linux-kernel - Re: perf: documentation for cycles_no

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

Date:   Mon, 8 Jan 2018 15:00:08 +0100
From:   Jiri Olsa <jolsa@...hat.com>
To:     Julia Lawall <julia.lawall@...6.fr>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Namhyung Kim <namhyung@...nel.org>,
        linux-kernel@...r.kernel.org, Andi Kleen <andi@...stfloor.org>
Subject: Re: perf: documentation for cycles_no_execute event

On Fri, Dec 29, 2017 at 11:58:42AM +0100, Julia Lawall wrote:
> Hello,

hi,
adding Andi in cc, he should be able to answer this

thanks,
jirka

> 
> Many of the x86 pipeline.json files have the brief description "Total
> execution stalls" for both CYCLE_ACTIVITY.CYCLES_NO_EXECUTE and
> CYCLE_ACTIVITY.STALLS_TOTAL.  Should the case for
> CYCLE_ACTIVITY.CYCLES_NO_EXECUTE have a brief description that mentions
> cycles?  Some of the files do have a public description that mentions
> cycles, eg broadwellde/pipeline.json has "Counts number of cycles nothing
> is executed on any execution port.", but others (eg ivytown/pipeline.json)
> just have "Total execution stalls." twice.  Maybe "Cycles where nothing is
> executed" would be ok for CYCLE_ACTIVITY.CYCLES_NO_EXECUTE?
> 
> thanks,
> julia