From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757772Ab2IXTEK (ORCPT ); Mon, 24 Sep 2012 15:04:10 -0400 Received: from mx1.redhat.com ([209.132.183.28]:1229 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757597Ab2IXTEJ (ORCPT ); Mon, 24 Sep 2012 15:04:09 -0400 Date: Mon, 24 Sep 2012 15:04:04 -0400 From: Jason Baron To: Joe Perches Cc: Jim Cromie , linux-kernel@vger.kernel.org, gregkh@linuxfoundation.org Subject: Re: [PATCH 5/6] dyndbg: in dynamic_emit_prefix, change inter-field separator Message-ID: <20120924190403.GG2492@redhat.com> References: <1348011407-24108-1-git-send-email-jim.cromie@gmail.com> <1348011407-24108-6-git-send-email-jim.cromie@gmail.com> <1348023402.11276.5.camel@joe2Laptop> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1348023402.11276.5.camel@joe2Laptop> User-Agent: Mutt/1.5.20 (2009-12-10) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Sep 18, 2012 at 07:56:42PM -0700, Joe Perches wrote: > On Tue, 2012-09-18 at 17:36 -0600, Jim Cromie wrote: > > dynamic_emit_prefix() currently separates modname, funcname, lineno > > with ':'. This is confounds use of cut -d: , since the field > > positions can change per callsite with dynamic-debug. So change > > inter-field separator to '.' and keep the ':' prefix terminator. > > > > This improves the situation, but doesnt solve it entirely; if > > dyndbg==p is used instead of dyndbg==p[fmlt]+, the callsite is enabled > > but no prefix is added, so theres one less ':' in the message. > > Changing the terminator to ',' would fix this, and might be warranted, > > especially since pr_fmt() typically adds a ':' as well. > > > > Joe Perches wasnt a fan of this, but his complaint was essentially > > that cut -d: was a poor way to do this kind of thing. I concede that > > point, but note that the kernel is not in the habit of needlessly > > confounding users work, at least when accommodating them is so trivial. > > And I still think this is ugly as it requires different parsing > by scripts when using combinations of +pfmlt > > If this patch doesn't 'solve it entirely', I'm reluctant to ack it, Would brackets, such as {} around the optional prefix be reasonable? Thanks, -Jason