Update incubation with downstream changes (red-hat-data-services#783)

* fix(oauth-dashboard): update APIversion when patch oauth-client (red-hat-data-services#136) add more comment and error message Signed-off-by: Wen Zhou <wenzhou@redhat.com> (cherry picked from commit d688f25) * Update kube-aggregator version (cherry picked from commit a0c7864) * fix(kserve): check on multiple depends operators if all pre-installed (red-hat-data-services#744) (red-hat-data-services#119) Signed-off-by: Wen Zhou <wenzhou@redhat.com> (cherry picked from commit 57c4b82) * [backport]: changes from rhods_2.4 to rhods_2.5 (red-hat-data-services#129) * [cherry-pick]: split workbenches image into 2 params.env file Signed-off-by: Wen Zhou <wenzhou@redhat.com> * Update opendatahub label (cherry picked from commit 3e975f9) (cherry picked from commit 9f8b649) * Update Codeflare manifests path (cherry picked from commit 014396c) (cherry picked from commit 5f1c0d4) * Move creation of default DSC (cherry picked from commit ab33109) (cherry picked from commit 00ddd6c) * update(manifests): enable kserve, modelmesh and workbenches - dashboard and modelmesh-monitoring still from odh-manifests Signed-off-by: Wen Zhou <wenzhou@redhat.com> * Fix cherry-pick for dsci * fix(mm): set the new logic for modelmesh Signed-off-by: Wen Zhou <wenzhou@redhat.com> * Fix the KF deployment: * fix(monitoring): do the switch for dev mode to not send alert Signed-off-by: Wen Zhou <wenzhou@redhat.com> (cherry picked from commit 001cad1) * refactor: reduce alert level for codeflare operator * Update(manifests): for monitoring - remove https:// for dashbaord target - add nwp from odh-deployer - fix: wrong service name for operator, this is defined in CSV - port: do not use https but 8080 Signed-off-by: Wen Zhou <wenzhou@redhat.com> * Fix manifests for monitoring (cherry picked from commit 85883f102bc15f2343c0f6afe253a29a4ff3f64f) * Revert changes to prometheus port Changes to prometheus port makes the route inaccessible * fix rebase * fix(dsci): missing label on namespaces (red-hat-data-services#98) - add SM which is in modelmesh-monitroing into operator monitoring - add roles which are in modelmesh-monitoring into ours too - apply 3 labels to both monitoring and application namespace (which is v1 doing) Signed-off-by: Wen Zhou <wenzhou@redhat.com> * fix(monitoring): typo (red-hat-data-services#101) Signed-off-by: Wen Zhou <wenzhou@redhat.com> * update(monitoring) - remove hardcoded app. namespace in segment manifests - remove hardcoded monitoring. namepsace in base manifests - add placeholder to inject monitoring namespace in Servicemonitor Signed-off-by: Wen Zhou <wenzhou@redhat.com> * uplift: package version - github.com/operator-framework/operator-lifecycle-manager/releases/tag/v0.26.0 - github.com/openshift/api to latest v0.0.0 Signed-off-by: Wen Zhou <wenzhou@redhat.com> * Remove odh csv * fix(crd): do not set ownerreference on CRD (red-hat-data-services#725) - we covered the case when set component from Managed to Remvoe - this is to cover the case when set have component as Managed and delete DSC CR - so if we do not set at first it wont get deleted Signed-off-by: Wen Zhou <wenzhou@redhat.com> (cherry picked from commit e9461e0) * Fix DSCI Patch * update(monitoring): metrics (red-hat-data-services#107) * update(monitoring): - add log in pod for QE to see it is dev mode cluster - add two metrics: i do not think they are used in this config but they are presented in v1 config , so i add back - move recording for workbench to correct rule file - remove operator-alerting.rules it is not used in v1 to keep it simple - fix: openshift-monitoring is using web as port name and our port - add more comments for the config and comments out not needed config - add egress for odh monitoring and add cluster monitoring NS for ingress - keep rhdos_aggerate_avaiablity from proemtehusrules along with 2 users reason for this is: PSI does not get non openshift-* or kube-* NS metrics to cluster-monitoring prometheus. as cluster-monitoring prometheus-k8s only use prometheusrule not serivcemonitor ? - from test result: if our monitoring ns not set cluster-monitoring, there is no targets on federation2 and no rhods_aggreated_in metrics - fix(monitoring): removed duplicated alerts of dashboard in workbenches - add UWM ns for operator ingress - according to doc: when enable UWM should not have custom Prometheus, this might be the conflicts why we cannot see metrics from odh monitoring in cluster-monitoring prometheus? Signed-off-by: Wen Zhou <wenzhou@redhat.com> * Remove DSCI explicit naming * Fix regression in Prometheus Deployment * Remove os.exit for custom functions * Delete legacy blackbox exporter * fix(monitoring): add missing role and rolebinding for prometheus (red-hat-data-services#112) Signed-off-by: Wen Zhou <wenzhou@redhat.com> * fix(monitoring): missing add new files into kustomization (red-hat-data-services#113) Signed-off-by: Wen Zhou <wenzhou@redhat.com> * cleanup(monitoring): after previous 2 commits this is not needed/useful (red-hat-data-services#114) Signed-off-by: Wen Zhou <wenzhou@redhat.com> * fix(monitoring): do not set odh monitoring namespace when apply for manifests in "monitoring/base" (red-hat-data-services#115) * fix(monitoring): not set our monitoring when apply to monitoring/base folder - hardcode our monitoring namespace for all needed manifests Signed-off-by: Wen Zhou <wenzhou@redhat.com> * revert: label changes made in upgrade PR Signed-off-by: Wen Zhou <wenzhou@redhat.com> * fix(monitoring): cannot load dashbaord record rules (red-hat-data-services#123) Signed-off-by: Wen Zhou <wenzhou@redhat.com> * fix(monitoring): when DSC is removed entry in rule_files should be cleanedup - match does not work with * in the string need to use (.*) - add (-) in the front for diffientiate the rule_file or the real rules Signed-off-by: Wen Zhou <wenzhou@redhat.com> * cherry-pick: edson's rhods-12939 from odh + debug + timeout tuning comnent out ExpointialBackoffWithContext for now to test not add v2 into markedDeletion list Signed-off-by: Wen Zhou <wenzhou@redhat.com> * fix(upgrade): modelmesh monitoring deployment need deletion as well Signed-off-by: Wen Zhou <wenzhou@redhat.com> * fix: add statefulset Signed-off-by: Wen Zhou <wenzhou@redhat.com> * cherrypick: upstream 748 fix no reconcile when no error return Signed-off-by: Wen Zhou <wenzhou@redhat.com> * RHODS-12956: removing CR update from the operator reconciliation loop to avoid infinite loop (red-hat-data-services#128) * chore Signed-off-by: Wen Zhou <wenzhou@redhat.com> --------- Signed-off-by: Wen Zhou <wenzhou@redhat.com> Co-authored-by: Vaishnavi Hire <vhire@redhat.com> Co-authored-by: Dimitri Saridakis <dimitri.saridakis@gmail.com> Co-authored-by: Edson Tirelli <ed.tirelli@gmail.com> (cherry picked from commit 81ebc87) (cherry picked from commit 7525f99) * fix(rebase): in previous commits (red-hat-data-services#131) Signed-off-by: Wen Zhou <wenzhou@redhat.com> (cherry picked from commit 15b2db8) (cherry picked from commit 0062ba3) * [rhods-2.5] Add Predicate for Prometheus Configmap (red-hat-data-services#134) * Add Predicate for Prometheus Configmap (cherry picked from commit 35f4136) * fix(linter) Signed-off-by: Wen Zhou <wenzhou@redhat.com> --------- Signed-off-by: Wen Zhou <wenzhou@redhat.com> Co-authored-by: Wen Zhou <wenzhou@redhat.com> (cherry picked from commit 6ecf2b5) (cherry picked from commit deeccb7) * fix(monitoring): only set prometheus as part-of label from component (red-hat-data-services#135) this will reduced necessary updates on configmap Signed-off-by: Wen Zhou <wenzhou@redhat.com> (cherry picked from commit 13c28ec) (cherry picked from commit b809260) * update: set kserve as Managed by default DSC (red-hat-data-services#130) - keep modelmesh in clean install removed(flip from previous managed) - keep modelmesh from old version as-was set OSSM and serving both as default Managaed - update docs with default status and missing new components - fix nilpointer in DSCI Signed-off-by: Wen Zhou <wenzhou@redhat.com> (cherry picked from commit f7c2713) (cherry picked from commit 4f3cd66) * fix(monitoring): do not add component rules till service is up (red-hat-data-services#137) Signed-off-by: Wen Zhou <wenzhou@redhat.com> (cherry picked from commit d85efc5) (cherry picked from commit 8cca478) * fix(secret): do not delete secret if cannot find (red-hat-data-services#140) Signed-off-by: Wen Zhou <wenzhou@redhat.com> (cherry picked from commit 60f0419) (cherry picked from commit 5e3731b) * chore: typo (red-hat-data-services#141) Signed-off-by: Wen Zhou <wenzhou@redhat.com> (cherry picked from commit 0f9fe32) (cherry picked from commit b8926f7) * Add defaults for Kserve for new install (cherry picked from commit 8bd2782) (cherry picked from commit 81433ba) * Revert "Update defaults for modelmesh" (red-hat-data-services#146) (cherry picked from commit e5a27c4) (cherry picked from commit 7389619) * fix(mm-monitoring): revert the code logic but set to disable as delete (red-hat-data-services#153) Signed-off-by: Wen Zhou <wenzhou@redhat.com> fix(dsc): stop watching validationwebhook for non-create/delete events (red-hat-data-services#150) * fix(dsc): stop watching validationwebhook for non-create/delete events * update: remove CRD in the DSC watch and cleanup debug * fix: add more ignore on the label changes --------- Signed-off-by: Wen Zhou <wenzhou@redhat.com> Revert "Remove modelmesh monitoring" This reverts commit 91dd78f. fix(modelmesh): remove wrong check on the deployment of modelmesh (red-hat-data-services#148) Signed-off-by: Wen Zhou <wenzhou@redhat.com> Retain existing DSCI values Explicilty add Servicemesh in default dsci Update defaults for modelmesh (cherry picked from commit 6eb6d4a) (cherry picked from commit a4788f3) * fix: update default name for DSC in initialization-resource - add missing default config for serving of kserve in sample - set modelmesh in sample and init as Managed Signed-off-by: Wen Zhou <wenzhou@redhat.com> (cherry picked from commit 633d9f6) * fix: do not force check if servicemesh is set to managed in DSCI (red-hat-data-services#154) * fix: do not force check if servicemesh is set to managed in DSCI Signed-off-by: Wen Zhou <wenzhou@redhat.com> * update: add supported value for serverless and servicemesh - currently removed and unmanaged are the same logic Signed-off-by: Wen Zhou <wenzhou@redhat.com> * update: do not remove resources if it has label Signed-off-by: Wen Zhou <wenzhou@redhat.com> --------- Signed-off-by: Wen Zhou <wenzhou@redhat.com> (cherry picked from commit 3a672d4) * Fix lint * fix: rebase incubation Signed-off-by: Wen Zhou <wenzhou@redhat.com> * cherry-pick: red-hat-data-services#157 Signed-off-by: Wen Zhou <wenzhou@redhat.com> * fix: for ODH to resolve https://issues.redhat.com/browse/RHOAIENG-157 Signed-off-by: Wen Zhou <wenzhou@redhat.com> * update: CSV Signed-off-by: Wen Zhou <wenzhou@redhat.com> * fix: linter Signed-off-by: Wen Zhou <wenzhou@redhat.com> --------- Signed-off-by: Wen Zhou <wenzhou@redhat.com> Co-authored-by: Wen Zhou <wenzhou@redhat.com>
biswassri · Dec 12, 2023 · f756e40 · f756e40
1 parent 42b2bdd
commit f756e40
Show file tree

Hide file tree

Showing 38 changed files with 693 additions and 1,579 deletions.
diff --git a/Makefile b/Makefile
@@ -162,7 +162,7 @@ run: manifests generate fmt vet ## Run a controller from your host.
 	go run ./main.go
 
 .PHONY: image-build
-image-build: unit-test ## Build image with the manager.
+image-build: # unit-test ## Build image with the manager.
 	$(IMAGE_BUILDER) build --no-cache -f Dockerfiles/Dockerfile  ${IMAGE_BUILD_FLAGS} -t $(IMG) .
 
 .PHONY: image-push

diff --git a/README.md b/README.md
@@ -225,6 +225,8 @@ spec:
       managementState: Managed
     workbenches:
       managementState: Managed
+    trustyai:
+      managementState: Managed
 ```
 
 2. Enable only Dashboard and Workbenches

diff --git a/bundle/manifests/datasciencecluster.opendatahub.io_datascienceclusters.yaml b/bundle/manifests/datasciencecluster.opendatahub.io_datascienceclusters.yaml
@@ -262,9 +262,10 @@ spec:
                                 type: string
                             type: object
                           managementState:
-                            default: Removed
+                            default: Managed
                             enum:
                             - Managed
+                            - Unmanaged
                             - Removed
                             pattern: ^(Managed|Unmanaged|Force|Removed)$
                             type: string

diff --git a/bundle/manifests/dscinitialization.opendatahub.io_dscinitializations.yaml b/bundle/manifests/dscinitialization.opendatahub.io_dscinitializations.yaml
@@ -118,6 +118,7 @@ spec:
                     default: Removed
                     enum:
                     - Managed
+                    - Unmanaged
                     - Removed
                     pattern: ^(Managed|Unmanaged|Force|Removed)$
                     type: string

diff --git a/bundle/manifests/opendatahub-operator.clusterserviceversion.yaml b/bundle/manifests/opendatahub-operator.clusterserviceversion.yaml
@@ -29,7 +29,16 @@ metadata:
                 "managementState": "Managed"
               },
               "kserve": {
-                "managementState": "Removed"
+                "managementState": "Managed",
+                "serving": {
+                  "ingressGateway": {
+                    "certificate": {
+                      "type": "SelfSigned"
+                    }
+                  },
+                  "managementState": "Managed",
+                  "name": "knative-serving"
+                }
               },
               "modelmeshserving": {
                 "managementState": "Managed"
@@ -64,6 +73,14 @@ metadata:
             "monitoring": {
               "managementState": "Managed",
               "namespace": "opendatahub"
+            },
+            "serviceMesh": {
+              "controlPlane": {
+                "metricsCollection": "Istio",
+                "name": "data-science-smcp",
+                "namespace": "istio-system"
+              },
+              "managementState": "Managed"
             }
           }
         },

diff --git a/components/README.md b/components/README.md
@@ -36,6 +36,8 @@ can be found [here](https://github.com/opendatahub-io/opendatahub-operator/tree/
       GetComponentName() string
       GetManagementState() operatorv1.ManagementState
       SetImageParamsMap(imageMap map[string]string) map[string]string
+      UpdatePrometheusConfig(cli client.Client, enable bool, component string) error
+      WaitForDeploymentAvailable(ctx context.Context, r *rest.Config, c string, n string, i int, t int) error
     }
     ```
 ### Add reconcile and Events

diff --git a/components/codeflare/codeflare.go b/components/codeflare/codeflare.go
@@ -3,16 +3,19 @@
 package codeflare
 
 import (
+	"context"
 	"fmt"
 	"path/filepath"
 
 	operatorv1 "github.com/openshift/api/operator/v1"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/client-go/rest"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 
 	dsciv1 "github.com/opendatahub-io/opendatahub-operator/v2/apis/dscinitialization/v1"
 	"github.com/opendatahub-io/opendatahub-operator/v2/components"
 	"github.com/opendatahub-io/opendatahub-operator/v2/pkg/deploy"
+	"github.com/opendatahub-io/opendatahub-operator/v2/pkg/monitoring"
 )
 
 var (
@@ -53,7 +56,7 @@ func (c *CodeFlare) GetComponentName() string {
 	return ComponentName
 }
 
-func (c *CodeFlare) ReconcileComponent(cli client.Client, owner metav1.Object, dscispec *dsciv1.DSCInitializationSpec, _ bool) error {
+func (c *CodeFlare) ReconcileComponent(ctx context.Context, cli client.Client, resConf *rest.Config, owner metav1.Object, dscispec *dsciv1.DSCInitializationSpec, _ bool) error {
 	var imageParamMap = map[string]string{
 		"odh-codeflare-operator-controller-image": "RELATED_IMAGE_ODH_CODEFLARE_OPERATOR_IMAGE", // no need mcad, embedded in cfo
 		"namespace": dscispec.ApplicationsNamespace,
@@ -78,7 +81,7 @@ func (c *CodeFlare) ReconcileComponent(cli client.Client, owner metav1.Object, d
 		}
 
 		if found, err := deploy.OperatorExists(cli, dependentOperator); err != nil {
-			return err
+			return fmt.Errorf("operator exists throws error %v", err)
 		} else if found {
 			return fmt.Errorf("operator %s is found. Please uninstall the operator before enabling %s component",
 				dependentOperator, ComponentName)
@@ -102,14 +105,22 @@ func (c *CodeFlare) ReconcileComponent(cli client.Client, owner metav1.Object, d
 
 	// CloudServiceMonitoring handling
 	if platform == deploy.ManagedRhods {
+		if enabled {
+			// first check if the service is up, so prometheus wont fire alerts when it is just startup
+			if err := monitoring.WaitForDeploymentAvailable(ctx, resConf, ComponentName, dscispec.ApplicationsNamespace, 20, 2); err != nil {
+				return fmt.Errorf("deployment for %s is not ready to server: %w", ComponentName, err)
+			}
+			fmt.Printf("deployment for %s is done, updating monitoring rules\n", ComponentName)
+		}
+
 		// inject prometheus codeflare*.rules in to /opt/manifests/monitoring/prometheus/prometheus-configs.yaml
 		if err = c.UpdatePrometheusConfig(cli, enabled && monitoringEnabled, ComponentName); err != nil {
 			return err
 		}
 		if err = deploy.DeployManifestsFromPath(cli, owner,
 			filepath.Join(deploy.DefaultManifestPath, "monitoring", "prometheus", "apps"),
 			dscispec.Monitoring.Namespace,
-			ComponentName+"prometheus", true); err != nil {
+			"prometheus", true); err != nil {
 			return err
 		}
 	}

diff --git a/components/component.go b/components/component.go
@@ -1,6 +1,7 @@
 package components
 
 import (
+	"context"
 	"fmt"
 	"os"
 	"path/filepath"
@@ -9,6 +10,7 @@ import (
 	operatorv1 "github.com/openshift/api/operator/v1"
 	"gopkg.in/yaml.v2"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/client-go/rest"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 
 	dsciv1 "github.com/opendatahub-io/opendatahub-operator/v2/apis/dscinitialization/v1"
@@ -78,13 +80,14 @@ type ManifestsConfig struct {
 }
 
 type ComponentInterface interface {
-	ReconcileComponent(cli client.Client, owner metav1.Object, DSCISpec *dsciv1.DSCInitializationSpec, currentComponentStatus bool) error
+	ReconcileComponent(ctx context.Context, cli client.Client, resConf *rest.Config, owner metav1.Object, DSCISpec *dsciv1.DSCInitializationSpec, currentComponentStatus bool) error
 	Cleanup(cli client.Client, DSCISpec *dsciv1.DSCInitializationSpec) error
 	GetComponentName() string
 	GetManagementState() operatorv1.ManagementState
 	SetImageParamsMap(imageMap map[string]string) map[string]string
 	OverrideManifests(platform string) error
 	UpdatePrometheusConfig(cli client.Client, enable bool, component string) error
+	// WaitForDeploymentAvailable(ctx context.Context, r *rest.Config, c string, n string, i int, t int) error
 }
 
 // UpdatePrometheusConfig update prometheus-configs.yaml to include/exclude <component>.rules
@@ -106,7 +109,7 @@ func (c *Component) UpdatePrometheusConfig(_ client.Client, enable bool, compone
 			DeadManSnitchRules string `yaml:"deadmanssnitch-alerting.rules"`
 			CFRRules           string `yaml:"codeflare-recording.rules"`
 			CRARules           string `yaml:"codeflare-alerting.rules"`
-			DashboardRRules    string `yaml:"rhods-dashboard-recording.rule"`
+			DashboardRRules    string `yaml:"rhods-dashboard-recording.rules"`
 			DashboardARules    string `yaml:"rhods-dashboard-alerting.rules"`
 			DSPRRules          string `yaml:"data-science-pipelines-operator-recording.rules"`
 			DSPARules          string `yaml:"data-science-pipelines-operator-alerting.rules"`
@@ -181,3 +184,34 @@ func (c *Component) UpdatePrometheusConfig(_ client.Client, enable bool, compone
 
 	return err
 }
+
+// WaitForDeploymentAvailable to check if component deployment from 'namepsace' is ready within 'timeout' before apply prometheus rules for the component
+// func (c *Component) WaitForDeploymentAvailable(ctx context.Context, restConfig *rest.Config, componentName string, namespace string, interval int, timeout int) error {
+// 	resourceInterval := time.Duration(interval) * time.Second
+// 	resourceTimeout := time.Duration(timeout) * time.Minute
+// 	return wait.PollUntilContextTimeout(context.TODO(), resourceInterval, resourceTimeout, true, func(ctx context.Context) (bool, error) {
+// 		clientset, err := kubernetes.NewForConfig(restConfig)
+// 		if err != nil {
+// 			return false, fmt.Errorf("error getting client %w", err)
+// 		}
+// 		componentDeploymentList, err := clientset.AppsV1().Deployments(namespace).List(context.TODO(), metav1.ListOptions{
+// 			LabelSelector: "app.opendatahub.io/" + componentName,
+// 		})
+// 		if err != nil {
+// 			if errors.IsNotFound(err) {
+// 				return false, nil
+// 			}
+// 		}
+// 		isReady := false
+// 		if len(componentDeploymentList.Items) != 0 {
+// 			for _, deployment := range componentDeploymentList.Items {
+// 				if deployment.Status.ReadyReplicas == deployment.Status.Replicas {
+// 					isReady = true
+// 				} else {
+// 					isReady = false
+// 				}
+// 			}
+// 		}
+// 		return isReady, nil
+// 	})
+// }
diff --git a/components/dashboard/dashboard.go b/components/dashboard/dashboard.go
@@ -13,13 +13,15 @@ import (
 	v1 "k8s.io/api/core/v1"
 	apierrs "k8s.io/apimachinery/pkg/api/errors"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/client-go/rest"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 
 	dsciv1 "github.com/opendatahub-io/opendatahub-operator/v2/apis/dscinitialization/v1"
 	"github.com/opendatahub-io/opendatahub-operator/v2/components"
 	"github.com/opendatahub-io/opendatahub-operator/v2/pkg/cluster"
 	"github.com/opendatahub-io/opendatahub-operator/v2/pkg/common"
 	"github.com/opendatahub-io/opendatahub-operator/v2/pkg/deploy"
+	"github.com/opendatahub-io/opendatahub-operator/v2/pkg/monitoring"
 )
 
 var (
@@ -78,7 +80,13 @@ func (d *Dashboard) GetComponentName() string {
 }
 
 //nolint:gocyclo
-func (d *Dashboard) ReconcileComponent(cli client.Client, owner metav1.Object, dscispec *dsciv1.DSCInitializationSpec, currentComponentStatus bool) error {
+func (d *Dashboard) ReconcileComponent(ctx context.Context,
+	cli client.Client,
+	resConf *rest.Config,
+	owner metav1.Object,
+	dscispec *dsciv1.DSCInitializationSpec,
+	currentComponentExist bool,
+) error {
 	var imageParamMap = map[string]string{
 		"odh-dashboard-image": "RELATED_IMAGE_ODH_DASHBOARD_IMAGE",
 	}
@@ -92,9 +100,11 @@ func (d *Dashboard) ReconcileComponent(cli client.Client, owner metav1.Object, d
 
 	// Update Default rolebinding
 	if enabled {
-		if err := d.cleanOauthClientSecrets(cli, dscispec, currentComponentStatus); err != nil {
+		// cleanup OAuth client related secret and CR if dashboard is in 'installed falas' status
+		if err := d.cleanOauthClient(cli, dscispec, currentComponentExist); err != nil {
 			return err
 		}
+
 		// Download manifests and update paths
 		if err := d.OverrideManifests(string(platform)); err != nil {
 			return err
@@ -162,13 +172,21 @@ func (d *Dashboard) ReconcileComponent(cli client.Client, owner metav1.Object, d
 		}
 		// CloudService Monitoring handling
 		if platform == deploy.ManagedRhods {
+			if enabled {
+				// first check if the service is up, so prometheus wont fire alerts when it is just startup
+				if err := monitoring.WaitForDeploymentAvailable(ctx, resConf, ComponentNameSupported, dscispec.ApplicationsNamespace, 20, 3); err != nil {
+					return fmt.Errorf("deployment for %s is not ready to server: %w", ComponentName, err)
+				}
+				fmt.Printf("deployment for %s is done, updating monitoring rules\n", ComponentNameSupported)
+			}
+
 			if err := d.UpdatePrometheusConfig(cli, enabled && monitoringEnabled, ComponentNameSupported); err != nil {
 				return err
 			}
 			if err = deploy.DeployManifestsFromPath(cli, owner,
 				filepath.Join(deploy.DefaultManifestPath, "monitoring", "prometheus", "apps"),
 				dscispec.Monitoring.Namespace,
-				ComponentName+"prometheus", true); err != nil {
+				"prometheus", true); err != nil {
 				return err
 			}
 		}
@@ -263,25 +281,26 @@ func (d *Dashboard) deployConsoleLink(cli client.Client, owner metav1.Object, na
 	return nil
 }
 
-func (d *Dashboard) cleanOauthClientSecrets(cli client.Client, dscispec *dsciv1.DSCInitializationSpec, currentComponentStatus bool) error {
+func (d *Dashboard) cleanOauthClient(cli client.Client, dscispec *dsciv1.DSCInitializationSpec, currentComponentExist bool) error {
 	// Remove previous oauth-client secrets
 	// Check if component is going from state of `Not Installed --> Installed`
 	// Assumption: Component is currently set to enabled
-	if !currentComponentStatus {
+	name := "dashboard-oauth-client"
+	if !currentComponentExist {
+		fmt.Println("Cleanup any left secret")
 		// Delete client secrets from previous installation
 		oauthClientSecret := &v1.Secret{}
 		err := cli.Get(context.TODO(), client.ObjectKey{
 			Namespace: dscispec.ApplicationsNamespace,
-			Name:      "dashboard-oauth-client",
+			Name:      name,
 		}, oauthClientSecret)
 		if err != nil {
 			if !apierrs.IsNotFound(err) {
-				return err
+				return fmt.Errorf("error getting secret %s: %w", name, err)
 			}
 		} else {
-			err := cli.Delete(context.TODO(), oauthClientSecret)
-			if err != nil {
-				return fmt.Errorf("error deleting oauth client secret: %v", err)
+			if err := cli.Delete(context.TODO(), oauthClientSecret); err != nil {
+				return fmt.Errorf("error deleting secret %s in namespace %s : %w", name, dscispec.ApplicationsNamespace, err)
 			}
 		}
 	}

diff --git a/components/datasciencepipelines/datasciencepipelines.go b/components/datasciencepipelines/datasciencepipelines.go
@@ -3,15 +3,19 @@
 package datasciencepipelines
 
 import (
+	"context"
+	"fmt"
 	"path/filepath"
 
 	operatorv1 "github.com/openshift/api/operator/v1"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/client-go/rest"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 
 	dsciv1 "github.com/opendatahub-io/opendatahub-operator/v2/apis/dscinitialization/v1"
 	"github.com/opendatahub-io/opendatahub-operator/v2/components"
 	"github.com/opendatahub-io/opendatahub-operator/v2/pkg/deploy"
+	"github.com/opendatahub-io/opendatahub-operator/v2/pkg/monitoring"
 )
 
 var (
@@ -50,7 +54,13 @@ func (d *DataSciencePipelines) GetComponentName() string {
 	return ComponentName
 }
 
-func (d *DataSciencePipelines) ReconcileComponent(cli client.Client, owner metav1.Object, dscispec *dsciv1.DSCInitializationSpec, _ bool) error {
+func (d *DataSciencePipelines) ReconcileComponent(ctx context.Context,
+	cli client.Client,
+	resConf *rest.Config,
+	owner metav1.Object,
+	dscispec *dsciv1.DSCInitializationSpec,
+	_ bool,
+) error {
 	var imageParamMap = map[string]string{
 		"IMAGES_APISERVER":         "RELATED_IMAGE_ODH_ML_PIPELINES_API_SERVER_IMAGE",
 		"IMAGES_ARTIFACT":          "RELATED_IMAGE_ODH_ML_PIPELINES_ARTIFACT_MANAGER_IMAGE",
@@ -88,13 +98,22 @@ func (d *DataSciencePipelines) ReconcileComponent(cli client.Client, owner metav
 	}
 	// CloudService Monitoring handling
 	if platform == deploy.ManagedRhods {
+		if enabled {
+			// first check if the service is up, so prometheus wont fire alerts when it is just startup
+			// only 1 replica should be very quick
+			if err := monitoring.WaitForDeploymentAvailable(ctx, resConf, ComponentName, dscispec.ApplicationsNamespace, 10, 1); err != nil {
+				return fmt.Errorf("deployment for %s is not ready to server: %w", ComponentName, err)
+			}
+			fmt.Printf("deployment for %s is done, updating monitoring rules\n", ComponentName)
+		}
+
 		if err := d.UpdatePrometheusConfig(cli, enabled && monitoringEnabled, ComponentName); err != nil {
 			return err
 		}
 		if err = deploy.DeployManifestsFromPath(cli, owner,
 			filepath.Join(deploy.DefaultManifestPath, "monitoring", "prometheus", "apps"),
 			dscispec.Monitoring.Namespace,
-			ComponentName+"prometheus", true); err != nil {
+			"prometheus", true); err != nil {
 			return err
 		}
 	}