From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from cuda.sgi.com (cuda3.sgi.com [192.48.176.15]) by oss.sgi.com (8.14.3/8.14.3/SuSE Linux 0.8) with ESMTP id o3D1IfcZ177908 for ; Mon, 12 Apr 2010 20:18:42 -0500 Received: from mail.internode.on.net (localhost [127.0.0.1]) by cuda.sgi.com (Spam Firewall) with ESMTP id ACF131269E0B for ; Mon, 12 Apr 2010 18:20:34 -0700 (PDT) Received: from mail.internode.on.net (bld-mail16.adl2.internode.on.net [150.101.137.101]) by cuda.sgi.com with ESMTP id YiNWwq4XkJ7FQjlr for ; Mon, 12 Apr 2010 18:20:34 -0700 (PDT) From: Dave Chinner Subject: [PATCH 0/2] Context sensitive memory shrinker support Date: Tue, 13 Apr 2010 10:24:13 +1000 Message-Id: <1271118255-21070-1-git-send-email-david@fromorbit.com> List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 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: linux-kernel@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org, linux-mm@kvack.org, xfs@oss.sgi.com Recently I made the XFS inode reclaim operate entirely in the background for both clean and dirty inodes as it simplified the code a lot and is somewhat more efficient. Unfortunately, there are some workloads where the background reclaim is not freeing memory fast enough, so the reclaim needs an extra push when memory is low. The inode caches are per-filesystem on XFS, so to make effective use of the shrinker callbacks when memory is low, we need a context to be passed through the shrinker to give us the filesystem context to run the reclaim from. The two patches introduce the shrinker context and implement the XFS inode reclaim shrinkers. _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs