Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752725AbZG2OLS (ORCPT ); Wed, 29 Jul 2009 10:11:18 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751928AbZG2OLQ (ORCPT ); Wed, 29 Jul 2009 10:11:16 -0400 Received: from smtp-out.google.com ([216.239.33.17]:3449 "EHLO smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750776AbZG2OLQ convert rfc822-to-8bit (ORCPT ); Wed, 29 Jul 2009 10:11:16 -0400 DomainKey-Signature: a=rsa-sha1; s=beta; d=google.com; c=nofws; q=dns; h=mime-version:in-reply-to:references:date:message-id:subject:from:to: cc:content-type:content-transfer-encoding:x-system-of-record; b=d6tfNQQcWvcQ1gpJGCW1oxzUKUO74EzWuxLDVBRAymcBcHgbNjCovI/rAcKLN5r/1 l995T82Oc5+xydLEe/NRw== MIME-Version: 1.0 In-Reply-To: <20090729114322.GA9335@localhost> References: <1786ab030907281211x6e432ba6ha6afe9de73f24e0c@mail.gmail.com> <33307c790907281449k5e8d4f6cib2c93848f5ec2661@mail.gmail.com> <33307c790907290015m1e6b5666x9c0014cdaf5ed08@mail.gmail.com> <20090729114322.GA9335@localhost> Date: Wed, 29 Jul 2009 07:11:10 -0700 Message-ID: <33307c790907290711s320607b0i79c939104d4c2d61@mail.gmail.com> Subject: Re: Bug in kernel 2.6.31, Slow wb_kupdate writeout From: Martin Bligh To: Wu Fengguang Cc: Chad Talbott , linux-kernel@vger.kernel.org, linux-mm@kvack.org, Michael Rubin , Andrew Morton , sandeen@redhat.com, Michael Davidson Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT X-System-Of-Record: true Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4183 Lines: 77 > --- mm.orig/fs/fs-writeback.c > +++ mm/fs/fs-writeback.c > @@ -325,7 +325,8 @@ __sync_single_inode(struct inode *inode, > ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? * soon as the queue becomes uncongested. > ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? */ > ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?inode->i_state |= I_DIRTY_PAGES; > - ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? if (wbc->nr_to_write <= 0) { > + ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? if (wbc->nr_to_write <= 0 || > + ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? wbc->encountered_congestion) { > ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?/* > ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? * slice used up: queue for next turn > ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? */ > That's not sufficient - it only the problem in the wb_kupdate path. If you want to be more conservative, how about we do this? --- linux-2.6.30/fs/fs-writeback.c.old 2009-07-29 00:08:29.000000000 -0700 +++ linux-2.6.30/fs/fs-writeback.c 2009-07-29 07:08:48.000000000 -0700 @@ -323,43 +323,14 @@ __sync_single_inode(struct inode *inode, * We didn't write back all the pages. nfs_writepages( ) * sometimes bales out without doing anything. Redirty * the inode; Move it from s_io onto s_more_io/s_dirty. + * It may well have just encountered congestion */ - /* - * akpm: if the caller was the kupdate function we put - * this inode at the head of s_dirty so it gets first - * consideration. Otherwise, move it to the tail, for - * the reasons described there. I'm not really sure - * how much sense this makes. Presumably I had a good - * reasons for doing it this way, and I'd rather not - * muck with it at present. - */ - if (wbc->for_kupdate) { - /* - * For the kupdate function we move the inode - * to s_more_io so it will get more writeout as - * soon as the queue becomes uncongested. - */ - inode->i_state |= I_DIRTY_PAGES; - if (wbc->nr_to_write <= 0) { - /* - * slice used up: queue for next turn - */ - requeue_io(inode); - } else { - /* - * somehow blocked: retry later - */ - redirty_tail(inode); - } - } else { - /* - * Otherwise fully redirty the inode so that - * other inodes on this superblock will get som e - * writeout. Otherwise heavy writing to one - * file would indefinitely suspend writeout of - * all the other files. - */ - inode->i_state |= I_DIRTY_PAGES; + inode->i_state |= I_DIRTY_PAGES; + if (wbc->nr_to_write <= 0 || /* sliced used up */ + wbc->encountered_congestion) + requeue_io(inode); + else { + /* somehow blocked: retry later */ redirty_tail(inode); } } else if (inode->i_state & I_DIRTY) { -- 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/