Re: [PATCH v1 03/20] perf jevents: Add smi metric group for Intel models

From: Liang, Kan
Date: Thu Feb 29 2024 - 16:13:31 EST




On 2024-02-28 7:17 p.m., Ian Rogers wrote:
> Allow duplicated metric to be dropped from json files.
>
> Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
> ---
> tools/perf/pmu-events/intel_metrics.py | 18 +++++++++++++++++-
> 1 file changed, 17 insertions(+), 1 deletion(-)
>
> diff --git a/tools/perf/pmu-events/intel_metrics.py b/tools/perf/pmu-events/intel_metrics.py
> index 46866a25b166..20c25d142f24 100755
> --- a/tools/perf/pmu-events/intel_metrics.py
> +++ b/tools/perf/pmu-events/intel_metrics.py
> @@ -2,7 +2,7 @@
> # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
> from metric import (d_ratio, has_event, max, Event, JsonEncodeMetric,
> JsonEncodeMetricGroupDescriptions, LoadEvents, Metric,
> - MetricGroup, Select)
> + MetricGroup, MetricRef, Select)
> import argparse
> import json
> import math
> @@ -62,9 +62,25 @@ def Rapl() -> MetricGroup:
> description="Processor socket power consumption estimates")
>
>
> +def Smi() -> MetricGroup:
> + aperf = Event('msr/aperf/')

There are CPUID enumeration for the aperf and mperf. I believe they
should be always available for a newer bare metal. But they may not be
enumerated in an virtualization env. Should we add a has_event() check
before using it?

Thanks,
Kan

> + cycles = Event('cycles')
> + smi_num = Event('msr/smi/')
> + smi_cycles = Select((aperf - cycles) / aperf, smi_num > 0, 0)
> + return MetricGroup('smi', [
> + Metric('smi_num', 'Number of SMI interrupts.',
> + smi_num, 'SMI#'),
> + # Note, the smi_cycles "Event" is really a reference to the metric.
> + Metric('smi_cycles',
> + 'Percentage of cycles spent in System Management Interrupts.',
> + smi_cycles, '100%', threshold=(MetricRef('smi_cycles') > 0.10))
> + ])
> +
> +
> all_metrics = MetricGroup("", [
> Idle(),
> Rapl(),
> + Smi(),
> ])
>
> if args.metricgroups: