disturbing behavior of `perf stat` and HLE events
Open
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 10.7k
- Forks
- 662
- Avg merge
- 2d 3h
- Merged PRs (30d)
- 2
Description
chdir to a Linux kernel checkout and then do:
perf stat -e el-start ls
...
Performance counter stats for 'ls':
0 el-start
perf stat -e el-start -e el-abort ls
...
Performance counter stats for 'ls':
0 el-start
1 el-abort
perf stat -e el-abort -e el-start ls
...
Performance counter stats for 'ls':
0 el-abort
1 el-start
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the two perf stat commands from the issue in a Linux kernel checkout and compare the results when the HLE events are reversed. Trace the handling of el-start and el-abort event selection, then define completion as consistent, order-independent counts with a regression check for both command forms.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, linux
- Domain
- devtools, operating-systems, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100