From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Paul E. McKenney" Subject: Load-balancing at migrate-enable time? Date: Wed, 26 Oct 2011 11:30:36 -0700 Message-ID: <20111026183036.GA3608@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: linux-rt-users@vger.kernel.org To: rostedt@goodmis.org, peterz@infradead.org Return-path: Received: from e7.ny.us.ibm.com ([32.97.182.137]:53394 "EHLO e7.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753601Ab1J0HqB (ORCPT ); Thu, 27 Oct 2011 03:46:01 -0400 Received: from /spool/local by e7.ny.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Thu, 27 Oct 2011 03:45:50 -0400 Received: from d01av04.pok.ibm.com (d01av04.pok.ibm.com [9.56.224.64]) by d01relay02.pok.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id p9R7jkNK457768 for ; Thu, 27 Oct 2011 03:45:46 -0400 Received: from d01av04.pok.ibm.com (loopback [127.0.0.1]) by d01av04.pok.ibm.com (8.14.4/8.13.1/NCO v10.0 AVout) with ESMTP id p9R7jjRC020112 for ; Thu, 27 Oct 2011 03:45:45 -0400 Content-Disposition: inline Sender: linux-rt-users-owner@vger.kernel.org List-ID: Hello! So I am getting the second round of the model beaten into shape, but have a question... Assume the following state: 1. Task 0 preempted in a migrate-disable region on CPU 0. 2. Task 1 preempted, but not in a migrate-disable region, also on CPU 0. 3. Task 2 running in a migrate-disable region also on CPU 0 Suppose that Task 2 enables migration. Will it actually migrate in order to allow Task 1 to run? (My guess is "no", but...) Thanx, Paul ------------------------------------------------------------------------ PS. We get to the above state by starting as follows: 1. Task 0 blocked in a migrate-disable region on CPU 0. 2. Task 1 running on CPU 0 without migration disabled. 3. Task 2 blocked in a migrate-disable region also on CPU 0 Then Task 2 awakens, preempting Task 1. (In the more-aggressive model, this would trigger migration of Task 1, but I am trying to match what the load balancer actually does.)