From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753823Ab0INNIH (ORCPT ); Tue, 14 Sep 2010 09:08:07 -0400 Received: from mail-bw0-f46.google.com ([209.85.214.46]:41876 "EHLO mail-bw0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753755Ab0INNIE (ORCPT ); Tue, 14 Sep 2010 09:08:04 -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=XaMkCh3yLMFexjdvYvghufLNXt23E2qpb0qS8SH5hcgjPCrMbh4+QkBBL33IJkub5p 2MU7BrbM19mOqXbB14eWbafmq63u4QUXK+z/y3hZpa7po9uwpmCID23DIPNahlzN8sJa kAc3jG1ss9xucVHhJLN7cTw5aap63JLgO3hkc= Date: Tue, 14 Sep 2010 15:07:57 +0200 From: Frederic Weisbecker To: Ingo Molnar Cc: Peter Zijlstra , Arnaldo Carvalho de Melo , linux-kernel@vger.kernel.org, Christoph Hellwig , Mike Galbraith , Paul Mackerras , Stephane Eranian , Tom Zanussi Subject: Re: [GIT PULL 0/1] perf/core ui browser improvement Message-ID: <20100914130753.GA5341@nowhere> References: <1284395692-11298-1-git-send-email-acme@infradead.org> <20100913174845.GC18428@elte.hu> <20100913190758.GB31907@ghostprotocols.net> <20100913204217.GA2505@elte.hu> <20100913212951.GI31907@ghostprotocols.net> <1284450852.2275.458.camel@laptop> <20100914121611.GD12425@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20100914121611.GD12425@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, Sep 14, 2010 at 02:16:11PM +0200, Ingo Molnar wrote: > > * Peter Zijlstra wrote: > > > On Mon, 2010-09-13 at 18:29 -0300, Arnaldo Carvalho de Melo wrote: > > > + 3.00% find [kernel.kallsyms] [k] n_tty_write > > > > > + 3.00% find kernel k n_tty_write > > > > I find that [k] is visually easier to separate from the symbol name. > > me too. Something like: > > before: > > 1.08% cc1 libc-2.12.so [.] _int_malloc > 0.94% cc1 [kernel.kallsyms] [k] clear_page_c > 0.74% cc1 libc-2.12.so [.] _int_free > 0.69% cc1 [kernel.kallsyms] [k] page_fault > 0.46% cc1 libc-2.12.so [.] malloc_consolidate > > after: > > 1.08% cc1 # libc-2.12.so [.] _int_malloc > 0.94% cc1 # kernel [k] clear_page_c > 0.74% cc1 # libc-2.12.so [.] _int_free > 0.69% cc1 # kernel [k] page_fault > 0.46% cc1 # libc-2.12.so [.] malloc_consolidate > > > Would largely do the trick i think. The comments delineate the DSO > portion from the task portion nicely - while also being a familar > pattern. The column of [.] and [k] gives kernel developers a quick > glance wrt. whether it's kernel or user-space - and it also delineates > the symbol column from the DSO column. > > Thanks, > > Ingo BTW, having [u] instead of [.] would perhaps be more clearer? And one day we might want to extend that with more granularity, like major contexts in uppercase: K=kernel, U=user, H=hypervisor and some minor in lowercase: h=hardirq, s=softirq, t=task. So you can get [Kh], [Ks], etc... User could then sort by context, which could be useful without callchains for example.