Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754086AbZIHKGV (ORCPT ); Tue, 8 Sep 2009 06:06:21 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754029AbZIHKGU (ORCPT ); Tue, 8 Sep 2009 06:06:20 -0400 Received: from fgwmail6.fujitsu.co.jp ([192.51.44.36]:39886 "EHLO fgwmail6.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753961AbZIHKGT (ORCPT ); Tue, 8 Sep 2009 06:06:19 -0400 X-SecurityPolicyCheck-FJ: OK by FujitsuOutboundMailChecker v1.3.1 From: KOSAKI Motohiro To: Peter Zijlstra Subject: Re: [rfc] lru_add_drain_all() vs isolation Cc: kosaki.motohiro@jp.fujitsu.com, Mike Galbraith , Ingo Molnar , linux-mm , Christoph Lameter , Oleg Nesterov , lkml In-Reply-To: <1252398006.7746.3.camel@twins> References: <20090908085344.0CBD.A69D9226@jp.fujitsu.com> <1252398006.7746.3.camel@twins> Message-Id: <20090908190148.0CC9.A69D9226@jp.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit X-Mailer: Becky! ver. 2.50.07 [ja] Date: Tue, 8 Sep 2009 19:06:17 +0900 (JST) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2762 Lines: 54 > On Tue, 2009-09-08 at 08:56 +0900, KOSAKI Motohiro wrote: > > Hi Peter, > > > > > On Mon, 2009-09-07 at 10:17 +0200, Mike Galbraith wrote: > > > > > > > [ 774.651779] SysRq : Show Blocked State > > > > [ 774.655770] task PC stack pid father > > > > [ 774.655770] evolution.bin D ffff8800bc1575f0 0 7349 6459 0x00000000 > > > > [ 774.676008] ffff8800bc3c9d68 0000000000000086 ffff8800015d9340 ffff8800bb91b780 > > > > [ 774.676008] 000000000000dd28 ffff8800bc3c9fd8 0000000000013340 0000000000013340 > > > > [ 774.676008] 00000000000000fd ffff8800015d9340 ffff8800bc1575f0 ffff8800bc157888 > > > > [ 774.676008] Call Trace: > > > > [ 774.676008] [] schedule_timeout+0x2d/0x20c > > > > [ 774.676008] [] wait_for_common+0xde/0x155 > > > > [ 774.676008] [] ? default_wake_function+0x0/0x14 > > > > [ 774.676008] [] ? lru_add_drain_per_cpu+0x0/0x10 > > > > [ 774.676008] [] ? lru_add_drain_per_cpu+0x0/0x10 > > > > [ 774.676008] [] wait_for_completion+0x1d/0x1f > > > > [ 774.676008] [] flush_work+0x7f/0x93 > > > > [ 774.676008] [] ? wq_barrier_func+0x0/0x14 > > > > [ 774.676008] [] schedule_on_each_cpu+0xb4/0xed > > > > [ 774.676008] [] lru_add_drain_all+0x15/0x17 > > > > [ 774.676008] [] sys_mlock+0x2e/0xde > > > > [ 774.676008] [] system_call_fastpath+0x16/0x1b > > > > > > FWIW, something like the below (prone to explode since its utterly > > > untested) should (mostly) fix that one case. Something similar needs to > > > be done for pretty much all machine wide workqueue thingies, possibly > > > also flush_workqueue(). > > > > Can you please explain reproduce way and problem detail? > > > > AFAIK, mlock() call lru_add_drain_all() _before_ grab semaphoe. Then, > > it doesn't cause any deadlock. > > Suppose you have 2 cpus, cpu1 is busy doing a SCHED_FIFO-99 while(1), > cpu0 does mlock()->lru_add_drain_all(), which does > schedule_on_each_cpu(), which then waits for all cpus to complete the > work. Except that cpu1, which is busy with the RT task, will never run > keventd until the RT load goes away. > > This is not so much an actual deadlock as a serious starvation case. This seems flush_work vs RT-thread problem, not only lru_add_drain_all(). Why other workqueue flusher doesn't affect this issue? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/