From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754231AbYK0Oov (ORCPT ); Thu, 27 Nov 2008 09:44:51 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752373AbYK0Oon (ORCPT ); Thu, 27 Nov 2008 09:44:43 -0500 Received: from mail-qy0-f11.google.com ([209.85.221.11]:48712 "EHLO mail-qy0-f11.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752238AbYK0Oom (ORCPT ); Thu, 27 Nov 2008 09:44:42 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:to:subject:cc:in-reply-to:mime-version :content-type:content-transfer-encoding:content-disposition :references; b=BL2yF/cYXw1/2SzcHDUD/lHvN7LZpG6U8WUvQzVTzG6t9ucoQJHidst0gT8+o7bqPX +a/eyo1b6JjAx65TtlCtNLDigRgsdA4Ad66CR/yWh1m6fM5MNHAp/Vo5hdn/KWyZ7OQz Ho7X+/e2TdbbMS4D5VQL5aQG3mpc7JOI1Lax0= Message-ID: Date: Thu, 27 Nov 2008 15:44:40 +0100 From: "=?ISO-8859-1?Q?Fr=E9d=E9ric_Weisbecker?=" To: "Ingo Molnar" Subject: Re: [PATCH] tracing/function-branch-tracer: enhancements for the trace output Cc: "Steven Rostedt" , "Tim Bird" , "Linux Kernel" , "Peter Zijlstra" In-Reply-To: <20081127135155.GA23076@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <492DEDE9.9010109@gmail.com> <20081127103424.GA9132@elte.hu> <20081127135155.GA23076@elte.hu> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 2008/11/27 Ingo Molnar : > We can still add the overhead signs. > > We still have a single space in the first column before the CPU number > (that looks better when these traces are pasted into email, which is > one of the most common uses of them), and we can add the sign there. > > I.e. something like this: > >> > --------------------------------------------------------- >> > CPU) cost | function >> > --------------------------------------------------------- >> > >> > 0) | sys_read() { >> > 0) 0.331 us | fget_light(); >> > 0) | vfs_read() { >> > 0) | rw_verify_area() { >> > 0) | security_file_permission() { >> > 0) 0.306 us | cap_file_permission(); >> > 0) 0.300 us | cap_file_permission(); >> > 0) 8.909 us | } >> > 0) 0.993 us | } >> > +0) 11.649 us | } >> > 0) | do_sync_read() { >> > 0) | sock_aio_read() { >> > 0) | __sock_recvmsg() { >> > 0) | security_socket_recvmsg() { >> > !0) 100.319 us | cap_socket_recvmsg(); >> > --------------------------------------------------------- > > Or we could add them to the function name bit - there we have two free > space characters anyway: > > Something like this: > >> > --------------------------------------------------------- >> > CPU) cost | function >> > --------------------------------------------------------- >> > >> > 0) | sys_read() { >> > 0) 0.331 us | fget_light(); >> > 0) | vfs_read() { >> > 0) | rw_verify_area() { >> > 0) | security_file_permission() { >> > 0) 0.306 us | cap_file_permission(); >> > 0) 0.300 us | cap_file_permission(); >> > 0) 8.909 us | } >> > 0) 0.993 us | } >> > 0) 11.649 us |+ } >> > 0) | do_sync_read() { >> > 0) | sock_aio_read() { >> > 0) | __sock_recvmsg() { >> > 0) | security_socket_recvmsg() { >> > 0) 100.319 us |! cap_socket_recvmsg(); >> > --------------------------------------------------------- > > Hm? I like it before the CPU number. The main purpose would be to scroll quickly the file and find the overheads. That would be easy if set as a first character. I will set it as a default disabled option. > >> I don't know, perhaps that will actually be better in practice... > > i think it will be better. I'm biased, so i gave the output to two > people with good visual taste (one of them female), [note, i gave them > the mockup from the previous mail] and the first question of both of > them was: "why arent the times on the left?". Really? Actually yes, I'm certainly biased too. > I think we could make the time column a trace_option as well - > default-enabled. Ok, I will apply it.