From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: A proposal - binary Date: Sat, 5 Aug 2006 13:57:09 +0200 Message-ID: <200608051357.09432.ak@suse.de> References: <44D1CC7D.4010600@vmware.com> <200608050001.52535.ak@suse.de> <20060805104735.GS25692@stusta.de> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20060805104735.GS25692@stusta.de> Content-Disposition: inline List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Adrian Bunk Cc: Zachary Amsden , Andrew Morton , xen-devel@lists.xensource.com, Christoph Hellwig , Jack Lo , Greg KH , Rusty Russell , Linux Kernel Mailing List , Chris Wright , virtualization@lists.osdl.org, Linus Torvalds , James.Bottomley@steeleye.com, pazke@donpac.ru List-Id: virtualization@lists.linuxfoundation.org > Has anyone measured the performance impact of rutime CLOCK_TICK_RATE > switching (since this will no longer allow some compile time > optimizations in jiffies.h)? SUSE shipped a kernel briefly that had runtime switchable jiffies and there were some benchmarks done and they didn't show noticeable slowdown. But with hr timers it should be pretty much obsolete anyways. -Andi