Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754912AbYF0KAi (ORCPT ); Fri, 27 Jun 2008 06:00:38 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752567AbYF0KA1 (ORCPT ); Fri, 27 Jun 2008 06:00:27 -0400 Received: from styx.suse.cz ([82.119.242.94]:41411 "EHLO mail.suse.cz" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1752226AbYF0KA0 (ORCPT ); Fri, 27 Jun 2008 06:00:26 -0400 Date: Fri, 27 Jun 2008 12:00:24 +0200 From: Jan Kara To: "Aneesh Kumar K.V" Cc: Mingming , Holger Kiehl , Theodore Tso , Eric Sandeen , Jan Kara , Solofo.Ramangalahy@bull.net, Nick Dokos , linux-ext4@vger.kernel.org, linux-kernel Subject: Re: Performance of ext4 Message-ID: <20080627100024.GB3602@duck.suse.cz> References: <20080623174508.GA7216@skywalker> <1214267492.27507.285.camel@BVR-FS.beaverton.ibm.com> <20080624030721.GB10469@skywalker> <20080624033349.GD10469@skywalker> <1214348318.27507.330.camel@BVR-FS.beaverton.ibm.com> <1214441199.27507.351.camel@BVR-FS.beaverton.ibm.com> <20080627091459.GA32723@skywalker> <20080627094913.GB32723@skywalker> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20080627094913.GB32723@skywalker> User-Agent: Mutt/1.5.16 (2007-06-09) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3651 Lines: 99 On Fri 27-06-08 15:19:13, Aneesh Kumar K.V wrote: > On Fri, Jun 27, 2008 at 02:44:59PM +0530, Aneesh Kumar K.V wrote: > > On Wed, Jun 25, 2008 at 05:46:39PM -0700, Mingming wrote: > > > > > > On Wed, 2008-06-25 at 09:09 +0000, Holger Kiehl wrote: > > > > On Tue, 24 Jun 2008, Mingming wrote: > > > > > > > > > > > > > > On Tue, 2008-06-24 at 21:12 +0000, Holger Kiehl wrote: > > > > >> Yes, with this patch applied on top of latest patch queue I no longer > > > > >> get truncated files, after running a short test. Tomorrow I will do some > > > > >> more thorough testing and use the patch you have send to me in a separate > > > > >> mail. The above patch did not apply but it was easy to apply by hand. > > > > > > > > > > > > > > > Thanks for quick response and test. I have updated the patch queue with > > > > > above patch merged. Please let me know if you still see apply issue and > > > > > file size update issue with current patch queue. > > > > > > > > > Thanks, it applies without any problems. However I still hit an oops. What > > > > I find strange is that I got the oops just as the benchmark is done and > > > > all process where shutting down. The same behaviour I reported here: > > > > http://www.ussg.iu.edu/hypermail/linux/kernel/0806.2/2113.html > > > > Only this time I got just one oops. This is on x86_64 system (4 Opteron CPU's > > > > and SW Raid 1+0). I have not seen this on my home system x86 (1 Dual Core > > > > and HW Raid). Anyway, here the dmesg output: > > > > > > > > kjournald2 starting. Commit interval 15 seconds > > > > EXT4 FS on md7, internal journal > > > > EXT4-fs: mounted filesystem with ordered data mode. > > > > EXT4-fs: file extents enabled > > > > EXT4-fs: mballoc enabled > > > > JBD: barrier-based sync failed on md7 - disabling barriers > > > > ------------[ cut here ]------------ > > > > kernel BUG at fs/ext4/inode.c:1667! > > > > > > Did not get a chance to look more closely today, but it's point to this > > > code in ext4_da_writepage() > > > > > > page_bufs = page_buffers(page); > > > > > > and appearently it's BUG_ON at > > > BUG_ON(!PagePrivate(page)); in page_buffers(). > > > > > > > > > > Ok so we are doing the journal_commit and meanwhile shrink_page_list > > dropped the buffer. I guess what is happening is > > > > > > journal_submit_inode_data_buffers > > generic_writepages > > write_cache_pages > > pagevec_lookup_tag(..PAGECACHE_TAG_DIRTY,..) > > foreach(page) > > shrink_page_list > > lock_page > > ext4_releasepage > > try_to_free_buffers > > drop_buffers > > cancel_dirty_page > > unlock_page > > lock_page() > > BUG_ON(!PagePrivate(page)); > > > > > > How about the below ? > > or update write_cache_pages not to call writepage if the page is not > dirty ? But that is already happening :) Look a few lines above your patch into clear_page_dirty_for_io()... Honza > diff --git a/mm/page-writeback.c b/mm/page-writeback.c > index ded57d5..0a13702 100644 > --- a/mm/page-writeback.c > +++ b/mm/page-writeback.c > @@ -929,6 +929,11 @@ int write_cache_pages(struct address_space *mapping, > continue; > } > > + if (!PageDirty(page)) { > + unlock_page(page); > + continue; > + } > + > ret = (*writepage)(page, wbc, data); > > if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE)) { -- Jan Kara SUSE Labs, CR -- 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/