Load-test rig: k6 swarm script + in-cluster target drone

manifests/loadtest/k6-script.yaml

@@ -0,0 +1,38 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: loadtest
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: k6-script
+  namespace: loadtest
+data:
+  test.js: |
+    // Generic load generator. Configured by env:
+    //   TARGET_URL  - full URL to hit
+    //   VUS         - virtual users per pod (default 20)
+    //   DURATION    - k6 duration string (default "60s")
+    import http from 'k6/http';
+    import { check, sleep } from 'k6';
+
+    const target = __ENV.TARGET_URL || 'http://example.com';
+    const vus = parseInt(__ENV.VUS || '20');
+    const duration = __ENV.DURATION || '60s';
+
+    export const options = {
+      stages: [
+        { duration: '10s', target: vus },
+        { duration: duration, target: vus },
+        { duration: '5s', target: 0 },
+      ],
+      thresholds: { http_req_failed: ['rate<0.01'] },
+      noConnectionReuse: false,
+    };
+
+    export default function () {
+      const res = http.get(target, { timeout: '10s' });
+      check(res, { 'status 2xx/3xx': (r) => r.status < 300 });
+      sleep(1 / vus * 10);
+    }

manifests/loadtest/target-drone.yaml

@@ -0,0 +1,31 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: target-drone
+  namespace: loadtest
+spec:
+  replicas: 3
+  selector:
+    matchLabels: {app: target-drone}
+  template:
+    metadata:
+      labels: {app: target-drone}
+    spec:
+      containers:
+        - name: nginx
+          image: nginx:1.29-alpine
+          ports: [{containerPort: 80}]
+          resources:
+            requests: {cpu: 10m, memory: 16Mi}
+            limits: {memory: 64Mi}
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: target-drone
+  namespace: loadtest
+spec:
+  selector: {app: target-drone}
+  ports:
+    - port: 80
+      targetPort: 80

manifests/monitoring/grafana.yaml

@@ -0,0 +1,65 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: grafana-datasources
+  namespace: monitoring
+data:
+  datasources.yaml: |
+    apiVersion: 1
+    datasources:
+      - name: Prometheus
+        type: prometheus
+        access: proxy
+        url: http://prometheus.monitoring.svc:9090
+        isDefault: true
+---
+apiVersion: v1
+kind: Secret
+metadata:
+  name: grafana-admin
+  namespace: monitoring
+stringData:
+  admin-user: adamcarr
+  admin-password: planck-lab-admin
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: grafana
+  namespace: monitoring
+spec:
+  replicas: 1
+  selector:
+    matchLabels: {app: grafana}
+  template:
+    metadata:
+      labels: {app: grafana}
+    spec:
+      containers:
+        - name: grafana
+          image: grafana/grafana:12.0.2
+          env:
+            - {name: GF_SECURITY_ADMIN_USER, valueFrom: {secretKeyRef: {name: grafana-admin, key: admin-user}}}
+            - {name: GF_SECURITY_ADMIN_PASSWORD, valueFrom: {secretKeyRef: {name: grafana-admin, key: admin-password}}}
+            - {name: GF_AUTH_ANONYMOUS_ENABLED, value: "true"}
+          ports:
+            - containerPort: 3000
+          resources:
+            requests: {cpu: 50m, memory: 128Mi}
+            limits: {memory: 512Mi}
+          volumeMounts:
+            - {name: datasources, mountPath: /etc/grafana/provisioning/datasources}
+      volumes:
+        - name: datasources
+          configMap: {name: grafana-datasources}
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: grafana
+  namespace: monitoring
+spec:
+  selector: {app: grafana}
+  ports:
+    - port: 3000
+      targetPort: 3000

manifests/monitoring/node-exporter.yaml

@@ -0,0 +1,41 @@
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: node-exporter
+  namespace: monitoring
+  labels: {app: node-exporter}
+spec:
+  selector:
+    matchLabels: {app: node-exporter}
+  template:
+    metadata:
+      labels: {app: node-exporter}
+    spec:
+      hostNetwork: true
+      hostPID: true
+      tolerations:
+        - operator: Exists
+      containers:
+        - name: node-exporter
+          image: quay.io/prometheus/node-exporter:v1.9.1
+          args:
+            - --path.procfs=/host/proc
+            - --path.sysfs=/host/sys
+            - --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/.+)($|/)
+          ports:
+            - containerPort: 9100
+              hostPort: 9100
+          resources:
+            requests: {cpu: 20m, memory: 32Mi}
+            limits: {memory: 64Mi}
+          volumeMounts:
+            - {name: proc, mountPath: /host/proc, readOnly: true}
+            - {name: sys, mountPath: /host/sys, readOnly: true}
+            - {name: root, mountPath: /rootfs, readOnly: true}
+      volumes:
+        - name: proc
+          hostPath: {path: /proc}
+        - name: sys
+          hostPath: {path: /sys}
+        - name: root
+          hostPath: {path: /}

manifests/monitoring/prometheus.yaml

@@ -0,0 +1,115 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: prometheus
+  namespace: monitoring
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: prometheus
+rules:
+  - apiGroups: [""]
+    resources: [nodes, nodes/proxy, services, endpoints, pods]
+    verbs: [get, list, watch]
+  - apiGroups: ["extensions", "networking.k8s.io"]
+    resources: [ingresses]
+    verbs: [get, list, watch]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: prometheus
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: prometheus
+subjects:
+  - kind: ServiceAccount
+    name: prometheus
+    namespace: monitoring
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: prometheus-config
+  namespace: monitoring
+data:
+  prometheus.yml: |
+    global:
+      scrape_interval: 15s
+      external_labels:
+        cluster: planck
+    scrape_configs:
+      - job_name: prometheus
+        static_configs:
+          - targets: ["localhost:9090"]
+      - job_name: node-exporter
+        kubernetes_sd_configs:
+          - role: node
+        relabel_configs:
+          - source_labels: [__meta_kubernetes_node_address_InternalIP]
+            target_label: instance_ip
+          - action: labelmap
+            regex: __meta_kubernetes_node_label_(.+)
+        metric_relabel_configs:
+          - source_labels: [__name__]
+            regex: go_.*
+            action: drop
+---
+apiVersion: apps/v1
+kind: StatefulSet
+metadata:
+  name: prometheus
+  namespace: monitoring
+spec:
+  serviceName: prometheus
+  replicas: 1
+  selector:
+    matchLabels: {app: prometheus}
+  template:
+    metadata:
+      labels: {app: prometheus}
+    spec:
+      serviceAccountName: prometheus
+      containers:
+        - name: prometheus
+          image: prom/prometheus:v3.6.0
+          args:
+            - --config.file=/etc/prometheus/prometheus.yml
+            - --storage.tsdb.retention.time=15d
+            - --storage.tsdb.path=/data
+          ports:
+            - containerPort: 9090
+          resources:
+            requests: {cpu: 150m, memory: 512Mi}
+            limits: {memory: 1Gi}
+          volumeMounts:
+            - {name: config, mountPath: /etc/prometheus}
+            - {name: data, mountPath: /data}
+      volumes:
+        - name: config
+          configMap: {name: prometheus-config}
+  volumeClaimTemplates:
+    - metadata: {name: data}
+      spec:
+        accessModes: [ReadWriteOnce]
+        storageClassName: local-path
+        resources:
+          requests: {storage: 20Gi}
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: prometheus
+  namespace: monitoring
+spec:
+  selector: {app: prometheus}
+  ports:
+    - port: 9090
+      targetPort: 9090