Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S262737AbVAFFgc (ORCPT ); Thu, 6 Jan 2005 00:36:32 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S262738AbVAFFgc (ORCPT ); Thu, 6 Jan 2005 00:36:32 -0500 Received: from smtp203.mail.sc5.yahoo.com ([216.136.129.93]:32955 "HELO smtp203.mail.sc5.yahoo.com") by vger.kernel.org with SMTP id S262737AbVAFFgX (ORCPT ); Thu, 6 Jan 2005 00:36:23 -0500 Message-ID: <41DCCE53.4000906@yahoo.com.au> Date: Thu, 06 Jan 2005 16:36:19 +1100 From: Nick Piggin User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.7.3) Gecko/20041007 Debian/1.7.3-5 X-Accept-Language: en MIME-Version: 1.0 To: Andrea Arcangeli CC: Andrew Morton , riel@redhat.com, marcelo.tosatti@cyclades.com, linux-kernel@vger.kernel.org Subject: Re: [PATCH][5/?] count writeback pages in nr_scanned References: <20050105173624.5c3189b9.akpm@osdl.org> <41DCB577.9000205@yahoo.com.au> <20050105202611.65eb82cf.akpm@osdl.org> <41DCC014.80007@yahoo.com.au> <20050105204706.0781d672.akpm@osdl.org> <20050106045932.GN4597@dualathlon.random> <20050105210539.19807337.akpm@osdl.org> <20050106051707.GP4597@dualathlon.random> <41DCCA68.3020100@yahoo.com.au> <20050106052507.GR4597@dualathlon.random> In-Reply-To: <20050106052507.GR4597@dualathlon.random> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1536 Lines: 39 Andrea Arcangeli wrote: > On Thu, Jan 06, 2005 at 04:19:36PM +1100, Nick Piggin wrote: > >>This is practically what blk_congestion_wait does when the queue >>isn't congested though, isn't it? > > > The fundamental difference that makes it reliable is that: > > 1) only the I/O we're throttling against will be considered for the > wakeup event, which means only clearing PG_writeback will be > considered eligible for wakeup > Currently _all_ unrelated write I/O was considered eligible > for wakeup events and that could cause spurious oom kills. I'm not entirely convinced. In Rik's case it didn't matter, because all his writeout was in the same zone that reclaim was happening against (ZONE_NORMAL), so in that case, PG_writeback throttling will do exactly the same thing as blk_congestion_wait. I do like your PG_writeback throttling idea for the other reason that it should behave better on NUMA systems with lots of zones and lots of disks. > 2) we won't need unreliable anti-deadlock timeouts anymore > Well I think you do need *something*. If you wake up each time a single page (or request) has completed, you only complete what, 12 (DEF_PRIORITY) requests before going OOM? In the worst possible case scenario, which looks like what Rik's running into. Nick - 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/