alerts6

monitoring/pra/alerts.yaml

@@ -8,9 +8,6 @@ x-inputs:
   - name: kafka_connect_sink_job
     type: config
     value: artesca-data-dr-sink-base-queue-connector-metrics
-  - name: threshold
-    type: constant
-    value: 10 # to be defined 
   - name: zenko_sink_instance
     type: config
     value: artesca-data-dr
@@ -44,28 +41,28 @@ groups:
 
   - alert: KafkaConnectOutageSource
     expr: |
-      rate(sum(kafka_connect_task_error_total_record_errors{job="${kafka_connect_src_job}"})[$__rate_interval]) > ${threshold}
+      rate(sum(kafka_connect_task_error_total_record_errors{job="${kafka_connect_src_job}"})[$__rate_interval]) > 0
       OR
-      rate(sum(kafka_connect_task_error_total_record_failures{job="${kafka_connect_src_job}"})[$__rate_interval]) > ${threshold}
+      rate(sum(kafka_connect_task_error_total_record_failures{job="${kafka_connect_src_job}"})[$__rate_interval]) > 0
     for: 1m
     labels:
       severity: critical
     annotations:
       description: >-
-        Kafka-connect on source is not working nominally. The rate of errors or failures has exceeded the threshold. This could lead DR to get out of sync if not addressed promptly.
+        Kafka-connect on source is not working nominally. The rate of errors or failures has exceeded 0. This could lead DR to get out of sync if not addressed promptly.
       summary: 'Kafka Connect not working'
 
   - alert: KafkaConnectOutageSink
     expr: |
-      rate(sum(kafka_connect_task_error_total_record_errors{job="${kafka_connect_sink_job}"})[$__rate_interval]) > ${threshold}
+      rate(sum(kafka_connect_task_error_total_record_errors{job="${kafka_connect_sink_job}"})[$__rate_interval]) > 0
       OR
-      rate(sum(kafka_connect_task_error_total_record_failures{job="${kafka_connect_sink_job}"})[$__rate_interval]) > ${threshold}
+      rate(sum(kafka_connect_task_error_total_record_failures{job="${kafka_connect_sink_job}"})[$__rate_interval]) > 0
     for: 1m
     labels:
       severity: critical
     annotations:
       description: >-
-        Kafka-connect on sink is not working nominally. The rate of errors or failures has exceeded the threshold. This could lead to data loss if not addressed promptly.
+        Kafka-connect on sink is not working nominally. The rate of errors or failures has exceeded 0. This could lead to data loss if not addressed promptly.
       summary: 'Kafka Connect not working'
 
   - alert: WriteTimesLatency