Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756912AbYCUMxR (ORCPT ); Fri, 21 Mar 2008 08:53:17 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753098AbYCUMxD (ORCPT ); Fri, 21 Mar 2008 08:53:03 -0400 Received: from fg-out-1718.google.com ([72.14.220.159]:23951 "EHLO fg-out-1718.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752471AbYCUMxA (ORCPT ); Fri, 21 Mar 2008 08:53:00 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=l1DgfFdgQiB6QKZJp6L/fK7Q3VWarnfqtXt0r+nvuT7MulcYAeFqKpBWW5hxKy3bcVWbW/5ic6I++KDKgzwYfKV1Lx5EOTUwZPu5Vf3y875PiWeOI3vQpo5WnIBjpPK6ll22ypdd2KqjiEnn27G/Os6ZpIqv15lk1yCj0n6+VaM= Message-ID: Date: Fri, 21 Mar 2008 13:52:59 +0100 From: "Bart Van Assche" To: "Nick Piggin" Subject: Re: quicklists confuse meminfo Cc: "Christoph Lameter" , "Andrew Morton" , "Ingo Molnar" , "KOSAKI Motohiro" , "Thomas Gleixner" , LKML , "Linus Torvalds" In-Reply-To: <200803111507.20870.nickpiggin@yahoo.com.au> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <20080309114640.85c9c3eb.akpm@linux-foundation.org> <200803111507.20870.nickpiggin@yahoo.com.au> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1049 Lines: 24 On Tue, Mar 11, 2008 at 5:07 AM, Nick Piggin wrote: > [ ... ] > > This is insane. We add more and more of this NUMA and cpuset and anti-frag > and page zeroing logic to the page allocator, and then decide that we > don't actually need to obey any of those rules when we're running lat_proc. > > You will never be able to make the page allocator faster than a single list > of pages. The reason is because we actually *want* some of these checks and > heuristics in the page allocator. > > And I doubt a list of zeroed pages is the right approach. That's just > adding more complexity for lat_proc AFAIKS. Is anyone currently working on this (http://bugzilla.kernel.org/show_bug.cgi?id=9991) ? I think this should either be fixed or documented as a known issue. Bart. -- 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/