[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87d1hmx7tn.fsf@tassilo.jf.intel.com>
Date: Wed, 23 Nov 2016 12:25:08 -0800
From: Andi Kleen <andi@...stfloor.org>
To: kan.liang@...el.com
Cc: peterz@...radead.org, mingo@...hat.com, acme@...nel.org,
linux-kernel@...r.kernel.org, alexander.shishkin@...ux.intel.com,
tglx@...utronix.de, namhyung@...nel.org, jolsa@...nel.org,
adrian.hunter@...el.com, wangnan0@...wei.com, mark.rutland@....com
Subject: Re: [PATCH 13/14] perf tools: warn on high overhead
kan.liang@...el.com writes:
> From: Kan Liang <kan.liang@...el.com>
>
> The rough overhead rate can be caculated by the sum of all kinds of
> overhead / elapsed time.
> If the overhead rate is higher than 10%, warning the user.
Thinking about this more: this is comparing the cost of a single
CPU to the total wall clock time. This isn't very good and can
give confusing results with many cores.
Perhaps we need two separate metrics here:
- cost of perf record on its CPU (or later on if it gets multi threaded
more multiple). Warn if this is >50% or so.
- average perf collection overhead on a CPU. The 10% threshold here
seems appropiate.
-Andi
Powered by blists - more mailing lists