From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail143.messagelabs.com (mail143.messagelabs.com [216.82.254.35]) by kanga.kvack.org (Postfix) with SMTP id AC0C06B02A6 for ; Wed, 28 Jul 2010 12:30:10 -0400 (EDT) Received: by pxi7 with SMTP id 7so1183715pxi.14 for ; Wed, 28 Jul 2010 09:30:04 -0700 (PDT) Date: Thu, 29 Jul 2010 01:29:53 +0900 From: Minchan Kim Subject: Re: [PATCH] vmscan: remove wait_on_page_writeback() from pageout() Message-ID: <20100728162953.GB5401@barrios-desktop> References: <20100728071705.GA22964@localhost> <20100728084654.GA26776@localhost> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20100728084654.GA26776@localhost> Sender: owner-linux-mm@kvack.org To: Wu Fengguang Cc: Andrew Morton , Andy Whitcroft , Rik van Riel , KOSAKI Motohiro , Mel Gorman , Christoph Hellwig , "linux-kernel@vger.kernel.org" , "linux-fsdevel@vger.kernel.org" , "linux-mm@kvack.org" , Dave Chinner , Chris Mason , Nick Piggin , Johannes Weiner , KAMEZAWA Hiroyuki , Andrea Arcangeli , Andreas Mohr , Bill Davidsen , Ben Gamari List-ID: On Wed, Jul 28, 2010 at 04:46:54PM +0800, Wu Fengguang wrote: > And the wait page-by-page behavior of pageout(SYNC) will lead to very > long stall time if running into some range of dirty pages. So it's bad > idea anyway to call wait_on_page_writeback() inside pageout(). Although we remove it in pageout, shrink_page_list still has it. So it would result in long stall. And it is for lumpy reclaim which means it's a trade-off, I think. -- Kind regards, Minchan Kim -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org