From owner-freebsd-current@FreeBSD.ORG Fri Oct 28 20:37:34 2005 Return-Path: X-Original-To: current@freebsd.org Delivered-To: freebsd-current@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7889616A41F for ; Fri, 28 Oct 2005 20:37:34 +0000 (GMT) (envelope-from phk@critter.freebsd.dk) Received: from phk.freebsd.dk (phk.freebsd.dk [130.225.244.222]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1C97B43D45 for ; Fri, 28 Oct 2005 20:37:34 +0000 (GMT) (envelope-from phk@critter.freebsd.dk) Received: from critter.freebsd.dk (unknown [192.168.48.2]) by phk.freebsd.dk (Postfix) with ESMTP id F2DB4BC7A; Fri, 28 Oct 2005 20:37:32 +0000 (UTC) To: John-Mark Gurney From: "Poul-Henning Kamp" In-Reply-To: Your message of "Fri, 28 Oct 2005 13:18:57 PDT." <20051028201857.GQ4115@funkthat.com> Date: Fri, 28 Oct 2005 22:37:32 +0200 Message-ID: <35317.1130531852@critter.freebsd.dk> Sender: phk@critter.freebsd.dk Cc: Michael VInce , current@freebsd.org Subject: Re: Timers and timing, was: MySQL Performance 6.0rc1 X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 28 Oct 2005 20:37:34 -0000 In message <20051028201857.GQ4115@funkthat.com>, John-Mark Gurney writes: >Michael VInce wrote this message on Fri, Oct 28, 2005 at 22:33 +1000: >> Hey guys, I been watching this thread and I can confirm that MySQL and >> the Super-smack benchmark greatly rely on this, >> I was able to increase performance %600 by changing >> kern.timecounter.hardware to dummy. > >This is probably because dummy doesn't actually do any real >timecounting... and that the times that the benchmark took was longer >then reported by the machine.. dummy just increments a counter, and >means that the times returned only have a relation to how often/much >the time "hardware" was queried... The dummy timecounter is there only to make the kernel survive during early boot and to push timecounters further down the list of things one have to deal with when porting FreeBSD to a new achitecture. But if you _truly_ don't care about time, it's undisputed the fastest timecounter "hardware" we have :-) -- Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 phk@FreeBSD.ORG | TCP/IP since RFC 956 FreeBSD committer | BSD since 4.3-tahoe Never attribute to malice what can adequately be explained by incompetence.