Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -144,6 +144,17 @@ tests:
- observers-resource-watch
workflow: openshift-e2e-aws-ovn-serial
timeout: 5h0m0s
- as: e2e-aws-ovn-techpreview-serial-debug
interval: 168h
steps:
cluster_profile: openshift-org-aws
env:
FEATURE_SET: TechPreviewNoUpgrade
observers:
enable:
- observers-resource-watch
workflow: openshift-e2e-aws-ovn-serial-debug
timeout: 12h0m0s
Comment on lines +147 to +157
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

⚠️ Potential issue | 🟠 Major

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
set -euo pipefail

# Confirm the new test stanza exists in ci-operator config
rg -n --iglob '*.yaml' 'as:\s*e2e-aws-ovn-techpreview-serial-debug' ci-operator/config

# Confirm generated Prow job manifests reference the new test/job name
if [ -d ci-operator/jobs ]; then
  rg -n --iglob '*.ya?ml' \
    'periodic-ci-openshift-release-main-ci-4\.22-e2e-aws-ovn-techpreview-serial-debug|e2e-aws-ovn-techpreview-serial-debug' \
    ci-operator/jobs
else
  echo "ci-operator/jobs directory is not present in this checkout."
fi

Repository: openshift/release

Length of output: 182


Run make update to generate downstream Prow job configuration for this new test.

The test entry e2e-aws-ovn-techpreview-serial-debug exists in the CI configuration, but the corresponding generated Prow job config was not found. Per the coding guidelines for ci-operator/config/**/*.yaml, after editing the configuration file, you must run make update to generate the downstream Prow job manifests in ci-operator/jobs/.

🤖 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__ci-4.22.yaml`
around lines 147 - 157, The CI config defines a new test entry
e2e-aws-ovn-techpreview-serial-debug (workflow:
openshift-e2e-aws-ovn-serial-debug) but the generated Prow job manifests are
missing; run make update locally to regenerate downstream job configs (which
will create/modify files under ci-operator/jobs/) and commit those generated
changes along with your YAML edit so the new test exists in both
ci-operator/config and the generated ci-operator/jobs outputs.

- as: e2e-aws-ovn-rhcos10-techpreview-serial
interval: 12h
shard_count: 3
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -49422,6 +49422,91 @@ periodics:
- name: result-aggregator
secret:
secretName: result-aggregator
- agent: kubernetes
cluster: build09
decorate: true
decoration_config:
skip_cloning: true
timeout: 12h0m0s
extra_refs:
- base_ref: main
org: openshift
repo: release
interval: 168h
labels:
ci-operator.openshift.io/cloud: aws
ci-operator.openshift.io/cloud-cluster-profile: openshift-org-aws
ci-operator.openshift.io/variant: ci-4.22
ci.openshift.io/generator: prowgen
ci.openshift.io/no-builds: "true"
job-release: "4.22"
pj-rehearse.openshift.io/can-be-rehearsed: "true"
name: periodic-ci-openshift-release-main-ci-4.22-e2e-aws-ovn-techpreview-serial-debug
spec:
containers:
- args:
- --gcs-upload-secret=/secrets/gcs/service-account.json
- --image-import-pull-secret=/etc/pull-secret/.dockerconfigjson
- --lease-server-credentials-file=/etc/boskos/credentials
- --report-credentials-file=/etc/report/credentials
- --secret-dir=/secrets/ci-pull-credentials
- --target=e2e-aws-ovn-techpreview-serial-debug
- --variant=ci-4.22
command:
- ci-operator
env:
- name: HTTP_SERVER_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
image: quay-proxy.ci.openshift.org/openshift/ci:ci_ci-operator_latest
imagePullPolicy: Always
name: ""
ports:
- containerPort: 8080
name: http
resources:
requests:
cpu: 10m
volumeMounts:
- mountPath: /etc/boskos
name: boskos
readOnly: true
- mountPath: /secrets/ci-pull-credentials
name: ci-pull-credentials
readOnly: true
- mountPath: /secrets/gcs
name: gcs-credentials
readOnly: true
- mountPath: /secrets/manifest-tool
name: manifest-tool-local-pusher
readOnly: true
- mountPath: /etc/pull-secret
name: pull-secret
readOnly: true
- mountPath: /etc/report
name: result-aggregator
readOnly: true
serviceAccountName: ci-operator
volumes:
- name: boskos
secret:
items:
- key: credentials
path: credentials
secretName: boskos-credentials
- name: ci-pull-credentials
secret:
secretName: ci-pull-credentials
- name: manifest-tool-local-pusher
secret:
secretName: manifest-tool-local-pusher
- name: pull-secret
secret:
secretName: registry-pull-credentials
- name: result-aggregator
secret:
secretName: result-aggregator
- agent: kubernetes
cluster: build09
decorate: true
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
approvers:
- weliang1
reviewers:
- weliang1
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
{
"path": "openshift/e2e/aws/ovn/serial-debug/openshift-e2e-aws-ovn-serial-debug-workflow.yaml",
"owners": {
"approvers": [
"weliang1"
],
"reviewers": [
"weliang1"
]
}
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,36 @@
workflow:
as: openshift-e2e-aws-ovn-serial-debug
steps:
allow_best_effort_post_steps: true
pre:
- chain: ipi-conf-aws
- ref: ovn-conf
- ref: ovn-conf-multi-network-policy-manifest
- ref: rhcos-conf-osstream
- chain: ipi-install
test:
- ref: openshift-e2e-test
post:
- ref: cucushift-installer-wait
timeout: 12h0m0s
best_effort: true
optional_on_success: true
- chain: gather-network
- chain: gather-core-dump
- chain: ipi-deprovision
env:
TEST_SUITE: openshift/conformance/serial
documentation: |-
Debug version of openshift-e2e-aws-ovn-serial workflow with cucushift-installer-wait
for extended cluster access. Supports SLEEP_DURATION environment variable for debugging.

This workflow:
- Installs OpenShift cluster on AWS with OVN network plugin
- Configures multi-network policy support
- Runs e2e tests (can be skipped with TEST_ARGS="--dry-run")
- Includes cucushift-installer-wait step for extended debugging (up to 12 hours)
- Supports SLEEP_DURATION environment variable (default 2h, max 72h)
Comment on lines +31 to +32
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

Align debug-duration docs with the enforced 12h limit.

Line 32 says SLEEP_DURATION supports up to 72h, but Line 15 enforces a 12h wait timeout in this workflow. Please document the effective cap for this workflow to avoid failed expectations.

Suggested doc fix
-    - Includes cucushift-installer-wait step for extended debugging (up to 12 hours)
-    - Supports SLEEP_DURATION environment variable (default 2h, max 72h)
+    - Includes cucushift-installer-wait step for extended debugging (up to 12 hours in this workflow)
+    - Supports SLEEP_DURATION environment variable (default 2h; effective max 12h due to workflow timeout)
📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
- Includes cucushift-installer-wait step for extended debugging (up to 12 hours)
- Supports SLEEP_DURATION environment variable (default 2h, max 72h)
- Includes cucushift-installer-wait step for extended debugging (up to 12 hours in this workflow)
- Supports SLEEP_DURATION environment variable (default 2h; effective max 12h due to workflow timeout)
🤖 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/step-registry/openshift/e2e/aws/ovn/serial-debug/openshift-e2e-aws-ovn-serial-debug-workflow.yaml`
around lines 31 - 32, Update the workflow documentation stanza that describes
SLEEP_DURATION to reflect the effective cap enforced by this workflow: change
the "max 72h" wording to state the 12h enforced timeout (or explicitly state
"max 72h, but capped to 12h in this workflow") so users aren't misled; reference
the SLEEP_DURATION environment variable and the cucushift-installer-wait usage
in the openshift-e2e-aws-ovn-serial-debug-workflow.yaml so it's clear the 12h
wait timeout applies to this workflow.


Usage with gangway-cli:
--env SLEEP_DURATION=8h
--env TEST_ARGS="--dry-run" (to skip actual test execution)