mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-21 17:07:24 +08:00
86 lines
3.6 KiB
YAML
86 lines
3.6 KiB
YAML
groups:
|
|
|
|
- name: EmbeddedExporter
|
|
|
|
rules:
|
|
|
|
- alert: NetdataHighCpuUsage
|
|
expr: 'rate(netdata_cpu_cpu_percentage_average{dimension="idle"}[1m]) > 80'
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Netdata high cpu usage (instance {{ $labels.instance }})
|
|
description: "Netdata high CPU usage (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: HostCpuStealNoisyNeighbor
|
|
expr: 'rate(netdata_cpu_cpu_percentage_average{dimension="steal"}[1m]) > 10'
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Host CPU steal noisy neighbor (instance {{ $labels.instance }})
|
|
description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: NetdataHighMemoryUsage
|
|
expr: '100 / netdata_system_ram_MiB_average * netdata_system_ram_MiB_average{dimension=~"free|cached"} < 20'
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Netdata high memory usage (instance {{ $labels.instance }})
|
|
description: "Netdata high memory usage (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: NetdataLowDiskSpace
|
|
expr: '100 / netdata_disk_space_GB_average * netdata_disk_space_GB_average{dimension=~"avail|cached"} < 20'
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Netdata low disk space (instance {{ $labels.instance }})
|
|
description: "Netdata low disk space (> 80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: NetdataPredictedDiskFull
|
|
expr: 'predict_linear(netdata_disk_space_GB_average{dimension=~"avail|cached"}[3h], 24 * 3600) < 0'
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Netdata predicted disk full (instance {{ $labels.instance }})
|
|
description: "Netdata predicted disk full in 24 hours\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: NetdataMdMismatchCntUnsynchronizedBlocks
|
|
expr: 'netdata_md_mismatch_cnt_unsynchronized_blocks_average > 1024'
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Netdata MD mismatch cnt unsynchronized blocks (instance {{ $labels.instance }})
|
|
description: "RAID Array have unsynchronized blocks\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: NetdataDiskReallocatedSectors
|
|
expr: 'increase(netdata_smartd_log_reallocated_sectors_count_sectors_average[1m]) > 0'
|
|
for: 0m
|
|
labels:
|
|
severity: info
|
|
annotations:
|
|
summary: Netdata disk reallocated sectors (instance {{ $labels.instance }})
|
|
description: "Reallocated sectors on disk\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: NetdataDiskCurrentPendingSector
|
|
expr: 'netdata_smartd_log_current_pending_sector_count_sectors_average > 0'
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Netdata disk current pending sector (instance {{ $labels.instance }})
|
|
description: "Disk current pending sector\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
|
|
- alert: NetdataReportedUncorrectableDiskSectors
|
|
expr: 'increase(netdata_smartd_log_offline_uncorrectable_sector_count_sectors_average[2m]) > 0'
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Netdata reported uncorrectable disk sectors (instance {{ $labels.instance }})
|
|
description: "Reported uncorrectable disk sectors\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|