From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Chris Friesen" Subject: Re: [patch] Performance Counters for Linux, v2 Date: Tue, 09 Dec 2008 10:39:26 -0600 Message-ID: <493E9F3E.3020902@nortel.com> References: <20081208012211.GA23106@elte.hu> <7c86c4470812082237ne58c814s7218cc663f3b49e9@mail.gmail.com> <20081209134636.GA1926@elte.hu> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from zcars04e.nortel.com ([47.129.242.56]:49108 "EHLO zcars04e.nortel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751629AbYLIQkK (ORCPT ); Tue, 9 Dec 2008 11:40:10 -0500 In-Reply-To: <20081209134636.GA1926@elte.hu> Sender: linux-arch-owner@vger.kernel.org List-ID: To: Ingo Molnar Cc: eranian@gmail.com, linux-kernel@vger.kernel.org, Thomas Gleixner , linux-arch@vger.kernel.org, Andrew Morton , Eric Dumazet , Robert Richter , Arjan van de Veen , Peter Anvin , Peter Zijlstra , Steven Rostedt , David Miller , Paul Mackerras , Paolo Ciarrocchi Ingo Molnar wrote: > When there are two (or more) hw metrics to profile, the ideally best > (i.e. the statistically most stable and most relevant) sampling for the > two statistical variables (say of l2_misses versus l2_accesses) is to > sample them independently, via their own metric. Not via a static 1khz > rate - or via picking one of the variables to generate samples. Regardless of sampling method, don't you still want some way to enable/disable the various counters as close to simultaneously as possible? Chris