From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753436Ab3JKMO7 (ORCPT ); Fri, 11 Oct 2013 08:14:59 -0400 Received: from science.horizon.com ([71.41.210.146]:59526 "HELO science.horizon.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1751225Ab3JKMO6 (ORCPT ); Fri, 11 Oct 2013 08:14:58 -0400 Date: 11 Oct 2013 08:14:57 -0400 Message-ID: <20131011121457.25042.qmail@science.horizon.com> From: "George Spelvin" To: rostedt@goodmis.org Subject: Re: [PATCH 0/6] Optimize the cpu hotplug locking -v2 Cc: linux@horizon.com, linux-kernel@vger.kernel.org, paulmck@linux.vnet.ibm.com, peterz@infradead.org, srivatsa.bhat@linux.vnet.ibm.com, torvalds@linux-foundation.org Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > There's places in the kernel that does for_each_cpu() that I'm sure you > don't want to disable preemption for. Especially when you start having > 4096 CPU machines! Er... why not? Seriously. If I have 4096 processors, and preemption is disabled on *one* of them for a long time, can't an urgent task just find a different processor to preempt? This seems like a non-problem. Or am I misunderstanding something about processor affinity?