Automatic notifications for Gateway problems.

/etc/prometheus/rules/gateway-alerts.yml:

groups:
  - name: data-gateway
    interval: 30s
    rules:
      # Gateway not reachable
      - alert: GatewayDown
        expr: up{job="data-gateway"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Data Gateway is not reachable"
          description: "{{ $labels.instance }} has been unreachable for 1 minute."
 
      # High error rate
      - alert: GatewayHighErrorRate
        expr: |
          sum(rate(http_requests_total{job="data-gateway",status=~"5.."}[5m]))
          /
          sum(rate(http_requests_total{job="data-gateway"}[5m]))
          > 0.05
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High error rate in Gateway"
          description: "Error rate is {{ $value | humanizePercentage }} (> 5%)."
 
      # Slow response times
      - alert: GatewaySlowResponses
        expr: |
          histogram_quantile(0.95,
            sum(rate(http_request_duration_seconds_bucket{job="data-gateway"}[5m])) by (le)
          ) > 2
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Gateway responding slowly"
          description: "P95 response time is {{ $value | humanizeDuration }}."
 
      # High memory usage
      - alert: GatewayHighMemory
        expr: |
          process_resident_memory_bytes{job="data-gateway"}
          / 1024 / 1024 > 450
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "Gateway using high memory"
          description: "Memory usage is {{ $value | humanize }}MB."
 
      # Certificate expiring soon
      - alert: GatewayCertExpiringSoon
        expr: |
          (probe_ssl_earliest_cert_expiry{job="gateway-tls"} - time())
          / 86400 < 14
        for: 1h
        labels:
          severity: warning
        annotations:
          summary: "Gateway TLS certificate expiring soon"
          description: "Certificate expires in {{ $value | humanize }} days."

/etc/prometheus/prometheus.yml:

rule_files:
  - "rules/*.yml"

alerting:
  alertmanagers:
    - static_configs:
        - targets:
            - alertmanager:9093

# Reload Prometheus
curl -X POST http://localhost:9090/-/reload

/etc/alertmanager/alertmanager.yml:

global:
  resolve_timeout: 5m
  smtp_smarthost: 'smtp.example.com:587'
  smtp_from: 'alertmanager@example.com'
  smtp_auth_username: 'alertmanager@example.com'
  smtp_auth_password: 'secret'

route:
  group_by: ['alertname', 'severity']
  group_wait: 30s
  group_interval: 5m
  repeat_interval: 4h
  receiver: 'default'
  routes:
    # Critical alerts immediately
    - match:
        severity: critical
      receiver: 'critical'
      group_wait: 10s
      repeat_interval: 1h

receivers:
  - name: 'default'
    email_configs:
      - to: 'ops@example.com'
        send_resolved: true

  - name: 'critical'
    email_configs:
      - to: 'oncall@example.com'
        send_resolved: true
    slack_configs:
      - api_url: 'https://hooks.slack.com/services/XXX/YYY/ZZZ'
        channel: '#alerts-critical'
        send_resolved: true
        title: '{{ .Status | toUpper }}: {{ .CommonAnnotations.summary }}'
        text: '{{ .CommonAnnotations.description }}'

inhibit_rules:
  - source_match:
      severity: 'critical'
    target_match:
      severity: 'warning'
    equal: ['alertname', 'instance']

# Slack section only
receivers:
  - name: 'slack-alerts'
    slack_configs:
      - api_url: 'https://hooks.slack.com/services/XXX/YYY/ZZZ'
        channel: '#gateway-alerts'
        send_resolved: true
        title: '{{ if eq .Status "firing" }}ALERT{{ else }}RESOLVED{{ end }} {{ .CommonAnnotations.summary }}'
        text: |
          *Alert:* {{ .CommonLabels.alertname }}
          *Severity:* {{ .CommonLabels.severity }}
          *Description:* {{ .CommonAnnotations.description }}
          *Instance:* {{ .CommonLabels.instance }}

# Via Prometheus MS Teams Webhook
receivers:
  - name: 'teams-alerts'
    webhook_configs:
      - url: 'http://prometheus-msteams:2000/gateway'
        send_resolved: true

# Check alert rules
curl http://localhost:9090/api/v1/rules | jq '.data.groups[].rules[] | {alert: .name, state: .state}'
 
# Active alerts
curl http://localhost:9090/api/v1/alerts | jq '.data.alerts[]'
 
# Alertmanager status
curl http://localhost:9093/api/v2/status | jq
 
# Send test alert
curl -X POST http://localhost:9093/api/v2/alerts \
  -H "Content-Type: application/json" \
  -d '[{
    "labels": {"alertname": "TestAlert", "severity": "warning"},
    "annotations": {"summary": "Test Alert", "description": "This is a test."}
  }]'

• Prometheus - Collect metrics
• Grafana - Visualization
• Set Up TLS - Certificate alerting

« <- Grafana Dashboard | -> Operator Overview »

Wolfgang van der Stille @ EMSR DATA d.o.o. - Data Gateway Professional