From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752460AbZILWHM (ORCPT ); Sat, 12 Sep 2009 18:07:12 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751118AbZILWHK (ORCPT ); Sat, 12 Sep 2009 18:07:10 -0400 Received: from swampdragon.chaosbits.net ([90.184.90.115]:22470 "EHLO swampdragon.chaosbits.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750904AbZILWHJ (ORCPT ); Sat, 12 Sep 2009 18:07:09 -0400 Date: Sun, 13 Sep 2009 00:07:11 +0200 (CEST) From: Jesper Juhl To: Ingo Molnar cc: Tony Luck , Linus Torvalds , linux-kernel@vger.kernel.org, Peter Zijlstra , Mike Galbraith Subject: Re: [GIT PULL] sched/core for v2.6.32 In-Reply-To: <20090912054917.GB9420@elte.hu> Message-ID: References: <20090911192505.GA20006@elte.hu> <12c511ca0909111924s42d000dsbf378009d9434ddc@mail.gmail.com> <20090912054917.GB9420@elte.hu> User-Agent: Alpine 2.00 (LNX 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sat, 12 Sep 2009, Ingo Molnar wrote: > > * Tony Luck wrote: > > > On Fri, Sep 11, 2009 at 4:34 PM, Jesper Juhl wrote: > > > That may be so; but most people I've ever talked to about multiple > > > processes, fork, vfork and the like, have mostly assumed child-runs-first. > > > That is just my personal experience. > > > So I get worried when that assumption is made false. > > > > With multi-core cpus becoming (being?) the norm, almost all > > systems are SMP now. So child and parent can surely end up > > running in parallel very often. So applications that make > > assumptions about child running first are going to be frequently > > surprised. Aren't they? > > We had parent-runs-first briefly, in v2.6.23 - this got changed by > v2.6.24 - but yes, it did trigger at least one app bug that i > remember (dont remember which one it was though). > > We are almost two years later now - maybe it works fine now. > > In any case, as a precaution i made the sched_child_runs_first > sysctl knob unconditional (previously it was under > CONFIG_SCHED_DEBUG). > > So if an old distro is upgraded with a new kernel (and user-space is > not updated), it can be worked around by putting this into > /etc/sysctl.conf: > > kernel.sched_child_runs_first = 1 > Always goo to have a workaround if something unexpectedly breaks. Makes perfect sense for that knob to now be unconditional - and with it, changing the behaviour is a much less risky operation. Glad to have it. > You are right to suggest that due to SMP and due to the general > non-determinism of preemption we _never_ made any 'promise' to run > the child first. > > It was a statistical property based on performance considerations - > and now we flipped it around based on latency and for kbuild > performance/throughput reasons: Serge Belyshev reported a 7% > increase on a quad due to this change and i measured a 1.5% > peak-kbuild performance increase. > Impressive. I wouldn't have expected that much gain by running the parent first. Actually I personally would have expected child-first to perform better since (in my experience) it's usually the child that's just forked that matters the most. A server process that spawns a child to service a request wants the child to run asap and process that forks, then execs cares primarily about the child. > So it's worth it for multiple reasons and even in the worst-case > problems can be worked around easily and without rebooting the > system. > Perfect :-) -- Jesper Juhl http://www.chaosbits.net/ Plain text mails only, please http://www.expita.com/nomime.html Don't top-post http://www.catb.org/~esr/jargon/html/T/top-post.html