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

scx_layered: Implement monitor #842

Open
hodgesds opened this issue Oct 23, 2024 · 0 comments
Open

scx_layered: Implement monitor #842

hodgesds opened this issue Oct 23, 2024 · 0 comments
Labels
bpf good first issue Good for newcomers help wanted Extra attention is needed scx_layered

Comments

@hodgesds
Copy link
Contributor

hodgesds commented Oct 23, 2024

After #841 lands the layered monitor should be implemented. Some ideas for what the monitor should do are:

  • Implement a global stat that indicates if the scheduler is in a degraded state. Figure out a good hueristic for what a degraded state is. Ideally, the state would still be collected before/if the scheduler gets kicked to help know if the scheduler is in a bad state.
  • Add a trace log if DSQs are backlogged by checking the results of scx_bpf_dsq_nr_queued for DSQs.

Other interesting ideas:

  • If a layer is backlogged apply a temporary performance boost using scx_bpf_cpuperf_set.
@hodgesds hodgesds added good first issue Good for newcomers help wanted Extra attention is needed bpf scx_layered labels Oct 23, 2024
@hodgesds hodgesds changed the title scx_layered: Implement watchdog scx_layered: Implement monitor Oct 24, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bpf good first issue Good for newcomers help wanted Extra attention is needed scx_layered
Projects
None yet
Development

No branches or pull requests

1 participant