Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759708AbXHBSdv (ORCPT ); Thu, 2 Aug 2007 14:33:51 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1759011AbXHBSdm (ORCPT ); Thu, 2 Aug 2007 14:33:42 -0400 Received: from dvhart.com ([64.146.134.43]:46027 "EHLO dvhart.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756323AbXHBSdl (ORCPT ); Thu, 2 Aug 2007 14:33:41 -0400 Message-ID: <46B22383.5020109@mbligh.org> Date: Thu, 02 Aug 2007 11:33:39 -0700 From: Martin Bligh User-Agent: Thunderbird 1.5.0.12 (X11/20070604) MIME-Version: 1.0 To: Nick Piggin Cc: Lee Schermerhorn , Andi Kleen , Ingo Molnar , Linux Kernel Mailing List , Linux Memory Management List , Eric Whitney Subject: Re: [rfc] balance-on-fork NUMA placement References: <20070731054142.GB11306@wotan.suse.de> <200707311114.09284.ak@suse.de> <20070801002313.GC31006@wotan.suse.de> <46B0C8A3.8090506@mbligh.org> <1185993169.5059.79.camel@localhost> <46B10E9B.2030907@mbligh.org> <20070802013631.GA15595@wotan.suse.de> In-Reply-To: <20070802013631.GA15595@wotan.suse.de> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1665 Lines: 34 Nick Piggin wrote: > On Wed, Aug 01, 2007 at 03:52:11PM -0700, Martin Bligh wrote: >>> And so forth. Initial forks will balance. If the children refuse to >>> die, forks will continue to balance. If the parent starts seeing short >>> lived children, fork()s will eventually start to stay local. >> Fork without exec is much more rare than without. Optimising for >> the uncommon case is the Wrong Thing to Do (tm). What we decided > > It's only the wrong thing to do if it hurts the common case too > much. Considering we _already_ balance on exec, then adding another > balance on fork is not going to introduce some order of magnitude > problem -- at worst it would be 2x but it really isn't too slow > anyway (at least nobody complained when we added it). > > One place where we found it helps is clone for threads. > > If we didn't do such a bad job at keeping tasks together with their > local memory, then we might indeed reduce some of the balance-on-crap > and increase the aggressiveness of periodic balancing. > > Considering we _already_ balance on fork/clone, I don't know what > your argument is against this patch is? Doing the balance earlier > and allocating more stuff on the local node is surely not a bad > idea. I don't know who turned that on ;-( I suspect nobody bothered actually measuring it at the time though, or used some crap benchmark like stream to do so. It should get reverted. - 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/