From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1765972AbZFLSAt (ORCPT ); Fri, 12 Jun 2009 14:00:49 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1765130AbZFLSAf (ORCPT ); Fri, 12 Jun 2009 14:00:35 -0400 Received: from e37.co.us.ibm.com ([32.97.110.158]:58691 "EHLO e37.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1765799AbZFLSAe (ORCPT ); Fri, 12 Jun 2009 14:00:34 -0400 Message-ID: <4A3297B5.7080401@linux.vnet.ibm.com> Date: Fri, 12 Jun 2009 11:00:21 -0700 From: Corey Ashford User-Agent: Thunderbird 2.0.0.21 (Windows/20090302) MIME-Version: 1.0 To: Paul Mackerras CC: Ingo Molnar , Peter Zijlstra , linux-kernel@vger.kernel.org, Thomas Gleixner Subject: Re: [PATCH 2/2] perf_counter: powerpc: Implement generalized cache events for POWER processors References: <18992.36329.189378.17992@drongo.ozlabs.ibm.com> <18992.36430.933526.742969@drongo.ozlabs.ibm.com> <20090611100720.GC12703@elte.hu> <18993.58058.194954.997480@drongo.ozlabs.ibm.com> In-Reply-To: <18993.58058.194954.997480@drongo.ozlabs.ibm.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Paul Mackerras wrote: > Ingo Molnar writes: > > Yeah. > > When thinking about having "composite" events, i.e. a counter whose > value is computed from two or more hardware counters, I couldn't see > how to do sampling in the general case. It's easy if we're just > adding multiple counters, but sampling when subtracting counters is > hard. For example, if you want to sample every N cache hits, and > you're computing hits as accesses - misses, I couldn't see a decent > way to know when to take the sample, not without having to take an > interrupt on every access in some circumstances. The PAPI equivalent of this, its preset aka standard events, do not allow profiling or interrupt on overflow for "derived" events. "derived events" has the same meaning as your composite events. So there is precedent for not allowing sampling on them. Regards, - Corey Corey Ashford Software Engineer IBM Linux Technology Center, Linux Toolchain