Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934121AbXLMWLh (ORCPT ); Thu, 13 Dec 2007 17:11:37 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1762566AbXLMWL0 (ORCPT ); Thu, 13 Dec 2007 17:11:26 -0500 Received: from relay2.sgi.com ([192.48.171.30]:43533 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1759047AbXLMWLZ (ORCPT ); Thu, 13 Dec 2007 17:11:25 -0500 Date: Thu, 13 Dec 2007 14:11:24 -0800 (PST) From: Christoph Lameter X-X-Sender: clameter@schroedinger.engr.sgi.com To: Linus Torvalds cc: Steven Rostedt , LKML , Ingo Molnar , Peter Zijlstra , Christoph Hellwig Subject: Re: Major regression on hackbench with SLUB In-Reply-To: Message-ID: References: <1197049846.1645.68.camel@localhost.localdomain> 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: 885 Lines: 20 On Fri, 7 Dec 2007, Linus Torvalds wrote: > The biggest cost of __slab_alloc() in my profile is the "slab_lock()", but > that may not be the one that causes problems in a 64-cpu setup, so it > would be good to have that verified. Hmmmm.. This would indicate lock contention on a slab. > [ The whole node match thing is likely totally bogus. I suspect we pay > *more* in trying to match nodes than we'd ever likely pay in just > returning the wrong node for an allocation, but that's neither here nor > there ] Node match is necessary in order to make the allocator able to get memory for the node that the caller requested. -- 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/