Create RBAC and ConfigMap before deployment

Signed-off-by: Shmuel Kallner <[email protected]>

Author: shmuelk

test/testdata/inferencepool-e2e.yaml

@@ -37,6 +37,87 @@ metadata:
   name: vllm-llama3-8b-instruct-epp
   namespace: $E2E_NS
 ---
+kind: Role
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: pod-read
+  namespace: $E2E_NS
+rules:
+- apiGroups: [ "inference.networking.x-k8s.io" ]
+  resources: [ "inferenceobjectives", "inferencepools" ]
+  verbs: [ "get", "watch", "list" ]
+- apiGroups: [ "inference.networking.k8s.io" ]
+  resources: [ "inferencepools" ]
+  verbs: [ "get", "watch", "list" ]
+- apiGroups: [ "" ]
+  resources: [ "pods" ]
+  verbs: [ "get", "watch", "list" ]
+---
+kind: RoleBinding
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: pod-read-binding
+  namespace: $E2E_NS
+subjects:
+- kind: ServiceAccount
+  name: vllm-llama3-8b-instruct-epp
+  namespace: $E2E_NS
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: pod-read
+---
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: auth-reviewer
+rules:
+- apiGroups:
+  - authentication.k8s.io
+  resources:
+  - tokenreviews
+  verbs:
+  - create
+- apiGroups:
+  - authorization.k8s.io
+  resources:
+  - subjectaccessreviews
+  verbs:
+  - create
+---
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: auth-reviewer-binding
+subjects:
+- kind: ServiceAccount
+  name: vllm-llama3-8b-instruct-epp
+  namespace: $E2E_NS
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: auth-reviewer
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: plugins-config
+  namespace: $E2E_NS
+data:
+  default-plugins.yaml: |
+    apiVersion: inference.networking.x-k8s.io/v1alpha1
+    kind: EndpointPickerConfig
+    plugins:
+    - type: queue-scorer
+    - type: kv-cache-utilization-scorer
+    - type: prefix-cache-scorer
+    schedulingProfiles:
+    - name: default
+      plugins:
+      - pluginRef: queue-scorer
+      - pluginRef: kv-cache-utilization-scorer
+      - pluginRef: prefix-cache-scorer
+---
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -100,84 +181,3 @@ spec:
       - name: plugins-config-volume
         configMap:
           name: plugins-config
----
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: plugins-config
-  namespace: $E2E_NS
-data:
-  default-plugins.yaml: |
-    apiVersion: inference.networking.x-k8s.io/v1alpha1
-    kind: EndpointPickerConfig
-    plugins:
-    - type: queue-scorer
-    - type: kv-cache-utilization-scorer
-    - type: prefix-cache-scorer
-    schedulingProfiles:
-    - name: default
-      plugins:
-      - pluginRef: queue-scorer
-      - pluginRef: kv-cache-utilization-scorer
-      - pluginRef: prefix-cache-scorer
----
-kind: Role
-apiVersion: rbac.authorization.k8s.io/v1
-metadata:
-  name: pod-read
-  namespace: $E2E_NS
-rules:
-- apiGroups: [ "inference.networking.x-k8s.io" ]
-  resources: [ "inferenceobjectives", "inferencepools" ]
-  verbs: [ "get", "watch", "list" ]
-- apiGroups: [ "inference.networking.k8s.io" ]
-  resources: [ "inferencepools" ]
-  verbs: [ "get", "watch", "list" ]
-- apiGroups: [ "" ]
-  resources: [ "pods" ]
-  verbs: [ "get", "watch", "list" ]
----
-kind: RoleBinding
-apiVersion: rbac.authorization.k8s.io/v1
-metadata:
-  name: pod-read-binding
-  namespace: $E2E_NS
-subjects:
-- kind: ServiceAccount
-  name: vllm-llama3-8b-instruct-epp
-  namespace: $E2E_NS
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: Role
-  name: pod-read
----
-kind: ClusterRole
-apiVersion: rbac.authorization.k8s.io/v1
-metadata:
-  name: auth-reviewer
-rules:
-- apiGroups:
-  - authentication.k8s.io
-  resources:
-  - tokenreviews
-  verbs:
-  - create
-- apiGroups:
-  - authorization.k8s.io
-  resources:
-  - subjectaccessreviews
-  verbs:
-  - create
----
-kind: ClusterRoleBinding
-apiVersion: rbac.authorization.k8s.io/v1
-metadata:
-  name: auth-reviewer-binding
-subjects:
-- kind: ServiceAccount
-  name: vllm-llama3-8b-instruct-epp
-  namespace: $E2E_NS
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: auth-reviewer

test/testdata/inferencepool-leader-election-e2e.yaml

@@ -35,91 +35,6 @@ metadata:
   name: vllm-llama3-8b-instruct-epp
   namespace: $E2E_NS
 ---
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: vllm-llama3-8b-instruct-epp
-  namespace: $E2E_NS
-  labels:
-    app: vllm-llama3-8b-instruct-epp
-spec:
-  replicas: 3
-  selector:
-    matchLabels:
-      app: vllm-llama3-8b-instruct-epp
-  template:
-    metadata:
-      labels:
-        app: vllm-llama3-8b-instruct-epp
-    spec:
-      serviceAccountName: vllm-llama3-8b-instruct-epp
-      # Conservatively, this timeout should mirror the longest grace period of the pods within the pool
-      terminationGracePeriodSeconds: 130
-      containers:
-      - name: epp
-        image: $E2E_IMAGE
-        imagePullPolicy: IfNotPresent
-        args:
-        - --pool-name
-        - "vllm-llama3-8b-instruct"
-        - --pool-namespace
-        - "$E2E_NS"
-        - --v
-        - "4"
-        - --zap-encoder
-        - "json"
-        - --grpc-port
-        - "9002"
-        - --grpc-health-port
-        - "9003"
-        - --ha-enable-leader-election
-        - "--config-file"
-        - "/config/default-plugins.yaml"
-        ports:
-        - containerPort: 9002
-        - containerPort: 9003
-        - name: metrics
-          containerPort: 9090
-        livenessProbe:
-          grpc:
-            port: 9003
-            service: liveness
-          initialDelaySeconds: 5
-          periodSeconds: 10
-        readinessProbe:
-          grpc:
-            port: 9003
-            service: readiness
-          initialDelaySeconds: 5
-          periodSeconds: 10
-        volumeMounts:
-        - name: plugins-config-volume
-          mountPath: "/config"
-      volumes:
-      - name: plugins-config-volume
-        configMap:
-          name: plugins-config
----
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: plugins-config
-  namespace: $E2E_NS
-data:
-  default-plugins.yaml: |
-    apiVersion: inference.networking.x-k8s.io/v1alpha1
-    kind: EndpointPickerConfig
-    plugins:
-    - type: queue-scorer
-    - type: kv-cache-utilization-scorer
-    - type: prefix-cache-scorer
-    schedulingProfiles:
-    - name: default
-      plugins:
-      - pluginRef: queue-scorer
-      - pluginRef: kv-cache-utilization-scorer
-      - pluginRef: prefix-cache-scorer
----
 kind: Role
 apiVersion: rbac.authorization.k8s.io/v1
 metadata:
@@ -207,3 +122,88 @@ roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: ClusterRole
   name: auth-reviewer
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: plugins-config
+  namespace: $E2E_NS
+data:
+  default-plugins.yaml: |
+    apiVersion: inference.networking.x-k8s.io/v1alpha1
+    kind: EndpointPickerConfig
+    plugins:
+    - type: queue-scorer
+    - type: kv-cache-utilization-scorer
+    - type: prefix-cache-scorer
+    schedulingProfiles:
+    - name: default
+      plugins:
+      - pluginRef: queue-scorer
+      - pluginRef: kv-cache-utilization-scorer
+      - pluginRef: prefix-cache-scorer
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: vllm-llama3-8b-instruct-epp
+  namespace: $E2E_NS
+  labels:
+    app: vllm-llama3-8b-instruct-epp
+spec:
+  replicas: 3
+  selector:
+    matchLabels:
+      app: vllm-llama3-8b-instruct-epp
+  template:
+    metadata:
+      labels:
+        app: vllm-llama3-8b-instruct-epp
+    spec:
+      serviceAccountName: vllm-llama3-8b-instruct-epp
+      # Conservatively, this timeout should mirror the longest grace period of the pods within the pool
+      terminationGracePeriodSeconds: 130
+      containers:
+      - name: epp
+        image: $E2E_IMAGE
+        imagePullPolicy: IfNotPresent
+        args:
+        - --pool-name
+        - "vllm-llama3-8b-instruct"
+        - --pool-namespace
+        - "$E2E_NS"
+        - --v
+        - "4"
+        - --zap-encoder
+        - "json"
+        - --grpc-port
+        - "9002"
+        - --grpc-health-port
+        - "9003"
+        - --ha-enable-leader-election
+        - "--config-file"
+        - "/config/default-plugins.yaml"
+        ports:
+        - containerPort: 9002
+        - containerPort: 9003
+        - name: metrics
+          containerPort: 9090
+        livenessProbe:
+          grpc:
+            port: 9003
+            service: liveness
+          initialDelaySeconds: 5
+          periodSeconds: 10
+        readinessProbe:
+          grpc:
+            port: 9003
+            service: readiness
+          initialDelaySeconds: 5
+          periodSeconds: 10
+        volumeMounts:
+        - name: plugins-config-volume
+          mountPath: "/config"
+      volumes:
+      - name: plugins-config-volume
+        configMap:
+          name: plugins-config