From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757928Ab2GRAQ0 (ORCPT ); Tue, 17 Jul 2012 20:16:26 -0400 Received: from mail-gg0-f174.google.com ([209.85.161.174]:50911 "EHLO mail-gg0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757922Ab2GRAQN (ORCPT ); Tue, 17 Jul 2012 20:16:13 -0400 Date: Tue, 17 Jul 2012 19:16:07 -0500 From: Jonathan Nieder To: Greg Kroah-Hartman Cc: linux-kernel@vger.kernel.org, stable@vger.kernel.org, torvalds@linux-foundation.org, akpm@linux-foundation.org, alan@lxorguk.ukuu.org.uk, Peter Zijlstra , Ingo Molnar Subject: Re: [ 11/37] sched/nohz: Rewrite and fix load-avg computation -- again Message-ID: <20120718001607.GJ25325@burratino> References: <20120717232455.GA5994@kroah.com> <20120717232431.399005532@linuxfoundation.org> <20120717232432.250519502@linuxfoundation.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20120717232432.250519502@linuxfoundation.org> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi, Greg Kroah-Hartman wrote: > commit 5167e8d5417bf5c322a703d2927daec727ea40dd upstream. > > Thanks to Charles Wang for spotting the defects in the current code: > > - If we go idle during the sample window -- after sampling, we get a > negative bias because we can negate our own sample. > > - If we wake up during the sample window we get a positive bias > because we push the sample to a known active period. > > So rewrite the entire nohz load-avg muck once again, now adding > copious documentation to the code. I'm thrilled to see this regression fix for stable@, but are we really really sure that it won't cause new regressions? Words like "rewrite" set off alarm bells. As do missing acks: > Cc: Linus Torvalds > Cc: Andrew Morton (though I guess there's an implied ack from Linus, given that it was pulled). And big diffstats: > include/linux/sched.h | 8 + > kernel/sched/core.c | 275 ++++++++++++++++++++++++++++++++++------------- > kernel/sched/idle_task.c | 1 > kernel/sched/sched.h | 2 > kernel/time/tick-sched.c | 2 > 5 files changed, 213 insertions(+), 75 deletions(-) Thanks, Jonathan