Critical: Blackbox Exporter replacement 從 K8s DNS 改為主機 IP (192.168.0.188:9115) Important: Descheduler namespace 顯式宣告 PSA restricted labels Suggestion: failedJobsHistoryLimit 3→1, 新增 MinioDiskUsageCritical 5% 告警 R1 Review by: 首席架構師 (Phase O-1) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
68 lines
2.4 KiB
YAML
68 lines
2.4 KiB
YAML
# =============================================================================
|
||
# MinIO + Kali 告警規則 - Phase O-1.3/O-1.4
|
||
# =============================================================================
|
||
# 建立者: Claude Code (首席架構師)
|
||
# 日期: 2026-04-02 (台北時間)
|
||
# 部署位置: 192.168.0.188 /etc/prometheus/rules/minio-kali-alerts.yaml
|
||
# =============================================================================
|
||
|
||
groups:
|
||
- name: minio-alerts
|
||
rules:
|
||
# MinIO 服務離線
|
||
- alert: MinioDown
|
||
expr: up{job="minio"} == 0
|
||
for: 5m
|
||
labels:
|
||
severity: critical
|
||
service: minio
|
||
annotations:
|
||
summary: "MinIO 儲存服務離線"
|
||
description: "MinIO ({{ $labels.instance }}) 已離線超過 5 分鐘,Velero 備份將失敗"
|
||
|
||
# MinIO 磁碟使用率過高
|
||
- alert: MinioDiskUsageHigh
|
||
expr: minio_cluster_capacity_usable_free_bytes / minio_cluster_capacity_usable_total_bytes < 0.2
|
||
for: 10m
|
||
labels:
|
||
severity: warning
|
||
service: minio
|
||
annotations:
|
||
summary: "MinIO 磁碟剩餘空間不足 20%"
|
||
description: "MinIO 可用空間: {{ $value | humanizePercentage }}"
|
||
|
||
# R1 Review: 加 5% critical 磁碟告警作為最後防線
|
||
- alert: MinioDiskUsageCritical
|
||
expr: minio_cluster_capacity_usable_free_bytes / minio_cluster_capacity_usable_total_bytes < 0.05
|
||
for: 5m
|
||
labels:
|
||
severity: critical
|
||
service: minio
|
||
annotations:
|
||
summary: "MinIO 磁碟剩餘空間不足 5% (緊急)"
|
||
description: "MinIO 可用空間: {{ $value | humanizePercentage }},備份即將失敗"
|
||
|
||
# MinIO 離線磁碟
|
||
- alert: MinioOfflineDisk
|
||
expr: minio_cluster_disk_offline_total > 0
|
||
for: 5m
|
||
labels:
|
||
severity: critical
|
||
service: minio
|
||
annotations:
|
||
summary: "MinIO 有離線磁碟"
|
||
description: "離線磁碟數: {{ $value }}"
|
||
|
||
- name: kali-alerts
|
||
rules:
|
||
# Kali Scanner 不可達
|
||
- alert: KaliScannerDown
|
||
expr: probe_success{job="blackbox-kali"} == 0
|
||
for: 10m
|
||
labels:
|
||
severity: warning
|
||
service: kali-scanner
|
||
annotations:
|
||
summary: "Kali Scanner API 不可達"
|
||
description: "192.168.0.112:8080 TCP 探測失敗超過 10 分鐘"
|