From: Pratik Rajesh Sampat <psampat@linux.ibm.com>
To: rjw@rjwysocki.net, daniel.lezcano@linaro.org, mpe@ellerman.id.au,
benh@kernel.crashing.org, paulus@samba.org,
srivatsa@csail.mit.edu, shuah@kernel.org, ego@linux.vnet.ibm.com,
svaidy@linux.ibm.com, linux-pm@vger.kernel.org,
linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org,
linux-kselftest@vger.kernel.org
Subject: [PATCH 0/2] Selftest for cpuidle latency measurement
Date: Tue, 7 Jul 2020 20:59:15 +0530 [thread overview]
Message-ID: <20200707152917.10652-1-psampat@linux.ibm.com> (raw)
The patch series introduces a mechanism to measure wakeup latency for
IPI and timer based interrupts
The motivation behind this series is to find significant deviations
behind advertised latency and resisdency values
To achieve this, we introduce a kernel module and expose its control
knobs through the debugfs interface that the selftests can engage with.
The kernel module provides the following interfaces within
/sys/kernel/debug/latency_test/ for,
1. IPI test:
ipi_cpu_dest # Destination CPU for the IPI
ipi_cpu_src # Origin of the IPI
ipi_latency_ns # Measured latency time in ns
2. Timeout test:
timeout_cpu_src # CPU on which the timer to be queued
timeout_expected_ns # Timer duration
timeout_diff_ns # Difference of actual duration vs expected timer
To include the module, check option and include as module
kernel hacking -> Cpuidle latency selftests
The selftest inserts the module, disables all the idle states and
enables them one by one testing:
1. Keeping source CPU constant, iterates through all the CPUS measuring
IPI latency for baseline (CPU is busy with "yes" workload) and the
when the CPU is at rest
2. Iterating through all the CPUs, sending expected timer durations to
be equivalent to the residency of the the deepest idle state
enabled and extracting the difference in time between the time of
wakeup and the expected timer duration
Usage
-----
Can be used in conjuction to the rest of the selftests.
Default Output location in: tools/testing/cpuidle/cpuidle.log
To run this test specifically:
$ make -C tools/testing/selftests TARGETS="cpuidle" run_tests
There are a few optinal arguments too that the script can take
[-h <help>]
[-m <location of the module>]
[-o <location of the output>]
Sample output snippet
---------------------
--IPI Latency Test---
---Enabling state: 0---
SRC_CPU DEST_CPU Base_IPI_Latency(ns) IPI_Latency(ns)
0 0 328 291
0 1 1500 1071
0 2 1070 1062
0 3 1557 1668
. . . .
Expected IPI latency(ns): 1000
Baseline Average IPI latency(ns): 1113
Observed Average IPI latency(ns): 1023
--Timeout Latency Test--
---Enabling state: 0---
Wakeup_src Baseline_delay(ns) Delay(ns)
0 3134 2128
1 2275 2107
2 2222 2198
3 2421 2325
. . . .
Expected timeout(ns): 200
Baseline Average timeout diff(ns): 2513
Observed Average timeout diff(ns): 2189
Pratik Rajesh Sampat (2):
cpuidle: Trace IPI based and timer based wakeup latency from idle
states
selftest/cpuidle: Add support for cpuidle latency measurement
drivers/cpuidle/Makefile | 1 +
drivers/cpuidle/test-cpuidle_latency.c | 150 +++++++++++++
lib/Kconfig.debug | 10 +
tools/testing/selftests/Makefile | 1 +
tools/testing/selftests/cpuidle/Makefile | 6 +
tools/testing/selftests/cpuidle/cpuidle.sh | 240 +++++++++++++++++++++
tools/testing/selftests/cpuidle/settings | 1 +
7 files changed, 409 insertions(+)
create mode 100644 drivers/cpuidle/test-cpuidle_latency.c
create mode 100644 tools/testing/selftests/cpuidle/Makefile
create mode 100755 tools/testing/selftests/cpuidle/cpuidle.sh
create mode 100644 tools/testing/selftests/cpuidle/settings
--
2.25.4
next reply other threads:[~2020-07-07 15:35 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-07 15:29 Pratik Rajesh Sampat [this message]
2020-07-07 15:29 ` [PATCH 1/2] cpuidle: Trace IPI based and timer based wakeup latency from idle states Pratik Rajesh Sampat
2020-07-07 15:29 ` [PATCH 2/2] selftest/cpuidle: Add support for cpuidle latency measurement Pratik Rajesh Sampat
2020-07-07 15:40 ` Shuah Khan
2020-07-07 15:53 ` Pratik Sampat
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200707152917.10652-1-psampat@linux.ibm.com \
--to=psampat@linux.ibm.com \
--cc=benh@kernel.crashing.org \
--cc=daniel.lezcano@linaro.org \
--cc=ego@linux.vnet.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mpe@ellerman.id.au \
--cc=paulus@samba.org \
--cc=rjw@rjwysocki.net \
--cc=shuah@kernel.org \
--cc=srivatsa@csail.mit.edu \
--cc=svaidy@linux.ibm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).