From 3eb5c49f71d0ecb290aba3bb2c9bb8a68b552623 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 12 May 2025 11:47:00 -0700 Subject: [PATCH] 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 Tested-by: Thomas Falcon Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Weilin Wang Link: https://lore.kernel.org/r/20250512184700.11691-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../tests/shell/lib/perf_metric_validation.py | 12 +++++++++--- tools/perf/tests/shell/stat_metrics_values.sh | 17 +++++++++++------ 2 files changed, 20 insertions(+), 9 deletions(-) diff --git a/tools/perf/tests/shell/lib/perf_metric_validation.py b/tools/perf/tests/shell/lib/perf_metric_validation.py index 0b94216c9c46..dea8ef1977bf 100644 --- a/tools/perf/tests/shell/lib/perf_metric_validation.py +++ b/tools/perf/tests/shell/lib/perf_metric_validation.py @@ -35,7 +35,8 @@ class TestError: class Validator: - def __init__(self, rulefname, reportfname='', t=5, debug=False, datafname='', fullrulefname='', workload='true', metrics=''): + def __init__(self, rulefname, reportfname='', t=5, debug=False, datafname='', fullrulefname='', + workload='true', metrics='', cputype='cpu'): self.rulefname = rulefname self.reportfname = reportfname self.rules = None @@ -43,6 +44,7 @@ class Validator: self.metrics = self.__set_metrics(metrics) self.skiplist = set() self.tolerance = t + self.cputype = cputype self.workloads = [x for x in workload.split(",") if x] self.wlidx = 0 # idx of current workloads @@ -377,7 +379,7 @@ class Validator: def _run_perf(self, metric, workload: str): tool = 'perf' - command = [tool, 'stat', '-j', '-M', f"{metric}", "-a"] + command = [tool, 'stat', '--cputype', self.cputype, '-j', '-M', f"{metric}", "-a"] wl = workload.split() command.extend(wl) print(" ".join(command)) @@ -443,6 +445,8 @@ class Validator: if 'MetricName' not in m: print("Warning: no metric name") continue + if 'Unit' in m and m['Unit'] != self.cputype: + continue name = m['MetricName'].lower() self.metrics.add(name) if 'ScaleUnit' in m and (m['ScaleUnit'] == '1%' or m['ScaleUnit'] == '100%'): @@ -578,6 +582,8 @@ def main() -> None: parser.add_argument( "-wl", help="Workload to run while data collection", default="true") parser.add_argument("-m", help="Metric list to validate", default="") + parser.add_argument("-cputype", help="Only test metrics for the given CPU/PMU type", + default="cpu") args = parser.parse_args() outpath = Path(args.output_dir) reportf = Path.joinpath(outpath, 'perf_report.json') @@ -586,7 +592,7 @@ def main() -> None: validator = Validator(args.rule, reportf, debug=args.debug, datafname=datafile, fullrulefname=fullrule, workload=args.wl, - metrics=args.m) + metrics=args.m, cputype=args.cputype) ret = validator.test() return ret diff --git a/tools/perf/tests/shell/stat_metrics_values.sh b/tools/perf/tests/shell/stat_metrics_values.sh index 279f19c5919a..30566f0b5427 100755 --- a/tools/perf/tests/shell/stat_metrics_values.sh +++ b/tools/perf/tests/shell/stat_metrics_values.sh @@ -16,11 +16,16 @@ workload="perf bench futex hash -r 2 -s" # Add -debug, save data file and full rule file echo "Launch python validation script $pythonvalidator" echo "Output will be stored in: $tmpdir" -$PYTHON $pythonvalidator -rule $rulefile -output_dir $tmpdir -wl "${workload}" -ret=$? -rm -rf $tmpdir -if [ $ret -ne 0 ]; then - echo "Metric validation return with erros. Please check metrics reported with errors." -fi +for cputype in /sys/bus/event_source/devices/cpu_*; do + cputype=$(basename "$cputype") + echo "Testing metrics for: $cputype" + $PYTHON $pythonvalidator -rule $rulefile -output_dir $tmpdir -wl "${workload}" \ + -cputype "${cputype}" + ret=$? + rm -rf $tmpdir + if [ $ret -ne 0 ]; then + echo "Metric validation return with errors. Please check metrics reported with errors." + fi +done exit $ret -- 2.25.1