From mboxrd@z Thu Jan 1 00:00:00 1970 From: Denis Richard Subject: Re: SCHED_RR preempted by SCHED_OTHER Date: Mon, 27 Jul 2009 15:31:34 +0200 Message-ID: <4A6DAC36.3040304@alcatel-lucent.fr> References: <4A6D962B.20408@alcatel-lucent.fr> <20090727123609.GA26176@pengutronix.de> Reply-To: denis.richard@alcatel-lucent.fr Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE To: linux-rt-users@vger.kernel.org Return-path: Received: from smail6.alcatel.fr ([64.208.49.42]:50158 "EHLO smail6.alcatel.fr" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754021AbZG0Nbg (ORCPT ); Mon, 27 Jul 2009 09:31:36 -0400 Received: from bsf.alcatel.fr (mail205.sxb.bsf.alcatel.fr [155.132.205.115]) by smail6.alcatel.fr (8.13.8/8.13.8/ICT) with ESMTP id n6RDVYsj028131 for ; Mon, 27 Jul 2009 15:31:35 +0200 Received: from mail (mail-bsf-alcatel-fr.sxb.bsf.alcatel.fr [155.132.205.91]) by bsf.alcatel.fr (8.8.8p2+Sun/8.9.3) with ESMTP id PAA19151 for ; Mon, 27 Jul 2009 15:31:34 +0200 (MET DST) Received: from [172.25.51.2] (frilln0l015383.emea.lucent.com [172.25.51.2]) by mail (8.8.8p2+Sun/) with ESMTP id PAA19146 for ; Mon, 27 Jul 2009 15:31:34 +0200 (MET DST) In-Reply-To: <20090727123609.GA26176@pengutronix.de> Sender: linux-rt-users-owner@vger.kernel.org List-ID: Uwe Kleine-K=F6nig a =E9crit : > On Mon, Jul 27, 2009 at 01:57:31PM +0200, Denis Richard wrote: > =20 >> Hi all, >> We work on powerpc board with kernel 2.6.29.6-rt23. >> The kernel is configured with "Complete Preemption (Real-Time)". >> Working on our software, we have a strange behavior. >> A real time thread (SCHED_RR) can be preempted by non real time one = =20 >> (SCHED_OTHER). >> >> We wrote a little test program (at the end of this mail). >> This program creates 2 threads, a SCHED_RR one which processes durin= g =20 >> about 12s >> (long for a real time, but just for test), and a SCHED_OTHER one, =20 >> started after the first one, >> which just modifies a global variable. The second one should not run= =20 >> during the execution of >> the first one. But it appends, the global variable is modified. >> >> =20 >>> rr_other >>> =20 >> Create thread >> OTHER ran during RR >> The end >> =20 >> Is it normal, a non real time thread preempts a real time one ? (we = =20 >> think, it is not) >> Or is there something wrong in the test program, the kernel =20 >> configuration, ... ? >> =20 > Does > > # echo -1 > /proc/sys/kernel/sched_rt_runtime_us > > help? > =20 Yes, it solves the problem. Thanks Uwe. Regards Denis -- To unsubscribe from this list: send the line "unsubscribe linux-rt-user= s" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html