From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756036Ab3LJInD (ORCPT ); Tue, 10 Dec 2013 03:43:03 -0500 Received: from cantor2.suse.de ([195.135.220.15]:58363 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753182Ab3LJInA (ORCPT ); Tue, 10 Dec 2013 03:43:00 -0500 Date: Tue, 10 Dec 2013 08:42:57 +0000 From: Mel Gorman To: Rik van Riel Cc: Andrew Morton , Alex Thorlton , Linux-MM , LKML , Drew Jones Subject: Re: [PATCH 17/18] sched: Tracepoint task movement Message-ID: <20131210084257.GD11295@suse.de> References: <1386572952-1191-1-git-send-email-mgorman@suse.de> <1386572952-1191-18-git-send-email-mgorman@suse.de> <52A611FB.7000305@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Disposition: inline In-Reply-To: <52A611FB.7000305@redhat.com> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Dec 09, 2013 at 01:54:51PM -0500, Rik van Riel wrote: > On 12/09/2013 02:09 AM, Mel Gorman wrote: > > move_task() is called from move_one_task and move_tasks and is an > > approximation of load balancer activity. We should be able to track > > tasks that move between CPUs frequently. If the tracepoint included node > > information then we could distinguish between in-node and between-node > > traffic for load balancer decisions. The tracepoint allows us to track > > local migrations, remote migrations and average task migrations. > > > > Signed-off-by: Mel Gorman > > Does this replicate the task_sched_migrate_task tracepoint in > set_task_cpu() ? > There is significant overlap but bits missing. We do not necessarily know where the task was previously running and whether this is a local->remote migration. We also cannot tell the difference between load balancer activity, numa balancing and try_to_wake_up. Still, you're right, this patch is not painting a full picture either. I'll drop it for now and look at improving the existing task_sched_migrate_task tracepoint. -- Mel Gorman SUSE Labs