testing nightly and build#81373
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Repository YAML (base), Central YAML (inherited) Review profile: CHILL Plan: Enterprise Run ID: ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (1)
👮 Files not reviewed due to content moderation or server errors (1)
🚥 Pre-merge checks | ❌ 10❌ Failed checks (10 inconclusive)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: miyadav The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:
Approvers can indicate their approval by writing |
There was a problem hiding this comment.
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
`@ci-operator/config/openshift/cluster-version-operator/openshift-cluster-version-operator-release-5.0__periodics.yaml`:
- Around line 31-34: The periodic job is pinned to an ephemeral ci-ln-* release
image override, which will disappear after garbage collection and make the
workflow stale. Update the periodic config for the
cucushift-installer-rehearse-gcp-ipi-compact job to use a stable release image
reference, or remove CUSTOM_OPENSHIFT_INSTALL_RELEASE_IMAGE_OVERRIDE entirely if
it is only intended for a one-time comparison, so the recurring job does not
depend on a transient payload.
🪄 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: fbf673f1-bb66-4c1c-bde7-ea56578cb8f9
⛔ Files ignored due to path filters (3)
ci-operator/jobs/openshift/cluster-version-operator/openshift-cluster-version-operator-release-5.0-periodics.yamlis excluded by!ci-operator/jobs/**ci-operator/jobs/openshift/cluster-version-operator/openshift-cluster-version-operator-release-5.0-postsubmits.yamlis excluded by!ci-operator/jobs/**ci-operator/jobs/openshift/cluster-version-operator/openshift-cluster-version-operator-release-5.0-presubmits.yamlis excluded by!ci-operator/jobs/**
📒 Files selected for processing (1)
ci-operator/config/openshift/cluster-version-operator/openshift-cluster-version-operator-release-5.0__periodics.yaml
| cluster_profile: gcp-qe | ||
| env: | ||
| CUSTOM_OPENSHIFT_INSTALL_RELEASE_IMAGE_OVERRIDE: registry.build10.ci.openshift.org/ci-ln-3qfdxwk/release:latest | ||
| workflow: cucushift-installer-rehearse-gcp-ipi-compact |
There was a problem hiding this comment.
🩺 Stability & Availability | 🟠 Major | ⚡ Quick win
🧩 Analysis chain
🌐 Web query:
How long are OpenShift CI build farm ci-ln- ephemeral namespaces retained before garbage collection?
💡 Result:
In the OpenShift CI build farm, ephemeral namespaces—which typically follow the naming pattern ci-op-* (as referenced in official documentation [1][2])—are automatically garbage-collected one hour after the job finishes executing [1][2]. If you are referring to namespaces managed by the ephemeral-namespace workflow (which reserves namespaces in a pool), the reservation duration is configurable and defaults to 1 hour, though it can be set to values ranging from 30 minutes to 14 days [3][4]. For more generalized namespace lifecycle management in the OpenShift CI infrastructure, the ci-ns-ttl-controller is used to manage both hard and soft Time-To-Live (TTL) values, which are configurable via namespace annotations [5]. - A hard TTL (annotation: ci.openshift.io/ttl.hard) deletes the namespace after a specific duration following its creation [5]. - A soft TTL (annotation: ci.openshift.io/ttl.soft) deletes the namespace after a duration of inactivity, defined as the time since the last active marker or pod termination, provided no other pods are running or pending [5].
Citations:
- 1: https://docs.ci.openshift.org/how-tos/use-registries-in-build-farm/
- 2: https://github.com/openshift/ci-docs/blob/main/content/en/how-tos/use-registries-in-build-farm.md
- 3: https://docs.ci.openshift.org/how-tos/ephemeral-namespace-workflow/
- 4: https://github.com/openshift/ci-docs/blob/main/content/en/how-tos/ephemeral-namespace-workflow.md
- 5: https://github.com/openshift/ci-ns-ttl-controller
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== File context =="
sed -n '1,120p' ci-operator/config/openshift/cluster-version-operator/openshift-cluster-version-operator-release-5.0__periodics.yaml
echo
echo "== Search for this exact pull spec / namespace pattern =="
rg -n "ci-ln-3qfdxwk|ci-ln-|CUSTOM_OPENSHIFT_INSTALL_RELEASE_IMAGE_OVERRIDE" ci-operator core-services services cluster projects tools -S
echo
echo "== Search CI docs references in repo =="
rg -n "ci-ln-|build farm|garbage-collected|ephemeral namespace|registry.build10.ci.openshift.org" -S .Repository: openshift/release
Length of output: 19647
Recurring periodic uses an ephemeral build-farm payload. CUSTOM_OPENSHIFT_INSTALL_RELEASE_IMAGE_OVERRIDE points to registry.build10.ci.openshift.org/ci-ln-3qfdxwk/release:latest; once that ci-ln-* namespace is garbage-collected, this tag disappears, so the weekly job will go stale. Replace it with a stable release image or remove the override if this is only meant for a one-off comparison.
🤖 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
`@ci-operator/config/openshift/cluster-version-operator/openshift-cluster-version-operator-release-5.0__periodics.yaml`
around lines 31 - 34, The periodic job is pinned to an ephemeral ci-ln-* release
image override, which will disappear after garbage collection and make the
workflow stale. Update the periodic config for the
cucushift-installer-rehearse-gcp-ipi-compact job to use a stable release image
reference, or remove CUSTOM_OPENSHIFT_INSTALL_RELEASE_IMAGE_OVERRIDE entirely if
it is only intended for a one-time comparison, so the recurring job does not
depend on a transient payload.
|
/pj-rehearse periodic-ci-openshift-cluster-version-operator-release-5.0-periodics-e2e-gcp-compact-install periodic-ci-openshift-cluster-version-operator-release-5.0-periodics-e2e-gcp-compact-install-withnightly |
|
@miyadav: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
|
/pj-rehearse periodic-ci-openshift-cluster-version-operator-release-5.0-periodics-e2e-gcp-compact-install periodic-ci-openshift-cluster-version-operator-release-5.0-periodics-e2e-gcp-compact-install-withnightly |
|
@miyadav: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
124f109 to
988bcf1
Compare
|
/pj-rehearse periodic-ci-openshift-cluster-version-operator-release-5.0-periodics-e2e-gcp-compact-install periodic-ci-openshift-cluster-version-operator-release-5.0-periodics-e2e-gcp-compact-install-withnightly |
|
@miyadav: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
|
/retest |
|
/pj-rehearse periodic-ci-openshift-cluster-version-operator-release-5.0-periodics-e2e-gcp-compact-install periodic-ci-openshift-cluster-version-operator-release-5.0-periodics-e2e-gcp-compact-install-withnightly |
|
@miyadav: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
|
/pj-rehearse periodic-ci-openshift-cluster-version-operator-release-5.0-periodics-e2e-gcp-compact-install-techpreview periodic-ci-openshift-cluster-version-operator-release-5.0-periodics-e2e-gcp-compact-install-withnightly-techpreview |
|
@miyadav: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
|
[REHEARSALNOTIFIER]
Interacting with pj-rehearseComment: Once you are satisfied with the results of the rehearsals, comment: |
|
@miyadav: all tests passed! Full PR test history. Your PR dashboard. DetailsInstructions 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. |
/hold
open PR and nightly build comparison for compact cluster install
Summary by CodeRabbit
This change adds new CI periodic configuration for the OpenShift Cluster Version Operator on the release-5.0 branch. In practical terms, it enables GCP compact cluster install testing on a regular 168h cadence, including both:
It also defines the build inputs (Dockerfile
Dockerfile.rhelmapped to thecluster-version-operatorimage), disables promotion to the5.0target namespace, enables integration for thelateststream with built images included, and sets default pod resource requests (100m CPU, 200Mi memory) for all configured workloads.