Conversation
bhavya76
force-pushed
the
bhavya76/otel-performance-skip-zero-pods
branch
from
September 10, 2026 14:00
2df0d81 to
8d85be0
Compare
bhavya76
marked this pull request as ready for review
September 10, 2026 14:09
bhavya76
force-pushed
the
bhavya76/otel-performance-skip-zero-pods
branch
from
September 10, 2026 16:01
8d85be0 to
d0d2c1a
Compare
bhavya76
marked this pull request as draft
September 10, 2026 16:21
bhavya76
force-pushed
the
bhavya76/otel-performance-skip-zero-pods
branch
from
September 10, 2026 17:49
d0d2c1a to
a91a8f1
Compare
bhavya76
force-pushed
the
bhavya76/otel-performance-skip-zero-pods
branch
4 times, most recently
from
September 16, 2026 14:01
9b16f39 to
6e2cccd
Compare
…hresholds Restrict threshold and regression measurements to pods currently running in the amazon-cloudwatch namespace, and skip series with no data in the query window, so metrics reflect only the current agent generation instead of stale/old-ReplicaSet and just-restarted pods that linger after the rollout restart. Calibrate per-class thresholds from clean runs and support per-metric and per-pod error_bound. Scraper CPU is highly variable at low absolute values, so it uses a ceiling ([0%, 2%] of node) rather than a tight two-sided band. Log a per-class calibration summary for future re-tuning.
bhavya76
force-pushed
the
bhavya76/otel-performance-skip-zero-pods
branch
from
September 16, 2026 14:03
6e2cccd to
55c559b
Compare
bhavya76
marked this pull request as ready for review
September 16, 2026 14:23
Paamicky
reviewed
Sep 16, 2026
Paamicky
reviewed
Sep 16, 2026
Paamicky
reviewed
Sep 16, 2026
…om agentNamespace
bhavya76
force-pushed
the
bhavya76/otel-performance-skip-zero-pods
branch
from
September 17, 2026 13:56
2bc969e to
e9efeb2
Compare
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
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.
Issue
eks_daemon:otel_performance_testnever passed. Two causes:Changes
amazon-cloudwatch(k8s API), dropping stale/old-ReplicaSet pods. Fail-soft: on API error, proceed unfiltered.threshold+/- per-metric or per-poderror_bound) and, alternatively, an explicit per-podmaxfor a one-sided ceiling[0, max].maxceiling for both pod classes. Per-pod CPU swings widely run-to-run on this small cluster, so a two-sided floor false-fails on the low side. Bloat is still caught by the ceiling, and drops are caught byTestRegressionCheck; memory stays two-sided.TestRegressionCheck(too noisy cross-commit; still bounded by its ceiling).CALIBRATIONsummary for future re-tuning.License
By submitting this pull request, I confirm that my contribution is made under the terms of the MIT license.