Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
IronPort-SDR: CmAeaSXKEuI2EX3CGO99S4RiPWEK8rouML4cKz2J2P5WbP12Orp0MPN/3cCSe55zZ2Qr5U6uHo
 5PqNXGDO+2DQ==
IronPort-SDR: L67woUpoVuqgVtgy6pkvyyzRjvNctYT8LWivC1LtOEmUFWlgEn3YgaVHpkdyYY9cehcrxZ7c+N
 uMZlBfRn1XBQ==
Message-ID: <b59481655c29d081eea4f34c00166517738000e5.camel@gmail.com>
Subject: Re: [RFC v4 1/1] selftests/cpuidle: Add support for cpuidle latency
 measurement
From:   Artem Bityutskiy <dedekind1@gmail.com>
Reply-To: dedekind1@gmail.com
To:     Pratik Rajesh Sampat <psampat@linux.ibm.com>, rjw@rjwysocki.net,
        daniel.lezcano@linaro.org, srivatsa@csail.mit.edu,
        shuah@kernel.org, npiggin@gmail.com, ego@linux.vnet.ibm.com,
        svaidy@linux.ibm.com, linux-pm@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org,
        pratik.r.sampat@gmail.com
Date:   Wed, 02 Sep 2020 18:25:24 +0300
In-Reply-To: <20200902114506.45809-2-psampat@linux.ibm.com>
References: <20200902114506.45809-1-psampat@linux.ibm.com>
         <20200902114506.45809-2-psampat@linux.ibm.com>
Content-Type: text/plain; charset="UTF-8"
User-Agent: Evolution 3.32.5 (3.32.5-1.fc30) 
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, 2020-09-02 at 17:15 +0530, Pratik Rajesh Sampat wrote:
> Measure cpuidle latencies on wakeup to determine and compare with the
> advertsied wakeup latencies for each idle state.

It looks like the measurements include more than just C-state wake,
they also include the overhead of waking up the proces, context switch,
and potentially any interrupts that happen on that CPU. I am not saying
this is not interesting data, it surely is, but it is going to be
larger than you see in cpuidle latency tables. Potentially
significantly larger.

Therefore, I am not sure this program should be advertised as "cpuidle
measurement". It really measures the "IPI latency" in case of the IPI
method.

> A baseline measurement for each case of IPI and timers is taken at
> 100 percent CPU usage to quantify for the kernel-userpsace overhead
> during execution.

At least on Intel platforms, this will mean that the IPI method won't
cover deep C-states like, say, PC6, because one CPU is busy. Again, not
saying this is not interesting, just pointing out the limitation.

I was working on a somewhat similar stuff for x86 platforms, and I am
almost ready to publish that on github. I can notify you when I do so
if you are interested. But here is a small presentation of the approach
that I did on Plumbers last year:

https://youtu.be/Opk92aQyvt0?t=8266

(the link points to the start of my talk)