| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <886aa016-a439-4981-892d-3e92df526f41@linux.ibm.com>
Date: Mon, 25 Nov 2024 12:02:18 +0530
From: Anjali K <anjalik@...ux.ibm.com>
To: Christian Loehle <christian.loehle@....com>,
Qais Yousef <qyousef@...alina.io>,
"Rafael J. Wysocki" <rafael@...nel.org>,
Viresh Kumar <viresh.kumar@...aro.org>, Ingo Molnar <mingo@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
Vincent Guittot <vincent.guittot@...aro.org>,
Juri Lelli <juri.lelli@...hat.com>
Cc: Steven Rostedt <rostedt@...dmis.org>,
Dietmar Eggemann <dietmar.eggemann@....com>,
Ben Segall
<bsegall@...gle.com>, Mel Gorman <mgorman@...e.de>,
Valentin Schneider <vschneid@...hat.com>,
Hongyan Xia
<hongyan.xia2@....com>, John Stultz <jstultz@...gle.com>,
linux-pm@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v7] sched: Consolidate cpufreq updates
On 19/10/24 00:02, Anjali K wrote:
>> Do you mind trying schedutil with a reasonable rate_limit_us, too?
> I think the schedutil governor is not working on my system because the cpu
> frequency shoots to the maximum (3.9GHz) even when the system is only 10%
> loaded.
> I ran stress-ng --cpu `nproc` --cpu-load 10.
> The mpstat command shows that the system is 10% loaded:
> 10:55:25 AM CPU %usr %nice %sys %iowait %irq %soft %steal %guest %gnice %idle
> 10:56:50 AM all 10.03 0.00 0.02 0.00 0.18 0.00 0.00 0.00 0.00 89.76
> But cpupower frequency-info showed that the system is at max frequency
> root@...zz10:~# cpupower frequency-info
> <snipped>
> available cpufreq governors: conservative ondemand performance schedutil
> current policy: frequency should be within 2.30 GHz and 3.90 GHz.
> The governor "schedutil" may decide which speed to use
> within this range.
> current CPU frequency: 3.90 GHz (asserted by call to hardware)
> <snipped>
> This is not expected, right?
> I will work on finding out why the schedutil governor is not working on
> this system and get back.
Hi, I found that the schedutil governor is working on this system. I
concluded this because when I printed the util parameter passed in
get_next_freq() when running stress-ng --cpu `nproc` --cpu-load 10, the
util parameter was always 1024 ( equal to the cpu capacity) and so the
frequency gets set to the maximum as expected. Adding `--cpu-load-slice 10`
to the stress-ng commandline, I got lower util values and found that the
frequency is being set as per the system load as shown below:
+-------------+------------+------------+
| stress-ng | avg | run-to-run |
| load % | cpu freq | std dev% |
| | (Hz) | |
+-------------+------------+------------+
| 10% | 2.80 | 1.51 |
| 30% | 3.53 | 2.47 |
| 50% | 3.70 | 0.01 |
| 70% | 3.61 | 0.08 |
| 90% | 3.54 | 0.04 |
+-------------+------------+------------+
Note that the frequency range for this system is 2.3GHz - 3.9Ghz.
The results with the schedutil governor for the same set of benchmarks is
as follows. Each benchmark is run 3 times:
+------------------------------------------------------+--------------------+----------+--------+---------+------------+
| Benchmark | Baseline | Baseline |Baseline|Baseline |Regression% |
| | (6.10.0-rc1 tip | + patch | |+ patch | |
| | sched/core) | |stdev % | stdev % | |
+------------------------------------------------------+--------------------+----------+--------+---------+------------+
|Hackbench run duration (sec) | 1 | 1.01 | 1.60 | 1.80 | 0.69 |
|Lmbench simple fstat (usec) | 1 | 0.99 | 0.40 | 0.07 | -0.66 |
|Lmbench simple open/close (usec) | 1 | 0.99 | 0.01 | 0.04 | -0.51 |
|Lmbench simple read (usec) | 1 | 1 | 0.23 | 0.41 | -0.05 |
|Lmbench simple stat (usec) | 1 | 0.98 | 0.13 | 0.03 | -1.54 |
|Lmbench simple syscall (usec) | 1 | 0.99 | 0.89 | 0.69 | -0.59 |
|Lmbench simple write (usec) | 1 | 1 | 0.27 | 0.80 | 0 |
|Unixbench execl throughput (lps) | 1 | 1 | 0.44 | 0.13 | 0.17 |
|Unixbench Process Creation (lps) | 1 | 0.99 | 0.11 | 0.13 | -0.68 |
|Unixbench Shell Scripts (1 concurrent) (lpm) | 1 | 1 | 0.07 | 0.05 | 0.03 |
|Unixbench Shell Scripts (8 concurrent) (lpm) | 1 | 1 | 0.05 | 0.11 | -0.13 |
+------------------------------------------------------+--------------------+----------+--------+---------+------------+
I did not see any significant improvements/regressions on applying the patch.
I ignored the Stress-ng and Unixbench Pipebased Context Switching
benchmarks as they showed high run-to-run variation with the schedutil
governor (without applying the patch) of 10.68% and 12.5% respectively.
Thank you,
Anjali K
Powered by blists - more mailing lists