Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752286AbZIXGyX (ORCPT ); Thu, 24 Sep 2009 02:54:23 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752007AbZIXGyV (ORCPT ); Thu, 24 Sep 2009 02:54:21 -0400 Received: from mga02.intel.com ([134.134.136.20]:24771 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751816AbZIXGyV (ORCPT ); Thu, 24 Sep 2009 02:54:21 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.44,444,1249282800"; d="scan'208";a="451211214" Subject: [RFC] page-writeback: move indoes from one superblock together From: Shaohua Li To: lkml Cc: "jens.axboe@oracle.com" , Peter Zijlstra , Andrew Morton , "Wu, Fengguang" , Chris Mason Content-Type: multipart/mixed; boundary="=-0Hp2fY4vZvzFvq5IqZad" Date: Thu, 24 Sep 2009 14:54:20 +0800 Message-Id: <1253775260.10618.10.camel@sli10-desk.sh.intel.com> Mime-Version: 1.0 X-Mailer: Evolution 2.26.1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2639 Lines: 90 --=-0Hp2fY4vZvzFvq5IqZad Content-Type: text/plain Content-Transfer-Encoding: 7bit __mark_inode_dirty adds inode to wb dirty list in random order. If a disk has several partitions, writeback might keep spindle moving between partitions. To reduce the move, better write big chunk of one partition and then move to another. Inodes from one fs usually are in one partion, so idealy move indoes from one fs together should reduce spindle move. This patch tries to address this. Before per-bdi writeback is added, the behavior is write indoes from one fs first and then another, so the patch restores previous behavior. The loop in the patch is a bit ugly, should we add a dirty list for each superblock in bdi_writeback? Test in a two partition disk with attached fio script shows about 3% ~ 6% improvement. Signed-off-by: Shaohua Li diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 8e1e5e1..fc87730 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -324,13 +324,29 @@ static void move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, unsigned long *older_than_this) { + LIST_HEAD(tmp); + struct list_head *pos, *node; + struct super_block *sb; + struct inode *inode; + while (!list_empty(delaying_queue)) { - struct inode *inode = list_entry(delaying_queue->prev, - struct inode, i_list); + inode = list_entry(delaying_queue->prev, struct inode, i_list); if (older_than_this && inode_dirtied_after(inode, *older_than_this)) break; - list_move(&inode->i_list, dispatch_queue); + list_move(&inode->i_list, &tmp); + } + + /* Move indoes from one superblock together */ + while (!list_empty(&tmp)) { + inode = list_entry(tmp.prev, struct inode, i_list); + sb = inode->i_sb; + list_for_each_prev_safe(pos, node, &tmp) { + struct inode *inode = list_entry(pos, + struct inode, i_list); + if (inode->i_sb == sb) + list_move(&inode->i_list, dispatch_queue); + } } } --=-0Hp2fY4vZvzFvq5IqZad Content-Disposition: attachment; filename="newfio" Content-Type: text/plain; name="newfio"; charset="UTF-8" Content-Transfer-Encoding: 7bit [global] runtime=120 ioscheduler=cfq size=2G ioengine=sync rw=write file_service_type=random:256 overwrite=1 [sdb1] directory=/mnt/b1 nrfiles=10 numjobs=4 [sdb2] directory=/mnt/b2 nrfiles=10 numjobs=4 --=-0Hp2fY4vZvzFvq5IqZad-- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/