[Scalability] Enable Horizontal Pod Autoscaler (HPA) for Alcor deployment

kubernetes/services/metrics-server.yaml

@@ -0,0 +1,208 @@
+# Metrics Server has specific requirements for cluster and network configuration. These requirements aren't the default for all cluster distributions. Please ensure that your cluster distribution supports these requirements before using Metrics Server:
+
+# 1. Metrics Server must be reachable from kube-apiserver by container IP address (or node IP if hostNetwork is enabled).
+
+# 2. The kube-apiserver must enable an aggregation layer.
+
+# 3. Nodes must have Webhook authentication and authorization enabled.
+
+# 4. Kubelet certificate needs to be signed by cluster Certificate Authority (or disable certificate validation by passing --kubelet-insecure-tls to Metrics Server)
+
+# 5. Container runtime must implement a container metrics RPCs (or have cAdvisor support)
+
+# Please look at the link https://github.com/kubernetes-sigs/metrics-server#requirements for reference
+
+# Latest Metrics Server release can be installed by running:
+# kubectl apply -f https://github.com/kubernetes-sigs/metrics-server/releases/latest/download/components.yaml
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  labels:
+    k8s-app: metrics-server
+  name: metrics-server
+  namespace: kube-system
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  labels:
+    k8s-app: metrics-server
+    rbac.authorization.k8s.io/aggregate-to-admin: "true"
+    rbac.authorization.k8s.io/aggregate-to-edit: "true"
+    rbac.authorization.k8s.io/aggregate-to-view: "true"
+  name: system:aggregated-metrics-reader
+rules:
+  - apiGroups:
+      - metrics.k8s.io
+    resources:
+      - pods
+      - nodes
+    verbs:
+      - get
+      - list
+      - watch
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  labels:
+    k8s-app: metrics-server
+  name: system:metrics-server
+rules:
+  - apiGroups:
+      - ""
+    resources:
+      - pods
+      - nodes
+      - nodes/stats
+      - namespaces
+      - configmaps
+    verbs:
+      - get
+      - list
+      - watch
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  labels:
+    k8s-app: metrics-server
+  name: metrics-server-auth-reader
+  namespace: kube-system
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: extension-apiserver-authentication-reader
+subjects:
+  - kind: ServiceAccount
+    name: metrics-server
+    namespace: kube-system
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  labels:
+    k8s-app: metrics-server
+  name: metrics-server:system:auth-delegator
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: system:auth-delegator
+subjects:
+  - kind: ServiceAccount
+    name: metrics-server
+    namespace: kube-system
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  labels:
+    k8s-app: metrics-server
+  name: system:metrics-server
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: system:metrics-server
+subjects:
+  - kind: ServiceAccount
+    name: metrics-server
+    namespace: kube-system
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    k8s-app: metrics-server
+  name: metrics-server
+  namespace: kube-system
+spec:
+  ports:
+    - name: https
+      port: 443
+      protocol: TCP
+      targetPort: https
+  selector:
+    k8s-app: metrics-server
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    k8s-app: metrics-server
+  name: metrics-server
+  namespace: kube-system
+spec:
+  selector:
+    matchLabels:
+      k8s-app: metrics-server
+  strategy:
+    rollingUpdate:
+      maxUnavailable: 0
+  template:
+    metadata:
+      labels:
+        k8s-app: metrics-server
+    spec:
+      containers:
+        - args:
+            - --cert-dir=/tmp
+            - --secure-port=443
+            - --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
+            - --kubelet-use-node-status-port
+            - --metric-resolution=15s
+          image: k8s.gcr.io/metrics-server/metrics-server:v0.5.0
+          imagePullPolicy: IfNotPresent
+          livenessProbe:
+            failureThreshold: 3
+            httpGet:
+              path: /livez
+              port: https
+              scheme: HTTPS
+            periodSeconds: 10
+          name: metrics-server
+          ports:
+            - containerPort: 443
+              name: https
+              protocol: TCP
+          readinessProbe:
+            failureThreshold: 3
+            httpGet:
+              path: /readyz
+              port: https
+              scheme: HTTPS
+            initialDelaySeconds: 20
+            periodSeconds: 10
+          resources:
+            requests:
+              cpu: 100m
+              memory: 200Mi
+          securityContext:
+            readOnlyRootFilesystem: true
+            runAsNonRoot: true
+            runAsUser: 1000
+          volumeMounts:
+            - mountPath: /tmp
+              name: tmp-dir
+      nodeSelector:
+        kubernetes.io/os: linux
+      priorityClassName: system-cluster-critical
+      serviceAccountName: metrics-server
+      volumes:
+        - emptyDir: {}
+          name: tmp-dir
+---
+apiVersion: apiregistration.k8s.io/v1
+kind: APIService
+metadata:
+  labels:
+    k8s-app: metrics-server
+  name: v1beta1.metrics.k8s.io
+spec:
+  group: metrics.k8s.io
+  groupPriorityMinimum: 100
+  insecureSkipTLSVerify: true
+  service:
+    name: metrics-server
+    namespace: kube-system
+  version: v1beta1
+  versionPriority: 100

kubernetes/services/subnet_manager_hpa.yaml

@@ -0,0 +1,65 @@
+apiVersion: autoscaling/v2beta1
+kind: HorizontalPodAutoscaler
+metadata:
+  name: subnetmanager-hpa
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: subnetmanager
+  # if minReplicas is less than Deployment replicas value, it may cause scale down
+  minReplicas: 5
+  maxReplicas: 10
+  metrics:
+#   Set the average usage rate of the cpu, scale up if it exceeds 50
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: AverageUtilization
+          averageUtilization: 50
+#    The average data volume per second reaches 1000 for scaling up
+#    - type: Pods
+#      pods:
+#        metric:
+#          name: packets-per-second
+#        target:
+#          type: AverageValue
+#          averageValue: 1k
+
+#    The value is derived from Ingress "main-route", scale up when the number of requests per second in Ingress reaches 2000
+#    - type: Object
+#      object:
+#        metric:
+#          name: requests-per-second
+#        describedObject:
+#          apiVersion: networking.k8s.io/v1beta1
+#          kind: Ingress
+#          name: main-route
+#        target:
+#          kind: Value
+#          value: 10k
+
+# HPA's current status data
+status:
+  observedGeneration: 1
+  lastScaleTime: <some-time>
+  currentReplicas: 1
+  desiredReplicas: 1
+  currentMetrics:
+    - type: Resource
+      resource:
+        name: cpu
+      current:
+        averageUtilization: 0
+        averageValue: 0
+#    - type: Object
+#      object:
+#        metric:
+#          name: requests-per-second
+#        describedObject:
+#          apiVersion: networking.k8s.io/v1beta1
+#          kind: Ingress
+#          name: main-route
+#        current:
+#          value: 10k

kubernetes/services/vpc_manager_hpa.yaml

@@ -0,0 +1,85 @@
+apiVersion: autoscaling/v2beta1
+kind: HorizontalPodAutoscaler
+metadata:
+  name: vpcmanager-hpa
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: vpcmanager
+  # if minReplicas is less than Deployment replicas value, it may cause scale down
+  minReplicas: 5
+  maxReplicas: 10
+  behavior:
+    scaleDown:
+      # Indicates that the stability window considers the expected state of the past (here within 300 sec) to prevent expansion and contraction
+      stabilizationWindowSeconds: 300
+      policies:
+        - type: Percent
+          value: 100
+          periodSeconds: 15
+      # The autoscaler will choose the strategy that affects the minimum number of Pods
+      selectPolicy: Min
+    scaleUp:
+      stabilizationWindowSeconds: 0
+      policies:
+        - type: Percent
+          value: 100
+          periodSeconds: 15
+        - type: Pods
+          value: 4
+          periodSeconds: 15
+      selectPolicy: Max
+  metrics:
+#   Set the average usage rate of the cpu, scale up if it exceeds 50
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: AverageUtilization
+          averageUtilization: 50
+#    The average data volume per second reaches 1000 for scaling up
+#    - type: Pods
+#      pods:
+#        metric:
+#          name: packets-per-second
+#        target:
+#          type: AverageValue
+#          averageValue: 1k
+
+#    The value is derived from Ingress "main-route", scale up when the number of requests per second in Ingress reaches 2000
+#    - type: Object
+#      object:
+#        metric:
+#          name: requests-per-second
+#        describedObject:
+#          apiVersion: networking.k8s.io/v1beta1
+#          kind: Ingress
+#          name: main-route
+#        target:
+#          kind: Value
+#          value: 10k
+
+# HPA's current status data
+status:
+  observedGeneration: 1
+  lastScaleTime: <some-time>
+  currentReplicas: 1
+  desiredReplicas: 1
+  currentMetrics:
+    - type: Resource
+      resource:
+        name: cpu
+      current:
+        averageUtilization: 0
+        averageValue: 0
+#    - type: Object
+#      object:
+#        metric:
+#          name: requests-per-second
+#        describedObject:
+#          apiVersion: networking.k8s.io/v1beta1
+#          kind: Ingress
+#          name: main-route
+#        current:
+#          value: 10k

services/vpc_manager/src/main/java/com/futurewei/alcor/vpcmanager/controller/VpcController.java

@@ -429,4 +429,20 @@ public VpcWebJson deleteSubnetIdInVpcState(@PathVariable String projectid, @Path
         return new VpcWebJson(inVpcState);
 
     }
+
+    @RequestMapping(
+            method = GET,
+            value = {"/hpatest"})
+    @DurationStatistics
+    public double hpaTest() throws Exception {
+
+        double res = 0.001;
+
+        for (int i = 0; i < 100000; i ++) {
+            res += res * res;
+        }
+
+        return res;
+
+    }
 }