feat(graph-proxy): test

backend/graph-proxy/src/graphql/mod.rs

@@ -34,6 +34,7 @@ use axum_extra::{
 use lazy_static::lazy_static;
 use opentelemetry::KeyValue;
 use std::fmt::Display;
+use tracing::instrument;
 use workflow_templates::WorkflowTemplatesMutation;
 
 /// The root schema of the service
@@ -60,6 +61,7 @@ pub struct NodeQuery;
 
 #[Object]
 impl NodeQuery {
+    #[instrument(name = "graph_proxy_node_query", skip(self, ctx))]
     async fn node(&self, ctx: &Context<'_>, id: ID) -> Option<NodeValue> {
         let id_str = id.to_string();
         let parts: Vec<&str> = id_str.split(':').collect();

charts/monitoring/staging-values.yaml

@@ -1,6 +1,14 @@
 cluster: pollux
 
 grafana:
+  datasources:
+    datasources.yaml:
+      apiVersion: 1
+      datasources:
+        - name: Prometheus
+          type: prometheus
+          url: "http://{{ .Release.Name }}-prometheus-server:80"
+          isDefault: true
   ingress:
     enabled: true
     path: "/"

charts/otel-collector/templates/role.yaml

@@ -5,5 +5,5 @@ metadata:
   name: opentelemetry-collector
 rules:
   - apiGroups: [""]
-    resources: ["pods", "services", "endpoints"]
+    resources: ["pods", "services", "endpoints", "namespaces", "nodes", "resourcequotas"]
     verbs: ["get", "list", "watch"]

charts/otel-collector/values.yaml

@@ -6,6 +6,20 @@ opentelemetry-collector:
   presets:
     kubernetesAttributes:
       enabled: true
+  clusterRole:
+    rules:
+      - apiGroups: [""]
+        resources: ["replicationcontrollers", "resourcequotas", "services", "endpoints"]
+        verbs: ["get", "list", "watch"]
+      - apiGroups: ["apps"]
+        resources: ["deployments", "replicasets", "statefulsets", "daemonsets"]
+        verbs: ["get", "list", "watch"]
+      - apiGroups: ["batch"]
+        resources: ["jobs", "cronjobs"]
+        verbs: ["get", "list", "watch"]
+      - apiGroups: ["autoscaling"]
+        resources: ["horizontalpodautoscalers"]
+        verbs: ["get", "list", "watch"]
   ports:
     prometheus:
       enabled: true
@@ -44,6 +58,9 @@ opentelemetry-collector:
       memory: 24Gi
   config:
     processors:
+      groupbyattrs:
+        keys:
+          - k8s.namespace.name
       batch:
         send_batch_size: 512
       k8sattributes:
@@ -119,6 +136,33 @@ opentelemetry-collector:
                 - source_labels: [__meta_kubernetes_pod_phase]
                   regex: Pending|Succeeded|Failed|Completed
                   action: drop
+            - job_name: 'kubelet-resource-metrics'
+              scheme: https
+              tls_config:
+                insecure_skip_verify: true
+              bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+              kubernetes_sd_configs:
+                - role: node
+              relabel_configs:
+                - action: labelmap
+                  regex: __meta_kubernetes_node_label_(.+)
+                - target_label: __address__
+                  replacement: kubernetes.default.svc:443
+                - source_labels: [__meta_kubernetes_node_name]
+                  regex: (.+)
+                  target_label: __metrics_path__
+                  replacement: /api/v1/nodes/$1/proxy/metrics/resource
+                - source_labels: [__meta_kubernetes_node_name]
+                  target_label: node
+      k8s_cluster:
+        collection_interval: 30s
+        auth_type: serviceAccount
+        resource_attributes:
+          k8s.namespace.name:
+            enabled: true
+        allocatable_types_to_report:
+          - cpu
+          - memory
       otlp:
         protocols:
           grpc:
@@ -147,8 +191,10 @@ opentelemetry-collector:
           receivers:
             - prometheus
             - otlp
+            - k8s_cluster
           processors:
             - k8sattributes
+            - groupbyattrs
             - memory_limiter
             - batch
           exporters:

charts/workflows-cluster/staging-values.yaml

@@ -14,6 +14,9 @@ vcluster:
       deployment:
         replicas: 2
 
+    serviceMonitor:
+      enabled: true
+
   experimental:
     deploy:
       vcluster: