From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S264686AbUEOTbL (ORCPT ); Sat, 15 May 2004 15:31:11 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S264692AbUEOTbC (ORCPT ); Sat, 15 May 2004 15:31:02 -0400 Received: from ns.virtualhost.dk ([195.184.98.160]:38608 "EHLO virtualhost.dk") by vger.kernel.org with ESMTP id S264686AbUEOTa0 (ORCPT ); Sat, 15 May 2004 15:30:26 -0400 Date: Sat, 15 May 2004 19:30:04 +0200 From: Jens Axboe To: Christoph Hellwig , torvalds@osdl.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH] slabify iocontext + request_queue Message-ID: <20040515173004.GA962@suse.de> References: <20040515190735.A4189@infradead.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20040515190735.A4189@infradead.org> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Sat, May 15 2004, Christoph Hellwig wrote: > this just went in: > > > From: Jens Axboe > > > > Move both request_queue and io_context allocation to a slab cache. > > > > This is mainly a space-saving exercise. Some setups have a lot of disks > > and the kmalloc rounding-up can consume significant amounts of memory. > > While I agree on the io_context part, slabifying request_queue is a space > waste on most machines out there. The averange desktop has less than a > handfull of these, and even for smaller servers it doesn't exactly look > like a gain. See the thread last week on queue congestion threshold calculations, there were some numbers in there. -- Jens Axboe