From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id A9A2EC61DF7 for ; Thu, 23 Nov 2023 14:18:34 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1345747AbjKWOS0 (ORCPT ); Thu, 23 Nov 2023 09:18:26 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:38216 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1345780AbjKWOSU (ORCPT ); Thu, 23 Nov 2023 09:18:20 -0500 Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id BC68610DD for ; Thu, 23 Nov 2023 06:18:25 -0800 (PST) Received: by smtp.kernel.org (Postfix) with ESMTPSA id 35997C433C7; Thu, 23 Nov 2023 14:18:25 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1700749105; bh=5dH3Z1NJbf5X4mxp0nH6utgpxlpIoWc66IrPh9xa4qg=; h=Date:From:To:Cc:Subject:References:In-Reply-To:From; b=sdhEehH/Lvn6xsUmZaa7Zn9iR0bMce7f6LD6JAW6bDLzFqIjJxD8Bl5bEVb6Ahihm EqwjJPRkegwijJcIsTzWndIeKmz1Ow2ocG5GHU5wY2xNQRnOsfVwSYQqjyo350lXIg 4SS0w8Xne4/DjKsZAif6vltTDfFBqgx7i5GtBJycK+1VTTyGg23R91OsfznvTNq/83 waqcF7ms9GmCtzvilcMajKyR4qQFqG75e3Phb9gEOEIYNfr0M3rIfaIzacCMG+kW6y /Xqrlgf4zqiCf760au146jJMKWCrXhHlYiACWV+l6+zmvgPEiZQUPYPb5XafHOmqxN sFp/Ap0v/yidQ== Received: by quaco.ghostprotocols.net (Postfix, from userid 1000) id 7B56140094; Thu, 23 Nov 2023 11:18:22 -0300 (-03) Date: Thu, 23 Nov 2023 11:18:22 -0300 From: Arnaldo Carvalho de Melo To: Hector Martin Cc: Mark Rutland , Ian Rogers , Marc Zyngier , Namhyung Kim , Peter Zijlstra , Ingo Molnar , Alexander Shishkin , Jiri Olsa , Adrian Hunter , Kan Liang , James Clark , linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [RFC PATCH v1] perf parse-events: Make legacy events lower priority than sysfs/json Message-ID: References: <20231123042922.834425-1-irogers@google.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: X-Url: http://acmel.wordpress.com Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Em Thu, Nov 23, 2023 at 05:45:19PM +0900, Hector Martin escreveu: > On 2023/11/23 13:29, Ian Rogers wrote: > > The bulk of this change is updating all of the parse-events test > > expectations so that if a sysfs/json event exists for a PMU the test > > doesn't fail - a further sign, if it were needed, that the legacy > > event priority was a known and tested behavior of the perf tool. > > Signed-off-by: Ian Rogers > > --- > > This is a large behavioral change: > > 1) the scope of the change means it should bake on linux-next and I > > don't believe should be a 6.7-rc fix. > > 2) a fixes tag and stable backport I don't think are appropriate. The > > real reported issue is with the PMU driver. A backport would bring the > > risk that later fixes, due to the large behavior change, wouldn't be > > backported and past releases get regressed in scenarios like > > hybrid. Backports for the perf tool are also less necessary than say a > > buggy PMU driver, as distributions should be updating to the latest > > perf tool regardless of what Linux kernel is being run (the perf tool > > is backward compatible). > > Tested-by: Hector Martin Thanks, applied locally, doing some tests and then will push for linux-next to pick it up. Mark, can I have your Reviewed-by or Acked-by? - Arnaldo > $ sudo taskset -c 2 ./perf stat -e apple_icestorm_pmu/cycles/ -e > apple_firestorm_pmu/cycles/ -e cycles echo > > > Performance counter stats for 'echo': > > apple_icestorm_pmu/cycles/ > (0.00%) > 34,622 apple_firestorm_pmu/cycles/ > > 30,751 cycles > > > 0.000429625 seconds time elapsed > > 0.000000000 seconds user > 0.000443000 seconds sys > > > $ sudo taskset -c 0 ./perf stat -e apple_icestorm_pmu/cycles/ -e > apple_firestorm_pmu/cycles/ -e cycles echo > > > Performance counter stats for 'echo': > > 13,413 apple_icestorm_pmu/cycles/ > > apple_firestorm_pmu/cycles/ > (0.00%) > cycles > (0.00%) > > 0.000898458 seconds time elapsed > > 0.000908000 seconds user > 0.000000000 seconds sys > > (It would be nice to have "cycles" match/aggregate both PMUs, but that's > a story for another day. The behavior above is what was there in 6.4 and > earlier.)