From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753521AbYKDISw (ORCPT ); Tue, 4 Nov 2008 03:18:52 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754635AbYKDISk (ORCPT ); Tue, 4 Nov 2008 03:18:40 -0500 Received: from mga05.intel.com ([192.55.52.89]:50052 "EHLO fmsmga101.fm.intel.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1754512AbYKDISi (ORCPT ); Tue, 4 Nov 2008 03:18:38 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.33,542,1220252400"; d="scan'208";a="399648256" Subject: Re: [PATCH 3/3] ftrace: function tracer with irqs disabled From: "Zhang, Yanmin" To: Ingo Molnar Cc: Steven Rostedt , linux-kernel@vger.kernel.org, Thomas Gleixner , Peter Zijlstra , Andrew Morton , Steven Rostedt In-Reply-To: <20081104080747.GA27075@elte.hu> References: <20081104041554.605521183@goodmis.org> <20081104042203.499871423@goodmis.org> <20081104080747.GA27075@elte.hu> Content-Type: text/plain Date: Tue, 04 Nov 2008 16:17:07 +0800 Message-Id: <1225786627.1685.112.camel@ymzhang> Mime-Version: 1.0 X-Mailer: Evolution 2.21.5 (2.21.5-2.fc9) Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2008-11-04 at 09:07 +0100, Ingo Molnar wrote: > * Steven Rostedt wrote: > > > Running hackbench 3 times with the irqs disabled and 3 times with > > the preempt disabled function tracer yielded: > > > > tracing type times entries recorded > > ------------ -------- ---------------- > > irq disabled 43.393 166433066 > > 43.282 166172618 > > 43.298 166256704 > > > > preempt disabled 38.969 159871710 > > 38.943 159972935 > > 39.325 161056510 > > your numbers might be correct, but i found that hackbench is not > reliable boot-to-boot I found that, too. But if I kill most background processes before testing, hackbench result looks quite stable. > - it can easily produce 10% systematic noise or > more. (perhaps depending on how the various socket data structures > happen to be allocated) > > the really conclusive way to test this would be to add a hack that > either does preempt disable or irqs disable, depending on a runtime > flag - and then observe how hackbench performance reacts to the value > of that flag. > > note that preempt-disable will also produce less trace entries, > especially in very irq-rich workloads. Hence it will be "faster". > > Ingo > -- > 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/