[Phase 4] feat(monitoring): add APIDataCriticallyStale alert and fix APIDataStale for duration #92
@@ -71,7 +71,7 @@ spec:
|
||||
- alert: APIDataStale
|
||||
expr: |
|
||||
api_data_freshness_seconds{job=~"zip|holidays|air-quality"} > 2592000
|
||||
for: 5m
|
||||
for: 30m
|
||||
labels:
|
||||
severity: warning
|
||||
team: api-company
|
||||
@@ -79,6 +79,20 @@ spec:
|
||||
summary: "Stale dataset on {{ $labels.job }} ({{ $labels.dataset }})"
|
||||
description: "{{ $labels.job }} dataset '{{ $labels.dataset }}' has not been re-seeded in {{ $value | humanizeDuration }} (threshold: 30 days). Re-seed required."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# APIDataCriticallyStale — data freshness > 60 days
|
||||
# -------------------------------------------------------------------
|
||||
- alert: APIDataCriticallyStale
|
||||
expr: |
|
||||
api_data_freshness_seconds{job=~"zip|holidays|air-quality"} > 5184000
|
||||
for: 1h
|
||||
labels:
|
||||
severity: critical
|
||||
team: api-company
|
||||
annotations:
|
||||
summary: "API data is critically stale on {{ $labels.job }}"
|
||||
description: "{{ $labels.job }} data has not been re-seeded in more than 60 days ({{ $value | humanizeDuration }})"
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# APIDown — any API job absent for 2 min
|
||||
# -------------------------------------------------------------------
|
||||
|
||||
Reference in New Issue
Block a user