linux-kernel - Re: [PATCH v3 0/8] perf sched: Introduce stats tool

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <1840fbe3-d538-4b41-8465-c22d9f1d1e1a@amd.com>
Date: Thu, 10 Apr 2025 15:59:04 +0530
From: "Sapkal, Swapnil" <swapnil.sapkal@....com>
To: "Chen, Yu C" <yu.c.chen@...el.com>
CC: <ravi.bangoria@....com>, <mark.rutland@....com>,
	<alexander.shishkin@...ux.intel.com>, <jolsa@...nel.org>,
	<rostedt@...dmis.org>, <vincent.guittot@...aro.org>,
	<adrian.hunter@...el.com>, <kan.liang@...ux.intel.com>,
	<gautham.shenoy@....com>, <kprateek.nayak@....com>, <juri.lelli@...hat.com>,
	<yangjihong@...edance.com>, <void@...ifault.com>, <tj@...nel.org>,
	<sshegde@...ux.ibm.com>, <linux-kernel@...r.kernel.org>,
	<linux-perf-users@...r.kernel.org>, <santosh.shukla@....com>,
	<ananth.narayan@....com>, <sandipan.das@....com>, <peterz@...radead.org>,
	<acme@...nel.org>, <james.clark@....com>, <namhyung@...nel.org>,
	<irogers@...gle.com>, <mingo@...hat.com>
Subject: Re: [PATCH v3 0/8] perf sched: Introduce stats tool

Hi Chenyu,

On 4/10/2025 3:11 PM, Chen, Yu C wrote:
> Hi Swapnil,
> 
> On 3/11/2025 8:02 PM, Swapnil Sapkal wrote:
>> MOTIVATION
>> ----------
>>
>> Existing `perf sched` is quite exhaustive and provides lot of insights
>> into scheduler behavior but it quickly becomes impractical to use for
>> long running or scheduler intensive workload. For ex, `perf sched record`
>> has ~7.77% overhead on hackbench (with 25 groups each running 700K loops
>> on a 2-socket 128 Cores 256 Threads 3rd Generation EPYC Server), and it
>> generates huge 56G perf.data for which perf takes ~137 mins to prepare
>> and write it to disk [1].
>>
>> Unlike `perf sched record`, which hooks onto set of scheduler tracepoints
>> and generates samples on a tracepoint hit, `perf sched stats record` takes
>> snapshot of the /proc/schedstat file before and after the workload, i.e.
>> there is almost zero interference on workload run. Also, it takes very
>> minimal time to parse /proc/schedstat, convert it into perf samples and
>> save those samples into perf.data file. Result perf.data file is much
>> smaller. So, overall `perf sched stats record` is much more light weight
>> compare to `perf sched record`.
>>
>> We, internally at AMD, have been using this (a variant of this, known as
>> "sched-scoreboard"[2]) and found it to be very useful to analyse impact
>> of any scheduler code changes[3][4]. Prateek used v2[5] of this patch
>> series to report the analysis[6][7].
>>
>> Please note that, this is not a replacement of perf sched record/report.
>> The intended users of the new tool are scheduler developers, not regular
>> users.
>>
>> USAGE
>> -----
>>
>>    # perf sched stats record
>>    # perf sched stats report
>>    # perf sched stats diff
>>
> 
> May I know the status of this patch set? I tested it on a 96 cores system and it works as expected in general.

Thank you for testing the patch set. I am working on v4 based on the Namhyung's suggestions.

> 
> One nit question:
> Is perf.data and perf.data.old the default files
> for comparison if no files are provided in
> perf sched stats diff?
> 

Yes, if no files are provided to `perf sched stats diff`, it will take perf.data and perf.data.old as defaults.

> 
> thanks,
> Chenyu
> 
> 
--
Thanks and Regards,
Swapnil