CORENET-6613: ClusterNetworkConnect DevPreview FG#2880
CORENET-6613: ClusterNetworkConnect DevPreview FG#2880openshift-merge-bot[bot] merged 1 commit intoopenshift:masterfrom
ClusterNetworkConnect DevPreview FG#2880Conversation
|
@tssurya: This pull request references CORENET-6613 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 story to target the "4.22.0" 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. |
|
Important Review skippedAuto reviews are limited based on label configuration. 🚫 Review skipped — only excluded labels are configured. (1)
Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
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:
WalkthroughThe PR adds NetworkConnect feature support to OVN Kubernetes by introducing a new ClusterNetworkConnect CustomResourceDefinition, enabling feature flags across common, managed, and self-hosted deployment manifests, and updating tests to validate the feature gate behavior. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
| fi | ||
|
|
||
| network_connect_enabled_flag= | ||
| if [[ "{{.OVN_NETWORK_CONNECT_ENABLE}}" == "true" && "${OVN_NODE_MODE}" != "dpu-host" ]]; then |
There was a problem hiding this comment.
What's up with "${OVN_NODE_MODE}" != "dpu-host"? I think it's only present here.
There was a problem hiding this comment.
hmm it seems the DPF folks added it to all of them?
I see:
multi_network_enabled_flag=
if [[ "{{.OVN_MULTI_NETWORK_ENABLE}}" == "true" && "${OVN_NODE_MODE}" != "dpu-host" ]]; then
multi_network_enabled_flag="--enable-multi-network"
fi
network_segmentation_enabled_flag=
if [[ "{{.OVN_NETWORK_SEGMENTATION_ENABLE}}" == "true" && "${OVN_NODE_MODE}" != "dpu-host" ]]; then
multi_network_enabled_flag="--enable-multi-network"
network_segmentation_enabled_flag="--enable-network-segmentation"
fi
multi_network_policy_enabled_flag=
if [[ "{{.OVN_MULTI_NETWORK_POLICY_ENABLE}}" == "true"&& "${OVN_NODE_MODE}" != "dpu-host" ]]; then
multi_network_policy_enabled_flag="--enable-multi-networkpolicy"
fi
admin_network_policy_enabled_flag=
if [[ "{{.OVN_ADMIN_NETWORK_POLICY_ENABLE}}" == "true" && "${OVN_NODE_MODE}" != "dpu-host" ]]; then
admin_network_policy_enabled_flag="--enable-admin-network-policy"
fi
not sure why some have it some don't?
94dc54c to
db2a8db
Compare
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@bindata/network/ovn-kubernetes/common/001-crd.yaml`:
- Around line 5173-5205: The x-kubernetes-validations rule currently enforces
networkPrefix must be strictly greater than the CIDR prefix, but the description
allows it to be equal; update the validation expression for the CRD so that it
permits equality: locate the x-kubernetes-validations entry that references
self.networkPrefix and cidr(self.cidr).prefixLength() and change the comparison
from ">" to ">=" (or adjust the negated logic accordingly) so networkPrefix can
be equal to the CIDR prefix while still rejecting shorter prefixes.
♻️ Duplicate comments (1)
bindata/network/ovn-kubernetes/managed/004-config.yaml (1)
130-140: Missing{{- end }}makes enable-network-connect incorrectly depend on segmentation.
enable-network-connect=trueis currently nested under{{- if .OVN_NETWORK_SEGMENTATION_ENABLE }}because the block is not closed. This will suppress the new flag unless segmentation is enabled.Suggested fix
{{- if .OVN_NETWORK_SEGMENTATION_ENABLE }} {{- if not .OVN_MULTI_NETWORK_ENABLE }} enable-multi-network=true {{- end }} enable-network-segmentation=true +{{- end }} {{- if .OVN_PRE_CONF_UDN_ADDR_ENABLE }} enable-preconfigured-udn-addresses=true {{- end }}
📜 Review details
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Cache: Disabled due to data retention organization setting
Knowledge base: Disabled due to Reviews -> Disable Knowledge Base setting
📒 Files selected for processing (9)
bindata/network/ovn-kubernetes/common/001-crd.yamlbindata/network/ovn-kubernetes/common/008-script-lib.yamlbindata/network/ovn-kubernetes/managed/004-config.yamlbindata/network/ovn-kubernetes/managed/ovnkube-control-plane.yamlbindata/network/ovn-kubernetes/self-hosted/004-config.yamlbindata/network/ovn-kubernetes/self-hosted/ovnkube-control-plane.yamlpkg/network/cluster_config_test.gopkg/network/ovn_kubernetes.gopkg/network/ovn_kubernetes_test.go
🚧 Files skipped from review as they are similar to previous changes (5)
- pkg/network/ovn_kubernetes.go
- bindata/network/ovn-kubernetes/self-hosted/004-config.yaml
- pkg/network/cluster_config_test.go
- bindata/network/ovn-kubernetes/common/008-script-lib.yaml
- pkg/network/ovn_kubernetes_test.go
🧰 Additional context used
📓 Path-based instructions (1)
**
⚙️ CodeRabbit configuration file
-Focus on major issues impacting performance, readability, maintainability and security. Avoid nitpicks and avoid verbosity.
Files:
bindata/network/ovn-kubernetes/managed/ovnkube-control-plane.yamlbindata/network/ovn-kubernetes/common/001-crd.yamlbindata/network/ovn-kubernetes/managed/004-config.yamlbindata/network/ovn-kubernetes/self-hosted/ovnkube-control-plane.yaml
🔇 Additional comments (3)
bindata/network/ovn-kubernetes/managed/004-config.yaml (1)
48-50: LGTM: feature-flagged enablement is cleanly scoped.bindata/network/ovn-kubernetes/managed/ovnkube-control-plane.yaml (1)
207-210: Feature-gated NetworkConnect flag is wired consistently.
Matches the existing flag pattern and cleanly injects the option into the ovnkube command.Also applies to: 256-256
bindata/network/ovn-kubernetes/self-hosted/ovnkube-control-plane.yaml (1)
158-161: NetworkConnect flag addition is consistent with existing gating.
No issues; the exec wiring is straightforward and aligned with the managed manifest.Also applies to: 213-213
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
7207d29 to
fe79b4b
Compare
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@pkg/network/ovn_kubernetes_test.go`:
- Around line 880-920: The test case with desc "enable network connect
(DevPreview)" is missing the controlPlaneReplicaCount field causing it to
default to 0; update that table entry to include controlPlaneReplicaCount (match
other non-SNO tests by setting controlPlaneReplicaCount: 2, or 1 if intended as
SNO) so the cluster config used by the test (and the expected output block)
reflects a valid replica count; locate the test case by its desc string and add
the controlPlaneReplicaCount key alongside enabledFeatureGates and expected.
♻️ Duplicate comments (1)
bindata/network/ovn-kubernetes/common/001-crd.yaml (1)
5174-5205: AlignnetworkPrefixvalidation with the “equal or longer” rule.The description allows equality, but the validation rule requires
networkPrefixto be strictly greater than the CIDR prefix length, rejecting valid configs (e.g.,/16withnetworkPrefix=16).Proposed fix
- - message: NetworkPrefix must be smaller than CIDR subnet - rule: '!has(self.networkPrefix) || !isCIDR(self.cidr) || self.networkPrefix - > cidr(self.cidr).prefixLength()' + - message: NetworkPrefix must be equal to or longer than the CIDR prefix + rule: '!has(self.networkPrefix) || !isCIDR(self.cidr) || self.networkPrefix + >= cidr(self.cidr).prefixLength()'
📜 Review details
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Cache: Disabled due to data retention organization setting
Knowledge base: Disabled due to Reviews -> Disable Knowledge Base setting
📒 Files selected for processing (9)
bindata/network/ovn-kubernetes/common/001-crd.yamlbindata/network/ovn-kubernetes/common/008-script-lib.yamlbindata/network/ovn-kubernetes/managed/004-config.yamlbindata/network/ovn-kubernetes/managed/ovnkube-control-plane.yamlbindata/network/ovn-kubernetes/self-hosted/004-config.yamlbindata/network/ovn-kubernetes/self-hosted/ovnkube-control-plane.yamlpkg/network/cluster_config_test.gopkg/network/ovn_kubernetes.gopkg/network/ovn_kubernetes_test.go
🚧 Files skipped from review as they are similar to previous changes (2)
- pkg/network/cluster_config_test.go
- bindata/network/ovn-kubernetes/managed/004-config.yaml
🧰 Additional context used
📓 Path-based instructions (1)
**
⚙️ CodeRabbit configuration file
-Focus on major issues impacting performance, readability, maintainability and security. Avoid nitpicks and avoid verbosity.
Files:
bindata/network/ovn-kubernetes/common/008-script-lib.yamlpkg/network/ovn_kubernetes.gobindata/network/ovn-kubernetes/self-hosted/ovnkube-control-plane.yamlpkg/network/ovn_kubernetes_test.gobindata/network/ovn-kubernetes/common/001-crd.yamlbindata/network/ovn-kubernetes/managed/ovnkube-control-plane.yamlbindata/network/ovn-kubernetes/self-hosted/004-config.yaml
🔇 Additional comments (11)
bindata/network/ovn-kubernetes/common/008-script-lib.yaml (2)
625-629: Network-connect gating matches existing feature flags.
735-735: Flag is correctly wired into the ovnkube invocation.bindata/network/ovn-kubernetes/self-hosted/004-config.yaml (1)
55-57: Config template emits enable-network-connect under the gate.bindata/network/ovn-kubernetes/self-hosted/ovnkube-control-plane.yaml (2)
158-161: Network-connect flag initialization looks consistent.
213-213: Flag inclusion in ovnkube args is correct.pkg/network/ovn_kubernetes.go (1)
337-342: Feature gate is correctly surfaced into render data.bindata/network/ovn-kubernetes/managed/ovnkube-control-plane.yaml (2)
207-210: Network-connect flag definition is consistent with other gates.
256-256: Flag is correctly wired into the command line.pkg/network/ovn_kubernetes_test.go (3)
76-85: LGTM!The feature gate is correctly added to the disabled list with an appropriate comment indicating its DevPreview status.
971-978: LGTM!The feature gate is correctly added to
knownFeatureGatesin alphabetical order, ensuring proper test coverage for the NetworkConnect feature.
3869-3878: LGTM!Consistent with the default feature gates configuration, keeping NetworkConnect disabled when testing unrelated features.
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
| { | ||
| desc: "enable network connect (DevPreview)", | ||
| expected: ` | ||
| [default] | ||
| mtu="1500" | ||
| cluster-subnets="10.128.0.0/15/23,10.0.0.0/14/24" | ||
| encap-port="8061" | ||
| enable-lflow-cache=true | ||
| lflow-cache-limit-kb=1048576 | ||
| enable-udp-aggregation=true | ||
| udn-allowed-default-services="default/kubernetes,openshift-dns/dns-default" | ||
|
|
||
| [kubernetes] | ||
| service-cidrs="172.30.0.0/16" | ||
| ovn-config-namespace="openshift-ovn-kubernetes" | ||
| apiserver="https://testing.test:8443" | ||
| host-network-namespace="openshift-host-network" | ||
| platform-type="GCP" | ||
| healthz-bind-address="0.0.0.0:10256" | ||
| dns-service-namespace="openshift-dns" | ||
| dns-service-name="dns-default" | ||
|
|
||
| [ovnkubernetesfeature] | ||
| egressip-node-healthcheck-port=9107 | ||
| enable-network-segmentation=true | ||
| enable-network-connect=true | ||
|
|
||
| [gateway] | ||
| mode=shared | ||
| nodeport=true | ||
|
|
||
| [logging] | ||
| libovsdblogfile=/var/log/ovnkube/libovsdb.log | ||
| logfile-maxsize=100 | ||
| logfile-maxbackups=5 | ||
| logfile-maxage=0`, | ||
| enabledFeatureGates: []configv1.FeatureGateName{ | ||
| apifeatures.FeatureGateNetworkSegmentation, | ||
| apifeatures.FeatureGateNetworkConnect, | ||
| }, | ||
| }, |
There was a problem hiding this comment.
Missing controlPlaneReplicaCount field.
All other test cases in this table specify controlPlaneReplicaCount: 2 (or 1 for SNO scenarios). This test case omits it, defaulting to 0, which may not represent a valid cluster configuration.
💡 Proposed fix
{
desc: "enable network connect (DevPreview)",
expected: `
[default]
...
logfile-maxage=0`,
enabledFeatureGates: []configv1.FeatureGateName{
apifeatures.FeatureGateNetworkSegmentation,
apifeatures.FeatureGateNetworkConnect,
},
+ controlPlaneReplicaCount: 2,
},📝 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.
| { | |
| desc: "enable network connect (DevPreview)", | |
| expected: ` | |
| [default] | |
| mtu="1500" | |
| cluster-subnets="10.128.0.0/15/23,10.0.0.0/14/24" | |
| encap-port="8061" | |
| enable-lflow-cache=true | |
| lflow-cache-limit-kb=1048576 | |
| enable-udp-aggregation=true | |
| udn-allowed-default-services="default/kubernetes,openshift-dns/dns-default" | |
| [kubernetes] | |
| service-cidrs="172.30.0.0/16" | |
| ovn-config-namespace="openshift-ovn-kubernetes" | |
| apiserver="https://testing.test:8443" | |
| host-network-namespace="openshift-host-network" | |
| platform-type="GCP" | |
| healthz-bind-address="0.0.0.0:10256" | |
| dns-service-namespace="openshift-dns" | |
| dns-service-name="dns-default" | |
| [ovnkubernetesfeature] | |
| egressip-node-healthcheck-port=9107 | |
| enable-network-segmentation=true | |
| enable-network-connect=true | |
| [gateway] | |
| mode=shared | |
| nodeport=true | |
| [logging] | |
| libovsdblogfile=/var/log/ovnkube/libovsdb.log | |
| logfile-maxsize=100 | |
| logfile-maxbackups=5 | |
| logfile-maxage=0`, | |
| enabledFeatureGates: []configv1.FeatureGateName{ | |
| apifeatures.FeatureGateNetworkSegmentation, | |
| apifeatures.FeatureGateNetworkConnect, | |
| }, | |
| }, | |
| { | |
| desc: "enable network connect (DevPreview)", | |
| expected: ` | |
| [default] | |
| mtu="1500" | |
| cluster-subnets="10.128.0.0/15/23,10.0.0.0/14/24" | |
| encap-port="8061" | |
| enable-lflow-cache=true | |
| lflow-cache-limit-kb=1048576 | |
| enable-udp-aggregation=true | |
| udn-allowed-default-services="default/kubernetes,openshift-dns/dns-default" | |
| [kubernetes] | |
| service-cidrs="172.30.0.0/16" | |
| ovn-config-namespace="openshift-ovn-kubernetes" | |
| apiserver="https://testing.test:8443" | |
| host-network-namespace="openshift-host-network" | |
| platform-type="GCP" | |
| healthz-bind-address="0.0.0.0:10256" | |
| dns-service-namespace="openshift-dns" | |
| dns-service-name="dns-default" | |
| [ovnkubernetesfeature] | |
| egressip-node-healthcheck-port=9107 | |
| enable-network-segmentation=true | |
| enable-network-connect=true | |
| [gateway] | |
| mode=shared | |
| nodeport=true | |
| [logging] | |
| libovsdblogfile=/var/log/ovnkube/libovsdb.log | |
| logfile-maxsize=100 | |
| logfile-maxbackups=5 | |
| logfile-maxage=0`, | |
| enabledFeatureGates: []configv1.FeatureGateName{ | |
| apifeatures.FeatureGateNetworkSegmentation, | |
| apifeatures.FeatureGateNetworkConnect, | |
| }, | |
| controlPlaneReplicaCount: 2, | |
| }, |
🤖 Prompt for AI Agents
In `@pkg/network/ovn_kubernetes_test.go` around lines 880 - 920, The test case
with desc "enable network connect (DevPreview)" is missing the
controlPlaneReplicaCount field causing it to default to 0; update that table
entry to include controlPlaneReplicaCount (match other non-SNO tests by setting
controlPlaneReplicaCount: 2, or 1 if intended as SNO) so the cluster config used
by the test (and the expected output block) reflects a valid replica count;
locate the test case by its desc string and add the controlPlaneReplicaCount key
alongside enabledFeatureGates and expected.
fe79b4b to
aeb049c
Compare
|
/retest-required |
|
grrrrr huge conflict thanks to #2456 I guess I should be able to drop my first commit hopefully.. |
|
PR needs rebase. 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. |
aeb049c to
f750d26
Compare
f750d26 to
44c906b
Compare
There was a problem hiding this comment.
♻️ Duplicate comments (1)
bindata/network/ovn-kubernetes/common/001-crd.yaml (1)
5500-5531:⚠️ Potential issue | 🟠 MajorAllow
networkPrefix == CIDR prefixas documented.Line 5502 allows equality, but Line 5530 enforces strict
>, which rejects documented-valid configs.Suggested fix
- - message: NetworkPrefix must be smaller than CIDR subnet - rule: '!has(self.networkPrefix) || !isCIDR(self.cidr) || self.networkPrefix - > cidr(self.cidr).prefixLength()' + - message: NetworkPrefix must be equal to or longer than the CIDR prefix + rule: '!has(self.networkPrefix) || !isCIDR(self.cidr) || self.networkPrefix + >= cidr(self.cidr).prefixLength()'🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@bindata/network/ovn-kubernetes/common/001-crd.yaml` around lines 5500 - 5531, The x-kubernetes-validations rule currently rejects configurations where self.networkPrefix equals the CIDR prefix because it uses a strict '>' comparison; update the validation expression in the x-kubernetes-validations rule to allow equality by replacing the strict greater-than check with a greater-than-or-equal check (i.e., change the comparison involving self.networkPrefix and cidr(self.cidr).prefixLength() to use >=) so that self.networkPrefix == cidr(self.cidr).prefixLength() is accepted.
🧹 Nitpick comments (1)
bindata/network/ovn-kubernetes/common/001-crd.yaml (1)
5743-5750: KeepnetworkSelectionTypeenum consistent with allowed values.The enum advertises values (
DefaultNetwork,SecondaryUserDefinedNetworks,NetworkAttachmentDefinitions) that are always rejected by the top-level rule. This makes the API contract confusing for clients and users.As per coding guidelines, "Focus on major issues impacting performance, readability, maintainability and security. Avoid nitpicks and avoid verbosity."
Also applies to: 5950-5953
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@bindata/network/ovn-kubernetes/common/001-crd.yaml` around lines 5743 - 5750, The CRD's networkSelectionType enum includes values (DefaultNetwork, SecondaryUserDefinedNetworks, NetworkAttachmentDefinitions) that are impossible under the top-level validation rule; update the enum to only list allowed values to keep the API contract consistent: locate the networkSelectionType field in the CRD (search for "networkSelectionType" and the enum block shown) and remove any enum entries that are rejected by the top-level rule or adjust the top-level rule to accept those values if intended (ensure the enum and the top-level validation rule are aligned so only permitted values remain).
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Duplicate comments:
In `@bindata/network/ovn-kubernetes/common/001-crd.yaml`:
- Around line 5500-5531: The x-kubernetes-validations rule currently rejects
configurations where self.networkPrefix equals the CIDR prefix because it uses a
strict '>' comparison; update the validation expression in the
x-kubernetes-validations rule to allow equality by replacing the strict
greater-than check with a greater-than-or-equal check (i.e., change the
comparison involving self.networkPrefix and cidr(self.cidr).prefixLength() to
use >=) so that self.networkPrefix == cidr(self.cidr).prefixLength() is
accepted.
---
Nitpick comments:
In `@bindata/network/ovn-kubernetes/common/001-crd.yaml`:
- Around line 5743-5750: The CRD's networkSelectionType enum includes values
(DefaultNetwork, SecondaryUserDefinedNetworks, NetworkAttachmentDefinitions)
that are impossible under the top-level validation rule; update the enum to only
list allowed values to keep the API contract consistent: locate the
networkSelectionType field in the CRD (search for "networkSelectionType" and the
enum block shown) and remove any enum entries that are rejected by the top-level
rule or adjust the top-level rule to accept those values if intended (ensure the
enum and the top-level validation rule are aligned so only permitted values
remain).
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 2be86cdd-8f98-43be-a296-aef0db14e87e
📒 Files selected for processing (10)
bindata/network/ovn-kubernetes/common/001-crd.yamlbindata/network/ovn-kubernetes/common/008-script-lib.yamlbindata/network/ovn-kubernetes/managed/004-config.yamlbindata/network/ovn-kubernetes/managed/ovnkube-control-plane.yamlbindata/network/ovn-kubernetes/self-hosted/004-config.yamlbindata/network/ovn-kubernetes/self-hosted/ovnkube-control-plane.yamlpkg/network/cluster_config_test.gopkg/network/ovn_kubernetes.gopkg/network/ovn_kubernetes_test.gopkg/network/render_test.go
🚧 Files skipped from review as they are similar to previous changes (5)
- pkg/network/cluster_config_test.go
- bindata/network/ovn-kubernetes/self-hosted/004-config.yaml
- bindata/network/ovn-kubernetes/common/008-script-lib.yaml
- bindata/network/ovn-kubernetes/managed/004-config.yaml
- pkg/network/ovn_kubernetes_test.go
|
Were you able to do a sanity check on a live cluster? DevPreview is not something we cover in CI. |
5d49430 to
aec03ba
Compare
c91a924 to
c60357b
Compare
YAML was copied from https://github.com/ovn-kubernetes/ovn-kubernetes/blob/master/dist/templates/k8s.ovn.org_clusternetworkconnects.yaml.j2 Signed-off-by: Surya Seetharaman <suryaseetharaman.9@gmail.com>
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: kyrtapz, tssurya The full list of commands accepted by this bot can be found here. The pull request process is described here DetailsNeeds approval from an approver in each of these files:
Approvers can indicate their approval by writing |
|
/verified |
|
@tssurya: The 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. |
|
/verified by manual testing |
|
@tssurya: This PR has been marked as verified by 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. |
|
/tide refresh |
|
/retest-failed |
|
/retest |
|
override ci/prow/e2e-metal-ipi-ovn-dualstack-bgp-local-gw https://prow.ci.openshift.org/view/gs/test-platform-results/pr-logs/pull/openshift_cluster-network-operator/2880/pull-ci-openshift-cluster-network-operator-master-e2e-metal-ipi-ovn-dualstack-bgp/2037795043955183616 and https://prow.ci.openshift.org/view/gs/test-platform-results/pr-logs/pull/openshift_cluster-network-operator/2880/pull-ci-openshift-cluster-network-operator-master-e2e-metal-ipi-ovn-dualstack-bgp-local-gw/2037795044001320960 are failing because of https://redhat.atlassian.net/browse/OCPBUGS-78053 |
|
@tssurya: Overrode contexts on behalf of tssurya: ci/prow/e2e-metal-ipi-ovn-dualstack-bgp 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. |
|
/override ci/prow/e2e-metal-ipi-ovn-dualstack-bgp-local-gw |
|
@tssurya: Overrode contexts on behalf of tssurya: ci/prow/e2e-metal-ipi-ovn-dualstack-bgp-local-gw 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. |
|
/tide refresh |
|
/test hypershift-e2e-aks |
|
/test 4.22-upgrade-from-stable-4.21-e2e-azure-ovn-upgrade |
|
/tide refresh |
|
/test hyoershift-e2e-aks |
|
/test hypershift-e2e-aks |
|
@tssurya: 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. |
|
/override ci/prow/hypershift-e2e-aks hypershift AKS job has 3 failures so far:
the first two links show: totally unrelated to a DevPreview FG activation that this PR is doing the last attempt gets closer: just had 1 restart but eventually came up.. so that's in CVO land I have no idea why CVO is crashing?! but regardless my PR has no effect on GA clusters and is purely a DevPreview change. I can't keep retesting this lane since its pencils down time so overriding this |
|
@tssurya: Overrode contexts on behalf of tssurya: ci/prow/hypershift-e2e-aks 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. |
|
/tide refresh |
|
/shrug |
|
/skip |
Consumes openshift/api#2629