[RFC PATCH v7 0/6] TPEBS counting mode support

weilin.wang@intel.com posted 6 patches 1 year, 10 months ago
There is a newer version of this series
tools/perf/builtin-stat.c                     |  249 +-
.../arch/x86/meteorlake/metricgroups.json     |  127 +
.../arch/x86/meteorlake/mtl-metrics.json      | 2551 +++++++++++++++++
tools/perf/util/data.c                        |    7 +-
tools/perf/util/metricgroup.c                 |   87 +-
tools/perf/util/metricgroup.h                 |   22 +-
tools/perf/util/stat-display.c                |   69 +
tools/perf/util/stat-shadow.c                 |   19 +
tools/perf/util/stat.h                        |    4 +
9 files changed, 3115 insertions(+), 20 deletions(-)
create mode 100644 tools/perf/pmu-events/arch/x86/meteorlake/metricgroups.json
create mode 100644 tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json
[RFC PATCH v7 0/6] TPEBS counting mode support
Posted by weilin.wang@intel.com 1 year, 10 months ago
From: Weilin Wang <weilin.wang@intel.com>

Changes in v7:
- Update code and comments for better code quality [Namhyung]
- Add a separate commit for perf data [Namhyung]
- Update retire latency print function to improve alignment [Namhyung]

v6: https://lore.kernel.org/all/20240329191224.1046866-1-weilin.wang@intel.com/

Weilin Wang (6):
  perf stat: Parse and find tpebs events when parsing metrics to prepare
    for perf record sampling
  perf data: Allow to use given fd in data->file.fd
  perf stat: Fork and launch perf record when perf stat needs to get
    retire latency value for a metric.
  perf stat: Add retire latency values into the expr_parse_ctx to
    prepare for final metric calculation
  perf stat: Add retire latency print functions to print out at the very
    end of print out
  perf vendor events intel: Add MTL metric json files

 tools/perf/builtin-stat.c                     |  249 +-
 .../arch/x86/meteorlake/metricgroups.json     |  127 +
 .../arch/x86/meteorlake/mtl-metrics.json      | 2551 +++++++++++++++++
 tools/perf/util/data.c                        |    7 +-
 tools/perf/util/metricgroup.c                 |   87 +-
 tools/perf/util/metricgroup.h                 |   22 +-
 tools/perf/util/stat-display.c                |   69 +
 tools/perf/util/stat-shadow.c                 |   19 +
 tools/perf/util/stat.h                        |    4 +
 9 files changed, 3115 insertions(+), 20 deletions(-)
 create mode 100644 tools/perf/pmu-events/arch/x86/meteorlake/metricgroups.json
 create mode 100644 tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json

--
2.43.0
Re: [RFC PATCH v7 0/6] TPEBS counting mode support
Posted by Namhyung Kim 1 year, 9 months ago
Hello Weilin,

On Tue, Apr 2, 2024 at 2:45 PM <weilin.wang@intel.com> wrote:
>
> From: Weilin Wang <weilin.wang@intel.com>
>
> Changes in v7:
> - Update code and comments for better code quality [Namhyung]
> - Add a separate commit for perf data [Namhyung]
> - Update retire latency print function to improve alignment [Namhyung]
>
> v6: https://lore.kernel.org/all/20240329191224.1046866-1-weilin.wang@intel.com/

In general, I think you need to explain what exactly TPEBS is and why
you want to do this for TPEBS.  Maybe somewhere in the documentation.

Thanks,
Namhyung

>
> Weilin Wang (6):
>   perf stat: Parse and find tpebs events when parsing metrics to prepare
>     for perf record sampling
>   perf data: Allow to use given fd in data->file.fd
>   perf stat: Fork and launch perf record when perf stat needs to get
>     retire latency value for a metric.
>   perf stat: Add retire latency values into the expr_parse_ctx to
>     prepare for final metric calculation
>   perf stat: Add retire latency print functions to print out at the very
>     end of print out
>   perf vendor events intel: Add MTL metric json files
>
>  tools/perf/builtin-stat.c                     |  249 +-
>  .../arch/x86/meteorlake/metricgroups.json     |  127 +
>  .../arch/x86/meteorlake/mtl-metrics.json      | 2551 +++++++++++++++++
>  tools/perf/util/data.c                        |    7 +-
>  tools/perf/util/metricgroup.c                 |   87 +-
>  tools/perf/util/metricgroup.h                 |   22 +-
>  tools/perf/util/stat-display.c                |   69 +
>  tools/perf/util/stat-shadow.c                 |   19 +
>  tools/perf/util/stat.h                        |    4 +
>  9 files changed, 3115 insertions(+), 20 deletions(-)
>  create mode 100644 tools/perf/pmu-events/arch/x86/meteorlake/metricgroups.json
>  create mode 100644 tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json
>
> --
> 2.43.0
>
>
RE: [RFC PATCH v7 0/6] TPEBS counting mode support
Posted by Wang, Weilin 1 year, 9 months ago

> -----Original Message-----
> From: Namhyung Kim <namhyung@kernel.org>
> Sent: Monday, April 22, 2024 12:10 PM
> To: Wang, Weilin <weilin.wang@intel.com>
> Cc: Ian Rogers <irogers@google.com>; Arnaldo Carvalho de Melo
> <acme@kernel.org>; Peter Zijlstra <peterz@infradead.org>; Ingo Molnar
> <mingo@redhat.com>; Alexander Shishkin
> <alexander.shishkin@linux.intel.com>; Jiri Olsa <jolsa@kernel.org>; Hunter,
> Adrian <adrian.hunter@intel.com>; Kan Liang <kan.liang@linux.intel.com>;
> linux-perf-users@vger.kernel.org; linux-kernel@vger.kernel.org; Taylor, Perry
> <perry.taylor@intel.com>; Alt, Samantha <samantha.alt@intel.com>; Biggers,
> Caleb <caleb.biggers@intel.com>
> Subject: Re: [RFC PATCH v7 0/6] TPEBS counting mode support
> 
> Hello Weilin,
> 
> On Tue, Apr 2, 2024 at 2:45 PM <weilin.wang@intel.com> wrote:
> >
> > From: Weilin Wang <weilin.wang@intel.com>
> >
> > Changes in v7:
> > - Update code and comments for better code quality [Namhyung]
> > - Add a separate commit for perf data [Namhyung]
> > - Update retire latency print function to improve alignment [Namhyung]
> >
> > v6: https://lore.kernel.org/all/20240329191224.1046866-1-
> weilin.wang@intel.com/
> 
> In general, I think you need to explain what exactly TPEBS is and why
> you want to do this for TPEBS.  Maybe somewhere in the documentation.
> 
Hi Namhyung,

Ok, I will work on this. I had explanations in about TPEBS in the first version of 
the code patch. I will add that in a more propriate place. 

Thanks,
Weilin

> Thanks,
> Namhyung
> 

> >
> > Weilin Wang (6):
> >   perf stat: Parse and find tpebs events when parsing metrics to prepare
> >     for perf record sampling
> >   perf data: Allow to use given fd in data->file.fd
> >   perf stat: Fork and launch perf record when perf stat needs to get
> >     retire latency value for a metric.
> >   perf stat: Add retire latency values into the expr_parse_ctx to
> >     prepare for final metric calculation
> >   perf stat: Add retire latency print functions to print out at the very
> >     end of print out
> >   perf vendor events intel: Add MTL metric json files
> >
> >  tools/perf/builtin-stat.c                     |  249 +-
> >  .../arch/x86/meteorlake/metricgroups.json     |  127 +
> >  .../arch/x86/meteorlake/mtl-metrics.json      | 2551 +++++++++++++++++
> >  tools/perf/util/data.c                        |    7 +-
> >  tools/perf/util/metricgroup.c                 |   87 +-
> >  tools/perf/util/metricgroup.h                 |   22 +-
> >  tools/perf/util/stat-display.c                |   69 +
> >  tools/perf/util/stat-shadow.c                 |   19 +
> >  tools/perf/util/stat.h                        |    4 +
> >  9 files changed, 3115 insertions(+), 20 deletions(-)
> >  create mode 100644 tools/perf/pmu-
> events/arch/x86/meteorlake/metricgroups.json
> >  create mode 100644 tools/perf/pmu-events/arch/x86/meteorlake/mtl-
> metrics.json
> >
> > --
> > 2.43.0
> >
> >