From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751179AbeAVFKg (ORCPT ); Mon, 22 Jan 2018 00:10:36 -0500 Received: from mga11.intel.com ([192.55.52.93]:39077 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750863AbeAVFKe (ORCPT ); Mon, 22 Jan 2018 00:10:34 -0500 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.46,395,1511856000"; d="scan'208";a="21222141" Subject: Re: [PATCH] perf stat: Ignore error thread when enabling system-wide --per-thread To: Jiri Olsa Cc: acme@kernel.org, jolsa@kernel.org, peterz@infradead.org, mingo@redhat.com, alexander.shishkin@linux.intel.com, Linux-kernel@vger.kernel.org, ak@linux.intel.com, kan.liang@intel.com, yao.jin@intel.com References: <1516117388-10120-1-git-send-email-yao.jin@linux.intel.com> <20180116125132.GD26643@krava> <1189ec53-0d3b-c59c-63f0-4c4ad0d72405@linux.intel.com> <20180116131743.GA17752@krava> From: "Jin, Yao" Message-ID: Date: Mon, 22 Jan 2018 13:10:31 +0800 User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101 Thunderbird/52.5.2 MIME-Version: 1.0 In-Reply-To: <20180116131743.GA17752@krava> Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 1/16/2018 9:17 PM, Jiri Olsa wrote: > On Tue, Jan 16, 2018 at 09:06:09PM +0800, Jin, Yao wrote: >> Just tested. But looks it's not OK for '--per-thread' case. > > yea, I haven't tested much.. might need soem tweaking, > but my point was that it could be doable on one place > instead of introducing another if possible > > jirka > Hi Jiri, I ever considered to move the operation of removing error thread to perf_evsel__fallback(). The perf_evsel__fallback() is common code and it's shared by perf report, perf stat and perf top. While finally I think it'd better let the caller decide to remove error thread and try again, or just return the warning message. perf_evsel__fallback() probably doesn't know what the caller want to do. That's my current thinking. Maybe there will be a better fix... Thanks Jin Yao