Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1750767AbVKERJR (ORCPT ); Sat, 5 Nov 2005 12:09:17 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1750783AbVKERJR (ORCPT ); Sat, 5 Nov 2005 12:09:17 -0500 Received: from ns2.suse.de ([195.135.220.15]:13021 "EHLO mx2.suse.de") by vger.kernel.org with ESMTP id S1750767AbVKERJQ (ORCPT ); Sat, 5 Nov 2005 12:09:16 -0500 To: Paul Jackson Cc: akpm@osdl.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH]: Clean up of __alloc_pages References: <20051028183326.A28611@unix-os.sc.intel.com> <20051029171630.04a69660.pj@sgi.com> From: Andi Kleen Date: 05 Nov 2005 18:09:14 +0100 In-Reply-To: <20051029171630.04a69660.pj@sgi.com> Message-ID: User-Agent: Gnus/5.09 (Gnus v5.9.0) Emacs/21.3 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 735 Lines: 18 Paul Jackson writes: Regarding cpumemset and alloc_pages. I recently rechecked the cpumemset hooks in there and I must say they turned out to be quite worse In hindsight it would have been better to use the "generate zonelists for all possible nodes" approach you originally had and which I rejected (sorry) That would make the code much cleaner and faster. Maybe it's not too late to switch for that? If not then the fast path definitely needs to be tuned a bit. -Andi - 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/