conformance: modify warmup from weighted two-pools test#2316
conformance: modify warmup from weighted two-pools test#2316k8s-ci-robot merged 2 commits intokubernetes-sigs:mainfrom
Conversation
✅ Deploy Preview for gateway-api-inference-extension ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
/retest |
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: danehans, howardjohn The full list of commands accepted by this bot can be found here. The pull request process is described here DetailsNeeds approval from an approver in each of these files:
Approvers can indicate their approval by writing |
…s test Drop the per-pod warmup loop in GatewayWeightedAcrossTwoInferencePools. The warmup used MakeRequestAndExpectEventuallyConsistentResponse (3 consecutive successes), which made requests targeting secondary endpoints probabilistic under 70/30 backendRef weighting and caused flakes. Signed-off-by: Daneyon Hansen <daneyon.hansen@solo.io>
|
/lgtm |
|
/cherrypick release-1.3 |
|
@kfswain: #2316 failed to apply on top of branch "release-1.3": DetailsIn response to this:
Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. |
* conformance: remove warmup from GatewayWeightedAcrossTwoInferencePools test Drop the per-pod warmup loop in GatewayWeightedAcrossTwoInferencePools. The warmup used MakeRequestAndExpectEventuallyConsistentResponse (3 consecutive successes), which made requests targeting secondary endpoints probabilistic under 70/30 backendRef weighting and caused flakes. Signed-off-by: Daneyon Hansen <daneyon.hansen@solo.io> * conformance: add single deterministic warmup for weighted pools --------- Signed-off-by: Daneyon Hansen <daneyon.hansen@solo.io>
…igs#2316) * conformance: remove warmup from GatewayWeightedAcrossTwoInferencePools test Drop the per-pod warmup loop in GatewayWeightedAcrossTwoInferencePools. The warmup used MakeRequestAndExpectEventuallyConsistentResponse (3 consecutive successes), which made requests targeting secondary endpoints probabilistic under 70/30 backendRef weighting and caused flakes. Signed-off-by: Daneyon Hansen <daneyon.hansen@solo.io> * conformance: add single deterministic warmup for weighted pools --------- Signed-off-by: Daneyon Hansen <daneyon.hansen@solo.io>
What type of PR is this?
/kind flake
What this PR does / why we need it:
Modify the per-pod warmup loop in GatewayWeightedAcrossTwoInferencePools. The warmup used MakeRequestAndExpectEventuallyConsistentResponse (3 consecutive successes), which made requests targeting secondary endpoints probabilistic under 70/30 backendRef weighting and caused flakes.
Which issue(s) this PR fixes:
Fixes #2315
Does this PR introduce a user-facing change?: