From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754524AbYISWOv (ORCPT ); Fri, 19 Sep 2008 18:14:51 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751421AbYISWOn (ORCPT ); Fri, 19 Sep 2008 18:14:43 -0400 Received: from ns.suse.de ([195.135.220.2]:57856 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751389AbYISWOm (ORCPT ); Fri, 19 Sep 2008 18:14:42 -0400 Date: Sat, 20 Sep 2008 00:41:10 +0200 From: Olaf Dabrunz To: Martin Bligh Cc: Randy Dunlap , Linux Kernel Mailing List , Linus Torvalds , Thomas Gleixner , Mathieu Desnoyers , Steven Rostedt , "od Frank Ch. Eigler" Subject: Re: Unified tracing buffer Message-ID: <20080919224109.GB4491@suse.de> Mail-Followup-To: Martin Bligh , Randy Dunlap , Linux Kernel Mailing List , Linus Torvalds , Thomas Gleixner , Mathieu Desnoyers , Steven Rostedt , "od Frank Ch. Eigler" References: <33307c790809191433w246c0283l55a57c196664ce77@mail.gmail.com> <20080919144258.ac787fdf.randy.dunlap@oracle.com> <33307c790809191457y3ebffa28xa6d9ab6431554618@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <33307c790809191457y3ebffa28xa6d9ab6431554618@mail.gmail.com> User-Agent: Mutt/1.5.16 (2007-06-09) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 19-Sep-08, Martin Bligh wrote: > >> Event ids are 16 bit, dynamically allocated. > > > > What are these (like)? > > u16 > > Sorry, probably lots of implicit assumptions in there that I forgot to explain Ids for event types. Either allocated dynamically, if the tracer needs new ids on each use, or statically assigned for others (like my fctrace or Steven's ftrace, I believe). Should we have a reserved range / registry for static allocation, maybe something like a very simple version of devices.txt? > > Arch-specific "word"? > > or some fixed-size-for-all-systems (so that trace buffers can be > > shared/used on other systems?) Preferably the latter. > > Mmmm. I don't see anything wrong with making it just 8 byte aligned, personally. > Steven - this was your thing? Unaligned can be much slower. I guess some very quick tracers can benefit from alignment. > as long as we record it in the buffer header at trace start. I guess we should > document the buffer header ;-) Yes. :) -- Olaf Dabrunz (od/odabrunz), SUSE Linux Products GmbH, Nürnberg