From: Fengguang Wu Subject: Re: regression: 100% io-wait with 2.6.24-rcX Date: Mon, 14 Jan 2008 17:55:18 +0800 Message-ID: References: <200801071151.11200.lists@naasa.net> <200801130905.44855.jplatte@naasa.net> <400212488.11031@ustc.edu.cn> <200801131049.33111.jplatte@naasa.net> <20080113115933.GA11045@mail.ustc.edu.cn> <20080114035439.GA7330@mail.ustc.edu.cn> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Peter Zijlstra , Ingo Molnar , linux-kernel@vger.kernel.org, "linux-ext4@vger.kernel.org" To: Joerg Platte Return-path: Content-Disposition: inline In-Reply-To: <20080114035439.GA7330@mail.ustc.edu.cn> Message-Id: Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org On Mon, Jan 14, 2008 at 11:54:39AM +0800, Fengguang Wu wrote: > > particular this bug is triggered because the dir mapping page has > > PAGECACHE_TAG_DIRTY set and PG_dirty cleared, staying in an > > inconsistent state. > > Just found that a deleted dir will enter that inconsistent state when > someone still have reference to it... Joerg, this patch fixed the bug for me :-) Fengguang --- clear PAGECACHE_TAG_DIRTY for truncated page in block_write_full_page() The `truncated' page in block_write_full_page() may stick for a long time. E.g. ext2_rmdir() will set i_size to 0. The dir may still be referenced by someone, and have dirty pages in it. So clear PAGECACHE_TAG_DIRTY to prevent pdflush from retrying and iowaiting on it. Signed-off-by: Fengguang Wu --- fs/buffer.c | 2 ++ 1 files changed, 2 insertions(+) Index: linux/fs/buffer.c =================================================================== --- linux.orig/fs/buffer.c +++ linux/fs/buffer.c @@ -2820,7 +2820,9 @@ int block_write_full_page(struct page *p * freeable here, so the page does not leak. */ do_invalidatepage(page, 0); + set_page_writeback(page); unlock_page(page); + end_page_writeback(page); return 0; /* don't care */ }