From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from moutng.kundenserver.de (moutng.kundenserver.de [212.227.126.187]) by ozlabs.org (Postfix) with ESMTP id 8DF7567B7B for ; Sun, 16 Jul 2006 02:42:35 +1000 (EST) From: Arnd Bergmann To: Anton Blanchard Subject: Re: [PATCH 0/3] powerpc: Instrument Hypervisor Calls Date: Sat, 15 Jul 2006 18:42:26 +0200 References: <20060714233739.GA11487@monkey.ibm.com> <200607150200.03494.arnd@arndb.de> <20060715153053.GK31081@krispykreme> In-Reply-To: <20060715153053.GK31081@krispykreme> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Message-Id: <200607151842.27568.arnd@arndb.de> Cc: Bryan Rosenburg , linuxppc-dev@ozlabs.org, Nathan Lynch , Paul Mackerras , Christopher Yeoh List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Saturday 15 July 2006 17:30, Anton Blanchard wrote: > > What happened to the question whether to use PURR values for also measuring > > cycles spent executing the hcall as opposed to cycles that passed before > > the hcall returns. Did that turn out not giving extra information after all > > or was there a different reason to drop that idea? > > You have to be careful with PURR since it may be context switched > between partitions. > Not sure I follow you. I would expect the PURR value to be restored after a context switch, even if we continue on a different physical CPU. The idea behind monitoring both PURR and timebase is that the difference between the two tells you how long the partition was suspended during the hcall. Arnd <><