chat-deploy/deployments/observability/config/prometheus-agent-entrypoint.sh

#!/usr/bin/env sh
set -eu

# ------------------------------
# chat-deploy 指标采集：Prometheus Agent Entrypoint
# - 根据环境变量生成 /prometheus/prometheus.yml 与 /prometheus/targets.json
# - 然后以 agent 模式启动 Prometheus（remote_write 推送到 itom-platform 中心）
#
# 关键环境变量（来自 config.env）：
# - METRICS_REMOTE_WRITE_URL=http(s)://<OBS_HOST>/api/v1/write
# - METRICS_TARGETS=name=host:port,name2=host:port
# - OBS_AUTH_ENABLE=false/true（中心侧是否要求鉴权）
# - OBS_AUTH_TOKEN=xxxxx（当 OBS_AUTH_ENABLE=true 时必填）
# - OBS_PROJECT/OBS_ENV：写入 labels，便于中心侧筛选
# ------------------------------

METRICS_REMOTE_WRITE_URL="${METRICS_REMOTE_WRITE_URL:-}"
OBS_AUTH_ENABLE="${OBS_AUTH_ENABLE:-false}"
OBS_AUTH_TOKEN="${OBS_AUTH_TOKEN:-}"
METRICS_TARGETS="${METRICS_TARGETS:-}"

OBS_PROJECT="${OBS_PROJECT:-chat-deploy}"
OBS_ENV="${OBS_ENV:-prod}"
OBS_SERVICE="${OBS_SERVICE:-chat-deploy}"
OBS_SERVICE_NAME="${OBS_SERVICE_NAME:-$OBS_SERVICE}"
if [ -z "$OBS_SERVICE_NAME" ]; then
  OBS_SERVICE_NAME="chat-deploy"
fi

is_truthy() { case "$1" in 1|true|TRUE|yes|YES|on|ON) return 0 ;; esac; return 1; }

if [ -z "$METRICS_REMOTE_WRITE_URL" ]; then
  echo "[prometheus-agent] FAIL: METRICS_REMOTE_WRITE_URL 为空" >&2
  exit 2
fi

if is_truthy "$OBS_AUTH_ENABLE" && [ -z "$OBS_AUTH_TOKEN" ]; then
  echo "[prometheus-agent] FAIL: OBS_AUTH_ENABLE=true 但 OBS_AUTH_TOKEN 为空" >&2
  exit 2
fi

# 确保数据目录存在且有写权限
mkdir -p /prometheus/data
chmod -R 777 /prometheus 2>/dev/null || true

TARGETS_JSON="/prometheus/targets.json"
echo "[" > "$TARGETS_JSON"

first=1
IFS=','
for item in $METRICS_TARGETS; do
  item="$(printf "%s" "$item" | sed 's/^[[:space:]]*//;s/[[:space:]]*$//')"
  [ -z "$item" ] && continue

  name="$(printf "%s" "$item" | cut -d= -f1 | tr -d '[:space:]')"
  target="$(printf "%s" "$item" | cut -d= -f2- | tr -d '[:space:]')"
  [ -z "$name" ] && continue
  [ -z "$target" ] && continue

  target="$(printf "%s" "$target" | sed -E 's#^https?://##; s#/.*$##')"

  if [ $first -eq 1 ]; then first=0; else echo "," >> "$TARGETS_JSON"; fi
  cat >> "$TARGETS_JSON" <<EOF
  {"targets":["$target"],"labels":{"service":"$name","project":"$OBS_PROJECT","env":"$OBS_ENV"}}
EOF
done
unset IFS
echo "]" >> "$TARGETS_JSON"

if [ "$first" -eq 1 ]; then
  echo "[prometheus-agent] WARN: METRICS_TARGETS 为空或格式无效，仅采集 prometheus-agent 自身指标和 Exporter 指标" >&2
fi

CONFIG="/prometheus/prometheus.yml"
cat > "$CONFIG" <<EOF
global:
  scrape_interval: 15s
  external_labels:
    project: $OBS_PROJECT
    env: $OBS_ENV
    service: $OBS_SERVICE_NAME

scrape_configs:
  # Prometheus Agent 自身指标（用于验证采集链路是否正常）
  - job_name: "prometheus-agent"
    static_configs:
      - targets: ["localhost:9090"]

  # 业务服务指标（通过 METRICS_TARGETS 或 file_sd_configs 配置）
  - job_name: "services"
    metrics_path: /metrics
    file_sd_configs:
      - files: ["$TARGETS_JSON"]
        refresh_interval: 10s
EOF

# 自动发现并采集 Exporter 指标（Redis、MongoDB）
echo "" >> "$CONFIG"
echo "  # 自动发现/手动指定的 Exporter 指标" >> "$CONFIG"

trim() {
  printf "%s" "$1" | sed 's/^[[:space:]]*//;s/[[:space:]]*$//'
}

normalize_target() {
  raw="$1"
  default_port="$2"
  raw="$(printf "%s" "$raw" | sed -E 's#^https?://##; s#/.*$##')"
  raw="$(trim "$raw")"
  [ -z "$raw" ] && return 1
  case "$raw" in
    *:*) printf "%s" "$raw" ;;
    *) printf "%s:%s" "$raw" "$default_port" ;;
  esac
}

append_exporter_job() {
  job="$1"
  targets="$2"
  default_port="$3"
  service_label="$4"
  targets_list=""

  IFS=','
  for item in $targets; do
    item="$(normalize_target "$item" "$default_port" || true)"
    [ -z "$item" ] && continue
    if [ -z "$targets_list" ]; then
      targets_list="$item"
    else
      targets_list="${targets_list},$item"
    fi
  done
  unset IFS

  if [ -z "$targets_list" ]; then
    return 0
  fi

  echo "  - job_name: '$job'" >> "$CONFIG"
  echo "    static_configs:" >> "$CONFIG"
  echo "      - targets:" >> "$CONFIG"
  IFS=','
  for item in $targets_list; do
    echo "          - '$item'" >> "$CONFIG"
  done
  unset IFS
  cat >> "$CONFIG" <<EOF
        labels:
          project: '${OBS_PROJECT}'
          service: '${service_label}'
EOF
}

# Redis Exporter（端口 9121）
REDIS_EXPORTER_HOST=""
REDIS_EXPORTER_TARGETS="${REDIS_EXPORTER_TARGETS:-}"
REDIS_EXPORTER_SERVICE="${REDIS_EXPORTER_SERVICE:-$OBS_SERVICE_NAME}"
if getent hosts redis-exporter >/dev/null 2>&1; then
  REDIS_EXPORTER_HOST="redis-exporter"
elif getent hosts chat-deploy-redis-exporter >/dev/null 2>&1; then
  REDIS_EXPORTER_HOST="chat-deploy-redis-exporter"
fi
if [ -n "$REDIS_EXPORTER_HOST" ]; then
  if [ -n "$REDIS_EXPORTER_TARGETS" ]; then
    REDIS_EXPORTER_TARGETS="${REDIS_EXPORTER_TARGETS},${REDIS_EXPORTER_HOST}:9121"
  else
    REDIS_EXPORTER_TARGETS="${REDIS_EXPORTER_HOST}:9121"
  fi
fi
append_exporter_job "redis" "$REDIS_EXPORTER_TARGETS" "9121" "$REDIS_EXPORTER_SERVICE"
if [ -n "$REDIS_EXPORTER_TARGETS" ]; then
  echo "[prometheus-agent] Redis Exporter 采集目标已配置（project=${OBS_PROJECT} service=${REDIS_EXPORTER_SERVICE}）"
fi

# MongoDB Exporter（端口 9216）- chat-deploy 使用 MongoDB
MONGODB_EXPORTER_HOST=""
MONGODB_EXPORTER_TARGETS="${MONGODB_EXPORTER_TARGETS:-}"
MONGODB_EXPORTER_SERVICE="${MONGODB_EXPORTER_SERVICE:-$OBS_SERVICE_NAME}"
if getent hosts mongodb-exporter >/dev/null 2>&1; then
  MONGODB_EXPORTER_HOST="mongodb-exporter"
elif getent hosts chat-deploy-mongodb-exporter >/dev/null 2>&1; then
  MONGODB_EXPORTER_HOST="chat-deploy-mongodb-exporter"
fi
if [ -n "$MONGODB_EXPORTER_HOST" ]; then
  if [ -n "$MONGODB_EXPORTER_TARGETS" ]; then
    MONGODB_EXPORTER_TARGETS="${MONGODB_EXPORTER_TARGETS},${MONGODB_EXPORTER_HOST}:9216"
  else
    MONGODB_EXPORTER_TARGETS="${MONGODB_EXPORTER_HOST}:9216"
  fi
fi
append_exporter_job "mongodb" "$MONGODB_EXPORTER_TARGETS" "9216" "$MONGODB_EXPORTER_SERVICE"
if [ -n "$MONGODB_EXPORTER_TARGETS" ]; then
  echo "[prometheus-agent] MongoDB Exporter 采集目标已配置（project=${OBS_PROJECT} service=${MONGODB_EXPORTER_SERVICE}）"
fi

# Node Exporter（端口 9100）- 用于系统级指标（CPU/Memory/Disk/Network/IO）
NODE_EXPORTER_HOST=""
NODE_EXPORTER_TARGETS="${NODE_EXPORTER_TARGETS:-}"
NODE_EXPORTER_SERVICE="${NODE_EXPORTER_SERVICE:-$OBS_SERVICE_NAME}"
if getent hosts node-exporter >/dev/null 2>&1; then
  NODE_EXPORTER_HOST="node-exporter"
elif getent hosts chat-deploy-node-exporter >/dev/null 2>&1; then
  NODE_EXPORTER_HOST="chat-deploy-node-exporter"
fi
if [ -n "$NODE_EXPORTER_HOST" ]; then
  if [ -n "$NODE_EXPORTER_TARGETS" ]; then
    NODE_EXPORTER_TARGETS="${NODE_EXPORTER_TARGETS},${NODE_EXPORTER_HOST}:9100"
  else
    NODE_EXPORTER_TARGETS="${NODE_EXPORTER_HOST}:9100"
  fi
fi
append_exporter_job "node" "$NODE_EXPORTER_TARGETS" "9100" "$NODE_EXPORTER_SERVICE"
if [ -n "$NODE_EXPORTER_TARGETS" ]; then
  echo "[prometheus-agent] Node Exporter 采集目标已配置（project=${OBS_PROJECT} service=${NODE_EXPORTER_SERVICE}）"
fi

cat >> "$CONFIG" <<EOF

remote_write:
  - url: "$METRICS_REMOTE_WRITE_URL"
EOF

if is_truthy "$OBS_AUTH_ENABLE"; then
  echo "    bearer_token: \"$OBS_AUTH_TOKEN\"" >> "$CONFIG"
  echo "[prometheus-agent] remote_write 鉴权已启用" >&2
else
  echo "[prometheus-agent] remote_write 鉴权未启用" >&2
fi

echo "[prometheus-agent] 配置文件已生成:"
cat "$CONFIG"
echo ""

# Prometheus 3.x 不再需要 --enable-feature=agent
exec /bin/prometheus --config.file=/prometheus/prometheus.yml --storage.tsdb.path=/prometheus/data --web.enable-lifecycle