scx_metrics: add standalone scheduler metrics exporter - #3704
Open
newell-purdue wants to merge 1 commit into
Open
scx_metrics: add standalone scheduler metrics exporter#3704newell-purdue wants to merge 1 commit into
newell-purdue wants to merge 1 commit into
Conversation
Contributor
Author
|
@kkdwvd to review |
Contributor
|
It might make sense to keep this under tools/, but otherwise looks great. |
Collaborator
Good point, in my opinion, it definitely belongs in /tools. What do you think @htejun? |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
scx_metrics with work conservation as first metric
Trying to fill a need to track key metrics for scx schedulers over long periods of time with very little overhead.
Next steps listed in comment of: (1) handling tasks with affinity, (2) grouping metrics by task groups at cgroup boundary, and (3) including new low-overhead metrics critical to tracking scx scheduler behavior.
Testing
Ran on a 48 core machine where I ran
stress -c 20. Then, I toggled on an scx scheduler that happens to do poorly in terms of schedulingcargo run -p scx_layered -- f:scheds/rust/scx_layered/examples/avgruntime.json, effectively only limited cores to be used due to protected mode.Ran the following for scx_metrics, allowing prometheus to export the counters: