Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754060AbZG2O6F (ORCPT ); Wed, 29 Jul 2009 10:58:05 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752406AbZG2O6E (ORCPT ); Wed, 29 Jul 2009 10:58:04 -0400 Received: from mx2.redhat.com ([66.187.237.31]:59952 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752258AbZG2O6D (ORCPT ); Wed, 29 Jul 2009 10:58:03 -0400 Date: Wed, 29 Jul 2009 11:57:18 -0300 From: Arnaldo Carvalho de Melo To: Peter Zijlstra Cc: prasad@linux.vnet.ibm.com, Frederic Weisbecker , Ingo Molnar , LKML , Steven Rostedt , Thomas Gleixner , Mike Galbraith , Paul Mackerras , Arnaldo Carvalho de Melo , Lai Jiangshan , Anton Blanchard , Li Zefan , Zhaolei , KOSAKI Motohiro , Mathieu Desnoyers , Alan Stern Subject: Re: [RFC][PATCH 5/5] perfcounter: Add support for kernel hardware breakpoints Message-ID: <20090729145718.GB3040@ghostprotocols.net> References: <20090724174723.GA11985@nowhere> <1248519416.5780.12.camel@laptop> <20090725141918.GA5295@nowhere> <1248538972.5780.25.camel@laptop> <20090725235702.GA5082@in.ibm.com> <1248684817.6987.1573.camel@twins> <20090728161218.GA3526@in.ibm.com> <1248799286.6987.3026.camel@twins> <20090729063704.GA3297@in.ibm.com> <1248859372.6987.3062.camel@twins> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1248859372.6987.3062.camel@twins> X-Url: http://oops.ghostprotocols.net:81/blog User-Agent: Mutt/1.5.19 (2009-01-05) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1945 Lines: 42 Em Wed, Jul 29, 2009 at 11:22:52AM +0200, Peter Zijlstra escreveu: > On Wed, 2009-07-29 at 12:07 +0530, K.Prasad wrote: > > > > That still doesn't provide per-cpu breakpoints. > > > > > > > Yes, it doesn't provide a per-cpu only implementation. One can obtain > > the per-cpu data from the system-wide breakpoints by filtering it for a > > given CPU (agreed, it will associated overhead). > > > > A true per-cpu breakpoint implementation that co-exists with > > system-wide and per-task breakpoints will be difficult. It might require > > the re-introduction of some old features and a few new ones (like switching > > between kernel and user-space breakpoints at syscall time) that were > > rejected earlier by the community. > > I'm not clear on why you'd need to switch breakpoints on syscall entry. > You can simply leave the kernel address breakpoint around in userspace, > they're not able to poke at that address space anyway. > > > Also, the reason for a per-cpu only breakpoint (user and kernel-space) > > isn't very obvious. While kernel variables can be read/written > > throughout the system and user-space variables are per-task, the need > > for obtaining per-cpu information isn't clear. > > Well, suppose you're monitoring a per-cpu variable, or interested in the > effects of a workload confined to 1 cpu or node, there is no reason to > have this breakpoint on all cpus. I was going to talk about exactly that, CPU isolation for one specific workload, I don't want that hits on tcp_v4_rcv on another CPU get counted, just the ones on that specific CPU. The other CPUs can be given a break (pun intended :-P) by not having to process traps we're uninterested in. - Arnaldo -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/