From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934453Ab0KQEc4 (ORCPT ); Tue, 16 Nov 2010 23:32:56 -0500 Received: from mga02.intel.com ([134.134.136.20]:52857 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S934264Ab0KQEbj (ORCPT ); Tue, 16 Nov 2010 23:31:39 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.59,209,1288594800"; d="scan'208";a="574575910" Message-Id: <20101117042849.766920152@intel.com> User-Agent: quilt/0.48-1 Date: Wed, 17 Nov 2010 12:27:24 +0800 From: Wu Fengguang To: Andrew Morton CC: Jan Kara , Wu Fengguang CC: Christoph Hellwig CC: Dave Chinner CC: "Theodore Ts'o" CC: Chris Mason CC: Peter Zijlstra CC: Mel Gorman CC: Rik van Riel CC: KOSAKI Motohiro Cc: linux-mm Cc: Cc: LKML Subject: [PATCH 04/13] writeback: prevent duplicate balance_dirty_pages_ratelimited() calls References: <20101117042720.033773013@intel.com> Content-Disposition: inline; filename=writeback-fix-duplicate-bdp-calls.patch Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org When dd in 512bytes, balance_dirty_pages_ratelimited() used to be called 8 times for the same page, even if the page is only dirtied once. Fix it with a (slightly racy) PageDirty() test. Signed-off-by: Wu Fengguang --- mm/filemap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) --- linux-next.orig/mm/filemap.c 2010-11-16 22:20:08.000000000 +0800 +++ linux-next/mm/filemap.c 2010-11-16 22:45:05.000000000 +0800 @@ -2258,6 +2258,7 @@ static ssize_t generic_perform_write(str long status = 0; ssize_t written = 0; unsigned int flags = 0; + unsigned int dirty; /* * Copies from kernel address space cannot fail (NFSD is a big user). @@ -2306,6 +2307,7 @@ again: pagefault_enable(); flush_dcache_page(page); + dirty = PageDirty(page); mark_page_accessed(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); @@ -2332,7 +2334,8 @@ again: pos += copied; written += copied; - balance_dirty_pages_ratelimited(mapping); + if (!dirty) + balance_dirty_pages_ratelimited(mapping); } while (iov_iter_count(i));