Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757236Ab1BJWW3 (ORCPT ); Thu, 10 Feb 2011 17:22:29 -0500 Received: from mga09.intel.com ([134.134.136.24]:55589 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757161Ab1BJWW1 (ORCPT ); Thu, 10 Feb 2011 17:22:27 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.60,451,1291622400"; d="scan'208";a="601489535" Date: Thu, 10 Feb 2011 14:22:21 -0800 From: jacob pan To: Matt Helsley Cc: Arjan van de Ven , LKML , "Kirill A. Shutemov" , container cgroup , Li Zefan , Paul Menage , akpm@linux-foundation.org, rdunlap@xenotime.net, Cedric Le Goater , Wysocki Rafael Wysocki Subject: Re: [PATCH 1/1, v6] cgroup/freezer: add per freezer duty ratio control Message-ID: <20110210142221.6b984e45@jacob-laptop> In-Reply-To: <20110210191117.GI16432@count0.beaverton.ibm.com> References: <1297213541-18156-1-git-send-email-jacob.jun.pan@linux.intel.com> <20110210030442.GG16432@count0.beaverton.ibm.com> <4D535627.9090606@linux.intel.com> <20110210191117.GI16432@count0.beaverton.ibm.com> Organization: OTC X-Mailer: Claws Mail 3.7.4 (GTK+ 2.20.1; i486-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2706 Lines: 60 On Thu, 10 Feb 2011 11:11:17 -0800 Matt Helsley wrote: > On Wed, Feb 09, 2011 at 07:06:15PM -0800, Arjan van de Ven wrote: > > On 2/9/2011 7:04 PM, Matt Helsley wrote: > > >On Tue, Feb 08, 2011 at 05:05:41PM -0800, > > >jacob.jun.pan@linux.intel.com wrote: > > >>From: Jacob Pan > > >> > > >>Freezer subsystem is used to manage batch jobs which can start > > >>stop at the same time. However, sometime it is desirable to let > > >>the kernel manage the freezer state automatically with a given > > >>duty ratio. > > >>For example, if we want to reduce the time that backgroup apps > > >>are allowed to run we can put them into a freezer subsystem and > > >>set the kernel to turn them THAWED/FROZEN at given duty ratio. > > >> > > >>This patch introduces two file nodes under cgroup > > >>freezer.duty_ratio_pct and freezer.period_sec > > >> > > >>Usage example: set period to be 5 seconds and frozen duty ratio > > >>90% [root@localhost aoa]# echo 90> freezer.duty_ratio_pct > > >>[root@localhost aoa]# echo 5000> freezer.period_ms > > >I kept wondering how this was useful when we've got the "cpu" > > >subsystem because for some reason "duty cycle" made me think this > > >was a scheduling policy knob. In fact, I'm pretty sure it is -- it > > >just happens to sometimes reduce power consumption. > > > > > >Have you tried using the cpu cgroup subsystem's share to see if it > > >can have a similar effect? > > > > does the cpu cgroup system work on a 20 to 30 second time window? > > I don't think so -- it works directly with the scheduler IIRC. > I played with cpu subsystem a little today, it is for real-time tasks only. By data type of cpu.rt_period_us cpu.rt_runtime_us, it actually has a pretty long time window (35 mins, int type at usec resolution). For some reason, I could not even get cpu subsystem to work with RT task to work on 38-rc2 kernel. Here is what I did - mount and create cpu cgroup fs - launch task with SCHED_RR - attach task to my newly created cgroup - adjust cpu.rt_period_us cpu.rt_runtime_us But it never changed percentage of runtime. The ask in the cpu cgroup always run at 100% or more than the runtime_us as I specified. I have tried both with system idle and background tasks. I do agree that dealing with group scheduler directly might be more natural. but the hurdle might be changing cpu subsystem to support non-rt, and deal with scheduler heuristics. -- 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/