完善外部生成Worker动态扩缩容
新增外部生成controller进程角色与systemd服务 补齐队列统计procedure与spacetime-client绑定 更新生产部署脚本、健康巡检和server provision的worker/controller口径 新增容器worker smoke脚本并同步运维文档与团队记忆
This commit is contained in:
@@ -23,6 +23,46 @@ const checks = [
|
||||
includes: 'genarrative-health-patrol.timer',
|
||||
reason: 'Server-Provision 必须安装并启用健康巡检 timer。',
|
||||
},
|
||||
{
|
||||
file: 'scripts/jenkins-server-provision.sh',
|
||||
includes: 'genarrative-external-generation-controller.service',
|
||||
reason: 'Server-Provision 必须安装并启用外部生成 worker controller。',
|
||||
},
|
||||
{
|
||||
file: 'scripts/jenkins-server-provision.sh',
|
||||
includes: 'genarrative-external-generation-worker@1.service',
|
||||
reason: 'Server-Provision 必须启用外部生成保底 worker 实例。',
|
||||
},
|
||||
{
|
||||
file: 'scripts/deploy/production-api-deploy.sh',
|
||||
includes: 'ensure_default_worker_service',
|
||||
reason: 'API Deploy 必须在缺少 worker 实例时补启动默认外部生成 worker。',
|
||||
},
|
||||
{
|
||||
file: 'scripts/deploy/production-api-deploy.sh',
|
||||
includes: 'wait_for_worker_services',
|
||||
reason: 'API Deploy 必须等待外部生成 worker 实例 active。',
|
||||
},
|
||||
{
|
||||
file: 'scripts/deploy/production-api-deploy.sh',
|
||||
includes: 'wait_for_worker_controller_service',
|
||||
reason: 'API Deploy 必须重启并验活外部生成 worker controller。',
|
||||
},
|
||||
{
|
||||
file: 'deploy/systemd/genarrative-external-generation-worker@.service',
|
||||
includes: 'GENARRATIVE_PROCESS_ROLE=external-generation-worker',
|
||||
reason: '外部生成 worker 模板必须作为独立 worker 进程角色运行。',
|
||||
},
|
||||
{
|
||||
file: 'deploy/systemd/genarrative-external-generation-controller.service',
|
||||
includes: 'GENARRATIVE_PROCESS_ROLE=external-generation-controller',
|
||||
reason: '外部生成 worker controller 必须作为独立进程角色运行。',
|
||||
},
|
||||
{
|
||||
file: 'scripts/ops/production-health-patrol.mjs',
|
||||
includes: 'checkActiveWorkerInstances',
|
||||
reason: '生产健康巡检必须检查至少一个外部生成 worker 实例 active。',
|
||||
},
|
||||
{
|
||||
file: 'scripts/build-production-release.sh',
|
||||
includes: 'production-health-patrol.mjs',
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -5,11 +5,11 @@ set -euo pipefail
|
||||
usage() {
|
||||
cat <<'EOF'
|
||||
用法:
|
||||
./scripts/deploy/production-api-deploy.sh --source-dir build/<version> [--version <version>] [--release-root /opt/genarrative/releases] [--current-link /opt/genarrative/current] [--service genarrative-api.service] [--worker-service-pattern 'genarrative-external-generation-worker@*.service'] [--no-worker-services] [--health-url http://127.0.0.1:8082/readyz] [--api-env-file /etc/genarrative/api-server.env] [--database genarrative-prod] [--spacetime-server-url http://127.0.0.1:3101]
|
||||
./scripts/deploy/production-api-deploy.sh --source-dir build/<version> [--version <version>] [--release-root /opt/genarrative/releases] [--current-link /opt/genarrative/current] [--service genarrative-api.service] [--worker-service-pattern 'genarrative-external-generation-worker@*.service'] [--no-worker-services] [--worker-controller-service genarrative-external-generation-controller.service] [--no-worker-controller] [--health-url http://127.0.0.1:8082/readyz] [--api-env-file /etc/genarrative/api-server.env] [--database genarrative-prod] [--spacetime-server-url http://127.0.0.1:3101]
|
||||
|
||||
说明:
|
||||
进入维护模式,校验并发布 api-server 单文件,更新 current 链接,重启 systemd 服务并执行 readiness 检查。
|
||||
默认同时重启已加载的外部生成 worker 实例;未启用 worker 单元时会自动跳过。
|
||||
默认同时重启外部生成 worker controller 和已加载的 worker 实例;未启用 worker 单元时会自动跳过。
|
||||
若传入 --database,会在重启前把 GENARRATIVE_SPACETIME_DATABASE 写入 api-server 环境文件,避免服务继续读取旧库。
|
||||
失败时保留维护模式。
|
||||
EOF
|
||||
@@ -317,6 +317,43 @@ wait_for_worker_services() {
|
||||
return 1
|
||||
}
|
||||
|
||||
ensure_worker_controller_service() {
|
||||
local service="$1"
|
||||
|
||||
if [[ -z "${service}" ]]; then
|
||||
return 0
|
||||
fi
|
||||
|
||||
if ! systemctl cat "${service}" >/dev/null 2>&1; then
|
||||
echo "[production-api-deploy] 缺少外部生成 worker controller systemd 单元: ${service}" >&2
|
||||
return 1
|
||||
fi
|
||||
|
||||
echo "[production-api-deploy] 启用并重启外部生成 worker controller: ${service}"
|
||||
systemctl enable "${service}"
|
||||
systemctl restart "${service}"
|
||||
}
|
||||
|
||||
wait_for_worker_controller_service() {
|
||||
local service="$1"
|
||||
|
||||
if [[ -z "${service}" ]]; then
|
||||
return 0
|
||||
fi
|
||||
|
||||
echo "[production-api-deploy] 等待外部生成 worker controller active: ${service}"
|
||||
for _ in {1..30}; do
|
||||
if systemctl is-active --quiet "${service}"; then
|
||||
return 0
|
||||
fi
|
||||
sleep 2
|
||||
done
|
||||
|
||||
systemctl --no-pager --full status "${service}" || true
|
||||
echo "[production-api-deploy] 外部生成 worker controller 未在超时时间内进入 active,发布失败。" >&2
|
||||
return 1
|
||||
}
|
||||
|
||||
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
||||
SOURCE_DIR=""
|
||||
VERSION=""
|
||||
@@ -324,6 +361,7 @@ RELEASE_ROOT="/opt/genarrative/releases"
|
||||
CURRENT_LINK="/opt/genarrative/current"
|
||||
SERVICE_NAME="genarrative-api.service"
|
||||
WORKER_SERVICE_PATTERN="genarrative-external-generation-worker@*.service"
|
||||
WORKER_CONTROLLER_SERVICE="genarrative-external-generation-controller.service"
|
||||
HEALTH_URL="http://127.0.0.1:8082/readyz"
|
||||
API_ENV_FILE="/etc/genarrative/api-server.env"
|
||||
DATABASE=""
|
||||
@@ -364,6 +402,14 @@ while [[ $# -gt 0 ]]; do
|
||||
WORKER_SERVICE_PATTERN=""
|
||||
shift
|
||||
;;
|
||||
--worker-controller-service)
|
||||
WORKER_CONTROLLER_SERVICE="${2:?缺少 --worker-controller-service 的值}"
|
||||
shift 2
|
||||
;;
|
||||
--no-worker-controller)
|
||||
WORKER_CONTROLLER_SERVICE=""
|
||||
shift
|
||||
;;
|
||||
--health-url)
|
||||
HEALTH_URL="${2:?缺少 --health-url 的值}"
|
||||
shift 2
|
||||
@@ -488,6 +534,8 @@ echo "[production-api-deploy] 重启服务: ${SERVICE_NAME}"
|
||||
systemctl restart "${SERVICE_NAME}"
|
||||
restart_worker_services "${WORKER_SERVICE_PATTERN}"
|
||||
wait_for_worker_services "${WORKER_SERVICE_PATTERN}"
|
||||
ensure_worker_controller_service "${WORKER_CONTROLLER_SERVICE}"
|
||||
wait_for_worker_controller_service "${WORKER_CONTROLLER_SERVICE}"
|
||||
|
||||
echo "[production-api-deploy] 等待 readiness: ${HEALTH_URL}"
|
||||
for _ in {1..30}; do
|
||||
|
||||
@@ -5,6 +5,7 @@ PROVISION_TOOLS_DIR="${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}"
|
||||
WORKER_ENV_FILE="${WORKER_ENV_FILE:-/etc/genarrative/external-generation-worker.env}"
|
||||
CONTROLLER_ENV_FILE="${CONTROLLER_ENV_FILE:-/etc/genarrative/external-generation-controller.env}"
|
||||
GENARRATIVE_OPENSSL_VERSION="${GENARRATIVE_OPENSSL_VERSION:-3.2.0}"
|
||||
GENARRATIVE_OPENSSL_PREFIX="${GENARRATIVE_OPENSSL_PREFIX:-/opt/genarrative/openssl-3.2.0}"
|
||||
GENARRATIVE_OPENSSL_SOURCE_URL="${GENARRATIVE_OPENSSL_SOURCE_URL:-https://github.com/openssl/openssl/releases/download/openssl-${GENARRATIVE_OPENSSL_VERSION}/openssl-${GENARRATIVE_OPENSSL_VERSION}.tar.gz}"
|
||||
@@ -542,6 +543,10 @@ render_external_generation_worker_env_example() {
|
||||
cat deploy/env/external-generation-worker.env.example
|
||||
}
|
||||
|
||||
render_external_generation_controller_env_example() {
|
||||
cat deploy/env/external-generation-controller.env.example
|
||||
}
|
||||
|
||||
render_otelcol_service() {
|
||||
cat deploy/systemd/otelcol-contrib.service
|
||||
}
|
||||
@@ -740,6 +745,18 @@ render_external_generation_worker_service() {
|
||||
deploy/systemd/genarrative-external-generation-worker@.service
|
||||
}
|
||||
|
||||
render_external_generation_controller_service() {
|
||||
local current_escaped api_env_escaped controller_env_escaped
|
||||
current_escaped="$(escape_sed_replacement "${CURRENT_LINK}")"
|
||||
api_env_escaped="$(escape_sed_replacement "${API_ENV_FILE}")"
|
||||
controller_env_escaped="$(escape_sed_replacement "${CONTROLLER_ENV_FILE}")"
|
||||
sed \
|
||||
-e "s|/opt/genarrative/current|${current_escaped}|g" \
|
||||
-e "s|/etc/genarrative/api-server.env|${api_env_escaped}|g" \
|
||||
-e "s|/etc/genarrative/external-generation-controller.env|${controller_env_escaped}|g" \
|
||||
deploy/systemd/genarrative-external-generation-controller.service
|
||||
}
|
||||
|
||||
render_database_backup_service() {
|
||||
local current_escaped env_escaped
|
||||
current_escaped="$(escape_sed_replacement "${CURRENT_LINK}")"
|
||||
@@ -761,6 +778,7 @@ render_health_patrol_service() {
|
||||
require_path deploy/systemd/spacetimedb.service
|
||||
require_path deploy/systemd/genarrative-api.service
|
||||
require_path deploy/systemd/genarrative-external-generation-worker@.service
|
||||
require_path deploy/systemd/genarrative-external-generation-controller.service
|
||||
require_path deploy/systemd/genarrative-database-backup.service
|
||||
require_path deploy/systemd/genarrative-database-backup.timer
|
||||
require_path deploy/systemd/genarrative-health-patrol.service
|
||||
@@ -772,6 +790,7 @@ require_path deploy/nginx/genarrative-dev-http.conf
|
||||
require_path deploy/nginx/snippets/genarrative-maintenance.conf
|
||||
require_path deploy/env/api-server.env.example
|
||||
require_path deploy/env/external-generation-worker.env.example
|
||||
require_path deploy/env/external-generation-controller.env.example
|
||||
require_path scripts/deploy/maintenance-on.sh
|
||||
require_path scripts/deploy/maintenance-off.sh
|
||||
require_path scripts/deploy/maintenance-status.sh
|
||||
@@ -816,21 +835,24 @@ sync_spacetime_install "${SPACETIME_ROOT}"
|
||||
spacetimedb_service="$(mktemp)"
|
||||
api_service="$(mktemp)"
|
||||
external_generation_worker_service="$(mktemp)"
|
||||
external_generation_controller_service="$(mktemp)"
|
||||
database_backup_service="$(mktemp)"
|
||||
health_patrol_service="$(mktemp)"
|
||||
render_spacetimedb_service >"${spacetimedb_service}"
|
||||
render_api_service >"${api_service}"
|
||||
render_external_generation_worker_service >"${external_generation_worker_service}"
|
||||
render_external_generation_controller_service >"${external_generation_controller_service}"
|
||||
render_database_backup_service >"${database_backup_service}"
|
||||
render_health_patrol_service >"${health_patrol_service}"
|
||||
install_file "${spacetimedb_service}" /etc/systemd/system/spacetimedb.service 0644
|
||||
install_file "${api_service}" /etc/systemd/system/genarrative-api.service 0644
|
||||
install_file "${external_generation_worker_service}" /etc/systemd/system/genarrative-external-generation-worker@.service 0644
|
||||
install_file "${external_generation_controller_service}" /etc/systemd/system/genarrative-external-generation-controller.service 0644
|
||||
install_file "${database_backup_service}" /etc/systemd/system/genarrative-database-backup.service 0644
|
||||
install_file deploy/systemd/genarrative-database-backup.timer /etc/systemd/system/genarrative-database-backup.timer 0644
|
||||
install_file "${health_patrol_service}" /etc/systemd/system/genarrative-health-patrol.service 0644
|
||||
install_file deploy/systemd/genarrative-health-patrol.timer /etc/systemd/system/genarrative-health-patrol.timer 0644
|
||||
rm -f "${spacetimedb_service}" "${api_service}" "${external_generation_worker_service}" "${database_backup_service}" "${health_patrol_service}"
|
||||
rm -f "${spacetimedb_service}" "${api_service}" "${external_generation_worker_service}" "${external_generation_controller_service}" "${database_backup_service}" "${health_patrol_service}"
|
||||
|
||||
if [[ ! -f "${API_ENV_FILE}" ]]; then
|
||||
echo "+ create ${API_ENV_FILE} from example"
|
||||
@@ -855,6 +877,17 @@ else
|
||||
echo "[server-provision] 已存在 worker 环境文件,保留不覆盖: ${WORKER_ENV_FILE}"
|
||||
fi
|
||||
|
||||
if [[ ! -f "${CONTROLLER_ENV_FILE}" ]]; then
|
||||
echo "+ create ${CONTROLLER_ENV_FILE} from example"
|
||||
if [[ "${DRY_RUN}" != "true" ]]; then
|
||||
render_external_generation_controller_env_example >"${CONTROLLER_ENV_FILE}"
|
||||
chmod 0600 "${CONTROLLER_ENV_FILE}"
|
||||
chown root:root "${CONTROLLER_ENV_FILE}"
|
||||
fi
|
||||
else
|
||||
echo "[server-provision] 已存在 controller 环境文件,保留不覆盖: ${CONTROLLER_ENV_FILE}"
|
||||
fi
|
||||
|
||||
if [[ "${ENABLE_OTELCOL:-true}" == "true" ]]; then
|
||||
sync_otelcol_install
|
||||
otelcol_service="$(mktemp)"
|
||||
@@ -876,7 +909,7 @@ if [[ "${ENABLE_SERVICES}" == "true" ]]; then
|
||||
if [[ "${ENABLE_OTELCOL:-true}" == "true" ]]; then
|
||||
run_cmd systemctl enable otelcol-contrib.service
|
||||
fi
|
||||
run_cmd systemctl enable spacetimedb.service genarrative-api.service genarrative-database-backup.timer genarrative-external-generation-worker@1.service genarrative-health-patrol.timer
|
||||
run_cmd systemctl enable spacetimedb.service genarrative-api.service genarrative-database-backup.timer genarrative-external-generation-worker@1.service genarrative-external-generation-controller.service genarrative-health-patrol.timer
|
||||
if [[ "${ENABLE_OTELCOL:-true}" == "true" ]]; then
|
||||
run_cmd systemctl restart otelcol-contrib.service
|
||||
fi
|
||||
@@ -887,8 +920,10 @@ if [[ "${ENABLE_SERVICES}" == "true" ]]; then
|
||||
run_cmd systemctl restart genarrative-api.service
|
||||
run_cmd systemctl enable --now genarrative-external-generation-worker@1.service
|
||||
run_cmd systemctl restart genarrative-external-generation-worker@1.service
|
||||
run_cmd systemctl enable --now genarrative-external-generation-controller.service
|
||||
run_cmd systemctl restart genarrative-external-generation-controller.service
|
||||
else
|
||||
echo "[server-provision] 尚未发现 ${CURRENT_LINK}/api-server,跳过 api-server 和外部生成 worker 首次启动。后续 API deploy 会启用并启动默认 worker 实例。"
|
||||
echo "[server-provision] 尚未发现 ${CURRENT_LINK}/api-server,跳过 api-server、外部生成 worker 和 controller 首次启动。后续 API deploy 会启用并启动默认 worker 与 controller。"
|
||||
fi
|
||||
fi
|
||||
|
||||
|
||||
@@ -20,9 +20,11 @@ const DEFAULT_PUBLIC_PATHS = [
|
||||
|
||||
const DEFAULT_SERVICES = [
|
||||
'genarrative-api.service',
|
||||
'genarrative-external-generation-controller.service',
|
||||
'spacetimedb.service',
|
||||
'nginx.service',
|
||||
];
|
||||
const WORKER_SERVICE_PATTERN = 'genarrative-external-generation-worker@*.service';
|
||||
|
||||
function usage() {
|
||||
console.log(`Usage:
|
||||
@@ -216,6 +218,61 @@ async function checkService(serviceName, timeoutMs) {
|
||||
);
|
||||
}
|
||||
|
||||
async function checkActiveWorkerInstances(config) {
|
||||
const result = await runCommand(
|
||||
'systemctl',
|
||||
[
|
||||
'list-units',
|
||||
WORKER_SERVICE_PATTERN,
|
||||
'--type=service',
|
||||
'--state=active',
|
||||
'--no-legend',
|
||||
'--plain',
|
||||
'--no-pager',
|
||||
],
|
||||
config.timeoutMs,
|
||||
);
|
||||
if (result.code !== 0) {
|
||||
return checkResult(
|
||||
'service:external-generation-workers',
|
||||
'CRITICAL',
|
||||
'无法枚举外部生成 worker 实例',
|
||||
{
|
||||
command: result.command,
|
||||
stderr: result.stderr.trim() || result.error,
|
||||
},
|
||||
);
|
||||
}
|
||||
|
||||
const services = result.stdout
|
||||
.split('\n')
|
||||
.map((line) => line.trim().split(/\s+/u)[0])
|
||||
.filter((service) =>
|
||||
/^genarrative-external-generation-worker@.+\.service$/u.test(service),
|
||||
);
|
||||
|
||||
if (services.length === 0) {
|
||||
return checkResult(
|
||||
'service:external-generation-workers',
|
||||
'CRITICAL',
|
||||
'没有 active 的外部生成 worker 实例',
|
||||
{
|
||||
command: result.command,
|
||||
},
|
||||
);
|
||||
}
|
||||
|
||||
return checkResult(
|
||||
'service:external-generation-workers',
|
||||
'OK',
|
||||
`${services.length} 个 worker active`,
|
||||
{
|
||||
command: result.command,
|
||||
services,
|
||||
},
|
||||
);
|
||||
}
|
||||
|
||||
function requestUrl(url, timeoutMs) {
|
||||
return new Promise((resolve) => {
|
||||
const startedAt = Date.now();
|
||||
@@ -310,6 +367,10 @@ async function checkRecentJournal(config) {
|
||||
'-u',
|
||||
'genarrative-api.service',
|
||||
'-u',
|
||||
'genarrative-external-generation-controller.service',
|
||||
'-u',
|
||||
WORKER_SERVICE_PATTERN,
|
||||
'-u',
|
||||
'spacetimedb.service',
|
||||
'-u',
|
||||
'nginx.service',
|
||||
@@ -426,6 +487,7 @@ async function main() {
|
||||
for (const serviceName of DEFAULT_SERVICES) {
|
||||
checks.push(await checkService(serviceName, config.timeoutMs));
|
||||
}
|
||||
checks.push(await checkActiveWorkerInstances(config));
|
||||
|
||||
checks.push(await checkHttp('api:/healthz', joinUrl(config.apiBaseUrl, '/healthz'), config));
|
||||
checks.push(await checkHttp('api:/readyz', joinUrl(config.apiBaseUrl, '/readyz'), config));
|
||||
|
||||
Reference in New Issue
Block a user