From: "Darrick J. Wong" Subject: Re: [PATCHSET v3.1 0/7] data integrity: Stabilize pages during writeback for various fses Date: Mon, 16 May 2011 11:47:36 -0700 Message-ID: <20110516184736.GL20579@tux1.beaverton.ibm.com> References: <87tyd31fkc.fsf@devron.myhome.or.jp> <20110510123819.GB4402@quack.suse.cz> <87hb924s2x.fsf@devron.myhome.or.jp> <20110510132953.GE4402@quack.suse.cz> <878vue4qjb.fsf@devron.myhome.or.jp> <87zkmu3b2i.fsf@devron.myhome.or.jp> <20110510145421.GJ4402@quack.suse.cz> <87zkmupmaq.fsf@devron.myhome.or.jp> <20110510162237.GM4402@quack.suse.cz> <87vcxipljj.fsf@devron.myhome.or.jp> Reply-To: djwong@us.ibm.com Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Jan Kara , Theodore Tso , Alexander Viro , Jens Axboe , "Martin K. Petersen" , Jeff Layton , Dave Chinner , linux-kernel , Dave Hansen , Christoph Hellwig , linux-mm@kvack.org, Chris Mason , Joel Becker , linux-scsi , linux-fsdevel , linux-ext4@vger.kernel.org, Mingming Cao To: OGAWA Hirofumi Return-path: Received: from e4.ny.us.ibm.com ([32.97.182.144]:34679 "EHLO e4.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752687Ab1EPSrk (ORCPT ); Mon, 16 May 2011 14:47:40 -0400 Content-Disposition: inline In-Reply-To: <87vcxipljj.fsf@devron.myhome.or.jp> Sender: linux-ext4-owner@vger.kernel.org List-ID: On Wed, May 11, 2011 at 01:28:32AM +0900, OGAWA Hirofumi wrote: > Jan Kara writes: > > >> Maybe possible, but you really think on usual case just blocking is > >> better? > > Define usual case... As Christoph noted, we don't currently have a real > > practical case where blocking would matter (since frequent rewrites are > > rather rare). So defining what is usual when we don't have a single real > > case is kind of tough ;) > > OK. E.g. usual workload on desktop, but FS like ext2/fat. In the frequent rewrite case, here's what you get: Regular disk: (possibly garbage) write, followed by a second write to make the disk reflect memory contents. RAID w/ shadow pages: two writes, both consistent. Higher memory consumption. T10 DIF disk: disk error any time the CPU modifies a page that the disk controller is DMA'ing out of memory. I suppose one could simply retry the operation if the page is dirty, but supposing memory writes are happening fast enough that the retries also produce disk errors, _nothing_ ever gets written. With the new stable-page-writes patchset, the garbage write/disk error symptoms go away since the processes block instead of creating this window where it's not clear whether the disk's copy of the data is consistent. I could turn the wait_on_page_writeback calls into some sort of page migration if the performance turns out to be terrible, though I'm still working on quantifying the impact. Some people pointed out that sqlite tends to write the same blocks frequently, though I wonder if sqlite actually tries to write memory pages while syncing them? One use case where I could see a serious performance hit happening is the case where some app writes a bunch of memory pages, calls sync to force the dirty pages to disk, and /must/ resume writing those memory pages before the sync completes. The page migration would of course help there, provided a memory page can be found in less time than an I/O operation. Someone commented on the LWN article about this topic, claiming that he had a program that couldn't afford to block on writes to mlock()'d memory. I'm not sure how to fix that program, because if memory writes never coordinate with disk writes and the other threads are always writing memory, I wonder how the copy on disk isn't always indeterminate. --D