-
Notifications
You must be signed in to change notification settings - Fork 104
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
bpfland: "failed to run for" on heavy loaded system #1212
Comments
Can you post the trace printed by the scheduler (scx_bpfland stdout)? |
journalctl -o short-iso -u scx.service
|
...
Hm... why the sched class symbol is not resolved here? Can you share your kernel .config? Are you running services that are adjusting niceness / priority dynamically (such as ananicy-cpp or similar)? |
BTW @htejun what do you think about including |
I assume the only thing which cause a conflict: used "conservative" cpu governor with ignore_nice_load=1 .
|
@kmikita can you check if bpfland-next is fixing this? Thanks! |
@arighi I will be testing bpfland-next, but I do not promise results soon, because it needs a longtime heavy load cpu (multithreaded gcc or clang) and the issue does not often happens. |
Sure, no rush and only if you have time. Thanks! |
On heavy loaded system (especially during compilation) bpfland restarts ~ every hour with dmesg log:
linux 6.12.8, scx 1.0.8
The text was updated successfully, but these errors were encountered: