feat(monitoring): add Airflow monitoring via statsd-exporter

- Add statsd-exporter service to docker-compose.yml (prom/statsd-exporter:v0.27.1)
- Add StatsD env vars to airflow-default-env for metrics export
- Add airflow job to prometheus.yml scrape configs
- Add Airflow Overview dashboard (Grafana provisioning)
- Add Airflow alert rules: scheduler down, queue backlog, failures, parse time
- Add configs/statsd_mapping.yml for StatsD → Prometheus conversion
- Use Prometheus naming convention (_total for counters, _seconds for timers)
- Add monitoring plan at plans/monitoring_airflow_plan.md
- Update OPERATIONS.md and Makefile for airflow monitoring

Tested: all 3 jobs (airflow, clickhouse, kafka) showing UP in Prometheus,
metrics flowing (dagbag_size=3, executor slots, heartbeats with _total suffix),
all 4 alert rules loaded in Grafana
This commit is contained in:
2026-02-08 22:27:32 +03:00
parent 8e31b06241
commit 4917a9a6ad
8 changed files with 1701 additions and 8 deletions
@@ -0,0 +1,331 @@
apiVersion: 1
groups:
- orgId: 1
name: airflow_health_group
folder: Airflow Alerts
interval: 30s
rules:
# --- Alert: Airflow Scheduler Down ---
- uid: airflow_scheduler_down
title: Airflow Scheduler Down
condition: C
data:
- refId: A
relativeTimeRange:
from: 300
to: 0
datasourceUid: prometheus_uid
model:
datasource:
type: prometheus
uid: prometheus_uid
editorMode: code
expr: rate(airflow_scheduler_heartbeat_total[5m])
instant: false
intervalMs: 1000
legendFormat: __auto
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: Alerting
execErrState: Error
for: 2m
annotations:
summary: "Airflow scheduler не отправляет heartbeats"
description: "Scheduler possible down — rate(airflow_scheduler_heartbeat_total) < 0.1 в течение 2 минут"
labels:
severity: critical
# --- Alert: Airflow Queue Backlog ---
- uid: airflow_queue_high
title: Airflow Queue Backlog
condition: C
data:
- refId: A
relativeTimeRange:
from: 300
to: 0
datasourceUid: prometheus_uid
model:
datasource:
type: prometheus
uid: prometheus_uid
editorMode: code
expr: airflow_executor_queued_tasks
instant: false
intervalMs: 1000
legendFormat: __auto
maxDataPoints: 43200
range: true
refId: A
- refId: B
datasourceUid: __expr__
model:
conditions:
- evaluator:
params:
- 50
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: OK
execErrState: Error
for: 5m
annotations:
summary: "В очереди Airflow > 50 задач"
description: "airflow_executor_queued_tasks = {{ $values.A }} (превышает 50 в течение 5 минут) — возможна перегрузка"
labels:
severity: warning
# --- Alert: High Task Failure Rate ---
- uid: airflow_task_failures_high
title: High Task Failure Rate
condition: C
data:
- refId: A
relativeTimeRange:
from: 300
to: 0
datasourceUid: prometheus_uid
model:
datasource:
type: prometheus
uid: prometheus_uid
editorMode: code
expr: rate(airflow_task_failures_total[5m])
instant: false
intervalMs: 1000
legendFormat: __auto
maxDataPoints: 43200
range: true
refId: A
- refId: B
datasourceUid: __expr__
model:
conditions:
- evaluator:
params:
- 0.1
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: OK
execErrState: Error
for: 3m
annotations:
summary: "Высокий rate падений тасков"
description: "rate(airflow_task_failures_total) = {{ $values.A }} (превышает 0.1 в течение 3 минут) — проверьте логи DAG"
labels:
severity: warning
# --- Alert: High DAG Parse Time ---
- uid: airflow_parse_time_high
title: High DAG Parse Time
condition: C
data:
- refId: A
relativeTimeRange:
from: 300
to: 0
datasourceUid: prometheus_uid
model:
datasource:
type: prometheus
uid: prometheus_uid
editorMode: code
expr: airflow_dag_processing_total_parse_time
instant: false
intervalMs: 1000
legendFormat: __auto
maxDataPoints: 43200
range: true
refId: A
- refId: B
datasourceUid: __expr__
model:
conditions:
- evaluator:
params:
- 30
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: OK
execErrState: Error
for: 5m
annotations:
summary: "Парсинг DAG занимает > 30 секунд"
description: "airflow_dag_processing_total_parse_time = {{ $values.A }}s — возможно, есть тяжелые DAG"
labels:
severity: info
@@ -0,0 +1,805 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"description": "Обзор метрик Airflow через statsd-exporter",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": null,
"links": [],
"panels": [
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 1,
"panels": [],
"title": "Scheduler Health",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": 0
},
{
"color": "green",
"value": 1
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 0,
"y": 1
},
"id": 2,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.0.8",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"expr": "airflow_dagbag_size",
"refId": "A"
}
],
"title": "DAG Bag Size",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 10
},
{
"color": "red",
"value": 30
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 6,
"y": 1
},
"id": 3,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.0.8",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"expr": "airflow_dag_processing_total_parse_time",
"refId": "A"
}
],
"title": "Parse Time",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "ops"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 1
},
"id": 4,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "11.0.8",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"expr": "rate(airflow_scheduler_heartbeat_total[5m])",
"refId": "A"
}
],
"title": "Scheduler Heartbeat Rate",
"type": "timeseries"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 9
},
"id": 5,
"panels": [],
"title": "Executor Status",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": 0
},
{
"color": "yellow",
"value": 2
},
{
"color": "green",
"value": 8
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 8,
"x": 0,
"y": 10
},
"id": 6,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.0.8",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"expr": "airflow_executor_open_slots",
"refId": "A"
}
],
"title": "Open Slots",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 20
},
{
"color": "red",
"value": 50
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 8,
"x": 8,
"y": 10
},
"id": 7,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.0.8",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"expr": "airflow_executor_queued_tasks",
"refId": "A"
}
],
"title": "Queued Tasks",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "blue",
"value": null
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 8,
"x": 16,
"y": 10
},
"id": 8,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "11.0.8",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"expr": "airflow_executor_running_tasks",
"refId": "A"
}
],
"title": "Running Tasks",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 14
},
"id": 9,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "11.0.8",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"expr": "airflow_executor_queued_tasks",
"legendFormat": "Queued",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"expr": "airflow_executor_running_tasks",
"legendFormat": "Running",
"refId": "B"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"expr": "airflow_executor_open_slots",
"legendFormat": "Open Slots",
"refId": "C"
}
],
"title": "Executor Tasks Over Time",
"type": "timeseries"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 22
},
"id": 10,
"panels": [],
"title": "Task Performance",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 23
},
"id": 11,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "11.0.8",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"expr": "rate(airflow_task_duration_seconds_sum[5m]) / rate(airflow_task_duration_seconds_count[5m])",
"legendFormat": "{{dag_id}} / {{task_id}}",
"refId": "A"
}
],
"title": "Task Duration (avg)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "ops"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 23
},
"id": 12,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "11.0.8",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"expr": "rate(airflow_task_failures_total[5m])",
"legendFormat": "Failures: {{dag_id}} / {{task_id}}",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus_uid"
},
"expr": "rate(airflow_task_success_total[5m])",
"legendFormat": "Success: {{dag_id}} / {{task_id}}",
"refId": "B"
}
],
"title": "Task Failures vs Success Rate",
"type": "timeseries"
}
],
"refresh": "10s",
"schemaVersion": 39,
"tags": ["airflow", "orchestration"],
"templating": {
"list": []
},
"time": {
"from": "now-1h",
"to": "now"
},
"timepicker": {},
"timezone": "Europe/Moscow",
"title": "Airflow Overview",
"uid": "airflow-overview",
"version": 1,
"weekStart": ""
}
+9
View File
@@ -18,4 +18,13 @@ scrape_configs:
- targets: ["kafka-exporter:9308"]
labels:
instance: Kafka-1
honor_labels: true
# Airflow metrics via statsd-exporter (StatsD → Prometheus)
- job_name: "airflow"
metrics_path: "/metrics"
static_configs:
- targets: ["statsd-exporter:9102"]
labels:
instance: Airflow-1
honor_labels: true
+74
View File
@@ -0,0 +1,74 @@
# Mapping StatsD → Prometheus для Airflow
# См. документацию: https://github.com/prometheus/statsd_exporter#metric-mapping-and-configuration
mappings:
# DAG processing metrics
- match: "airflow.dag_processing.total_parse_time"
name: "airflow_dag_processing_total_parse_time"
help: "Total time to parse all DAGs"
type: gauge
- match: "airflow.dagbag_size"
name: "airflow_dagbag_size"
help: "DAGs in the DagBag"
type: gauge
# Executor metrics
- match: "airflow.executor.open_slots"
name: "airflow_executor_open_slots"
help: "Open slots on executor"
type: gauge
- match: "airflow.executor.queued_tasks"
name: "airflow_executor_queued_tasks"
help: "Queued tasks on executor"
type: gauge
- match: "airflow.executor.running_tasks"
name: "airflow_executor_running_tasks"
help: "Running tasks on executor"
type: gauge
# Scheduler metrics (counter → _total суффикс по Prometheus convention)
- match: "airflow.scheduler_heartbeat"
name: "airflow_scheduler_heartbeat_total"
help: "Scheduler heartbeats"
type: counter
- match: "airflow.scheduler.critical_section_busy"
name: "airflow_scheduler_critical_section_busy"
help: "Scheduler critical section busy"
type: gauge
# Task duration (timer → _seconds суффикс)
- match: "airflow.dag.*.task.*.duration"
name: "airflow_task_duration_seconds"
help: "Task duration"
type: timer
labels:
dag_id: "$1"
task_id: "$2"
# Task failures (counter → _total суффикс)
- match: "airflow.dag.*.task.*.failures"
name: "airflow_task_failures_total"
help: "Task failures"
type: counter
labels:
dag_id: "$1"
task_id: "$2"
# Task success (counter → _total суффикс)
- match: "airflow.dag.*.task.*.success"
name: "airflow_task_success_total"
help: "Task success"
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