b8b124c917
Some checks failed
CD Pipeline / build-and-deploy (push) Has been cancelled
2026-04-14 傍晚 Session 收尾: - LOGBOOK.md: 記錄本日 6 commits + Mission C E2E 驗證 + MASTER 藍圖 P0+P1 全綠 - k8s/monitoring/flywheel-alerts.yaml: 加 🔴 DEPRECATED 標記 （11/11 規則已遷入 ops/monitoring/alerts-unified.yml，此 CRD 檔無 Operator 支援） Backlog 清剿盤點： ✅ C2 hasType4 前端硬編（已接真實 API） ✅ C3 WebSocket 無重連（指數退避 + polling fallback） ✅ flywheel-alerts Docker 方式改寫（已完成，僅舊檔未清理 → 本 commit 封存） ✅ risk_level YAML 優先邏輯（decision_manager:1663） ⏳ SMTP_USER/SMTP_PASSWORD CHANGE_ME（需統帥提供帳密） ⏳ 各類 E2E 驗證（需真實告警觸發） Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
200 lines
8.5 KiB
YAML
200 lines
8.5 KiB
YAML
# =============================================================================
|
||
# 🔴 [已封存 / DEPRECATED] 請勿使用此檔案
|
||
# =============================================================================
|
||
# 2026-04-14 Claude Sonnet 4.6（Backlog 清剿）:
|
||
# - 本檔為 PrometheusRule CRD 格式，需 Prometheus Operator 才能載入
|
||
# - 但 AWOOOI 的 Prometheus 是 Docker 部署（188），無 Operator
|
||
# - 11 條規則已全數遷入 ops/monitoring/alerts-unified.yml（group: awoooi_flywheel_meta_alerts）
|
||
# - 本檔保留僅作歷史參考，請勿 kubectl apply
|
||
#
|
||
# 權威來源：ops/monitoring/alerts-unified.yml
|
||
# =============================================================================
|
||
# 歷史資訊：飛輪健康度告警規則 — ADR-074 M1
|
||
# 數據來源：/api/v1/stats/flywheel/metrics（awoooi-flywheel scrape job）
|
||
# 建立：2026-04-12 ogt (ADR-074 M1)
|
||
# 封存：2026-04-14 Claude Sonnet 4.6（11/11 規則已遷入 alerts-unified.yml）
|
||
# =============================================================================
|
||
|
||
apiVersion: monitoring.coreos.com/v1
|
||
kind: PrometheusRule
|
||
metadata:
|
||
name: flywheel-alerts
|
||
namespace: monitoring
|
||
labels:
|
||
release: prometheus
|
||
app: prometheus
|
||
spec:
|
||
groups:
|
||
- name: awoooi_flywheel_health
|
||
interval: 5m
|
||
rules:
|
||
|
||
# P0: Playbook 完全沒有 → 飛輪學習節點失效
|
||
- alert: FlywheelPlaybookZero
|
||
expr: awoooi_flywheel_playbook_count == 0
|
||
for: 1h
|
||
labels:
|
||
severity: critical
|
||
alert_category: infrastructure
|
||
notification_type: TYPE-3
|
||
annotations:
|
||
summary: "飛輪 Playbook 數量為 0"
|
||
description: "Playbook 數量持續 1 小時為 0，飛輪學習節點完全失效。"
|
||
runbook: "執行 scripts/cold_start_playbooks.py 冷啟動"
|
||
|
||
# P0: 執行成功率極低
|
||
- alert: FlywheelExecutionSuccessLow
|
||
expr: awoooi_flywheel_execution_success_rate < 0.1
|
||
for: 2h
|
||
labels:
|
||
severity: warning
|
||
alert_category: infrastructure
|
||
notification_type: TYPE-3
|
||
annotations:
|
||
summary: "飛輪自動修復成功率低於 10%"
|
||
description: "執行成功率 {{ $value | humanizePercentage }}，低於健康基線 10%。"
|
||
runbook: "檢查 decision_manager 日誌，確認 target 解析和 SSH MCP 狀態"
|
||
|
||
# P0: KM 大量未向量化 → RAG 無法使用歷史案例
|
||
- alert: FlywheelKMVectorizationLow
|
||
expr: awoooi_flywheel_km_unvectorized_count > 10
|
||
for: 30m
|
||
labels:
|
||
severity: warning
|
||
alert_category: infrastructure
|
||
notification_type: TYPE-3
|
||
annotations:
|
||
summary: "飛輪 KM 未向量化數量 > 10"
|
||
description: "{{ $value }} 筆 KM 條目尚未向量化，RAG 查詢品質下降。"
|
||
runbook: "執行 scripts/batch_vectorize_km.py 或檢查每日 CronJob 狀態"
|
||
|
||
# P1: alertname NULL 率異常
|
||
- alert: FlywheelAlertnameNullHigh
|
||
expr: awoooi_flywheel_alertname_null_rate > 0.05
|
||
for: 30m
|
||
labels:
|
||
severity: warning
|
||
alert_category: infrastructure
|
||
notification_type: TYPE-3
|
||
annotations:
|
||
summary: "飛輪 alertname NULL 率超過 5%"
|
||
description: "alertname NULL 率 {{ $value | humanizePercentage }}，影響路由準確性。"
|
||
runbook: "執行 scripts/backfill_alertname.py 回填"
|
||
|
||
# P1: Incident 卡住超過 24 小時
|
||
- alert: FlywheelIncidentsStuck
|
||
expr: awoooi_flywheel_incidents_stuck > 5
|
||
for: 10m
|
||
labels:
|
||
severity: warning
|
||
alert_category: infrastructure
|
||
notification_type: TYPE-3
|
||
annotations:
|
||
summary: "{{ $value }} 筆 Incident 卡在 INVESTIGATING 超過 24 小時"
|
||
description: "大量 Incident 未推進，可能是決策引擎或 Telegram 通知阻塞。"
|
||
|
||
- name: awoooi_backup_restore
|
||
interval: 1h
|
||
rules:
|
||
|
||
# P0: 備份還原 dry-run 失敗
|
||
- alert: BackupRestoreTestFailed
|
||
expr: awoooi_backup_restore_test_success == 0
|
||
for: 5m
|
||
labels:
|
||
severity: critical
|
||
alert_category: infrastructure
|
||
notification_type: TYPE-3
|
||
annotations:
|
||
summary: "備份還原 dry-run 測試失敗"
|
||
description: "Velero restore dry-run 失敗，備份可能無法還原。立即人工驗證備份狀態。"
|
||
runbook: "執行 velero backup describe awoooi-daily 及 velero restore create --from-backup awoooi-daily --dry-run"
|
||
|
||
# P1: 備份還原測試超過 8 天未執行（週排程失效）
|
||
- alert: BackupRestoreTestStale
|
||
expr: (time() - awoooi_backup_restore_test_timestamp_seconds) > 691200
|
||
for: 10m
|
||
labels:
|
||
severity: warning
|
||
alert_category: infrastructure
|
||
notification_type: TYPE-3
|
||
annotations:
|
||
summary: "備份還原測試超過 8 天未執行"
|
||
description: "上次備份測試距今 {{ $value | humanizeDuration }}，週排程 CronJob 可能失效。"
|
||
runbook: "檢查 velero namespace 中的 backup-restore-test CronJob 狀態"
|
||
|
||
- name: awoooi_infrastructure_detailed
|
||
interval: 60s
|
||
rules:
|
||
|
||
# P1: Docker 188 容器不健康（docker inspect health=unhealthy）
|
||
# node-exporter + cAdvisor 暴露 container_last_seen / container_tasks_state
|
||
- alert: DockerContainerUnhealthyDetailed
|
||
expr: |
|
||
count by (name, instance) (
|
||
container_tasks_state{state="running", instance=~"192.168.0.188.*"}
|
||
) == 0
|
||
or
|
||
container_last_seen{instance=~"192.168.0.188.*", name!=""} < (time() - 120)
|
||
for: 5m
|
||
labels:
|
||
severity: warning
|
||
alert_category: infrastructure
|
||
notification_type: TYPE-3
|
||
annotations:
|
||
summary: "188 主機容器 {{ $labels.name }} 異常"
|
||
description: "容器 {{ $labels.name }} 在 {{ $labels.instance }} 已超過 2 分鐘無活動或不在 running 狀態。"
|
||
runbook: "SSH 到 192.168.0.188：docker inspect {{ $labels.name }} 確認健康狀態"
|
||
|
||
# P1: Redis Streams 積壓過高（alert stream 或 incident stream）
|
||
- alert: RedisStreamBacklogHigh
|
||
expr: awoooi_redis_stream_len > 500
|
||
for: 10m
|
||
labels:
|
||
severity: warning
|
||
alert_category: infrastructure
|
||
notification_type: TYPE-3
|
||
annotations:
|
||
summary: "Redis Stream {{ $labels.stream }} 積壓 {{ $value }} 筆"
|
||
description: "Redis Stream 積壓超過 500 筆，飛輪消費者可能阻塞。"
|
||
runbook: "檢查 consumer group lag：XINFO GROUPS <stream-key>"
|
||
|
||
# P1: PostgreSQL 磁碟增長率過快（1小時增長超過 500MB）
|
||
- alert: PostgreSQLDiskGrowthRate
|
||
expr: |
|
||
(
|
||
node_filesystem_size_bytes{instance="192.168.0.188:9100", mountpoint="/"}
|
||
- node_filesystem_avail_bytes{instance="192.168.0.188:9100", mountpoint="/"}
|
||
)
|
||
- (
|
||
node_filesystem_size_bytes{instance="192.168.0.188:9100", mountpoint="/"}
|
||
- node_filesystem_avail_bytes{instance="192.168.0.188:9100", mountpoint="/"}
|
||
) offset 1h
|
||
> 524288000
|
||
for: 5m
|
||
labels:
|
||
severity: warning
|
||
alert_category: infrastructure
|
||
notification_type: TYPE-3
|
||
annotations:
|
||
summary: "188 主機磁碟 1 小時增長超過 500MB"
|
||
description: "磁碟在過去 1 小時增長 {{ $value | humanize1024 }}B，可能是 PostgreSQL WAL 或日誌暴增。"
|
||
runbook: "SSH 188：df -h / && du -sh /var/lib/postgresql/*/pg_wal"
|
||
|
||
- name: awoooi_host_connectivity
|
||
interval: 60s
|
||
rules:
|
||
|
||
# P0: 主機間網路分區
|
||
- alert: HostNetworkPartition
|
||
expr: probe_success{job="host-connectivity"} == 0
|
||
for: 5m
|
||
labels:
|
||
severity: critical
|
||
alert_category: infrastructure
|
||
notification_type: TYPE-3
|
||
annotations:
|
||
summary: "主機 {{ $labels.instance }} 無法連通"
|
||
description: "TCP probe 到 {{ $labels.instance }} 失敗超過 5 分鐘，可能發生網路分區。"
|
||
runbook: "SSH 檢查路由和防火牆規則"
|