Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758679Ab0KQSgq (ORCPT ); Wed, 17 Nov 2010 13:36:46 -0500 Received: from mail.openrapids.net ([64.15.138.104]:45435 "EHLO blackscsi.openrapids.net" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1758259Ab0KQSgp (ORCPT ); Wed, 17 Nov 2010 13:36:45 -0500 Date: Wed, 17 Nov 2010 13:36:42 -0500 From: Mathieu Desnoyers To: Tom Zanussi Cc: Peter Zijlstra , Ingo Molnar , "Ted Ts'o" , Thomas Gleixner , LKML , Linus Torvalds , Andrew Morton , Steven Rostedt , Arjan van de Ven , Arnaldo Carvalho de Melo , Frederic Weisbecker , Masami Hiramatsu , Li Zefan , Jason Baron , "David S. Miller" , Christoph Hellwig , Pekka Enberg , Lai Jiangshan , Eric Dumazet Subject: Re: [ANNOUNCE] New utility: 'trace' Message-ID: <20101117183642.GE13717@Krystal> References: <20101117013700.GA3290@thunk.org> <20101117132404.GF27063@elte.hu> <1290001128.2109.785.camel@laptop> <20101117140002.GH27063@elte.hu> <1290003110.2109.822.camel@laptop> <1290008001.1921.14.camel@elnicho> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1290008001.1921.14.camel@elnicho> X-Editor: vi X-Info: http://www.efficios.com X-Operating-System: Linux/2.6.26-2-686 (i686) X-Uptime: 13:29:14 up 55 days, 22:31, 6 users, load average: 0.22, 0.24, 0.18 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 Content-Length: 2158 Lines: 53 * Tom Zanussi (tzanussi@gmail.com) wrote: [...] > IIRC, I think the conclusion we came to was that it could be done > mechanically if for example the right-hand-side of an assignment in > TP_fast_assign() only involved a simple variable assignment, but as > Steve pointed out, some assignments are more complicated than that. Yep, we came up to the same conclusions in UST. > For example, in the sched_switch tracepoint assignments: > > __entry->prev_prio = prev->prio; > __entry->prev_state = __trace_sched_switch_state(prev); > > so the prev_prio should be able to be tested 'in-line' but the > prev_state would require a temporary buffer to write the value into > before doing the test as mentioned by Steve. At which point you're no > further ahead (in that case) than the current situation... if we change all assignments to, e.g.: _tp_assign(__entry->prev_prio, prev->prio) _tp_assign(__entry->prev_state, __trace_sched_switch_state(prev)) then we can redefine the macros for filtering much more easily than with the " = " assignment operator. About your comment above, what is the problem with evaluating "__trace_sched_switch_state(prev)" twice ? It will typically be cache-hot after the first evaluation, so I wonder if, in practice, we really save a significant amount of cycles by saving its result between filtering and writing into trace buffers. As I pointed out earlier, for my customers, having a very, very fast filter "out" case is more important that trying to squeeze a few cycles out of the filter passed case. Also, how many of these "__trace_sched_switch_state(prev)" are static inlines vs actual function calls ? If it's mostly static inlines to dereference a few pointers, doing it the second time when the filter passed won't hurt much. Thanks, Mathieu -- Mathieu Desnoyers Operating System Efficiency R&D Consultant EfficiOS Inc. http://www.efficios.com -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/