mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-21 17:07:24 +08:00
62 lines
2.7 KiB
YAML
62 lines
2.7 KiB
YAML
groups:
|
|
|
|
- name: EmbeddedExporter
|
|
|
|
|
|
rules:
|
|
|
|
- alert: CortexRulerConfigurationReloadFailure
|
|
expr: 'cortex_ruler_config_last_reload_successful != 1'
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Cortex ruler configuration reload failure (instance {{ $labels.instance }})
|
|
description: "Cortex ruler configuration reload failure (instance {{ $labels.instance }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: CortexNotConnectedToAlertmanager
|
|
expr: 'cortex_prometheus_notifications_alertmanagers_discovered < 1'
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Cortex not connected to Alertmanager (instance {{ $labels.instance }})
|
|
description: "Cortex not connected to Alertmanager (instance {{ $labels.instance }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
# Threshold of 0.05/s avoids firing on transient single-event spikes.
|
|
- alert: CortexNotificationsAreBeingDropped
|
|
expr: 'rate(cortex_prometheus_notifications_dropped_total[5m]) > 0.05'
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Cortex notifications are being dropped (instance {{ $labels.instance }})
|
|
description: "Cortex notifications are being dropped due to errors (instance {{ $labels.instance }}, {{ $value | humanize }}/s).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
# Threshold of 0.05/s avoids firing on transient single-event spikes.
|
|
- alert: CortexNotificationErrors
|
|
expr: 'rate(cortex_prometheus_notifications_errors_total[5m]) > 0.05'
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Cortex notification errors (instance {{ $labels.instance }})
|
|
description: "Cortex is failing when sending alert notifications (instance {{ $labels.instance }}, {{ $value | humanize }}/s).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: CortexIngesterUnhealthy
|
|
expr: 'cortex_ring_members{state="Unhealthy", name="ingester"} > 0'
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Cortex ingester unhealthy (instance {{ $labels.instance }})
|
|
description: "Cortex has an unhealthy ingester\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: CortexFrontendQueriesStuck
|
|
expr: 'sum by (job) (cortex_query_frontend_queue_length) > 0'
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Cortex frontend queries stuck (instance {{ $labels.instance }})
|
|
description: "There are queued up queries in query-frontend.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|