fix(monitoring): align airflow statsd mapping and reload flow
- Why: - Airflow task metrics were mapped to non-emitted StatsD keys - reload-monitoring did not restart statsd-exporter after mapping changes - What: - update StatsD mapping for Airflow 2.10.5 metric names - remove problematic catch-all mapping that produced inconsistent series - restart statsd-exporter in reload-monitoring flow - sync operations runbook and airflow monitoring plan with actual metrics - Check: - make reload-monitoring - Prometheus targets: airflow/clickhouse/kafka are UP - trigger ddl_init and verify airflow_task_duration_seconds_count - verify airflow_task_success_total and airflow_task_failures_total in Prometheus
This commit is contained in:
@@ -41,7 +41,8 @@ mappings:
|
||||
type: gauge
|
||||
|
||||
# Task duration (timer → _seconds суффикс)
|
||||
- match: "airflow.dag.*.task.*.duration"
|
||||
# Проверено для Airflow 2.10.5: metric key = dag.<dag_id>.<task_id>.duration
|
||||
- match: "airflow.dag.*.*.duration"
|
||||
name: "airflow_task_duration_seconds"
|
||||
help: "Task duration"
|
||||
type: timer
|
||||
@@ -49,26 +50,20 @@ mappings:
|
||||
dag_id: "$1"
|
||||
task_id: "$2"
|
||||
|
||||
# Task failures (counter → _total суффикс)
|
||||
- match: "airflow.dag.*.task.*.failures"
|
||||
# Task failures/success (counter → _total суффикс)
|
||||
# Проверено для Airflow 2.10.5: metric key = ti.finish.<dag_id>.<task_id>.<state>
|
||||
- match: "airflow.ti.finish.*.*.failed"
|
||||
name: "airflow_task_failures_total"
|
||||
help: "Task failures"
|
||||
help: "Task failures by dag_id and task_id"
|
||||
type: counter
|
||||
labels:
|
||||
dag_id: "$1"
|
||||
task_id: "$2"
|
||||
|
||||
# Task success (counter → _total суффикс)
|
||||
- match: "airflow.dag.*.task.*.success"
|
||||
- match: "airflow.ti.finish.*.*.success"
|
||||
name: "airflow_task_success_total"
|
||||
help: "Task success"
|
||||
help: "Task successes by dag_id and task_id"
|
||||
type: counter
|
||||
labels:
|
||||
dag_id: "$1"
|
||||
task_id: "$2"
|
||||
|
||||
# Catch-all для остальных airflow метрик
|
||||
- match: "airflow.*.*"
|
||||
name: "airflow_${1}_${2}"
|
||||
help: "Airflow metric $1.$2"
|
||||
type: gauge
|
||||
|
||||
Reference in New Issue
Block a user