k6 step-load rig: staircase scenarios, per-step/per-endpoint tagging, live Prometheus remote-write, Grafana dashboard

manifests/monitoring/grafana-dashboards.yaml

@@ -0,0 +1,86 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: grafana-dashboard-provider
+  namespace: monitoring
+data:
+  dashboards.yaml: |
+    apiVersion: 1
+    providers:
+      - name: default
+        orgId: 1
+        folder: ""
+        type: file
+        disableDeletion: false
+        updateIntervalSeconds: 30
+        options:
+          path: /var/lib/grafana/dashboards
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: grafana-dashboards
+  namespace: monitoring
+data:
+  k6-step-load.json: |
+    {
+      "title": "k6 Step Load",
+      "uid": "k6step",
+      "timezone": "browser",
+      "refresh": "5s",
+      "time": { "from": "now-30m", "to": "now" },
+      "panels": [
+        {
+          "id": 1, "type": "timeseries", "title": "Request rate (the staircase)",
+          "gridPos": {"x": 0, "y": 0, "w": 24, "h": 8},
+          "targets": [
+            {"expr": "sum(rate(k6_http_reqs_total[30s]))", "legendFormat": "total rps"},
+            {"expr": "sum by (name) (rate(k6_http_reqs_total[30s]))", "legendFormat": "{{name}}"}
+          ],
+          "fieldConfig": {"defaults": {"unit": "reqps"}, "overrides": []}
+        },
+        {
+          "id": 2, "type": "timeseries", "title": "Latency avg / p50 / p95 / p99",
+          "gridPos": {"x": 0, "y": 8, "w": 12, "h": 8},
+          "targets": [
+            {"expr": "k6_http_req_duration_avg", "legendFormat": "avg"},
+            {"expr": "k6_http_req_duration_p50", "legendFormat": "p50"},
+            {"expr": "k6_http_req_duration_p95", "legendFormat": "p95"},
+            {"expr": "k6_http_req_duration_p99", "legendFormat": "p99"}
+          ],
+          "fieldConfig": {"defaults": {"unit": "ms"}, "overrides": []}
+        },
+        {
+          "id": 3, "type": "timeseries", "title": "p95 latency per step",
+          "gridPos": {"x": 12, "y": 8, "w": 12, "h": 8},
+          "targets": [
+            {"expr": "k6_http_req_duration_p95", "legendFormat": "{{step}}"}
+          ],
+          "fieldConfig": {"defaults": {"unit": "ms"}, "overrides": []}
+        },
+        {
+          "id": 4, "type": "timeseries", "title": "p95 latency per endpoint",
+          "gridPos": {"x": 0, "y": 16, "w": 12, "h": 8},
+          "targets": [
+            {"expr": "k6_http_req_duration_p95", "legendFormat": "{{name}}"}
+          ],
+          "fieldConfig": {"defaults": {"unit": "ms"}, "overrides": []}
+        },
+        {
+          "id": 5, "type": "timeseries", "title": "Error rate",
+          "gridPos": {"x": 12, "y": 16, "w": 12, "h": 8},
+          "targets": [
+            {"expr": "sum(rate(k6_http_req_failed_total[30s])) / sum(rate(k6_http_reqs_total[30s]))", "legendFormat": "error fraction"}
+          ],
+          "fieldConfig": {"defaults": {"unit": "percentunit", "min": 0, "max": 1}, "overrides": []}
+        },
+        {
+          "id": 6, "type": "timeseries", "title": "Active VUs",
+          "gridPos": {"x": 0, "y": 24, "w": 24, "h": 6},
+          "targets": [{"expr": "k6_vus", "legendFormat": "vus"}],
+          "fieldConfig": {"defaults": {"unit": "short"}, "overrides": []}
+        }
+      ],
+      "schemaVersion": 39,
+      "version": 1
+    }

manifests/monitoring/grafana.yaml

@@ -49,9 +49,15 @@ spec:
             limits: {memory: 512Mi}
           volumeMounts:
             - {name: datasources, mountPath: /etc/grafana/provisioning/datasources}
+            - {name: dashboard-provider, mountPath: /etc/grafana/provisioning/dashboards}
+            - {name: dashboards, mountPath: /var/lib/grafana/dashboards}
       volumes:
         - name: datasources
           configMap: {name: grafana-datasources}
+        - name: dashboard-provider
+          configMap: {name: grafana-dashboard-provider}
+        - name: dashboards
+          configMap: {name: grafana-dashboards}
 ---
 apiVersion: v1
 kind: Service

manifests/monitoring/prometheus.yaml

@@ -84,6 +84,7 @@ spec:
             - --config.file=/etc/prometheus/prometheus.yml
             - --storage.tsdb.retention.time=15d
             - --storage.tsdb.path=/data
+            - --web.enable-remote-write-receiver
           ports:
             - containerPort: 9090
           resources: