telecom-platform/deployments/kubernetes/manifests/monitoring-configmaps.yaml

---
apiVersion: v1
kind: ConfigMap
metadata:
  name: alertmanager-config
  namespace: telecom-monitoring
data:
  alertmanager.yml: |
    global:
      smtp_smarthost: 'localhost:587'
      smtp_from: '[email protected]'
    
    route:
      group_by: ['alertname']
      group_wait: 10s
      group_interval: 10s
      repeat_interval: 1h
      receiver: 'web.hook'
      routes:
      - match:
          severity: critical
        receiver: 'critical-alerts'
      - match:
          severity: warning
        receiver: 'warning-alerts'
    
    receivers:
    - name: 'web.hook'
      webhook_configs:
      - url: 'http://api-server-service:8000/webhooks/alertmanager'
        send_resolved: true
    - name: 'critical-alerts'
      webhook_configs:
      - url: 'http://api-server-service:8000/webhooks/critical-alerts'
        send_resolved: true
      email_configs:
      - to: '[email protected]'
        subject: '[CRITICAL] Telecom Platform Alert'
        body: |
          {{ range .Alerts }}
          Alert: {{ .Annotations.summary }}
          Description: {{ .Annotations.description }}
          Labels: {{ range .Labels.SortedPairs }}{{ .Name }}={{ .Value }} {{ end }}
          {{ end }}
    - name: 'warning-alerts'
      webhook_configs:
      - url: 'http://api-server-service:8000/webhooks/warning-alerts'
        send_resolved: true
    
    inhibit_rules:
    - source_match:
        severity: 'critical'
      target_match:
        severity: 'warning'
      equal: ['alertname', 'instance']
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: grafana-provisioning
  namespace: telecom-monitoring
data:
  datasources.yml: |
    apiVersion: 1
    
    datasources:
    - name: Prometheus
      type: prometheus
      access: proxy
      url: http://prometheus:9090
      isDefault: true
      editable: true
    
    - name: InfluxDB
      type: influxdb
      access: proxy
      url: http://influxdb-service:8086
      database: telecom
      user: admin
      jsonData:
        version: Flux
        organization: telecom
        defaultBucket: telecom
        tlsSkipVerify: true
      secureJsonData:
        token: telecom-super-secret-auth-token
      editable: true
  
  dashboards.yml: |
    apiVersion: 1
    
    providers:
    - name: 'telecom-dashboards'
      orgId: 1
      folder: ''
      type: file
      disableDeletion: false
      updateIntervalSeconds: 10
      allowUiUpdates: true
      options:
        path: /var/lib/grafana/dashboards
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: grafana-dashboards
  namespace: telecom-monitoring
data:
  telecom-overview.json: |
    {
      "annotations": {
        "list": [
          {
            "builtIn": 1,
            "datasource": {
              "type": "grafana",
              "uid": "-- Grafana --"
            },
            "enable": true,
            "hide": true,
            "iconColor": "rgba(0, 211, 255, 1)",
            "name": "Annotations & Alerts",
            "type": "dashboard"
          }
        ]
      },
      "description": "Telecom Platform Overview Dashboard",
      "editable": true,
      "fiscalYearStartMonth": 0,
      "graphTooltip": "shared_crosshair",
      "id": null,
      "links": [],
      "liveNow": false,
      "panels": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "description": "Total number of subscribers",
          "fieldConfig": {
            "defaults": {
              "color": {
                "mode": "palette-classic"
              },
              "custom": {
                "axisLabel": "",
                "axisPlacement": "auto",
                "barAlignment": 0,
                "drawStyle": "line",
                "fillOpacity": 10,
                "gradientMode": "none",
                "hideFrom": {
                  "legend": false,
                  "tooltip": false,
                  "vis": false
                },
                "lineInterpolation": "linear",
                "lineWidth": 1,
                "pointSize": 5,
                "scaleDistribution": {
                  "type": "linear"
                },
                "showPoints": "never",
                "spanNulls": false,
                "stacking": {
                  "group": "A",
                  "mode": "none"
                },
                "thresholdsStyle": {
                  "mode": "off"
                }
              },
              "mappings": [],
              "thresholds": {
                "mode": "absolute",
                "steps": [
                  {
                    "color": "green",
                    "value": null
                  },
                  {
                    "color": "red",
                    "value": 80
                  }
                ]
              },
              "unit": "short"
            },
            "overrides": []
          },
          "gridPos": {
            "h": 8,
            "w": 12,
            "x": 0,
            "y": 0
          },
          "id": 1,
          "options": {
            "legend": {
              "calcs": [],
              "displayMode": "list",
              "placement": "bottom"
            },
            "tooltip": {
              "mode": "single",
              "sort": "none"
            }
          },
          "targets": [
            {
              "datasource": {
                "type": "prometheus",
                "uid": "${DS_PROMETHEUS}"
              },
              "expr": "telecom_subscribers_total",
              "interval": "",
              "legendFormat": "Total Subscribers",
              "refId": "A"
            }
          ],
          "title": "Total Subscribers",
          "type": "timeseries"
        }
      ],
      "refresh": "5s",
      "schemaVersion": 38,
      "style": "dark",
      "tags": ["telecom"],
      "templating": {
        "list": []
      },
      "time": {
        "from": "now-1h",
        "to": "now"
      },
      "timepicker": {},
      "timezone": "",
      "title": "Telecom Platform Overview",
      "uid": "telecom-overview",
      "version": 1,
      "weekStart": ""
    }
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-rules
  namespace: telecom-monitoring
data:
  alert_rules.yml: |
    groups:
    - name: telecom_alerts
      rules:
      - alert: HighErrorRate
        expr: rate(telecom_http_requests_total{status_code=~"5.."}[5m]) > 0.1
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "High error rate detected"
          description: "Error rate is {{ $value }} errors per second"
      
      - alert: LowCreditBalance
        expr: telecom_credit_balance < 5
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: "Subscriber has low credit balance"
          description: "Subscriber {{ $labels.subscriber_id }} has balance {{ $value }}"
      
      - alert: HighMemoryUsage
        expr: (container_memory_usage_bytes / container_spec_memory_limit_bytes) * 100 > 90
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High memory usage"
          description: "Container {{ $labels.container }} memory usage is {{ $value }}%"
      
      - alert: HighCPUUsage
        expr: rate(container_cpu_usage_seconds_total[5m]) * 100 > 80
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High CPU usage"
          description: "Container {{ $labels.container }} CPU usage is {{ $value }}%"
      
      - alert: DatabaseConnectionFailure
        expr: up{job="postgres"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Database connection failure"
          description: "PostgreSQL database is down"
      
      - alert: RedisConnectionFailure
        expr: up{job="redis"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Redis connection failure"
          description: "Redis cache is down"
      
      - alert: ChargingEngineDown
        expr: up{job="telecom-charging-engine"} == 0
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "Charging engine is down"
          description: "Rust charging engine service is not responding"
      
      - alert: PacketGatewayDown
        expr: up{job="telecom-packet-gateway"} == 0
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "Packet gateway is down"
          description: "eBPF packet gateway service is not responding"