Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759456AbZF2OAn (ORCPT ); Mon, 29 Jun 2009 10:00:43 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756782AbZF2OAY (ORCPT ); Mon, 29 Jun 2009 10:00:24 -0400 Received: from casper.infradead.org ([85.118.1.10]:36617 "EHLO casper.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752786AbZF2OAV (ORCPT ); Mon, 29 Jun 2009 10:00:21 -0400 Date: Mon, 29 Jun 2009 07:01:23 -0700 From: Arjan van de Ven To: Luming Yu Cc: Ingo Molnar , LKML , suresh.b.siddha@intel.com, venkatesh.pallipadi@intel.com, Thomas Gleixner , "H. Peter Anvin" Subject: Re: [RFC patch] Use IPI_shortcut for lapic timer broadcast Message-ID: <20090629070123.5e874497@infradead.org> In-Reply-To: <3877989d0906290143y3b5306f4s4a990ecbfbfc49b6@mail.gmail.com> References: <3877989d0906282347i311eb14bp80a7c80878219c31@mail.gmail.com> <20090629072047.GB20225@elte.hu> <3877989d0906290104q11a767b6qcc1acc4c2d1feba6@mail.gmail.com> <20090629081615.GB571@elte.hu> <3877989d0906290121l15705d2cn72e4c49dd96ed950@mail.gmail.com> <20090629083035.GA4017@elte.hu> <3877989d0906290143y3b5306f4s4a990ecbfbfc49b6@mail.gmail.com> Organization: Intel X-Mailer: Claws Mail 3.7.1 (GTK+ 2.14.7; i386-redhat-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-SRS-Rewrite: SMTP reverse-path rewritten from by casper.infradead.org See http://www.infradead.org/rpr.html Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1174 Lines: 32 On Mon, 29 Jun 2009 16:43:16 +0800 Luming Yu wrote: > > Even a Pentium-5 100 MHz dual box was able to do cross-CPU IPIs > > within 10-20 microseconds more than a decade ago - so 50-100 usecs > > latency on a modern platform is totally out of this planet and will > > hurt Linux performance big time. And the worst thing about it is > > that none of the usual performance metrics will really show _why_ > > performance is tanking ... > > > > > Please note this is deep-C-state related. > C state does add extra latency.. but I don't know how much... C states normally only add on the "wait for" side, not on the "send" side. (RHEL5 is rather old, so it may have done things a bit different) Maybe it is time for mainline to not allow a !NO_HZ config.... -- Arjan van de Ven Intel Open Source Technology Centre For development, discussion and tips for power savings, visit http://www.lesswatts.org -- 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/