From mboxrd@z Thu Jan 1 00:00:00 1970 From: Will Deacon Subject: Re: [PATCH 8/7] net/netfilter/nf_conntrack_core: Remove another memory barrier Date: Tue, 6 Sep 2016 18:56:48 +0100 Message-ID: <20160906175648.GC29382@arm.com> References: <1472743673-15585-1-git-send-email-manfred@colorfullife.com> <20160901153039.GN6721@arm.com> <20160901164126.GZ10153@twins.programming.kicks-ass.net> <1971bcf8-0f42-c0b7-5e59-2ceaa6e024a7@colorfullife.com> <20160902192213.GM10153@twins.programming.kicks-ass.net> <5d88110f-cf0e-c72e-7acc-518b736e715e@colorfullife.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Peter Zijlstra , benh@kernel.crashing.org, paulmck@linux.vnet.ibm.com, Ingo Molnar , Boqun Feng , Andrew Morton , LKML , 1vier1@web.de, Davidlohr Bueso , Pablo Neira Ayuso , netfilter-devel@vger.kernel.org To: Manfred Spraul Return-path: Received: from foss.arm.com ([217.140.101.70]:60896 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755322AbcIFR4p (ORCPT ); Tue, 6 Sep 2016 13:56:45 -0400 Content-Disposition: inline In-Reply-To: <5d88110f-cf0e-c72e-7acc-518b736e715e@colorfullife.com> Sender: netfilter-devel-owner@vger.kernel.org List-ID: On Mon, Sep 05, 2016 at 08:57:19PM +0200, Manfred Spraul wrote: > On 09/02/2016 09:22 PM, Peter Zijlstra wrote: > Anyone around with a ppc or arm? How slow is the loop of the > spin_unlock_wait() calls? > Single CPU is sufficient. > > Question 1: How large is the difference between: > #./sem-scalebench -t 10 -c 1 -p 1 -o 4 -f -d 1 > #./sem-scalebench -t 10 -c 1 -p 1 -o 4 -f -d 256 > https://github.com/manfred-colorfu/ipcscale Not sure exactly what you want me to run here, but with an arm64 defconfig -rc3 kernel, those two invocations give me "Max total" values where the first is 20x bigger than the second. Will