Sync odh-2.12 (#1011)

* Update version to v2.12.0 (#1007)

* upgrade: retry if default DSCI creation fails (#1008)

After removing leader election, operator fails to start if it is
instructed to create default DSCI. Looks like webhook is not ready
by the time:

```
create default DSCI CR.
{"level":"error","ts":"2024-05-13T09:25:58Z","logger":"setup","msg":"unable to create initial setup for the operator","error":"Internal error occurred: failed calling webhook \"operator.opendatahub.io\": failed to call webhook: Post \"https://opendatahub-operator-controller-manager-service.oo-2ts9m.svc:443/validate-opendatahub-io-v1?timeout=10s\": no endpoints available for service \"opendatahub-operator-controller-manager-service\"","stacktrace":"main.main.func1\n\t/workspace/main.go:200\nsigs.k8s.io/controller-runtime/pkg/manager.RunnableFunc.Start\n\t/remote-source/operator/deps/gomod/pkg/mod/sigs.k8s.io/controller-runtime@v0.14.6/pkg/manager/manager.go:336\nsigs.k8s.io/controller-runtime/pkg/manager.(*runnableGroup).reconcile.func1\n\t/remote-source/operator/deps/gomod/pkg/mod/sigs.k8s.io/controller-runtime@v0.14.6/pkg/manager/runnable_group.go:219"}
```
Leader election added some delay.

The problem does not happen in default configuration since it
explicitly disables DSCI creation in the manifests:

```
       containers:
       - command:
         - /manager
         env:
           - name: DISABLE_DSC_CONFIG
             value: 'true'
         args:
         - --operator-name=opendatahub
         image: controller:latest
```

Make a wrapper function cluster.CreateWithRetry for client.Object
creation with timeout. Use hardcoded 5s interval, just seems
reasonable, and timeout in minutes as the parameter.

It requires disable linter nilerr since for the polling function
error in creation is a valid condition, something the function wait
to disappear.

Fixes: 3610b0b ("feat: remove leader election for operator (#1000)")

Signed-off-by: Yauheni Kaliuta <ykaliuta@redhat.com>

---------

Signed-off-by: Yauheni Kaliuta <ykaliuta@redhat.com>
Co-authored-by: Yauheni Kaliuta <ykaliuta@redhat.com>

Makefile

@@ -3,7 +3,7 @@
 # To re-generate a bundle for another specific version without changing the standard setup, you can:
 # - use the VERSION as arg of the bundle target (e.g make bundle VERSION=0.0.2)
 # - use environment variables to overwrite this value (e.g export VERSION=0.0.2)
-VERSION ?= 2.10.1
+VERSION ?= 2.12.0
 # IMAGE_TAG_BASE defines the opendatahub.io namespace and part of the image name for remote images.
 # This variable is used to construct full image tags for bundle and catalog images.
 #

bundle/manifests/opendatahub-operator.clusterserviceversion.yaml

@@ -101,14 +101,14 @@ metadata:
     capabilities: Full Lifecycle
     categories: AI/Machine Learning, Big Data
     certified: "False"
-    containerImage: quay.io/opendatahub/opendatahub-operator:v2.10.0
+    containerImage: quay.io/opendatahub/opendatahub-operator:v2.12.0
     createdAt: "2024-4-22T00:00:00Z"
-    olm.skipRange: '>=1.0.0 <2.11.0'
+    olm.skipRange: '>=1.0.0 <2.12.0'
     operators.operatorframework.io/builder: operator-sdk-v1.24.1
     operators.operatorframework.io/internal-objects: '[dscinitialization.opendatahub.io]'
     operators.operatorframework.io/project_layout: go.kubebuilder.io/v3
     repository: https://github.com/opendatahub-io/opendatahub-operator
-  name: opendatahub-operator.v2.10.1
+  name: opendatahub-operator.v2.12.0
   namespace: placeholder
 spec:
   apiservicedefinitions: {}
@@ -1763,7 +1763,7 @@ spec:
   selector:
     matchLabels:
       component: opendatahub-operator
-  version: 2.10.1
+  version: 2.12.0
   webhookdefinitions:
   - admissionReviewVersions:
     - v1

config/manifests/bases/opendatahub-operator.clusterserviceversion.yaml

@@ -6,12 +6,12 @@ metadata:
     capabilities: Full Lifecycle
     categories: AI/Machine Learning, Big Data
     certified: "False"
-    containerImage: quay.io/opendatahub/opendatahub-operator:v2.10.0
+    containerImage: quay.io/opendatahub/opendatahub-operator:v2.12.0
     createdAt: "2024-4-22T00:00:00Z"
-    olm.skipRange: '>=1.0.0 <2.11.0'
+    olm.skipRange: '>=1.0.0 <2.12.0'
     operators.operatorframework.io/internal-objects: '[dscinitialization.opendatahub.io]'
     repository: https://github.com/opendatahub-io/opendatahub-operator
-  name: opendatahub-operator.v2.11.0
+  name: opendatahub-operator.v2.12.0
   namespace: placeholder
 spec:
   apiservicedefinitions: {}
@@ -105,4 +105,4 @@ spec:
   selector:
     matchLabels:
       component: opendatahub-operator
-  version: 2.11.0
+  version: 2.12.0

pkg/cluster/resources.go

@@ -174,3 +174,16 @@ func WaitForDeploymentAvailable(ctx context.Context, c client.Client, componentN
 		return true, nil
 	})
 }
+
+func CreateWithRetry(ctx context.Context, cli client.Client, obj client.Object, timeoutMin int) error {
+	interval := time.Second * 5 // arbitrary value
+	timeout := time.Duration(timeoutMin) * time.Minute
+
+	return wait.PollUntilContextTimeout(ctx, interval, timeout, true, func(ctx context.Context) (bool, error) {
+		err := cli.Create(ctx, obj)
+		if err != nil {
+			return false, nil //nolint:nilerr
+		}
+		return true, nil
+	})
+}

pkg/upgrade/upgrade.go

@@ -166,7 +166,7 @@ func CreateDefaultDSCI(ctx context.Context, cli client.Client, _ cluster.Platfor
 		return nil
 	case len(instances.Items) == 0:
 		fmt.Println("create default DSCI CR.")
-		err := cli.Create(ctx, defaultDsci)
+		err := cluster.CreateWithRetry(ctx, cli, defaultDsci, 1) // 1 min timeout
 		if err != nil {
 			return err
 		}