From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752397AbbJFMRX (ORCPT ); Tue, 6 Oct 2015 08:17:23 -0400 Received: from mail-wi0-f195.google.com ([209.85.212.195]:32995 "EHLO mail-wi0-f195.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751382AbbJFMRW (ORCPT ); Tue, 6 Oct 2015 08:17:22 -0400 Message-ID: <1444133838.2832.141.camel@gmail.com> Subject: Re: CFS scheduler unfairly prefers pinned tasks From: Mike Galbraith To: paul.szabo@sydney.edu.au Cc: linux-kernel@vger.kernel.org Date: Tue, 06 Oct 2015 14:17:18 +0200 In-Reply-To: <201510061006.t96A69I8007672@como.maths.usyd.edu.au> References: <201510061006.t96A69I8007672@como.maths.usyd.edu.au> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.12.11 Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2015-10-06 at 21:06 +1100, paul.szabo@sydney.edu.au wrote: > And further... the CFS is meant to be fair, using things like vruntime > to preempt, and throttling. Why are those pinned tasks not preempted or > throttled? Imagine you own a 8192 CPU box for a moment, all CPUs having one pinned task, plus one extra unpinned task, and ponder what would have to happen in order to meet your utilization expectation.