fix

packages/apps/kafka/templates/podscrape.yaml

@@ -1,7 +1,7 @@
 apiVersion: operator.victoriametrics.com/v1beta1
 kind: VMPodScrape
 metadata:
-  name: {{ .Release.Name }}-pod-scrape
+  name: {{ .Release.Name }}
 spec:
   podMetricsEndpoints:
     - port: tcp-prometheus
@@ -20,13 +20,13 @@ spec:
       - sourceLabels: [__meta_kubernetes_pod_name]
         separator: ;
         regex: (.*)
-        targetLabel: kubernetes_pod_name
+        targetLabel: pod
         replacement: $1
         action: replace
       - sourceLabels: [__meta_kubernetes_pod_node_name]
         separator: ;
         regex: (.*)
-        targetLabel: node_name
+        targetLabel: node
         replacement: $1
         action: replace
       - sourceLabels: [__meta_kubernetes_pod_host_ip]

packages/system/kafka-operator/templates/prometheus-rules.yaml

@@ -24,7 +24,7 @@ spec:
         severity: warning
       annotations:
         summary: 'Kafka under replicated partitions'
-        description: 'There are {{ $value }} under replicated partitions on {{ $labels.kubernetes_pod_name }}'
+        description: 'There are {{ $value }} under replicated partitions on {{ $labels.pod }}'
     - alert: AbnormalControllerState
       expr: sum(kafka_controller_kafkacontroller_activecontrollercount) by (strimzi_io_name) != 1
       for: 10s
@@ -48,7 +48,7 @@ spec:
         severity: warning
       annotations:
         summary: 'Kafka under min ISR partitions'
-        description: 'There are {{ $value }} partitions under the min ISR on {{ $labels.kubernetes_pod_name }}'
+        description: 'There are {{ $value }} partitions under the min ISR on {{ $labels.pod }}'
     - alert: OfflineLogDirectoryCount
       expr: kafka_log_logmanager_offlinelogdirectorycount > 0
       for: 10s
@@ -56,15 +56,15 @@ spec:
         severity: warning
       annotations:
         summary: 'Kafka offline log directories'
-        description: 'There are {{ $value }} offline log directories on {{ $labels.kubernetes_pod_name }}'
+        description: 'There are {{ $value }} offline log directories on {{ $labels.pod }}'
     - alert: ScrapeProblem
-      expr: up{kubernetes_namespace!~"openshift-.+",kubernetes_pod_name=~".+-kafka-[0-9]+"} == 0
+      expr: up{kubernetes_namespace!~"openshift-.+",pod=~".+-kafka-[0-9]+"} == 0
       for: 3m
       labels:
         severity: major
       annotations:
-        summary: 'Prometheus unable to scrape metrics from {{ $labels.kubernetes_pod_name }}/{{ $labels.instance }}'
-        description: 'Prometheus was unable to scrape metrics from {{ $labels.kubernetes_pod_name }}/{{ $labels.instance }} for more than 3 minutes'
+        summary: 'Prometheus unable to scrape metrics from {{ $labels.pod }}/{{ $labels.instance }}'
+        description: 'Prometheus was unable to scrape metrics from {{ $labels.pod }}/{{ $labels.instance }} for more than 3 minutes'
     - alert: ClusterOperatorContainerDown
       expr: count((container_last_seen{container="strimzi-cluster-operator"} > (time() - 90))) < 1 or absent(container_last_seen{container="strimzi-cluster-operator"})
       for: 1m
@@ -98,7 +98,7 @@ spec:
         severity: warning
       annotations:
         summary: 'Zookeeper average request latency'
-        description: 'The average request latency is {{ $value }} on {{ $labels.kubernetes_pod_name }}'
+        description: 'The average request latency is {{ $value }} on {{ $labels.pod }}'
     - alert: OutstandingRequests
       expr: zookeeper_outstandingrequests > 10
       for: 10s
@@ -106,7 +106,7 @@ spec:
         severity: warning
       annotations:
         summary: 'Zookeeper outstanding requests'
-        description: 'There are {{ $value }} outstanding requests on {{ $labels.kubernetes_pod_name }}'
+        description: 'There are {{ $value }} outstanding requests on {{ $labels.pod }}'
     - alert: ZookeeperRunningOutOfSpace
       expr: kubelet_volume_stats_available_bytes{persistentvolumeclaim=~"data-(.+)-zookeeper-[0-9]+"} < 5368709120
       for: 10s