Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757928AbYCWGix (ORCPT ); Sun, 23 Mar 2008 02:38:53 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752772AbYCWGiq (ORCPT ); Sun, 23 Mar 2008 02:38:46 -0400 Received: from fg-out-1718.google.com ([72.14.220.158]:6166 "EHLO fg-out-1718.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752722AbYCWGiq (ORCPT ); Sun, 23 Mar 2008 02:38:46 -0400 Message-ID: <47E5FAF2.2060508@colorfullife.com> Date: Sun, 23 Mar 2008 07:38:42 +0100 From: Manfred Spraul User-Agent: Thunderbird 2.0.0.12 (X11/20080226) MIME-Version: 1.0 To: Mike Galbraith CC: paulmck@linux.vnet.ibm.com, Nadia Derbey , Linux Kernel Mailing List , Andrew Morton Subject: Re: Scalability requirements for sysv ipc References: <47E382DB.70503@colorfullife.com> <47E3ADE3.4030304@bull.net> <47E3B924.3000304@colorfullife.com> <20080321141339.GB9618@linux.vnet.ibm.com> <47E3DD8C.4000904@colorfullife.com> <1206164608.3659.11.camel@marge.simson.net> <47E4DB06.3020003@colorfullife.com> <1206186832.4545.1.camel@marge.simson.net> <47E51637.8060102@colorfullife.com> <1206214504.4538.8.camel@marge.simson.net> In-Reply-To: <1206214504.4538.8.camel@marge.simson.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1216 Lines: 38 Mike Galbraith wrote: > On Sat, 2008-03-22 at 15:22 +0100, Manfred Spraul wrote: > >> Mike Galbraith wrote: >> >>> Total: 4691827 Total: 3942000 >>> >>> >> Thanks. Unfortunately the test was buggy, it bound the tasks to the >> wrong cpu :-( >> Could you run it again? Actually 1 cpu and 4 cpus are probably enough. >> > > Sure. (ran as before, hopefully no transcription errors) > > Thanks: sysv sem: - 2.6.22 had almost linear scaling (up to 4 cores). - 2.6.24.3 scales to 2 cpus, then it collapses. with 4 cores, it's 75% slower than 2.6.22. sysv msg: - neither 2.6.22 nor 2.6.24 scale very good. That's more or less expected, the message queue code contains a few global statistic counters (msg_hdrs, msg_bytes). The cleanup of sysv is nice, but IMHO sysv sem should remain scalable - and a gloal semaphore with IDR can't be as scalable as the RCU protected array that was used before. -- Manfred -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/