[PATCH v6 0/1] sched/fair: Fix low cpu usage with high throttling by removing expiration of cpu-local slices

From: Dave Chiluk
Date: Tue Jul 23 2019 - 12:45:11 EST


Changelog v6
- Added back missing call to lsub_positive(&cfs_b->runtime, runtime);
- Added Reviewed-by: Ben Segall <bsegall@xxxxxxxxxx>
- Fix some grammar in the Documentation, and change some wording.
- Updated documentation due to the .rst change

Changelog v5
- Based on this comment from Ben Segall's comment on v4
> If the cost of taking this global lock across all cpus without a
> ratelimit was somehow not a problem, I'd much prefer to just set
> min_cfs_rq_runtime = 0. (Assuming it is, I definitely prefer the "lie
> and sorta have 2x period 2x runtime" solution of removing expiration)
I'm resubmitting my v3 patchset, with the requested changes.
- Updated Commit log given review comments
- Update sched-bwc.txt give my new understanding of the slack timer.

Changelog v4
- Rewrote patchset around the concept of returning all of runtime_remaining
when cfs_b nears the end of available quota.

Changelog v3
- Reworked documentation to better describe behavior of slice expiration per
feedback from Peter Oskolkov

Changelog v2
- Fixed some checkpatch errors in the commit message.