All of lore.kernel.org
 help / color / mirror / Atom feed
From: Namhyung Kim <namhyung@kernel.org>
To: Ian Rogers <irogers@google.com>
Cc: linux-perf-users@vger.kernel.org
Subject: Re: [RFC] perf tools: Update JSON event description
Date: Fri, 31 Oct 2025 12:25:55 -0700	[thread overview]
Message-ID: <aQUNQ8sHpTqQXoez@google.com> (raw)
In-Reply-To: <CAP-5=fW==xQ=fgyCTZmrPDTc3aikdoLdRUYk5NxEbDq+0HP6mQ@mail.gmail.com>

On Wed, Oct 29, 2025 at 08:28:34AM -0700, Ian Rogers wrote:
> On Mon, Oct 27, 2025 at 11:58 AM Namhyung Kim <namhyung@kernel.org> wrote:
> >
> > Hi Ian,
> >
> > I'm trying to make this change in the JSON description for hardware and
> > software events.  But I got a build failure in the empty-pmu-events.c
> > even after I re-generated it like below.
> >
> >   cd pmu-events
> >   ./jevents.py none none $PWD empty-pmu-events.c
> >
> > Did I miss something?
> 
> So the build failure/diff has the path to the generated
> empty-pmu-events.c. I'd copy that file rather than try to recreate the

I see.

> command line - although there should be no reason generating the
> command line fails it looks to me that you need to pass "$PWD/arch"
> rather than "$PWD":
> https://web.git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git/tree/tools/perf/pmu-events/Build?h=tmp.perf-tools-next#n51
> Fwiw, the formatting in legacy-hardware.json was based on Intel doing
> the same thing and not wanting to start new conventions:
> https://web.git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git/tree/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json?h=tmp.perf-tools-next#n32
> ```
>     {
>         "BriefDescription": "Conditional branch instructions retired.
> [This event is alias to BR_INST_RETIRED.CONDITIONAL]",
>         "Counter": "0,1,2,3",
>         "Errata": "SKL091",
>         "EventCode": "0xC4",
>         "EventName": "BR_INST_RETIRED.COND",
>         "PublicDescription": "This event counts conditional branch
> instructions retired. [This event is alias to
> BR_INST_RETIRED.CONDITIONAL]",
>         "SampleAfterValue": "400009",
>         "UMask": "0x1"
>     },
>     {
>         "BriefDescription": "Conditional branch instructions retired.
> [This event is alias to BR_INST_RETIRED.COND]",
>         "Counter": "0,1,2,3",
>         "Errata": "SKL091",
>         "EventCode": "0xC4",
>         "EventName": "BR_INST_RETIRED.CONDITIONAL",
>         "PEBS": "1",
>         "PublicDescription": "This event counts conditional branch
> instructions retired. [This event is alias to BR_INST_RETIRED.COND]",
>         "SampleAfterValue": "400009",
>         "UMask": "0x1"
>     },
> ```
> As the order of seeing events isn't well defined, I'm not sure what we
> gain by shorter descriptions and it could be frustrating for a user to
> see that 'cycles' definition is in effect a redirection.

I generally prefer short and clear descriptions and feel better to
remove duplications.  But I don't want to change the vendor JSON and
this change is not important so I can drop it.

Thanks,
Namhyung


      reply	other threads:[~2025-10-31 19:25 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-27 18:58 [RFC] perf tools: Update JSON event description Namhyung Kim
2025-10-29 15:28 ` Ian Rogers
2025-10-31 19:25   ` Namhyung Kim [this message]

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=aQUNQ8sHpTqQXoez@google.com \
    --to=namhyung@kernel.org \
    --cc=irogers@google.com \
    --cc=linux-perf-users@vger.kernel.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.