From: Christoph Hellwig Subject: Re: [PATCH] JBD slab cleanups Date: Mon, 17 Sep 2007 20:34:43 +0100 Message-ID: <20070917193443.GA32013@infradead.org> References: <1188605538.3837.51.camel@localhost.localdomain> <20070901183922.GA12907@infradead.org> <20070902152801.GA19962@infradead.org> <20070903134043.GB28962@infradead.org> <20070903193308.GA7771@infradead.org> <1189796027.3841.6.camel@localhost.localdomain> <1190057391.3845.22.camel@localhost.localdomain> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Christoph Hellwig , pbadari@us.ibm.com, Christoph Lameter , linux-fsdevel@vger.kernel.org, ext4 development , linux-kernel@vger.kernel.org To: Mingming Cao Return-path: Content-Disposition: inline In-Reply-To: <1190057391.3845.22.camel@localhost.localdomain> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org On Mon, Sep 17, 2007 at 12:29:51PM -0700, Mingming Cao wrote: > The problem with this patch, as Andreas Dilger pointed today in ext4 > interlock call, for 1k,2k block size ext2/3/4, get_free_pages() waste > 1/3-1/2 page space. > > What was the originally intention to set up slabs for committed_data(and > frozen_buffer) in JBD? Why not using kmalloc? kmalloc is using slabs :) The intent was to avoid the wasted memory, but as we've repeated a gazillion times wasted memory on a rather rare codepath doesn't really matter when you just crash random storage drivers otherwise.