[PATCH 0/5] Support metric group constraint

From: kan . liang
Date: Wed Feb 19 2020 - 14:10:48 EST

From: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>

Some metric groups, e.g. Page_Walks_Utilization, will never count when
NMI watchdog is enabled.

$echo 1 > /proc/sys/kernel/nmi_watchdog
$perf stat -M Page_Walks_Utilization

Performance counter stats for 'system wide':

<not counted> itlb_misses.walk_pending (0.00%)
<not counted> dtlb_load_misses.walk_pending (0.00%)
<not counted> dtlb_store_misses.walk_pending (0.00%)
<not counted> ept.walk_pending (0.00%)
<not counted> cycles (0.00%)

2.343460588 seconds time elapsed

Some events weren't counted. Try disabling the NMI watchdog:
echo 0 > /proc/sys/kernel/nmi_watchdog
perf stat ...
echo 1 > /proc/sys/kernel/nmi_watchdog
The events in group usually have to be from the same PMU. Try
reorganizing the group.

A metric group is a weak group, which relies on group validation
code in the kernel to determine whether to be opened as a group or
a non-group. However, group validation code may return false-positives,
especially when NMI watchdog is enabled. (The metric group is allowed
as a group but will never be scheduled.)

The attempt to fix the group validation code has been rejected.
Because we cannot accurately predict whether the group can be scheduled
as a group, only by checking current status.

This patch set provides another solution to mitigate the issue.
Add "MetricConstraint" in event list, which provides a hint for perf tool,
e.g. "MetricConstraint": "NO_NMI_WATCHDOG". Perf tool can change the
metric group to non-group (standalone metrics) if NMI watchdog is enabled.

After applying the patch,

$echo 1 > /proc/sys/kernel/nmi_watchdog
$perf stat -M Page_Walks_Utilization
Splitting metric group Page_Walks_Utilization into standalone metrics.
Try disabling the NMI watchdog to comply NO_NMI_WATCHDOG metric constraint:
echo 0 > /proc/sys/kernel/nmi_watchdog
perf stat ...
echo 1 > /proc/sys/kernel/nmi_watchdog

Performance counter stats for 'system wide':

18,253,454 itlb_misses.walk_pending # 0.0
Page_Walks_Utilization (50.55%)
78,051,525 dtlb_load_misses.walk_pending (50.55%)
29,213,063 dtlb_store_misses.walk_pending (50.55%)
0 ept.walk_pending (50.55%)
2,542,132,364 cycles (49.92%)

1.037095993 seconds time elapsed

Kan Liang (5):
perf jevents: Support metric constraint
perf metricgroup: Factor out metricgroup__add_metric_weak_group()
perf util: Factor out sysctl__nmi_watchdog_enabled()
perf metricgroup: Support metric constraint
perf vendor events: Add NO_NMI_WATCHDOG metric constraint

.../arch/x86/cascadelakex/clx-metrics.json | 3 +-
.../pmu-events/arch/x86/skylake/skl-metrics.json | 3 +-
.../pmu-events/arch/x86/skylakex/skx-metrics.json | 3 +-
tools/perf/pmu-events/jevents.c | 19 +++--
tools/perf/pmu-events/jevents.h | 2 +-
tools/perf/pmu-events/pmu-events.h | 1 +
tools/perf/util/metricgroup.c | 97 ++++++++++++++++------
tools/perf/util/stat-display.c | 6 +-
tools/perf/util/util.c | 18 ++++
tools/perf/util/util.h | 2 +
10 files changed, 116 insertions(+), 38 deletions(-)