Date: Fri, 24 Mar 2017 04:40:51 -0700
From: Andi Kleen <ak@linux.intel.com>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Kan Liang <kan.liang@intel.com>, peterz@infradead.org,
        mingo@redhat.com, acme@kernel.org, linux-kernel@vger.kernel.org,
        eranian@google.com, jolsa@kernel.org
Subject: Re: [PATCH 0/3]measure SMI cost
Message-ID: <20170324114051.GC9371@tassilo.jf.intel.com>
References: <1490293551-5552-1-git-send-email-kan.liang@intel.com>
 <alpine.DEB.2.20.1703240942590.3688@nanos>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <alpine.DEB.2.20.1703240942590.3688@nanos>
User-Agent: Mutt/1.8.0 (2017-02-23)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 564
Lines: 13

> > A new --smi-cost mode in perf stat is implemented to measure the SMI cost
> > by calculating cycles and aperf results. In practice, the percentages of
> > SMI cycles should be more useful than absolute value.
> 
> That's only true for performance oriented analysis, but for analyzing the
> root cause of latencies the actual cycles are definitely interesting.

perf stat also prints the absolute cycles of course (unless you do --metric-only)

It cannot print individual cycles (per SMI occurrence), the only
way to do that would be to poll constantly.

-Andi