Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758914AbYCNVJm (ORCPT ); Fri, 14 Mar 2008 17:09:42 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754789AbYCNVJd (ORCPT ); Fri, 14 Mar 2008 17:09:33 -0400 Received: from relay2.sgi.com ([192.48.171.30]:50606 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1754424AbYCNVJd (ORCPT ); Fri, 14 Mar 2008 17:09:33 -0400 Date: Fri, 14 Mar 2008 14:08:36 -0700 (PDT) From: Christoph Lameter X-X-Sender: clameter@schroedinger.engr.sgi.com To: "Zhang, Yanmin" cc: Andrew Morton , Kay Sievers , Greg Kroah-Hartman , LKML , Ingo Molnar Subject: Re: hackbench regression since 2.6.25-rc In-Reply-To: <1205478861.3215.279.camel@ymzhang> Message-ID: References: <1205394417.3215.85.camel@ymzhang> <20080313014808.f8d25c2a.akpm@linux-foundation.org> <1205400538.3215.148.camel@ymzhang> <1205463842.3215.188.camel@ymzhang> <1205478861.3215.279.camel@ymzhang> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1361 Lines: 36 On Fri, 14 Mar 2008, Zhang, Yanmin wrote: > > Ahhh... Okay those slabs did not change for 2.6.25-rc. Is there > > really a difference to 2.6.24? > As oprofile shows slub functions spend more than 80% cpu time, I would like > to focus on optimizing SLUB before going back to 2.6.24. I thought you wanted to address a regression vs 2.6.24? > kmalloc-512: No NUMA information available. > > Slab Perf Counter Alloc Free %Al %Fr > -------------------------------------------------- > Fastpath 55039159 5006829 68 6 > Slowpath 24975754 75007769 31 93 > Page Alloc 73840 73779 0 0 > Add partial 0 24341085 0 30 > Remove partial 24267297 73779 30 0 ^^^ add partial/remove partial is likely the cause for trouble here. 30% is unacceptably high. The larger allocs will reduce the partial handling overhead. That is likely the effect that we see here. > Refill 24975738 Duh refills at 50%? We could try to just switch to another slab instead of reusing the existing one. May also affect the add/remove partial situation. -- 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/