Capture critical PMCs for perf and render flamegraph using these
Open
enhancement
- Dominant language
- Python
- Stars
- 826
- Forks
- 79
- PR merge metrics
- No merged PRs in 30d
Description
Currently we are only capturing default perf for perf based profiling, it doesn't capture any other types of events. This issue is created to request we that we allow ability for dynamic profiler to invoke perf with specific events and build a flamegraph for these to aid in solving and tracing performance issues.
To start with we want:
- cache-misses
- stalled-frontend / backend
Contributor guide
Assessment
This issue has not been assessed yet.