d2a4a17969
Some checks failed
Code Review / ai-code-review (push) Successful in 22s
Deploy Alert Rules / Deploy Prometheus Alert Rules (push) Successful in 25s
CD Pipeline / tests (push) Successful in 1m11s
CD Pipeline / post-deploy-checks (push) Has been cancelled
CD Pipeline / build-and-deploy (push) Has been cancelled
99 lines
3.7 KiB
Bash
Executable File
99 lines
3.7 KiB
Bash
Executable File
#!/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
|
||
|
||
ALERT_RULES_FILE="ops/monitoring/alerts-unified.yml"
|
||
SLO_RULES_FILE="ops/monitoring/slo-rules.yml"
|
||
TARGET_HOST="192.168.0.110"
|
||
TARGET_ALERTS_PATH="/home/wooo/monitoring/alerts.yml"
|
||
TARGET_SLO_PATH="/home/wooo/monitoring/slo-rules.yml"
|
||
PROMETHEUS_URL="http://${TARGET_HOST}:9090"
|
||
DRY_RUN="${1:-}"
|
||
|
||
log() { echo "[$(date '+%H:%M:%S')] $*"; }
|
||
|
||
# 確認檔案存在
|
||
for file in "$ALERT_RULES_FILE" "$SLO_RULES_FILE"; do
|
||
if [ ! -f "$file" ]; then
|
||
echo "ERROR: $file not found"
|
||
exit 1
|
||
fi
|
||
done
|
||
|
||
# 驗證 YAML 語法
|
||
for file in "$ALERT_RULES_FILE" "$SLO_RULES_FILE"; do
|
||
if python3 -c "import yaml; yaml.safe_load(open('$file'))" 2>/dev/null; then
|
||
:
|
||
elif ruby -e "require 'yaml'; YAML.load_file('$file')" 2>/dev/null; then
|
||
:
|
||
else
|
||
echo "ERROR: YAML syntax error or no YAML parser available: $file"
|
||
exit 1
|
||
fi
|
||
done
|
||
log "✅ YAML 語法驗證通過"
|
||
|
||
# Dry run 模式
|
||
if [ "$DRY_RUN" = "--dry-run" ]; then
|
||
log "DRY RUN: would deploy $ALERT_RULES_FILE to ${TARGET_HOST}:${TARGET_ALERTS_PATH}"
|
||
log "DRY RUN: would deploy $SLO_RULES_FILE to ${TARGET_HOST}:${TARGET_SLO_PATH}"
|
||
ALERT_COUNT=$(grep -c "alert:" "$ALERT_RULES_FILE")
|
||
SLO_RECORD_COUNT=$(grep -c "record:" "$SLO_RULES_FILE")
|
||
SLO_ALERT_COUNT=$(grep -c "alert:" "$SLO_RULES_FILE")
|
||
log "告警規則數量: $ALERT_COUNT 條；SLO recording: $SLO_RECORD_COUNT 條；SLO alerts: $SLO_ALERT_COUNT 條"
|
||
exit 0
|
||
fi
|
||
|
||
# 備份現有規則
|
||
ssh wooo@${TARGET_HOST} "\
|
||
cp ${TARGET_ALERTS_PATH} ${TARGET_ALERTS_PATH}.bak.\$(date +%Y%m%d%H%M%S) 2>/dev/null || true; \
|
||
cp ${TARGET_SLO_PATH} ${TARGET_SLO_PATH}.bak.\$(date +%Y%m%d%H%M%S) 2>/dev/null || true"
|
||
log "✅ 現有規則已備份"
|
||
|
||
# 部署新規則
|
||
scp "$ALERT_RULES_FILE" wooo@${TARGET_HOST}:${TARGET_ALERTS_PATH}
|
||
scp "$SLO_RULES_FILE" wooo@${TARGET_HOST}:${TARGET_SLO_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 "❌ $rule 未找到"
|
||
exit 1
|
||
fi
|
||
done
|
||
|
||
KEY_SLO_RULES=("sli:autonomy_rate:5m" "sli:decision_accuracy:5m" "sli:confidence_calibration:1h" "sli:km_growth_rate:24h" "SLO_KMGrowthRate_Critical")
|
||
for rule in "${KEY_SLO_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"
|