From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from cuda.sgi.com (cuda1.sgi.com [192.48.157.11]) by oss.sgi.com (8.14.3/8.14.3/SuSE Linux 0.8) with ESMTP id q0CHPL66008500 for ; Thu, 12 Jan 2012 11:25:21 -0600 Received: from ustc.edu.cn (smtp2.ustc.edu.cn [202.38.64.46]) by cuda.sgi.com with SMTP id WQHGBbtdZNBfJ5Na for ; Thu, 12 Jan 2012 09:25:18 -0800 (PST) Date: Fri, 13 Jan 2012 01:30:28 +0800 From: JiSheng Zhang Subject: [PATCH] xfs: remove unecessary AIL push wakeups Message-ID: <20120113013028.6802d878@ustc> Mime-Version: 1.0 List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: xfs-bounces@oss.sgi.com Errors-To: xfs-bounces@oss.sgi.com To: xfs@oss.sgi.com, elder@kernel.org Cc: linux-kernel@vger.kernel.org In commit 0030807c66("xfs: revert to using a kthread for AIL pushing"), AIL pushing is revert back to use a kthread. But unfortunately, it introduced a regression: there are unnecessary AIL push wakeups during idle, ~20 wakeups/s. This change remove the wakeups by reverting a bit more: set "tout" value as zero during idle. Signed-off-by: JiSheng Zhang --- fs/xfs/xfs_trans_ail.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index ed9252b..2014387 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -508,7 +508,7 @@ out_done: ailp->xa_last_pushed_lsn = 0; ailp->xa_log_flush = 0; - tout = 50; + tout = 0; } else if (XFS_LSN_CMP(lsn, target) >= 0) { /* * We reached the target so wait a bit longer for I/O to -- 1.7.8.3 _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs