From: Joel Becker Subject: Re: upcoming kerneloops.org item: get_page_from_freelist Date: Thu, 25 Jun 2009 14:05:49 -0700 Message-ID: <20090625210549.GM20311@mail.oracle.com> References: <20090624130121.99321cca.akpm@linux-foundation.org> <20090624150714.c7264768.akpm@linux-foundation.org> <20090625132544.GB9995@mit.edu> <20090625193806.GA6472@mit.edu> <20090625194423.GB6472@mit.edu> <20090625203743.GD6472@mit.edu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii To: Theodore Tso , David Rientjes , Andrew Morton , Linus Torvalds , penberg@cs.helsinki.fi, Return-path: Received: from acsinet11.oracle.com ([141.146.126.233]:36201 "EHLO acsinet11.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751225AbZFYVH5 (ORCPT ); Thu, 25 Jun 2009 17:07:57 -0400 Content-Disposition: inline In-Reply-To: <20090625203743.GD6472@mit.edu> Sender: linux-ext4-owner@vger.kernel.org List-ID: On Thu, Jun 25, 2009 at 04:37:43PM -0400, Theodore Tso wrote: > Nicely spotted. Yeah, that's a bug; we need to do something about > that one, too. And what we're doing is a bit silly; it may make sense > to use __get_free_pages if filesystem blocksize == PAGE_SIZE, but > otherwise we should be using a sub-page allocator. Right now, we're > chewing up a 16k PPC page for every 4k filesystem metadata page > allocated in journal_write_metadata_buffer(), and on x86, for the > (admittedly uncommon) 1k block filesystem, we'd be chewing up a 4k > page for a 1k block buffer. > > > Both of these problems exist for both ext3 and ext4. And ocfs2. Joel -- Life's Little Instruction Book #337 "Reread your favorite book." Joel Becker Principal Software Developer Oracle E-mail: joel.becker@oracle.com Phone: (650) 506-8127