Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752614AbcLFLZm (ORCPT ); Tue, 6 Dec 2016 06:25:42 -0500 Received: from bombadil.infradead.org ([198.137.202.9]:55588 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751427AbcLFLZl (ORCPT ); Tue, 6 Dec 2016 06:25:41 -0500 Date: Tue, 6 Dec 2016 12:25:31 +0100 From: Peter Zijlstra To: kan.liang@intel.com Cc: mingo@redhat.com, acme@kernel.org, linux-kernel@vger.kernel.org, alexander.shishkin@linux.intel.com, tglx@linutronix.de, namhyung@kernel.org, jolsa@kernel.org, adrian.hunter@intel.com, wangnan0@huawei.com, mark.rutland@arm.com, andi@firstfloor.org Subject: Re: [PATCH V2 05/13] perf/core: output side-band events overhead Message-ID: <20161206112531.GM3124@twins.programming.kicks-ass.net> References: <1480713561-6617-1-git-send-email-kan.liang@intel.com> <1480713561-6617-6-git-send-email-kan.liang@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1480713561-6617-6-git-send-email-kan.liang@intel.com> User-Agent: Mutt/1.5.23.1 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1136 Lines: 33 On Fri, Dec 02, 2016 at 04:19:13PM -0500, kan.liang@intel.com wrote: > From: Kan Liang > > Iterating all events which need to receive side-band events also bring > some overhead. > > The side-band events overhead PERF_CORE_SB_OVERHEAD is a common overhead > type. > > Signed-off-by: Kan Liang > diff --git a/kernel/events/core.c b/kernel/events/core.c > index 025a19d..85706fb 100644 > --- a/kernel/events/core.c > +++ b/kernel/events/core.c > @@ -1830,8 +1830,12 @@ event_sched_out(struct perf_event *event, > if (event->attr.exclusive || !cpuctx->active_oncpu) > cpuctx->exclusive = 0; > > - if (log_overhead && cpuctx->mux_overhead.nr) > - perf_log_overhead(event, PERF_CORE_MUX_OVERHEAD, &cpuctx->mux_overhead); > + if (log_overhead) { > + if (cpuctx->mux_overhead.nr) > + perf_log_overhead(event, PERF_CORE_MUX_OVERHEAD, &cpuctx->mux_overhead); > + if (ctx->sb_overhead.nr) > + perf_log_overhead(event, PERF_CORE_SB_OVERHEAD, &ctx->sb_overhead); > + } Urgh, that's getting uglier by the minute, and again, its not mentioned. > > perf_pmu_enable(event->pmu); > }