- Change manifests for Prometheus installation

- Change instructions for deploying Prometheus stack and Pushgateway
- Additional grouping to pushgateway to avoid overwriting of metrics in different pods / processes
- Bugfix to ensure good retrieval of css en js files in eveai_app

scaleway/manifests/base/applications/backend/eveai-chat-workers/deployment.yaml

@@ -54,6 +54,14 @@ spec:
               name: eveai-secrets
               key: PUSH_GATEWAY_PORT
               optional: true
+        - name: POD_NAME
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.name
+        - name: POD_NAMESPACE
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.namespace
         volumeMounts:
         - name: logs-volume
           mountPath: /app/logs

scaleway/manifests/base/applications/backend/eveai-entitlements/deployment.yaml

@@ -54,6 +54,14 @@ spec:
               name: eveai-secrets
               key: PUSH_GATEWAY_PORT
               optional: true
+        - name: POD_NAME
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.name
+        - name: POD_NAMESPACE
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.namespace
         resources:
           requests:
             cpu: "100m"

scaleway/manifests/base/applications/backend/eveai-workers/deployment.yaml

@@ -54,6 +54,14 @@ spec:
               name: eveai-secrets
               key: PUSH_GATEWAY_PORT
               optional: true
+        - name: POD_NAME
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.name
+        - name: POD_NAMESPACE
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.namespace
         resources:
           requests:
             cpu: "200m"

scaleway/manifests/base/applications/frontend/eveai-api/deployment.yaml

@@ -49,6 +49,14 @@ spec:
               name: eveai-secrets
               key: PUSH_GATEWAY_PORT
               optional: true
+        - name: POD_NAME
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.name
+        - name: POD_NAMESPACE
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.namespace
         resources:
           requests:
             cpu: "150m"

scaleway/manifests/base/applications/frontend/eveai-app/deployment.yaml

@@ -49,6 +49,14 @@ spec:
               name: eveai-secrets
               key: PUSH_GATEWAY_PORT
               optional: true
+        - name: POD_NAME
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.name
+        - name: POD_NAMESPACE
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.namespace
         resources:
           requests:
             cpu: "150m"

scaleway/manifests/base/applications/frontend/eveai-chat-client/deployment.yaml

@@ -49,6 +49,14 @@ spec:
               name: eveai-secrets
               key: PUSH_GATEWAY_PORT
               optional: true
+        - name: POD_NAME
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.name
+        - name: POD_NAMESPACE
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.namespace
         resources:
           requests:
             cpu: "150m"

scaleway/manifests/base/monitoring/prometheus-values.yaml

@@ -1,71 +0,0 @@
-# prometheus-values.yaml
-# Global settings
-fullnameOverride: "monitoring"
-
-# Prometheus configuration
-prometheus:
-  prometheusSpec:
-    retention: 15d
-    resources:
-      limits:
-        cpu: 500m
-        memory: 2Gi
-      requests:
-        cpu: 100m
-        memory: 512Mi
-    storageSpec:
-      volumeClaimTemplate:
-        spec:
-          accessModes: ["ReadWriteOnce"]
-          resources:
-            requests:
-              storage: 10Gi
-
-# Grafana configuration
-grafana:
-  enabled: true
-  adminPassword: "admin123"  # Change this for production
-  resources:
-    limits:
-      cpu: 200m
-      memory: 256Mi
-    requests:
-      cpu: 50m
-      memory: 128Mi
-  persistence:
-    enabled: true
-    size: 2Gi
-
-# AlertManager configuration
-alertmanager:
-  alertmanagerSpec:
-    resources:
-      limits:
-        cpu: 100m
-        memory: 256Mi
-      requests:
-        cpu: 10m
-        memory: 64Mi
-    storage:
-      volumeClaimTemplate:
-        spec:
-          accessModes: ["ReadWriteOnce"]
-          resources:
-            requests:
-              storage: 2Gi
-
-# Node Exporter
-nodeExporter:
-  enabled: true
-
-# Kube State Metrics
-kubeStateMetrics:
-  enabled: true
-
-# Disable components you might not need in staging
-kubeEtcd:
-  enabled: false
-kubeScheduler:
-  enabled: false
-kubeControllerManager:
-  enabled: false

scaleway/manifests/base/monitoring/values-monitoring.yaml

@@ -9,7 +9,7 @@ global:
 # Prometheus configuration
 prometheus:
   prometheusSpec:
-    retention: 30d
+    retention: 7d
     storageSpec:
       volumeClaimTemplate:
         spec:
@@ -17,21 +17,7 @@ prometheus:
           accessModes: ["ReadWriteOnce"]
           resources:
             requests:
-              storage: 50Gi
-
-    # External services monitoring (Scaleway managed services)
-    additionalScrapeConfigs:
-      - job_name: 'scaleway-redis'
-        static_configs:
-          - targets: ['redis-endpoint:6379']
-        metrics_path: /metrics
-        scrape_interval: 30s
-
-      - job_name: 'scaleway-postgresql'
-        static_configs:
-          - targets: ['postgres-endpoint:5432']
-        metrics_path: /metrics
-        scrape_interval: 30s
+              storage: 5Gi
 
     # Resource limits
     resources:
@@ -48,7 +34,7 @@ grafana:
   persistence:
     enabled: true
     storageClassName: scw-bssd
-    size: 10Gi
+    size: 2Gi
 
   # Resource limits
   resources:
@@ -97,7 +83,7 @@ alertmanager:
           accessModes: ["ReadWriteOnce"]
           resources:
             requests:
-              storage: 10Gi
+              storage: 1Gi
     resources:
       requests:
         memory: 128Mi