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:
2026-06-12 15:21:35 +08:00
parent 69815d918a
commit 4a6c126366
30 changed files with 2030 additions and 28 deletions

View File

@@ -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