From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1751122AbdFSPKj (ORCPT <rfc822;w@1wt.eu>);
        Mon, 19 Jun 2017 11:10:39 -0400
Received: from foss.arm.com ([217.140.101.70]:51340 "EHLO foss.arm.com"
        rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
        id S1750982AbdFSPKh (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
        Mon, 19 Jun 2017 11:10:37 -0400
Date: Mon, 19 Jun 2017 16:09:39 +0100
From: Mark Rutland <mark.rutland@arm.com>
To: Andi Kleen <ak@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>,
        Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@redhat.com>,
        Arnaldo Carvalho de Melo <acme@kernel.org>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        Kan Liang <kan.liang@intel.com>,
        Dmitri Prokhorov <Dmitry.Prohorov@intel.com>,
        Valery Cherepennikov <valery.cherepennikov@intel.com>,
        David Carrillo-Cisneros <davidcc@google.com>,
        Stephane Eranian <eranian@google.com>, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3 1/n] perf/core: addressing 4x slowdown during
 per-process profiling of STREAM benchmark on Intel Xeon Phi
Message-ID: <20170619150939.GA4555@leverpostej>
References: <09226446-39b9-9bd2-d60f-b9bb947987c5@linux.intel.com>
 <20170615195618.GA8807@leverpostej>
 <07a76338-4c71-569a-d36e-7d6bcd10bd74@linux.intel.com>
 <20170616090938.GB20092@leverpostej>
 <f918eb9b-d856-a3ee-a76b-0aeca8141554@linux.intel.com>
 <22a2dafb-de05-199b-54ed-0c3b24349826@linux.intel.com>
 <20170619124639.GA3661@leverpostej>
 <20170619133831.GB3894@leverpostej>
 <20170619145908.GA23705@tassilo.jf.intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20170619145908.GA23705@tassilo.jf.intel.com>
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Mon, Jun 19, 2017 at 07:59:08AM -0700, Andi Kleen wrote:
> > > For comparison, can you give --per-thread a go prior to these patches
> > > being applied?
> > 
> > FWIW, I had a go with (an old) perf record on an arm64 system using
> > --per-thread, and I see that no samples are recorded, which seems like a
> > bug.
> > 
> > With --per-thread, the slwodown was ~20%, whereas with the defaults it
> > was > 400%.
> 
> I'm not sure what the point of the experiment is? It has to work
> with reasonable overead even without --per-thread.
> 
> FWIW Alexey already root caused the problem, so there's no need
> to restart the debugging.

Sure; we understand where that overhead is coming from, we have an idea
as to how to mitigate that, and we should try to make that work it we
can.

I was trying to get a feel for how that compares to what we can do
today. For other reasons (e.g. fd exhaustion), opening NR_CPUS * n
events might not be a great idea on systems with a huge number of CPUs.
We might want a heuristic in the perf tool regardless.

Thanks,
Mark.