Merge branch 'master' of https://github.com/OneUptime/oneuptime

HelmChart/Public/kubernetes-agent/templates/configmap-daemonset.yaml

@@ -17,7 +17,7 @@ data:
       kubeletstats:
         collection_interval: {{ .Values.collectionInterval }}
         auth_type: serviceAccount
-        endpoint: "https://${env:NODE_NAME}:10250"
+        endpoint: "https://${env:NODE_IP}:10250"
         insecure_skip_verify: true
         metric_groups:
           - node
@@ -130,12 +130,30 @@ data:
           - sources:
               - from: connection
 
-      # Stamp with cluster name
+      # Stamp with cluster name and default service name
       resource:
         attributes:
           - key: k8s.cluster.name
             value: {{ .Values.clusterName | quote }}
             action: upsert
+          - key: service.name
+            value: "kubernetes-agent-{{ .Values.clusterName }}"
+            action: upsert
+
+      # Set service.name from deployment/statefulset/daemonset name when available
+      transform:
+        log_statements:
+          - context: resource
+            statements:
+              - set(attributes["service.name"], attributes["k8s.deployment.name"]) where attributes["k8s.deployment.name"] != nil and attributes["k8s.deployment.name"] != ""
+              - set(attributes["service.name"], attributes["k8s.statefulset.name"]) where attributes["k8s.statefulset.name"] != nil and attributes["k8s.statefulset.name"] != "" and attributes["k8s.deployment.name"] == nil
+              - set(attributes["service.name"], attributes["k8s.daemonset.name"]) where attributes["k8s.daemonset.name"] != nil and attributes["k8s.daemonset.name"] != "" and attributes["k8s.deployment.name"] == nil and attributes["k8s.statefulset.name"] == nil
+        metric_statements:
+          - context: resource
+            statements:
+              - set(attributes["service.name"], attributes["k8s.deployment.name"]) where attributes["k8s.deployment.name"] != nil and attributes["k8s.deployment.name"] != ""
+              - set(attributes["service.name"], attributes["k8s.statefulset.name"]) where attributes["k8s.statefulset.name"] != nil and attributes["k8s.statefulset.name"] != "" and attributes["k8s.deployment.name"] == nil
+              - set(attributes["service.name"], attributes["k8s.daemonset.name"]) where attributes["k8s.daemonset.name"] != nil and attributes["k8s.daemonset.name"] != "" and attributes["k8s.deployment.name"] == nil and attributes["k8s.statefulset.name"] == nil
 
       batch:
         send_batch_size: 1024
@@ -163,6 +181,7 @@ data:
             - memory_limiter
             - k8sattributes
             - resource
+            - transform
             - batch
           exporters:
             - otlphttp
@@ -173,6 +192,7 @@ data:
             - memory_limiter
             - k8sattributes
             - resource
+            - transform
             - batch
           exporters:
             - otlphttp

HelmChart/Public/kubernetes-agent/templates/configmap-deployment.yaml

@@ -63,13 +63,28 @@ data:
             mode: pull
             interval: {{ .Values.resourceSpecs.interval }}
             group: batch
+          - name: persistentvolumeclaims
+            mode: pull
+            interval: {{ .Values.resourceSpecs.interval }}
+          - name: persistentvolumes
+            mode: pull
+            interval: {{ .Values.resourceSpecs.interval }}
+          - name: horizontalpodautoscalers
+            mode: pull
+            interval: {{ .Values.resourceSpecs.interval }}
+            group: autoscaling
+          - name: verticalpodautoscalers
+            mode: pull
+            interval: {{ .Values.resourceSpecs.interval }}
+            group: autoscaling.k8s.io
           {{- end }}
 
-      {{- if .Values.controlPlane.enabled }}
-      # Scrape control plane metrics via Prometheus endpoints
+      {{- if or .Values.controlPlane.enabled .Values.serviceMesh.enabled }}
+      # Scrape metrics via Prometheus endpoints (control plane and/or service mesh)
       prometheus:
         config:
           scrape_configs:
+            {{- if .Values.controlPlane.enabled }}
             - job_name: etcd
               scheme: https
               tls_config:
@@ -109,6 +124,53 @@ data:
                 - targets:
                     - {{ . | quote }}
                 {{- end }}
+            {{- end }}
+            {{- if and .Values.serviceMesh.enabled (eq .Values.serviceMesh.provider "istio") }}
+            - job_name: envoy-stats
+              metrics_path: /stats/prometheus
+              scrape_interval: {{ .Values.serviceMesh.istio.scrapeInterval }}
+              kubernetes_sd_configs:
+                - role: pod
+              relabel_configs:
+                - source_labels: [__meta_kubernetes_pod_container_name]
+                  action: keep
+                  regex: istio-proxy
+                - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_port, __meta_kubernetes_pod_ip]
+                  action: replace
+                  regex: (\d+);((([0-9]+?)(\.|$)){4})
+                  replacement: $2:15090
+                  target_label: __address__
+                - action: labelmap
+                  regex: __meta_kubernetes_pod_label_(.+)
+                - source_labels: [__meta_kubernetes_namespace]
+                  action: replace
+                  target_label: namespace
+                - source_labels: [__meta_kubernetes_pod_name]
+                  action: replace
+                  target_label: pod_name
+            {{- end }}
+            {{- if and .Values.serviceMesh.enabled (eq .Values.serviceMesh.provider "linkerd") }}
+            - job_name: linkerd-proxy
+              metrics_path: /metrics
+              scrape_interval: {{ .Values.serviceMesh.linkerd.scrapeInterval }}
+              kubernetes_sd_configs:
+                - role: pod
+              relabel_configs:
+                - source_labels: [__meta_kubernetes_pod_container_name]
+                  action: keep
+                  regex: linkerd-proxy
+                - source_labels: [__meta_kubernetes_pod_container_port_name]
+                  action: keep
+                  regex: linkerd-admin
+                - action: labelmap
+                  regex: __meta_kubernetes_pod_label_(.+)
+                - source_labels: [__meta_kubernetes_namespace]
+                  action: replace
+                  target_label: namespace
+                - source_labels: [__meta_kubernetes_pod_name]
+                  action: replace
+                  target_label: pod_name
+            {{- end }}
       {{- end }}
 
     processors:
@@ -145,12 +207,15 @@ data:
           - sources:
               - from: connection
 
-      # Stamp all telemetry with the cluster name
+      # Stamp all telemetry with the cluster name and service name
       resource:
         attributes:
           - key: k8s.cluster.name
             value: {{ .Values.clusterName | quote }}
             action: upsert
+          - key: service.name
+            value: "kubernetes-agent-{{ .Values.clusterName }}"
+            action: upsert
 
       # Batch telemetry for efficient export
       batch:
@@ -187,7 +252,7 @@ data:
         metrics:
           receivers:
             - k8s_cluster
-            {{- if .Values.controlPlane.enabled }}
+            {{- if or .Values.controlPlane.enabled .Values.serviceMesh.enabled }}
             - prometheus
             {{- end }}
           processors:

HelmChart/Public/kubernetes-agent/templates/daemonset.yaml

@@ -34,6 +34,10 @@ spec:
               valueFrom:
                 fieldRef:
                   fieldPath: spec.nodeName
+            - name: NODE_IP
+              valueFrom:
+                fieldRef:
+                  fieldPath: status.hostIP
             - name: ONEUPTIME_API_KEY
               valueFrom:
                 secretKeyRef:

HelmChart/Public/kubernetes-agent/templates/rbac.yaml

@@ -66,6 +66,24 @@ rules:
     resources:
       - events
     verbs: ["get", "list", "watch"]
+  - apiGroups: ["autoscaling.k8s.io"]
+    resources:
+      - verticalpodautoscalers
+    verbs: ["get", "list", "watch"]
+{{- if and .Values.serviceMesh.enabled (eq .Values.serviceMesh.provider "istio") }}
+  - apiGroups: ["networking.istio.io"]
+    resources:
+      - virtualservices
+      - destinationrules
+      - gateways
+      - serviceentries
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["security.istio.io"]
+    resources:
+      - peerauthentications
+      - authorizationpolicies
+    verbs: ["get", "list", "watch"]
+{{- end }}
   # For kubeletstats receiver
   - nonResourceURLs:
       - /metrics

HelmChart/Public/kubernetes-agent/values.yaml

@@ -80,6 +80,16 @@ resourceSpecs:
 # Collection intervals
 collectionInterval: 30s
 
+# Service mesh observability (Istio / Linkerd sidecar metrics)
+serviceMesh:
+  enabled: false
+  # Supported providers: "istio", "linkerd"
+  provider: "istio"
+  istio:
+    scrapeInterval: 15s
+  linkerd:
+    scrapeInterval: 15s
+
 # Service account configuration
 serviceAccount:
   create: true