From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754145Ab1IDCOa (ORCPT ); Sat, 3 Sep 2011 22:14:30 -0400 Received: from mga03.intel.com ([143.182.124.21]:57046 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752975Ab1IDCN2 (ORCPT ); Sat, 3 Sep 2011 22:13:28 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.68,326,1312182000"; d="scan'208";a="45377086" Message-Id: <20110904020916.460538138@intel.com> User-Agent: quilt/0.48-1 Date: Sun, 04 Sep 2011 09:53:19 +0800 From: Wu Fengguang to: cc: Peter Zijlstra , Wu Fengguang cc: Andrew Morton CC: Jan Kara CC: Christoph Hellwig CC: Dave Chinner CC: Greg Thelen CC: Minchan Kim CC: Vivek Goyal CC: Andrea Righi Cc: linux-mm Cc: LKML Subject: [PATCH 14/18] writeback: control dirty pause time References: <20110904015305.367445271@intel.com> Content-Disposition: inline; filename=max-pause-adaption Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The dirty pause time shall ultimately be controlled by adjusting nr_dirtied_pause, since there is relationship pause = pages_dirtied / task_ratelimit Assuming pages_dirtied ~= nr_dirtied_pause task_ratelimit ~= dirty_ratelimit We get nr_dirtied_pause ~= dirty_ratelimit * desired_pause Here dirty_ratelimit is preferred over task_ratelimit because it's more stable. It's also important to limit possible large transitional errors: - bw is changing quickly - pages_dirtied << nr_dirtied_pause on entering dirty exceeded area - pages_dirtied >> nr_dirtied_pause on btrfs (to be improved by a separate fix, but still expect non-trivial errors) So we end up using the above formula inside clamp_val(). The best test case for this code is to run 100 "dd bs=4M" tasks on btrfs and check its pause time distribution. Signed-off-by: Wu Fengguang --- mm/page-writeback.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) --- linux-next.orig/mm/page-writeback.c 2011-08-29 19:08:43.000000000 +0800 +++ linux-next/mm/page-writeback.c 2011-08-29 19:08:44.000000000 +0800 @@ -1193,7 +1193,20 @@ pause: if (!dirty_exceeded && bdi->dirty_exceeded) bdi->dirty_exceeded = 0; - current->nr_dirtied_pause = dirty_poll_interval(nr_dirty, dirty_thresh); + if (pause == 0) + current->nr_dirtied_pause = + dirty_poll_interval(nr_dirty, dirty_thresh); + else if (period <= max_pause / 4 && + pages_dirtied >= current->nr_dirtied_pause) + current->nr_dirtied_pause = clamp_val( + dirty_ratelimit * (max_pause / 2) / HZ, + pages_dirtied + pages_dirtied / 8, + pages_dirtied * 4); + else if (pause >= max_pause) + current->nr_dirtied_pause = 1 | clamp_val( + dirty_ratelimit * (max_pause * 3/8)/HZ, + pages_dirtied / 4, + pages_dirtied * 7/8); if (writeback_in_progress(bdi)) return; From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail138.messagelabs.com (mail138.messagelabs.com [216.82.249.35]) by kanga.kvack.org (Postfix) with SMTP id 88C116B018A for ; Sat, 3 Sep 2011 22:13:28 -0400 (EDT) Message-Id: <20110904020916.460538138@intel.com> Date: Sun, 04 Sep 2011 09:53:19 +0800 From: Wu Fengguang Subject: [PATCH 14/18] writeback: control dirty pause time References: <20110904015305.367445271@intel.com> Content-Disposition: inline; filename=max-pause-adaption Sender: owner-linux-mm@kvack.org List-ID: To: linux-fsdevel@vger.kernel.org Cc: Peter Zijlstra , Wu Fengguang , Andrew Morton , Jan Kara , Christoph Hellwig , Dave Chinner , Greg Thelen , Minchan Kim , Vivek Goyal , Andrea Righi , linux-mm , LKML The dirty pause time shall ultimately be controlled by adjusting nr_dirtied_pause, since there is relationship pause = pages_dirtied / task_ratelimit Assuming pages_dirtied ~= nr_dirtied_pause task_ratelimit ~= dirty_ratelimit We get nr_dirtied_pause ~= dirty_ratelimit * desired_pause Here dirty_ratelimit is preferred over task_ratelimit because it's more stable. It's also important to limit possible large transitional errors: - bw is changing quickly - pages_dirtied << nr_dirtied_pause on entering dirty exceeded area - pages_dirtied >> nr_dirtied_pause on btrfs (to be improved by a separate fix, but still expect non-trivial errors) So we end up using the above formula inside clamp_val(). The best test case for this code is to run 100 "dd bs=4M" tasks on btrfs and check its pause time distribution. Signed-off-by: Wu Fengguang --- mm/page-writeback.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) --- linux-next.orig/mm/page-writeback.c 2011-08-29 19:08:43.000000000 +0800 +++ linux-next/mm/page-writeback.c 2011-08-29 19:08:44.000000000 +0800 @@ -1193,7 +1193,20 @@ pause: if (!dirty_exceeded && bdi->dirty_exceeded) bdi->dirty_exceeded = 0; - current->nr_dirtied_pause = dirty_poll_interval(nr_dirty, dirty_thresh); + if (pause == 0) + current->nr_dirtied_pause = + dirty_poll_interval(nr_dirty, dirty_thresh); + else if (period <= max_pause / 4 && + pages_dirtied >= current->nr_dirtied_pause) + current->nr_dirtied_pause = clamp_val( + dirty_ratelimit * (max_pause / 2) / HZ, + pages_dirtied + pages_dirtied / 8, + pages_dirtied * 4); + else if (pause >= max_pause) + current->nr_dirtied_pause = 1 | clamp_val( + dirty_ratelimit * (max_pause * 3/8)/HZ, + pages_dirtied / 4, + pages_dirtied * 7/8); if (writeback_in_progress(bdi)) return; -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: email@kvack.org