python: judge the CPU throttle by duty cycle instead of wall-clock ratio - #226
Merged
Conversation
The throttle stops the child for half of every 100ms period, and it does so precisely: wall time is 2.00x the child's CPU time in every measured run. The wall-clock ratio still drifts to 3x on hosts with aggressive frequency scaling (amd-pstate powersave here), because a core that idles every 50ms clocks down and the awake half needs up to 30% more CPU time for the same work. Measuring child CPU time against wall time isolates the duty cycle the throttle actually promises; it sits at 0.50 with a spread under 0.01 on an idle host and is unchanged with four busy cores. Signed-off-by: Cong Wang <cwang@multikernel.io>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The throttle test measured wall-clock slowdown, which drifts to 3x on hosts with aggressive frequency scaling even though the SIGSTOP/SIGCONT cycle is exact (wall = 2.00x child CPU time in every run). Measure the duty cycle (child CPU time over wall time) instead, which is the quantity the throttle loop actually controls. Reads 0.50 with a spread under 0.01 on an idle host.