From owner-freebsd-current@FreeBSD.ORG Wed Jan 25 17:55:41 2006 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 C202916A41F for ; Wed, 25 Jan 2006 17:55:41 +0000 (GMT) (envelope-from rwatson@FreeBSD.org) Received: from cyrus.watson.org (cyrus.watson.org [209.31.154.42]) by mx1.FreeBSD.org (Postfix) with ESMTP id 23EC443D76 for ; Wed, 25 Jan 2006 17:55:41 +0000 (GMT) (envelope-from rwatson@FreeBSD.org) Received: from fledge.watson.org (fledge.watson.org [209.31.154.41]) by cyrus.watson.org (Postfix) with ESMTP id 9363E46B91; Wed, 25 Jan 2006 12:55:34 -0500 (EST) Date: Wed, 25 Jan 2006 17:56:59 +0000 (GMT) From: Robert Watson X-X-Sender: robert@fledge.watson.org To: Christopher Arnold In-Reply-To: <20060125182006.I94600@home.arnold.se> Message-ID: <20060125175504.Q70912@fledge.watson.org> References: <20060125182006.I94600@home.arnold.se> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: current@freebsd.org Subject: Re: MySql and timekeeping? 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: Wed, 25 Jan 2006 17:55:41 -0000 On Wed, 25 Jan 2006, Christopher Arnold wrote: > some time ago there was some discussions regarding MySql and timekeeping. > > There was some ideas of using lower resolution when doing timekeeping to > keep the timekeeping cost down. Has anything been done in this area? > > Or should we stick to using Linux as our MySql platform? > > While we are at it, have anyone done a recent comparison of the MySql > performance under Linux and FreeBSD? I added new clock_gettime() variants that allow retrieval of a low accuracy low granularity on -CURRENT, time stamp at low cost. I also wrote a small wrapper library to allow people to compare before/after with various benchmarks. I never really heard back from anyone authoritatively. phk has also been circulating patches that reduce general CPU accounting measurement in the CPU by switching to a different definition of CPU time, which should also affect MySQL significantly, especially when running the MySQL benchmark client and server on the same hardware. Robert N M Watson