From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752193AbbFKN6q (ORCPT ); Thu, 11 Jun 2015 09:58:46 -0400 Received: from mail-la0-f68.google.com ([209.85.215.68]:34630 "EHLO mail-la0-f68.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751101AbbFKN6j (ORCPT ); Thu, 11 Jun 2015 09:58:39 -0400 Message-ID: <1434031116.4051.18.camel@gmail.com> Subject: Re: RFC: futex_wait() can DoS the tick From: Mike Galbraith To: Thomas Gleixner Cc: LKML , Peter Zijlstra , Ingo Molnar , Steven Rostedt Date: Thu, 11 Jun 2015 15:58:36 +0200 In-Reply-To: References: <1433940278.6814.66.camel@gmail.com> <1433957421.6306.28.camel@gmail.com> <1433989634.3411.15.camel@gmail.com> <1434022875.4051.5.camel@gmail.com> 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 Thu, 2015-06-11 at 15:13 +0200, Thomas Gleixner wrote: > What you are looking at is the actual timer interrupt vector, but > that's not the the tick. > > # grep 'expire_entry.*tick_sched_timer' trace2 | wc -l > 45 > > 175 / 45 =~ 4 . So I you have CPNFIG_HZ=250 > > The kernel does not care whether the actual interrupt happens or the > timer is expired by other means. Learn something new every day. I (obviously) had no idea that it's perfectly fine for interrupts to go away when the CPU is busy. Oh well. Thanks for the new wrinkle in the mush between my ears. -Mike