diff options
| author | Ian Rogers <[email protected]> | 2023-04-06 23:52:56 +0000 |
|---|---|---|
| committer | Arnaldo Carvalho de Melo <[email protected]> | 2023-04-07 00:54:03 +0000 |
| commit | 3f980eab56d1c4226bcb91a5f21c9c32a56edb5a (patch) | |
| tree | d52cfc611abffef08c58e2fd541fd07e2b76c111 /tools/perf/util/scripting-engines/trace-event-python.c | |
| parent | perf pmu: Improve name/comments, avoid a memory allocation (diff) | |
| download | kernel-3f980eab56d1c4226bcb91a5f21c9c32a56edb5a.tar.gz kernel-3f980eab56d1c4226bcb91a5f21c9c32a56edb5a.zip | |
perf pmu: Sort and remove duplicates using JSON PMU name
We may have a lot of copies of a particular uncore PMU, such as
uncore_cha_0 to uncore_cha_59 on Intel sapphirerapids.
The JSON events may match each of PMUs and so the events are copied to
it.
In 'perf list' this means we see the same JSON event 60 times as events
on different PMUs don't have duplicates removed.
There are 284 uncore_cha events on sapphirerapids.
Rather than use the PMU's name to sort and remove duplicates, use the
JSON PMU name.
This reduces the 60 copies back down to 1 and has the side effect of
speeding things like the "perf all PMU test" shell test.
Signed-off-by: Ian Rogers <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: James Clark <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ravi Bangoria <[email protected]>
Cc: Rob Herring <[email protected]>
Cc: Sean Christopherson <[email protected]>
Cc: Suzuki Poulouse <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Diffstat (limited to 'tools/perf/util/scripting-engines/trace-event-python.c')
0 files changed, 0 insertions, 0 deletions
