From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from e33.co.us.ibm.com (e33.co.us.ibm.com [32.97.110.151]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client CN "e33.co.us.ibm.com", Issuer "Equifax" (verified OK)) by ozlabs.org (Postfix) with ESMTP id 0652967B87 for ; Wed, 19 Jul 2006 07:28:58 +1000 (EST) Received: from westrelay02.boulder.ibm.com (westrelay02.boulder.ibm.com [9.17.195.11]) by e33.co.us.ibm.com (8.12.11.20060308/8.12.11) with ESMTP id k6ILStjn015870 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=FAIL) for ; Tue, 18 Jul 2006 17:28:55 -0400 Received: from d03av04.boulder.ibm.com (d03av04.boulder.ibm.com [9.17.195.170]) by westrelay02.boulder.ibm.com (8.13.6/NCO/VER7.0) with ESMTP id k6ILStoo310294 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO) for ; Tue, 18 Jul 2006 15:28:55 -0600 Received: from d03av04.boulder.ibm.com (loopback [127.0.0.1]) by d03av04.boulder.ibm.com (8.12.11.20060308/8.13.3) with ESMTP id k6ILSslJ003916 for ; Tue, 18 Jul 2006 15:28:54 -0600 Date: Tue, 18 Jul 2006 14:29:13 -0700 From: Mike Kravetz To: Paul Mackerras Subject: Re: [PATCH 0/3] powerpc: Instrument Hypervisor Calls Message-ID: <20060718212913.GB3091@w-mikek2.ibm.com> References: <20060718204723.GA6104@w-mikek2.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <20060718204723.GA6104@w-mikek2.ibm.com> Cc: linuxppc-dev@ozlabs.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Tue, Jul 18, 2006 at 01:47:23PM -0700, Mike Kravetz wrote: > A small update from the last version. By popular demand, both > wall time (mftb) and cpu cycles(PURR) are collected for each call. > It is interesting to see these two values side by side in the > output files. Arnd asked on IRC, so I thought others may be interested in a sample output file. Remember, there is one file per CPU. All values are decimal. First number is hcall # (in decimal), second is number of calls, third is total time (mftb) and fourth is cpu time (PURR). Note that 'total times' are still in cycles and can be converted to another format in user space. [elm3b125]/sys/kernel/debug/hcall_inst >cat cpu0 4 140651 21538230 14456409 8 130064 11855094 9459178 24 14259 1496316 986702 32 1809 354584 315399 84 103 27196 17763 88 1046 108106 109322 100 2596 251229 205154 104 1 1040 1061 108 2208 320491 242708 116 2669 1030894 713272 220 2 532 510 224 130662 47508588184 169383891 228 5 2689902 4622 260 3018 261893 230753 -- Mike