From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754914AbdDEIzR (ORCPT ); Wed, 5 Apr 2017 04:55:17 -0400 Received: from outbound-smtp03.blacknight.com ([81.17.249.16]:53672 "EHLO outbound-smtp03.blacknight.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754443AbdDEIxy (ORCPT ); Wed, 5 Apr 2017 04:53:54 -0400 Date: Wed, 5 Apr 2017 09:53:52 +0100 From: Mel Gorman To: Jesper Dangaard Brouer Cc: Matthew Wilcox , Peter Zijlstra , Pankaj Gupta , Tariq Toukan , Tariq Toukan , netdev@vger.kernel.org, akpm@linux-foundation.org, linux-mm , Saeed Mahameed , linux-kernel@vger.kernel.org Subject: Re: in_irq_or_nmi() and RFC patch Message-ID: <20170405085352.52rb3k34omndei63@techsingularity.net> References: <20170327165817.GA28494@bombadil.infradead.org> <20170329081219.lto7t4fwmponokzh@hirez.programming.kicks-ass.net> <20170329105928.609bc581@redhat.com> <20170329091949.o2kozhhdnszgwvtn@hirez.programming.kicks-ass.net> <20170329181226.GA8256@bombadil.infradead.org> <20170329211144.3e362ac9@redhat.com> <20170329214441.08332799@redhat.com> <20170330130436.l37yazbxlrkvcbf3@techsingularity.net> <20170330170708.084bd16c@redhat.com> <20170403120506.y7z3cncyi65bcgen@techsingularity.net> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Disposition: inline In-Reply-To: <20170403120506.y7z3cncyi65bcgen@techsingularity.net> User-Agent: Mutt/1.6.2 (2016-07-01) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Apr 03, 2017 at 01:05:06PM +0100, Mel Gorman wrote: > > Started performance benchmarking: > > 163 cycles = current state > > 183 cycles = with BH disable + in_irq > > 218 cycles = with BH disable + in_irq + irqs_disabled > > > > Thus, the performance numbers unfortunately looks bad, once we add the > > test for irqs_disabled(). The slowdown by replacing preempt_disable > > with BH-disable is still a win (we saved 29 cycles before, and loose > > 20, I was expecting regression to be only 10 cycles). > > > > This surprises me because I'm not seeing the same severity of problems > with irqs_disabled. Your path is slower than what's currently upstream > but it's still far better than a revert. The softirq column in the > middle is your patch versus a full revert which is the last columnm > Any objection to resending the local_bh_enable/disable patch with the in_interrupt() check based on this data or should I post the revert and go back to the drawing board? -- Mel Gorman SUSE Labs