From mboxrd@z Thu Jan 1 00:00:00 1970 Date: Thu, 1 May 2008 03:44:18 +0200 From: Nick Piggin Subject: Re: Warning on memory offline (and possible in usual migration?) Message-ID: <20080501014418.GB15179@wotan.suse.de> References: <20080422045205.GH21993@wotan.suse.de> <20080422165608.7ab7026b.kamezawa.hiroyu@jp.fujitsu.com> <20080422094352.GB23770@wotan.suse.de> <20080423004804.GA14134@wotan.suse.de> <20080429162016.961aa59d.kamezawa.hiroyu@jp.fujitsu.com> <20080430065611.GH27652@wotan.suse.de> <20080430001249.c07ff5c8.akpm@linux-foundation.org> <20080430072620.GI27652@wotan.suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: Sender: owner-linux-mm@kvack.org Return-Path: To: Christoph Lameter Cc: Andrew Morton , KAMEZAWA Hiroyuki , "linux-mm@kvack.org" , GOTO List-ID: On Wed, Apr 30, 2008 at 11:01:39AM -0700, Christoph Lameter wrote: > One issue that I am still not clear on is (in particular for memory > offline) is how exactly to determine if a page is under read I/O. I > initially thought simply checking for PageUptodate would do the trick. Yes if PageUptodate and the page is locked, then I don't believe any read IO should happen. But you definitely do seem to be migrating !PageUptodate pages. In that case I think it works because of buffer_migrate_page which takes the buffer locks and holds off read IO to buffers too. -- 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