From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759230AbaDKPXy (ORCPT ); Fri, 11 Apr 2014 11:23:54 -0400 Received: from forward2m.mail.yandex.net ([37.140.138.2]:38957 "EHLO forward2m.mail.yandex.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757942AbaDKPXx (ORCPT ); Fri, 11 Apr 2014 11:23:53 -0400 X-Greylist: delayed 455 seconds by postgrey-1.27 at vger.kernel.org; Fri, 11 Apr 2014 11:23:53 EDT From: Kirill Tkhai To: Sasha Levin , Michael wang , Peter Zijlstra , "ktkhai@parallels.com" Cc: Ingo Molnar , LKML In-Reply-To: <5347FCED.8040706@oracle.com> References: <5304F32A.4040907@oracle.com> <5305856F.3000109@linux.vnet.ibm.com> <53078241.3060201@oracle.com> <53080122.609@linux.vnet.ibm.com> <530ABB44.5000601@oracle.com> <530AD653.3000808@linux.vnet.ibm.com> <20140224071028.GW9987@twins.programming.kicks-ass.net> <530B1B80.4000307@linux.vnet.ibm.com> <20140224121218.GR15586@twins.programming.kicks-ass.net> <534610A4.5000302@oracle.com> <53464164.5030701@linux.vnet.ibm.com> <336561397137116@web27h.yandex.ru> <5347FCED.8040706@oracle.com> Subject: Re: sched: hang in migrate_swap MIME-Version: 1.0 Message-Id: <1442521397229373@web20m.yandex.ru> X-Mailer: Yamail [ http://yandex.ru ] 5.0 Date: Fri, 11 Apr 2014 19:16:13 +0400 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=koi8-r Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 11.04.2014, 18:33, "Sasha Levin" : > On 04/10/2014 09:38 AM, Kirill Tkhai wrote: > >> š10.04.2014, 11:00, "Michael wang" : >>>> šOn 04/10/2014 11:31 AM, Sasha Levin wrote: >>>> š[snip] >>>>>> ššI'd like to re-open this issue. It seems that something broke and I'm >>>>>> ššnow seeing the same issues that have gone away 2 months with this patch >>>>>> ššagain. >>>> šA new mechanism has been designed to move the priority checking inside >>>> šidle_balance(), including Kirill who is the designer ;-) >> šNot sure, it's connected with my patch. But looks like, we forgot >> šexactly stop class. Maybe this will help? >> >> š[PATCH] sched: Checking for stop task appearance when balancing happens >> >> šJust do it, like we do for other higher priority classes... >> >> šSigned-off-by: Kirill Tkhai > > I've been running with this patch for the last two days and the hang > seems to be gone. > > I'll leave it running on the weekend and will update again on Monday. Thanks for testing. Sorry for I killed your linuxes by this lost need_resched(). > > Thanks, > Sasha