Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

drmemtrace API is_record_kernel() fails for live injected kernel sequences #7375

Closed
derekbruening opened this issue Mar 19, 2025 · 0 comments · Fixed by #7378
Closed

drmemtrace API is_record_kernel() fails for live injected kernel sequences #7375

derekbruening opened this issue Mar 19, 2025 · 0 comments · Fixed by #7378
Assignees

Comments

@derekbruening
Copy link
Contributor

The drmemtrace stream API routine is_record_kernel() is only implemented in the reader_t layer, where it looks for kernel sequence markers. It works on core-sharded-on-disk traces or other traces where the kernel sequences are stored inside the trace files. But when the sequences are dynamically injected, it fails during that live run. This breaks my intended usage in schedule_stats for #7355.

@derekbruening derekbruening self-assigned this Mar 19, 2025
derekbruening added a commit that referenced this issue Mar 19, 2025
Adds state to the scheduler's output stream to track kernel sequences
so that is_record_kernel() works properly for live kernel sequence
insertions.

Augments the kernel unit tests with checks of is_record_kernel() which
fail without the fix.

Fixes #7375
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant