From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753886AbZHKMZO (ORCPT ); Tue, 11 Aug 2009 08:25:14 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753741AbZHKMZN (ORCPT ); Tue, 11 Aug 2009 08:25:13 -0400 Received: from ey-out-2122.google.com ([74.125.78.24]:21130 "EHLO ey-out-2122.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752644AbZHKMZM (ORCPT ); Tue, 11 Aug 2009 08:25:12 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=date:from:to:cc:subject:message-id:references:mime-version :content-type:content-disposition:in-reply-to:user-agent; b=xCn0QmkfrGy2mrqgjbD2+C2jPs39/ezK7YBL4cWW4vm6bwdLEiIsd5kpvFM8MqqMTo fNSMqLrPqhscVuenH7khVEKDQI5yW4eNvuYWuOHDcuESSkqpThp4cHVE3thnim8PUDsl JBkUGjQCtmUkJDEvje4dRyTdjolrObgU8jeew= Date: Tue, 11 Aug 2009 14:25:09 +0200 From: Frederic Weisbecker To: Ingo Molnar Cc: Jason Baron , linux-kernel@vger.kernel.org, laijs@cn.fujitsu.com, rostedt@goodmis.org, peterz@infradead.org, mathieu.desnoyers@polymtl.ca, jiayingz@google.com, mbligh@google.com, lizf@cn.fujitsu.com Subject: Re: [PATCH 10/12] add perf counter support Message-ID: <20090811122507.GG4938@nowhere> References: <20090811121227.GF4938@nowhere> <20090811121711.GA31549@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20090811121711.GA31549@elte.hu> User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Aug 11, 2009 at 02:17:11PM +0200, Ingo Molnar wrote: > > * Frederic Weisbecker wrote: > > > On Mon, Aug 10, 2009 at 04:53:02PM -0400, Jason Baron wrote: > > > Make 'perf stat -e syscalls:sys_enter_blah' work with syscall style tracepoints. > > > > > > It would be nice to also be able to type: > > > > perf stat -e syscalls:blah > > > > and then having both enter/exit counters. > > Plus wildcard/regex support would be nice as well in the listing of > events. That way one could do a shortcut of: > > perf stat -e syscalls:* > > to trace all syscalls. Or: > > perf stat -e syscalls:*read* > > to see all the read variants - etc. > > Ingo Plus filters in syscalls field. Because arguments are wrapped and post-processed, they are not treated as usual fields. I must confess this part is not trivial though.