OCPEDGE-2485: TNF RHCOS10 adding recovery CI Lane#80581
Conversation
openshift-ci-robot
added
the
jira/valid-reference
|
@dhensel-rh: This pull request references OCPEDGE-2485 which is a valid jira issue. 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 openshift-eng/jira-lifecycle-plugin repository. |
|
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 selected for processing (2)
🚧 Files skipped from review as they are similar to previous changes (1)
WalkthroughTwo nightly CI configuration files (4.22 and 4.23) each receive a new periodic test job ChangesTechPreview fencing recovery periodic job configuration
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 15✅ Passed checks (15 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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. Comment |
openshift-ci
Bot
added
the
do-not-merge/work-in-progress
|
Skipping CI for Draft Pull Request. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
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/release/openshift-release-main__nightly-4.22.yaml`:
- Around line 853-860: Both RHCOS10 techpreview recovery job definitions have a
naming-to-config mismatch: they are named as rhcos10-techpreview lanes but lack
explicit techpreview configuration and reference non-techpreview workflows. In
ci-operator/config/openshift/release/openshift-release-main__nightly-4.22.yaml
(lines 853-860), add an env block to the steps section with an OSSTREAM selector
set to rhel-10 (or the appropriate RHCOS10 techpreview value), and update the
workflow reference from baremetalds-two-node-fencing-recovery to the techpreview
variant if available. Apply the identical changes to the corresponding job in
ci-operator/config/openshift/release/openshift-release-main__nightly-4.23.yaml
(lines 827-834) so both lanes consistently exercise the intended RHCOS10
techpreview recovery path.
🪄 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: ec44a2b1-8687-48dc-904f-9c862e08176c
📒 Files selected for processing (2)
ci-operator/config/openshift/release/openshift-release-main__nightly-4.22.yamlci-operator/config/openshift/release/openshift-release-main__nightly-4.23.yaml
| - as: e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreview | ||
| capabilities: | ||
| - intranet | ||
| interval: 168h | ||
| shard_count: 3 | ||
| steps: | ||
| cluster_profile: equinix-edge-enablement | ||
| workflow: baremetalds-two-node-fencing-recovery |
There was a problem hiding this comment.
Both new rhcos10-techpreview recovery lanes are missing explicit techpreview/RHCOS10 configuration.
The shared root cause is a naming-to-config mismatch: both jobs are named as rhcos10 techpreview lanes, but neither sets an explicit RHCOS10 selector (for example OSSTREAM: rhel-10) and both point at the non-techpreview recovery workflow.
ci-operator/config/openshift/release/openshift-release-main__nightly-4.22.yaml#L853-L860: add techpreview-specific env (for exampleOSSTREAM: rhel-10) and use the techpreview recovery workflow variant if available.ci-operator/config/openshift/release/openshift-release-main__nightly-4.23.yaml#L827-L834: apply the same techpreview selectors/workflow alignment so this lane actually exercises the intended rhcos10 recovery path.
📍 Affects 2 files
ci-operator/config/openshift/release/openshift-release-main__nightly-4.22.yaml#L853-L860(this comment)ci-operator/config/openshift/release/openshift-release-main__nightly-4.23.yaml#L827-L834
🤖 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/release/openshift-release-main__nightly-4.22.yaml`
around lines 853 - 860, Both RHCOS10 techpreview recovery job definitions have a
naming-to-config mismatch: they are named as rhcos10-techpreview lanes but lack
explicit techpreview configuration and reference non-techpreview workflows. In
ci-operator/config/openshift/release/openshift-release-main__nightly-4.22.yaml
(lines 853-860), add an env block to the steps section with an OSSTREAM selector
set to rhel-10 (or the appropriate RHCOS10 techpreview value), and update the
workflow reference from baremetalds-two-node-fencing-recovery to the techpreview
variant if available. Apply the identical changes to the corresponding job in
ci-operator/config/openshift/release/openshift-release-main__nightly-4.23.yaml
(lines 827-834) so both lanes consistently exercise the intended RHCOS10
techpreview recovery path.
openshift-merge-bot
Bot
added
the
rehearsals-ack
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: dhensel-rh 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 |
openshift-merge-bot
Bot
removed
the
rehearsals-ack
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/release/openshift-release-main__nightly-4.23.yaml`:
- Around line 834-838: Remove the line `AGENT_E2E_TEST_SCENARIO=TNF_IPV4` from
the `DEVSCRIPTS_CONFIG` environment variable block. This variable is specific to
agent workflows and is not consumed by the
`baremetalds-two-node-fencing-recovery` workflow used by this job, making it
ineffective configuration. Keep only `BMC_DRIVER=redfish` and
`FEATURE_SET="TechPreviewNoUpgrade"` in the DEVSCRIPTS_CONFIG section,
consistent with other similar baremetalds-based jobs in the configuration.
🪄 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: 990ec0c5-e068-4c32-a20a-100fe7fcf386
⛔ Files ignored due to path filters (1)
ci-operator/jobs/openshift/release/openshift-release-main-periodics.yamlis excluded by!ci-operator/jobs/**
📒 Files selected for processing (2)
ci-operator/config/openshift/release/openshift-release-main__nightly-4.22.yamlci-operator/config/openshift/release/openshift-release-main__nightly-4.23.yaml
🚧 Files skipped from review as they are similar to previous changes (1)
- ci-operator/config/openshift/release/openshift-release-main__nightly-4.22.yaml
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/release/openshift-release-main__nightly-4.22.yaml`:
- Around line 861-864: The DEVSCRIPTS_CONFIG at lines 861-864 is incomplete and
replaces the workflow's full configuration, losing critical defaults like
IP_STACK, MASTER_DISK, MASTER_MEMORY, MASTER_VCPU, NUM_MASTERS, and NUM_WORKERS.
Replace the current minimal DEVSCRIPTS_CONFIG with a complete configuration that
includes all required defaults (IP_STACK=v4, MASTER_DISK=100,
MASTER_MEMORY=32768, MASTER_VCPU=8, NUM_MASTERS=2, NUM_WORKERS=0) plus your
additions (BMC_DRIVER=redfish and FEATURE_SET=TechPreviewNoUpgrade), following
the pattern used in similar workflows like
e2e-metal-ovn-two-node-fencing-ipv6-recovery.
🪄 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: e19b7a78-10c2-4e19-b5bd-0d4fa8e3f9ce
📒 Files selected for processing (2)
ci-operator/config/openshift/release/openshift-release-main__nightly-4.22.yamlci-operator/config/openshift/release/openshift-release-main__nightly-4.23.yaml
🚧 Files skipped from review as they are similar to previous changes (1)
- ci-operator/config/openshift/release/openshift-release-main__nightly-4.23.yaml
|
[REHEARSALNOTIFIER]
Interacting with pj-rehearseComment: Once you are satisfied with the results of the rehearsals, comment: |
openshift-ci
Bot
removed
the
do-not-merge/work-in-progress
|
/pj-rehearse periodic-ci-openshift-release-main-nightly-4.22-e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreview-1of3 periodic-ci-openshift-release-main-nightly-4.22-e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreview-2of3 periodic-ci-openshift-release-main-nightly-4.22-e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreview-3of3 periodic-ci-openshift-release-main-nightly-4.23-e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreview-1of3 periodic-ci-openshift-release-main-nightly-4.23-e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreview-2of3 periodic-ci-openshift-release-main-nightly-4.23-e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreview-3of3 |
|
@kasturinarra: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
|
/pj-rehearse periodic-ci-openshift-release-main-nightly-4.22-e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreview-1of3 |
|
@kasturinarra: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
|
/pj-rehearse periodic-ci-openshift-release-main-nightly-4.22-e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreview-2of3 periodic-ci-openshift-release-main-nightly-4.22-e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreview-3of3 periodic-ci-openshift-release-main-nightly-4.23-e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreview-1of3 periodic-ci-openshift-release-main-nightly-4.23-e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreview-2of3 periodic-ci-openshift-release-main-nightly-4.23-e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreview-3of3 |
|
@kasturinarra: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
|
@dhensel-rh: The following tests failed, say
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. |
3 participants
This PR adds the TNF recovery CI Lane to 4.22 and 4.23
Summary by CodeRabbit
This PR updates the OpenShift CI release configuration (
ci-operator) to add a new TNF (Test Network Function) recovery nightly lane for OpenShift 4.22 and 4.23 in theequinix-edge-enablementcluster profile.It introduces the
e2e-metal-ovn-two-node-fencing-recovery-rhcos10-techpreviewtestsjob in:ci-operator/config/openshift/release/openshift-release-main__nightly-4.22.yaml168hwithshard_count: 3capabilities: [intranet]OSSTREAM: rhel-10baremetalds-two-node-fencing-techpreviewworkflowDEVSCRIPTS_CONFIGwithBMC_DRIVER=redfish,FEATURE_SET=TechPreviewNoUpgrade,IP_STACK=v4, plus two-node fencing/recovery sizing parameters.ci-operator/config/openshift/release/openshift-release-main__nightly-4.23.yaml168hwithshard_count: 3capabilities: [intranet]OSSTREAM: rhel-10baremetalds-two-node-fencing-recoveryworkflowDEVSCRIPTS_CONFIGwithBMC_DRIVER=redfish,FEATURE_SET=TechPreviewNoUpgrade,IP_STACK=v4, and two-node fencing/recovery sizing parameters (NUM_WORKERS=0).Overall, the change extends nightly metal OVN two-node fencing recovery coverage for the RHCOS10 TechPreview TNF scenario on edge clusters.