7HYEUW6tUfJ3qOYtW5GodlYY K3zq95zyWsnFJx9Ck3OrH6eOShZ7IF0aZxvKtnE+m+SivAj5mA= Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2017-12-19 at 20:06 +0100, Peter Zijlstra wrote: > > Our SYNC hint does promise the caller will go away 'soon', although I'm > not sure how many of the current users actually honor that. The sync hint is not a lie, or even a damn lie, it's a statistic :) It's very useful for... TCP_SENDFILE homer:..debug/tracing # cat trace|grep netperf|grep wakes|wc -l 2417 homer:..debug/tracing # cat trace|grep netperf|grep schedules|wc -l 4 TCP_STREAM homer:..debug/tracing # cat trace|grep netperf|grep wakes|wc -l 2506 homer:..debug/tracing # cat trace|grep netperf|grep schedules|wc -l 3 TCP_MAERTS homer:..debug/tracing # cat trace|grep netperf|grep wakes|wc -l 2465 homer:..debug/tracing # cat trace|grep netperf|grep schedules|wc -l 2 ...knowing that tasks are talking, but not the least bit useful for scheduler decisions other than "pull to same planet".  Those are single instances, all of which exceed 180% combined util, one at 100%.  Then there are multi-wakers, tasks that would have scheduled if they hadn't been given more work to do etc etc.  Nope, stacking based upon that hint is most definitely not a good idea :) -Mike