Publish

dist/rules/oracle-database/iamseth-oracledb-exporter.yml

@@ -0,0 +1,85 @@
+groups:
+
+- name: IamsethOracledbExporter
+
+  
+  rules:
+
+    # 1m delay allows a restart without triggering an alert.
+    - alert: OracleDbDown
+      expr: 'oracledb_up == 0'
+      for: 1m
+      labels:
+        severity: critical
+      annotations:
+        summary: Oracle DB down (instance {{ $labels.instance }})
+        description: "Oracle Database instance is down on {{ $labels.instance }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    # Threshold is workload-dependent. Adjust 85% to suit your environment.
+    - alert: OracleDbSessionsReachingLimit(>85%)
+      expr: 'oracledb_resource_current_utilization{resource_name="sessions"} / oracledb_resource_limit_value{resource_name="sessions"} * 100 > 85 and oracledb_resource_limit_value{resource_name="sessions"} > 0'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Oracle DB sessions reaching limit (> 85%) (instance {{ $labels.instance }})
+        description: "Oracle Database session utilization is above 85% on {{ $labels.instance }} (current value: {{ $value }}%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    # Threshold is workload-dependent. Adjust 85% to suit your environment.
+    - alert: OracleDbProcessesReachingLimit(>85%)
+      expr: 'oracledb_resource_current_utilization{resource_name="processes"} / oracledb_resource_limit_value{resource_name="processes"} * 100 > 85 and oracledb_resource_limit_value{resource_name="processes"} > 0'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Oracle DB processes reaching limit (> 85%) (instance {{ $labels.instance }})
+        description: "Oracle Database process utilization is above 85% on {{ $labels.instance }} (current value: {{ $value }}%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: OracleDbTablespaceReachingCapacity(>85%)
+      expr: 'oracledb_tablespace_used_percent > 85'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Oracle DB tablespace reaching capacity (> 85%) (instance {{ $labels.instance }})
+        description: "Oracle Database tablespace {{ $labels.tablespace }} is above 85% usage on {{ $labels.instance }} (current value: {{ $value }}%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: OracleDbTablespaceFull(>95%)
+      expr: 'oracledb_tablespace_used_percent > 95'
+      for: 5m
+      labels:
+        severity: critical
+      annotations:
+        summary: Oracle DB tablespace full (> 95%) (instance {{ $labels.instance }})
+        description: "Oracle Database tablespace {{ $labels.tablespace }} is critically full on {{ $labels.instance }} (current value: {{ $value }}%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    # A high rollback rate (>20%) often indicates application-level issues such as deadlocks, constraint violations, or poorly designed transactions.
+    - alert: OracleDbHighUserRollbacks
+      expr: 'rate(oracledb_activity_user_rollbacks[5m]) / (rate(oracledb_activity_user_commits[5m]) + rate(oracledb_activity_user_rollbacks[5m])) * 100 > 20 and (rate(oracledb_activity_user_commits[5m]) + rate(oracledb_activity_user_rollbacks[5m])) > 0'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Oracle DB high user rollbacks (instance {{ $labels.instance }})
+        description: "Oracle Database on {{ $labels.instance }} has a high rollback rate ({{ $value }}% of transactions are rolled back)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    # Threshold is highly workload-dependent. Adjust 200 to suit your environment.
+    - alert: OracleDbTooManyActiveSessions
+      expr: 'oracledb_sessions_activity{status="ACTIVE", type="USER"} > 200'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Oracle DB too many active sessions (instance {{ $labels.instance }})
+        description: "Oracle Database on {{ $labels.instance }} has too many active user sessions (current value: {{ $value }})\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    # High user I/O wait time indicates storage performance issues (slow disks, SAN latency, etc.).
+    # The metric is in centiseconds per second. Threshold 300 means 3 seconds of I/O wait per second of wall time.
+    - alert: OracleDbHighWaitTime(userI/o)
+      expr: 'rate(oracledb_wait_time_user_io[5m]) > 300'
+      for: 5m
+      labels:
+        severity: warning
+      annotations:
+        summary: Oracle DB high wait time (user I/O) (instance {{ $labels.instance }})
+        description: "Oracle Database on {{ $labels.instance }} is experiencing high user I/O wait time\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"