Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759709AbYAJPp1 (ORCPT ); Thu, 10 Jan 2008 10:45:27 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754301AbYAJPpR (ORCPT ); Thu, 10 Jan 2008 10:45:17 -0500 Received: from waste.org ([66.93.16.53]:54131 "EHLO waste.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754032AbYAJPpP (ORCPT ); Thu, 10 Jan 2008 10:45:15 -0500 Subject: Re: [RFC PATCH] greatly reduce SLOB external fragmentation From: Matt Mackall To: Pekka J Enberg Cc: Christoph Lameter , Ingo Molnar , Linus Torvalds , Hugh Dickins , Andi Kleen , Peter Zijlstra , Linux Kernel Mailing List In-Reply-To: References: <84144f020801021109v78e06c6k10d26af0e330fc85@mail.gmail.com> <1199314218.4497.109.camel@cinder.waste.org> <20080103085239.GA10813@elte.hu> <1199378818.8274.25.camel@cinder.waste.org> <1199419890.4608.77.camel@cinder.waste.org> <1199641910.8215.28.camel@cinder.waste.org> <1199906151.6245.57.camel@cinder.waste.org> <1199919548.6245.74.camel@cinder.waste.org> Content-Type: text/plain Date: Thu, 10 Jan 2008 09:44:17 -0600 Message-Id: <1199979858.5331.15.camel@cinder.waste.org> Mime-Version: 1.0 X-Mailer: Evolution 2.12.2 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1444 Lines: 37 On Thu, 2008-01-10 at 12:54 +0200, Pekka J Enberg wrote: > Hi Matt, > > On Thu, 10 Jan 2008, Pekka J Enberg wrote: > > I'll double check the results for SLUB next but it seems obvious that your > > patches are a net gain for SLOB and should be applied. One problem though > > with SLOB seems to be that its memory efficiency is not so stable. Any > > ideas why that is? We're seeing different numbers in each allocator indicating that the ordering of allocations is not stable. When fragmentation occurs, it magnifies the underlying instability. On my config, where the split list combats fragmentation extremely effectively, the stability is quite good. Perhaps I'll add a printk to allocs and generate some size histograms. lguest + grep = relayfs for dummies. > Ok, I did that. The number are stable and reproducible. In fact, the > average for SLUB is within 1 KB of the previous numbers. So, we have the > same .config, the same userspace, and the same hypervisor, so what's the > difference here? I've got: gcc version 4.2.3 20080102 (prerelease) (Debian 4.2.2-5) BusyBox v1.2.1 (2006.11.01-11:21+0000) Built-in shell (ash) -- Mathematics is the supreme nostalgia of our time. -- 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/