| Rule |
State |
Error |
Last Evaluation |
Evaluation Time |
| alert: HighMemoryUsage
expr: (node_memory_MemAvailable_bytes
/ node_memory_MemTotal_bytes) < 0.15
for: 2m
labels:
severity: warning
annotations:
description: Available memory is less than 15% for 2 minutes.
summary: ⚠️ High memory usage on {{ $labels.instance }}
|
ok
|
|
2.444s ago
|
1.1ms |
| alert: DiskSpaceLow
expr: (node_filesystem_avail_bytes{mountpoint="/"}
/ node_filesystem_size_bytes{mountpoint="/"}) < 0.1
for: 2m
labels:
severity: critical
annotations:
description: Root filesystem has less than 10% space left.
summary: "\U0001F4BE Low disk space on {{ $labels.instance }}"
|
ok
|
|
2.443s ago
|
550us |
| alert: HighCPUUsage
expr: 100
- (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100)
> 90
for: 2m
labels:
severity: warning
annotations:
description: CPU usage over 90% for 2 minutes.
summary: "\U0001F525 High CPU usage on {{ $labels.instance }}"
|
ok
|
|
2.443s ago
|
660.3us |
| alert: NodeExporterDown
expr: up{job="node_exporter"}
== 0
for: 1m
labels:
severity: critical
annotations:
description: Prometheus target `node_exporter` is unreachable.
summary: ❌ Node Exporter down on {{ $labels.instance }}
|
ok
|
|
2.442s ago
|
238.3us |
| alert: RPCDown
expr: probe_success{job="blackbox_eth_blocknumber"}
== 0
for: 1m
labels:
severity: critical
annotations:
description: The endpoint at {{ $labels.instance }} failed probe.
summary: ⛔ RPC endpoint is down
|
ok
|
|
2.442s ago
|
133.8us |
| alert: ValidatorNotSigning
expr: time()
- max by(instance) (besu_block_timestamp{job=~"validators|besu"}) > 7200
for: 10m
labels:
severity: critical
annotations:
description: Validator {{ $labels.instance }} hasn't signed a block in the last
2 hours.
summary: ⛔ Validator not signing blocks
|
ok
|
|
2.442s ago
|
203.6us |
| alert: NoNewBlocks
expr: increase(besu_block_number[10m])
== 0
for: 5m
labels:
severity: critical
annotations:
description: No block has been produced in the last 10 minutes. Network may be stuck.
summary: "\U0001F4C9 No new blocks produced"
|
ok
|
|
2.442s ago
|
108.9us |
| alert: DataDiskUsageCritical
expr: (node_filesystem_size_bytes{mountpoint="/data"}
- node_filesystem_avail_bytes{mountpoint="/data"}) / node_filesystem_size_bytes{mountpoint="/data"}
> 0.9
for: 2m
labels:
severity: critical
annotations:
description: The /data mount is over 90% full on {{ $labels.instance }}
summary: "\U0001F4E6 Disk usage > 90% on /data"
|
ok
|
|
2.442s ago
|
220.8us |
| alert: FaucetTxErrorSpike
expr: increase(faucet_tx_errors_total[5m])
> 3
for: 1m
labels:
severity: warning
annotations:
description: Faucet had more than 3 transaction errors in 5 minutes on {{ $labels.instance
}}
summary: "\U0001F6B1 Faucet transaction errors"
|
ok
|
|
2.442s ago
|
87.71us |
| alert: PrometheusTargetMissing
expr: up == 0
for: 2m
labels:
severity: critical
annotations:
description: 'Target {{ $labels.instance }} (job: {{ $labels.job }}) is down.'
summary: "\U0001F4E1 Prometheus target down: {{ $labels.job }}"
|
ok
|
|
2.442s ago
|
170.9us |
|
2.257s ago |
536.3us |