feat(deploy): prepare offline provision tools and container loadtest

scripts/jenkins-server-provision.sh

@@ -1,6 +1,24 @@
 #!/usr/bin/env bash
 set -euo pipefail
 
+PROVISION_TOOLS_DIR="${PROVISION_TOOLS_DIR:-provision-tools}"
+SPACETIME_BIN_SOURCE="${SPACETIME_BIN_SOURCE:-${PROVISION_TOOLS_DIR}/spacetime/spacetime}"
+OTELCOL_BIN_SOURCE="${OTELCOL_BIN_SOURCE:-${PROVISION_TOOLS_DIR}/otelcol-contrib}"
+
+require_non_root_relative_path() {
+  local label="$1"
+  local path="$2"
+
+  if [[ -z "${path}" ]]; then
+    echo "[server-provision] ${label} 不能为空。" >&2
+    exit 1
+  fi
+  if [[ "${path}" == /* || "${path}" == *..* ]]; then
+    echo "[server-provision] ${label} 只能是工作区内的相对路径: ${path}" >&2
+    exit 1
+  fi
+}
+
 require_path() {
   local path="$1"
   if [[ ! -e "${path}" ]]; then
@@ -81,16 +99,16 @@ install_sccache() {
   fi
 
   echo "[server-provision] 未找到 sccache，准备通过 cargo install sccache 安装。"
-  if ! command -v cargo >/dev/null 2>&1; then
-    echo "[server-provision] 未找到 cargo，无法自动安装 sccache。请先安装 Rust 工具链后重跑 Server-Provision。" >&2
-    exit 1
-  fi
-
   if [[ "${DRY_RUN}" == "true" ]]; then
     echo "+ cargo install sccache --locked"
     return
   fi
 
+  if ! command -v cargo >/dev/null 2>&1; then
+    echo "[server-provision] 未找到 cargo，无法自动安装 sccache。请先安装 Rust 工具链后重跑 Server-Provision。" >&2
+    exit 1
+  fi
+
   cargo install sccache --locked
   if ! command -v sccache >/dev/null 2>&1 && [[ ! -x /root/.cargo/bin/sccache ]]; then
     echo "[server-provision] sccache 安装后仍不可用，请检查 cargo bin 目录是否在 PATH 中。" >&2
@@ -98,6 +116,42 @@ install_sccache() {
   fi
 }
 
+sync_otelcol_install() {
+  local target_bin="/usr/local/bin/otelcol-contrib"
+  local source_bin="${OTELCOL_BIN_SOURCE}"
+  local version="${OTELCOL_VERSION:-0.151.0}"
+  local resolved_source="${source_bin}"
+
+  if [[ "${ENABLE_OTELCOL:-true}" != "true" ]]; then
+    echo "[server-provision] ENABLE_OTELCOL=${ENABLE_OTELCOL:-}，跳过 otelcol-contrib 配置。"
+    return
+  fi
+
+  if command -v readlink >/dev/null 2>&1; then
+    resolved_source="$(readlink -f "${source_bin}" 2>/dev/null || echo "${source_bin}")"
+  fi
+
+  if [[ ! -x "${resolved_source}" ]]; then
+    echo "[server-provision] otelcol-contrib 不存在或不可执行: ${source_bin}" >&2
+    echo "[server-provision] 请先在构建机准备好 otelcol-contrib ${version}，再通过 provision-tools 上传到目标机。" >&2
+    exit 1
+  fi
+
+  if [[ "${DRY_RUN}" == "true" ]]; then
+    echo "+ install -m 0755 ${resolved_source} ${target_bin}"
+    return
+  fi
+
+  install -m 0755 "${resolved_source}" "${target_bin}"
+  if ! "${target_bin}" --version >/dev/null 2>&1; then
+    echo "[server-provision] otelcol-contrib 安装后无法执行: ${target_bin}" >&2
+    exit 1
+  fi
+  if ! "${target_bin}" --version 2>/dev/null | grep -q "${version}"; then
+    echo "[server-provision] 警告: otelcol-contrib 版本不是期望的 ${version}: $("${target_bin}" --version 2>/dev/null || true)" >&2
+  fi
+}
+
 sync_spacetime_install() {
   local root_dir="$1"
   local target_bin_dir="${root_dir}/bin/current"
@@ -106,14 +160,6 @@ sync_spacetime_install() {
   local resolved_command="${SPACETIME_BIN_SOURCE}"
   local install_dir=""
   local root_bin="${root_dir}/bin"
-  local share_bin_dir=""
-  local version_dir=""
-  local parent_dir=""
-
-  if [[ -x "${target_cli}" && -x "${target_standalone}" ]]; then
-    echo "[server-provision] SpacetimeDB current 目录已存在: ${target_bin_dir}"
-    return
-  fi
 
   echo "[server-provision] 同步 SpacetimeDB current 目录到 ${target_bin_dir}"
   if [[ "${DRY_RUN}" == "true" ]]; then
@@ -128,26 +174,10 @@ sync_spacetime_install() {
   install_dir="$(cd -- "$(dirname -- "${resolved_command}")" && pwd)"
   mkdir -p "${root_bin}"
 
-  for share_bin_dir in \
-    "/usr/.local/share/spacetime/bin" \
-    "/root/.local/share/spacetime/bin" \
-    "${HOME:-}/.local/share/spacetime/bin"; do
-    if [[ -d "${share_bin_dir}" ]]; then
-      version_dir="$(find "${share_bin_dir}" -mindepth 1 -maxdepth 1 -type d | sort -V | tail -n 1)"
-      if [[ -n "${version_dir}" && -x "${version_dir}/spacetimedb-cli" && -x "${version_dir}/spacetimedb-standalone" ]]; then
-        echo "[server-provision] 同步 SpacetimeDB 安装: ${version_dir} -> ${target_bin_dir}"
-        rm -rf "${target_bin_dir}"
-        mkdir -p "${target_bin_dir}"
-        cp -a "${version_dir}/." "${target_bin_dir}/"
-        chmod +x "${target_cli}" "${target_standalone}"
-        chown -R spacetimedb:spacetimedb "${root_bin}"
-        return
-      fi
-    fi
-  done
-
   if [[ -d "${install_dir}/bin" ]]; then
     echo "[server-provision] 同步 SpacetimeDB 安装: ${install_dir}/bin -> ${root_bin}"
+    rm -rf "${root_bin}"
+    mkdir -p "${root_bin}"
     cp -a "${install_dir}/bin/." "${root_bin}/"
   elif [[ -x "${install_dir}/spacetimedb-cli" && -x "${install_dir}/spacetimedb-standalone" ]]; then
     echo "[server-provision] 同步 SpacetimeDB 安装: ${install_dir} -> ${target_bin_dir}"
@@ -156,14 +186,8 @@ sync_spacetime_install() {
     cp -f "${install_dir}/spacetimedb-cli" "${target_cli}"
     cp -f "${install_dir}/spacetimedb-standalone" "${target_standalone}"
     chmod +x "${target_cli}" "${target_standalone}"
-  elif [[ -f "${resolved_command}" ]]; then
-    parent_dir="$(cd -- "${install_dir}/.." && pwd)"
-    if [[ -d "${parent_dir}/bin" && -x "${parent_dir}/bin/current/spacetimedb-cli" && -x "${parent_dir}/bin/current/spacetimedb-standalone" ]]; then
-      echo "[server-provision] 同步 SpacetimeDB 安装: ${parent_dir}/bin -> ${root_bin}"
-      cp -a "${parent_dir}/bin/." "${root_bin}/"
-    else
-      echo "[server-provision] 未能从 spacetime 命令路径推断完整 SpacetimeDB 安装目录: ${resolved_command}" >&2
-    fi
+  else
+    echo "[server-provision] 未能从 SpacetimeDB 交付包推断完整安装目录: ${resolved_command}" >&2
   fi
 
   if [[ ! -x "${target_cli}" || ! -x "${target_standalone}" ]]; then
@@ -387,6 +411,10 @@ render_api_env_example() {
     deploy/env/api-server.env.example
 }
 
+render_otelcol_service() {
+  cat deploy/systemd/otelcol-contrib.service
+}
+
 validate_nginx_tls() {
   local cert_dir="/etc/letsencrypt/live/${SERVER_NAME}"
   if [[ "${SERVER_NAME}" == "genarrative.example.com" ]]; then
@@ -523,6 +551,8 @@ render_api_service() {
 
 require_path deploy/systemd/spacetimedb.service
 require_path deploy/systemd/genarrative-api.service
+require_path deploy/systemd/otelcol-contrib.service
+require_path deploy/otelcol/genarrative-debug.yaml
 require_path deploy/nginx/genarrative.conf
 require_path deploy/nginx/genarrative-dev-http.conf
 require_path deploy/nginx/snippets/genarrative-maintenance.conf
@@ -532,6 +562,7 @@ require_path scripts/deploy/maintenance-off.sh
 require_path scripts/deploy/maintenance-status.sh
 
 validate_server_names
+require_non_root_relative_path "PROVISION_TOOLS_DIR" "${PROVISION_TOOLS_DIR}"
 
 echo "[server-provision] target=${DEPLOY_TARGET}, dry_run=${DRY_RUN}, nginx_config_mode=${NGINX_CONFIG_MODE}, source_commit=$(cat .jenkins-source-commit)"
 
@@ -585,6 +616,16 @@ else
   echo "[server-provision] 已存在环境文件，保留不覆盖: ${API_ENV_FILE}"
 fi
 
+if [[ "${ENABLE_OTELCOL:-true}" == "true" ]]; then
+  sync_otelcol_install
+  otelcol_service="$(mktemp)"
+  render_otelcol_service >"${otelcol_service}"
+  install_file "${otelcol_service}" /etc/systemd/system/otelcol-contrib.service 0644
+  rm -f "${otelcol_service}"
+else
+  echo "[server-provision] ENABLE_OTELCOL=${ENABLE_OTELCOL:-}，跳过 otelcol-contrib service 安装。"
+fi
+
 if [[ "${NGINX_CONFIG_MODE}" != "none" ]]; then
   install_nginx_config_with_rollback
 else
@@ -593,7 +634,13 @@ fi
 
 run_cmd systemctl daemon-reload
 if [[ "${ENABLE_SERVICES}" == "true" ]]; then
+  if [[ "${ENABLE_OTELCOL:-true}" == "true" ]]; then
+    run_cmd systemctl enable otelcol-contrib.service
+  fi
   run_cmd systemctl enable spacetimedb.service genarrative-api.service
+  if [[ "${ENABLE_OTELCOL:-true}" == "true" ]]; then
+    run_cmd systemctl restart otelcol-contrib.service
+  fi
   run_cmd systemctl restart spacetimedb.service
   wait_for_spacetimedb_service
   ensure_spacetime_owner_client_token