Skip to content

OCPBUGS-85426: improve DCM tests to reduce flakiness in endpoints#31173

Open
jcmoraisjr wants to merge 1 commit into
openshift:mainfrom
jcmoraisjr:OCPBUGS-85426-dcm-test-flakiness
Open

OCPBUGS-85426: improve DCM tests to reduce flakiness in endpoints#31173
jcmoraisjr wants to merge 1 commit into
openshift:mainfrom
jcmoraisjr:OCPBUGS-85426-dcm-test-flakiness

Conversation

@jcmoraisjr
Copy link
Copy Markdown
Member

@jcmoraisjr jcmoraisjr commented May 13, 2026

Addressing a race when patching endpoints resource. This update adds a polling to ensure the endpoints resource was created. Also, dump all endpoints and endpointSlice in the test namespace in case of a test failure, which helps to correlate the current state and what should be expected in the test scenario.

Example of deployments state log:

deployment state: replicas=4 pods=route-scale-in-5b7b4f6b8c-9ncjg/Running/10.128.1.27 // route-scale-in-5b7b4f6b8c-ck45n/Running/10.128.1.28 // route-scale-in-5b7b4f6b8c-srffr/Running/10.128.1.29 // route-scale-in-5b7b4f6b8c-v9hm2/Running/10.128.1.26

Example of Endpoints and EndpointSlice resources listed if the test fails:

Endpoints:
NAME                  ADDRESSES                                        NOT READY ADDRESSES  PORTS
route-scale-in        10.128.1.26,10.128.1.27,10.128.1.28,10.128.1.29                       9376
route-scale-in-khbh5  10.128.1.26                                                           9376

EndpointSlices:
NAME                        SERVICE               ADDRESSES                                        NOT READY ADDRESSES  PORTS
route-scale-in-khbh5-8ncmh  route-scale-in-khbh5  10.128.1.26                                                           9376
route-scale-in-rrhzv        route-scale-in        10.128.1.27,10.128.1.28,10.128.1.29,10.128.1.26                       9376

https://redhat.atlassian.net/browse/OCPBUGS-85426

Summary by CodeRabbit

  • Tests
    • Improved router test observability with richer, tabular endpoint and route diagnostics for easier failure investigation.
    • Added iterative progress and deployment-state logging during scale/churn and steady-state tests to track iterations and pod health.
    • Made endpoint retrieval more robust by retrying transient fetches and logging transient errors to stabilize timing-sensitive scenarios.

@openshift-merge-bot
Copy link
Copy Markdown
Contributor

Pipeline controller notification
This repo is configured to use the pipeline controller. Second-stage tests will be triggered either automatically or after lgtm label is added, depending on the repository configuration. The pipeline controller will automatically detect which contexts are required and will utilize /test Prow commands to trigger the second stage.

For optional jobs, comment /test ? to see a list of all defined jobs. To trigger manually all jobs from second stage use /pipeline required command.

This repository is configured in: automatic mode

@openshift-ci-robot openshift-ci-robot added jira/valid-reference Indicates that this PR references a valid Jira ticket of any type. jira/valid-bug Indicates that a referenced Jira bug is valid for the branch this PR is targeting. labels May 13, 2026
@openshift-ci-robot
Copy link
Copy Markdown

@jcmoraisjr: This pull request references Jira Issue OCPBUGS-85426, which is valid. The bug has been moved to the POST state.

3 validation(s) were run on this bug
  • bug is open, matching expected state (open)
  • bug target version (5.0.0) matches configured target version for branch (5.0.0)
  • bug is in the state ASSIGNED, which is one of the valid states (NEW, ASSIGNED, POST)

Requesting review from QA contact:
/cc @melvinjoseph86

The bug has been updated to refer to the pull request using the external bug tracker.

Details

In response to this:

Addressing some flakes in the DCM e2e tests:

  • Race patching endpoints resource: add a polling to ensure the endpoints resource was created. Also, dump all endpoints and endpointSlice in the test namespace in case of a test failure.
  • Timeout calling the router: increase the timeout, reading all the fast ones from a single const. Also, dumping router logs which should help to correlate failures when calling its service.
  • Router container not found: router pod should be reporting container as running and healthy, but it was not running. Attaching the router log, which should help to explain why router container was not found.

Example of testing deployment state log, added whenever it is scaled:

deployment state: replicas=4 pods=route-scale-in-5b7b4f6b8c-9ncjg/Running/10.128.1.27 // route-scale-in-5b7b4f6b8c-ck45n/Running/10.128.1.28 // route-scale-in-5b7b4f6b8c-srffr/Running/10.128.1.29 // route-scale-in-5b7b4f6b8c-v9hm2/Running/10.128.1.26

Example of Endpoints and EndpointSlice resources listed if the test fails:

Endpoints:
NAME                  ADDRESSES                                        NOT READY ADDRESSES  PORTS
route-scale-in        10.128.1.26,10.128.1.27,10.128.1.28,10.128.1.29                       9376
route-scale-in-khbh5  10.128.1.26                                                           9376

EndpointSlices:
NAME                        SERVICE               ADDRESSES                                        NOT READY ADDRESSES  PORTS
route-scale-in-khbh5-8ncmh  route-scale-in-khbh5  10.128.1.26                                                           9376
route-scale-in-rrhzv        route-scale-in        10.128.1.27,10.128.1.28,10.128.1.29,10.128.1.26                       9376

https://redhat.atlassian.net/browse/OCPBUGS-85426

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 openshift-eng/jira-lifecycle-plugin repository.

@openshift-ci openshift-ci Bot requested a review from melvinjoseph86 May 13, 2026 19:52
@coderabbitai
Copy link
Copy Markdown

coderabbitai Bot commented May 13, 2026

Walkthrough

This PR improves router e2e diagnostics and stability: it adds an admin Route client and extended failure output, tabular Endpoints/EndpointSlice logging, deployment-state fetch/print helpers used during churn/scale operations, and retries Endpoints retrieval for detached services.

Changes

Router Test Diagnostics and Stability

Layer / File(s) Summary
Failure handler & route client initialization
test/extended/router/config_manager_ingress.go
Initializes an admin routeClient and extends the AfterEach failure handler to list OpenShift Routes and emit outputIngress alongside existing Endpoints and EndpointSlices output.
Endpoints & EndpointSlice output helpers
test/extended/router/stress.go
Adds strconv and discoveryv1 imports and introduces outputEndpoints() and outputEndpointSlice() which render Kubernetes Endpoints and EndpointSlice objects as formatted tables and log them via e2e.Logf.
Deployment state fetch and print helpers
test/extended/router/config_manager_ingress.go
Adds printDeploymentState(ctx) to best-effort fetch and log exposed deployment pods (name, phase, pod IPs), introduces fetchPods(ctx), and refactors fetchServiceReplicas(ctx) to reuse fetchPods.
Integrate deployment-state logging into flows
test/extended/router/config_manager_ingress.go
Integrates printDeploymentState calls into createDeploymentStack (captures exposeDeployment results and logs), scaleDeployment (logs before return), and emits per-iteration deployment state during balance/churn and steady PID loops.
Detached service endpoints polling
test/extended/router/config_manager_ingress.go
Stabilizes detached service creation by replacing a single Endpoints Get with a retrying polling loop that logs transient fetch errors until Endpoints are retrievable.
Comments and small fixes
test/extended/router/config_manager_ingress.go
Adds clarifying comment for execPodRef, adjusts router/service namespace wording, fixes "subnets" → "subsets" typo, and documents SNO safety for the created deployment.

🎯 3 (Moderate) | ⏱️ ~25 minutes

🚥 Pre-merge checks | ✅ 9 | ❌ 3

❌ Failed checks (3 warnings)

Check name Status Explanation Resolution
Docstring Coverage ⚠️ Warning Docstring coverage is 28.57% which is insufficient. The required threshold is 80.00%. Write docstrings for the functions missing them to satisfy the coverage threshold.
Test Structure And Quality ⚠️ Warning 39 assertions use Expect(err).NotTo(o.HaveOccurred()) without custom failure messages; per check requirement, assertions should include meaningful messages to diagnose failures. Add custom failure messages to all assertion statements, e.g., Expect(err).NotTo(o.HaveOccurred(), "failed to create deployment") to aid diagnosis when tests fail.
Microshift Test Compatibility ⚠️ Warning config_manager_ingress.go uses operatorv1.IngressController from operator.openshift.io, not available on MicroShift. Test lacks [apigroup:operator.openshift.io] protection. Add [apigroup:operator.openshift.io] to test's g.Describe tag or add exutil.IsMicroShiftCluster() check with g.Skip().
✅ Passed checks (9 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title accurately summarizes the main objective of the pull request: improving DCM (Dynamic Configuration Manager) router tests to reduce flakiness related to endpoints handling.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
Stable And Deterministic Test Names ✅ Passed All test declarations use static, descriptive strings with no dynamic content (pod names, timestamps, IDs, node names, namespaces, or IPs). Test titles clearly indicate validation purpose.
Single Node Openshift (Sno) Test Compatibility ✅ Passed New tests have no multi-node assumptions: no anti-affinity, topology spread, or node constraints. Deployments explicitly documented as SNO-safe. All replicas can coexist on single node as intended.
Topology-Aware Scheduling Compatibility ✅ Passed Only test files were modified; no deployment manifests or operator code. No scheduling constraints added. Code documents SNO compatibility.
Ote Binary Stdout Contract ✅ Passed All logging uses e2e.Logf() from Ginkgo framework, not process stdout. All calls from test-level code (AfterEach/It), not process-level. No direct stdout writes found.
Ipv6 And Disconnected Network Test Compatibility ✅ Passed Tests properly handle IPv6: loopback detection uses utilnet.IsIPv6String() to select ::1 for IPv6 clusters. The 10.0.0.1 is dummy test data, not a network requirement. No external connectivity needed.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@openshift-ci
Copy link
Copy Markdown
Contributor

openshift-ci Bot commented May 13, 2026

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: jcmoraisjr

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Details Needs approval from an approver in each of these files:

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@openshift-ci openshift-ci Bot added the approved Indicates a PR has been approved by an approver from all required OWNERS files. label May 13, 2026
@openshift-ci openshift-ci Bot requested review from Thealisyed and gcs278 May 13, 2026 19:53
@openshift-ci-robot
Copy link
Copy Markdown

@jcmoraisjr: This pull request references Jira Issue OCPBUGS-85426, which is valid.

3 validation(s) were run on this bug
  • bug is open, matching expected state (open)
  • bug target version (5.0.0) matches configured target version for branch (5.0.0)
  • bug is in the state POST, which is one of the valid states (NEW, ASSIGNED, POST)

Requesting review from QA contact:
/cc @melvinjoseph86

Details

In response to this:

Addressing some flakes in the DCM e2e tests:

  • Race patching endpoints resource: add a polling to ensure the endpoints resource was created. Also, dump all endpoints and endpointSlice in the test namespace in case of a test failure.
  • Timeout calling the router: increase the timeout, reading all the fast ones from a single const. Also, dumping router logs which should help to correlate failures when calling its service.
  • Router container not found: router pod should be reporting container as running and healthy, but it was not running. Attaching the router log, which should help to explain why router container was not found.

Example of testing deployment state log, added whenever it is scaled:

deployment state: replicas=4 pods=route-scale-in-5b7b4f6b8c-9ncjg/Running/10.128.1.27 // route-scale-in-5b7b4f6b8c-ck45n/Running/10.128.1.28 // route-scale-in-5b7b4f6b8c-srffr/Running/10.128.1.29 // route-scale-in-5b7b4f6b8c-v9hm2/Running/10.128.1.26

Example of Endpoints and EndpointSlice resources listed if the test fails:

Endpoints:
NAME                  ADDRESSES                                        NOT READY ADDRESSES  PORTS
route-scale-in        10.128.1.26,10.128.1.27,10.128.1.28,10.128.1.29                       9376
route-scale-in-khbh5  10.128.1.26                                                           9376

EndpointSlices:
NAME                        SERVICE               ADDRESSES                                        NOT READY ADDRESSES  PORTS
route-scale-in-khbh5-8ncmh  route-scale-in-khbh5  10.128.1.26                                                           9376
route-scale-in-rrhzv        route-scale-in        10.128.1.27,10.128.1.28,10.128.1.29,10.128.1.26                       9376

https://redhat.atlassian.net/browse/OCPBUGS-85426

Summary by CodeRabbit

  • Tests
  • Enhanced router test observability with improved logging and debug output for network endpoints and configuration details.
  • Stabilized timing-sensitive test operations through configurable timeout handling.
  • Expanded test failure diagnostics to capture detailed state information for troubleshooting.

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 openshift-eng/jira-lifecycle-plugin repository.

@openshift-merge-bot openshift-merge-bot Bot added the ready-for-human-review Indicates a PR has been reviewed by automated tools and is ready for human review label May 13, 2026
@openshift-merge-bot
Copy link
Copy Markdown
Contributor

Scheduling required tests:
/test e2e-aws-csi
/test e2e-aws-ovn-fips
/test e2e-aws-ovn-microshift
/test e2e-aws-ovn-microshift-serial
/test e2e-aws-ovn-serial-1of2
/test e2e-aws-ovn-serial-2of2
/test e2e-gcp-csi
/test e2e-gcp-ovn
/test e2e-gcp-ovn-upgrade
/test e2e-metal-ipi-ovn-ipv6
/test e2e-vsphere-ovn
/test e2e-vsphere-ovn-upi

@jcmoraisjr jcmoraisjr force-pushed the OCPBUGS-85426-dcm-test-flakiness branch from 3dcf0fe to f272628 Compare May 18, 2026 13:22
@jcmoraisjr jcmoraisjr changed the title OCPBUGS-85426: improve DCM tests to reduce flakiness OCPBUGS-85426: improve DCM tests to reduce flakiness in endpoints May 18, 2026
@openshift-merge-bot
Copy link
Copy Markdown
Contributor

Scheduling required tests:
/test e2e-aws-csi
/test e2e-aws-ovn-fips
/test e2e-aws-ovn-microshift
/test e2e-aws-ovn-microshift-serial
/test e2e-aws-ovn-serial-1of2
/test e2e-aws-ovn-serial-2of2
/test e2e-gcp-csi
/test e2e-gcp-ovn
/test e2e-gcp-ovn-upgrade
/test e2e-metal-ipi-ovn-ipv6
/test e2e-vsphere-ovn
/test e2e-vsphere-ovn-upi

@melvinjoseph86
Copy link
Copy Markdown
Contributor

/jira-refresh

@melvinjoseph86
Copy link
Copy Markdown
Contributor

cc @rhamini3

@melvinjoseph86
Copy link
Copy Markdown
Contributor

/jira refresh

@openshift-ci-robot
Copy link
Copy Markdown

@melvinjoseph86: This pull request references Jira Issue OCPBUGS-85426, which is valid.

3 validation(s) were run on this bug
  • bug is open, matching expected state (open)
  • bug target version (5.0.0) matches configured target version for branch (5.0.0)
  • bug is in the state POST, which is one of the valid states (NEW, ASSIGNED, POST)

No GitHub users were found matching the public email listed for the QA contact in Jira (iamin@redhat.com), skipping review request.

The bug has been updated to refer to the pull request using the external bug tracker.

Details

In response to this:

/jira refresh

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 openshift-eng/jira-lifecycle-plugin repository.

@jcmoraisjr jcmoraisjr force-pushed the OCPBUGS-85426-dcm-test-flakiness branch from f272628 to 1a4ff75 Compare May 20, 2026 12:35
Copy link
Copy Markdown

@coderabbitai coderabbitai Bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@test/extended/router/config_manager_ingress.go`:
- Around line 71-83: The list calls swallow errors; change each call to capture
the error (routes, err :=
routeClient.RouteV1().Routes(oc.Namespace()).List(...); endpoints, err :=
kubeClient.CoreV1().Endpoints(oc.Namespace()).List(...); epsList, err :=
kubeClient.DiscoveryV1().EndpointSlices(oc.Namespace()).List(...)) and if err !=
nil log the error with context (e.g. include namespace and operation) before
attempting to output items; update the branches that currently call
outputIngress, outputEndpoints, outputEndpointSlice to still run when results
exist but ensure the err is logged (using the test/logger available in the file,
e.g. framework.Logf/t.Logf or the existing logger) so failed specs include
actionable diagnostics.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: Repository YAML (base), Central YAML (inherited)

Review profile: CHILL

Plan: Enterprise

Run ID: 30a7ec20-63d2-4427-8031-a2cc9653b227

📥 Commits

Reviewing files that changed from the base of the PR and between f272628 and 1a4ff75.

📒 Files selected for processing (2)
  • test/extended/router/config_manager_ingress.go
  • test/extended/router/stress.go

Comment thread test/extended/router/config_manager_ingress.go
@jcmoraisjr
Copy link
Copy Markdown
Member Author

/test verify

@bentito
Copy link
Copy Markdown
Contributor

bentito commented May 20, 2026

/assign @bentito

@openshift-merge-bot
Copy link
Copy Markdown
Contributor

Scheduling required tests:
/test e2e-aws-csi
/test e2e-aws-ovn-fips
/test e2e-aws-ovn-microshift
/test e2e-aws-ovn-microshift-serial
/test e2e-aws-ovn-serial-1of2
/test e2e-aws-ovn-serial-2of2
/test e2e-gcp-csi
/test e2e-gcp-ovn
/test e2e-gcp-ovn-upgrade
/test e2e-metal-ipi-ovn-ipv6
/test e2e-vsphere-ovn
/test e2e-vsphere-ovn-upi

Addressing a race when patching endpoints resource. This update adds a
polling to ensure the endpoints resource was created. Also, dump all
endpoints and endpointSlice in the test namespace in case of a test
failure, which helps to correlate the current state and what should be
expected in the test scenario.

Example of deployments state log:

```
deployment state: replicas=4 pods=route-scale-in-5b7b4f6b8c-9ncjg/Running/10.128.1.27 // route-scale-in-5b7b4f6b8c-ck45n/Running/10.128.1.28 // route-scale-in-5b7b4f6b8c-srffr/Running/10.128.1.29 // route-scale-in-5b7b4f6b8c-v9hm2/Running/10.128.1.26
```

Example of Endpoints and EndpointSlice resources listed if the test
fails:

```
Endpoints:
NAME                  ADDRESSES                                        NOT READY ADDRESSES  PORTS
route-scale-in        10.128.1.26,10.128.1.27,10.128.1.28,10.128.1.29                       9376
route-scale-in-khbh5  10.128.1.26                                                           9376

EndpointSlices:
NAME                        SERVICE               ADDRESSES                                        NOT READY ADDRESSES  PORTS
route-scale-in-khbh5-8ncmh  route-scale-in-khbh5  10.128.1.26                                                           9376
route-scale-in-rrhzv        route-scale-in        10.128.1.27,10.128.1.28,10.128.1.29,10.128.1.26                       9376
```

https://redhat.atlassian.net/browse/OCPBUGS-85426
@jcmoraisjr jcmoraisjr force-pushed the OCPBUGS-85426-dcm-test-flakiness branch from 1a4ff75 to 7ae081b Compare May 21, 2026 11:59
Copy link
Copy Markdown

@coderabbitai coderabbitai Bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🧹 Nitpick comments (2)
test/extended/router/stress.go (2)

699-699: 💤 Low value

Nit: simplify boolean comparison.

*ready == true can be written as just *ready. go vet/linters typically flag this as S1002.

Proposed change
-			if ready := ep.Conditions.Ready; ready == nil || *ready == true {
+			if ready := ep.Conditions.Ready; ready == nil || *ready {
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@test/extended/router/stress.go` at line 699, The boolean comparison is overly
verbose: in the condition that checks ep.Conditions.Ready, replace the explicit
comparison "*ready == true" with the simpler dereference "*ready" so the if
becomes "if ready := ep.Conditions.Ready; ready == nil || *ready { ... }";
update the conditional around ep.Conditions.Ready accordingly to satisfy linters
like S1002.

667-679: 💤 Low value

Optional: hoist resumeAddrs out of the subset loop and simplify boolean check.

resumeAddrs is redefined on every Subsets iteration; it can be a package-level helper (or defined once above the loop). Also consider renaming to summarizeAddrs for clarity — "resume" reads as the Portuguese/Spanish cognate of "summarize" rather than the English meaning. Purely stylistic; no behavior impact.

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@test/extended/router/stress.go` around lines 667 - 679, The inline function
resumeAddrs defined inside the Subsets iteration should be hoisted so it’s
defined once (either as a package-level helper or above the loop) and renamed to
summarizeAddrs for clarity; update calls inside the loop to use
summarizeAddrs(addrs). While moving it, simplify the logic that picks the
address by returning the first non-empty of addr.IP or addr.Hostname (instead of
nested if/else) and keep the join behavior the same so the behavior of functions
referencing Subsets remains unchanged.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Nitpick comments:
In `@test/extended/router/stress.go`:
- Line 699: The boolean comparison is overly verbose: in the condition that
checks ep.Conditions.Ready, replace the explicit comparison "*ready == true"
with the simpler dereference "*ready" so the if becomes "if ready :=
ep.Conditions.Ready; ready == nil || *ready { ... }"; update the conditional
around ep.Conditions.Ready accordingly to satisfy linters like S1002.
- Around line 667-679: The inline function resumeAddrs defined inside the
Subsets iteration should be hoisted so it’s defined once (either as a
package-level helper or above the loop) and renamed to summarizeAddrs for
clarity; update calls inside the loop to use summarizeAddrs(addrs). While moving
it, simplify the logic that picks the address by returning the first non-empty
of addr.IP or addr.Hostname (instead of nested if/else) and keep the join
behavior the same so the behavior of functions referencing Subsets remains
unchanged.

ℹ️ Review info
⚙️ Run configuration

Configuration used: Repository YAML (base), Central YAML (inherited)

Review profile: CHILL

Plan: Enterprise

Run ID: 108561fd-89f8-4529-b2a1-2862fa2cac51

📥 Commits

Reviewing files that changed from the base of the PR and between 1a4ff75 and 7ae081b.

📒 Files selected for processing (2)
  • test/extended/router/config_manager_ingress.go
  • test/extended/router/stress.go

@openshift-merge-bot
Copy link
Copy Markdown
Contributor

Scheduling required tests:
/test e2e-aws-csi
/test e2e-aws-ovn-fips
/test e2e-aws-ovn-microshift
/test e2e-aws-ovn-microshift-serial
/test e2e-aws-ovn-serial-1of2
/test e2e-aws-ovn-serial-2of2
/test e2e-gcp-csi
/test e2e-gcp-ovn
/test e2e-gcp-ovn-upgrade
/test e2e-metal-ipi-ovn-ipv6
/test e2e-vsphere-ovn
/test e2e-vsphere-ovn-upi

@jcmoraisjr
Copy link
Copy Markdown
Member Author

/test e2e-gcp-ovn

@openshift-ci
Copy link
Copy Markdown
Contributor

openshift-ci Bot commented May 21, 2026

@jcmoraisjr: all tests passed!

Full PR test history. Your PR dashboard.

Details

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. I understand the commands that are listed here.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

approved Indicates a PR has been approved by an approver from all required OWNERS files. jira/valid-bug Indicates that a referenced Jira bug is valid for the branch this PR is targeting. jira/valid-reference Indicates that this PR references a valid Jira ticket of any type. ready-for-human-review Indicates a PR has been reviewed by automated tools and is ready for human review

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants