Throttling BE tasks (under CPU stress) could be not enough.

bwplotka commented 9 years ago

Our throttled BE tasks can still interfere with LC PR task because they still can be scheduled for a short while by Linux Scheduler. They could create ctx switching and interfere with PR. (There could be no IPC drop, however interference appears) Mitigations:

We should try to find a way to remove BE tasks when too many of them are on our node (even throttled)
Move BE jobs into Freezer cgroup?

We should make some experiments on how does BE task cntx switches affects LC task on different levels of PR utilization and amount of CPU-stress BE tasks.

skonefal commented 9 years ago

Maybe, this could also be solved @ Mesos level.

Vinod has raised this issue on Community sync on Sept 3rd, 2015 https://docs.google.com/document/d/153CUCj5LOJCFAVpdDZC7COJDwKh9RDjxaTA0S7lzwDA/edit

skonefal commented 8 years ago

Can we consider it done? We have OverloadDetector in Serenity and load-based QoS Controller in Mesos.

If we would like to introduce cpu-pinning, we should do that in separate issue.

d2iq-archive / serenity

Throttling BE tasks (under CPU stress) could be not enough. #89