From owner-svn-src-stable@freebsd.org Tue Jan 24 18:44:27 2017 Return-Path: Delivered-To: svn-src-stable@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id AA51BCC0B33; Tue, 24 Jan 2017 18:44:27 +0000 (UTC) (envelope-from vangyzen@FreeBSD.org) Received: from smtp.vangyzen.net (hotblack.vangyzen.net [IPv6:2607:fc50:1000:7400:216:3eff:fe72:314f]) by mx1.freebsd.org (Postfix) with ESMTP id 93CEC1B3; Tue, 24 Jan 2017 18:44:27 +0000 (UTC) (envelope-from vangyzen@FreeBSD.org) Received: from sweettea.beer.town (unknown [76.164.8.130]) by smtp.vangyzen.net (Postfix) with ESMTPSA id AA3D05649D; Tue, 24 Jan 2017 12:44:26 -0600 (CST) Subject: Re: svn commit: r312666 - stable/10/sys/kern To: Andriy Gapon , Bruce Evans References: <201701230834.v0N8Ypnu011042@repo.freebsd.org> <20170124002712.Q903@besplex.bde.org> <49838a2b-c628-da8c-4c9c-4a66c83119f8@FreeBSD.org> Cc: src-committers@FreeBSD.org, svn-src-all@FreeBSD.org, svn-src-stable@FreeBSD.org, svn-src-stable-10@FreeBSD.org From: Eric van Gyzen Message-ID: <0f2c3b59-54d3-a83a-29ba-4fcda2db25f2@FreeBSD.org> Date: Tue, 24 Jan 2017 12:44:25 -0600 User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:45.0) Gecko/20100101 Thunderbird/45.5.0 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit X-BeenThere: svn-src-stable@freebsd.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: SVN commit messages for all the -stable branches of the src tree List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Jan 2017 18:44:27 -0000 On 01/23/2017 12:12, Eric van Gyzen wrote: > On 01/23/2017 10:03, Andriy Gapon wrote: >> On 23/01/2017 15:34, Bruce Evans wrote: >>> What is a good benchmark for showing that the fix helps? >> >> Honestly, I do not know. We ran into a pathology where a thread was not getting >> scheduled for a long time after being preempted while in a critical section (so >> the actual preemption was a voluntary switch when exiting the critical section). >> I am not sure what kind of a synthetic benchmark or a test case would readily >> demonstrate the problem. > > I submitted r270423, which introduced the bug Andriy just fixed. I'm > already setting up the performance test that I used for that change. > It's a macro-benchmark of a commercial product, so I can't elaborate on > details, but at least I can give a thumb indication in the style of a > Roman Dictator. My performance tests showed no change, so although r312666 does not improve performance under my workload, it also does not hurt. Specifically, it does not reintroduce the regression introduced in r239157 that I poorly fixed in r270423. Thanks again for the fix, Andriy. Eric