Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755604Ab1CWFVO (ORCPT ); Wed, 23 Mar 2011 01:21:14 -0400 Received: from fgwmail6.fujitsu.co.jp ([192.51.44.36]:42460 "EHLO fgwmail6.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754625Ab1CWFVM (ORCPT ); Wed, 23 Mar 2011 01:21:12 -0400 X-SecurityPolicyCheck-FJ: OK by FujitsuOutboundMailChecker v1.3.1 From: KOSAKI Motohiro To: Minchan Kim Subject: Re: [PATCH 1/5] vmscan: remove all_unreclaimable check from direct reclaim path completely Cc: kosaki.motohiro@jp.fujitsu.com, linux-kernel@vger.kernel.org, Andrew Morton , David Rientjes , Linus Torvalds , Rik van Riel , Oleg Nesterov , linux-mm , Andrey Vagin , Hugh Dickins , KAMEZAWA Hiroyuki , Nick Piggin , Johannes Weiner In-Reply-To: <20110322144950.GA2628@barrios-desktop> References: <20110322200523.B061.A69D9226@jp.fujitsu.com> <20110322144950.GA2628@barrios-desktop> Message-Id: <20110323142133.1AC6.A69D9226@jp.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit X-Mailer: Becky! ver. 2.56.05 [ja] Date: Wed, 23 Mar 2011 14:21:08 +0900 (JST) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3466 Lines: 88 Hi Minchan, > > zone->all_unreclaimable and zone->pages_scanned are neigher atomic > > variables nor protected by lock. Therefore a zone can become a state > > of zone->page_scanned=0 and zone->all_unreclaimable=1. In this case, > > Possible although it's very rare. Can you test by yourself andrey's case on x86 box? It seems reprodusable. > > current all_unreclaimable() return false even though > > zone->all_unreclaimabe=1. > > The case is very rare since we reset zone->all_unreclaimabe to zero > right before resetting zone->page_scanned to zero. > But I admit it's possible. Please apply this patch and run oom-killer. You may see following pages_scanned:0 and all_unreclaimable:yes combination. likes below. (but you may need >30min) Node 0 DMA free:4024kB min:40kB low:48kB high:60kB active_anon:11804kB inactive_anon:0kB active_file:0kB inactive_file:4kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:15676kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB shmem:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:68kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? yes > > CPU 0 CPU 1 > free_pcppages_bulk balance_pgdat > zone->all_unreclaimabe = 0 > zone->all_unreclaimabe = 1 > zone->pages_scanned = 0 > > > > Is this ignorable minor issue? No. Unfortunatelly, x86 has very > > small dma zone and it become zone->all_unreclamble=1 easily. and > > if it becase all_unreclaimable, it never return all_unreclaimable=0 > ^^^^^ it's very important verb. ^^^^^ return? reset? > > I can't understand your point due to the typo. Please correct the typo. > > > beucase it typicall don't have reclaimable pages. > > If DMA zone have very small reclaimable pages or zero reclaimable pages, > zone_reclaimable() can return false easily so all_unreclaimable() could return > true. Eventually oom-killer might works. The point is, vmscan has following all_unreclaimable check in several place. if (zone->all_unreclaimable && priority != DEF_PRIORITY) continue; But, if the zone has only a few lru pages, get_scan_count(DEF_PRIORITY) return {0, 0, 0, 0} array. It mean zone will never scan lru pages anymore. therefore false negative smaller pages_scanned can't be corrected. Then, false negative all_unreclaimable() also can't be corrected. btw, Why get_scan_count() return 0 instead 1? Why don't we round up? Git log says it is intentionally. commit e0f79b8f1f3394bb344b7b83d6f121ac2af327de Author: Johannes Weiner Date: Sat Oct 18 20:26:55 2008 -0700 vmscan: don't accumulate scan pressure on unrelated lists > > In my test, I saw the livelock, too so apparently we have a problem. > I couldn't dig in it recently by another urgent my work. > I think you know root cause but the description in this patch isn't enough > for me to be persuaded. > > Could you explain the root cause in detail? If you have an another fixing idea, please let me know. :) -- 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/