awesome-prometheus-alerts/dist/rules/graph-node/embedded-exporter.yml
2026-04-06 18:38:45 +00:00

62 lines
2.7 KiB
YAML

groups:
- name: EmbeddedExporter
rules:
- alert: ProviderFailedBecauseNet_versionFailed
expr: 'eth_rpc_status == 1'
for: 0m
labels:
severity: critical
annotations:
summary: Provider failed because net_version failed (instance {{ $labels.instance }})
description: "Failed net_version for Provider `{{$labels.provider}}` in Graph node `{{$labels.instance}}`\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ProviderFailedBecauseGetGenesisFailed
expr: 'eth_rpc_status == 2'
for: 0m
labels:
severity: critical
annotations:
summary: Provider failed because get genesis failed (instance {{ $labels.instance }})
description: "Failed to get genesis for Provider `{{$labels.provider}}` in Graph node `{{$labels.instance}}`\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ProviderFailedBecauseNet_versionTimeout
expr: 'eth_rpc_status == 3'
for: 0m
labels:
severity: critical
annotations:
summary: Provider failed because net_version timeout (instance {{ $labels.instance }})
description: "net_version timeout for Provider `{{$labels.provider}}` in Graph node `{{$labels.instance}}`\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ProviderFailedBecauseGetGenesisTimeout
expr: 'eth_rpc_status == 4'
for: 0m
labels:
severity: critical
annotations:
summary: Provider failed because get genesis timeout (instance {{ $labels.instance }})
description: "Timeout to get genesis for Provider `{{$labels.provider}}` in Graph node `{{$labels.instance}}`\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Threshold of 10ms. Adjust based on your expected database latency.
- alert: StoreConnectionSlow
expr: 'store_connection_wait_time_ms > 10'
for: 0m
labels:
severity: warning
annotations:
summary: Store connection slow (instance {{ $labels.instance }})
description: "Store connection is too slow to `{{$labels.pool}}` pool, `{{$labels.shard}}` shard in Graph node `{{$labels.instance}}`\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
# Threshold of 20ms. Adjust based on your expected database latency.
- alert: StoreConnectionVerySlow
expr: 'store_connection_wait_time_ms > 20'
for: 0m
labels:
severity: critical
annotations:
summary: Store connection very slow (instance {{ $labels.instance }})
description: "Store connection is very slow to `{{$labels.pool}}` pool, `{{$labels.shard}}` shard in Graph node `{{$labels.instance}}`\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"