[PATCH v7 0/7] Hwmon PMUs

Ian Rogers posted 7 patches 2 weeks, 1 day ago
There is a newer version of this series
tools/lib/api/io.h                     |   1 +
tools/perf/Documentation/perf-list.txt |  15 +
tools/perf/tests/Build                 |   1 +
tools/perf/tests/builtin-test.c        |   1 +
tools/perf/tests/hwmon_pmu.c           | 340 ++++++++++
tools/perf/tests/tests.h               |   1 +
tools/perf/util/Build                  |   1 +
tools/perf/util/evsel.c                |   9 +
tools/perf/util/hwmon_pmu.c            | 825 +++++++++++++++++++++++++
tools/perf/util/hwmon_pmu.h            | 156 +++++
tools/perf/util/pmu.c                  |  20 +
tools/perf/util/pmu.h                  |   2 +
tools/perf/util/pmus.c                 |   9 +
tools/perf/util/pmus.h                 |   3 +
14 files changed, 1384 insertions(+)
create mode 100644 tools/perf/tests/hwmon_pmu.c
create mode 100644 tools/perf/util/hwmon_pmu.c
create mode 100644 tools/perf/util/hwmon_pmu.h
[PATCH v7 0/7] Hwmon PMUs
Posted by Ian Rogers 2 weeks, 1 day ago
Following the convention of the tool PMU, create a hwmon PMU that
exposes hwmon data for reading. For example, the following shows
reading the CPU temperature and 2 fan speeds alongside the uncore
frequency:
```
$ perf stat -e temp_cpu,fan1,hwmon_thinkpad/fan2/,tool/num_cpus_online/ -M UNCORE_FREQ -I 1000
     1.001153138              52.00 'C   temp_cpu
     1.001153138              2,588 rpm  fan1
     1.001153138              2,482 rpm  hwmon_thinkpad/fan2/
     1.001153138                  8      tool/num_cpus_online/
     1.001153138      1,077,101,397      UNC_CLOCK.SOCKET                 #     1.08 UNCORE_FREQ
     1.001153138      1,012,773,595      duration_time
...
```

Additional data on the hwmon events is in perf list:
```
$ perf list
...
hwmon:
...
  temp_core_0 OR temp2
       [Temperature in unit coretemp named Core 0. crit=100'C,max=100'C crit_alarm=0'C. Unit:
        hwmon_coretemp]
...
```

v7: Try to address feedback from Namhyung wrt size/comprehensibility
    of the hwmon PMU patch. To better explain the config encoding put
    the parser into a patch ahead of the PMU patch and add a unit
    test. This shows how a hwmon filename can be moved back-and-forth
    with a config value as a single patch (two with the test). The
    hwmon PMU patch is then putting the wrapping around that for the
    pmus', parse_event's and evsel reading's benefit.
    
    The alternate approach of not caring about the mapping, name to
    config value, and using the evsel->name wasn't followed. In the
    tool PMU it was made so we can go back-and-forth between event
    names and a type+config, this removed the tool enum value from the
    evsel as now tool events were more 1st class and evsel should
    really just be a wrapper on a perf_event_attr. Using the
    evsel->name wasn't doing that and so the approach of mapping
    filenames and configs, as better highlighted in this series was
    pursued.

    It is expected future PMUs won't be able to cleanly map fixed
    strings to config values, in those cases tables would be
    necessary. Making a hwmon PMU do this and then removing it to
    follow the parsing/mapping done in patch 2 here, would have been a
    lot of additional work which then would be removed.

v6: Add string.h #include for issue reported by kernel test robot.
v5: Fix asan issue in parse_hwmon_filename caught by a TMA metric.
v4: Drop merged patches 1 to 10. Separate adding the hwmon_pmu from
    the update to perf_pmu to use it. Try to make source of literal
    strings clearer via named #defines. Fix a number of GCC warnings.
v3: Rebase, add Namhyung's acked-by to patches 1 to 10.
v2: Address Namhyung's review feedback. Rebase dropping 4 patches
    applied by Arnaldo, fix build breakage reported by Arnaldo.

Ian Rogers (7):
  tools api io: Ensure line_len_out is always initialized
  perf hwmon_pmu: Add hwmon filename parser
  perf test: Add hwmon filename parser test
  perf hwmon_pmu: Add a tool PMU exposing events from hwmon in sysfs
  perf pmu: Add calls enabling the hwmon_pmu
  perf test: Add hwmon "PMU" test
  perf docs: Document tool and hwmon events

 tools/lib/api/io.h                     |   1 +
 tools/perf/Documentation/perf-list.txt |  15 +
 tools/perf/tests/Build                 |   1 +
 tools/perf/tests/builtin-test.c        |   1 +
 tools/perf/tests/hwmon_pmu.c           | 340 ++++++++++
 tools/perf/tests/tests.h               |   1 +
 tools/perf/util/Build                  |   1 +
 tools/perf/util/evsel.c                |   9 +
 tools/perf/util/hwmon_pmu.c            | 825 +++++++++++++++++++++++++
 tools/perf/util/hwmon_pmu.h            | 156 +++++
 tools/perf/util/pmu.c                  |  20 +
 tools/perf/util/pmu.h                  |   2 +
 tools/perf/util/pmus.c                 |   9 +
 tools/perf/util/pmus.h                 |   3 +
 14 files changed, 1384 insertions(+)
 create mode 100644 tools/perf/tests/hwmon_pmu.c
 create mode 100644 tools/perf/util/hwmon_pmu.c
 create mode 100644 tools/perf/util/hwmon_pmu.h

-- 
2.47.0.277.g8800431eea-goog
Re: [PATCH v7 0/7] Hwmon PMUs
Posted by Namhyung Kim 2 weeks, 1 day ago
On Fri, Nov 08, 2024 at 09:49:29AM -0800, Ian Rogers wrote:
> Following the convention of the tool PMU, create a hwmon PMU that
> exposes hwmon data for reading. For example, the following shows
> reading the CPU temperature and 2 fan speeds alongside the uncore
> frequency:
> ```
> $ perf stat -e temp_cpu,fan1,hwmon_thinkpad/fan2/,tool/num_cpus_online/ -M UNCORE_FREQ -I 1000
>      1.001153138              52.00 'C   temp_cpu
>      1.001153138              2,588 rpm  fan1
>      1.001153138              2,482 rpm  hwmon_thinkpad/fan2/
>      1.001153138                  8      tool/num_cpus_online/
>      1.001153138      1,077,101,397      UNC_CLOCK.SOCKET                 #     1.08 UNCORE_FREQ
>      1.001153138      1,012,773,595      duration_time
> ...
> ```
> 
> Additional data on the hwmon events is in perf list:
> ```
> $ perf list
> ...
> hwmon:
> ...
>   temp_core_0 OR temp2
>        [Temperature in unit coretemp named Core 0. crit=100'C,max=100'C crit_alarm=0'C. Unit:
>         hwmon_coretemp]
> ...
> ```
> 
> v7: Try to address feedback from Namhyung wrt size/comprehensibility
>     of the hwmon PMU patch. To better explain the config encoding put
>     the parser into a patch ahead of the PMU patch and add a unit
>     test. This shows how a hwmon filename can be moved back-and-forth
>     with a config value as a single patch (two with the test). The
>     hwmon PMU patch is then putting the wrapping around that for the
>     pmus', parse_event's and evsel reading's benefit.

Thanks for doing this!
Namhyung

>     
>     The alternate approach of not caring about the mapping, name to
>     config value, and using the evsel->name wasn't followed. In the
>     tool PMU it was made so we can go back-and-forth between event
>     names and a type+config, this removed the tool enum value from the
>     evsel as now tool events were more 1st class and evsel should
>     really just be a wrapper on a perf_event_attr. Using the
>     evsel->name wasn't doing that and so the approach of mapping
>     filenames and configs, as better highlighted in this series was
>     pursued.
> 
>     It is expected future PMUs won't be able to cleanly map fixed
>     strings to config values, in those cases tables would be
>     necessary. Making a hwmon PMU do this and then removing it to
>     follow the parsing/mapping done in patch 2 here, would have been a
>     lot of additional work which then would be removed.
> 
> v6: Add string.h #include for issue reported by kernel test robot.
> v5: Fix asan issue in parse_hwmon_filename caught by a TMA metric.
> v4: Drop merged patches 1 to 10. Separate adding the hwmon_pmu from
>     the update to perf_pmu to use it. Try to make source of literal
>     strings clearer via named #defines. Fix a number of GCC warnings.
> v3: Rebase, add Namhyung's acked-by to patches 1 to 10.
> v2: Address Namhyung's review feedback. Rebase dropping 4 patches
>     applied by Arnaldo, fix build breakage reported by Arnaldo.
> 
> Ian Rogers (7):
>   tools api io: Ensure line_len_out is always initialized
>   perf hwmon_pmu: Add hwmon filename parser
>   perf test: Add hwmon filename parser test
>   perf hwmon_pmu: Add a tool PMU exposing events from hwmon in sysfs
>   perf pmu: Add calls enabling the hwmon_pmu
>   perf test: Add hwmon "PMU" test
>   perf docs: Document tool and hwmon events
> 
>  tools/lib/api/io.h                     |   1 +
>  tools/perf/Documentation/perf-list.txt |  15 +
>  tools/perf/tests/Build                 |   1 +
>  tools/perf/tests/builtin-test.c        |   1 +
>  tools/perf/tests/hwmon_pmu.c           | 340 ++++++++++
>  tools/perf/tests/tests.h               |   1 +
>  tools/perf/util/Build                  |   1 +
>  tools/perf/util/evsel.c                |   9 +
>  tools/perf/util/hwmon_pmu.c            | 825 +++++++++++++++++++++++++
>  tools/perf/util/hwmon_pmu.h            | 156 +++++
>  tools/perf/util/pmu.c                  |  20 +
>  tools/perf/util/pmu.h                  |   2 +
>  tools/perf/util/pmus.c                 |   9 +
>  tools/perf/util/pmus.h                 |   3 +
>  14 files changed, 1384 insertions(+)
>  create mode 100644 tools/perf/tests/hwmon_pmu.c
>  create mode 100644 tools/perf/util/hwmon_pmu.c
>  create mode 100644 tools/perf/util/hwmon_pmu.h
> 
> -- 
> 2.47.0.277.g8800431eea-goog
>