ddadmin
8e31b06241
- Why: - dashboard showed offset as throughput and produced misleading values - kafka-exporter metric/label naming was inconsistent across alerts/docs - consumer-group-missing alert was noisy for demo runs - What: - switch throughput panel to rate(kafka_topic_partition_current_offset[5m]) aggregated by topic and exclude __* topics - align lag metric/labels to kafka_consumergroup_lag + consumergroup - remove Kafka Consumer Group Missing alert from provisioning - pin kafka-exporter image to v1.9.0 and update OPERATIONS.md checks - Check: - airflow dags list-import-errors -> No data found - Prometheus targets: clickhouse up, kafka up - PromQL kafka_consumergroup_lag returns series - Grafana dashboards provisioning reload returns success
251 lines
7.2 KiB
YAML
251 lines
7.2 KiB
YAML
apiVersion: 1
|
||
|
||
groups:
|
||
- orgId: 1
|
||
name: kafka_health_group
|
||
folder: Kafka Alerts
|
||
interval: 1m
|
||
rules:
|
||
# --- Alert: Kafka Broker Down ---
|
||
- uid: kafka_broker_down
|
||
title: Kafka Broker Down
|
||
condition: C
|
||
data:
|
||
- refId: A
|
||
relativeTimeRange:
|
||
from: 300
|
||
to: 0
|
||
datasourceUid: prometheus_uid
|
||
model:
|
||
datasource:
|
||
type: prometheus
|
||
uid: prometheus_uid
|
||
editorMode: code
|
||
expr: kafka_brokers
|
||
instant: false
|
||
intervalMs: 1000
|
||
legendFormat: __auto
|
||
maxDataPoints: 43200
|
||
range: true
|
||
refId: A
|
||
- refId: B
|
||
datasourceUid: __expr__
|
||
model:
|
||
conditions:
|
||
- evaluator:
|
||
params:
|
||
- 1
|
||
type: lt
|
||
operator:
|
||
type: and
|
||
query:
|
||
params:
|
||
- B
|
||
reducer:
|
||
params: []
|
||
type: last
|
||
type: query
|
||
datasource:
|
||
type: __expr__
|
||
uid: __expr__
|
||
expression: A
|
||
intervalMs: 1000
|
||
maxDataPoints: 43200
|
||
refId: B
|
||
type: threshold
|
||
- refId: C
|
||
datasourceUid: __expr__
|
||
model:
|
||
conditions:
|
||
- evaluator:
|
||
params:
|
||
- 0
|
||
type: gt
|
||
operator:
|
||
type: and
|
||
query:
|
||
params:
|
||
- C
|
||
reducer:
|
||
params: []
|
||
type: last
|
||
type: query
|
||
datasource:
|
||
type: __expr__
|
||
uid: __expr__
|
||
expression: B
|
||
intervalMs: 1000
|
||
maxDataPoints: 43200
|
||
refId: C
|
||
type: threshold
|
||
noDataState: Alerting
|
||
execErrState: Error
|
||
for: 1m
|
||
annotations:
|
||
summary: "Kafka broker недоступен"
|
||
description: "Количество доступных брокеров: {{ $values.A }} (ожидается ≥ 1)"
|
||
labels:
|
||
severity: critical
|
||
|
||
# --- Alert: High Consumer Lag ---
|
||
- uid: kafka_consumer_lag_high
|
||
title: Kafka Consumer Lag High
|
||
condition: C
|
||
data:
|
||
- refId: A
|
||
relativeTimeRange:
|
||
from: 300
|
||
to: 0
|
||
datasourceUid: prometheus_uid
|
||
model:
|
||
datasource:
|
||
type: prometheus
|
||
uid: prometheus_uid
|
||
editorMode: code
|
||
expr: kafka_consumergroup_lag
|
||
instant: false
|
||
intervalMs: 1000
|
||
legendFormat: "{{ consumergroup }} - {{ topic }}:{{ partition }}"
|
||
maxDataPoints: 43200
|
||
range: true
|
||
refId: A
|
||
- refId: B
|
||
datasourceUid: __expr__
|
||
model:
|
||
conditions:
|
||
- evaluator:
|
||
params:
|
||
- 10000
|
||
type: gt
|
||
operator:
|
||
type: and
|
||
query:
|
||
params:
|
||
- B
|
||
reducer:
|
||
params: []
|
||
type: last
|
||
type: query
|
||
datasource:
|
||
type: __expr__
|
||
uid: __expr__
|
||
expression: A
|
||
intervalMs: 1000
|
||
maxDataPoints: 43200
|
||
refId: B
|
||
type: threshold
|
||
- refId: C
|
||
datasourceUid: __expr__
|
||
model:
|
||
conditions:
|
||
- evaluator:
|
||
params:
|
||
- 0
|
||
type: gt
|
||
operator:
|
||
type: and
|
||
query:
|
||
params:
|
||
- C
|
||
reducer:
|
||
params: []
|
||
type: last
|
||
type: query
|
||
datasource:
|
||
type: __expr__
|
||
uid: __expr__
|
||
expression: B
|
||
intervalMs: 1000
|
||
maxDataPoints: 43200
|
||
refId: C
|
||
type: threshold
|
||
noDataState: NoData
|
||
execErrState: Error
|
||
for: 5m
|
||
annotations:
|
||
summary: "Высокий лаг консьюмера {{ $labels.consumergroup }}"
|
||
description: "Lag для {{ $labels.topic }}:{{ $labels.partition }} составляет {{ $values.A }} сообщений (порог: 10000)"
|
||
labels:
|
||
severity: warning
|
||
|
||
# --- Alert: No Messages Produced ---
|
||
- uid: kafka_no_messages_produced
|
||
title: Kafka No Messages Produced
|
||
condition: C
|
||
data:
|
||
- refId: A
|
||
relativeTimeRange:
|
||
from: 600
|
||
to: 0
|
||
datasourceUid: prometheus_uid
|
||
model:
|
||
datasource:
|
||
type: prometheus
|
||
uid: prometheus_uid
|
||
editorMode: code
|
||
expr: rate(kafka_topic_partition_current_offset[5m])
|
||
instant: false
|
||
intervalMs: 1000
|
||
legendFormat: "{{ topic }}"
|
||
maxDataPoints: 43200
|
||
range: true
|
||
refId: A
|
||
- refId: B
|
||
datasourceUid: __expr__
|
||
model:
|
||
conditions:
|
||
- evaluator:
|
||
params:
|
||
- 0.1
|
||
type: lt
|
||
operator:
|
||
type: and
|
||
query:
|
||
params:
|
||
- B
|
||
reducer:
|
||
params: []
|
||
type: last
|
||
type: query
|
||
datasource:
|
||
type: __expr__
|
||
uid: __expr__
|
||
expression: A
|
||
intervalMs: 1000
|
||
maxDataPoints: 43200
|
||
refId: B
|
||
type: threshold
|
||
- refId: C
|
||
datasourceUid: __expr__
|
||
model:
|
||
conditions:
|
||
- evaluator:
|
||
params:
|
||
- 0
|
||
type: gt
|
||
operator:
|
||
type: and
|
||
query:
|
||
params:
|
||
- C
|
||
reducer:
|
||
params: []
|
||
type: last
|
||
type: query
|
||
datasource:
|
||
type: __expr__
|
||
uid: __expr__
|
||
expression: B
|
||
intervalMs: 1000
|
||
maxDataPoints: 43200
|
||
refId: C
|
||
type: threshold
|
||
noDataState: NoData
|
||
execErrState: Error
|
||
for: 10m
|
||
annotations:
|
||
summary: "В топик {{ $labels.topic }} не поступают сообщения"
|
||
description: "Rate сообщений < 0.1 msg/sec в течение 10 минут"
|
||
labels:
|
||
severity: warning
|