HIVE-3148: add OTE e2e test jobs for openshift/hive#78554
HIVE-3148: add OTE e2e test jobs for openshift/hive#78554miyadav wants to merge 6 commits intoopenshift:mainfrom
Conversation
openshift-ci-robot
added
the
jira/valid-reference
|
@miyadav: This pull request references HIVE-3148 which is a valid jira issue. Warning: The referenced jira issue has an invalid target version for the target branch this PR targets: expected the task to target the "5.0.0" version, but no target version was set. 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. |
openshift-ci
Bot
added
the
do-not-merge/hold
|
[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 |
|
/pj-rehearse pull-ci-openshift-hive-master-e2e-ote |
|
@miyadav: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
WalkthroughAdds a Changes
Sequence Diagram(s)sequenceDiagram
actor CI as CI Operator
participant Builder as Image Builder
participant Registry as Image Registry
participant Job as ci-operator Job
participant Cloud as Cloud Provider
participant ClusterClaim as cluster_claim
participant TestRunner as openshift-tests-extension
CI->>Builder: build `hive-tests` (compile & gzip openshift-tests-extension)
Builder-->>Registry: push `hive-tests`
CI->>Job: trigger e2e-*-ote variant
Job->>Registry: pull `hive-tests`, `HIVE_IMAGE`, `RELEASE_IMAGE`
Job->>Cloud: request provider credentials / provision cluster
Cloud->>ClusterClaim: provision cluster and return kubeconfig/env
ClusterClaim-->>Job: provide kubeconfig and platform-specific env
Job->>TestRunner: run `openshift-tests-extension run-suite -c 1 openshift/hive`
TestRunner-->>Job: emit results/logs
Job-->>CI: report job outcome
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes 🚥 Pre-merge checks | ✅ 12✅ Passed checks (12 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@ci-operator/config/openshift/hive/openshift-hive-master.yaml`:
- Around line 353-355: This job's command block runs the Hive test suite but
doesn't export BASE_DOMAIN like the e2e-gcp job; update the commands (the block
that sets KUBECONFIG and calls /usr/bin/openshift-tests-extension run-suite
openshift/hive) to also export BASE_DOMAIN by reading it from
${CLUSTER_PROFILE_DIR}/public_hosted_zone (e.g., export BASE_DOMAIN="$(cat
${CLUSTER_PROFILE_DIR}/public_hosted_zone)") so downstream Hive provisioning has
the DNS zone available.
- Around line 399-418: The OTE job's commands block sources vsphere helper
scripts (source $SHARED_DIR/vsphere_context.sh, source $SHARED_DIR/govc.sh) but
does not mount the vsphere secret; update the job spec that contains the
commands/from: hive-tests to add a volume/volumeMount or secret mount for
vsphere-ibmcloud-ci at /var/run/vault/vsphere-ibmcloud-ci (matching the
e2e-vsphere job) so the helpers can read the credentials when sourcing those
scripts.
- Around line 29-40: Replace the moving branch reference in the
dockerfile_literal (the RUN git clone --branch fix-ote-init --depth 1
https://github.com/miyadav/hive.git . line) with a clone and checkout pinned to
a specific commit SHA so the image is reproducible; e.g., clone the repo (no
branch), fetch the desired commit SHA, and checkout that SHA (or use git clone
--depth 1 <repo> && git -C hive checkout <COMMIT_SHA>) so the build always uses
an immutable revision—update the RUN line to perform these steps and document
the chosen commit SHA in the file.
🪄 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: c6ccca02-6f9c-4ba5-9ac9-33212b4bc53e
⛔ Files ignored due to path filters (3)
ci-operator/jobs/openshift/hive/openshift-hive-master-periodics.yamlis excluded by!ci-operator/jobs/**ci-operator/jobs/openshift/hive/openshift-hive-master-postsubmits.yamlis excluded by!ci-operator/jobs/**ci-operator/jobs/openshift/hive/openshift-hive-master-presubmits.yamlis excluded by!ci-operator/jobs/**
📒 Files selected for processing (1)
ci-operator/config/openshift/hive/openshift-hive-master.yaml
| - dockerfile_literal: | | ||
| FROM registry.ci.openshift.org/ocp/builder:rhel-9-golang-1.25-openshift-4.22 as builder | ||
| RUN mkdir -p /go/src/github.com/openshift/hive | ||
| WORKDIR /go/src/github.com/openshift/hive | ||
| RUN git clone --branch fix-ote-init --depth 1 https://github.com/miyadav/hive.git . | ||
| RUN make -C test/ote build | ||
| FROM registry.access.redhat.com/ubi9/ubi-minimal:latest | ||
| RUN microdnf install -y gzip jq && microdnf clean all | ||
| COPY --from=builder /go/src/github.com/openshift/hive/test/ote/bin/hive /usr/bin/openshift-tests-extension | ||
| RUN gzip -f -k /usr/bin/openshift-tests-extension | ||
| WORKDIR /tmp | ||
| to: hive-tests |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Shows the current branch head that this Dockerfile consumes today.
git ls-remote https://github.com/miyadav/hive.git refs/heads/fix-ote-initRepository: openshift/release
Length of output: 126
Pin the temporary miyadav/hive source to an immutable revision.
Cloning from the fix-ote-init branch makes this image non-reproducible and allows future branch updates to change the test binary without additional openshift/release review. Pin a commit SHA instead of using a moving branch reference.
Suggested change
- dockerfile_literal: |
FROM registry.ci.openshift.org/ocp/builder:rhel-9-golang-1.25-openshift-4.22 as builder
RUN mkdir -p /go/src/github.com/openshift/hive
WORKDIR /go/src/github.com/openshift/hive
- RUN git clone --branch fix-ote-init --depth 1 https://github.com/miyadav/hive.git .
+ ARG HIVE_OTE_COMMIT=<pinned-sha>
+ RUN git init . \
+ && git remote add origin https://github.com/miyadav/hive.git \
+ && git fetch --depth 1 origin "${HIVE_OTE_COMMIT}" \
+ && git checkout --detach FETCH_HEAD
RUN make -C test/ote build🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@ci-operator/config/openshift/hive/openshift-hive-master.yaml` around lines 29
- 40, Replace the moving branch reference in the dockerfile_literal (the RUN git
clone --branch fix-ote-init --depth 1 https://github.com/miyadav/hive.git .
line) with a clone and checkout pinned to a specific commit SHA so the image is
reproducible; e.g., clone the repo (no branch), fetch the desired commit SHA,
and checkout that SHA (or use git clone --depth 1 <repo> && git -C hive checkout
<COMMIT_SHA>) so the build always uses an immutable revision—update the RUN line
to perform these steps and document the chosen commit SHA in the file.
| commands: | | ||
| export KUBECONFIG="${SHARED_DIR}/kubeconfig" | ||
| source $SHARED_DIR/vsphere_context.sh | ||
| source $SHARED_DIR/govc.sh | ||
| source $SHARED_DIR/additional_cluster.sh | ||
|
|
||
| export CLUSTER_NAME=$ADDITIONAL_CLUSTER_NAME | ||
| export VSPHERE_API_VIP=$ADDITIONAL_CLUSTER_API_VIP | ||
| export VSPHERE_INGRESS_VIP=$ADDITIONAL_CLUSTER_INGRESS_VIP | ||
| export VSPHERE_MACHINE_NETWORK=$(<"${SHARED_DIR}"/machinecidr.txt) | ||
| export BASE_DOMAIN=$(<"${SHARED_DIR}"/basedomain.txt) | ||
| export VSPHERE_INSTALLER_PLATFORM_SPEC_JSON=$(<"${SHARED_DIR}"/platform.json) | ||
|
|
||
| /usr/bin/openshift-tests-extension run-suite openshift/hive | ||
| dependencies: | ||
| - env: HIVE_IMAGE | ||
| name: hive | ||
| - env: RELEASE_IMAGE | ||
| name: release:latest | ||
| from: hive-tests |
There was a problem hiding this comment.
Mount the vSphere credentials in the OTE variant too.
This step sources the same vSphere helper scripts as e2e-vsphere, but unlike the existing job it never mounts vsphere-ibmcloud-ci at /var/run/vault/vsphere-ibmcloud-ci. Those helpers depend on that secret, so this job is likely to fail before the suite starts.
Suggested change
commands: |
export KUBECONFIG="${SHARED_DIR}/kubeconfig"
source $SHARED_DIR/vsphere_context.sh
source $SHARED_DIR/govc.sh
source $SHARED_DIR/additional_cluster.sh
@@
export VSPHERE_INSTALLER_PLATFORM_SPEC_JSON=$(<"${SHARED_DIR}"/platform.json)
/usr/bin/openshift-tests-extension run-suite openshift/hive
+ credentials:
+ - mount_path: /var/run/vault/vsphere-ibmcloud-ci
+ name: vsphere-ibmcloud-ci
+ namespace: test-credentials
dependencies:
- env: HIVE_IMAGE
name: hive📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| commands: | | |
| export KUBECONFIG="${SHARED_DIR}/kubeconfig" | |
| source $SHARED_DIR/vsphere_context.sh | |
| source $SHARED_DIR/govc.sh | |
| source $SHARED_DIR/additional_cluster.sh | |
| export CLUSTER_NAME=$ADDITIONAL_CLUSTER_NAME | |
| export VSPHERE_API_VIP=$ADDITIONAL_CLUSTER_API_VIP | |
| export VSPHERE_INGRESS_VIP=$ADDITIONAL_CLUSTER_INGRESS_VIP | |
| export VSPHERE_MACHINE_NETWORK=$(<"${SHARED_DIR}"/machinecidr.txt) | |
| export BASE_DOMAIN=$(<"${SHARED_DIR}"/basedomain.txt) | |
| export VSPHERE_INSTALLER_PLATFORM_SPEC_JSON=$(<"${SHARED_DIR}"/platform.json) | |
| /usr/bin/openshift-tests-extension run-suite openshift/hive | |
| dependencies: | |
| - env: HIVE_IMAGE | |
| name: hive | |
| - env: RELEASE_IMAGE | |
| name: release:latest | |
| from: hive-tests | |
| commands: | | |
| export KUBECONFIG="${SHARED_DIR}/kubeconfig" | |
| source $SHARED_DIR/vsphere_context.sh | |
| source $SHARED_DIR/govc.sh | |
| source $SHARED_DIR/additional_cluster.sh | |
| export CLUSTER_NAME=$ADDITIONAL_CLUSTER_NAME | |
| export VSPHERE_API_VIP=$ADDITIONAL_CLUSTER_API_VIP | |
| export VSPHERE_INGRESS_VIP=$ADDITIONAL_CLUSTER_INGRESS_VIP | |
| export VSPHERE_MACHINE_NETWORK=$(<"${SHARED_DIR}"/machinecidr.txt) | |
| export BASE_DOMAIN=$(<"${SHARED_DIR}"/basedomain.txt) | |
| export VSPHERE_INSTALLER_PLATFORM_SPEC_JSON=$(<"${SHARED_DIR}"/platform.json) | |
| /usr/bin/openshift-tests-extension run-suite openshift/hive | |
| credentials: | |
| - mount_path: /var/run/vault/vsphere-ibmcloud-ci | |
| name: vsphere-ibmcloud-ci | |
| namespace: test-credentials | |
| dependencies: | |
| - env: HIVE_IMAGE | |
| name: hive | |
| - env: RELEASE_IMAGE | |
| name: release:latest | |
| from: hive-tests |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@ci-operator/config/openshift/hive/openshift-hive-master.yaml` around lines
399 - 418, The OTE job's commands block sources vsphere helper scripts (source
$SHARED_DIR/vsphere_context.sh, source $SHARED_DIR/govc.sh) but does not mount
the vsphere secret; update the job spec that contains the commands/from:
hive-tests to add a volume/volumeMount or secret mount for vsphere-ibmcloud-ci
at /var/run/vault/vsphere-ibmcloud-ci (matching the e2e-vsphere job) so the
helpers can read the credentials when sourcing those scripts.
|
/pj-rehearse pull-ci-openshift-hive-master-e2e-ote |
|
@miyadav: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (2)
ci-operator/config/openshift/hive/openshift-hive-master.yaml (2)
397-419:⚠️ Potential issue | 🔴 CriticalMount the vSphere secret on the OTE variant too.
This job sources the same vSphere helper scripts as
e2e-vsphereon Lines 250-252, but unlike Lines 262-265 it never mountsvsphere-ibmcloud-ci. Those helpers read credentials from that path, so this variant is likely to fail before the suite starts.Suggested change
commands: | export KUBECONFIG="${SHARED_DIR}/kubeconfig" source $SHARED_DIR/vsphere_context.sh source $SHARED_DIR/govc.sh source $SHARED_DIR/additional_cluster.sh @@ /usr/bin/openshift-tests-extension run-suite openshift/hive + credentials: + - mount_path: /var/run/vault/vsphere-ibmcloud-ci + name: vsphere-ibmcloud-ci + namespace: test-credentials dependencies: - env: HIVE_IMAGE name: hive🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@ci-operator/config/openshift/hive/openshift-hive-master.yaml` around lines 397 - 419, The OTE test job's "test:" block (the job with "as: test" and "commands: | ... /usr/bin/openshift-tests-extension run-suite openshift/hive") sources the vSphere helper scripts but does not mount the vsphere-ibmcloud-ci secret that those helpers expect; add a dependency entry to the job's "dependencies:" list to mount the vsphere-ibmcloud-ci secret (same pattern used by the e2e-vsphere job) so the helper scripts can read credentials from that path.
29-34:⚠️ Potential issue | 🟠 MajorPin the temporary Hive source to an immutable revision.
This image still clones
fix-ote-init, so future pushes to that branch can change the OTE runner without anotheropenshift/releasereview. Fetch and check out a specific commit SHA instead.Suggested change
- dockerfile_literal: | FROM registry.ci.openshift.org/ocp/builder:rhel-9-golang-1.25-openshift-4.22 as builder RUN mkdir -p /go/src/github.com/openshift/hive WORKDIR /go/src/github.com/openshift/hive - RUN git clone --branch fix-ote-init --depth 1 https://github.com/miyadav/hive.git . + ARG HIVE_OTE_COMMIT=<pinned-sha> + RUN git init . \ + && git remote add origin https://github.com/miyadav/hive.git \ + && git fetch --depth 1 origin "${HIVE_OTE_COMMIT}" \ + && git checkout --detach FETCH_HEAD RUN make -C test/ote build🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@ci-operator/config/openshift/hive/openshift-hive-master.yaml` around lines 29 - 34, The Dockerfile fragment in dockerfile_literal currently clones the branch name "fix-ote-init" (RUN git clone --branch fix-ote-init --depth 1 ...), which is mutable; change the git clone invocation to fetch and check out a specific commit SHA (immutable) instead: clone the repo without relying on a branch (or clone then checkout) and checkout the provided commit SHA before running make -C test/ote build so the builder stage uses a pinned commit; update the RUN lines in the Dockerfile snippet that include git clone and any subsequent git checkout to use the chosen commit SHA.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@ci-operator/config/openshift/hive/openshift-hive-master.yaml`:
- Around line 322-327: Add an export of KUBECONFIG pointing to the shared
kubeconfig before running tests: in the commands block that sets
AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, PULL_SECRET_FILE and CLUSTER_NAME and
then calls /usr/bin/openshift-tests-extension run-suite openshift/hive, insert
export KUBECONFIG="${SHARED_DIR}/kubeconfig" so the openshift-tests-extension
run-suite has access to the claimed cluster kubeconfig.
---
Duplicate comments:
In `@ci-operator/config/openshift/hive/openshift-hive-master.yaml`:
- Around line 397-419: The OTE test job's "test:" block (the job with "as: test"
and "commands: | ... /usr/bin/openshift-tests-extension run-suite
openshift/hive") sources the vSphere helper scripts but does not mount the
vsphere-ibmcloud-ci secret that those helpers expect; add a dependency entry to
the job's "dependencies:" list to mount the vsphere-ibmcloud-ci secret (same
pattern used by the e2e-vsphere job) so the helper scripts can read credentials
from that path.
- Around line 29-34: The Dockerfile fragment in dockerfile_literal currently
clones the branch name "fix-ote-init" (RUN git clone --branch fix-ote-init
--depth 1 ...), which is mutable; change the git clone invocation to fetch and
check out a specific commit SHA (immutable) instead: clone the repo without
relying on a branch (or clone then checkout) and checkout the provided commit
SHA before running make -C test/ote build so the builder stage uses a pinned
commit; update the RUN lines in the Dockerfile snippet that include git clone
and any subsequent git checkout to use the chosen commit SHA.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository YAML (base), Central YAML (inherited)
Review profile: CHILL
Plan: Enterprise
Run ID: eb93571c-1839-43ad-a430-68b90a762544
⛔ Files ignored due to path filters (1)
ci-operator/jobs/openshift/hive/openshift-hive-master-presubmits.yamlis excluded by!ci-operator/jobs/**
📒 Files selected for processing (1)
ci-operator/config/openshift/hive/openshift-hive-master.yaml
| commands: | | ||
| export AWS_ACCESS_KEY_ID=$(cat /tmp/secret/hiveci-aws-creds/AWS_ACCESS_KEY_ID) | ||
| export AWS_SECRET_ACCESS_KEY=$(cat /tmp/secret/hiveci-aws-creds/AWS_SECRET_ACCESS_KEY) | ||
| export PULL_SECRET_FILE=/tmp/secret/pull-secret/.dockerconfigjson | ||
| export CLUSTER_NAME=$(printf "hiveci-%x-%x" $(date +%s) $PULL_NUMBER) | ||
| /usr/bin/openshift-tests-extension run-suite openshift/hive |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== OTE jobs in this file =="
rg -n -C2 'as: e2e(-gcp|-azure|-vsphere)?-ote|KUBECONFIG|openshift-tests-extension run-suite openshift/hive' ci-operator/config/openshift/hive/openshift-hive-master.yaml
echo
echo "== generic-claim workflow / steps mentioning kubeconfig =="
fd -i 'generic-claim' step-registry ci-operator | xargs -r rg -n -C3 'KUBECONFIG|kubeconfig'
echo
echo "== other generic-claim jobs that run openshift-tests-extension =="
rg -n -C3 'workflow:\s*generic-claim|openshift-tests-extension run-suite' ci-operator/configRepository: openshift/release
Length of output: 50452
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== Searching for generic-claim workflow definition =="
find ci-operator -name "*generic*claim*" -type f | head -20
echo
echo "== Looking for generic-claim in workflows directory =="
find ci-operator/step-registry -name "generic-claim" -type d 2>/dev/null | head -10
echo
echo "== Searching for generic-claim workflow in all files =="
rg -l "generic-claim" ci-operator/step-registry --max-count=20 2>/dev/null || trueRepository: openshift/release
Length of output: 2625
🏁 Script executed:
cat -n ci-operator/step-registry/generic-claim/generic-claim-workflow.yamlRepository: openshift/release
Length of output: 814
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== Checking ipi-install-rbac ref =="
cat ci-operator/step-registry/ipi/install/rbac/ipi-install-rbac-ref.yaml | head -50
echo
echo "== Searching for where SHARED_DIR/kubeconfig gets created =="
rg 'SHARED_DIR.*kubeconfig|kubeconfig.*SHARED_DIR' ci-operator/step-registry --max-count=10 -A2
echo
echo "== Looking at cluster-claim setup in generic-claim usage =="
rg -B5 'workflow: generic-claim' ci-operator/config/openshift/hive/openshift-hive-master.yaml | grep -A5 'as: e2e-ote'Repository: openshift/release
Length of output: 50374
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== Looking for cluster-claim kubeconfig injection =="
rg 'cluster.claim|cluster_claim' ci-operator/step-registry/generic-claim/ -A5 -B5 | head -40
echo
echo "== Checking if KUBECONFIG is set in container environment =="
rg 'KUBECONFIG.*SHARED_DIR|/tmp.*kubeconfig' ci-operator/step-registry/cluster-claim* -i 2>/dev/null || echo "No direct cluster-claim kubeconfig injection found"
echo
echo "== Searching for documentation on cluster-claim kubeconfig handling =="
find ci-operator -name "*.yaml" -path "*/cluster-claim*" | head -5
echo
echo "== Examine the actual e2e-ote job in context to see if it has a step before openshift-tests-extension =="
sed -n '306,330p' ci-operator/config/openshift/hive/openshift-hive-master.yamlRepository: openshift/release
Length of output: 114
🏁 Script executed:
#!/bin/bash
set -euo pipefail
echo "== Full e2e-ote job definition =="
sed -n '306,380p' ci-operator/config/openshift/hive/openshift-hive-master.yaml
echo
echo "== Check if there are any pre steps in the e2e-ote job =="
sed -n '306,380p' ci-operator/config/openshift/hive/openshift-hive-master.yaml | grep -A100 'as: e2e-ote' | grep -E '^\s+pre:|^\s+- ref:|^\s+- chain:'Repository: openshift/release
Length of output: 2410
Add export KUBECONFIG="${SHARED_DIR}/kubeconfig" to the test commands.
The AWS OTE job using workflow: generic-claim is missing the KUBECONFIG export that all other OTE variants (GCP, Azure, vSphere) include. Without this, the openshift-tests-extension suite will run without access to the claimed cluster's kubeconfig. Align with the pattern used in e2e-gcp-ote, e2e-azure-ote, and e2e-vsphere-ote.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@ci-operator/config/openshift/hive/openshift-hive-master.yaml` around lines
322 - 327, Add an export of KUBECONFIG pointing to the shared kubeconfig before
running tests: in the commands block that sets AWS_ACCESS_KEY_ID,
AWS_SECRET_ACCESS_KEY, PULL_SECRET_FILE and CLUSTER_NAME and then calls
/usr/bin/openshift-tests-extension run-suite openshift/hive, insert export
KUBECONFIG="${SHARED_DIR}/kubeconfig" so the openshift-tests-extension run-suite
has access to the claimed cluster kubeconfig.
|
/retest |
|
/pj-rehearse pull-ci-openshift-hive-master-e2e-ote |
|
@miyadav: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
|
/pj-rehearse pull-ci-openshift-hive-master-e2e-ote |
|
@miyadav: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
|
/pj-rehearse pull-ci-openshift-hive-master-e2e-ote |
|
@miyadav: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
|
/pj-rehearse pull-ci-openshift-hive-master-e2e-ote |
|
@miyadav: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
|
/pj-rehearse pull-ci-openshift-hive-master-e2e-ote |
|
@miyadav: now processing your pj-rehearse request. Please allow up to 10 minutes for jobs to trigger or cancel. |
|
/pj-rehearse pull-ci-openshift-hive-master-e2e-ote |
|
@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: 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. |
|
/close |
|
@miyadav: Closed this PR. 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. |
2 participants
/hold
Add e2e-ote, e2e-gcp-ote, e2e-azure-ote, and e2e-vsphere-ote test jobs using the OpenShift Tests Extension framework. Temporarily uses dockerfile_literal to build hive-tests from miyadav/hive:fix-ote-init branch while the hive PR is validated.
Summary by CodeRabbit
New Features
Tests