Files
truenas-stacks/monitoring/alerts.yml

57 lines
2.3 KiB
YAML

groups:
- name: homelab-core
rules:
- alert: ScrapeTargetDown
expr: up == 0
for: 5m
labels:
severity: warning
annotations:
summary: "Prometheus target down: {{ $labels.job }}"
description: "Target {{ $labels.instance }} for job {{ $labels.job }} has been down for more than 5 minutes."
- alert: PDMemoryPressureHigh
expr: 100 * (1 - (node_memory_MemAvailable_bytes{job="pd-node"} / node_memory_MemTotal_bytes{job="pd-node"})) > 90
for: 10m
labels:
severity: warning
annotations:
summary: "PD memory usage is high"
description: "PlausibleDeniability memory usage has been above 90% for more than 10 minutes."
- alert: PDFilesystemUsageHigh
expr: 100 * (1 - (node_filesystem_avail_bytes{job="pd-node", mountpoint="/", fstype!~"tmpfs|ramfs|overlay|squashfs|nfs4"} / node_filesystem_size_bytes{job="pd-node", mountpoint="/", fstype!~"tmpfs|ramfs|overlay|squashfs|nfs4"})) > 85
for: 15m
labels:
severity: warning
annotations:
summary: "PD root filesystem is filling up"
description: "PlausibleDeniability root filesystem has been above 85% for more than 15 minutes."
- alert: PDContainerRecentlyRestarted
expr: changes(container_start_time_seconds{job="pd-cadvisor", name!=""}[30m]) > 0
for: 5m
labels:
severity: info
annotations:
summary: "PD container restarted recently"
description: "Container {{ $labels.name }} restarted within the last 30 minutes."
- alert: PDRestoreVerificationFailed
expr: pd_restore_verification_success == 0
for: 15m
labels:
severity: warning
annotations:
summary: "PD restore verification failed"
description: "The last scheduled restore verification on PlausibleDeniability failed."
- alert: PDRestoreVerificationStale
expr: time() - pd_restore_verification_last_success_timestamp_seconds > 8640000
for: 1h
labels:
severity: warning
annotations:
summary: "PD restore verification is stale"
description: "No successful PD restore verification has been recorded in the last 100 days."