Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1424471AbWKKBBz (ORCPT ); Fri, 10 Nov 2006 20:01:55 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1424472AbWKKBBz (ORCPT ); Fri, 10 Nov 2006 20:01:55 -0500 Received: from omx2-ext.sgi.com ([192.48.171.19]:59611 "EHLO omx2.sgi.com") by vger.kernel.org with ESMTP id S1424471AbWKKBBy (ORCPT ); Fri, 10 Nov 2006 20:01:54 -0500 Date: Fri, 10 Nov 2006 17:01:27 -0800 (PST) From: Christoph Lameter To: Ingo Molnar cc: "Chen, Kenneth W" , "Siddha, Suresh B" , akpm@osdl.org, mm-commits@vger.kernel.org, nickpiggin@yahoo.com.au, linux-kernel@vger.kernel.org Subject: Re: + sched-use-tasklet-to-call-balancing.patch added to -mm tree In-Reply-To: <20061110213839.GA21928@elte.hu> Message-ID: References: <000001c70490$01cea4b0$8bc8180a@amr.corp.intel.com> <20061110213839.GA21928@elte.hu> 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: 1302 Lines: 26 On Fri, 10 Nov 2006, Ingo Molnar wrote: > ok, that's what i suspected - what made the difference wasnt the fact > that it was moved out of irqs-off section, but that it was running > globally, instead of in parallel on every cpu. I have no conceptual > problem with single-threading the more invasive load-balancing bits. > (since it has to touch every runqueue anyway there's probably little > parallelism possible) But it's a scary change nevertheless, it > materially affects every SMP system's balancing characteristics. We saw multiple issues. The first we saw was interrupt holdoff related since IPIs took a long time to complete. The other was that multiple load balance actions in multiple CPUs seem to serialize on the locks trying each to move tasks off the same busy processor. So both better be addressed. Load balancing for small domains is running faster so there is less chance of parallelism. It seems that the staggering of the timer interrupt is sufficient on smaller systems to avoid concurrent load balancing operations. - 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/