perf test: Hybrid improvements for metric value validation test
authorIan Rogers <irogers@google.com>
Mon, 12 May 2025 18:47:00 +0000 (11:47 -0700)
committerArnaldo Carvalho de Melo <acme@redhat.com>
Tue, 13 May 2025 20:24:42 +0000 (17:24 -0300)
commit3eb5c49f71d0ecb290aba3bb2c9bb8a68b552623
treefcc4e532658d76035b464b1bd36a37105706443e
parent7f84f67418e3a10c4bba721081f5c4a2c22bea8a
perf test: Hybrid improvements for metric value validation test

On my alderlake I currently see for the "perf metrics value validation" test:

```
Total Test Count:  142
Passed Test Count:  139
[
Metric Relationship Error:      The collected value of metric ['tma_fetch_latency', 'tma_fetch_bandwidth', 'tma_frontend_bound']
                        is [31.137028] in workload(s): ['perf bench futex hash -r 2 -s']
                        but expected value range is [tma_frontend_bound, tma_frontend_bound]
                        Relationship rule description: 'Sum of the level 2 children should equal level 1 parent',
Metric Relationship Error:      The collected value of metric ['tma_memory_bound', 'tma_core_bound', 'tma_backend_bound']
                        is [6.564442] in workload(s): ['perf bench futex hash -r 2 -s']
                        but expected value range is [tma_backend_bound, tma_backend_bound]
                        Relationship rule description: 'Sum of the level 2 children should equal level 1 parent',
Metric Relationship Error:      The collected value of metric ['tma_light_operations', 'tma_heavy_operations', 'tma_retiring']
                        is [57.806179] in workload(s): ['perf bench futex hash -r 2 -s']
                        but expected value range is [tma_retiring, tma_retiring]
                        Relationship rule description: 'Sum of the level 2 children should equal level 1 parent']
Metric validation return with erros. Please check metrics reported with errors.
```

I suspect it is due to two metrics for different CPU types being
enabled. Add a -cputype option to avoid this. The test still fails with:

```
Total Test Count:  115
Passed Test Count:  114
[
Wrong Metric Value Error:       The collected value of metric ['tma_l2_hit_latency']
                        is [117.947088] in workload(s): ['perf bench futex hash -r 2 -s']
                        but expected value range is [0, 100]]
Metric validation return with errors. Please check metrics reported with errors.
```

which is a reproducible genuine error and likely requires a metric fix.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Weilin Wang <weilin.wang@intel.com>
Link: https://lore.kernel.org/r/20250512184700.11691-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
tools/perf/tests/shell/lib/perf_metric_validation.py
tools/perf/tests/shell/stat_metrics_values.sh