From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756473AbZEEL5V (ORCPT ); Tue, 5 May 2009 07:57:21 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752007AbZEEL5J (ORCPT ); Tue, 5 May 2009 07:57:09 -0400 Received: from bilbo.ozlabs.org ([203.10.76.25]:43441 "EHLO bilbo.ozlabs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751908AbZEEL5I (ORCPT ); Tue, 5 May 2009 07:57:08 -0400 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <18944.10637.877638.642187@cargo.ozlabs.ibm.com> Date: Tue, 5 May 2009 21:57:01 +1000 From: Paul Mackerras To: Ingo Molnar Cc: Robert Richter , Peter Zijlstra , Thomas Gleixner , linux-kernel@vger.kernel.org, Mike Galbraith Subject: Re: round-robining per-cpu counters In-Reply-To: <20090505064051.GA27191@elte.hu> References: <18943.47474.963294.862139@drongo.ozlabs.ibm.com> <20090505064051.GA27191@elte.hu> X-Mailer: VM 8.0.12 under 22.2.1 (i486-pc-linux-gnu) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Ingo Molnar writes: > The reservation mechanism really suffered from not being used by > anything or anyone, and it thus bit-rotted across 300 follow-on > commits. Yeah. > What would be the primary usecase? Allow admin to set aside (and > guarantee) space for task counters? Allow admin to 'force' > exclusivity of counter ownership? > > I think a better general solution would be to have a single > round-robin list for all currently active counters (both percpu and > task counters) - and fairly round-robin all of them. The scaling > information makes it obvious when this is happening. Sounds good, but I'm having trouble visualizing how we combine a fairly static set of per-cpu counters with several sets of per-task counters that come and go as their tasks get scheduled in and out. Is there some clever scheduling technique that sorts all that out? > If admin wants stronger ownership of counters then the > pinned/exclusive attribute can be used. I agree. > We really want to keep the counter-scheduler simple, and we also > want to make the default to be as permissive as possible. Definitely. Paul.