Changeset 0.33.0 (#207)

Co-authored-by: Jeffrey Smith <jasafpro@gmail.com>
Co-committed-by: Jeffrey Smith <jasafpro@gmail.com>

chart/templates/configmap.yaml

@@ -19,6 +19,8 @@ data:
   EXTRACTION_CONCURRENCY: {{ .Values.extraction.concurrency | quote }}
   WORKSPACE_INDEXING_ENABLED: {{ .Values.workspace.indexingEnabled | quote }}
   WORKSPACE_INDEX_CONCURRENCY: {{ .Values.workspace.indexConcurrency | quote }}
+  LOG_FORMAT: {{ .Values.logging.format | default "text" | quote }}
+  LOG_LEVEL: {{ .Values.logging.level | default "info" | quote }}
   CORS_ALLOWED_ORIGINS: {{ .Values.corsAllowedOrigins | quote }}
   {{- if .Values.storage.s3.endpoint }}
   S3_ENDPOINT: {{ .Values.storage.s3.endpoint | quote }}

chart/templates/grafana-dashboard-configmap.yaml

@@ -0,0 +1,14 @@
+{{- if .Values.monitoring.grafanaDashboard.enabled }}
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ include "switchboard.fullname" . }}-grafana-dashboard
+  labels:
+    {{- include "switchboard.labels" . | nindent 4 }}
+    {{- with .Values.monitoring.grafanaDashboard.labels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
+data:
+  switchboard-overview.json: |-
+    {{- .Files.Get "dashboards/switchboard-overview.json" | nindent 4 }}
+{{- end }}

chart/templates/prometheusrule.yaml

@@ -0,0 +1,61 @@
+{{- if .Values.monitoring.prometheusRule.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: {{ include "switchboard.fullname" . }}-alerts
+  labels:
+    {{- include "switchboard.labels" . | nindent 4 }}
+    {{- with .Values.monitoring.prometheusRule.labels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
+spec:
+  groups:
+    - name: switchboard.rules
+      rules:
+        - alert: SwitchboardPodRestart
+          expr: increase(kube_pod_container_status_restarts_total{container="backend"}[1h]) > 0
+          for: 0m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Switchboard backend pod restarted (possible OOM)"
+        - alert: SwitchboardProviderDown
+          expr: switchboard_provider_status > 2
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Provider {{`{{ $labels.provider_config_id }}`}} is down"
+        - alert: SwitchboardDBPoolExhaustion
+          expr: switchboard_db_in_use_connections / switchboard_db_open_connections > 0.8
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "DB connection pool >80% utilized"
+        - alert: SwitchboardHighErrorRate
+          expr: |
+            sum(rate(switchboard_http_requests_total{status=~"5.."}[5m]))
+            / sum(rate(switchboard_http_requests_total[5m])) > 0.05
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "HTTP 5xx error rate exceeds 5%"
+        - alert: SwitchboardTaskFailureRate
+          expr: |
+            rate(switchboard_task_executions_total{status="error"}[15m])
+            / rate(switchboard_task_executions_total[15m]) > 0.25
+          for: 10m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Task failure rate exceeds 25%"
+        - alert: SwitchboardNoCompletions
+          expr: sum(rate(switchboard_completions_total[10m])) == 0
+          for: 15m
+          labels:
+            severity: critical
+          annotations:
+            summary: "No completions processed in 15 minutes"
+{{- end }}

chart/templates/servicemonitor.yaml

@@ -0,0 +1,20 @@
+{{- if .Values.monitoring.serviceMonitor.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: {{ include "switchboard.fullname" . }}
+  labels:
+    {{- include "switchboard.labels" . | nindent 4 }}
+    {{- with .Values.monitoring.serviceMonitor.labels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
+spec:
+  selector:
+    matchLabels:
+      {{- include "switchboard.selectorLabels" . | nindent 6 }}
+      app.kubernetes.io/component: backend
+  endpoints:
+    - port: http
+      path: {{ .Values.monitoring.serviceMonitor.path | default "/metrics" }}
+      interval: {{ .Values.monitoring.serviceMonitor.interval | default "30s" }}
+{{- end }}

chart/templates/services.yaml

@@ -4,6 +4,10 @@ metadata:
   name: {{ .Release.Name }}-backend
   labels:
     {{- include "switchboard.backend.labels" . | nindent 4 }}
+  annotations:
+    prometheus.io/scrape: "true"
+    prometheus.io/port: {{ .Values.backend.port | quote }}
+    prometheus.io/path: "/metrics"
 spec:
   type: ClusterIP
   ports: