ops(scripts): 加入 deploy-alerts.sh 自動部署 Prometheus 規則
功能: 驗證 YAML → 備份 → scp → reload → 驗證規則數+關鍵規則 同步啟用 Prometheus --web.enable-lifecycle (110 docker-compose.yml) 部署驗證: 28 條規則全部 ✅,關鍵規則 SentryDown/HarborDown/GiteaDown/OpenClawDown/AlertmanagerDown/AlertChainUnhealthy 已上線 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
68
scripts/ops/deploy-alerts.sh
Executable file
68
scripts/ops/deploy-alerts.sh
Executable file
@@ -0,0 +1,68 @@
|
||||
#!/bin/bash
|
||||
# scripts/ops/deploy-alerts.sh
|
||||
# 部署統一告警規則到 110 Prometheus
|
||||
# 2026-04-05 Claude Code: Sprint 1 自動化部署
|
||||
# 用法: bash scripts/ops/deploy-alerts.sh [--dry-run]
|
||||
|
||||
set -eo pipefail
|
||||
|
||||
RULES_FILE="ops/monitoring/alerts-unified.yml"
|
||||
TARGET_HOST="192.168.0.110"
|
||||
TARGET_PATH="/home/wooo/monitoring/alerts.yml"
|
||||
PROMETHEUS_URL="http://${TARGET_HOST}:9090"
|
||||
DRY_RUN="${1:-}"
|
||||
|
||||
log() { echo "[$(date '+%H:%M:%S')] $*"; }
|
||||
|
||||
# 確認檔案存在
|
||||
if [ ! -f "$RULES_FILE" ]; then
|
||||
echo "ERROR: $RULES_FILE not found"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# 驗證 YAML 語法
|
||||
python3 -c "import yaml; yaml.safe_load(open('$RULES_FILE'))" || { echo "ERROR: YAML syntax error"; exit 1; }
|
||||
log "✅ YAML 語法驗證通過"
|
||||
|
||||
# Dry run 模式
|
||||
if [ "$DRY_RUN" = "--dry-run" ]; then
|
||||
log "DRY RUN: would deploy $RULES_FILE to ${TARGET_HOST}:${TARGET_PATH}"
|
||||
RULE_COUNT=$(grep -c "alert:" "$RULES_FILE")
|
||||
log "規則數量: $RULE_COUNT 條"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# 備份現有規則
|
||||
ssh wooo@${TARGET_HOST} "cp ${TARGET_PATH} ${TARGET_PATH}.bak.\$(date +%Y%m%d%H%M%S) 2>/dev/null || true"
|
||||
log "✅ 現有規則已備份"
|
||||
|
||||
# 部署新規則
|
||||
scp "$RULES_FILE" wooo@${TARGET_HOST}:${TARGET_PATH}
|
||||
log "✅ 規則已複製到 ${TARGET_HOST}"
|
||||
|
||||
# Reload Prometheus
|
||||
ssh wooo@${TARGET_HOST} "curl -s -X POST ${PROMETHEUS_URL}/-/reload"
|
||||
sleep 3
|
||||
|
||||
# 驗證規則數量
|
||||
RULE_COUNT=$(ssh wooo@${TARGET_HOST} "curl -s ${PROMETHEUS_URL}/api/v1/rules | python3 -c \"import sys,json; r=json.load(sys.stdin); print(sum(len(g['rules']) for g in r['data']['groups']))\"")
|
||||
log "Prometheus 已載入 ${RULE_COUNT} 條規則"
|
||||
|
||||
if [ "$RULE_COUNT" -lt 25 ]; then
|
||||
echo "ERROR: 規則數量異常 ($RULE_COUNT < 25),請檢查"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# 驗證關鍵規則存在
|
||||
KEY_RULES=("SentryDown" "HarborDown" "GiteaDown" "OpenClawDown" "AlertmanagerDown" "AlertChainUnhealthy")
|
||||
for rule in "${KEY_RULES[@]}"; do
|
||||
EXISTS=$(ssh wooo@${TARGET_HOST} "curl -s ${PROMETHEUS_URL}/api/v1/rules | python3 -c \"import sys,json; r=json.load(sys.stdin); names=[x['name'] for g in r['data']['groups'] for x in g['rules']]; print('OK' if '$rule' in names else 'MISSING')\"")
|
||||
if [ "$EXISTS" = "OK" ]; then
|
||||
log "✅ $rule"
|
||||
else
|
||||
echo "❌ $rule 未找到"
|
||||
exit 1
|
||||
fi
|
||||
done
|
||||
|
||||
log "🎉 部署完成!所有關鍵規則已生效"
|
||||
Reference in New Issue
Block a user