You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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.
The text was updated successfully, but these errors were encountered:
After #841 lands the layered monitor should be implemented. Some ideas for what the monitor should do are:
scx_bpf_dsq_nr_queued
for DSQs.Other interesting ideas:
scx_bpf_cpuperf_set
.The text was updated successfully, but these errors were encountered: