From mboxrd@z Thu Jan 1 00:00:00 1970 From: akpm@linux-foundation.org Subject: + mm-avoid-resetting-wb_start-after-each-writeback-round.patch added to -mm tree Date: Thu, 05 Aug 2010 17:21:51 -0700 Message-ID: <201008060021.o760LpSl014748@imap1.linux-foundation.org> Reply-To: linux-kernel@vger.kernel.org Return-path: Received: from smtp1.linux-foundation.org ([140.211.169.13]:48672 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S934047Ab0HFAWx (ORCPT ); Thu, 5 Aug 2010 20:22:53 -0400 Sender: mm-commits-owner@vger.kernel.org List-Id: mm-commits@vger.kernel.org To: mm-commits@vger.kernel.org Cc: jack@suse.cz, axboe@kernel.dk, fengguang.wu@intel.com, hch@lst.de The patch titled mm: avoid resetting wb_start after each writeback round has been added to the -mm tree. Its filename is mm-avoid-resetting-wb_start-after-each-writeback-round.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find out what to do about this The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: mm: avoid resetting wb_start after each writeback round From: Jan Kara WB_SYNC_NONE writeback is done in rounds of 1024 pages so that we don't write out some huge inode for too long while starving writeout of other inodes. To avoid livelocks, we record time we started writeback in wbc->wb_start and do not write out inodes which were dirtied after this time. But currently, writeback_inodes_wb() resets wb_start each time it is called thus effectively invalidating this logic and making any WB_SYNC_NONE writeback prone to livelocks. This patch makes sure wb_start is set only once when we start writeback. Signed-off-by: Jan Kara Reviewed-by: Wu Fengguang Cc: Christoph Hellwig Cc: Jens Axboe Signed-off-by: Andrew Morton --- fs/fs-writeback.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff -puN fs/fs-writeback.c~mm-avoid-resetting-wb_start-after-each-writeback-round fs/fs-writeback.c --- a/fs/fs-writeback.c~mm-avoid-resetting-wb_start-after-each-writeback-round +++ a/fs/fs-writeback.c @@ -524,7 +524,8 @@ void writeback_inodes_wb(struct bdi_writ { int ret = 0; - wbc->wb_start = jiffies; /* livelock avoidance */ + if (!wbc->wb_start) + wbc->wb_start = jiffies; /* livelock avoidance */ spin_lock(&inode_lock); if (!wbc->for_kupdate || list_empty(&wb->b_io)) queue_io(wb, wbc->older_than_this); @@ -553,7 +554,6 @@ static void __writeback_inodes_sb(struct { WARN_ON(!rwsem_is_locked(&sb->s_umount)); - wbc->wb_start = jiffies; /* livelock avoidance */ spin_lock(&inode_lock); if (!wbc->for_kupdate || list_empty(&wb->b_io)) queue_io(wb, wbc->older_than_this); @@ -619,6 +619,7 @@ static long wb_writeback(struct bdi_writ wbc.range_end = LLONG_MAX; } + wbc.wb_start = jiffies; /* livelock avoidance */ for (;;) { /* * Stop writeback when nr_pages has been consumed _ Patches currently in -mm which might be from jack@suse.cz are origin.patch linux-next.patch radix-tree-implement-function-radix_tree_range_tag_if_tagged.patch mm-implement-writeback-livelock-avoidance-using-page-tagging.patch writeback-reduce-calls-to-global_page_state-in-balance_dirty_pages.patch writeback-reduce-calls-to-global_page_state-in-balance_dirty_pages-update.patch writeback-dont-redirty-tail-an-inode-with-dirty-pages.patch mm-fix-writeback_in_progress.patch mm-avoid-resetting-wb_start-after-each-writeback-round.patch aio-do-not-return-erestartsys-and-friends-from-aio.patch reiser4.patch