From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752474AbdHGIeJ (ORCPT ); Mon, 7 Aug 2017 04:34:09 -0400 Received: from merlin.infradead.org ([205.233.59.134]:45196 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752232AbdHGIeI (ORCPT ); Mon, 7 Aug 2017 04:34:08 -0400 Date: Mon, 7 Aug 2017 10:33:54 +0200 From: Peter Zijlstra To: "Ofer Levi(SW)" Cc: "rusty@rustcorp.com.au" , "vatsa@in.ibm.com" , "mingo@redhat.com" , "Vineet.Gupta1@synopsys.com" , "linux-kernel@vger.kernel.org" Subject: Re: hotplug support for arch/arc/plat-eznps platform Message-ID: <20170807083354.ptkehfql54xydsvm@hirez.programming.kicks-ass.net> References: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: NeoMutt/20170609 (1.8.3) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sun, Aug 06, 2017 at 05:53:37AM +0000, Ofer Levi(SW) wrote: > I'm adding hot-plug support for the above arch and ran into performance issue with execution of > partition_sched_domains () - About 0.5 sec per cpu, which is unacceptable with the arch supported 4k cpus. > To my limited understanding, on the plat-eznps arch, where each cpu is always running a single threaded process in > isolation mode, the above call is not necessary, > Can you please confirm (or reject) my understanding? If I'm wrong short explanation will be appreciated. > If I'm correct, I will be grateful if you can point me to how to skip this call in a way acceptable by community. You've failed to explain why you think hotplug should be a performance critical path. I'm also not seeing how it would be different from boot; you'd be looking at a similar cost for SMP bringup.