Skip to content

Commit

Permalink
Rename service label to kafkaCluster
Browse files Browse the repository at this point in the history
Issue: ZENKO-4857
  • Loading branch information
KillianG committed Aug 13, 2024
1 parent 35b73aa commit 18d4c2b
Show file tree
Hide file tree
Showing 2 changed files with 20 additions and 20 deletions.
24 changes: 12 additions & 12 deletions monitoring/kafka/alerts.test.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ tests:
description: 'Kafka: Broker count is down'
exp_labels:
severity: warning
service: ${service}
kafkaCluster: ${cluster}
- alertname: BrokersCountCritical
eval_time: 3m
exp_alerts: []
Expand All @@ -50,7 +50,7 @@ tests:
description: 'Kafka: Broker count is 0'
exp_labels:
namespace: zenko
service: ${service}
kafkaCluster: ${cluster}
severity: critical

# ActiveControllerCritical
Expand Down Expand Up @@ -79,7 +79,7 @@ tests:
summary: 'Kafka: No active controller'
exp_labels:
severity: critical
service: ${service}
kafkaCluster: ${cluster}
- alertname: ActiveControllerCritical
eval_time: 3m
exp_alerts: []
Expand Down Expand Up @@ -110,7 +110,7 @@ tests:
summary: 'Kafka: 1 under-replicated partitons'
exp_labels:
severity: critical
service: ${service}
kafkaCluster: ${cluster}
- alertname: UnderReplicatedPartitions
eval_time: 3m
exp_alerts:
Expand All @@ -122,7 +122,7 @@ tests:
summary: 'Kafka: 2 under-replicated partitons'
exp_labels:
severity: critical
service: ${service}
kafkaCluster: ${cluster}

# OfflinePartitons
##################################################################################################
Expand Down Expand Up @@ -151,7 +151,7 @@ tests:
summary: 'Kafka: 1 offline partitons'
exp_labels:
severity: critical
service: ${service}
kafkaCluster: ${cluster}
- alertname: OfflinePartitons
eval_time: 3m
exp_alerts:
Expand All @@ -164,7 +164,7 @@ tests:
summary: 'Kafka: 2 offline partitons'
exp_labels:
severity: critical
service: ${service}
kafkaCluster: ${cluster}

# RemainingDiskSpaceWarning
##################################################################################################
Expand Down Expand Up @@ -204,7 +204,7 @@ tests:
namespace: zenko
persistentvolumeclaim: artesca-data-base-queue-1
severity: warning
service: ${service}
kafkaCluster: ${cluster}
- alertname: RemainingDiskSpaceWarning
eval_time: 5d8h
exp_alerts: []
Expand Down Expand Up @@ -232,7 +232,7 @@ tests:
summary: Zookeeper Sync Disconected
exp_labels:
severity: warning
service: ${service}
kafkaCluster: ${cluster}

# ConsumerLagWarning
##################################################################################################
Expand Down Expand Up @@ -282,7 +282,7 @@ tests:
cluster_name: artesca-data-base-queue
group: notification
severity: warning
service: ${service}
kafkaCluster: ${cluster}
- alertname: ConsumerLagWarning
eval_time: 20m
exp_alerts:
Expand All @@ -299,7 +299,7 @@ tests:
cluster_name: artesca-data-base-queue
group: replication
severity: warning
service: ${service}
kafkaCluster: ${cluster}
- exp_annotations:
description: |
Kafka consumer lag has been more more than 300 seconds
Expand All @@ -313,4 +313,4 @@ tests:
cluster_name: artesca-data-base-queue
group: notification
severity: warning
service: ${service}
kafkaCluster: ${cluster}
16 changes: 8 additions & 8 deletions monitoring/kafka/alerts.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ groups:
for: 1m
labels:
severity: warning
service: ${service}
kafkaCluster: ${cluster}
annotations:
summary: 'Not all expected brokers are online.'
description: 'Kafka: Broker count is down'
Expand All @@ -45,7 +45,7 @@ groups:
for: 1m
labels:
severity: critical
service: ${service}
kafkaCluster: ${cluster}
annotations:
summary: 'No Brokers online'
description: 'Kafka: Broker count is 0'
Expand All @@ -55,7 +55,7 @@ groups:
for: 1m
labels:
severity: critical
service: ${service}
kafkaCluster: ${cluster}
annotations:
description: >-
No broker in the cluster is reporting as the active controller in the last 1 minute interval. During steady state there should
Expand All @@ -67,7 +67,7 @@ groups:
for: 1m
labels:
severity: critical
service: ${service}
kafkaCluster: ${cluster}
annotations:
description: >-
Under-replicated partitions means that one or more replicas are not available. This is usually because a broker is down. Restart
Expand All @@ -79,7 +79,7 @@ groups:
for: 1m
labels:
severity: critical
service: ${service}
kafkaCluster: ${cluster}
annotations:
description: >-
After successful leader election, if the leader for partition dies, then the partition moves to the OfflinePartition state.
Expand All @@ -96,7 +96,7 @@ groups:
for: 2m
labels:
severity: warning
service: ${service}
kafkaCluster: ${cluster}
annotations:
description: 'Kafka Broker has low disk space'
summary: 'Kafka Broker has low disk space'
Expand All @@ -107,7 +107,7 @@ groups:
for: 1m
labels:
severity: warning
service: ${service}
kafkaCluster: ${cluster}
annotations:
summary: 'Zookeeper Sync Disconected'
description: 'Kafka Zookeeper Sync Disconected'
Expand All @@ -123,7 +123,7 @@ groups:
for: 5m
labels:
severity: warning
service: ${service}
kafkaCluster: ${cluster}
annotations:
summary: 'Kafka: consumer lag is too high for {{ $labels.group }}'
description: |
Expand Down

0 comments on commit 18d4c2b

Please sign in to comment.