1322: Modified manifests to use all-in-one training-operator (#1346)

* 1322: Modified manifests to use all-in-one training-operator WIP Actions taken: - replaced tf-job-operator => training-operator - replaced kubeflow-tfjobs- => kubeflow-training- - moved crds for mxjobs, tgjobs, pytorchjobs and xgboostjobs from config/crd/bases to manifests/base/ and prefixed them with crd_ Ref: #1322 Testing steps: To be added Work in Progress * 1322: synced up config/manager with manifests Training operator was found to be working <pre> k -n kubeflow logs -f training-operator-694766989-pp2j4 I0812 21:43:24.739862 1 request.go:645] Throttling request took 1.048945631s, request: GET:https://172.19.0.1:443/apis/networking.k8s.io/v1?timeout=32s 2021-08-12T21:43:25.694Z INFO controller-runtime.metrics metrics server is starting to listen {"addr": ":8080"} 2021-08-12T21:43:25.790Z INFO setup starting manager 2021-08-12T21:43:25.790Z INFO controller-runtime.manager starting metrics server {"path": "/metrics"} 2021-08-12T21:43:25.790Z INFO controller-runtime.manager.controller.tf-operator Starting EventSource {"source": "kind source: /, Kind="} 2021-08-12T21:43:25.790Z INFO controller-runtime.manager.controller.mxnet-operator Starting EventSource {"source": "kind source: /, Kind="} 2021-08-12T21:43:25.791Z INFO controller-runtime.manager.controller.pytorchjob-operator Starting EventSource {"source": "kind source: /, Kind="} 2021-08-12T21:43:25.791Z INFO controller-runtime.manager.controller.xgboostjob-operator Starting EventSource {"source": "kind source: /, Kind="} 2021-08-12T21:43:26.289Z INFO controller-runtime.manager.controller.xgboostjob-operator Starting EventSource {"source": "kind source: /, Kind="} 2021-08-12T21:43:26.294Z INFO controller-runtime.manager.controller.pytorchjob-operator Starting EventSource {"source": "kind source: /, Kind="} 2021-08-12T21:43:26.589Z INFO controller-runtime.manager.controller.mxnet-operator Starting EventSource {"source": "kind source: /, Kind="} 2021-08-12T21:43:26.688Z INFO controller-runtime.manager.controller.tf-operator Starting EventSource {"source": "kind source: /, Kind="} 2021-08-12T21:43:26.889Z INFO controller-runtime.manager.controller.tf-operator Starting EventSource {"source": "kind source: /, Kind="} 2021-08-12T21:43:26.889Z INFO controller-runtime.manager.controller.pytorchjob-operator Starting EventSource {"source": "kind source: /, Kind="} 2021-08-12T21:43:26.890Z INFO controller-runtime.manager.controller.xgboostjob-operator Starting EventSource {"source": "kind source: /, Kind="} 2021-08-12T21:43:26.890Z INFO controller-runtime.manager.controller.mxnet-operator Starting EventSource {"source": "kind source: /, Kind="} 2021-08-12T21:43:26.990Z INFO controller-runtime.manager.controller.xgboostjob-operator Starting Controller 2021-08-12T21:43:26.990Z INFO controller-runtime.manager.controller.tf-operator Starting Controller 2021-08-12T21:43:26.990Z INFO controller-runtime.manager.controller.tf-operator Starting workers {"worker count": 1} 2021-08-12T21:43:26.990Z INFO controller-runtime.manager.controller.pytorchjob-operator Starting Controller 2021-08-12T21:43:26.991Z INFO controller-runtime.manager.controller.xgboostjob-operator Starting workers {"worker count": 1} 2021-08-12T21:43:26.991Z INFO controller-runtime.manager.controller.pytorchjob-operator Starting workers {"worker count": 1} 2021-08-12T21:43:26.991Z INFO controller-runtime.manager.controller.mxnet-operator Starting Controller 2021-08-12T21:43:26.991Z INFO controller-runtime.manager.controller.mxnet-operator Starting workers {"worker count": 1} </pre> * 1322: incorporated review comments - added all resources in ClusterRole * 1322: incorporated review comments - now controller-gen generates the crds directly in manifests/base instead of config/crd/bases - updated setup-training-operator.sh to use manifests/overlays/standalone * 1322: removed config/crd/bases as its now getting generated in manifests * 1322: incorporated review comments related to using separate role files * 1322: removed image name replacement
kubeflow · Aug 13, 2021 · 46c5864 · 46c5864
1 parent 3e11cde
commit 46c5864
Show file tree

Hide file tree

Showing 46 changed files with 180 additions and 331 deletions.
diff --git a/Makefile b/Makefile
@@ -38,7 +38,7 @@ help: ## Display this help.
 ##@ Development
 
 manifests: controller-gen ## Generate WebhookConfiguration, ClusterRole and CustomResourceDefinition objects.
-	$(CONTROLLER_GEN) $(CRD_OPTIONS) rbac:roleName=manager-role webhook paths="./pkg/apis/..." output:crd:artifacts:config=config/crd/bases
+	$(CONTROLLER_GEN) $(CRD_OPTIONS) rbac:roleName=manager-role webhook paths="./pkg/apis/..." output:crd:artifacts:config=manifests/base
 
 generate: controller-gen ## Generate code containing DeepCopy, DeepCopyInto, and DeepCopyObject method implementations.
 	$(CONTROLLER_GEN) object:headerFile="hack/boilerplate.go.txt" paths="./pkg/apis/..."

diff --git a/config/crd/kustomization.yaml b/config/crd/kustomization.yaml
diff --git a/config/crd/kustomizeconfig.yaml b/config/crd/kustomizeconfig.yaml
diff --git a/config/manager/manager.yaml b/config/manager/manager.yaml
diff --git a/manifests/base/cluster-role-binding.yaml b/manifests/base/cluster-role-binding.yaml
@@ -3,12 +3,12 @@ apiVersion: rbac.authorization.k8s.io/v1beta1
 kind: ClusterRoleBinding
 metadata:
   labels:
-    app: tf-job-operator
-  name: tf-job-operator
+    app: training-operator
+  name: training-operator
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: ClusterRole
-  name: tf-job-operator
+  name: training-operator
 subjects:
 - kind: ServiceAccount
-  name: tf-job-operator
+  name: training-operator
diff --git a/manifests/base/cluster-role.yaml b/manifests/base/cluster-role.yaml
@@ -3,100 +3,47 @@ apiVersion: rbac.authorization.k8s.io/v1beta1
 kind: ClusterRole
 metadata:
   labels:
-    app: tf-job-operator
-  name: tf-job-operator
+    app: training-operator
+  name: training-operator
 rules:
-- apiGroups:
-  - kubeflow.org
-  resources:
-  - tfjobs
-  - tfjobs/status
-  - tfjobs/finalizers
-  verbs:
-  - '*'
-- apiGroups:
-  - apiextensions.k8s.io
-  resources:
-  - customresourcedefinitions
-  verbs:
-  - '*'
-- apiGroups:
-  - ""
-  resources:
-  - pods
-  - services
-  - endpoints
-  - events
-  verbs:
-  - '*'
-- apiGroups:
-  - apps
-  - extensions
-  resources:
-  - deployments
-  verbs:
-  - '*'
-- apiGroups:
-  - scheduling.volcano.sh
-  resources:
-  - podgroups
-  verbs:
-  - '*'
-
----
-
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: kubeflow-tfjobs-admin
-  labels:
-    rbac.authorization.kubeflow.org/aggregate-to-kubeflow-admin: "true"
-aggregationRule:
-  clusterRoleSelectors:
-  - matchLabels:
-      rbac.authorization.kubeflow.org/aggregate-to-kubeflow-tfjobs-admin: "true"
-rules: []
-
----
-
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: kubeflow-tfjobs-edit
-  labels:
-    rbac.authorization.kubeflow.org/aggregate-to-kubeflow-edit: "true"
-    rbac.authorization.kubeflow.org/aggregate-to-kubeflow-tfjobs-admin: "true"
-rules:
-- apiGroups:
-  - kubeflow.org
-  resources:
-  - tfjobs
-  - tfjobs/status
-  verbs:
-  - get
-  - list
-  - watch
-  - create
-  - delete
-  - deletecollection
-  - patch
-  - update
-
----
-
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: kubeflow-tfjobs-view
-  labels:
-    rbac.authorization.kubeflow.org/aggregate-to-kubeflow-view: "true"
-rules:
-- apiGroups:
-  - kubeflow.org
-  resources:
-  - tfjobs
-  - tfjobs/status
-  verbs:
-  - get
-  - list
-  - watch
+  - apiGroups:
+      - kubeflow.org
+    resources:
+      - tfjobs
+      - mxjobs
+      - pytorchjobs
+      - xgboostjobs
+      - tfjobs/status
+      - pytorchjobs/status
+      - mxjobs/status
+      - xgboostjobs/status
+    verbs:
+      - "*"
+  - apiGroups:
+      - apiextensions.k8s.io
+    resources:
+      - customresourcedefinitions
+    verbs:
+      - "*"
+  - apiGroups:
+      - ""
+    resources:
+      - pods
+      - services
+      - endpoints
+      - events
+    verbs:
+      - "*"
+  - apiGroups:
+      - apps
+      - extensions
+    resources:
+      - deployments
+    verbs:
+      - "*"
+  - apiGroups:
+      - scheduling.volcano.sh
+    resources:
+      - podgroups
+    verbs:
+      - "*"
diff --git a/manifests/base/crd.yaml b/manifests/base/crd.yaml
diff --git a/manifests/base/deployment.yaml b/manifests/base/deployment.yaml
diff --git a/config/crd/bases/kubeflow.org_mxjobs.yaml → manifests/base/kubeflow.org_mxjobs.yaml b/config/crd/bases/kubeflow.org_mxjobs.yaml → manifests/base/kubeflow.org_mxjobs.yaml
diff --git a/...g/crd/bases/kubeflow.org_pytorchjobs.yaml → manifests/base/kubeflow.org_pytorchjobs.yaml b/...g/crd/bases/kubeflow.org_pytorchjobs.yaml → manifests/base/kubeflow.org_pytorchjobs.yaml
diff --git a/config/crd/bases/kubeflow.org_tfjobs.yaml → manifests/base/kubeflow.org_tfjobs.yaml b/config/crd/bases/kubeflow.org_tfjobs.yaml → manifests/base/kubeflow.org_tfjobs.yaml
diff --git a/...g/crd/bases/kubeflow.org_xgboostjobs.yaml → manifests/base/kubeflow.org_xgboostjobs.yaml b/...g/crd/bases/kubeflow.org_xgboostjobs.yaml → manifests/base/kubeflow.org_xgboostjobs.yaml
diff --git a/manifests/base/kustomization.yaml b/manifests/base/kustomization.yaml
@@ -2,14 +2,11 @@ apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 namespace: kubeflow
 resources:
-- crd.yaml
-- cluster-role-binding.yaml
-- cluster-role.yaml
-- deployment.yaml
-- service-account.yaml
-- service.yaml
-commonLabels:
-  app: tf-job-operator
-  kustomize.component: tf-job-operator
-  app.kubernetes.io/component: tfjob
-  app.kubernetes.io/name: tf-job-operator
+  - kubeflow.org_tfjobs.yaml
+  - kubeflow.org_mxjobs.yaml
+  - kubeflow.org_pytorchjobs.yaml
+  - kubeflow.org_xgboostjobs.yaml
+  - cluster-role-binding.yaml
+  - cluster-role.yaml
+  - service-account.yaml
+  - service.yaml
diff --git a/manifests/base/service-account.yaml b/manifests/base/service-account.yaml
@@ -2,5 +2,5 @@ apiVersion: v1
 kind: ServiceAccount
 metadata:
   labels:
-    app: tf-job-operator
-  name: tf-job-operator
+    app: training-operator
+  name: training-operator
diff --git a/manifests/base/service.yaml b/manifests/base/service.yaml
@@ -7,13 +7,13 @@ metadata:
     prometheus.io/scrape: "true"
     prometheus.io/port: "8443"
   labels:
-    app: tf-job-operator
-  name: tf-job-operator
+    app: training-operator
+  name: training-operator
 spec:
   ports:
   - name: monitoring-port
     port: 8443
     targetPort: 8443
   selector:
-    name: tf-job-operator
+    name: training-operator
   type: ClusterIP
diff --git a/config/default/kustomization.yaml → manifests/default/kustomization.yaml b/config/default/kustomization.yaml → manifests/default/kustomization.yaml
diff --git a/config/default/manager_config_patch.yaml → manifests/default/manager_config_patch.yaml b/config/default/manager_config_patch.yaml → manifests/default/manager_config_patch.yaml
diff --git a/...ig/manager/controller_manager_config.yaml → ...ts/manager/controller_manager_config.yaml b/...ig/manager/controller_manager_config.yaml → ...ts/manager/controller_manager_config.yaml