From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755230AbYIGJfR (ORCPT ); Sun, 7 Sep 2008 05:35:17 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752844AbYIGJfF (ORCPT ); Sun, 7 Sep 2008 05:35:05 -0400 Received: from bombadil.infradead.org ([18.85.46.34]:54215 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752681AbYIGJfC (ORCPT ); Sun, 7 Sep 2008 05:35:02 -0400 Subject: Re: nice and hyperthreading on atom From: Peter Zijlstra To: Ulrich Drepper Cc: Arjan van de Ven , Phil Endecott , Linux Kernel Mailing List In-Reply-To: References: <1220715811849@dmwebmail.dmwebmail.chezphil.org> <20080906094248.5930911a@infradead.org> Content-Type: text/plain Date: Sun, 07 Sep 2008 11:34:58 +0200 Message-Id: <1220780098.8687.40.camel@twins.programming.kicks-ass.net> Mime-Version: 1.0 X-Mailer: Evolution 2.23.91 (2.23.91-1.fc10) Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sat, 2008-09-06 at 11:30 -0700, Ulrich Drepper wrote: > On Sat, Sep 6, 2008 at 9:42 AM, Arjan van de Ven wrote: > > As an OS one COULD decide to just not schedule the nice task at all, > > but then, especially on atom where HT has a high efficiency, your cpu > > is mostly idle ... > > One thread being idle is even on Atom the right thing to do in some > situations. If you have processes which, when HT is used, experience > high pressure on the common cache(s) then you should not schedule them > together. We can theoretically find out whether this is the case > using the PMCs. With perfmon2 hopefully on the horizon soon it might > actually be possible to automatically make these measurements. > > There is another aspect I talked to Peter about already. We really > want concurrent threat scheduling in some cases. For the > implementation of helper threads you don't want two threads to be > scheduled independently, you want them to be scheduled on a HT pair. > Currently this isn't possible except by pinning them to fixed threads. > We really want to have a new way to express this type of scheduling > (Peter, how did you call it?) Really helps if you make sure I'm on the CC ;-) I think I called it something like affinity grouping - but I'm still a bit scared of the bin-packing issues involved - those will really mess up the already complex balancing rules.