fixing gradle build

2025-07-30 00:01:22 +02:00
parent 965aa68fa7
commit ea75bbdb24
33 changed files with 497 additions and 175 deletions
@@ -0,0 +1,82 @@
+global:
+  resolve_timeout: 5m
+  # SMTP configuration for email alerts
+  smtp_smarthost: 'smtp.example.com:587'
+  smtp_from: 'alertmanager@meldestelle.at'
+  smtp_auth_username: 'alertmanager@meldestelle.at'
+  smtp_auth_password: 'password' # Use environment variable in production
+  smtp_require_tls: true
+
+# The root route on which each incoming alert enters.
+route:
+  # The root route must not have any matchers as it is the entry point for all alerts
+  # The default receiver is the one that handles alerts that don't match any of the specific routes
+  receiver: 'email-notifications'
+
+  # How long to wait before sending a notification again if it has already been sent successfully
+  repeat_interval: 4h
+
+  # How long to initially wait to send a notification for a group of alerts
+  group_wait: 30s
+
+  # How long to wait before sending a notification about new alerts that are added to a group
+  group_interval: 5m
+
+  # A default grouping of alerts
+  group_by: ['alertname', 'cluster', 'service']
+
+  # Child routes for specific alert categories
+  routes:
+  - receiver: 'slack-critical'
+    matchers:
+      - severity="critical"
+    repeat_interval: 1h
+
+  - receiver: 'slack-warnings'
+    matchers:
+      - severity="warning"
+    repeat_interval: 12h
+
+# Inhibition rules allow to mute a set of alerts given that another alert is firing
+inhibit_rules:
+  - source_matchers:
+      - severity="critical"
+    target_matchers:
+      - severity="warning"
+    # Apply inhibition if the alertname is the same
+    equal: ['alertname', 'cluster', 'service']
+
+# Receivers define notification integrations
+receivers:
+- name: 'email-notifications'
+  email_configs:
+  - to: 'admin@meldestelle.at'
+    send_resolved: true
+
+- name: 'slack-critical'
+  slack_configs:
+  - api_url: 'https://hooks.slack.com/services/REPLACE_WITH_YOUR_WEBHOOK_URL'
+    channel: '#alerts-critical'
+    send_resolved: true
+    title: '{{ .CommonAnnotations.summary }}'
+    text: >-
+      {{ range .Alerts }}
+        *Alert:* {{ .Annotations.summary }}
+        *Description:* {{ .Annotations.description }}
+        *Severity:* {{ .Labels.severity }}
+        *Instance:* {{ .Labels.instance }}
+      {{ end }}
+
+- name: 'slack-warnings'
+  slack_configs:
+  - api_url: 'https://hooks.slack.com/services/REPLACE_WITH_YOUR_WEBHOOK_URL'
+    channel: '#alerts-warnings'
+    send_resolved: true
+    title: '{{ .CommonAnnotations.summary }}'
+    text: >-
+      {{ range .Alerts }}
+        *Alert:* {{ .Annotations.summary }}
+        *Description:* {{ .Annotations.description }}
+        *Severity:* {{ .Labels.severity }}
+        *Instance:* {{ .Labels.instance }}
+      {{ end }}
@@ -0,0 +1,62 @@
+groups:
+  - name: meldestelle_alerts
+    rules:
+      # Alert for high memory usage
+      - alert: HighMemoryUsage
+        expr: (jvm_memory_used_bytes{area="heap"} / jvm_memory_max_bytes{area="heap"}) * 100 > 85
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High memory usage ({{ $value }}%)"
+          description: "JVM memory usage is above 85% for 5 minutes.\n  Instance: {{ $labels.instance }}\n  Service: {{ $labels.service }}"
+
+      # Alert for high CPU usage
+      - alert: HighCpuUsage
+        expr: process_cpu_usage > 0.85
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High CPU usage ({{ $value }})"
+          description: "CPU usage is above 85% for 5 minutes.\n  Instance: {{ $labels.instance }}\n  Service: {{ $labels.service }}"
+
+      # Alert for high error rate
+      - alert: HighErrorRate
+        expr: sum(rate(http_server_requests_seconds_count{status=~"5.."}[5m])) / sum(rate(http_server_requests_seconds_count[5m])) * 100 > 5
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "High error rate ({{ $value }}%)"
+          description: "Error rate is above 5% for 2 minutes.\n  Instance: {{ $labels.instance }}\n  Service: {{ $labels.service }}"
+
+      # Alert for service unavailability
+      - alert: ServiceUnavailable
+        expr: up{job="meldestelle-server"} == 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Service unavailable"
+          description: "Meldestelle service is down.\n  Instance: {{ $labels.instance }}"
+
+      # Alert for slow response time
+      - alert: SlowResponseTime
+        expr: http_server_requests_seconds_sum / http_server_requests_seconds_count > 1
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Slow response time ({{ $value }}s)"
+          description: "Average response time is above 1 second for 5 minutes.\n  Instance: {{ $labels.instance }}\n  Path: {{ $labels.uri }}"
+
+      # Alert for high GC pause time
+      - alert: HighGcPauseTime
+        expr: jvm_gc_pause_seconds_sum / jvm_gc_pause_seconds_count > 0.5
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High GC pause time ({{ $value }}s)"
+          description: "Average GC pause time is above 0.5 seconds for 5 minutes.\n  Instance: {{ $labels.instance }}"