指標に基づいて Pod の自動スケーリングを最適化する

package main

import (
	"fmt"
	"log"
	"net/http"
	"os"
)

func main() {
	// register hello function to handle all requests
	mux := http.NewServeMux()
	mux.HandleFunc("/", hello)

	// use PORT environment variable, or default to 8080
	port := os.Getenv("PORT")
	if port == "" {
		port = "8080"
	}

	// start the web server on port and accept requests
	log.Printf("Server listening on port %s", port)
	log.Fatal(http.ListenAndServe(":"+port, mux))
}

// hello responds to the request with a plain-text "Hello, world" message.
func hello(w http.ResponseWriter, r *http.Request) {
	log.Printf("Serving request: %s", r.URL.Path)
	host, _ := os.Hostname()
	fmt.Fprintf(w, "Hello, world!\n")
	fmt.Fprintf(w, "Version: 1.0.0\n")
	fmt.Fprintf(w, "Hostname: %s\n", host)
}

from google import auth
from google.cloud import pubsub_v1


def main():
    """Continuously pull messages from subsciption"""

    # read default project ID
    _, project_id = auth.default()
    subscription_id = 'echo-read'

    subscriber = pubsub_v1.SubscriberClient()
    subscription_path = subscriber.subscription_path(
        project_id, subscription_id)

    def callback(message: pubsub_v1.subscriber.message.Message) -> None:
        """Process received message"""
        print(f"Received message: ID={message.message_id} Data={message.data}")
        print(f"[{datetime.datetime.now()}] Processing: {message.message_id}")
        time.sleep(3)
        print(f"[{datetime.datetime.now()}] Processed: {message.message_id}")
        message.ack()

    streaming_pull_future = subscriber.subscribe(
        subscription_path, callback=callback)
    print(f"Pulling messages from {subscription_path}...")

    with subscriber:
        try:
            streaming_pull_future.result()
        except Exception as e:
            print(e)

metric := prometheus.NewGauge(
	prometheus.GaugeOpts{
		Name: *metricName,
		Help: "Custom metric",
	},
)
prometheus.MustRegister(metric)
metric.Set(float64(*metricValue))

http.Handle("/metrics", promhttp.Handler())
log.Printf("Starting to listen on :%d", *port)
err := http.ListenAndServe(fmt.Sprintf(":%d", *port), nil)

apiVersion: apps/v1
kind: Deployment
metadata:
  name: helloweb
  labels:
    app: hello
spec:
  selector:
    matchLabels:
      app: hello
      tier: web
  template:
    metadata:
      labels:
        app: hello
        tier: web
    spec:
      containers:
      - name: hello-app
        image: us-docker.pkg.dev/google-samples/containers/gke/hello-app:1.0
        ports:
        - containerPort: 8080
        resources:
          requests:
            cpu: 200m

apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    run: custom-metrics-gmp
  name: custom-metrics-gmp
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      run: custom-metrics-gmp
  template:
    metadata:
      labels:
        run: custom-metrics-gmp
    spec:
      containers:
      # sample container generating custom metrics
      - name: prometheus-dummy-exporter
        image: us-docker.pkg.dev/google-samples/containers/gke/prometheus-dummy-exporter:v0.2.0
        command: ["./prometheus-dummy-exporter"]
        args:
        - --metric-name=custom_prometheus
        - --metric-value=40
        - --port=8080

apiVersion: monitoring.googleapis.com/v1
kind: PodMonitoring
metadata:
  name: "custom-metrics-exporter"
spec:
  selector:
    matchLabels:
      run: custom-metrics-gmp
  endpoints:
  - port: 8080
    path: /metrics
    interval: 15s

apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: cpu
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: helloweb
  minReplicas: 1
  maxReplicas: 5
  metrics:
  - type: Resource
    resource:
      name: cpu
      target:
        type: Utilization
        averageUtilization: 30

apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: pubsub
spec:
  minReplicas: 1
  maxReplicas: 5
  metrics:
  - external:
      metric:
       name: pubsub.googleapis.com|subscription|num_undelivered_messages
       selector:
         matchLabels:
           resource.labels.subscription_id: echo-read
      target:
        type: AverageValue
        averageValue: 2
    type: External
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: pubsub

apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: custom-metrics-gmp-hpa
  namespace: default
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: custom-metrics-gmp
  minReplicas: 1
  maxReplicas: 5
  metrics:
  - type: Pods
    pods:
      metric:
        name: prometheus.googleapis.com|custom_prometheus|gauge
      target:
        type: AverageValue
        averageValue: 20