linux-kernel - Re: [PATCH v7 0/6] perf record: Track sideband events for all CPUs when tracing selected CPUs

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: <603dc4b9-31ae-1525-5668-7dbb1f64420b@intel.com>
Date:   Thu, 31 Aug 2023 13:13:01 +0300
From:   Adrian Hunter <adrian.hunter@...el.com>
To:     Ravi Bangoria <ravi.bangoria@....com>,
        Yang Jihong <yangjihong1@...wei.com>, acme@...nel.org,
        irogers@...gle.com, jolsa@...nel.org, namhyung@...nel.org
Cc:     peterz@...radead.org, mingo@...hat.com, mark.rutland@....com,
        alexander.shishkin@...ux.intel.com, kan.liang@...ux.intel.com,
        james.clark@....com, tmricht@...ux.ibm.com, ak@...ux.intel.com,
        anshuman.khandual@....com, linux-kernel@...r.kernel.org,
        linux-perf-users@...r.kernel.org
Subject: Re: [PATCH v7 0/6] perf record: Track sideband events for all CPUs
 when tracing selected CPUs

On 29/08/23 15:24, Ravi Bangoria wrote:
>>> Number of actual samples are same ~38K. However, the perf.data file is 5x
>>> bigger because of additional sideband data.
>>
>> Yes, if record system wide sideband data, the amount of sideband events will increase proportionally, which is expected.
>>
>>>
>>> I'm pretty sure we don't need most of those additional data. So, thinking
>>> loud, should we post-process perf.data file and filter out unnecessary data?
>>>
>>
>> I wonder if we can add a new function in perf inject.
> 
> Ok. perf inject is one option. But shall we do it bydefault in perf-record?
> It's needed only when profiling target is set of cpus, not for systemwide or
> per-process mode.
> 
>> By reading perf.data and comparing tid of SAMPLE events and sideband events, we can filter out the sideband data of unmatched tasks.
> 
> Yup. But AFAIK, perf-record keeps writing to perf.data and never does post-
> processing on it. So adding support for this will take a bit of effort. Not
> sure if we should do it as part of this series.

I agree there could be more work, but probably better for a separate patch set.