add debug

README.md

@@ -1,13 +1,110 @@
-efka
-=====
+# ws_channel 模块 API 文档与交互逻辑
 
-An OTP application
+## 注意websocket的数据格式为: text
 
-1. 先解决数据的上行问题
-2. todo list
-    要解决连接断开重新连接的问题 !!!
+## 一、模块概述
+`ws_channel` 是基于 Erlang + Cowboy WebSocket 实现的 MQTT 相关交互模块，主要用于服务注册、主题订阅、指标数据上报、事件发送及消息广播等功能，通过 WebSocket 协议实现客户端与服务端的实时双向通信。
 
-Build
------
 
-    $ rebar3 compile
+## 三、核心 API 方法
+客户端通过发送 **JSON 格式文本消息** 与服务端交互，消息格式遵循 JSON-RPC 风格（包含 `id`、`method`、`params` 字段）。
+
+
+### 1. 服务注册（register）
+#### 功能
+注册服务并建立客户端与服务进程的关联，是后续操作（订阅、上报数据等）的前提。
+
+#### 请求格式
+```json
+{
+  "id": <整数，请求唯一标识>,
+  "method": "register",
+  "params": {
+    "service_id": <二进制，服务唯一标识，必填>,
+    "meta_data": <映射，服务元数据，可选>,
+    "container_name": <二进制，容器名称，可选>
+  }
+}
+```
+
+#### 响应格式
+- 成功响应：
+  ```json
+  {
+    "id": <与请求id一致>,
+    "result": "ok"
+  }
+  ```
+- 失败处理：服务端直接关闭连接（因 `attach_channel` 失败）
+
+### 2. 主题订阅（subscribe）
+#### 功能
+订阅指定主题，后续可接收该主题的广播消息。
+
+#### 请求格式
+```json
+{
+  "id": <整数，请求唯一标识>,
+  "method": "subscribe",
+  "params": {
+    "topic": <二进制，订阅的主题名称，必填>
+  }
+}
+```
+
+#### 响应格式
+- 成功响应：
+  ```json
+  {
+    "id": <与请求id一致>,
+    "result": "ok"
+  }
+  ```
+- 失败响应：
+  ```json
+  {
+    "id": <与请求id一致>,
+    "error": {
+      "code": -1,
+      "message": "错误描述"
+    }
+  }
+  ```
+
+#### 处理逻辑
+通过 `efka_subscription:subscribe(Topic, self())` 完成订阅，订阅成功后客户端会收到该主题的广播消息。
+
+
+### 3. 指标数据上报（metric_data）
+#### 功能
+向服务进程上报设备指标数据。
+
+#### 请求格式
+```json
+{
+  "method": "metric_data",
+  "params": {
+    "route_key": <二进制，路由键，必填>,
+    "metric": <指标数据，必填>
+  }
+}
+```
+
+#### 响应处理
+服务端接收后无返回消息（处理逻辑：`efka_service:metric_data(ServicePid, DeviceUUID, RouteKey, Metric)`）
+
+## 五、基础交互协议
+1. **Ping/Pong 心跳**：
+    - 客户端发送 `ping` 消息
+    - 服务端回复 `pong` 消息，维持连接
+
+2. **未知消息处理**：
+    - 客户端发送未定义格式的消息时，服务端记录错误并关闭连接
+
+## 七、典型交互流程
+1. 客户端发起 WebSocket 连接
+2. 客户端发送 `register` 请求完成注册
+3. 客户端发送 `subscribe` 请求订阅目标主题
+4. 客户端通过 `metric_data` 上报指标数据 / 通过 `event` 发送事件
+5. 服务端向客户端推送已订阅主题的消息（`publish` 方法）
+6. 连接关闭（主动断开或异常终止）

apps/efka/include/efka.hrl

@@ -1,54 +0,0 @@
-%%%-------------------------------------------------------------------
-%%% @author anlicheng
-%%% @copyright (C) 2025, <COMPANY>
-%%% @doc
-%%% 扩展部分, 1: 支持基于topic的pub/sub机制; 2. 基于target的单点通讯和广播
-%%% @end
-%%% Created : 21. 4月 2025 17:28
-%%%-------------------------------------------------------------------
--author("anlicheng").
-
-%% efka主动发起的消息体类型, 消息大类
--define(PACKET_REQUEST, 16#01).
--define(PACKET_RESPONSE, 16#02).
-
-%% 服务器基于pub/sub的消息, 消息大类
--define(PACKET_PUB, 16#03).
-
-%% push调用不需要返回, 消息大类
--define(PACKET_COMMAND, 16#04).
-
-%% 服务器端推送消息
--define(PACKET_ASYNC_CALL, 16#05).
--define(PACKET_ASYNC_CALL_REPLY, 16#06).
-
-%% ping包，客户端主动发起
--define(PACKET_PING, 16#FF).
-
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-%%%% 二级分类定义
-%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
-
-%% 主机端上报数据类型标识
--define(METHOD_AUTH, 16#01).
--define(METHOD_DATA, 16#02).
--define(METHOD_PING, 16#03).
--define(METHOD_INFORM, 16#04).
--define(METHOD_EVENT, 16#05).
--define(METHOD_PHASE, 16#06).
--define(METHOD_REQUEST_SERVICE_CONFIG, 16#07).
-
-%%%% 命令类型子分类, 不需要返回值
-
-%% 授权
--define(COMMAND_AUTH, 16#08).
-
-%%%% 主动推送的消息类型子分类, 需要返回值
-
--define(PUSH_DEPLOY, 16#01).
--define(PUSH_START_SERVICE, 16#02).
--define(PUSH_STOP_SERVICE, 16#03).
-
--define(PUSH_SERVICE_CONFIG, 16#04).
--define(PUSH_INVOKE, 16#05).
--define(PUSH_TASK_LOG, 16#06).

apps/efka/include/efka_tables.hrl

@@ -4,37 +4,21 @@
 %%% @doc
 %%%
 %%% @end
-%%% Created : 30. 4月 2025 11:16
+%%% Created : 29. 9月 2025 15:27
 %%%-------------------------------------------------------------------
 -author("anlicheng").
 
+-define(SERVICE_STOPPED, 0).
+-define(SERVICE_RUNNING, 1).
+
 %% 用来保存微服务
 -record(service, {
     service_id :: binary(),
-    tar_url :: binary(),
-    %% 工作目录
-    root_dir :: string(),
-    %% 配置信息
-    config_json :: binary(),
+    container_name :: binary(),
+    %% 配置信息, 微服务启动的时候自己注册的信息
+    meta_data = #{} :: map(),
     %% 状态： 0: 停止, 1: 运行中
-    status = 0
-}).
-
-%% 数据缓存
--record(cache, {
-    id = 0 :: integer(),
-    method :: integer(),
-    data :: binary()
-}).
-
-%% 数据缓存
--record(task_log, {
-    task_id = 0 :: integer(),
-    logs = []:: list()
-}).
-
-%% id生成器
--record(id_generator, {
-    id,
-    value = 1
+    status = 0,
+    create_ts  = 0 :: integer(),
+    update_ts  = 0 :: integer()
 }).

apps/efka/include/message.hrl

@@ -0,0 +1,86 @@
+%%%-------------------------------------------------------------------
+%%% @author anlicheng
+%%% @copyright (C) 2025, <COMPANY>
+%%% @doc
+%%% 扩展部分, 1: 支持基于topic的pub/sub机制; 2. 基于target的单点通讯和广播
+%%% @end
+%%% Created : 21. 4月 2025 17:28
+%%%-------------------------------------------------------------------
+-author("anlicheng").
+
+%% efka主动发起的消息体类型, 消息大类
+-define(PACKET_REQUEST, 16#01).
+-define(PACKET_RESPONSE, 16#02).
+
+%% efka主动发起不需要返回的数据
+-define(PACKET_CAST, 16#03).
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%% 二级分类定义
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%% 主机端上报数据类型标识
+-define(MESSAGE_AUTH_REQUEST, 16#01).
+-define(MESSAGE_AUTH_REPLY, 16#02).
+
+-define(MESSAGE_COMMAND, 16#03).
+-define(MESSAGE_DEPLOY, 16#04).
+-define(MESSAGE_PUB, 16#05).
+
+-define(MESSAGE_DATA, 16#06).
+-define(MESSAGE_EVENT, 16#07).
+
+%% efka主动上报的event-stream流, 单向消息，主要是: docker-create的实时处理逻辑上报
+-define(MESSAGE_EVENT_STREAM, 16#08).
+
+-define(MESSAGE_JSONRPC_REQUEST, 16#F0).
+-define(MESSAGE_JSONRPC_REPLY, 16#F1).
+
+%%%% 命令类型子分类, 不需要返回值
+%% 授权
+-define(COMMAND_AUTH, 16#08).
+
+-record(auth_request, {
+    uuid :: binary(),
+    username :: binary(),
+    salt :: binary(),
+    token :: binary(),
+    timestamp :: integer()
+}).
+
+-record(auth_reply, {
+    code :: integer(),
+    payload :: binary()
+}).
+
+-record(pub, {
+    topic :: binary(),
+    qos = 0 :: integer(),
+    content :: binary()
+}).
+
+-record(command, {
+    command_type :: integer(),
+    command :: binary()
+}).
+
+-record(jsonrpc_request, {
+    method :: binary(),
+    params = <<>> :: any()
+}).
+
+-record(jsonrpc_reply, {
+    result :: any() | undefined,
+    error :: any() | undefined
+}).
+
+-record(data, {
+    route_key :: binary(),
+    metric :: binary()
+}).
+
+-record(task_event_stream, {
+    task_id :: integer(),
+    type :: binary(),
+    stream :: binary()
+}).

apps/efka/include/message_pb.hrl

@@ -1,128 +0,0 @@
-%% -*- coding: utf-8 -*-
-%% Automatically generated, do not edit
-%% Generated by gpb_compile version 4.21.1
-
--ifndef(message_pb).
--define(message_pb, true).
-
--define(message_pb_gpb_version, "4.21.1").
-
-
--ifndef('AUTH_REQUEST_PB_H').
--define('AUTH_REQUEST_PB_H', true).
--record(auth_request,
-        {uuid = <<>>            :: unicode:chardata() | undefined, % = 1, optional
-         username = <<>>        :: unicode:chardata() | undefined, % = 2, optional
-         salt = <<>>            :: unicode:chardata() | undefined, % = 4, optional
-         token = <<>>           :: unicode:chardata() | undefined, % = 5, optional
-         timestamp = 0          :: non_neg_integer() | undefined % = 6, optional, 32 bits
-        }).
--endif.
-
--ifndef('AUTH_REPLY_PB_H').
--define('AUTH_REPLY_PB_H', true).
--record(auth_reply,
-        {code = 0               :: non_neg_integer() | undefined, % = 1, optional, 32 bits
-         message = <<>>         :: unicode:chardata() | undefined % = 2, optional
-        }).
--endif.
-
--ifndef('PUB_PB_H').
--define('PUB_PB_H', true).
--record(pub,
-        {topic = <<>>           :: unicode:chardata() | undefined, % = 1, optional
-         content = <<>>         :: unicode:chardata() | undefined % = 2, optional
-        }).
--endif.
-
--ifndef('ASYNC_CALL_REPLY_PB_H').
--define('ASYNC_CALL_REPLY_PB_H', true).
--record(async_call_reply,
-        {code = 0               :: non_neg_integer() | undefined, % = 1, optional, 32 bits
-         result = <<>>          :: unicode:chardata() | undefined, % = 2, optional
-         message = <<>>         :: unicode:chardata() | undefined % = 3, optional
-        }).
--endif.
-
--ifndef('DEPLOY_PB_H').
--define('DEPLOY_PB_H', true).
--record(deploy,
-        {task_id = 0            :: non_neg_integer() | undefined, % = 1, optional, 32 bits
-         service_id = <<>>      :: unicode:chardata() | undefined, % = 2, optional
-         tar_url = <<>>         :: unicode:chardata() | undefined % = 3, optional
-        }).
--endif.
-
--ifndef('FETCH_TASK_LOG_PB_H').
--define('FETCH_TASK_LOG_PB_H', true).
--record(fetch_task_log,
-        {task_id = 0            :: non_neg_integer() | undefined % = 1, optional, 32 bits
-        }).
--endif.
-
--ifndef('INVOKE_PB_H').
--define('INVOKE_PB_H', true).
--record(invoke,
-        {service_id = <<>>      :: unicode:chardata() | undefined, % = 1, optional
-         payload = <<>>         :: unicode:chardata() | undefined, % = 2, optional
-         timeout = 0            :: non_neg_integer() | undefined % = 3, optional, 32 bits
-        }).
--endif.
-
--ifndef('PUSH_SERVICE_CONFIG_PB_H').
--define('PUSH_SERVICE_CONFIG_PB_H', true).
--record(push_service_config,
-        {service_id = <<>>      :: unicode:chardata() | undefined, % = 1, optional
-         config_json = <<>>     :: unicode:chardata() | undefined, % = 2, optional
-         timeout = 0            :: non_neg_integer() | undefined % = 3, optional, 32 bits
-        }).
--endif.
-
--ifndef('DATA_PB_H').
--define('DATA_PB_H', true).
--record(data,
-        {service_id = <<>>      :: unicode:chardata() | undefined, % = 1, optional
-         device_uuid = <<>>     :: unicode:chardata() | undefined, % = 2, optional
-         metric = <<>>          :: unicode:chardata() | undefined % = 3, optional
-        }).
--endif.
-
--ifndef('PING_PB_H').
--define('PING_PB_H', true).
--record(ping,
-        {adcode = <<>>          :: unicode:chardata() | undefined, % = 1, optional
-         boot_time = 0          :: non_neg_integer() | undefined, % = 2, optional, 32 bits
-         province = <<>>        :: unicode:chardata() | undefined, % = 3, optional
-         city = <<>>            :: unicode:chardata() | undefined, % = 4, optional
-         efka_version = <<>>    :: unicode:chardata() | undefined, % = 5, optional
-         kernel_arch = <<>>     :: unicode:chardata() | undefined, % = 6, optional
-         ips = []               :: [unicode:chardata()] | undefined, % = 7, repeated
-         cpu_core = 0           :: non_neg_integer() | undefined, % = 8, optional, 32 bits
-         cpu_load = 0           :: non_neg_integer() | undefined, % = 9, optional, 32 bits
-         cpu_temperature = 0.0  :: float() | integer() | infinity | '-infinity' | nan | undefined, % = 10, optional
-         disk = []              :: [integer()] | undefined, % = 11, repeated, 32 bits
-         memory = []            :: [integer()] | undefined, % = 12, repeated, 32 bits
-         interfaces = <<>>      :: unicode:chardata() | undefined % = 13, optional
-        }).
--endif.
-
--ifndef('SERVICE_INFORM_PB_H').
--define('SERVICE_INFORM_PB_H', true).
--record(service_inform,
-        {service_id = <<>>      :: unicode:chardata() | undefined, % = 1, optional
-         props = <<>>           :: unicode:chardata() | undefined, % = 2, optional
-         status = 0             :: non_neg_integer() | undefined, % = 3, optional, 32 bits
-         timestamp = 0          :: non_neg_integer() | undefined % = 4, optional, 32 bits
-        }).
--endif.
-
--ifndef('EVENT_PB_H').
--define('EVENT_PB_H', true).
--record(event,
-        {service_id = <<>>      :: unicode:chardata() | undefined, % = 1, optional
-         event_type = 0         :: non_neg_integer() | undefined, % = 2, optional, 32 bits
-         params = <<>>          :: unicode:chardata() | undefined % = 3, optional
-        }).
--endif.
-
--endif.

apps/efka/src/channel/upload_channel.erl

@@ -0,0 +1,79 @@
+%%%-------------------------------------------------------------------
+%%% @author anlicheng
+%%% @copyright (C) 2025, <COMPANY>
+%%% @doc
+%%%
+%%% @end
+%%% Created : 12. 11月 2025 17:08
+%%%-------------------------------------------------------------------
+-module(upload_channel).
+-author("anlicheng").
+
+%% API
+-export([init/2]).
+
+init(Req0, Opts) ->
+    Method = binary_to_list(cowboy_req:method(Req0)),
+    lager:debug("[upload_channel] method is: ~p", [Method]),
+
+    Headers = cowboy_req:headers(Req0),
+    lager:debug("headers is: ~p", [Headers]),
+    case maps:find(<<"content-type">>, Headers) of
+        {ok, <<"application/octet-stream">>} ->
+            Filename = maps:get(<<"x-filename">>, Headers),
+            case filename:extension(Filename) of
+                <<>> ->
+                    Req = cowboy_req:reply(400, #{
+                        <<"Content-Type">> => <<"text/html;charset=utf-8">>
+                    }, <<"Miss file extension">>, Req0),
+                    {ok, Req, Opts};
+                _ ->
+                    Basename = filename:basename(Filename),
+                    handle_raw_file(Req0, binary_to_list(Basename)),
+                    Req2 = cowboy_req:reply(400, #{
+                        <<"Content-Type">> => <<"text/html;charset=utf-8">>
+                    }, <<"ok">>, Req0),
+                    {ok, Req2, Opts}
+            end;
+        {ok, ContentType} ->
+            lager:debug("[upload_channel] unexpect content-type: ~p", [ContentType]),
+            Req = cowboy_req:reply(400, #{
+                <<"Content-Type">> => <<"text/html;charset=utf-8">>
+            }, <<"Expected application/octet-stream">>, Req0),
+            {ok, Req, Opts};
+        error ->
+            Req = cowboy_req:reply(400, #{
+                <<"Content-Type">> => <<"text/html;charset=utf-8">>
+            }, <<"Miss content-type header">>, Req0),
+            {ok, Req, Opts}
+    end.
+
+%% 读取请求体
+handle_raw_file(Req, Basename) ->
+    Filename = make_file(Basename),
+    {ok, IoDevice} = file:open(Filename, [write]),
+    ok = handle_raw_file0(Req, IoDevice),
+    ok = file:close(IoDevice).
+
+handle_raw_file0(Req, IoDevice) ->
+    case cowboy_req:read_body(Req) of
+        {ok, Data, Req1} ->
+            file:write(IoDevice, Data),
+            ok;
+        {more, Data, Req1} ->
+            file:write(IoDevice, Data),
+            handle_raw_file0(Req1, IoDevice)
+    end.
+
+make_file(Basename) when is_list(Basename) ->
+    {ok, UploadDir} = application:get_env(efka, upload_dir),
+    {{Y, M, D}, _} = calendar:local_time(),
+    DateDir = io_lib:format("~p-~p-~p", [Y, M, D]),
+    BaseDir = UploadDir ++ DateDir,
+    case filelib:is_dir(BaseDir) of
+        true ->
+            ok;
+        false ->
+            ok = file:make_dir(BaseDir)
+    end,
+    BaseDir ++ "/" ++ Basename.

apps/efka/src/channel/ws_channel.erl

@@ -0,0 +1,257 @@
+%%%-------------------------------------------------------------------
+%%% @author licheng5
+%%% @copyright (C) 2021, <COMPANY>
+%%% @doc
+%%%
+%%% @end
+%%% Created : 11. 1月 2021 上午12:17
+%%%-------------------------------------------------------------------
+-module(ws_channel).
+-author("licheng5").
+-include("efka_tables.hrl").
+
+%% API
+-export([init/2]).
+-export([websocket_init/1, websocket_handle/2, websocket_info/2, terminate/3]).
+
+%% 最大的等待时间
+-define(PENDING_TIMEOUT, 10 * 1000).
+
+-record(state, {
+    service_id :: undefined | binary(),
+    service_pid :: undefined | pid(),
+
+    stream_id = 1,
+    %% #{stream_id => {StreamPid, StreamRef}}
+    stream_map = #{},
+
+    is_registered = false :: boolean()
+}).
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%% 逻辑处理方法
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+init(Req, Opts) ->
+    {cowboy_websocket, Req, Opts}.
+
+websocket_init(_State) ->
+    lager:debug("[ws_channel] get a new connection"),
+    %% 初始状态为true
+    {ok, #state{}}.
+
+websocket_handle(ping, State) ->
+    {reply, pong, State};
+
+websocket_handle({text, Data}, State) ->
+    Request = jiffy:decode(Data, [return_maps]),
+    lager:debug("[ws_channle] get request: ~p", [Request]),
+    handle_request(Request, State);
+
+websocket_handle(Info, State) ->
+    lager:error("[ws_channel] get a unknown message: ~p, channel will closed", [Info]),
+    {ok, State}.
+
+%% 订阅的消息
+websocket_info({topic_broadcast, Topic, Content}, State = #state{}) ->
+    Req = iolist_to_binary(jiffy:encode(#{
+        <<"method">> => <<"publish">>,
+        <<"params">> => #{<<"topic">> => Topic, <<"content">> => Content}
+    }, [force_utf8])),
+
+    lager:debug("[ws_channel] will publish topic: ~p, message: ~p", [Topic, Req]),
+
+    {reply, {text, Req}, State};
+
+%% service进程关闭
+websocket_info({'DOWN', _Ref, process, ServicePid, Reason}, State = #state{service_pid = ServicePid}) ->
+    lager:debug("[ws_channel] container_pid: ~p, exited: ~p", [ServicePid, Reason]),
+    {stop, State#state{service_pid = undefined}};
+
+%% stream进程关闭
+websocket_info({'DOWN', _Ref, process, StreamPid, Reason}, State = #state{stream_map = StreamMap}) ->
+    case search_stream_id(StreamPid, StreamMap) of
+        error ->
+            {ok, State};
+        {ok, StreamId} ->
+            case Reason of
+                normal ->
+                    {ok, State#state{stream_map = maps:remove(StreamId, StreamMap)}};
+                _ ->
+                    PushReply = json_push(#{
+                        <<"stream_reply">> => #{
+                            <<"stream_id">> => StreamId,
+                            <<"result">> => <<"task failed">>
+                        }
+                    }),
+                    {reply, {text, PushReply}, State#state{stream_map = maps:remove(StreamId, StreamMap)}}
+            end
+    end;
+
+%% stream任务完成
+websocket_info({stream_reply, StreamPid, Reply}, State = #state{stream_map = StreamMap}) ->
+    case search_stream_id(StreamPid, StreamMap) of
+        error ->
+            {ok, State};
+        {ok, StreamId} ->
+            PushReply = json_push(#{
+                <<"stream_reply">> => #{
+                    <<"stream_id">> => StreamId,
+                    <<"result">> => Reply
+                }
+            }),
+            {reply, {text, PushReply}, State}
+    end;
+
+%% 处理关闭信号
+websocket_info({stop, Reason}, State) ->
+    lager:debug("[ws_channel] the channel will be closed with reason: ~p", [Reason]),
+    {stop, State};
+
+%% 处理其他未知消息
+websocket_info(Info, State) ->
+    lager:debug("[ws_channel] channel get unknown info: ~p", [Info]),
+    {ok, State}.
+
+%% 进程关闭事件
+terminate(Reason, _Req, State = #state{service_id = ServiceId, is_registered = IsRegistered}) ->
+    case IsRegistered of
+        true ->
+            ok = service_model:change_status(ServiceId, 0);
+        false ->
+            ok
+    end,
+    lager:debug("[ws_channel] channel close with reason: ~p, state is: ~p", [Reason, State]),
+    ok.
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%% helper methods
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%% 注册, 要建立程序和容器之间的关系
+handle_request(#{<<"id">> := Id, <<"method">> := <<"register">>, <<"params">> := Params = #{<<"service_id">> := ServiceId}}, State) ->
+    {ok, ServicePid} = efka_service_sup:start_service(ServiceId),
+    case efka_service:attach_channel(ServicePid, self()) of
+        ok ->
+            Reply = json_result(Id, <<"ok">>),
+            erlang:monitor(process, ServicePid),
+
+            %% 更新微服务的状态
+            MetaData = maps:get(<<"meta_data">>, Params, #{}),
+            ContainerName = maps:get(<<"container_name">>, Params, <<>>),
+            ok = service_model:insert(#service{
+                service_id = ServiceId,
+                container_name = ContainerName,
+                status = ?SERVICE_RUNNING,
+                meta_data = MetaData,
+                create_ts = efka_util:timestamp(),
+                update_ts = efka_util:timestamp()
+            }),
+
+            {reply, {text, Reply}, State#state{service_id = ServiceId, service_pid = ServicePid, is_registered = true}};
+        {error, Error} ->
+            lager:warning("[ws_channel] service_id: ~p, attach_channel get error: ~p", [ServiceId, Error]),
+            {stop, State}
+    end;
+
+%% 订阅事件
+handle_request(#{<<"id">> := Id, <<"method">> := <<"subscribe">>, <<"params">> := #{<<"topic">> := Topic}}, State = #state{is_registered = true}) ->
+    Reply = case efka_subscription:subscribe(Topic, self()) of
+                ok ->
+                    json_result(Id, <<"ok">>);
+                {error, Reason} ->
+                    json_error(Id, -1, Reason)
+            end,
+    {reply, {text, Reply}, State};
+
+%% 文件上传
+handle_request(#{<<"id">> := Id, <<"method">> := <<"new_stream">>,
+    <<"params">> := #{<<"file_name">> := Filename0, <<"file_size">> := FileSize}}, State = #state{stream_id = StreamId, stream_map = StreamMap, is_registered = true}) ->
+    Filename = filename:basename(binary_to_list(Filename0)),
+
+    {ok, {StreamPid, StreamRef}} = efka_stream:start_monitor(self()),
+    {ok, Path} = efka_stream:setup(StreamPid, Filename, FileSize),
+
+    Reply = json_result(Id, #{
+        <<"stream_id">> => StreamId,
+        <<"path">> => Path
+    }),
+    {reply, {text, Reply}, State#state{stream_id = StreamId + 1, stream_map = maps:put(StreamId, {StreamPid, StreamRef}, StreamMap)}};
+
+handle_request(#{<<"method">> := <<"stream_chunk">>,
+    <<"params">> := #{<<"stream_id">> := StreamId, <<"chunk_data">> := ChunkData}}, State = #state{stream_map = StreamMap, is_registered = true}) ->
+    case maps:find(StreamId, StreamMap) of
+        error ->
+            {ok, State};
+        {ok, {StreamPid, _}} ->
+            case ChunkData =:= <<>> of
+                true ->
+                    efka_stream:finish(StreamPid);
+                false ->
+                    efka_stream:data(StreamPid, ChunkData)
+            end,
+            {ok, State}
+    end;
+
+%% 数据项
+handle_request(#{<<"method">> := <<"metric_data">>,
+    <<"params">> := #{<<"route_key">> := RouteKey, <<"metric">> := Metric0}}, State = #state{service_pid = ServicePid, is_registered = true}) ->
+    case map_metric(Metric0) of
+        {ok, Metric} ->
+            efka_service:metric_data(ServicePid, RouteKey, Metric);
+        error ->
+            lager:debug("[ws_channel] metric_data get invalid metric: ~p", Metric0)
+    end,
+    {ok, State}.
+
+-spec json_result(Id :: integer(), Result :: term()) -> binary().
+json_result(Id, Result) when is_integer(Id) ->
+    Response = #{
+        <<"id">> => Id,
+        <<"result">> => Result
+    },
+    jiffy:encode(Response, [force_utf8]).
+
+-spec json_error(Id :: integer(), Code :: integer(), Message :: binary()) -> binary().
+json_error(Id, Code, Message) when is_integer(Id), is_integer(Code), is_binary(Message) ->
+    Response = #{
+        <<"id">> => Id,
+        <<"error">> => #{<<"code">> => Code, <<"message">> => Message}
+    },
+    jiffy:encode(Response, [force_utf8]).
+
+-spec json_push(Result :: term()) -> binary().
+json_push(Result) ->
+    Response = #{
+        <<"push">> => Result
+    },
+    jiffy:encode(Response, [force_utf8]).
+
+-spec search_stream_id(StreamPid :: pid(), StreamMap :: map()) -> error | {ok, StreamId :: integer()}.
+search_stream_id(StreamPid, StreamMap) when is_pid(StreamPid), is_map(StreamMap) ->
+    StreamIds = lists:filtermap(fun({StreamId, {StreamPid0, _}}) ->
+        case StreamPid0 =:= StreamPid of
+            true ->
+                {true, StreamId};
+            false ->
+                false
+        end
+                                end, maps:to_list(StreamMap)),
+    case StreamIds of
+        [] ->
+            error;
+        [StreamId|_] ->
+            {ok, StreamId}
+    end.
+
+-spec map_metric(Metric :: any()) -> {ok, binary()} | error.
+map_metric(Metric) when is_binary(Metric) ->
+    {ok, Metric};
+map_metric(Metric) when is_map(Metric) orelse is_list(Metric) ->
+    {ok, jiffy:encode(Metric, [force_utf8])};
+map_metric(Metric) when is_integer(Metric) ->
+    {ok, integer_to_binary(Metric)};
+map_metric(Metric) when is_float(Metric) ->
+    {ok, erlang:float_to_binary(Metric, [compact, {decimals, 10}])};
+map_metric(_) ->
+    error.

apps/efka/src/docker/docker_commands.erl

@@ -0,0 +1,466 @@
+%%%-------------------------------------------------------------------
+%%% @author anlicheng
+%%% @copyright (C) 2025, <COMPANY>
+%%% @doc
+%%%
+%%% @end
+%%% Created : 15. 9月 2025 16:11
+%%%-------------------------------------------------------------------
+-module(docker_commands).
+-author("anlicheng").
+
+%% API
+-export([pull_image/2, check_image_exist/1]).
+-export([create_container/3, check_container_exist/1, is_container_running/1,
+    start_container/1, stop_container/1, remove_container/1, kill_container/1,
+    get_containers/0]).
+
+-spec pull_image(Image :: binary(), Callback :: fun((Msg :: any()) -> no_return())) -> ok | {error, Reason :: any()}.
+pull_image(Image, Callback) when is_binary(Image), is_function(Callback, 1) ->
+    Url = lists:flatten(io_lib:format("/images/create?fromImage=~s", [binary_to_list(Image)])),
+    docker_http:stream_request(Callback, "POST", Url, <<>>, []).
+
+-spec check_image_exist(Image :: binary()) -> boolean().
+check_image_exist(Image) when is_binary(Image) ->
+    Url = lists:flatten(io_lib:format("/images/~s/json", [binary_to_list(Image)])),
+    case docker_http:request("GET", Url, <<"">>, []) of
+        {ok, 200, _Headers, Resp} ->
+            M = catch jiffy:decode(Resp, [return_maps]),
+            is_map(M) andalso maps:is_key(<<"Id">>, M);
+        _ ->
+            false
+    end.
+
+-spec create_container(ContainerName :: binary(), ContainerDir :: string(), Config :: map()) -> {ok, ContainerId :: binary()} | {error, Reason :: any()}.
+create_container(ContainerName, ContainerDir, Config) when is_binary(ContainerName), is_list(ContainerDir), is_map(Config) ->
+    Url = lists:flatten(io_lib:format("/containers/create?name=~s", [binary_to_list(ContainerName)])),
+    %% 挂载预留的目录，用来作为配置文件的存放
+    ConfigFile = list_to_binary(docker_helper:get_config_file(ContainerDir)),
+
+    %% 增加自定义的用来放配置文件的目录
+    Volumes0 = maps:get(<<"volumes">>, Config, []),
+    Volumes = [<<ConfigFile/binary, ":/usr/local/etc/service.conf">>|Volumes0],
+    NewConfig = Config#{<<"volumes">> => Volumes},
+
+    Options = build_options(ContainerName, NewConfig),
+    display_options(Options),
+
+    Body = iolist_to_binary(jiffy:encode(Options, [force_utf8])),
+    true = is_binary(Body),
+
+    Headers = [
+        {<<"Content-Type">>, <<"application/json">>}
+    ],
+    case docker_http:request("POST", Url, Body, Headers) of
+        {ok, 201, _Headers, Resp} ->
+            case catch jiffy:decode(Resp, [return_maps]) of
+                #{<<"Id">> := ContainerId} when is_binary(ContainerId) ->
+                    {ok, ContainerId};
+                _ ->
+                    {error, Resp}
+            end;
+        {ok, _StatusCode, _, ErrorResp} ->
+            case catch jiffy:decode(ErrorResp, [return_maps]) of
+                #{<<"message">> := Msg} ->
+                    {error, Msg};
+                _ ->
+                    {error, ErrorResp}
+            end;
+        {error, Reason} ->
+            {error, Reason}
+    end.
+
+-spec is_container_running(ContainerId :: binary()) -> boolean().
+is_container_running(ContainerId) when is_binary(ContainerId) ->
+    case inspect_container(ContainerId) of
+        {ok, #{<<"State">> := #{<<"Running">> := Running}}} ->
+            Running;
+        {error, _} ->
+            false
+    end.
+
+-spec check_container_exist(ContainerName :: binary()) -> boolean().
+check_container_exist(ContainerName) when is_binary(ContainerName) ->
+    case inspect_container(ContainerName) of
+        {ok, #{<<"Id">> := Id}} when is_binary(Id) ->
+            true;
+        _ ->
+            false
+    end.
+
+-spec start_container(ContainerName :: binary()) -> ok | {error, Reason :: binary()}.
+start_container(ContainerName) when is_binary(ContainerName) ->
+    Url = lists:flatten(io_lib:format("/containers/~s/start", [binary_to_list(ContainerName)])),
+    Headers = [
+        {<<"Content-Type">>, <<"application/json">>}
+    ],
+    case docker_http:request("POST", Url, <<>>, Headers) of
+        {ok, 204, _Headers, _} ->
+            ok;
+        {ok, 304, _Headers, _} ->
+            {error, <<"container already started">>};
+        {ok, _StatusCode, _Header, ErrorResp} ->
+            case catch jiffy:decode(ErrorResp) of
+                #{<<"message">> := Msg} ->
+                    {error, Msg};
+                _ ->
+                    {error, ErrorResp}
+            end;
+        {error, Reason} ->
+            {error, Reason}
+    end.
+
+-spec stop_container(ContainerName :: binary()) -> ok | {error, Reason :: binary()}.
+stop_container(ContainerName) when is_binary(ContainerName) ->
+    Url = lists:flatten(io_lib:format("/containers/~s/stop", [binary_to_list(ContainerName)])),
+    Headers = [
+        {<<"Content-Type">>, <<"application/json">>}
+    ],
+    case docker_http:request("POST", Url, <<>>, Headers) of
+        {ok, 204, _Headers, _} ->
+            ok;
+        {ok, 304, _Headers, _} ->
+            {error, <<"container already stopped">>};
+        {ok, _StatusCode, _Header, ErrorResp} ->
+            case catch jiffy:decode(ErrorResp) of
+                #{<<"message">> := Msg} ->
+                    {error, Msg};
+                _ ->
+                    {error, ErrorResp}
+            end;
+        {error, Reason} ->
+            {error, Reason}
+    end.
+
+-spec kill_container(ContainerName :: binary()) -> ok | {error, Reason :: binary()}.
+kill_container(ContainerName) when is_binary(ContainerName) ->
+    Url = lists:flatten(io_lib:format("/containers/~s/kill", [binary_to_list(ContainerName)])),
+    Headers = [
+        {<<"Content-Type">>, <<"application/json">>}
+    ],
+    case docker_http:request("POST", Url, <<>>, Headers) of
+        {ok, 204, _Headers, _} ->
+            ok;
+        {ok, _StatusCode, _Header, ErrorResp} ->
+            case catch jiffy:decode(ErrorResp) of
+                #{<<"message">> := Msg} ->
+                    {error, Msg};
+                _ ->
+                    {error, ErrorResp}
+            end;
+        {error, Reason} ->
+            {error, Reason}
+    end.
+
+-spec remove_container(ContainerName :: binary()) -> ok | {error, Reason :: binary()}.
+remove_container(ContainerName) when is_binary(ContainerName) ->
+    Url = lists:flatten(io_lib:format("/containers/~s", [binary_to_list(ContainerName)])),
+    Headers = [
+        {<<"Content-Type">>, <<"application/json">>}
+    ],
+    case docker_http:request("DELETE", Url, <<>>, Headers) of
+        {ok, 204, _Headers, _} ->
+            ok;
+        {ok, 304, _Headers, _} ->
+            {error, <<"container already stopped">>};
+        {ok, _StatusCode, _Header, ErrorResp} ->
+            case catch jiffy:decode(ErrorResp) of
+                #{<<"message">> := Msg} ->
+                    {error, Msg};
+                _ ->
+                    {error, ErrorResp}
+            end;
+        {error, Reason} ->
+            {error, Reason}
+    end.
+
+-spec get_containers() -> {ok, Containers :: [map()]} | {error, Reason :: binary()}.
+get_containers() ->
+    Url = "/containers/json?all=true",
+    Headers = [
+        {<<"Content-Type">>, <<"application/json">>}
+    ],
+    case docker_http:request("GET", Url, <<>>, Headers) of
+        {ok, 200, _Headers, ContainersBin} ->
+            Containers = jiffy:decode(ContainersBin, [return_maps]),
+            {ok, Containers};
+        {ok, _StatusCode, _Header, ErrorResp} ->
+            case catch jiffy:decode(ErrorResp) of
+                #{<<"message">> := Msg} ->
+                    {error, Msg};
+                _ ->
+                    {error, ErrorResp}
+            end;
+        {error, Reason} ->
+            {error, Reason}
+    end.
+
+-spec inspect_container(ContainerId :: binary()) -> {ok, Json :: map()} | {error, Error :: any()}.
+inspect_container(ContainerId) when is_binary(ContainerId) ->
+    Url = lists:flatten(io_lib:format("/containers/~s/json", [binary_to_list(ContainerId)])),
+    Headers = [
+        {<<"Content-Type">>, <<"application/json">>}
+    ],
+    case docker_http:request("GET", Url, <<>>, Headers) of
+        {ok, 200, _Headers, Resp} ->
+            Json = jiffy:decode(Resp, [return_maps]),
+            {ok, Json};
+        {ok, _StatusCode, _Header, ErrorResp} ->
+            case catch jiffy:decode(ErrorResp) of
+                #{<<"message">> := Msg} ->
+                    {error, Msg};
+                _ ->
+                    {error, ErrorResp}
+            end;
+        {error, Reason} ->
+            {error, Reason}
+    end.
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%% helper methods
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%% 构建最终 JSON Map
+build_options(ContainerName, Config) when is_binary(ContainerName), is_map(Config) ->
+    %% 容器名称作为环境变量，注入到运行时环境中
+    Envs0 = maps:get(<<"envs">>, Config, []),
+    Envs = [<<"CONTAINER_NAME=", ContainerName/binary>>|Envs0],
+    #{
+        <<"Image">> => maps:get(<<"image">>, Config, <<>>),
+        <<"Cmd">> => maps:get(<<"command">>, Config, []),
+        <<"Entrypoint">> => maps:get(<<"entrypoint">>, Config, []),
+        <<"Env">> => Envs,
+        <<"Labels">> => maps:get(<<"labels">>, Config, #{}),
+        <<"Volumes">> => build_volumes(Config),
+        <<"User">> => maps:get(<<"user">>, Config, <<>>),
+        <<"WorkingDir">> => maps:get(<<"working_dir">>, Config, <<>>),
+        <<"Hostname">> => maps:get(<<"hostname">>, Config, <<>>),
+        <<"ExposedPorts">> => build_expose(Config),
+        <<"NetworkingConfig">> => build_networks(Config),
+        <<"Healthcheck">> => build_healthcheck(Config),
+        <<"HostConfig">> => fold_merge([
+            build_network_mode(Config),
+            build_binds(Config),
+            build_restart(Config),
+            build_privileged(Config),
+            build_cap_add_drop(Config),
+            build_devices(Config),
+            build_memory(Config),
+            build_cpu(Config),
+            build_ulimits(Config),
+            build_tmpfs(Config),
+            build_sysctls(Config),
+            build_extra_hosts(Config)
+        ])
+    }.
+
+%% 工具函数
+fold_merge(List) ->
+    lists:foldl(fun maps:merge/2, #{}, List).
+
+%% --- 构建子字段 ---
+build_expose(Config) ->
+    Ports = maps:get(<<"expose">>, Config, []),
+    case Ports of
+        [] -> #{};
+        _ ->
+            maps:from_list([{<<P/binary, "/tcp">>, #{}} || P <- Ports])
+    end.
+
+build_volumes(Config) ->
+    Vols = maps:get(<<"volumes">>, Config, []),
+    case Vols of
+        [] ->
+            #{};
+        _ ->
+            maps:from_list(lists:map(fun(V) ->
+                [_Host, Cont] = binary:split(V, <<":">>, []),
+                {Cont, #{}}
+                                     end, Vols))
+    end.
+
+build_binds(Config) ->
+    Vols = maps:get(<<"volumes">>, Config, []),
+    case Vols of
+        [] ->
+            #{};
+        _ ->
+            #{<<"Binds">> => Vols}
+    end.
+
+build_networks(Config) ->
+    Nets = maps:get(<<"networks">>, Config, []),
+    case Nets of
+        [] -> #{};
+        _ ->
+            NetCfg = maps:from_list([{N, #{}} || N <- Nets]),
+            #{<<"EndpointsConfig">> => NetCfg}
+    end.
+
+build_network_mode(Config) ->
+    NetworkMode = maps:get(<<"network_mode">>, Config, <<"bridge">>),
+    #{<<"NetworkMode">> => NetworkMode}.
+
+parse_mem(Val) ->
+    case binary:last(Val) of
+        $m ->
+            N = binary:part(Val, {0, byte_size(Val)-1}),
+            list_to_integer(binary_to_list(N)) * 1024 * 1024;
+        $g ->
+            N = binary:part(Val, {0, byte_size(Val)-1}),
+            list_to_integer(binary_to_list(N)) * 1024 * 1024 * 1024;
+        _ ->
+            list_to_integer(binary_to_list(Val))
+    end.
+
+build_healthcheck(Config) ->
+    HC = maps:get(<<"healthcheck">>, Config, #{}),
+    case maps:size(HC) of
+        0 ->
+            #{};
+        _ ->
+            #{
+                <<"Test">> => maps:get(<<"test">>, HC, []),
+                <<"Interval">> => parse_duration(maps:get(<<"interval">>, HC, <<"0s">>)),
+                <<"Timeout">> => parse_duration(maps:get(<<"timeout">>, HC, <<"0s">>)),
+                <<"Retries">> => maps:get(<<"retries">>, HC, 0)
+            }
+    end.
+
+parse_duration(Bin) ->
+    %% "30s" -> 30000000000
+    Sz = byte_size(Bin),
+    NBin = binary:part(Bin, {0, Sz-1}),
+    N = list_to_integer(binary_to_list(NBin)),
+    case binary:last(Bin) of
+        $s ->
+            N * 1000000000;
+        $m ->
+            N * 60000000000;
+        _ ->
+            N
+    end.
+
+%% --- 构建子字段 ---
+
+build_restart(Config) ->
+    case maps:get(<<"restart">>, Config, undefined) of
+        undefined ->
+            #{};
+        Policy ->
+            #{<<"RestartPolicy">> => #{<<"Name">> => Policy}}
+    end.
+
+build_privileged(Config) ->
+    case maps:get(<<"privileged">>, Config, false) of
+        true ->
+            #{<<"Privileged">> => true};
+        _ ->
+            #{}
+    end.
+
+build_cap_add_drop(Config) ->
+    Add = maps:get(<<"cap_add">>, Config, []),
+    Drop = maps:get(<<"cap_drop">>, Config, []),
+    case {Add, Drop} of
+        {[], []} ->
+            #{};
+        _ ->
+            #{<<"CapAdd">> => Add, <<"CapDrop">> => Drop}
+    end.
+
+build_devices(Config) ->
+    Devs = maps:get(<<"devices">>, Config, []),
+    case Devs of
+        [] ->
+            #{};
+        _ ->
+            DevObjs = [#{<<"PathOnHost">> => H, <<"PathInContainer">> => C,
+                <<"CgroupPermissions">> => <<"rwm">>}
+                || D <- Devs,
+                [H, C] <- [binary:split(D, <<":">>, [])]],
+            #{<<"Devices">> => DevObjs}
+    end.
+
+build_memory(Config) ->
+    Mem = maps:get(<<"mem_limit">>, Config, undefined),
+    MemRes = maps:get(<<"mem_reservation">>, Config, undefined),
+    HCfg = #{},
+    HCfg1 = if
+                Mem /= undefined ->
+                    maps:put(<<"Memory">>, parse_mem(Mem), HCfg);
+                true ->
+                    HCfg
+            end,
+    if
+        MemRes /= undefined ->
+            maps:put(<<"MemoryReservation">>, parse_mem(MemRes), HCfg1);
+        true ->
+            HCfg1
+    end.
+
+
+build_cpu(Config) ->
+    CPU = maps:get(<<"cpus">>, Config, undefined),
+    Shares = maps:get(<<"cpu_shares">>, Config, undefined),
+    HCfg = #{},
+    HCfg1 = if
+                CPU /= undefined ->
+                    maps:put(<<"NanoCpus">>, trunc(CPU * 1000000000), HCfg);
+                true ->
+                    HCfg
+            end,
+    if
+        Shares /= undefined ->
+            maps:put(<<"CpuShares">>, Shares, HCfg1);
+        true ->
+            HCfg1
+    end.
+
+build_ulimits(Config) ->
+    UL = maps:get(<<"ulimits">>, Config, #{}),
+    case maps:size(UL) of
+        0 ->
+            #{};
+        _ ->
+            ULList = lists:map(fun({K, V}) ->
+                [S1, H1] = binary:split(V, <<":">>, []),
+                S = list_to_integer(binary_to_list(S1)),
+                H = list_to_integer(binary_to_list(H1)),
+                #{<<"Name">> => K, <<"Soft">> => S, <<"Hard">> => H}
+                               end, maps:to_list(UL)),
+
+            #{<<"Ulimits">> => ULList}
+    end.
+
+build_sysctls(Config) ->
+    SC = maps:get(<<"sysctls">>, Config, #{}),
+    case maps:size(SC) of
+        0 ->
+            #{};
+        _ ->
+            #{<<"Sysctls">> => SC}
+    end.
+
+build_tmpfs(Config) ->
+    Tmp = maps:get(<<"tmpfs">>, Config, []),
+    case Tmp of
+        [] ->
+            #{};
+        _ ->
+            #{<<"Tmpfs">> => maps:from_list([{T, <<>>} || T <- Tmp])}
+    end.
+
+build_extra_hosts(Config) ->
+    Hosts = maps:get(<<"extra_hosts">>, Config, []),
+    case Hosts of
+        [] ->
+            #{};
+        _ ->
+            #{<<"ExtraHosts">> => Hosts}
+    end.
+
+-spec display_options(Options :: map()) -> no_return().
+display_options(Options) when is_map(Options) ->
+    lager:debug("deploy options: ~p", [jiffy:encode(Options, [force_utf8])]),
+    lists:foreach(fun({K, V}) -> lager:debug("~p => ~p", [K, V]) end, maps:to_list(Options)).

apps/efka/src/docker/docker_deployer.erl

@@ -0,0 +1,117 @@
+%%%-------------------------------------------------------------------
+%%% @author anlicheng
+%%% @copyright (C) 2025, <COMPANY>
+%%% @doc
+%%%
+%%% @end
+%%% Created : 07. 5月 2025 15:47
+%%%-------------------------------------------------------------------
+-module(docker_deployer).
+-author("anlicheng").
+-dialyzer([{nowarn_function, normalize_image/1}]).
+
+%% API
+-export([start_monitor/3]).
+-export([deploy/3]).
+
+-define(TASK_SUCCESS, <<"success">>).
+-define(TASK_FAIL, <<"fail">>).
+
+%%%===================================================================
+%%% API
+%%%===================================================================
+
+%% @doc Spawns the server and registers the local name (unique)
+-spec(start_monitor(TaskId :: integer(), ContainerDir :: string(), Config :: map()) -> {ok, {Pid :: pid(), MRef :: reference()}}).
+start_monitor(TaskId, ContainerDir, Config) when is_integer(TaskId), is_list(ContainerDir), is_map(Config) ->
+    {ok, spawn_monitor(?MODULE, deploy, [TaskId, ContainerDir, Config])}.
+
+%%%===================================================================
+%%% Internal functions
+%%%===================================================================
+
+%{
+%   "image": "nginx:latest",
+%   "container_name": "my_nginx",
+%   "ports": ["8080:80", "443:443"],
+%   "volumes": ["/host/data:/data", "/host/log:/var/log"],
+%   "envs": ["ENV1=val1", "ENV2=val2"],
+%   "entrypoint": ["/docker-entrypoint.sh"],
+%   "command": ["nginx", "-g", "daemon off;"],
+%   "restart": "always"
+%}
+-spec deploy(TaskId :: integer(), ContainerDir :: string(), Config :: map()) -> no_return().
+deploy(TaskId, ContainerDir, Config) when is_integer(TaskId), is_list(ContainerDir), is_map(Config) ->
+    %% 尝试拉取镜像
+    ContainerName = maps:get(<<"container_name">>, Config),
+    trace_log(TaskId, <<"info">>, <<"开始部署容器:"/utf8, ContainerName/binary>>),
+
+    case docker_commands:check_container_exist(ContainerName) of
+        true ->
+            trace_log(TaskId, <<"info">>, <<"本地容器已经存在:"/utf8, ContainerName/binary>>),
+            efka_remote_agent:close_task_event_stream(TaskId, ?TASK_FAIL);
+        false ->
+            Image0 = maps:get(<<"image">>, Config),
+            Image = normalize_image(Image0),
+
+            trace_log(TaskId, <<"info">>, <<"使用镜像:"/utf8, Image/binary>>),
+            PullResult = case docker_commands:check_image_exist(Image) of
+                             true ->
+                                 trace_log(TaskId, <<"info">>, <<"镜像本地已存在:"/utf8, Image/binary>>),
+                                 ok;
+                             false ->
+                                 trace_log(TaskId, <<"info">>, <<"开始拉取镜像:"/utf8, Image/binary>>),
+                                 CB = fun
+                                          ({message, M}) ->
+                                              trace_log(TaskId, <<"info">>, M);
+                                          ({error, Error}) ->
+                                              trace_log(TaskId, <<"error">>, Error)
+                                      end,
+                                 docker_commands:pull_image(Image, CB)
+                         end,
+
+            case PullResult of
+                ok ->
+                    trace_log(TaskId, <<"info">>, <<"开始创建容器: "/utf8, ContainerName/binary>>),
+                    case docker_commands:create_container(ContainerName, ContainerDir, Config) of
+                        {ok, ContainerId} ->
+                            %% 创建容器对应的配置文件
+                            ConfigFile = docker_helper:get_config_file(ContainerDir),
+                            case file:open(ConfigFile, [write, exclusive]) of
+                                {ok, FD} ->
+                                    ok = file:write(FD, <<>>),
+                                    file:close(FD);
+                                {error, Reason} ->
+                                    Reason1 = list_to_binary(io_lib:format("~p", [Reason])),
+                                    trace_log(TaskId, <<"notice">>, <<"创建配置文件失败: "/utf8, Reason1/binary>>)
+                            end,
+                            ShortContainerId = binary:part(ContainerId, 1, 12),
+                            trace_log(TaskId, <<"info">>, <<"容器创建成功: "/utf8, ShortContainerId/binary>>),
+                            trace_log(TaskId, <<"info">>, <<"任务完成"/utf8>>),
+                            efka_remote_agent:close_task_event_stream(TaskId, ?TASK_SUCCESS);
+                        {error, Reason} ->
+                            trace_log(TaskId, <<"error">>, <<"容器创建失败: "/utf8, Reason/binary>>),
+                            trace_log(TaskId, <<"error">>, <<"任务失败"/utf8>>),
+                            efka_remote_agent:close_task_event_stream(TaskId, ?TASK_FAIL)
+                    end;
+                {error, Reason} ->
+                    trace_log(TaskId, <<"error">>, <<"镜像拉取失败: "/utf8, Reason/binary>>),
+                    efka_remote_agent:close_task_event_stream(TaskId, ?TASK_FAIL)
+            end
+    end.
+
+-spec normalize_image(binary()) -> binary().
+normalize_image(Image) when is_binary(Image) ->
+    Parts = binary:split(Image, <<"/">>, [global]),
+    {PrefixParts, [Last]} = lists:split(length(Parts) - 1, Parts),
+    NormalizedLast = case binary:split(Last, <<":">>, [global]) of
+                         [_Name] -> <<Last/binary, ":latest">>;
+                         [_Name, _Tag] -> Last
+                     end,
+    iolist_to_binary(lists:join(<<"/">>, PrefixParts ++ [NormalizedLast])).
+
+-spec trace_log(TaskId :: integer(), Level :: binary(), Msg :: binary()) -> no_return().
+trace_log(TaskId, Level, Msg) when is_integer(TaskId), is_binary(Level), is_binary(Msg) ->
+    efka_remote_agent:task_event_stream(TaskId, Level, Msg),
+    Info = iolist_to_binary([<<"task_id=">>, integer_to_binary(TaskId), <<" ">>, Level, <<" ">>, Msg]),
+    efka_logger:write(Info).

apps/efka/src/docker/docker_events.erl

@@ -4,16 +4,16 @@
 %%% @doc
 %%%
 %%% @end
-%%% Created : 09. 5月 2025 16:45
+%%% Created : 16. 9月 2025 16:48
 %%%-------------------------------------------------------------------
--module(efka_inetd_task_log).
+-module(docker_events).
 -author("anlicheng").
 
 -behaviour(gen_server).
 
 %% API
 -export([start_link/0]).
--export([stash/2, flush/1, get_logs/1]).
+-export([monitor_container/2]).
 
 %% gen_server callbacks
 -export([init/1, handle_call/3, handle_cast/2, handle_info/2, terminate/2, code_change/3]).
@@ -21,30 +21,18 @@
 -define(SERVER, ?MODULE).
 
 -record(state, {
-    %% #{task_id => queue:new()}
-    pending_map = #{}
+    port,
+    %% 观察者
+    monitors = #{}
 }).
 
 %%%===================================================================
 %%% API
 %%%===================================================================
 
--spec stash(TaskId :: integer(), Items :: binary() | [binary()]) -> no_return().
-stash(TaskId, Log) when is_integer(TaskId), is_binary(Log) ->
-    stash(TaskId, [Log]);
-stash(TaskId, Items) when is_integer(TaskId), is_list(Items) ->
-    {{Y, M, D}, {H, I, S}} = calendar:local_time(),
-    TimePrefix = iolist_to_binary(io_lib:format("[~b-~2..0b-~2..0b ~2..0b:~2..0b:~2..0b]", [Y, M, D, H, I, S])),
-    Log = iolist_to_binary([TimePrefix, <<" ">>, lists:join(<<" ">>, Items)]),
-    gen_server:cast(?SERVER, {stash, TaskId, Log}).
-
--spec flush(TaskId :: integer()) -> no_return().
-flush(TaskId) when is_integer(TaskId) ->
-    gen_server:cast(?SERVER, {flush, TaskId}).
-
--spec get_logs(TaskId :: integer()) -> {ok, Logs :: list()}.
-get_logs(TaskId) when is_integer(TaskId) ->
-    gen_server:call(?SERVER, {get_logs, TaskId}).
+-spec monitor_container(ReceiverPid :: pid(), ContainerId :: binary()) -> no_return().
+monitor_container(ReceiverPid, ContainerId) when is_pid(ReceiverPid), is_binary(ContainerId) ->
+    gen_server:cast(?SERVER, {monitor_container, ReceiverPid, ContainerId}).
 
 %% @doc Spawns the server and registers the local name (unique)
 -spec(start_link() ->
@@ -62,6 +50,8 @@ start_link() ->
     {ok, State :: #state{}} | {ok, State :: #state{}, timeout() | hibernate} |
     {stop, Reason :: term()} | ignore).
 init([]) ->
+    process_flag(trap_exit, true),
+    try_attach_events(0),
     {ok, #state{}}.
 
 %% @private
@@ -74,15 +64,8 @@ init([]) ->
     {noreply, NewState :: #state{}, timeout() | hibernate} |
     {stop, Reason :: term(), Reply :: term(), NewState :: #state{}} |
     {stop, Reason :: term(), NewState :: #state{}}).
-handle_call({get_logs, TaskId}, _From, State = #state{pending_map = PendingMap}) ->
-    case maps:find(TaskId, PendingMap) of
-        error ->
-            Logs = task_log_model:get_logs(TaskId),
-            {reply, {ok, Logs}, State};
-        {ok, Q} ->
-            Logs = queue:to_list(Q),
-            {reply, {ok, Logs}, State}
-    end.
+handle_call(_Request, _From, State = #state{}) ->
+    {reply, ok, State}.
 
 %% @private
 %% @doc Handling cast messages
@@ -90,19 +73,9 @@ handle_call({get_logs, TaskId}, _From, State = #state{pending_map = PendingMap})
     {noreply, NewState :: #state{}} |
     {noreply, NewState :: #state{}, timeout() | hibernate} |
     {stop, Reason :: term(), NewState :: #state{}}).
-handle_cast({stash, TaskId, Log}, State = #state{pending_map = PendingMap}) ->
-    Q = maps:get(TaskId, PendingMap, queue:new()),
-    NQ = queue:in(Log, Q),
-    {noreply, State#state{pending_map = maps:put(TaskId, NQ, PendingMap)}};
-handle_cast({flush, TaskId}, State = #state{pending_map = PendingMap}) ->
-    case maps:take(TaskId, PendingMap) of
-        error ->
-            {noreply, State};
-        {Q, NPendingMap} ->
-            Logs = queue:to_list(Q),
-            ok = task_log_model:insert(TaskId, Logs),
-            {noreply, State#state{pending_map = NPendingMap}}
-    end.
+handle_cast({monitor_container, ReceiverPid, ContainerId}, State = #state{monitors = Monitors}) ->
+    MRef = erlang:monitor(process, ReceiverPid),
+    {noreply, State#state{monitors = maps:put(ContainerId, {ReceiverPid, MRef}, Monitors)}}.
 
 %% @private
 %% @doc Handling all non call/cast messages
@@ -110,8 +83,31 @@ handle_cast({flush, TaskId}, State = #state{pending_map = PendingMap}) ->
     {noreply, NewState :: #state{}} |
     {noreply, NewState :: #state{}, timeout() | hibernate} |
     {stop, Reason :: term(), NewState :: #state{}}).
-handle_info(_Info, State = #state{}) ->
-    {noreply, State}.
+handle_info({timeout, _, attach_docker_events}, State = #state{port = undefined}) ->
+    ExecCmd = "docker events --format \"{{json .}}\"",
+    case catch erlang:open_port({spawn, ExecCmd}, [exit_status, {line, 10239}, use_stdio, stderr_to_stdout, binary]) of
+        Port when is_port(Port) ->
+            {noreply, State#state{port = Port}};
+        _Error ->
+            try_attach_events(5000),
+            {noreply, State}
+    end;
+handle_info({Port, {data, {eol, BinLine}}}, State = #state{port = Port}) ->
+    Event = catch jiffy:decode(BinLine, [return_maps]),
+    lager:debug("event: ~p", [Event]),
+    handle_event(Event, State),
+    {noreply, State};
+
+%% 进程退出的时候删除掉管理的Pid
+handle_info({'DOWN', MRef, process, _Pid, _Reason}, State = #state{monitors = Monitors}) ->
+    NMonitors = maps:filter(fun(_Key, {_, Ref}) -> MRef =/= Ref end, Monitors),
+    {noreply, State#state{monitors = NMonitors}};
+
+%% Port退出的时候，尝试重启
+handle_info({'EXIT', Port, Reason}, State = #state{port = Port}) ->
+    lager:warning("[efka_docker_events] exit with reason: ~p", [Reason]),
+    try_attach_events(5000),
+    {noreply, State#state{port = undefined}}.
 
 %% @private
 %% @doc This function is called by a gen_server when it is about to
@@ -134,3 +130,22 @@ code_change(_OldVsn, State = #state{}, _Extra) ->
 %%%===================================================================
 %%% Internal functions
 %%%===================================================================
+handle_event(#{<<"Type">> := <<"container">>, <<"status">> := Status, <<"id">> := Id}, #state{monitors = Monitors}) ->
+    case maps:find(Id, Monitors) of
+        error ->
+            ok;
+        {ok, {ReceiverPid, _}} ->
+            case Status of
+                <<"start">> ->
+                    ReceiverPid ! {docker_events, start};
+                <<"stop">> ->
+                    ReceiverPid ! {docker_events, stop};
+                _ ->
+                    ok
+            end
+    end;
+handle_event(_, _) ->
+    ok.
+
+try_attach_events(Timeout) ->
+    erlang:start_timer(Timeout, self(), attach_docker_events).

apps/efka/src/docker/docker_helper.erl

@@ -0,0 +1,36 @@
+%%%-------------------------------------------------------------------
+%%% @author anlicheng
+%%% @copyright (C) 2025, <COMPANY>
+%%% @doc
+%%%
+%%% @end
+%%% Created : 17. 9月 2025 14:50
+%%%-------------------------------------------------------------------
+-module(docker_helper).
+-author("anlicheng").
+
+%% API
+-export([ensure_container_dir/2, get_container_dir/2, get_config_file/1]).
+
+-spec ensure_container_dir(RootDir :: string(), ContainerName :: binary()) -> {ok, ServerRootDir :: string()}.
+ensure_container_dir(RootDir, ContainerName) when is_list(RootDir), is_binary(ContainerName) ->
+    %% 根目录
+    ContainerRootDir = RootDir ++ "/" ++ binary_to_list(ContainerName) ++ "/",
+    ok = filelib:ensure_dir(ContainerRootDir),
+    {ok, ContainerRootDir}.
+
+-spec get_config_file(ContainerDir :: string()) -> ConfigFile :: string().
+get_config_file(ContainerDir) when is_list(ContainerDir) ->
+    %% 根目录
+    ContainerDir ++ "service.conf".
+
+-spec get_container_dir(RootDir :: string(), ContainerName :: binary()) -> {ok, ServerRootDir :: string()} | error.
+get_container_dir(RootDir, ContainerName) when is_list(RootDir), is_binary(ContainerName) ->
+    %% 根目录
+    ContainerRootDir = RootDir ++ "/" ++ binary_to_list(ContainerName) ++ "/",
+    case filelib:is_dir(ContainerRootDir) of
+        true ->
+            {ok, ContainerRootDir};
+        false ->
+            error
+    end.

apps/efka/src/docker/docker_http.erl

@@ -0,0 +1,85 @@
+%%% docker_http.erl
+-module(docker_http).
+-export([request/4, stream_request/5]).
+
+%% 通过 Unix Socket 调用 Docker API
+-spec request(Method :: string(), Path :: string(), Body :: binary() | undefined, Headers :: list()) ->
+    {ok, StatusCode :: integer(), RespHeaders :: proplists:proplist(), RespBody :: binary()} | {error, any()}.
+request(Method, Path, Body, Headers) when is_list(Method), is_list(Path), is_binary(Body), is_list(Headers) ->
+    SocketPath = "/var/run/docker.sock",
+    %% 使用 gun:open/2 + {local, Path} 方式
+    case gun:open_unix(SocketPath, #{}) of
+        {ok, ConnPid} ->
+            case gun:await_up(ConnPid) of
+                {ok, _} ->
+                    %% 发送 HTTP 请求
+                    StreamRef = gun:request(ConnPid, Method, Path, Headers, Body),
+                    receive_response(ConnPid, StreamRef);
+                {error, Reason} ->
+                    {error, Reason}
+            end;
+        {error, Reason} ->
+            {error, Reason}
+    end.
+
+receive_response(ConnPid, StreamRef) ->
+    receive
+        {gun_response, ConnPid, StreamRef, nofin, Status, Headers} ->
+            receive_body(ConnPid, StreamRef, Status, Headers, <<>>);
+        {gun_response, ConnPid, StreamRef, fin, Status, Headers} ->
+            {ok, Status, Headers, <<>>};
+        {gun_down, ConnPid, _, Reason, _} ->
+            {error, {http_closed, Reason}}
+    after 5000 ->
+        {error, timeout}
+    end.
+receive_body(ConnPid, StreamRef, Status, Headers, Acc) ->
+    receive
+        {gun_data, ConnPid, StreamRef, fin, Data} ->
+            {ok, Status, Headers, <<Acc/binary, Data/binary>>};
+        {gun_data, ConnPid, StreamRef, nofin, Data} ->
+            NewAcc = <<Acc/binary, Data/binary>>,
+            receive_body(ConnPid, StreamRef, Status, Headers, NewAcc)
+    after 10000 ->
+        {error, timeout22}
+    end.
+
+%% 通过 Unix Socket 调用 Docker API
+-spec stream_request(Callback :: any(), Method :: string(), Path :: string(), Body :: binary(), Headers :: list()) -> ok | {error, Reason :: any()}.
+stream_request(Callback, Method, Path, Body, Headers) when is_list(Method), is_list(Path), is_binary(Body), is_list(Headers) ->
+    SocketPath = "/var/run/docker.sock",
+    case gun:open_unix(SocketPath, #{}) of
+        {ok, ConnPid} ->
+            case gun:await_up(ConnPid) of
+                {ok, _} ->
+                    %% 发送 HTTP 请求
+                    StreamRef = gun:request(ConnPid, Method, Path, Headers, Body),
+                    receive_response(Callback, ConnPid, StreamRef);
+                {error, Reason} ->
+                    {error, Reason}
+            end;
+        {error, Reason} ->
+            Callback({error, Reason}),
+            {error, Reason}
+    end.
+
+receive_response(Callback, ConnPid, StreamRef) ->
+    receive
+        {gun_response, ConnPid, StreamRef, nofin, _Status, _Headers} ->
+            receive_body(Callback, ConnPid, StreamRef);
+        {gun_down, ConnPid, _, Reason, _} ->
+            Callback({error, Reason}),
+            {error, Reason}
+    after 5000 ->
+        Callback({error, <<"处理超时"/utf8>>}),
+        {error, timeout}
+    end.
+receive_body(Callback, ConnPid, StreamRef) ->
+    receive
+        {gun_data, ConnPid, StreamRef, fin, Data} ->
+            Callback({message, Data}),
+            ok;
+        {gun_data, ConnPid, StreamRef, nofin, Data} ->
+            Callback({message, Data}),
+            receive_body(Callback, ConnPid, StreamRef)
+    end.

apps/efka/src/docker/docker_manager.erl

@@ -0,0 +1,225 @@
+%%%-------------------------------------------------------------------
+%%% @author anlicheng
+%%% @copyright (C) 2025, <COMPANY>
+%%% @doc
+%%% 微服务守护进程
+%%% 1. 负责微服务的下载, 版本的管理
+%%% 2. 目录管理等
+%%% @end
+%%% Created : 19. 4月 2025 14:55
+%%%-------------------------------------------------------------------
+-module(docker_manager).
+-author("anlicheng").
+
+-behaviour(gen_server).
+
+%% API
+-export([start_link/0]).
+-export([deploy/2, start_container/1, stop_container/1, config_container/2, kill_container/1, remove_container/1]).
+-export([get_containers/0]).
+
+%% gen_server callbacks
+-export([init/1, handle_call/3, handle_cast/2, handle_info/2, terminate/2, code_change/3]).
+
+-define(SERVER, ?MODULE).
+
+-record(state, {
+    root_dir :: string(),
+    %% 建立任务到ref之间的映射, #{TaskPid => TaskId}
+    task_map = #{}
+}).
+
+%%%===================================================================
+%%% API
+%%%===================================================================
+
+-spec get_containers() -> {ok, Containers :: [map()]} | {error, Reason :: binary()}.
+get_containers() ->
+    gen_server:call(?SERVER, get_containers).
+
+-spec deploy(TaskId :: integer(), Config :: map()) -> ok | {error, Reason :: binary()}.
+deploy(TaskId, Config) when is_integer(TaskId), is_map(Config) ->
+    gen_server:call(?SERVER, {deploy, TaskId, Config}).
+
+-spec config_container(ContainerName :: binary(), Config :: binary()) -> ok | {error, Reason :: binary()}.
+config_container(ContainerName, Config) when is_binary(ContainerName), is_binary(Config) ->
+    gen_server:call(?SERVER, {config_container, ContainerName, Config}).
+
+-spec start_container(ServiceId :: binary()) -> ok | {error, Reason :: term()}.
+start_container(ContainerId) when is_binary(ContainerId) ->
+    gen_server:call(?SERVER, {start_container, ContainerId}).
+
+-spec stop_container(ServiceId :: binary()) -> ok | {error, Reason :: term()}.
+stop_container(ContainerId) when is_binary(ContainerId) ->
+    gen_server:call(?SERVER, {stop_container, ContainerId}).
+
+-spec kill_container(ServiceId :: binary()) -> ok | {error, Reason :: term()}.
+kill_container(ContainerId) when is_binary(ContainerId) ->
+    gen_server:call(?SERVER, {kill_container, ContainerId}).
+
+-spec remove_container(ServiceId :: binary()) -> ok | {error, Reason :: term()}.
+remove_container(ContainerId) when is_binary(ContainerId) ->
+    gen_server:call(?SERVER, {remove_container, ContainerId}).
+
+%% @doc Spawns the server and registers the local name (unique)
+-spec(start_link() ->
+    {ok, Pid :: pid()} | ignore | {error, Reason :: term()}).
+start_link() ->
+    gen_server:start_link({local, ?SERVER}, ?MODULE, [], []).
+
+%%%===================================================================
+%%% gen_server callbacks
+%%%===================================================================
+
+%% @private
+%% @doc Initializes the server
+-spec(init(Args :: term()) ->
+    {ok, State :: #state{}} | {ok, State :: #state{}, timeout() | hibernate} |
+    {stop, Reason :: term()} | ignore).
+init([]) ->
+    erlang:process_flag(trap_exit, true),
+    {ok, RootDir} = application:get_env(efka, root_dir),
+    {ok, #state{root_dir = RootDir}}.
+
+%% @private
+%% @doc Handling call messages
+-spec(handle_call(Request :: term(), From :: {pid(), Tag :: term()},
+    State :: #state{}) ->
+    {reply, Reply :: term(), NewState :: #state{}} |
+    {reply, Reply :: term(), NewState :: #state{}, timeout() | hibernate} |
+    {noreply, NewState :: #state{}} |
+    {noreply, NewState :: #state{}, timeout() | hibernate} |
+    {stop, Reason :: term(), Reply :: term(), NewState :: #state{}} |
+    {stop, Reason :: term(), NewState :: #state{}}).
+handle_call({deploy, TaskId, Config = #{<<"container_name">> := ContainerName}}, _From, State = #state{root_dir = RootDir, task_map = TaskMap}) ->
+    %% 创建目录
+    {ok, ContainerDir} = docker_helper:ensure_container_dir(RootDir, ContainerName),
+    {ok, {TaskPid, _Ref}} = docker_deployer:start_monitor(TaskId, ContainerDir, Config),
+    lager:debug("[docker_manager] start deploy task_id: ~p, config: ~p", [TaskId, Config]),
+    {reply, ok, State#state{task_map = maps:put(TaskPid, TaskId, TaskMap)}};
+
+%% 处理容器关联的配置文件
+handle_call({config_container, ContainerName, Config}, _From, State = #state{root_dir = RootDir}) ->
+    case docker_helper:get_container_dir(RootDir, ContainerName) of
+        {ok, ContainerDir} ->
+            %% 覆盖容器的配置文件
+            ConfigFile = docker_helper:get_config_file(ContainerDir),
+            case file:write_file(ConfigFile, Config, [write, binary]) of
+                ok ->
+                    lager:warning("[docker_manager] write config file: ~p success", [ConfigFile]),
+                    {reply, ok, State};
+                {error, Reason} ->
+                    lager:warning("[docker_manager] write config file: ~p, get error: ~p", [ConfigFile, Reason]),
+                    {reply, {error, <<"write config failed">>}, State}
+            end;
+        error ->
+            {reply, {error, <<"error">>}, State}
+    end;
+
+%% 启动服务: 当前服务如果正常运行，则不允许重启
+handle_call({start_container, ContainerId}, _From, State) ->
+    case docker_commands:start_container(ContainerId) of
+        ok ->
+            {reply, ok, State};
+        {error, Reason} ->
+            {reply, {error, Reason}, State}
+    end;
+
+
+%% 停止服务, 主动停止的时候会改变服务配置的status字段
+handle_call({stop_container, ContainerId}, _From, State = #state{}) ->
+    case docker_commands:stop_container(ContainerId) of
+        ok ->
+            {reply, ok, State};
+        {error, Reason} ->
+            {reply, {error, Reason}, State}
+    end;
+
+%% 停止服务, 主动停止的时候会改变服务配置的status字段
+handle_call({kill_container, ContainerId}, _From, State = #state{}) ->
+    case docker_commands:kill_container(ContainerId) of
+        ok ->
+            {reply, ok, State};
+        {error, Reason} ->
+            {reply, {error, Reason}, State}
+    end;
+
+%% 停止服务, 主动停止的时候会改变服务配置的status字段
+handle_call(get_containers, _From, State = #state{}) ->
+    case docker_commands:get_containers() of
+        {ok, Containers} ->
+            {reply, {ok, Containers}, State};
+        {error, Reason} ->
+            {reply, {error, Reason}, State}
+    end;
+
+%% 停止服务, 主动停止的时候会改变服务配置的status字段
+handle_call({remove_container, ContainerId}, _From, State = #state{}) ->
+    case docker_commands:remove_container(ContainerId) of
+        ok ->
+            {reply, ok, State};
+        {error, Reason} ->
+            {reply, {error, Reason}, State}
+    end;
+
+handle_call(_Request, _From, State = #state{}) ->
+    {reply, ok, State}.
+
+%% @private
+%% @doc Handling cast messages
+-spec(handle_cast(Request :: term(), State :: #state{}) ->
+    {noreply, NewState :: #state{}} |
+    {noreply, NewState :: #state{}, timeout() | hibernate} |
+    {stop, Reason :: term(), NewState :: #state{}}).
+handle_cast(_Request, State = #state{}) ->
+    {noreply, State}.
+
+%% @private
+%% @doc Handling all non call/cast messages
+-spec(handle_info(Info :: timeout() | term(), State :: #state{}) ->
+    {noreply, NewState :: #state{}} |
+    {noreply, NewState :: #state{}, timeout() | hibernate} |
+    {stop, Reason :: term(), NewState :: #state{}}).
+handle_info({'DOWN', _Ref, process, TaskPid, Reason}, State = #state{task_map = TaskMap}) ->
+    case maps:take(TaskPid, TaskMap) of
+        error ->
+            {noreply, State};
+        {TaskId, NTaskMap} ->
+            case Reason of
+                normal ->
+                    lager:debug("[docker_manager] task_id: ~p, exit normal", [TaskId]),
+                    ok;
+                Error0 ->
+                    Error = iolist_to_binary(io_lib:format("~p", [Error0])),
+                    efka_remote_agent:task_event_stream(TaskId, <<"error">>, <<"任务失败: "/utf8, Error/binary>>),
+                    efka_remote_agent:close_task_event_stream(TaskId, <<"task exited">>),
+                    lager:notice("[docker_manager] task_id: ~p, exit with error: ~p", [TaskId, Error]),
+                    ok
+            end,
+            {noreply, State#state{task_map = NTaskMap}}
+    end;
+
+handle_info(_Info, State = #state{}) ->
+    {noreply, State}.
+
+%% @private
+%% @doc This function is called by a gen_server when it is about to
+%% terminate. It should be the opposite of Module:init/1 and do any
+%% necessary cleaning up. When it returns, the gen_server terminates
+%% with Reason. The return value is ignored.
+-spec(terminate(Reason :: (normal | shutdown | {shutdown, term()} | term()),
+    State :: #state{}) -> term()).
+terminate(_Reason, _State = #state{}) ->
+    ok.
+
+%% @private
+%% @doc Convert process state when code is changed
+-spec(code_change(OldVsn :: term() | {down, term()}, State :: #state{},
+    Extra :: term()) ->
+    {ok, NewState :: #state{}} | {error, Reason :: term()}).
+code_change(_OldVsn, State = #state{}, _Extra) ->
+    {ok, State}.
+
+%%%===================================================================
+%%% Internal functions
+%%%===================================================================

apps/efka/src/efka.app.src

@@ -7,19 +7,16 @@
    [
     sync,
     jiffy,
-    %gpb,
-    mnesia,
     parse_trans,
     lager,
+    cowboy,
+    ranch,
     crypto,
+    gun,
+    cowlib,
     inets,
     ssl,
     public_key,
-
-    %erts,
-    %runtime_tools,
-    %observer,
-
     kernel,
     stdlib
    ]},

apps/efka/src/efka_agent.erl

@@ -1,435 +0,0 @@
-%%%-------------------------------------------------------------------
-%%% @author anlicheng
-%%% @copyright (C) 2025, <COMPANY>
-%%% @doc
-%%%
-%%% @end
-%%% Created : 21. 5月 2025 18:38
-%%%-------------------------------------------------------------------
--module(efka_agent).
--author("anlicheng").
--include("message_pb.hrl").
--include("efka.hrl").
--include("efka_tables.hrl").
-
--behaviour(gen_statem).
-
-%% API
--export([start_link/0]).
--export([metric_data/3, event/3, ping/13, request_service_config/2, await_reply/2]).
-
-%% gen_statem callbacks
--export([init/1, handle_event/4, terminate/3, code_change/4, callback_mode/0]).
-
--define(SERVER, ?MODULE).
-
-%% 标记当前agent的状态，只有在 activated 状态下才可以正常的发送数据
--define(STATE_DENIED, denied).
--define(STATE_CONNECTING, connecting).
--define(STATE_AUTH, auth).
-%% 不能推送消息到服务，但是可以接受服务器的部分指令
--define(STATE_RESTRICTED, restricted).
-%% 激活状态下
--define(STATE_ACTIVATED, activated).
-
--record(state, {
-    transport_pid :: undefined | pid(),
-    transport_ref :: undefined | reference(),
-    %% 服务器端推送的消息的未确认列表, 映射关系 #{Ref => PacketId}
-    push_inflight = #{},
-    %% 发送的请求的未确认列表, 映射关系 #{Ref => ReceiverPid}
-    request_inflight = #{}
-}).
-
-%%%===================================================================
-%%% API
-%%%===================================================================
-
-%% 发送数据
--spec metric_data(ServiceId :: binary(), DeviceUUID::binary(), LineProtocolData :: binary()) -> no_return().
-metric_data(ServiceId, DeviceUUID, LineProtocolData) when is_binary(ServiceId), is_binary(DeviceUUID), is_binary(LineProtocolData) ->
-    gen_statem:cast(?SERVER, {metric_data, ServiceId, DeviceUUID, LineProtocolData}).
-
--spec event(ServiceId :: binary(), EventType :: integer(), Params :: binary()) -> no_return().
-event(ServiceId, EventType, Params) when is_binary(ServiceId), is_integer(EventType), is_binary(Params) ->
-    gen_statem:cast(?SERVER, {event, ServiceId, EventType, Params}).
-
-ping(AdCode, BootTime, Province, City, EfkaVersion, KernelArch, Ips, CpuCore, CpuLoad, CpuTemperature, Disk, Memory, Interfaces) ->
-    gen_statem:cast(?SERVER, {ping, AdCode, BootTime, Province, City, EfkaVersion, KernelArch, Ips, CpuCore, CpuLoad, CpuTemperature, Disk, Memory, Interfaces}).
-
-%% 请求微服务的配置
--spec request_service_config(ReceiverPid :: pid(), ServiceId :: binary()) -> {ok, Ref :: reference()} | {error, Reason :: term()}.
-request_service_config(ReceiverPid, ServiceId) when is_binary(ServiceId) ->
-    gen_statem:call(?SERVER, {request_service_config, ReceiverPid, ServiceId}).
-
-%% 等待消息的回复
--spec await_reply(Ref :: reference(), Timeout :: timeout()) -> {ok, Reply :: binary()} | {error, timeout}.
-await_reply(Ref, Timeout) when is_reference(Ref), is_integer(Timeout) ->
-    receive
-        {request_reply, Ref, ReplyBin} ->
-            {ok, ReplyBin}
-    after Timeout ->
-        {error, timeout}
-    end.
-
-%% @doc Creates a gen_statem process which calls Module:init/1 to
-%% initialize. To ensure a synchronized start-up procedure, this
-%% function does not return until Module:init/1 has returned.
-start_link() ->
-    gen_statem:start_link({local, ?SERVER}, ?MODULE, [], []).
-
-%%%===================================================================
-%%% gen_statem callbacks
-%%%===================================================================
-
-%% @private
-%% @doc Whenever a gen_statem is started using gen_statem:start/[3,4] or
-%% gen_statem:start_link/[3,4], this function is called by the new
-%% process to initialize.
-init([]) ->
-    erlang:start_timer(0, self(), create_transport),
-    {ok, ?STATE_DENIED, #state{}}.
-
-%% @private
-%% @doc This function is called by a gen_statem when it needs to find out
-%% the callback mode of the callback module.
-callback_mode() ->
-    handle_event_function.
-
-%% @private
-%% @doc If callback_mode is handle_event_function, then whenever a
-%% gen_statem receives an event from call/2, cast/2, or as a normal
-%% process message, this function is called.
-handle_event({call, From}, {request_service_config, ReceiverPid, ServiceId}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid, request_inflight = RequestInflight}) ->
-    Ref = efka_transport:request(TransportPid, ?METHOD_REQUEST_SERVICE_CONFIG, ServiceId),
-    {keep_state, State#state{request_inflight = maps:put(Ref, ReceiverPid, RequestInflight)}, [{reply, From, {ok, Ref}}]};
-
-handle_event({call, From}, {request_service_config, _ReceiverPid, _ServiceId}, _, State) ->
-    {keep_state, State, [{reply, From, {error, <<"transport is not alive">>}}]};
-
-%% 异步发送数据, 连接存在时候直接发送；否则缓存到mnesia
-handle_event(cast, {metric_data, ServiceId, DeviceUUID, LineProtocolData}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
-    Packet = message_pb:encode_msg(#data{
-        service_id = ServiceId,
-        device_uuid = DeviceUUID,
-        metric = LineProtocolData
-    }),
-    efka_transport:send(TransportPid, ?METHOD_DATA, Packet),
-    {keep_state, State};
-
-handle_event(cast, {metric_data, ServiceId, DeviceUUID, LineProtocolData}, _, State) ->
-    Packet = message_pb:encode_msg(#data{
-        service_id = ServiceId,
-        device_uuid = DeviceUUID,
-        metric = LineProtocolData
-    }),
-    ok = cache_model:insert(?METHOD_DATA, Packet),
-    {keep_state, State};
-
-%% 异步发送事件
-handle_event(cast, {event, ServiceId, EventType, Params}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
-    EventPacket = message_pb:encode_msg(#event{
-        service_id = ServiceId,
-        event_type = EventType,
-        params = Params
-    }),
-    efka_transport:send(TransportPid, ?METHOD_EVENT, EventPacket),
-    {keep_state, State};
-handle_event(cast, {event, ServiceId, EventType, Params}, ?STATE_ACTIVATED, State) ->
-    EventPacket = message_pb:encode_msg(#event{
-        service_id = ServiceId,
-        event_type = EventType,
-        params = Params
-    }),
-    ok = cache_model:insert(?METHOD_EVENT, EventPacket),
-    {keep_state, State};
-
-handle_event(cast, {ping, AdCode, BootTime, Province, City, EfkaVersion, KernelArch, Ips, CpuCore, CpuLoad, CpuTemperature, Disk, Memory, Interfaces}, ?STATE_ACTIVATED,
-    State = #state{transport_pid = TransportPid}) ->
-
-    Ping = message_pb:encode_msg(#ping{
-        adcode = AdCode,
-        boot_time = BootTime,
-        province = Province,
-        city = City,
-        efka_version = EfkaVersion,
-        kernel_arch = KernelArch,
-        ips = Ips,
-        cpu_core = CpuCore,
-        cpu_load = CpuLoad,
-        cpu_temperature = CpuTemperature,
-        disk = Disk,
-        memory = Memory,
-        interfaces = Interfaces
-    }),
-    efka_transport:send(TransportPid, ?METHOD_PING, Ping),
-    {keep_state, State};
-
-%% 异步建立到服务器的连接
-handle_event(info, {timeout, _, create_transport}, ?STATE_DENIED, State) ->
-    {ok, Props} = application:get_env(efka, tls_server),
-    Host = proplists:get_value(host, Props),
-    Port = proplists:get_value(port, Props),
-    {ok, {TransportPid, TransportRef}} = efka_transport:start_monitor(self(), Host, Port),
-    efka_transport:connect(TransportPid),
-
-    {next_state, ?STATE_CONNECTING, State#state{transport_pid = TransportPid, transport_ref = TransportRef}};
-
-handle_event(info, {connect_reply, Reply}, ?STATE_CONNECTING, State = #state{transport_pid = TransportPid}) ->
-    case Reply of
-        ok ->
-            AuthBin = auth_request(),
-            efka_transport:auth_request(TransportPid, AuthBin),
-            {next_state, ?STATE_AUTH, State};
-        {error, Reason} ->
-            lager:debug("[efka_agent] connect failed, error: ~p, pid: ~p", [Reason, TransportPid]),
-            efka_transport:stop(TransportPid),
-            {next_state, ?STATE_DENIED, State#state{transport_pid = undefined}}
-    end;
-
-handle_event(info, {auth_reply, Reply}, ?STATE_AUTH, State = #state{transport_pid = TransportPid}) ->
-    case Reply of
-        {ok, ReplyBin} ->
-            #auth_reply{code = Code, message = Message} = message_pb:decode_msg(ReplyBin, auth_reply),
-            case Code of
-                0 ->
-                    lager:debug("[efka_agent] auth success, message: ~p", [Message]),
-                    {next_state, ?STATE_ACTIVATED, State, [{next_event, info, flush_cache}]};
-                1 ->
-                    %% 主机在后台的授权未通过；此时agent不能推送数据给云端服务器，但是云端服务器可以推送命令给agent
-                    %% socket的连接状态需要维持
-                    lager:debug("[efka_agent] auth denied, message: ~p", [Message]),
-                    {next_state, ?STATE_RESTRICTED, State};
-                2 ->
-                    % 其他类型的错误，需要间隔时间重试
-                    lager:debug("[efka_agent] auth failed, message: ~p", [Message]),
-                    efka_transport:stop(TransportPid),
-                    {next_state, ?STATE_DENIED, State#state{transport_pid = undefined}};
-                _ ->
-                    % 其他类型的错误，需要间隔时间重试
-                    lager:debug("[efka_agent] auth failed, invalid message"),
-                    efka_transport:stop(TransportPid),
-                    {next_state, ?STATE_DENIED, State#state{transport_pid = undefined}}
-            end;
-        {error, Reason} ->
-            lager:debug("[efka_agent] auth_request failed, error: ~p", [Reason]),
-            efka_transport:stop(TransportPid),
-            {next_state, ?STATE_DENIED, State#state{transport_pid = undefined}}
-    end;
-
-%% 将缓存中的数据推送到服务器端
-handle_event(info, flush_cache, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
-    case cache_model:fetch_next() of
-        {ok, #cache{id = Id, method = Method, data = Packet}} ->
-            efka_transport:send(TransportPid, Method, Packet),
-            cache_model:delete(Id),
-            {keep_state, State, [{next_event, info, flush_cache}]};
-        error ->
-            {keep_state, State}
-    end;
-handle_event(info, flush_cache, _, State) ->
-    {keep_state, State};
-
-%% 云端服务器推送了消息
-%% 激活消息
-
-%% 微服务部署
-handle_event(info, {server_async_call, PacketId, <<?PUSH_DEPLOY:8, DeployBin/binary>>}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
-    #deploy{task_id = TaskId, service_id = ServiceId, tar_url = TarUrl} = message_pb:decode_msg(DeployBin, deploy),
-
-    %% 短暂的等待，efka_inetd收到消息后就立即返回了
-    Reply = case efka_inetd:deploy(TaskId, ServiceId, TarUrl) of
-                ok ->
-                    #async_call_reply{code = 1, result = <<"ok">>};
-                {error, Reason} when is_binary(Reason) ->
-                    #async_call_reply{code = 0, message = Reason}
-            end,
-    efka_transport:async_call_reply(TransportPid, PacketId, message_pb:encode_msg(Reply)),
-
-    {keep_state, State};
-
-%% 启动微服务
-handle_event(info, {server_async_call, PacketId, <<?PUSH_START_SERVICE:8, ServiceId/binary>>}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
-    %% 短暂的等待，efka_inetd收到消息后就立即返回了
-    Reply = case efka_inetd:start_service(ServiceId) of
-                ok ->
-                    #async_call_reply{code = 1, result = <<"ok">>};
-                {error, Reason} when is_binary(Reason) ->
-                    #async_call_reply{code = 0, message = Reason}
-            end,
-    efka_transport:async_call_reply(TransportPid, PacketId, message_pb:encode_msg(Reply)),
-
-    {keep_state, State};
-
-%% 停止微服务
-handle_event(info, {server_async_call, PacketId, <<?PUSH_STOP_SERVICE:8, ServiceId/binary>>}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
-    %% 短暂的等待，efka_inetd收到消息后就立即返回了
-    Reply = case efka_inetd:stop_service(ServiceId) of
-                ok ->
-                    #async_call_reply{code = 1, result = <<"ok">>};
-                {error, Reason} when is_binary(Reason) ->
-                    #async_call_reply{code = 0, message = Reason}
-            end,
-    efka_transport:async_call_reply(TransportPid, PacketId, message_pb:encode_msg(Reply)),
-
-    {keep_state, State};
-
-%% config.json配置信息
-handle_event(info, {server_async_call, PacketId, <<?PUSH_SERVICE_CONFIG:8, ConfigBin/binary>>}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid, push_inflight = PushInflight}) ->
-    #push_service_config{service_id = ServiceId, config_json = ConfigJson, timeout = Timeout} = message_pb:decode_msg(ConfigBin, push_service_config),
-
-    case efka_service:get_pid(ServiceId) of
-        undefined ->
-            Reply = #async_call_reply{code = 0, message = <<"service not run">>},
-            efka_transport:async_call_reply(TransportPid, PacketId, message_pb:encode_msg(Reply)),
-            {keep_state, State};
-        ServicePid when is_pid(ServicePid) ->
-            Ref = make_ref(),
-            %% 将配置文件推送到对应的微服务
-            efka_service:push_config(ServicePid, Ref, ConfigJson),
-            %% 处理超时逻辑
-            erlang:start_timer(Timeout, self(), {request_timeout, Ref}),
-
-            {keep_state, State#state{push_inflight = maps:put(Ref, PacketId, PushInflight)}}
-    end;
-
-%% 收到需要回复的指令
-handle_event(info, {server_async_call, PacketId, <<?PUSH_INVOKE:8, InvokeBin/binary>>}, ?STATE_ACTIVATED, State = #state{push_inflight = PushInflight, transport_pid = TransportPid}) ->
-    #invoke{service_id = ServiceId, payload = Payload, timeout = Timeout} = message_pb:decode_msg(InvokeBin, invoke),
-    %% 消息发送到订阅系统
-    case efka_service:get_pid(ServiceId) of
-        undefined ->
-            Reply = #async_call_reply{code = 0, message = <<"micro_service not run">>},
-            efka_transport:async_call_reply(TransportPid, PacketId, message_pb:encode_msg(Reply)),
-
-            {keep_state, State};
-        ServicePid when is_pid(ServicePid) ->
-            Ref = make_ref(),
-            efka_service:invoke(ServicePid, Ref, Payload),
-            %% 处理超时逻辑
-            erlang:start_timer(Timeout, self(), {request_timeout, Ref}),
-
-            {keep_state, State#state{push_inflight = maps:put(Ref, PacketId, PushInflight)}}
-    end;
-
-%% 处理task_log
-handle_event(info, {server_async_call, PacketId, <<?PUSH_TASK_LOG:8, TaskLogBin/binary>>}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
-    #fetch_task_log{task_id = TaskId} = message_pb:decode_msg(TaskLogBin, fetch_task_log),
-    lager:debug("[efka_agent] get task_log request: ~p", [TaskId]),
-    {ok, Logs} = efka_inetd_task_log:get_logs(TaskId),
-    Reply = case length(Logs) > 0 of
-                true ->
-                    Result = iolist_to_binary(jiffy:encode(Logs, [force_utf8])),
-                    #async_call_reply{code = 1, result = Result};
-                false ->
-                    #async_call_reply{code = 1, result = <<"[]">>}
-            end,
-    efka_transport:async_call_reply(TransportPid, PacketId, message_pb:encode_msg(Reply)),
-
-    {keep_state, State};
-
-%% 处理命令
-handle_event(info, {server_command, ?COMMAND_AUTH, <<Auth:8>>}, StateName, State = #state{transport_pid = TransportPid}) ->
-    case {Auth, StateName} of
-        {1, ?STATE_ACTIVATED} ->
-            {keep_state, State};
-        {1, ?STATE_DENIED} ->
-            %% 重新激活, 需要重新校验
-            AuthRequestBin = auth_request(),
-            efka_transport:auth_request(TransportPid, AuthRequestBin),
-            {next_state, ?STATE_AUTH, State};
-        {0, _} ->
-            %% 这个时候的主机应该是受限制的状态，不允许发送消息；但是能够接受服务器推送的消息
-            {next_state, ?STATE_RESTRICTED, State}
-    end;
-
-%% 处理Pub/Sub机制
-handle_event(info, {server_pub, Topic, Content}, ?STATE_ACTIVATED, State) ->
-    lager:debug("[efka_agent] get pub topic: ~p, content: ~p", [Topic, Content]),
-    %% 消息发送到订阅系统
-    efka_subscription:publish(Topic, Content),
-    {keep_state, State};
-
-%% 收到来自efka_service的回复
-handle_event(info, {service_reply, Ref, EmsReply}, ?STATE_ACTIVATED, State = #state{push_inflight = PushInflight, transport_pid = TransportPid}) ->
-    case maps:take(Ref, PushInflight) of
-        error ->
-            {keep_state, State};
-        {PacketId, NPushInflight} ->
-            Reply = case EmsReply of
-                        {ok, Result} ->
-                            #async_call_reply{code = 1, result = Result};
-                        {error, Reason} ->
-                            #async_call_reply{code = 0, message = Reason}
-                    end,
-            efka_transport:async_call_reply(TransportPid, PacketId, message_pb:encode_msg(Reply)),
-
-            {keep_state, State#state{push_inflight = NPushInflight}}
-    end;
-
-%% 收到来自服务器端的回复
-handle_event(info, {server_reply, Ref, ReplyBin}, ?STATE_ACTIVATED, State = #state{request_inflight = RequestInflight}) ->
-    case maps:take(Ref, RequestInflight) of
-        error ->
-            {keep_state, State};
-        {ReceiverPid, NRequestInflight} ->
-            is_process_alive(ReceiverPid) andalso erlang:send(ReceiverPid, {request_reply, Ref, ReplyBin}),
-            {keep_state, State#state{push_inflight = NRequestInflight}}
-    end;
-
-%% todo 请求超时逻辑处理
-handle_event(info, {timeout, _, {request_timeout, Ref}}, ?STATE_ACTIVATED, State = #state{push_inflight = PushInflight, transport_pid = TransportPid}) ->
-    case maps:take(Ref, PushInflight) of
-        error ->
-            {keep_state, State};
-        {PacketId, NPushInflight} ->
-            Reply = #async_call_reply{code = 0, message = <<"reqeust timeout">>, result = <<>>},
-            efka_transport:async_call_reply(TransportPid, PacketId, message_pb:encode_msg(Reply)),
-
-            {keep_state, State#state{push_inflight = NPushInflight}}
-    end;
-
-%% transport进程退出
-handle_event(info, {'DOWN', MRef, process, TransportPid, Reason}, _, State = #state{transport_ref = MRef}) ->
-    lager:debug("[efka_agent] transport pid: ~p, exit with reason: ~p", [TransportPid, Reason]),
-    erlang:start_timer(5000, self(), create_transport),
-    {next_state, ?STATE_DENIED, State#state{transport_pid = undefined, transport_ref = undefined}}.
-
-%% @private
-%% @doc This function is called by a gen_statem when it is about to
-%% terminate. It should be the opposite of Module:init/1 and do any
-%% necessary cleaning up. When it returns, the gen_statem terminates with
-%% Reason. The return value is ignored.
-terminate(_Reason, _StateName, _State = #state{transport_pid = TransportPid}) ->
-    case is_pid(TransportPid) andalso is_process_alive(TransportPid) of
-        true ->
-            efka_transport:stop(TransportPid);
-        false ->
-            ok
-    end,
-    ok.
-
-%% @private
-%% @doc Convert process state when code is changed
-code_change(_OldVsn, StateName, State = #state{}, _Extra) ->
-    {ok, StateName, State}.
-
-%%%===================================================================
-%%% Internal functions
-%%%===================================================================
-
--spec auth_request() -> binary().
-auth_request() ->
-    {ok, AuthInfo} = application:get_env(efka, auth),
-    UUID = proplists:get_value(uuid, AuthInfo),
-    Username = proplists:get_value(username, AuthInfo),
-    Salt = proplists:get_value(salt, AuthInfo),
-    Token = proplists:get_value(token, AuthInfo),
-
-    message_pb:encode_msg(#auth_request{
-        uuid = unicode:characters_to_binary(UUID),
-        username = unicode:characters_to_binary(Username),
-        salt = unicode:characters_to_binary(Salt),
-        token = unicode:characters_to_binary(Token),
-        timestamp = efka_util:timestamp()
-    }).

apps/efka/src/efka_app.erl

@@ -11,44 +11,47 @@
 
 start(_StartType, _StartArgs) ->
     io:setopts([{encoding, unicode}]),
-    %% 启动mnesia数据库
-    start_mnesia(),
+    ensure_upload_dir(),
     %% 加速内存的回收
     erlang:system_flag(fullsweep_after, 16),
+    start_http_server(),
+
     efka_sup:start_link().
 
 stop(_State) ->
     ok.
 
-%% internal functions
+%% 微服务和efka之间通过websocket协议通讯
+start_http_server() ->
+    {ok, Props} = application:get_env(efka, http_server),
+    Acceptors = proplists:get_value(acceptors, Props, 50),
+    MaxConnections = proplists:get_value(max_connections, Props, 10240),
+    Backlog = proplists:get_value(backlog, Props, 1024),
+    Port = proplists:get_value(port, Props),
 
-%% 启动内存数据库
-start_mnesia() ->
-    %% 启动数据库
-    ensure_mnesia_schema(),
-    ok = mnesia:start(),
-    Tables = mnesia:system_info(tables),
-    lager:debug("[efka_app] tables: ~p", [Tables]),
-    %% 创建数据库表
-    not lists:member(id_generator, Tables) andalso id_generator_model:create_table(),
-    not lists:member(service, Tables) andalso service_model:create_table(),
-    not lists:member(cache, Tables) andalso cache_model:create_table(),
-    not lists:member(task_log, Tables) andalso task_log_model:create_table(),
-    ok.
+    Dispatcher = cowboy_router:compile([
+        {'_', [
+            {"/ws", ws_channel, []},
+            {"/files/[...]", cowboy_static, {dir, "/usr/local/code/downloads"}},
+            {"/upload", upload_channel, []}
+        ]}
+    ]),
 
--spec ensure_mnesia_schema() -> any().
-ensure_mnesia_schema() ->
-    case mnesia:system_info(use_dir) of
+    TransOpts = [
+        {port, Port},
+        {num_acceptors, Acceptors},
+        {backlog, Backlog},
+        {max_connections, MaxConnections}
+    ],
+    {ok, Pid} = cowboy:start_clear(ws_listener, TransOpts, #{env => #{dispatch => Dispatcher}}),
+
+    lager:debug("[efka_app] websocket server start at: ~p, pid is: ~p", [Port, Pid]).
+
+ensure_upload_dir() ->
+    {ok, UploadDir} = application:get_env(efka, upload_dir),
+    case filelib:is_dir(UploadDir) of
         true ->
-            lager:debug("[efka_app] mnesia schema exists"),
             ok;
         false ->
-            mnesia:stop(),
-            case mnesia:create_schema([node()]) of
-                ok -> ok;
-                {error, {_, {already_exists, _}}} -> ok;
-                Error ->
-                    lager:debug("[iot_app] create mnesia schema failed with error: ~p", [Error]),
-                    throw({init_schema, Error})
-            end
+            ok = file:make_dir(UploadDir)
     end.

apps/efka/src/efka_inetd.erl

@@ -1,212 +0,0 @@
-%%%-------------------------------------------------------------------
-%%% @author anlicheng
-%%% @copyright (C) 2025, <COMPANY>
-%%% @doc
-%%% 微服务守护进程
-%%% 1. 负责微服务的下载, 版本的管理
-%%% 2. 目录管理等
-%%% @end
-%%% Created : 19. 4月 2025 14:55
-%%%-------------------------------------------------------------------
--module(efka_inetd).
--author("anlicheng").
--include("efka_tables.hrl").
--include("message_pb.hrl").
-
--behaviour(gen_server).
-
-%% API
--export([start_link/0]).
--export([deploy/3, start_service/1, stop_service/1]).
-
-%% gen_server callbacks
--export([init/1, handle_call/3, handle_cast/2, handle_info/2, terminate/2, code_change/3]).
-
--define(SERVER, ?MODULE).
-
--record(state, {
-    root_dir :: string(),
-    %% 建立任务到ref之间的映射, #{TaskPid => {TaskId, ServiceId}}
-    task_map = #{}
-}).
-
-%%%===================================================================
-%%% API
-%%%===================================================================
-
--spec deploy(TaskId :: integer(), ServerId :: binary(), TarUrl :: binary()) -> ok | {error, Reason :: binary()}.
-deploy(TaskId, ServerId, TarUrl) when is_integer(TaskId), is_binary(ServerId), is_binary(TarUrl) ->
-    gen_server:call(?SERVER, {deploy, TaskId, ServerId, TarUrl}).
-
--spec start_service(ServiceId :: binary()) -> ok | {error, Reason :: term()}.
-start_service(ServiceId) when is_binary(ServiceId) ->
-    gen_server:call(?SERVER, {start_service, ServiceId}).
-
--spec stop_service(ServiceId :: binary()) -> ok | {error, Reason :: term()}.
-stop_service(ServiceId) when is_binary(ServiceId) ->
-    gen_server:call(?SERVER, {stop_service, ServiceId}).
-
-%% @doc Spawns the server and registers the local name (unique)
--spec(start_link() ->
-    {ok, Pid :: pid()} | ignore | {error, Reason :: term()}).
-start_link() ->
-    gen_server:start_link({local, ?SERVER}, ?MODULE, [], []).
-
-%%%===================================================================
-%%% gen_server callbacks
-%%%===================================================================
-
-%% @private
-%% @doc Initializes the server
--spec(init(Args :: term()) ->
-    {ok, State :: #state{}} | {ok, State :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term()} | ignore).
-init([]) ->
-    erlang:process_flag(trap_exit, true),
-    {ok, RootDir} = application:get_env(efka, root_dir),
-    {ok, #state{root_dir = RootDir}}.
-
-%% @private
-%% @doc Handling call messages
--spec(handle_call(Request :: term(), From :: {pid(), Tag :: term()},
-    State :: #state{}) ->
-    {reply, Reply :: term(), NewState :: #state{}} |
-    {reply, Reply :: term(), NewState :: #state{}, timeout() | hibernate} |
-    {noreply, NewState :: #state{}} |
-    {noreply, NewState :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term(), Reply :: term(), NewState :: #state{}} |
-    {stop, Reason :: term(), NewState :: #state{}}).
-handle_call({deploy, TaskId, ServiceId, TarUrl}, _From, State = #state{root_dir = RootDir, task_map = TaskMap}) ->
-    %% 创建目录
-    {ok, ServiceRootDir} = ensure_dirs(RootDir, ServiceId),
-
-    ServicePid = efka_service:get_pid(ServiceId),
-    case is_pid(ServicePid) of
-        true ->
-            {reply, {error, <<"the service is running, stop first">>}, State};
-        false ->
-            case check_download_url(TarUrl) of
-                ok ->
-                    {ok, TaskPid} = efka_inetd_task:start_link(TaskId, ServiceRootDir, ServiceId, TarUrl),
-                    efka_inetd_task:deploy(TaskPid),
-                    lager:debug("[efka_inetd] start task_id: ~p, tar_url: ~p", [TaskId, TarUrl]),
-
-                    {reply, ok, State#state{task_map = maps:put(TaskPid, {TaskId, ServiceId}, TaskMap)}};
-                {error, Reason} ->
-                    lager:debug("[efka_inetd] check_download_url: ~p, get error: ~p", [TarUrl, Reason]),
-                    {reply, {error, <<"download url error">>}, State}
-            end
-    end;
-
-%% 启动服务: 当前服务如果正常运行，则不允许重启
-handle_call({start_service, ServiceId}, _From, State) ->
-    case efka_service:get_pid(ServiceId) of
-        undefined ->
-            case efka_service_sup:start_service(ServiceId) of
-                {ok, _} ->
-                    %% 更新数据库状态, 状态是为了保证下次efka重启的时候，服务能够启动
-                    ok = service_model:change_status(ServiceId, 1),
-                    {reply, ok, State};
-                {error, Reason} ->
-                    {reply, {error, Reason}, State}
-            end;
-        ServicePid when is_pid(ServicePid) ->
-            {reply, {error, <<"service is running">>}, State}
-    end;
-
-%% 停止服务, 主动停止的时候会改变服务配置的status字段
-handle_call({stop_service, ServiceId}, _From, State = #state{}) ->
-    case efka_service:get_pid(ServiceId) of
-        undefined ->
-            {reply, {error, <<"service not running">>}, State};
-        ServicePid when is_pid(ServicePid) ->
-            efka_service_sup:stop_service(ServiceId),
-            %% 主动停止的服务，需要更新数据库状态, 状态是为了保证下次efka重启的时候，不自动启动服务
-            ok = service_model:change_status(ServiceId, 0),
-            {reply, ok, State}
-    end;
-
-handle_call(_Request, _From, State = #state{}) ->
-    {reply, ok, State}.
-
-%% @private
-%% @doc Handling cast messages
--spec(handle_cast(Request :: term(), State :: #state{}) ->
-    {noreply, NewState :: #state{}} |
-    {noreply, NewState :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term(), NewState :: #state{}}).
-handle_cast(_Request, State = #state{}) ->
-    {noreply, State}.
-
-%% @private
-%% @doc Handling all non call/cast messages
--spec(handle_info(Info :: timeout() | term(), State :: #state{}) ->
-    {noreply, NewState :: #state{}} |
-    {noreply, NewState :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term(), NewState :: #state{}}).
-handle_info({'EXIT', TaskPid, Reason}, State = #state{task_map = TaskMap}) ->
-    case maps:take(TaskPid, TaskMap) of
-        error ->
-            {noreply, State};
-        {{TaskId, ServiceId}, NTaskMap} ->
-            case Reason of
-                normal ->
-                    lager:debug("[efka_inetd] service_id: ~p, task_pid: ~p, exit normal", [ServiceId, TaskPid]),
-                    efka_inetd_task_log:flush(TaskId);
-                Error ->
-                    lager:notice("[efka_inetd] service_id: ~p, task_pid: ~p, exit with error: ~p", [ServiceId, TaskPid, Error]),
-                    efka_inetd_task_log:stash(TaskId, <<"task aborted">>),
-                    efka_inetd_task_log:flush(TaskId)
-            end,
-            {noreply, State#state{task_map = NTaskMap}}
-    end;
-
-handle_info(_Info, State = #state{}) ->
-    {noreply, State}.
-
-%% @private
-%% @doc This function is called by a gen_server when it is about to
-%% terminate. It should be the opposite of Module:init/1 and do any
-%% necessary cleaning up. When it returns, the gen_server terminates
-%% with Reason. The return value is ignored.
--spec(terminate(Reason :: (normal | shutdown | {shutdown, term()} | term()),
-    State :: #state{}) -> term()).
-terminate(_Reason, _State = #state{}) ->
-    ok.
-
-%% @private
-%% @doc Convert process state when code is changed
--spec(code_change(OldVsn :: term() | {down, term()}, State :: #state{},
-    Extra :: term()) ->
-    {ok, NewState :: #state{}} | {error, Reason :: term()}).
-code_change(_OldVsn, State = #state{}, _Extra) ->
-    {ok, State}.
-
-%%%===================================================================
-%%% Internal functions
-%%%===================================================================
-
--spec ensure_dirs(RootDir :: string(), ServerId :: binary()) -> {ok, ServerRootDir :: string()}.
-ensure_dirs(RootDir, ServerId) when is_list(RootDir), is_binary(ServerId) ->
-    %% 根目录
-    ServiceRootDir = RootDir ++ "/" ++ binary_to_list(ServerId) ++ "/",
-    ok = filelib:ensure_dir(ServiceRootDir),
-    {ok, ServiceRootDir}.
-
-%% 通过head请求先判定下载地址是否正确
--spec check_download_url(Url :: string() | binary()) -> ok | {error, Reason :: term()}.
-check_download_url(Url) when is_binary(Url) ->
-    check_download_url(binary_to_list(Url));
-check_download_url(Url) when is_list(Url) ->
-    SslOpts = [
-        {ssl, [
-            % 完全禁用证书验证
-            {verify, verify_none}
-        ]}
-    ],
-    case httpc:request(head, {Url, []}, SslOpts, [{sync, true}]) of
-        {ok, {{_, 200, "OK"}, _Headers, _}} ->
-            ok;
-        {error, Reason} ->
-            {error, Reason}
-    end.

apps/efka/src/efka_inetd_task.erl

@@ -1,241 +0,0 @@
-%%%-------------------------------------------------------------------
-%%% @author anlicheng
-%%% @copyright (C) 2025, <COMPANY>
-%%% @doc
-%%%
-%%% @end
-%%% Created : 07. 5月 2025 15:47
-%%%-------------------------------------------------------------------
--module(efka_inetd_task).
--author("anlicheng").
--include("efka_tables.hrl").
-
--behaviour(gen_server).
-
-%% API
--export([start_link/4]).
--export([deploy/1]).
-
-%% gen_server callbacks
--export([init/1, handle_call/3, handle_cast/2, handle_info/2, terminate/2, code_change/3]).
-
--define(SERVER, ?MODULE).
-
--record(state, {
-    service_root_dir :: string(),
-    task_id :: integer(),
-    service_id :: binary(),
-    tar_url :: binary()
-}).
-
-%%%===================================================================
-%%% API
-%%%===================================================================
-
--spec deploy(Pid :: pid()) -> no_return().
-deploy(Pid) when is_pid(Pid) ->
-    gen_server:cast(Pid, deploy).
-
-%% @doc Spawns the server and registers the local name (unique)
--spec(start_link(TaskId :: integer(), ServiceRootDir :: string(), ServiceId :: binary(), TarUrl :: binary()) ->
-    {ok, Pid :: pid()} | ignore | {error, Reason :: term()}).
-start_link(TaskId, ServiceRootDir, ServiceId, TarUrl) when is_integer(TaskId), is_list(ServiceRootDir), is_binary(ServiceId), is_binary(TarUrl) ->
-    gen_server:start_link(?MODULE, [TaskId, ServiceRootDir, ServiceId, TarUrl], []).
-
-%%%===================================================================
-%%% gen_server callbacks
-%%%===================================================================
-
-%% @private
-%% @doc Initializes the server
--spec(init(Args :: term()) ->
-    {ok, State :: #state{}} | {ok, State :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term()} | ignore).
-init([TaskId, ServiceRootDir, ServiceId, TarUrl]) ->
-    {ok, #state{task_id = TaskId, service_root_dir = ServiceRootDir, service_id = ServiceId, tar_url = TarUrl}}.
-
-%% @private
-%% @doc Handling call messages
--spec(handle_call(Request :: term(), From :: {pid(), Tag :: term()},
-    State :: #state{}) ->
-    {reply, Reply :: term(), NewState :: #state{}} |
-    {reply, Reply :: term(), NewState :: #state{}, timeout() | hibernate} |
-    {noreply, NewState :: #state{}} |
-    {noreply, NewState :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term(), Reply :: term(), NewState :: #state{}} |
-    {stop, Reason :: term(), NewState :: #state{}}).
-handle_call(_Request, _From, State = #state{}) ->
-    {reply, ok, State}.
-
-%% @private
-%% @doc Handling cast messages
--spec(handle_cast(Request :: term(), State :: #state{}) ->
-    {noreply, NewState :: #state{}} |
-    {noreply, NewState :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term(), NewState :: #state{}}).
-handle_cast(deploy, State = #state{task_id = TaskId, service_root_dir = ServiceRootDir, service_id = ServiceId, tar_url = TarUrl}) ->
-    do_deploy(TaskId, ServiceRootDir, ServiceId, TarUrl),
-    {stop, normal, State};
-handle_cast(_Request, State) ->
-    {stop, normal, State}.
-
-%% @private
-%% @doc Handling all non call/cast messages
--spec(handle_info(Info :: timeout() | term(), State :: #state{}) ->
-    {noreply, NewState :: #state{}} |
-    {noreply, NewState :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term(), NewState :: #state{}}).
-handle_info(_Info, State = #state{}) ->
-    {noreply, State}.
-
-%% @private
-%% @doc This function is called by a gen_server when it is about to
-%% terminate. It should be the opposite of Module:init/1 and do any
-%% necessary cleaning up. When it returns, the gen_server terminates
-%% with Reason. The return value is ignored.
--spec(terminate(Reason :: (normal | shutdown | {shutdown, term()} | term()),
-    State :: #state{}) -> term()).
-terminate(_Reason, _State = #state{}) ->
-    ok.
-
-%% @private
-%% @doc Convert process state when code is changed
--spec(code_change(OldVsn :: term() | {down, term()}, State :: #state{},
-    Extra :: term()) ->
-    {ok, NewState :: #state{}} | {error, Reason :: term()}).
-code_change(_OldVsn, State = #state{}, _Extra) ->
-    {ok, State}.
-
-%%%===================================================================
-%%% Internal functions
-%%%===================================================================
-
--spec do_deploy(TaskId :: integer(), ServiceRootDir :: string(), ServiceId :: binary(), TarUrl :: binary()) -> no_return().
-do_deploy(TaskId, ServiceRootDir, ServiceId, TarUrl) when is_integer(TaskId), is_list(ServiceRootDir), is_binary(ServiceId), is_binary(TarUrl) ->
-    case download(binary_to_list(TarUrl), ServiceRootDir) of
-        {ok, TarFile, CostTs} ->
-            Log = io_lib:format("download: ~p completed, cost time: ~p(ms)", [binary_to_list(TarUrl), CostTs]),
-            efka_inetd_task_log:stash(TaskId, list_to_binary(Log)),
-
-            %% 创建工作目录
-            WorkDir = ServiceRootDir ++ "/work_dir/",
-            case filelib:ensure_dir(WorkDir) of
-                ok ->
-                    %% 清理目录下的文件
-                    catch delete_directory(WorkDir),
-                    case tar_extract(TarFile, WorkDir) of
-                        ok ->
-                            %% 更新数据
-                            ok = service_model:insert(#service{
-                                service_id = ServiceId,
-                                tar_url = TarUrl,
-                                %% 工作目录
-                                root_dir = ServiceRootDir,
-                                config_json = <<"">>,
-                                %% 状态： 0: 停止, 1: 运行中
-                                status = 0
-                            }),
-                            efka_inetd_task_log:stash(TaskId, <<"deploy success">>);
-                        {error, Reason} ->
-                            TarLog = io_lib:format("tar decompression: ~p, error: ~p", [filename:basename(TarFile), Reason]),
-                            efka_inetd_task_log:stash(TaskId, list_to_binary(TarLog))
-                    end;
-                {error, Reason} ->
-                    DownloadLog = io_lib:format("make work_dir error: ~p", [Reason]),
-                    efka_inetd_task_log:stash(TaskId, list_to_binary(DownloadLog))
-            end;
-        {error, Reason} ->
-            DownloadLog = io_lib:format("download: ~p, error: ~p", [binary_to_list(TarUrl), Reason]),
-            efka_inetd_task_log:stash(TaskId, list_to_binary(DownloadLog))
-    end.
-
-%% 递归删除目录下的问题
--spec delete_directory(string()) -> ok | {error, term()}.
-delete_directory(Dir) when is_list(Dir) ->
-    % 递归删除目录内容
-    case file:list_dir(Dir) of
-        {ok, Files} ->
-            lists:foreach(fun(File) ->
-                FullPath = filename:join(Dir, File),
-                case filelib:is_dir(FullPath) of
-                    true ->
-                        delete_directory(FullPath);
-                    false ->
-                        file:delete(FullPath)
-                end
-                          end, Files),
-            % 删除空目录
-            file:del_dir(Dir);
-        {error, enoent} ->
-            ok;
-        {error, Reason} ->
-            {error, Reason}
-    end.
-
-%% 解压文件到指定目录
--spec tar_extract(string(), string()) -> ok | {error, term()}.
-tar_extract(TarFile, TargetDir) when is_list(TarFile), is_list(TargetDir) ->
-    %% 判断文件的后缀名来判断, options: verbose
-    erl_tar:extract(TarFile, [compressed, {cwd, TargetDir}]).
-
-%% 下载文件
--spec download(Url :: string(), TargetDir :: string()) ->
-    {ok, TarFile :: string(), CostTs :: integer()} | {error, Reason :: term()}.
-download(Url, TargetDir) when is_list(Url), is_list(TargetDir) ->
-    SslOpts = [
-        {ssl, [
-            % 完全禁用证书验证
-            {verify, verify_none}
-        ]}
-    ],
-
-    TargetFile = get_filename_from_url(Url),
-    FullFilename = TargetDir ++ TargetFile,
-
-    StartTs = os:timestamp(),
-    case httpc:request(get, {Url, []}, SslOpts, [{sync, false}, {stream, self}]) of
-        {ok, RequestId} ->
-            case receive_data(RequestId, FullFilename) of
-                ok ->
-                    EndTs = os:timestamp(),
-                    %% 计算操作的时间，单位为毫秒
-                    CostMs = timer:now_diff(EndTs, StartTs) div 1000,
-                    {ok, FullFilename, CostMs};
-                {error, Reason} ->
-                    %% 出错需要删除掉文件
-                    file:delete(FullFilename),
-                    {error, Reason}
-            end;
-        {error, Reason} ->
-            {error, Reason}
-    end.
-
-%% 处理头部信息, 解析可能的文件名
-receive_data(RequestId, FullFilename) ->
-    receive
-        {http, {RequestId, stream_start, _Headers}} ->
-            {ok, File} = file:open(FullFilename, [write, binary]),
-            receive_data0(RequestId, File);
-        {http, {RequestId, {{_, 404, Status}, _Headers, Body}}} ->
-            lager:debug("[efka_downloader] http_status: ~p, body: ~p", [Status, Body]),
-            {error, Status}
-    end.
-%% 接受文件数据
-receive_data0(RequestId, File) ->
-    receive
-        {http, {RequestId, {error, Reason}}} ->
-            ok = file:close(File),
-            {error, Reason};
-        {http, {RequestId, stream_end, _Headers}} ->
-            ok = file:close(File),
-            ok;
-        {http, {RequestId, stream, Data}} ->
-            file:write(File, Data),
-            receive_data0(RequestId, File)
-    end.
-
--spec get_filename_from_url(Url :: string()) -> string().
-get_filename_from_url(Url) when is_list(Url) ->
-    URIMap = uri_string:parse(Url),
-    Path = maps:get(path, URIMap),
-    filename:basename(Path).

apps/efka/src/efka_logger.erl

@@ -0,0 +1,175 @@
+%%%-------------------------------------------------------------------
+%%% @author aresei
+%%% @copyright (C) 2023, <COMPANY>
+%%% @doc
+%%%
+%%% @end
+%%% Created : 07. 9月 2023 17:07
+%%%-------------------------------------------------------------------
+-module(efka_logger).
+-author("aresei").
+
+-behaviour(gen_server).
+
+%% API
+-export([start_link/1, write/1, write_lines/1]).
+
+%% gen_server callbacks
+-export([init/1, handle_call/3, handle_cast/2, handle_info/2, terminate/2, code_change/3]).
+
+-define(SERVER, ?MODULE).
+
+-record(state, {
+    file_name :: string(),
+    date :: calendar:date(),
+    file
+}).
+
+%%%===================================================================
+%%% API
+%%%===================================================================
+
+-spec write(Data :: binary()) -> no_return().
+write(Data) when is_binary(Data) ->
+    gen_server:cast(?SERVER, {write, Data}).
+
+write_lines(Lines) when is_list(Lines) ->
+    gen_server:cast(?SERVER, {write_lines, Lines}).
+
+%% @doc Spawns the server and registers the local name (unique)
+-spec(start_link(FileName :: string()) ->
+    {ok, Pid :: pid()} | ignore | {error, Reason :: term()}).
+start_link(FileName) when is_list(FileName) ->
+    gen_server:start_link({local, ?SERVER}, ?MODULE, [FileName], []).
+
+%%%===================================================================
+%%% gen_server callbacks
+%%%===================================================================
+
+%% @private
+%% @doc Initializes the server
+-spec(init(Args :: term()) ->
+    {ok, State :: #state{}} | {ok, State :: #state{}, timeout() | hibernate} |
+    {stop, Reason :: term()} | ignore).
+init([FileName]) ->
+    ensure_dir(),
+    FilePath = make_file(FileName),
+    {ok, File} = file:open(FilePath, [append, binary]),
+
+    {ok, #state{file = File, file_name = FileName, date = get_date()}}.
+
+%% @private
+%% @doc Handling call messages
+-spec(handle_call(Request :: term(), From :: {pid(), Tag :: term()},
+    State :: #state{}) ->
+    {reply, Reply :: term(), NewState :: #state{}} |
+    {reply, Reply :: term(), NewState :: #state{}, timeout() | hibernate} |
+    {noreply, NewState :: #state{}} |
+    {noreply, NewState :: #state{}, timeout() | hibernate} |
+    {stop, Reason :: term(), Reply :: term(), NewState :: #state{}} |
+    {stop, Reason :: term(), NewState :: #state{}}).
+handle_call(_Request, _From, State = #state{}) ->
+    {reply, ok, State}.
+
+%% @private
+%% @doc Handling cast messages
+-spec(handle_cast(Request :: term(), State :: #state{}) ->
+    {noreply, NewState :: #state{}} |
+    {noreply, NewState :: #state{}, timeout() | hibernate} |
+    {stop, Reason :: term(), NewState :: #state{}}).
+handle_cast({write, Data}, State = #state{file = OldFile, file_name = FileName, date = Date}) ->
+    Line = <<(time_prefix())/binary, " ", (format(Data))/binary, $\n>>,
+    case maybe_new_file(Date) of
+        true ->
+            file:close(OldFile),
+
+            FilePath = make_file(FileName),
+            {ok, File} = file:open(FilePath, [append, binary]),
+            ok = file:write(File, Line),
+            {noreply, State#state{file = File, date = get_date()}};
+        false ->
+            ok = file:write(OldFile, Line),
+            {noreply, State}
+    end;
+handle_cast({write_lines, Lines}, State = #state{file = OldFile, file_name = FileName, date = Date}) ->
+    Data = iolist_to_binary(lists:join(<<$\n>>, Lines)),
+    case maybe_new_file(Date) of
+        true ->
+            file:close(OldFile),
+
+            FilePath = make_file(FileName),
+            {ok, File} = file:open(FilePath, [append, binary]),
+            ok = file:write(File, Data),
+            {noreply, State#state{file = File, date = get_date()}};
+        false ->
+            ok = file:write(OldFile, Data),
+            {noreply, State}
+    end.
+
+%% @private
+%% @doc Handling all non call/cast messages
+-spec(handle_info(Info :: timeout() | term(), State :: #state{}) ->
+    {noreply, NewState :: #state{}} |
+    {noreply, NewState :: #state{}, timeout() | hibernate} |
+    {stop, Reason :: term(), NewState :: #state{}}).
+handle_info(_Info, State = #state{}) ->
+    {noreply, State}.
+
+%% @private
+%% @doc This function is called by a gen_server when it is about to
+%% terminate. It should be the opposite of Module:init/1 and do any
+%% necessary cleaning up. When it returns, the gen_server terminates
+%% with Reason. The return value is ignored.
+-spec(terminate(Reason :: (normal | shutdown | {shutdown, term()} | term()),
+    State :: #state{}) -> term()).
+terminate(_Reason, _State = #state{}) ->
+    ok.
+
+%% @private
+%% @doc Convert process state when code is changed
+-spec(code_change(OldVsn :: term() | {down, term()}, State :: #state{},
+    Extra :: term()) ->
+    {ok, NewState :: #state{}} | {error, Reason :: term()}).
+code_change(_OldVsn, State = #state{}, _Extra) ->
+    {ok, State}.
+
+%%%===================================================================
+%%% Internal functions
+%%%===================================================================
+
+format(Data) when is_binary(Data) ->
+    iolist_to_binary(Data);
+format(Items) when is_list(Items) ->
+    iolist_to_binary(lists:join(<<"\t">>, Items)).
+
+time_prefix() ->
+    {{Y, M, D}, {H, I, S}} = calendar:local_time(),
+    iolist_to_binary(io_lib:format("[~b-~2..0b-~2..0b ~2..0b:~2..0b:~2..0b]", [Y, M, D, H, I, S])).
+
+-spec make_file(LogFile :: string()) -> string().
+make_file(LogFile) when is_list(LogFile) ->
+    {Year, Month, Day} = erlang:date(),
+    Suffix = io_lib:format("~b~2..0b~2..0b", [Year, Month, Day]),
+    RootDir = code:root_dir() ++ "/log/",
+    lists:flatten(RootDir ++ LogFile ++ "." ++ Suffix).
+
+ensure_dir() ->
+    RootDir = code:root_dir() ++ "/log/",
+    case filelib:is_dir(RootDir) of
+        true ->
+            ok;
+        false ->
+            file:make_dir(RootDir)
+    end.
+
+%% 获取日期信息
+-spec get_date() -> Date :: calendar:date().
+get_date() ->
+    {Date, _} = calendar:local_time(),
+    Date.
+
+%% 通过日志判断是否需要生成新的日志文件
+-spec maybe_new_file(Date :: calendar:date()) -> boolean().
+maybe_new_file({Y, M, D}) ->
+    {{Y0, M0, D0}, _} = calendar:local_time(),
+    not (Y =:= Y0 andalso M =:= M0 andalso D =:= D0).

apps/efka/src/efka_manifest.erl

@@ -1,124 +0,0 @@
-%%%-------------------------------------------------------------------
-%%% @author anlicheng
-%%% @copyright (C) 2025, <COMPANY>
-%%% @doc
-%%% 用于管理manifest.json配置文件
-%%% @end
-%%% Created : 05. 5月 2025 22:39
-%%%-------------------------------------------------------------------
--module(efka_manifest).
--author("anlicheng").
-
--record(manifest, {
-    work_dir = "" :: string(),
-    id = <<"">> :: binary(),
-    exec = <<"">>:: binary(),
-    args = [],
-    health_check = <<"">>
-}).
-
--type manifest() :: #manifest{}.
-
--export_type([manifest/0]).
-
-%% API
--export([new/1, startup/1]).
-
--spec new(ServiceRootDir :: string()) -> {ok, #manifest{}} | {error, Reason :: binary()}.
-new(ServiceRootDir) when is_list(ServiceRootDir) ->
-    WorkDir = ServiceRootDir ++ "/work_dir/",
-    case file:read_file(WorkDir ++ "manifest.json") of
-        {ok, ManifestInfo} ->
-            Settings = catch jiffy:decode(ManifestInfo, [return_maps]),
-            case check_manifest(Settings) of
-                {ok, Manifest} ->
-                    {ok, Manifest#manifest{work_dir = WorkDir}};
-                {error, Reason} ->
-                    {error, Reason}
-            end;
-        {error, Reason} ->
-            {error, Reason}
-    end.
-
--spec startup(Manifest :: #manifest{}) -> {ok, Port :: port()} | {error, Reason :: binary()}.
-startup(#manifest{id = Id, work_dir = WorkDir, exec = ExecCmd0, args = Args0}) ->
-    PortSettings = [
-        {cd, WorkDir},
-        {args, [binary_to_list(A) || A <- Args0]},
-        exit_status
-    ],
-    ExecCmd = binary_to_list(ExecCmd0),
-    RealExecCmd = filename:absname_join(WorkDir, ExecCmd),
-    lager:debug("[efka_manifest] service_id: ~p, real command is: ~p", [Id, RealExecCmd]),
-    case catch erlang:open_port({spawn_executable, RealExecCmd}, PortSettings) of
-        Port when is_port(Port) ->
-            {ok, Port};
-        _Other ->
-            {error, <<"exec command startup failed">>}
-    end.
-
-%% 检查配置是否合法
--spec check_manifest(Manifest :: map()) -> {ok, #manifest{}} | {error, Reason :: binary()}.
-check_manifest(Manifest) when is_map(Manifest) ->
-    RequiredKeys = [<<"id">>, <<"exec">>, <<"args">>, <<"health_check">>],
-    check_manifest0(RequiredKeys, Manifest, #manifest{});
-check_manifest(_Manifest) ->
-    {error, <<"invalid manifest json">>}.
-
-check_manifest0([], _Settings, Manifest) ->
-    {ok, Manifest};
-check_manifest0([<<"id">>|T], Settings, Manifest) ->
-    case maps:find(<<"id">>, Settings) of
-        error ->
-            {error, <<"miss service_id">>};
-        {ok, Id} when is_binary(Id) ->
-            check_manifest0(T, Settings, Manifest#manifest{id = Id});
-        {ok, _} ->
-            {error, <<"service_id is not string">>}
-    end;
-check_manifest0([<<"health_check">>|T], Settings, Manifest) ->
-    case maps:find(<<"health_check">>, Settings) of
-        error ->
-            {error, <<"miss health_check">>};
-        {ok, Url} when is_binary(Url) ->
-            case is_url(Url) of
-                true ->
-                    check_manifest0(T, Settings, Manifest#manifest{health_check = Url});
-                false ->
-                    {error, <<"health_check is not a invalid url">>}
-            end;
-        {ok, _} ->
-            {error, <<"health_check is not string">>}
-    end;
-check_manifest0([<<"exec">>|T], Settings, Manifest) ->
-    case maps:find(<<"exec">>, Settings) of
-        error ->
-            {error, <<"miss start">>};
-        {ok, Exec} when is_binary(Exec) ->
-            %% 不能包含空格
-            case binary:match(Exec, <<" ">>) of
-                nomatch ->
-                    check_manifest0(T, Settings, Manifest#manifest{exec = Exec});
-                _ ->
-                    {error, <<"start cmd cannot contain args">>}
-            end
-    end;
-check_manifest0([<<"args">>|T], Settings, Manifest) ->
-    case maps:find(<<"args">>, Settings) of
-        error ->
-            check_manifest0(T, Settings, Manifest#manifest{args = []});
-        %% 对参数项目不进行检查
-        {ok, Args} when is_list(Args) ->
-            check_manifest0(T, Settings, Manifest#manifest{args = Args});
-        {ok, _} ->
-            {error, <<"args must be list">>}
-    end.
-
--spec is_url(binary()) -> boolean().
-is_url(Input) when is_binary(Input) ->
-    try
-        uri_string:parse(Input),
-        true
-    catch
-        _:_ -> false
-    end.

apps/efka/src/efka_monitor.erl

@@ -1,25 +0,0 @@
-%%%-------------------------------------------------------------------
-%%% @author anlicheng
-%%% @copyright (C) 2025, <COMPANY>
-%%% @doc
-%%%
-%%% @end
-%%% Created : 03. 6月 2025 14:09
-%%%-------------------------------------------------------------------
--module(efka_monitor).
--author("anlicheng").
-
-%% API
--export([]).
-
-%% API
--export([memory_top/1, cpu_top/1, stop/0]).
-
-memory_top(Interval) when is_integer(Interval) ->
-    spawn(fun()->etop:start([{output, text}, {interval, Interval}, {lines, 20}, {sort, memory}])end).
-
-cpu_top(Interval) when is_integer(Interval) ->
-    spawn(fun()->etop:start([{output, text}, {interval, Interval}, {lines, 20}, {sort, runtime}])end).
-
-stop() ->
-    etop:stop().

apps/efka/src/efka_remote_agent.erl

@@ -0,0 +1,390 @@
+%%%-------------------------------------------------------------------
+%%% @author anlicheng
+%%% @copyright (C) 2025, <COMPANY>
+%%% @doc
+%%%
+%%% @end
+%%% Created : 21. 5月 2025 18:38
+%%%-------------------------------------------------------------------
+-module(efka_remote_agent).
+-author("anlicheng").
+-include("message.hrl").
+-include("efka_tables.hrl").
+
+-behaviour(gen_statem).
+
+%% API
+-export([start_link/0]).
+-export([metric_data/2, ping/13, task_event_stream/3, close_task_event_stream/2]).
+
+%% gen_statem callbacks
+-export([init/1, handle_event/4, terminate/3, code_change/4, callback_mode/0]).
+
+-define(SERVER, ?MODULE).
+
+%% 标记当前agent的状态，只有在 activated 状态下才可以正常的发送数据
+-define(STATE_DENIED, denied).
+-define(STATE_CONNECTING, connecting).
+-define(STATE_AUTH, auth).
+%% 不能推送消息到服务，但是可以接受服务器的部分指令
+-define(STATE_RESTRICTED, restricted).
+%% 激活状态下
+-define(STATE_ACTIVATED, activated).
+
+-record(state, {
+    transport_pid :: undefined | pid(),
+    transport_ref :: undefined | reference()
+}).
+
+%%%===================================================================
+%%% API
+%%%===================================================================
+
+%% 发送数据
+-spec metric_data(RouteKey :: binary(), Metric :: binary()) -> no_return().
+metric_data(RouteKey, Metric) when is_binary(RouteKey), is_binary(Metric) ->
+    gen_statem:cast(?SERVER, {metric_data, RouteKey, Metric}).
+
+-spec task_event_stream(TaskId :: integer(), Type :: binary(), Stream :: binary()) -> no_return().
+task_event_stream(TaskId, Type, Stream) when is_integer(TaskId), is_binary(Type), is_binary(Stream) ->
+    gen_statem:cast(?SERVER, {task_event_stream, TaskId, Type, Stream}).
+
+-spec close_task_event_stream(TaskId :: integer(), Reason :: binary()) -> no_return().
+close_task_event_stream(TaskId, Reason) when is_integer(TaskId), is_binary(Reason) ->
+    gen_statem:cast(?SERVER, {close_task_event_stream, TaskId, Reason}).
+
+ping(AdCode, BootTime, Province, City, EfkaVersion, KernelArch, Ips, CpuCore, CpuLoad, CpuTemperature, Disk, Memory, Interfaces) ->
+    gen_statem:cast(?SERVER, {ping, AdCode, BootTime, Province, City, EfkaVersion, KernelArch, Ips, CpuCore, CpuLoad, CpuTemperature, Disk, Memory, Interfaces}).
+
+%% @doc Creates a gen_statem process which calls Module:init/1 to
+%% initialize. To ensure a synchronized start-up procedure, this
+%% function does not return until Module:init/1 has returned.
+start_link() ->
+    gen_statem:start_link({local, ?SERVER}, ?MODULE, [], []).
+
+%%%===================================================================
+%%% gen_statem callbacks
+%%%===================================================================
+
+%% @private
+%% @doc Whenever a gen_statem is started using gen_statem:start/[3,4] or
+%% gen_statem:start_link/[3,4], this function is called by the new
+%% process to initialize.
+init([]) ->
+    erlang:start_timer(0, self(), create_transport),
+    {ok, ?STATE_DENIED, #state{}}.
+
+%% @private
+%% @doc This function is called by a gen_statem when it needs to find out
+%% the callback mode of the callback module.
+callback_mode() ->
+    handle_event_function.
+
+%% @private
+%% @doc If callback_mode is handle_event_function, then whenever a
+%% gen_statem receives an event from call/2, cast/2, or as a normal
+%% process message, this function is called.
+
+%% 异步发送数据, 连接存在时候直接发送；否则缓存到mnesia
+handle_event(cast, {metric_data, RouteKey, Metric}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
+    Packet = message_codec:encode(?MESSAGE_DATA, #data{
+        route_key = RouteKey,
+        metric = Metric
+    }),
+    efka_transport:send(TransportPid, Packet),
+    {keep_state, State};
+
+handle_event(cast, {metric_data, RouteKey, Metric}, _, State) ->
+    Packet = message_codec:encode(?MESSAGE_DATA, #data{
+        route_key = RouteKey,
+        metric = Metric
+    }),
+    ok = cache_model:insert(Packet),
+    {keep_state, State};
+
+handle_event(cast, {task_event_stream, TaskId, Type, Stream}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
+    lager:debug("[efka_remote_agent] event_stream task_id: ~p, stream: ~ts", [TaskId, Stream]),
+    EventPacket = message_codec:encode(?MESSAGE_EVENT_STREAM, #task_event_stream{
+        task_id = TaskId,
+        type = Type,
+        stream = Stream
+    }),
+    efka_transport:send(TransportPid, EventPacket),
+    {keep_state, State};
+
+handle_event(cast, {close_task_event_stream, TaskId, Reason}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
+    EventPacket = message_codec:encode(?MESSAGE_EVENT_STREAM, #task_event_stream{
+        task_id = TaskId,
+        type = <<"close">>,
+        stream = Reason
+    }),
+    efka_transport:send(TransportPid, EventPacket),
+    {keep_state, State};
+
+%% 其他情况下直接忽略
+handle_event(cast, {task_event_stream, _TaskId, _Stream}, _, State = #state{}) ->
+    {keep_state, State};
+
+%handle_event(cast, {ping, AdCode, BootTime, Province, City, EfkaVersion, KernelArch, Ips, CpuCore, CpuLoad, CpuTemperature, Disk, Memory, Interfaces}, ?STATE_ACTIVATED,
+%    State = #state{transport_pid = TransportPid}) ->
+%
+%    Ping = message_pb:encode_msg(#ping{
+%        adcode = AdCode,
+%        boot_time = BootTime,
+%        province = Province,
+%        city = City,
+%        efka_version = EfkaVersion,
+%        kernel_arch = KernelArch,
+%        ips = Ips,
+%        cpu_core = CpuCore,
+%        cpu_load = CpuLoad,
+%        cpu_temperature = CpuTemperature,
+%        disk = Disk,
+%        memory = Memory,
+%        interfaces = Interfaces
+%    }),
+%    efka_transport:send(TransportPid, ?METHOD_PING, Ping),
+%    {keep_state, State};
+
+%% 异步建立到服务器的连接
+handle_event(info, {timeout, _, create_transport}, ?STATE_DENIED, State) ->
+    {ok, Props} = application:get_env(efka, tls_server),
+    Host = proplists:get_value(host, Props),
+    Port = proplists:get_value(port, Props),
+    {ok, {TransportPid, TransportRef}} = efka_transport:start_monitor(self(), Host, Port),
+    efka_transport:connect(TransportPid),
+
+    {next_state, ?STATE_CONNECTING, State#state{transport_pid = TransportPid, transport_ref = TransportRef}};
+
+handle_event(info, {connect_reply, Reply}, ?STATE_CONNECTING, State = #state{transport_pid = TransportPid}) ->
+    case Reply of
+        ok ->
+            AuthBin = auth_request(),
+            efka_transport:auth_request(TransportPid, AuthBin),
+            {next_state, ?STATE_AUTH, State};
+        {error, Reason} ->
+            lager:debug("[efka_remote_agent] connect failed, error: ~p, pid: ~p", [Reason, TransportPid]),
+            efka_transport:stop(TransportPid),
+            {next_state, ?STATE_DENIED, State#state{transport_pid = undefined}}
+    end;
+
+handle_event(info, {auth_reply, Reply}, ?STATE_AUTH, State = #state{transport_pid = TransportPid}) ->
+    case Reply of
+        {ok, #auth_reply{code = Code, payload = Message}} ->
+            case Code of
+                0 ->
+                    lager:debug("[efka_remote_agent] auth success, message: ~p", [Message]),
+                    {next_state, ?STATE_ACTIVATED, State, [{next_event, info, flush_cache}]};
+                1 ->
+                    %% 主机在后台的授权未通过；此时agent不能推送数据给云端服务器，但是云端服务器可以推送命令给agent
+                    %% socket的连接状态需要维持
+                    lager:debug("[efka_remote_agent] auth denied, message: ~p", [Message]),
+                    {next_state, ?STATE_RESTRICTED, State};
+                2 ->
+                    % 其他类型的错误，需要间隔时间重试
+                    lager:debug("[efka_remote_agent] auth failed, message: ~p", [Message]),
+                    efka_transport:stop(TransportPid),
+                    {next_state, ?STATE_DENIED, State#state{transport_pid = undefined}};
+                _ ->
+                    % 其他类型的错误，需要间隔时间重试
+                    lager:debug("[efka_remote_agent] auth failed, invalid message"),
+                    efka_transport:stop(TransportPid),
+                    {next_state, ?STATE_DENIED, State#state{transport_pid = undefined}}
+            end;
+        {error, Reason} ->
+            lager:debug("[efka_remote_agent] auth_request failed, error: ~p", [Reason]),
+            efka_transport:stop(TransportPid),
+            {next_state, ?STATE_DENIED, State#state{transport_pid = undefined}}
+    end;
+
+%% 将缓存中的数据推送到服务器端
+handle_event(info, flush_cache, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
+    case cache_model:fetch_next() of
+        {ok, {Id, Packet}} ->
+            efka_transport:send(TransportPid, Packet),
+            cache_model:delete(Id),
+            {keep_state, State, [{next_event, info, flush_cache}]};
+        error ->
+            {keep_state, State}
+    end;
+handle_event(info, flush_cache, _, State) ->
+    {keep_state, State};
+
+%% 云端服务器推送了消息
+%% 激活消息
+
+%% 微服务部署
+handle_event(info, {server_rpc, PacketId, #jsonrpc_request{method = <<"get_containers">>}}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
+    %% 短暂的等待，efka_inetd收到消息后就立即返回了
+    case docker_manager:get_containers() of
+        {ok, Containers} ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_success(Containers));
+        {error, Reason} when is_binary(Reason) ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_error(-1, Reason))
+    end,
+    {keep_state, State};
+
+%% 微服务部署
+handle_event(info, {server_rpc, PacketId, #jsonrpc_request{method = <<"deploy">>, params = Params}}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
+    #{<<"task_id">> := TaskId, <<"config">> := Config} = Params,
+    %% 短暂的等待，efka_inetd收到消息后就立即返回了
+    case docker_manager:deploy(TaskId, Config) of
+        ok ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_success(<<"ok">>));
+        {error, Reason} when is_binary(Reason) ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_error(-1, Reason))
+    end,
+    {keep_state, State};
+
+%% 启动微服务
+handle_event(info, {server_rpc, PacketId, #jsonrpc_request{method = <<"start_container">>, params = Params}}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
+    #{<<"container_name">> := ContainerName} = Params,
+    %% 短暂的等待，efka_inetd收到消息后就立即返回了
+    case docker_manager:start_container(ContainerName) of
+        ok ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_success(<<"ok">>));
+        {error, Reason} when is_binary(Reason) ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_error(-1, Reason))
+    end,
+    {keep_state, State};
+
+%% 停止微服务
+handle_event(info, {server_rpc, PacketId, #jsonrpc_request{method = <<"stop_container">>, params = Params}}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
+    #{<<"container_name">> := ContainerName} = Params,
+    %% 短暂的等待，efka_inetd收到消息后就立即返回了
+    case docker_manager:stop_container(ContainerName) of
+        ok ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_success(<<"ok">>));
+        {error, Reason} when is_binary(Reason) ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_error(-1, Reason))
+    end,
+    {keep_state, State};
+
+handle_event(info, {server_rpc, PacketId, #jsonrpc_request{method = <<"kill_container">>, params = Params}}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
+    #{<<"container_name">> := ContainerName} = Params,
+    %% 短暂的等待，efka_inetd收到消息后就立即返回了
+    case docker_manager:kill_container(ContainerName) of
+        ok ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_success(<<"ok">>));
+        {error, Reason} when is_binary(Reason) ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_error(-1, Reason))
+    end,
+    {keep_state, State};
+
+handle_event(info, {server_rpc, PacketId, #jsonrpc_request{method = <<"remove_container">>, params = Params}}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
+    #{<<"container_name">> := ContainerName} = Params,
+    %% 短暂的等待，efka_inetd收到消息后就立即返回了
+    case docker_manager:remove_container(ContainerName) of
+        ok ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_success(<<"ok">>));
+        {error, Reason} when is_binary(Reason) ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_error(-1, Reason))
+    end,
+    {keep_state, State};
+
+%% config.json配置信息
+handle_event(info, {server_rpc, PacketId, #jsonrpc_request{method = <<"config_container">>, params = Params}}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
+    #{<<"container_name">> := ContainerName, <<"config">> := Config} = Params,
+    case docker_manager:config_container(ContainerName, Config) of
+        ok ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_success(<<"ok">>));
+        {error, Reason} ->
+            efka_transport:rpc_reply(TransportPid, PacketId, reply_error(-1, Reason))
+    end,
+    {keep_state, State};
+
+%% 处理task_log
+%handle_event(info, {server_async_call, PacketId, <<?PUSH_TASK_LOG:8, TaskLogBin/binary>>}, ?STATE_ACTIVATED, State = #state{transport_pid = TransportPid}) ->
+%    #fetch_task_log{task_id = TaskId} = message_pb:decode_msg(TaskLogBin, fetch_task_log),
+%    lager:debug("[efka_remote_agent] get task_log request: ~p", [TaskId]),
+%    {ok, Logs} = efka_inetd_task_log:get_logs(TaskId),
+%    Reply = case length(Logs) > 0 of
+%                true ->
+%                    Result = iolist_to_binary(jiffy:encode(Logs, [force_utf8])),
+%                    #async_call_reply{code = 1, result = Result};
+%                false ->
+%                    #async_call_reply{code = 1, result = <<"[]">>}
+%            end,
+%    efka_transport:async_call_reply(TransportPid, PacketId, message_pb:encode_msg(Reply)),
+%
+%    {keep_state, State};
+
+%% 处理命令
+handle_event(info, {server_cast, #command{command_type = ?COMMAND_AUTH, command = Auth0}}, StateName, State = #state{transport_pid = TransportPid}) ->
+    Auth = binary_to_integer(Auth0),
+    case {Auth, StateName} of
+        {1, ?STATE_ACTIVATED} ->
+            {keep_state, State};
+        {1, ?STATE_DENIED} ->
+            %% 重新激活, 需要重新校验
+            AuthRequestBin = auth_request(),
+            efka_transport:auth_request(TransportPid, AuthRequestBin),
+            {next_state, ?STATE_AUTH, State};
+        {0, _} ->
+            %% 这个时候的主机应该是受限制的状态，不允许发送消息；但是能够接受服务器推送的消息
+            {next_state, ?STATE_RESTRICTED, State}
+    end;
+
+%% 处理Pub/Sub机制
+handle_event(info, {server_cast, #pub{topic = Topic, qos = Qos, content = Content}}, ?STATE_ACTIVATED, State) ->
+    lager:debug("[efka_remote_agent] get pub topic: ~p, qos: ~p, content: ~p", [Topic, Qos, Content]),
+    %% 消息发送到订阅系统
+    efka_subscription:publish(Topic, Qos, Content),
+    {keep_state, State};
+
+%% transport进程退出
+handle_event(info, {'DOWN', MRef, process, TransportPid, Reason}, _, State = #state{transport_ref = MRef}) ->
+    lager:debug("[efka_remote_agent] transport pid: ~p, exit with reason: ~p", [TransportPid, Reason]),
+    erlang:start_timer(5000, self(), create_transport),
+    {next_state, ?STATE_DENIED, State#state{transport_pid = undefined, transport_ref = undefined}}.
+
+%% @private
+%% @doc This function is called by a gen_statem when it is about to
+%% terminate. It should be the opposite of Module:init/1 and do any
+%% necessary cleaning up. When it returns, the gen_statem terminates with
+%% Reason. The return value is ignored.
+terminate(_Reason, _StateName, _State = #state{transport_pid = TransportPid}) ->
+    case is_pid(TransportPid) andalso is_process_alive(TransportPid) of
+        true ->
+            efka_transport:stop(TransportPid);
+        false ->
+            ok
+    end,
+    ok.
+
+%% @private
+%% @doc Convert process state when code is changed
+code_change(_OldVsn, StateName, State = #state{}, _Extra) ->
+    {ok, StateName, State}.
+
+%%%===================================================================
+%%% Internal functions
+%%%===================================================================
+
+-spec auth_request() -> binary().
+auth_request() ->
+    {ok, AuthInfo} = application:get_env(efka, auth),
+    UUID = proplists:get_value(uuid, AuthInfo),
+    Username = proplists:get_value(username, AuthInfo),
+    Salt = proplists:get_value(salt, AuthInfo),
+    Token = proplists:get_value(token, AuthInfo),
+
+    message_codec:encode(?MESSAGE_AUTH_REQUEST, #auth_request{
+        uuid = unicode:characters_to_binary(UUID),
+        username = unicode:characters_to_binary(Username),
+        salt = unicode:characters_to_binary(Salt),
+        token = unicode:characters_to_binary(Token),
+        timestamp = efka_util:timestamp()
+    }).
+
+-spec reply_success(Result :: any()) -> binary().
+reply_success(Result) ->
+    message_codec:encode(?MESSAGE_JSONRPC_REPLY, #jsonrpc_reply{result = Result}).
+
+-spec reply_error(Code :: integer(), Message :: binary()) -> binary().
+reply_error(Code, Message) when is_integer(Code), is_binary(Message) ->
+    Error = #{
+        <<"code">> => Code,
+        <<"message">> => Message
+    },
+    message_codec:encode(?MESSAGE_JSONRPC_REPLY, #jsonrpc_reply{error = Error}).

apps/efka/src/efka_service.erl

@@ -17,7 +17,6 @@
 %% API
 -export([start_link/2]).
 -export([get_name/1, get_pid/1, attach_channel/2]).
--export([push_config/3, request_config/1, invoke/3]).
 -export([metric_data/3, send_event/3]).
 
 %% gen_server callbacks
@@ -26,17 +25,7 @@
 -record(state, {
     service_id :: binary(),
     %% 通道id信息
-    channel_pid :: pid() | undefined,
-    %% 当前进程的port信息, OSPid = erlang:port_info(Port, os_pid)
-    port :: undefined | port(),
-    %% 系统对应的pid
-    os_pid :: undefined | integer(),
-    %% 配置信息
-    manifest :: undefined | efka_manifest:manifest(),
-    inflight = #{},
-
-    %% 映射关系: #{Ref => Fun}
-    callbacks = #{}
+    channel_pid :: pid() | undefined
 }).
 
 %%%===================================================================
@@ -51,21 +40,9 @@ get_name(ServiceId) when is_binary(ServiceId) ->
 get_pid(ServiceId) when is_binary(ServiceId) ->
     whereis(get_name(ServiceId)).
 
--spec push_config(Pid :: pid(), Ref :: reference(), ConfigJson :: binary()) -> no_return().
-push_config(Pid, Ref, ConfigJson) when is_pid(Pid), is_binary(ConfigJson) ->
-    gen_server:cast(Pid, {push_config, Ref, self(), ConfigJson}).
-
--spec invoke(Pid :: pid(), Ref :: reference(), Payload :: binary()) -> no_return().
-invoke(Pid, Ref, Payload) when is_pid(Pid), is_reference(Ref), is_binary(Payload) ->
-    gen_server:cast(Pid, {invoke, Ref, self(), Payload}).
-
--spec request_config(Pid :: pid()) -> {ok, Config :: binary()}.
-request_config(Pid) when is_pid(Pid) ->
-    gen_server:call(Pid, request_config).
-
--spec metric_data(Pid :: pid(), DeviceUUID :: binary(), Data :: binary()) -> no_return().
-metric_data(Pid, DeviceUUID, Data) when is_pid(Pid), is_binary(DeviceUUID), is_binary(Data) ->
-    gen_server:cast(Pid, {metric_data, DeviceUUID, Data}).
+-spec metric_data(Pid :: pid(), RouteKey :: binary(), Metric :: binary()) -> no_return().
+metric_data(Pid, RouteKey, Metric) when is_pid(Pid), is_binary(RouteKey),  is_binary(Metric) ->
+    gen_server:cast(Pid, {metric_data, RouteKey, Metric}).
 
 -spec send_event(Pid :: pid(), EventType :: integer(), Params :: binary()) -> no_return().
 send_event(Pid, EventType, Params) when is_pid(Pid), is_integer(EventType), is_binary(Params) ->
@@ -92,29 +69,8 @@ start_link(Name, ServiceId) when is_atom(Name), is_binary(ServiceId) ->
     {stop, Reason :: term()} | ignore).
 init([ServiceId]) ->
     %% supervisor进程通过exit(ChildPid, shutdown)调用的时候，确保terminate函数被调用
-    erlang:process_flag(trap_exit, true),
-    case service_model:get_service(ServiceId) of
-        error ->
-            lager:notice("[efka_service] service_id: ~p, not found", [ServiceId]),
-            ignore;
-        {ok, #service{root_dir = RootDir}} ->
-            %% 第一次启动，要求必须成功；只有第一次启动成功，后续的重启逻辑才有意义
-            case efka_manifest:new(RootDir) of
-                {ok, Manifest} ->
-                    case efka_manifest:startup(Manifest) of
-                        {ok, Port} ->
-                            {os_pid, OSPid} = erlang:port_info(Port, os_pid),
-                            lager:debug("[efka_service] service: ~p, port: ~p, boot_service success os_pid: ~p", [ServiceId, Port, OSPid]),
-                            {ok, #state{service_id = ServiceId, manifest = Manifest, port = Port, os_pid = OSPid}};
-                        {error, Reason} ->
-                            lager:debug("[efka_service] service: ~p, boot_service get error: ~p", [ServiceId, Reason]),
-                            {stop, Reason}
-                    end;
-                {error, Reason} ->
-                    lager:notice("[efka_service] service: ~p, read manifest.json get error: ~p", [ServiceId, Reason]),
-                    ignore
-            end
-    end.
+    lager:debug("[efka_service] service_id: ~p, started", [ServiceId]),
+    {ok, #state{service_id = ServiceId}}.
 
 %% @private
 %% @doc Handling call messages
@@ -137,15 +93,6 @@ handle_call({attach_channel, ChannelPid}, _From, State = #state{channel_pid = Ol
             {reply, {error, <<"channel exists">>}, State}
     end;
 
-%% 请求参数项 done
-handle_call(request_config, _From, State = #state{service_id = ServiceId}) ->
-    case service_model:get_config_json(ServiceId) of
-        {ok, ConfigJson} ->
-            {reply, {ok, ConfigJson}, State};
-        error ->
-            {reply, {ok, <<>>}, State}
-    end;
-
 handle_call(_Request, _From, State = #state{}) ->
     {reply, ok, State}.
 
@@ -155,40 +102,11 @@ handle_call(_Request, _From, State = #state{}) ->
     {noreply, NewState :: #state{}} |
     {noreply, NewState :: #state{}, timeout() | hibernate} |
     {stop, Reason :: term(), NewState :: #state{}}).
-handle_cast({metric_data, DeviceUUID, LineProtocolData}, State = #state{service_id = ServiceId}) ->
-    lager:debug("[efka_service] metric_data service_id: ~p, device_uuid: ~p, metric data: ~p", [ServiceId, DeviceUUID, LineProtocolData]),
-    efka_agent:metric_data(ServiceId, DeviceUUID, LineProtocolData),
+handle_cast({metric_data, RouteKey, Metric}, State = #state{service_id = ServiceId}) ->
+    lager:debug("[efka_service] metric_data service_id: ~p, route_key: ~p, metric data: ~p", [ServiceId, RouteKey, Metric]),
+    efka_remote_agent:metric_data(RouteKey, Metric),
     {noreply, State};
 
-handle_cast({send_event, EventType, Params}, State = #state{service_id = ServiceId}) ->
-    efka_agent:event(ServiceId, EventType, Params),
-    lager:debug("[efka_service] send_event, service_id: ~p, event_type: ~p, params: ~p", [ServiceId, EventType, Params]),
-    {noreply, State};
-
-%% 推送配置项目
-handle_cast({push_config, Ref, ReceiverPid, ConfigJson}, State = #state{channel_pid = ChannelPid, service_id = ServiceId, inflight = Inflight, callbacks = Callbacks}) ->
-    case is_pid(ChannelPid) andalso is_process_alive(ChannelPid) of
-        true ->
-            efka_tcp_channel:push_config(ChannelPid, Ref, self(), ConfigJson),
-            %% 设置成功，需要更新微服务的配置
-            CB = fun() -> service_model:set_config(ServiceId, ConfigJson) end,
-            {noreply, State#state{inflight = maps:put(Ref, ReceiverPid, Inflight), callbacks = maps:put(Ref, CB, Callbacks)}};
-        false ->
-            ReceiverPid ! {service_reply, Ref, {error, <<"channel is not alive">>}},
-            {noreply, State}
-    end;
-
-%% 推送配置项目
-handle_cast({invoke, Ref, ReceiverPid, Payload}, State = #state{channel_pid = ChannelPid, inflight = Inflight}) ->
-    case is_pid(ChannelPid) andalso is_process_alive(ChannelPid) of
-        true ->
-            efka_tcp_channel:invoke(ChannelPid, Ref, self(), Payload),
-            {noreply, State#state{inflight = maps:put(Ref, ReceiverPid, Inflight)}};
-        false ->
-            ReceiverPid ! {service_reply, Ref, {error, <<"channel is not alive">>}},
-            {reply, State}
-    end;
-
 handle_cast(_Request, State = #state{}) ->
     {noreply, State}.
 
@@ -198,49 +116,10 @@ handle_cast(_Request, State = #state{}) ->
     {noreply, NewState :: #state{}} |
     {noreply, NewState :: #state{}, timeout() | hibernate} |
     {stop, Reason :: term(), NewState :: #state{}}).
-%% 重启服务
-handle_info({timeout, _, reboot_service}, State = #state{service_id = ServiceId, manifest = Manifest}) ->
-    case efka_manifest:startup(Manifest) of
-        {ok, Port} ->
-            {os_pid, OSPid} = erlang:port_info(Port, os_pid),
-            lager:debug("[efka_service] service_id: ~p, reboot success, port: ~p, os_pid: ~p", [ServiceId, Port, OSPid]),
-            {noreply, State#state{port = Port, os_pid = OSPid}};
-        {error, Reason} ->
-            lager:debug("[efka_service] service_id: ~p, boot_service get error: ~p", [ServiceId, Reason]),
-            try_reboot(),
-            {noreply, State}
-    end;
-
-%% 处理channel的回复
-handle_info({channel_reply, Ref, Reply}, State = #state{inflight = Inflight, callbacks = Callbacks}) ->
-    case maps:take(Ref, Inflight) of
-        error ->
-            {noreply, State};
-        {ReceiverPid, NInflight} ->
-            ReceiverPid ! {service_reply, Ref, Reply},
-
-            {noreply, State#state{inflight = NInflight, callbacks = trigger_callback(Ref, Callbacks)}}
-    end;
-
-handle_info({Port, {data, Data}}, State = #state{service_id = ServiceId}) when is_port(Port) ->
-    lager:debug("[efka_service] service_id: ~p, port data: ~p", [ServiceId, Data]),
-    {noreply, State};
-
-%% 处理port的消息, Port的被动关闭会触发；因此这个时候的Port和State.port的值是相等的
-handle_info({Port, {exit_status, Code}}, State = #state{service_id = ServiceId}) when is_port(Port) ->
-    lager:debug("[efka_service] service_id: ~p, port: ~p, exit with code: ~p", [ServiceId, Port, Code]),
-    {noreply, State#state{port = undefined, os_pid = undefined}};
-
-%% 处理port的退出消息
-handle_info({'EXIT', Port, Reason}, State = #state{service_id = ServiceId}) when is_port(Port) ->
-    lager:debug("[efka_service] service_id: ~p, port: ~p, exit with reason: ~p", [ServiceId, Port, Reason]),
-    try_reboot(),
-    {noreply, State#state{port = undefined, os_pid = undefined}};
-
 %% 处理channel进程的退出
 handle_info({'DOWN', _Ref, process, ChannelPid, Reason}, State = #state{channel_pid = ChannelPid, service_id = ServiceId}) ->
     lager:debug("[efka_service] service_id: ~p, channel exited: ~p", [ServiceId, Reason]),
-    {noreply, State#state{channel_pid = undefined, inflight = #{}}}.
+    {noreply, State#state{channel_pid = undefined}}.
 
 %% @private
 %% @doc This function is called by a gen_server when it is about to
@@ -249,9 +128,7 @@ handle_info({'DOWN', _Ref, process, ChannelPid, Reason}, State = #state{channel_
 %% with Reason. The return value is ignored.
 -spec(terminate(Reason :: (normal | shutdown | {shutdown, term()} | term()),
     State :: #state{}) -> term()).
-terminate(Reason, _State = #state{service_id = ServiceId, port = Port, os_pid = OSPid}) ->
-    erlang:is_port(Port) andalso erlang:port_close(Port),
-    catch kill_os_pid(OSPid),
+terminate(Reason, _State = #state{service_id = ServiceId}) ->
     lager:debug("[efka_service] service_id: ~p, terminate with reason: ~p", [ServiceId, Reason]),
     ok.
 
@@ -266,26 +143,3 @@ code_change(_OldVsn, State = #state{}, _Extra) ->
 %%%===================================================================
 %%% Internal functions
 %%%===================================================================
-
-%% 关闭系统进程
--spec kill_os_pid(port() | undefined) -> no_return().
-kill_os_pid(undefined) ->
-    ok;
-kill_os_pid(OSPid) when is_integer(OSPid) ->
-    Cmd = lists:flatten(io_lib:format("kill -9 ~p", [OSPid])),
-    lager:debug("kill cmd is: ~p", [Cmd]),
-    os:cmd(Cmd).
-
--spec try_reboot() -> no_return().
-try_reboot() ->
-    erlang:start_timer(5000, self(), reboot_service).
-
--spec trigger_callback(Ref :: reference(), Callbacks :: map()) -> NewCallbacks :: map().
-trigger_callback(Ref, Callbacks) ->
-    case maps:take(Ref, Callbacks) of
-        error ->
-            Callbacks;
-        {Fun, NCallbacks} ->
-            catch Fun(),
-            NCallbacks
-    end.

apps/efka/src/efka_service_sup.erl

@@ -41,14 +41,7 @@ start_link() ->
 %% specifications.
 init([]) ->
     SupFlags = #{strategy => one_for_one, intensity => 1000, period => 3600},
-    %% 简化逻辑，只启动需要运行的微服务
-    {ok, Services} = service_model:get_running_services(),
-    ServiceIds = lists:map(fun(#service{service_id = ServiceId}) -> ServiceId end, Services),
-    lager:debug("[efka_service_sup] will start services: ~p", [ServiceIds]),
-
-    Specs = lists:map(fun(ServiceId) -> child_spec(ServiceId) end, Services),
-
-    {ok, {SupFlags, Specs}}.
+    {ok, {SupFlags, []}}.
 
 %%%===================================================================
 %%% Internal functions
@@ -71,8 +64,6 @@ stop_service(ServiceId) when is_binary(ServiceId) ->
     supervisor:terminate_child(?MODULE, ChildId),
     supervisor:delete_child(?MODULE, ChildId).
 
-child_spec(#service{service_id = ServiceId}) when is_binary(ServiceId) ->
-    child_spec(ServiceId);
 child_spec(ServiceId) when is_binary(ServiceId) ->
     Name = efka_service:get_name(ServiceId),
     #{

apps/efka/src/efka_std_modbus_service.erl

@@ -1,291 +0,0 @@
-%%%-------------------------------------------------------------------
-%%% @author anlicheng
-%%% @copyright (C) 2025, <COMPANY>
-%%% @doc
-%%% 1. 需要管理服务的整个生命周期，包括: 启动，停止
-%%% 2. 需要监控服务的状态，通过port的方式
-%%% 3. 服务的启动和关闭，需要在更高的层级控制
-%%% @end
-%%% Created : 18. 4月 2025 16:50
-%%%-------------------------------------------------------------------
--module(efka_std_modbus_service).
--author("anlicheng").
--include("efka_tables.hrl").
-
--behaviour(gen_server).
-
-%% API
--export([start_link/2]).
--export([get_name/1, get_pid/1, attach_channel/2]).
--export([push_config/3, request_config/1, invoke/3]).
--export([metric_data/3, send_event/3]).
-
-%% gen_server callbacks
--export([init/1, handle_call/3, handle_cast/2, handle_info/2, terminate/2, code_change/3]).
-
--record(state, {
-    service_id :: binary(),
-    %% 通道id信息
-    channel_pid :: pid() | undefined,
-    %% 当前进程的port信息, OSPid = erlang:port_info(Port, os_pid)
-    port :: undefined | port(),
-    %% 系统对应的pid
-    os_pid :: undefined | integer(),
-    %% 配置信息
-    manifest :: undefined | efka_manifest:manifest(),
-    inflight = #{},
-
-    %% 映射关系: #{Ref => Fun}
-    callbacks = #{}
-}).
-
-%%%===================================================================
-%%% API
-%%%===================================================================
-
--spec get_name(ServiceId :: binary()) -> atom().
-get_name(ServiceId) when is_binary(ServiceId) ->
-    list_to_atom("efka_service:" ++ binary_to_list(ServiceId)).
-
--spec get_pid(ServiceId :: binary()) -> undefined | pid().
-get_pid(ServiceId) when is_binary(ServiceId) ->
-    whereis(get_name(ServiceId)).
-
--spec push_config(Pid :: pid(), Ref :: reference(), ConfigJson :: binary()) -> no_return().
-push_config(Pid, Ref, ConfigJson) when is_pid(Pid), is_binary(ConfigJson) ->
-    gen_server:cast(Pid, {push_config, Ref, self(), ConfigJson}).
-
--spec invoke(Pid :: pid(), Ref :: reference(), Payload :: binary()) -> no_return().
-invoke(Pid, Ref, Payload) when is_pid(Pid), is_reference(Ref), is_binary(Payload) ->
-    gen_server:cast(Pid, {invoke, Ref, self(), Payload}).
-
--spec request_config(Pid :: pid()) -> {ok, Config :: binary()}.
-request_config(Pid) when is_pid(Pid) ->
-    gen_server:call(Pid, request_config).
-
--spec metric_data(Pid :: pid(), DeviceUUID :: binary(), Data :: binary()) -> no_return().
-metric_data(Pid, DeviceUUID, Data) when is_pid(Pid), is_binary(DeviceUUID), is_binary(Data) ->
-    gen_server:cast(Pid, {metric_data, DeviceUUID, Data}).
-
--spec send_event(Pid :: pid(), EventType :: integer(), Params :: binary()) -> no_return().
-send_event(Pid, EventType, Params) when is_pid(Pid), is_integer(EventType), is_binary(Params) ->
-    gen_server:cast(Pid, {send_event, EventType, Params}).
-
--spec attach_channel(pid(), pid()) -> ok | {error, Reason :: binary()}.
-attach_channel(Pid, ChannelPid) when is_pid(Pid), is_pid(ChannelPid) ->
-    gen_server:call(Pid, {attach_channel, ChannelPid}).
-
-%% @doc Spawns the server and registers the local name (unique)
--spec(start_link(Name :: atom(), Service :: binary()) ->
-    {ok, Pid :: pid()} | ignore | {error, Reason :: term()}).
-start_link(Name, ServiceId) when is_atom(Name), is_binary(ServiceId) ->
-    gen_server:start_link({local, Name}, ?MODULE, [ServiceId], []).
-
-%%%===================================================================
-%%% gen_server callbacks
-%%%===================================================================
-
-%% @private
-%% @doc Initializes the server
--spec(init(Args :: term()) ->
-    {ok, State :: #state{}} | {ok, State :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term()} | ignore).
-init([ServiceId]) ->
-    %% supervisor进程通过exit(ChildPid, shutdown)调用的时候，确保terminate函数被调用
-    erlang:process_flag(trap_exit, true),
-    case service_model:get_service(ServiceId) of
-        error ->
-            lager:notice("[efka_service] service_id: ~p, not found", [ServiceId]),
-            ignore;
-        {ok, #service{root_dir = RootDir}} ->
-            %% 第一次启动，要求必须成功；只有第一次启动成功，后续的重启逻辑才有意义
-            case efka_manifest:new(RootDir) of
-                {ok, Manifest} ->
-                    case efka_manifest:startup(Manifest) of
-                        {ok, Port} ->
-                            {os_pid, OSPid} = erlang:port_info(Port, os_pid),
-                            lager:debug("[efka_service] service: ~p, port: ~p, boot_service success os_pid: ~p", [ServiceId, Port, OSPid]),
-                            {ok, #state{service_id = ServiceId, manifest = Manifest, port = Port, os_pid = OSPid}};
-                        {error, Reason} ->
-                            lager:debug("[efka_service] service: ~p, boot_service get error: ~p", [ServiceId, Reason]),
-                            {stop, Reason}
-                    end;
-                {error, Reason} ->
-                    lager:notice("[efka_service] service: ~p, read manifest.json get error: ~p", [ServiceId, Reason]),
-                    ignore
-            end
-    end.
-
-%% @private
-%% @doc Handling call messages
--spec(handle_call(Request :: term(), From :: {pid(), Tag :: term()},
-    State :: #state{}) ->
-    {reply, Reply :: term(), NewState :: #state{}} |
-    {reply, Reply :: term(), NewState :: #state{}, timeout() | hibernate} |
-    {noreply, NewState :: #state{}} |
-    {noreply, NewState :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term(), Reply :: term(), NewState :: #state{}} |
-    {stop, Reason :: term(), NewState :: #state{}}).
-%% 绑定channel
-handle_call({attach_channel, ChannelPid}, _From, State = #state{channel_pid = OldChannelPid, service_id = ServiceId}) ->
-    case is_pid(OldChannelPid) andalso is_process_alive(OldChannelPid) of
-        false ->
-            erlang:monitor(process, ChannelPid),
-            lager:debug("[efka_service] service_id: ~p, channel attched", [ServiceId]),
-            {reply, ok, State#state{channel_pid = ChannelPid}};
-        true ->
-            {reply, {error, <<"channel exists">>}, State}
-    end;
-
-%% 请求参数项 done
-handle_call(request_config, _From, State = #state{service_id = ServiceId}) ->
-    case service_model:get_config_json(ServiceId) of
-        {ok, ConfigJson} ->
-            {reply, {ok, ConfigJson}, State};
-        error ->
-            {reply, {ok, <<>>}, State}
-    end;
-
-handle_call(_Request, _From, State = #state{}) ->
-    {reply, ok, State}.
-
-%% @private
-%% @doc Handling cast messages
--spec(handle_cast(Request :: term(), State :: #state{}) ->
-    {noreply, NewState :: #state{}} |
-    {noreply, NewState :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term(), NewState :: #state{}}).
-handle_cast({metric_data, DeviceUUID, LineProtocolData}, State = #state{service_id = ServiceId}) ->
-    lager:debug("[efka_service] metric_data service_id: ~p, device_uuid: ~p, metric data: ~p", [ServiceId, DeviceUUID, LineProtocolData]),
-    efka_agent:metric_data(ServiceId, DeviceUUID, LineProtocolData),
-    {noreply, State};
-
-handle_cast({send_event, EventType, Params}, State = #state{service_id = ServiceId}) ->
-    efka_agent:event(ServiceId, EventType, Params),
-    lager:debug("[efka_service] send_event, service_id: ~p, event_type: ~p, params: ~p", [ServiceId, EventType, Params]),
-    {noreply, State};
-
-%% 推送配置项目
-handle_cast({push_config, Ref, ReceiverPid, ConfigJson}, State = #state{channel_pid = ChannelPid, service_id = ServiceId, inflight = Inflight, callbacks = Callbacks}) ->
-    case is_pid(ChannelPid) andalso is_process_alive(ChannelPid) of
-        true ->
-            efka_tcp_channel:push_config(ChannelPid, Ref, self(), ConfigJson),
-            %% 设置成功，需要更新微服务的配置
-            CB = fun() -> service_model:set_config(ServiceId, ConfigJson) end,
-            {noreply, State#state{inflight = maps:put(Ref, ReceiverPid, Inflight), callbacks = maps:put(Ref, CB, Callbacks)}};
-        false ->
-            ReceiverPid ! {service_reply, Ref, {error, <<"channel is not alive">>}},
-            {noreply, State}
-    end;
-
-%% 推送配置项目
-handle_cast({invoke, Ref, ReceiverPid, Payload}, State = #state{channel_pid = ChannelPid, inflight = Inflight}) ->
-    case is_pid(ChannelPid) andalso is_process_alive(ChannelPid) of
-        true ->
-            efka_tcp_channel:invoke(ChannelPid, Ref, self(), Payload),
-            {noreply, State#state{inflight = maps:put(Ref, ReceiverPid, Inflight)}};
-        false ->
-            ReceiverPid ! {service_reply, Ref, {error, <<"channel is not alive">>}},
-            {reply, State}
-    end;
-
-handle_cast(_Request, State = #state{}) ->
-    {noreply, State}.
-
-%% @private
-%% @doc Handling all non call/cast messages
--spec(handle_info(Info :: timeout() | term(), State :: #state{}) ->
-    {noreply, NewState :: #state{}} |
-    {noreply, NewState :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term(), NewState :: #state{}}).
-%% 重启服务
-handle_info({timeout, _, reboot_service}, State = #state{service_id = ServiceId, manifest = Manifest}) ->
-    case efka_manifest:startup(Manifest) of
-        {ok, Port} ->
-            {os_pid, OSPid} = erlang:port_info(Port, os_pid),
-            lager:debug("[efka_service] service_id: ~p, reboot success, port: ~p, os_pid: ~p", [ServiceId, Port, OSPid]),
-            {noreply, State#state{port = Port, os_pid = OSPid}};
-        {error, Reason} ->
-            lager:debug("[efka_service] service_id: ~p, boot_service get error: ~p", [ServiceId, Reason]),
-            try_reboot(),
-            {noreply, State}
-    end;
-
-%% 处理channel的回复
-handle_info({channel_reply, Ref, Reply}, State = #state{inflight = Inflight, callbacks = Callbacks}) ->
-    case maps:take(Ref, Inflight) of
-        error ->
-            {noreply, State};
-        {ReceiverPid, NInflight} ->
-            ReceiverPid ! {service_reply, Ref, Reply},
-
-            {noreply, State#state{inflight = NInflight, callbacks = trigger_callback(Ref, Callbacks)}}
-    end;
-
-handle_info({Port, {data, Data}}, State = #state{service_id = ServiceId}) when is_port(Port) ->
-    lager:debug("[efka_service] service_id: ~p, port data: ~p", [ServiceId, Data]),
-    {noreply, State};
-
-%% 处理port的消息, Port的被动关闭会触发；因此这个时候的Port和State.port的值是相等的
-handle_info({Port, {exit_status, Code}}, State = #state{service_id = ServiceId}) when is_port(Port) ->
-    lager:debug("[efka_service] service_id: ~p, port: ~p, exit with code: ~p", [ServiceId, Port, Code]),
-    {noreply, State#state{port = undefined, os_pid = undefined}};
-
-%% 处理port的退出消息
-handle_info({'EXIT', Port, Reason}, State = #state{service_id = ServiceId}) when is_port(Port) ->
-    lager:debug("[efka_service] service_id: ~p, port: ~p, exit with reason: ~p", [ServiceId, Port, Reason]),
-    try_reboot(),
-    {noreply, State#state{port = undefined, os_pid = undefined}};
-
-%% 处理channel进程的退出
-handle_info({'DOWN', _Ref, process, ChannelPid, Reason}, State = #state{channel_pid = ChannelPid, service_id = ServiceId}) ->
-    lager:debug("[efka_service] service_id: ~p, channel exited: ~p", [ServiceId, Reason]),
-    {noreply, State#state{channel_pid = undefined, inflight = #{}}}.
-
-%% @private
-%% @doc This function is called by a gen_server when it is about to
-%% terminate. It should be the opposite of Module:init/1 and do any
-%% necessary cleaning up. When it returns, the gen_server terminates
-%% with Reason. The return value is ignored.
--spec(terminate(Reason :: (normal | shutdown | {shutdown, term()} | term()),
-    State :: #state{}) -> term()).
-terminate(Reason, _State = #state{service_id = ServiceId, port = Port, os_pid = OSPid}) ->
-    erlang:is_port(Port) andalso erlang:port_close(Port),
-    catch kill_os_pid(OSPid),
-    lager:debug("[efka_service] service_id: ~p, terminate with reason: ~p", [ServiceId, Reason]),
-    ok.
-
-%% @private
-%% @doc Convert process state when code is changed
--spec(code_change(OldVsn :: term() | {down, term()}, State :: #state{},
-    Extra :: term()) ->
-    {ok, NewState :: #state{}} | {error, Reason :: term()}).
-code_change(_OldVsn, State = #state{}, _Extra) ->
-    {ok, State}.
-
-%%%===================================================================
-%%% Internal functions
-%%%===================================================================
-
-%% 关闭系统进程
--spec kill_os_pid(port() | undefined) -> no_return().
-kill_os_pid(undefined) ->
-    ok;
-kill_os_pid(OSPid) when is_integer(OSPid) ->
-    Cmd = lists:flatten(io_lib:format("kill -9 ~p", [OSPid])),
-    lager:debug("kill cmd is: ~p", [Cmd]),
-    os:cmd(Cmd).
-
--spec try_reboot() -> no_return().
-try_reboot() ->
-    erlang:start_timer(5000, self(), reboot_service).
-
--spec trigger_callback(Ref :: reference(), Callbacks :: map()) -> NewCallbacks :: map().
-trigger_callback(Ref, Callbacks) ->
-    case maps:take(Ref, Callbacks) of
-        error ->
-            Callbacks;
-        {Fun, NCallbacks} ->
-            catch Fun(),
-            NCallbacks
-    end.

apps/efka/src/efka_stream.erl

@@ -0,0 +1,164 @@
+%%%-------------------------------------------------------------------
+%%% @author anlicheng
+%%% @copyright (C) 2025, <COMPANY>
+%%% @doc
+%%%
+%%% @end
+%%% Created : 13. 11月 2025 10:57
+%%%-------------------------------------------------------------------
+-module(efka_stream).
+-author("anlicheng").
+
+-behaviour(gen_server).
+
+%% API
+-export([start_monitor/1]).
+-export([setup/3, data/2, finish/1]).
+
+%% gen_server callbacks
+-export([init/1, handle_call/3, handle_cast/2, handle_info/2, terminate/2, code_change/3]).
+
+-define(SERVER, ?MODULE).
+
+-record(state, {
+    parent_pid :: pid(),
+    ref :: reference(),
+    file_size = 0 :: integer(),
+    acc_size = 0 :: integer(),
+    real_file :: undefined | string(),
+    io_device :: undefined | file:fd()
+}).
+
+%%%===================================================================
+%%% API
+%%%===================================================================
+
+-spec setup(StreamPid :: pid(), FileName :: string(), FileSize :: integer()) -> {ok, Path :: string()}.
+setup(StreamPid, FileName, FileSize) when is_pid(StreamPid), is_list(FileName), is_integer(FileSize) ->
+    gen_server:call(StreamPid, {setup, FileName, FileSize}).
+
+-spec data(StreamPid :: pid(), ChunkData :: binary()) -> no_return().
+data(StreamPid, ChunkData) when is_pid(StreamPid), is_binary(ChunkData) ->
+    gen_server:cast(StreamPid, {data, ChunkData}).
+
+-spec finish(StreamPid :: pid()) -> no_return().
+finish(StreamPid) when is_pid(StreamPid) ->
+    gen_server:cast(StreamPid, finish).
+
+%% @doc Spawns the server and registers the local name (unique)
+-spec(start_monitor(ParentPid :: pid()) ->
+    {ok, {Pid :: pid(), MonRef :: reference()}} | ignore | {error, Reason :: term()}).
+start_monitor(ParentPid) when is_pid(ParentPid) ->
+    gen_server:start_monitor(?MODULE, [ParentPid], []).
+
+%%%===================================================================
+%%% gen_server callbacks
+%%%===================================================================
+
+%% @private
+%% @doc Initializes the server
+-spec(init(Args :: term()) ->
+    {ok, State :: #state{}} | {ok, State :: #state{}, timeout() | hibernate} |
+    {stop, Reason :: term()} | ignore).
+init([ParentPid]) ->
+    Ref = erlang:monitor(process, ParentPid),
+    {ok, #state{parent_pid = ParentPid, ref = Ref}}.
+
+%% @private
+%% @doc Handling call messages
+-spec(handle_call(Request :: term(), From :: {pid(), Tag :: term()},
+    State :: #state{}) ->
+    {reply, Reply :: term(), NewState :: #state{}} |
+    {reply, Reply :: term(), NewState :: #state{}, timeout() | hibernate} |
+    {noreply, NewState :: #state{}} |
+    {noreply, NewState :: #state{}, timeout() | hibernate} |
+    {stop, Reason :: term(), Reply :: term(), NewState :: #state{}} |
+    {stop, Reason :: term(), NewState :: #state{}}).
+handle_call({setup, FileName, FileSize}, _From, State = #state{}) ->
+    {RealFileName, Path} = make_file(filename:basename(FileName)),
+    {ok, IoDevice} = file:open(RealFileName, [write]),
+
+    {reply, {ok, Path}, State#state{io_device = IoDevice, real_file = RealFileName, file_size = FileSize, acc_size = 0}}.
+
+%% @private
+%% @doc Handling cast messages
+-spec(handle_cast(Request :: term(), State :: #state{}) ->
+    {noreply, NewState :: #state{}} |
+    {noreply, NewState :: #state{}, timeout() | hibernate} |
+    {stop, Reason :: term(), NewState :: #state{}}).
+handle_cast({data, ChunkData}, State = #state{io_device = IoDevice, acc_size = AccSize}) ->
+    Data = base64:decode(ChunkData),
+    Len = byte_size(Data),
+
+    ok = file:write(IoDevice, Data),
+    {noreply, State#state{acc_size = AccSize + Len}};
+handle_cast(finish, State = #state{parent_pid = ParentPid, io_device = IoDevice, acc_size = AccSize, file_size = FileSize, real_file = RealFile}) ->
+    case AccSize == FileSize of
+        true ->
+            ok = file:close(IoDevice),
+            ParentPid ! {stream_reply, self(), ok};
+        false ->
+            ok = file:close(IoDevice),
+            ok = file:delete(RealFile),
+            ParentPid ! {stream_reply, self(), invalid}
+    end,
+    {stop, normal, State}.
+
+%% @private
+%% @doc Handling all non call/cast messages
+-spec(handle_info(Info :: timeout() | term(), State :: #state{}) ->
+    {noreply, NewState :: #state{}} |
+    {noreply, NewState :: #state{}, timeout() | hibernate} |
+    {stop, Reason :: term(), NewState :: #state{}}).
+handle_info({'DOWN', Ref, process, Pid, normal}, State = #state{ref = Ref, parent_pid = Pid}) ->
+    {noreply, State};
+handle_info({'DOWN', Ref, process, Pid, Reason}, State = #state{ref = Ref, parent_pid = Pid, io_device = IoDevice, real_file = RealFile}) ->
+    lager:debug("[efka_stream] ws_channel close with reason: ~p", [Reason]),
+    case IoDevice =:= undefined of
+        true ->
+            ok;
+        false ->
+            ok = file:close(IoDevice),
+            RealFile /= undefined andalso file:delete(RealFile)
+    end,
+    {stop, normal, State};
+handle_info(_Info, State = #state{}) ->
+    {noreply, State}.
+
+%% @private
+%% @doc This function is called by a gen_server when it is about to
+%% terminate. It should be the opposite of Module:init/1 and do any
+%% necessary cleaning up. When it returns, the gen_server terminates
+%% with Reason. The return value is ignored.
+-spec(terminate(Reason :: (normal | shutdown | {shutdown, term()} | term()),
+    State :: #state{}) -> term()).
+terminate(_Reason, _State = #state{}) ->
+    ok.
+
+%% @private
+%% @doc Convert process state when code is changed
+-spec(code_change(OldVsn :: term() | {down, term()}, State :: #state{},
+    Extra :: term()) ->
+    {ok, NewState :: #state{}} | {error, Reason :: term()}).
+code_change(_OldVsn, State = #state{}, _Extra) ->
+    {ok, State}.
+
+%%%===================================================================
+%%% Internal functions
+%%%===================================================================
+
+-spec make_file(Basename :: string()) -> {string(), string()}.
+make_file(Basename) when is_list(Basename) ->
+    {ok, UploadDir} = application:get_env(efka, upload_dir),
+    {{Y, M, D}, _} = calendar:local_time(),
+    DateDir = io_lib:format("~p-~p-~p", [Y, M, D]),
+    BaseDir = UploadDir ++ DateDir,
+    case filelib:is_dir(BaseDir) of
+        true ->
+            ok;
+        false ->
+            ok = file:make_dir(BaseDir)
+    end,
+    Path = DateDir ++ "/" ++ Basename,
+
+    {UploadDir ++ Path, Path}.

apps/efka/src/efka_subscription.erl

@@ -13,7 +13,7 @@
 
 %% API
 -export([start_link/0]).
--export([subscribe/2, publish/2]).
+-export([subscribe/2, publish/3, debug_info/0]).
 -export([match_components/2, is_valid_components/1, of_components/1]).
 
 %% gen_server callbacks
@@ -34,20 +34,26 @@
 }).
 
 -record(state, {
-    subscribers = []
+    subscribers = [],
+    %% qos未1，并且未被消费的消息
+    remaining_messages = []
 }).
 
 %%%===================================================================
 %%% API
 %%%===================================================================
 
--spec subscribe(Topic :: binary(), SubscriberPid :: pid()) -> no_return().
+-spec subscribe(Topic :: binary(), SubscriberPid :: pid()) -> ok | {error, Reason :: binary()}.
 subscribe(Topic, SubscriberPid) when is_binary(Topic), is_pid(SubscriberPid) ->
-    gen_server:cast(?SERVER, {subscribe, Topic, SubscriberPid}).
+    gen_server:call(?SERVER, {subscribe, Topic, SubscriberPid}).
 
--spec publish(Topic :: binary(), Content :: binary()) -> no_return().
-publish(Topic, Content) when is_binary(Topic), is_binary(Content) ->
-    gen_server:cast(?SERVER, {publish, Topic, Content}).
+-spec publish(Topic :: binary(), Qos :: integer(), Content :: binary()) -> no_return().
+publish(Topic, Qos, Content) when is_binary(Topic), is_integer(Qos), is_binary(Content) ->
+    gen_server:cast(?SERVER, {publish, Topic, Qos, Content}).
+
+-spec debug_info() -> {ok, Info :: map()}.
+debug_info() ->
+    gen_server:call(?SERVER, debug_info).
 
 %% @doc Spawns the server and registers the local name (unique)
 -spec(start_link() ->
@@ -77,8 +83,26 @@ init([]) ->
     {noreply, NewState :: #state{}, timeout() | hibernate} |
     {stop, Reason :: term(), Reply :: term(), NewState :: #state{}} |
     {stop, Reason :: term(), NewState :: #state{}}).
-handle_call(_Request, _From, State = #state{}) ->
-    {reply, ok, State}.
+%%  同一个SubscriberPid只能订阅同一个topic一次
+handle_call({subscribe, Topic, SubscriberPid}, _From, State = #state{subscribers = Subscribers, remaining_messages = RemainingMessages}) ->
+    Components = of_components(Topic),
+    case is_valid_components(Components) of
+        true ->
+            Sub = #subscriber{topic = Topic, subscriber_pid = SubscriberPid, components = Components, order = order_num(Components)},
+            %% 建立到SubscriberPid的monitor，进程退出需要清理订阅
+            erlang:monitor(process, SubscriberPid),
+            %% 处理遗留的消息
+            RestRemainingMessages = dispatch_remaining_messages(Sub, RemainingMessages),
+            {reply, ok, State#state{subscribers = Subscribers ++ [Sub], remaining_messages = RestRemainingMessages}};
+        false ->
+            {reply, {error, <<"invalid topic name">>}, State}
+    end;
+handle_call(debug_info, _From, State = #state{subscribers = Subscribers, remaining_messages = RemainingMessages}) ->
+    Info = #{
+        subscribes => Subscribers,
+        remaining_messages => RemainingMessages
+    },
+    {reply, {ok, Info}, State}.
 
 %% @private
 %% @doc Handling cast messages
@@ -86,29 +110,19 @@ handle_call(_Request, _From, State = #state{}) ->
     {noreply, NewState :: #state{}} |
     {noreply, NewState :: #state{}, timeout() | hibernate} |
     {stop, Reason :: term(), NewState :: #state{}}).
-%%  同一个SubscriberPid只能订阅同一个topic一次
-handle_cast({subscribe, Topic, SubscriberPid}, State = #state{subscribers = Subscribers}) ->
-    Components = of_components(Topic),
-    case is_valid_components(Components) of
-        true ->
-            Sub = #subscriber{topic = Topic, subscriber_pid = SubscriberPid, components = Components, order = order_num(Components)},
-            %% 建立到SubscriberPid的monitor，进程退出需要清理订阅
-            erlang:monitor(process, SubscriberPid),
-
-            {noreply, State#state{subscribers = Subscribers ++ [Sub]}};
-        false ->
-            {noreply, State}
-    end;
-
 %% 发布消息
-handle_cast({publish, Topic, Content}, State = #state{subscribers = Subscribers}) ->
+handle_cast({publish, Topic, Qos, Content}, State = #state{subscribers = Subscribers, remaining_messages = RemainingMessages}) ->
     MatchedSubscribers = match_subscribers(Subscribers, Topic),
-    lists:foreach(fun(#subscriber{subscriber_pid = SubscriberPid}) ->
-        SubscriberPid ! {topic_broadcast, Topic, Content}
-                  end, MatchedSubscribers),
-
     lager:debug("[efka_subscription] topic: ~p, content: ~p, match subscribers: ~p", [Topic, Content, MatchedSubscribers]),
-    {noreply, State}.
+    case length(MatchedSubscribers) > 0 of
+        true ->
+            broadcast(Topic, Content, MatchedSubscribers),
+            {noreply, State};
+        false when Qos =:= 0 ->
+            {noreply, State};
+        false ->
+            {noreply, State#state{remaining_messages = [{Topic, Content}|RemainingMessages]}}
+    end.
 
 %% @private
 %% @doc Handling all non call/cast messages
@@ -202,3 +216,22 @@ order_num([<<$+>>|_]) ->
     3;
 order_num([_|Tail]) ->
     order_num(Tail).
+
+broadcast(Topic, Content, MatchedSubscribers) ->
+    lists:foreach(fun(#subscriber{subscriber_pid = SubscriberPid}) ->
+        SubscriberPid ! {topic_broadcast, Topic, Content}
+                  end, MatchedSubscribers).
+
+-spec dispatch_remaining_messages(Subscriber :: #subscriber{}, RemainingMessages :: list()) -> RestRemainingMessages :: list().
+dispatch_remaining_messages(#subscriber{subscriber_pid = SubscriberPid, components = Components}, RemainingMessages) when is_list(RemainingMessages) ->
+    %% 处理遗留的消息
+    lists:foldl(fun({Topic0, Content0}, Acc) ->
+        Components0 = of_components(Topic0),
+        case match_components(Components0, Components) of
+            true ->
+                SubscriberPid ! {topic_broadcast, Topic0, Content0},
+                Acc;
+            false ->
+                [{Topic0, Content0}|Acc]
+        end
+                end, [], RemainingMessages).

apps/efka/src/efka_sup.erl

@@ -29,12 +29,48 @@ init([]) ->
     SupFlags = #{strategy => one_for_one, intensity => 1000, period => 3600},
     ChildSpecs = [
         #{
-            id => 'efka_inetd_task_log',
-            start => {'efka_inetd_task_log', start_link, []},
+            id => 'efka_logger',
+            start => {'efka_logger', start_link, ["deploy_log"]},
             restart => permanent,
             shutdown => 2000,
             type => worker,
-            modules => ['efka_inetd_task_log']
+            modules => ['efka_logger']
+        },
+
+        #{
+            id => 'efka_service_sup',
+            start => {'efka_service_sup', start_link, []},
+            restart => permanent,
+            shutdown => 2000,
+            type => supervisor,
+            modules => ['efka_service_sup']
+        },
+
+        %#{
+        %    id => 'docker_events',
+        %    start => {'docker_events', start_link, []},
+        %    restart => permanent,
+        %    shutdown => 2000,
+        %    type => worker,
+        %    modules => ['docker_events']
+        %},
+
+        #{
+            id => cache_model,
+            start => {cache_model, start_link, []},
+            restart => permanent,
+            shutdown => 5000,
+            type => worker,
+            modules => ['cache_model']
+        },
+
+        #{
+            id => service_model,
+            start => {service_model, start_link, []},
+            restart => permanent,
+            shutdown => 5000,
+            type => worker,
+            modules => ['service_model']
         },
 
         #{
@@ -47,49 +83,23 @@ init([]) ->
         },
 
         #{
-            id => 'efka_inetd',
-            start => {'efka_inetd', start_link, []},
+            id => 'docker_manager',
+            start => {'docker_manager', start_link, []},
             restart => permanent,
             shutdown => 2000,
             type => worker,
-            modules => ['efka_inetd']
+            modules => ['docker_manager']
         },
 
         #{
-            id => 'efka_agent',
-            start => {'efka_agent', start_link, []},
+            id => 'efka_remote_agent',
+            start => {'efka_remote_agent', start_link, []},
             restart => permanent,
             shutdown => 2000,
             type => worker,
-            modules => ['efka_agent']
-        },
-
-        #{
-            id => 'efka_tcp_sup',
-            start => {'efka_tcp_sup', start_link, []},
-            restart => permanent,
-            shutdown => 2000,
-            type => supervisor,
-            modules => ['efka_tcp_sup']
-        },
-
-        #{
-            id => 'efka_tcp_server',
-            start => {'efka_tcp_server', start_link, []},
-            restart => permanent,
-            shutdown => 2000,
-            type => worker,
-            modules => ['efka_tcp_server']
-        },
-
-        #{
-            id => 'efka_service_sup',
-            start => {'efka_service_sup', start_link, []},
-            restart => permanent,
-            shutdown => 2000,
-            type => supervisor,
-            modules => ['efka_service_sup']
+            modules => ['efka_remote_agent']
         }
+
     ],
 
     {ok, {SupFlags, ChildSpecs}}.

apps/efka/src/efka_tcp_channel.erl

@@ -1,295 +0,0 @@
-%%%-------------------------------------------------------------------
-%%% @author anlicheng
-%%% @copyright (C) 2025, <COMPANY>
-%%% @doc
-%%%
-%%% @end
-%%% Created : 30. 4月 2025 09:22
-%%%-------------------------------------------------------------------
--module(efka_tcp_channel).
--author("anlicheng").
-
--behaviour(gen_server).
-
-%% API
--export([start_link/1]).
--export([push_config/4, invoke/4]).
-
-%% gen_server callbacks
--export([init/1, handle_call/3, handle_cast/2, handle_info/2, terminate/2, code_change/3]).
-
--define(SERVER, ?MODULE).
-
-%% 最大的等待时间
--define(PENDING_TIMEOUT, 10 * 1000).
-%% 消息类型
-
-%% 服务注册
--define(PACKET_REQUEST, 16#01).
-%% 消息响应
--define(PACKET_RESPONSE, 16#02).
-%% 上传数据
--define(PACKET_PUSH, 16#03).
-
--define(PACKET_PUB, 16#04).
-
--record(state, {
-    packet_id = 1,
-    socket :: gen_tcp:socket(),
-    service_id :: undefined | binary(),
-    service_pid :: undefined | pid(),
-    is_registered = false :: boolean(),
-
-    %% 请求响应的对应关系, #{packet_id => {ReceiverPid, Ref}}; 自身的inflight需要超时逻辑处理
-    inflight = #{}
-}).
-
-%%%===================================================================
-%%% API
-%%%===================================================================
-
--spec push_config(ChannelPid :: pid(), Ref :: reference(), ReceiverPid :: pid(), ConfigJson :: binary()) -> no_return().
-push_config(ChannelPid, Ref, ReceiverPid, ConfigJson) when is_pid(ChannelPid), is_pid(ReceiverPid), is_binary(ConfigJson), is_reference(Ref) ->
-    gen_server:cast(ChannelPid, {push_config, Ref, ReceiverPid, ConfigJson}).
-
--spec invoke(ChannelPid :: pid(), Ref :: reference(), ReceiverPid :: pid(), Payload :: binary()) -> no_return().
-invoke(ChannelPid, Ref, ReceiverPid, Payload) when is_pid(ChannelPid), is_pid(ReceiverPid), is_binary(Payload), is_reference(Ref) ->
-    gen_server:cast(ChannelPid, {invoke, Ref, ReceiverPid, Payload}).
-
-%% @doc Spawns the server and registers the local name (unique)
--spec(start_link(Socket :: gen_tcp:socket()) ->
-    {ok, Pid :: pid()} | ignore | {error, Reason :: term()}).
-start_link(Socket) ->
-    gen_server:start_link(?MODULE, [Socket], []).
-
-%%%===================================================================
-%%% gen_server callbacks
-%%%===================================================================
-
-%% @private
-%% @doc Initializes the server
--spec(init(Args :: term()) ->
-    {ok, State :: #state{}} | {ok, State :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term()} | ignore).
-init([Socket]) ->
-    ok = inet:setopts(Socket, [{active, true}]),
-    lager:debug("[efka_tcp_channel] get micro service socket: ~p", [Socket]),
-    {ok, #state{socket = Socket}}.
-
-%% @private
-%% @doc Handling call messages
--spec(handle_call(Request :: term(), From :: {pid(), Tag :: term()},
-    State :: #state{}) ->
-    {reply, Reply :: term(), NewState :: #state{}} |
-    {reply, Reply :: term(), NewState :: #state{}, timeout() | hibernate} |
-    {noreply, NewState :: #state{}} |
-    {noreply, NewState :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term(), Reply :: term(), NewState :: #state{}} |
-    {stop, Reason :: term(), NewState :: #state{}}).
-handle_call(_Request, _From, State = #state{}) ->
-    {reply, ok, State}.
-
-%% @private
-%% @doc Handling cast messages
--spec(handle_cast(Request :: term(), State :: #state{}) ->
-    {noreply, NewState :: #state{}} |
-    {noreply, NewState :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term(), NewState :: #state{}}).
-%% 推送配置项目
-handle_cast({push_config, Ref, ReceiverPid, ConfigJson}, State = #state{socket = Socket, packet_id = PacketId, inflight = Inflight}) ->
-    PushConfig = #{<<"id">> => PacketId, <<"method">> => <<"push_config">>, <<"params">> => #{<<"config">> => ConfigJson}},
-    Packet = jiffy:encode(PushConfig, [force_utf8]),
-    ok = gen_tcp:send(Socket, <<?PACKET_PUSH:8, Packet/binary>>),
-
-    erlang:start_timer(?PENDING_TIMEOUT, self(), {pending_timeout, PacketId}),
-    {noreply, State#state{packet_id = next_packet_id(PacketId), inflight = maps:put(PacketId, {ReceiverPid, Ref}, Inflight)}};
-
-%% 远程调用
-handle_cast({invoke, Ref, ReceiverPid, Payload}, State = #state{socket = Socket, packet_id = PacketId, inflight = Inflight}) ->
-    PushConfig = #{<<"id">> => PacketId, <<"method">> => <<"invoke">>, <<"params">> => #{<<"payload">> => Payload}},
-    Packet = jiffy:encode(PushConfig, [force_utf8]),
-    ok = gen_tcp:send(Socket, <<?PACKET_PUSH:8, Packet/binary>>),
-
-    erlang:start_timer(?PENDING_TIMEOUT, self(), {pending_timeout, PacketId}),
-    {noreply, State#state{packet_id = next_packet_id(PacketId), inflight = maps:put(PacketId, {ReceiverPid, Ref}, Inflight)}};
-
-handle_cast(_Request, State = #state{}) ->
-    {noreply, State}.
-
-%% @private
-%% @doc Handling all non call/cast messages
--spec(handle_info(Info :: timeout() | term(), State :: #state{}) ->
-    {noreply, NewState :: #state{}} |
-    {noreply, NewState :: #state{}, timeout() | hibernate} |
-    {stop, Reason :: term(), NewState :: #state{}}).
-%% 处理micro-client:request => efka 主动的请求
-handle_info({tcp, Socket, <<?PACKET_REQUEST:8, Data/binary>>}, State = #state{socket = Socket}) ->
-    Request = jiffy:decode(Data, [return_maps]),
-    case handle_request(Request, State) of
-        {ok, NewState} ->
-            {noreply, NewState};
-        {stop, Reason, NewState} ->
-            {stop, Reason, NewState}
-    end;
-
-%% 处理micro-client:response => efka 的响应
-handle_info({tcp, Socket, <<?PACKET_RESPONSE:8, Data/binary>>}, State = #state{socket = Socket, inflight = Inflight}) ->
-    Resp = jiffy:decode(Data, [return_maps]),
-    case Resp of
-        #{<<"id">> := Id, <<"result">> := Result} ->
-            case maps:take(Id, Inflight) of
-                error ->
-                    lager:warning("[tcp_channel] get unknown publish response message: ~p, packet_id: ~p", [Resp, Id]),
-                    {noreply, State};
-                {{ReceiverPid, Ref}, NInflight} ->
-                    case is_pid(ReceiverPid) andalso is_process_alive(ReceiverPid) of
-                        true ->
-                            ReceiverPid ! {channel_reply, Ref, {ok, Result}};
-                        false ->
-                            lager:warning("[tcp_channel] get publish response message: ~p, packet_id: ~p, but receiver_pid is deaded", [Resp, Id])
-                    end,
-                    {noreply, State#state{inflight = NInflight}}
-            end;
-        #{<<"id">> := Id, <<"error">> := #{<<"code">> := _Code, <<"message">> := Error}} ->
-            case maps:take(Id, Inflight) of
-                error ->
-                    lager:warning("[tcp_channel] get unknown publish response message: ~p, packet_id: ~p", [Resp, Id]),
-                    {noreply, State};
-                {{ReceiverPid, Ref}, NInflight} ->
-                    case is_pid(ReceiverPid) andalso is_process_alive(ReceiverPid) of
-                        true ->
-                            ReceiverPid ! {channel_reply, Ref, {error, Error}};
-                        false ->
-                            lager:warning("[tcp_channel] get publish response message: ~p, packet_id: ~p, but receiver_pid is deaded", [Resp, Id])
-                    end,
-                    {noreply, State#state{inflight = NInflight}}
-            end
-    end;
-
-%% 超时逻辑处理
-handle_info({timeout, _, {pending_timeout, Id}}, State = #state{inflight = Inflight}) ->
-    case maps:take(Id, Inflight) of
-        error ->
-            {noreply, State};
-        {{ReceiverPid, Ref}, NInflight} ->
-            case is_pid(ReceiverPid) andalso is_process_alive(ReceiverPid) of
-                true ->
-                    ReceiverPid ! {channel_reply, Ref, {error, <<"timeout">>}};
-                false ->
-                    ok
-            end,
-            {noreply, State#state{inflight = NInflight}}
-    end;
-
-%% 订阅的消息
-handle_info({topic_broadcast, Topic, Content}, State = #state{socket = Socket}) ->
-    Packet = jiffy:encode(#{<<"topic">> => Topic, <<"content">> => Content}, [force_utf8]),
-    ok = gen_tcp:send(Socket, <<?PACKET_PUB:8, Packet/binary>>),
-
-    {noreply, State};
-
-%% service进程关闭
-handle_info({'DOWN', _Ref, process, ServicePid, Reason}, State = #state{service_pid = ServicePid}) ->
-    lager:debug("[tcp_channel] service_pid: ~p, exited: ~p", [ServicePid, Reason]),
-    {stop, normal, State#state{service_pid = undefined}};
-
-handle_info({tcp_error, Socket, Reason}, State = #state{socket = Socket, service_id = ServiceId}) ->
-    lager:debug("[tcp_channel] tcp_error: ~p, assoc service: ~p", [Reason, ServiceId]),
-    {stop, normal, State};
-handle_info({tcp_closed, Socket}, State = #state{socket = Socket, service_id = ServiceId}) ->
-    lager:debug("[tcp_channel] tcp_closed: ~p, assoc service: ~p", [Socket, ServiceId]),
-    {stop, normal, State}.
-
-%% @private
-%% @doc This function is called by a gen_server when it is about to
-%% terminate. It should be the opposite of Module:init/1 and do any
-%% necessary cleaning up. When it returns, the gen_server terminates
-%% with Reason. The return value is ignored.
--spec(terminate(Reason :: (normal | shutdown | {shutdown, term()} | term()),
-    State :: #state{}) -> term()).
-terminate(_Reason, _State = #state{}) ->
-    ok.
-
-%% @private
-%% @doc Convert process state when code is changed
--spec(code_change(OldVsn :: term() | {down, term()}, State :: #state{},
-    Extra :: term()) ->
-    {ok, NewState :: #state{}} | {error, Reason :: term()}).
-code_change(_OldVsn, State = #state{}, _Extra) ->
-    {ok, State}.
-
-%%%===================================================================
-%%% Internal functions
-%%%===================================================================
-
-%% 注册
-handle_request(#{<<"id">> := Id, <<"method">> := <<"register">>, <<"params">> := #{<<"service_id">> := ServiceId}}, State = #state{socket = Socket}) ->
-    case efka_service:get_pid(ServiceId) of
-        undefined ->
-            lager:warning("[efka_tcp_channel] service_id: ~p, not running", [ServiceId]),
-            Packet = json_error(Id, -1, <<"service not running">>),
-            ok = gen_tcp:send(Socket, <<?PACKET_RESPONSE:8, Packet/binary>>),
-            {stop, normal, State};
-        ServicePid when is_pid(ServicePid) ->
-            case efka_service:attach_channel(ServicePid, self()) of
-                ok ->
-                    Packet = json_result(Id, <<"ok">>),
-                    erlang:monitor(process, ServicePid),
-
-                    ok = gen_tcp:send(Socket, <<?PACKET_RESPONSE:8, Packet/binary>>),
-                    {ok, State#state{service_id = ServiceId, service_pid = ServicePid, is_registered = true}};
-                {error, Error} ->
-                    lager:warning("[efka_tcp_channel] service_id: ~p, attach_channel get error: ~p", [ServiceId, Error]),
-                    Packet = json_error(Id, -1, Error),
-                    ok = gen_tcp:send(Socket, <<?PACKET_RESPONSE:8, Packet/binary>>),
-                    {stop, normal, State}
-            end
-    end;
-
-%% 请求参数
-handle_request(#{<<"id">> := Id, <<"method">> := <<"request_config">>}, State = #state{socket = Socket, service_pid = ServicePid, is_registered = true}) ->
-    {ok, ConfigJson} = efka_service:request_config(ServicePid),
-    Packet = json_result(Id, ConfigJson),
-    ok = gen_tcp:send(Socket, <<?PACKET_RESPONSE:8, Packet/binary>>),
-    {ok, State};
-
-%% 数据项
-handle_request(#{<<"id">> := 0, <<"method">> := <<"metric_data">>, <<"params">> := #{<<"device_uuid">> := DeviceUUID, <<"metric">> := Metric}}, State = #state{service_pid = ServicePid, is_registered = true}) ->
-    efka_service:metric_data(ServicePid, DeviceUUID, Metric),
-    {ok, State};
-
-%% Event事件
-handle_request(#{<<"id">> := 0, <<"method">> := <<"event">>, <<"params">> := #{<<"event_type">> := EventType, <<"body">> := Body}}, State = #state{service_pid = ServicePid, is_registered = true}) ->
-    efka_service:send_event(ServicePid, EventType, Body),
-    {ok, State};
-
-%% 订阅事件
-handle_request(#{<<"id">> := 0, <<"method">> := <<"subscribe">>, <<"params">> := #{<<"topic">> := Topic}}, State = #state{is_registered = true}) ->
-    efka_subscription:subscribe(Topic, self()),
-    {ok, State}.
-
-%% 采用32位编码
--spec next_packet_id(PacketId :: integer()) -> NextPacketId :: integer().
-next_packet_id(PacketId) when PacketId >= 4294967295 ->
-    1;
-next_packet_id(PacketId) ->
-    PacketId + 1.
-
--spec json_result(Id :: integer(), Result :: term()) -> binary().
-json_result(Id, Result) when is_integer(Id) ->
-    Response = #{
-        <<"id">> => Id,
-        <<"result">> => Result
-    },
-    jiffy:encode(Response, [force_utf8]).
-
--spec json_error(Id :: integer(), Code :: integer(), Message :: binary()) -> binary().
-json_error(Id, Code, Message) when is_integer(Id), is_integer(Code), is_binary(Message) ->
-    Response = #{
-        <<"id">> => Id,
-        <<"error">> => #{
-            <<"code">> => Code,
-            <<"message">> => Message
-        }
-    },
-    jiffy:encode(Response, [force_utf8]).

apps/efka/src/efka_tcp_server.erl

@@ -1,46 +0,0 @@
-%%%-------------------------------------------------------------------
-%%% @author anlicheng
-%%% @copyright (C) 2025, <COMPANY>
-%%% @doc
-%%%
-%%% @end
-%%% Created : 29. 4月 2025 23:24
-%%%-------------------------------------------------------------------
--module(efka_tcp_server).
--author("anlicheng").
-
-%% API
--export([start_link/0, init/0]).
-
-start_link() ->
-    {ok, spawn_link(?MODULE, init, [])}.
-
-%% 监听循环
-init() ->
-    {ok, TcpServerProps} = application:get_env(efka, tcp_server),
-    Port = proplists:get_value(port, TcpServerProps),
-
-    case gen_tcp:listen(Port, [binary, {packet, 4}, {active, false}, {reuseaddr, true}]) of
-        {ok, ListenSocket} ->
-            lager:debug("[efka_tcp_server] Server started on port ~p~n", [Port]),
-            main_loop(ListenSocket);
-        {error, Reason} ->
-            lager:debug("[efka_tcp_server] Failed to start server: ~p~n", [Reason]),
-            exit(Reason)
-    end.
-
-main_loop(ListenSocket) ->
-    case gen_tcp:accept(ListenSocket) of
-        {ok, Socket} ->
-            % 为每个新连接生成一个处理进程
-            {ok, ChannelPid} = efka_tcp_sup:start_child(Socket),
-            ok = gen_tcp:controlling_process(Socket, ChannelPid),
-            % 继续监听下一个连接
-            main_loop(ListenSocket);
-        {error, closed} ->
-            lager:debug("[efka_tcp_server] Server socket closed"),
-            exit(tcp_closed);
-        {error, Reason} ->
-            lager:debug("[efka_tcp_server] Accept error: ~p", [Reason]),
-            exit(Reason)
-    end.

apps/efka/src/efka_tcp_sup.erl

@@ -1,43 +0,0 @@
-%%%-------------------------------------------------------------------
-%% @doc efka top level supervisor.
-%% @end
-%%%-------------------------------------------------------------------
-
--module(efka_tcp_sup).
-
--behaviour(supervisor).
-
--export([start_link/0, start_child/1]).
-
--export([init/1]).
-
--define(SERVER, ?MODULE).
-
-start_link() ->
-    supervisor:start_link({local, ?SERVER}, ?MODULE, []).
-
-%% sup_flags() = #{strategy => strategy(),         % optional
-%%                 intensity => non_neg_integer(), % optional
-%%                 period => pos_integer()}        % optional
-%% child_spec() = #{id => child_id(),       % mandatory
-%%                  start => mfargs(),      % mandatory
-%%                  restart => restart(),   % optional
-%%                  shutdown => shutdown(), % optional
-%%                  type => worker(),       % optional
-%%                  modules => modules()}   % optional
-init([]) ->
-    SupFlags = #{strategy => simple_one_for_one, intensity => 0, period => 1},
-    ChildSpec = #{
-        id => efka_tcp_channel,
-        start => {efka_tcp_channel, start_link, []},
-        restart => temporary,
-        type => worker
-    },
-    {ok, {SupFlags, [ChildSpec]}}.
-
-%% internal functions
-
-start_child(Socket) ->
-    supervisor:start_child(?MODULE, [Socket]).
-
-

apps/efka/src/efka_transport.erl

@@ -8,15 +8,13 @@
 %%%-------------------------------------------------------------------
 -module(efka_transport).
 -author("anlicheng").
--include("message_pb.hrl").
--include("efka.hrl").
+-include("message.hrl").
 
 -behaviour(gen_server).
 
 %% API
 -export([start_monitor/3]).
--export([connect/1, auth_request/2, send/3, async_call_reply/3, stop/1]).
--export([request/3]).
+-export([connect/1, auth_request/2, send/2, rpc_reply/3, stop/1]).
 
 %% gen_server callbacks
 -export([init/1, handle_call/3, handle_cast/2, handle_info/2, terminate/2, code_change/3]).
@@ -27,10 +25,7 @@
     parent_pid :: pid(),
     host :: string(),
     port :: integer(),
-    socket :: undefined | ssl:sslsocket(),
-    packet_id = 1,
-    %% 通过packet_id建立请求和响应的关系
-    inflight = #{}
+    socket :: undefined | ssl:sslsocket()
 }).
 
 %%%===================================================================
@@ -41,25 +36,19 @@
 auth_request(Pid, AuthBin) when is_pid(Pid), is_binary(AuthBin) ->
     gen_server:cast(Pid, {auth_request, AuthBin}).
 
--spec request(Pid :: pid(), Method :: integer(), ReqBin :: binary()) -> Ref :: reference().
-request(Pid, Method, ReqBin) when is_pid(Pid), is_binary(ReqBin) ->
-    Ref = make_ref(),
-    gen_server:cast(Pid, {request, Ref, Method, ReqBin}),
-    Ref.
-
 -spec connect(Pid :: pid()) -> no_return().
 connect(Pid) when is_pid(Pid) ->
     gen_server:cast(Pid, connect).
 
--spec send(Pid :: pid(), Method :: integer(), Packet :: binary()) -> no_return().
-send(Pid, Method, Packet) when is_pid(Pid), is_integer(Method), is_binary(Packet) ->
-    gen_server:cast(Pid, {send, Method, Packet}).
+-spec send(Pid :: pid(), Packet :: binary()) -> no_return().
+send(Pid, Packet) when is_pid(Pid), is_binary(Packet) ->
+    gen_server:cast(Pid, {send, Packet}).
 
--spec async_call_reply(Pid :: pid() | undefined, PacketId :: integer(), Response :: binary()) -> no_return().
-async_call_reply(undefined, PacketId, Response) when is_integer(PacketId), is_binary(Response) ->
+-spec rpc_reply(Pid :: pid() | undefined, PacketId :: integer(), Response :: binary()) -> no_return().
+rpc_reply(undefined, PacketId, Response) when is_integer(PacketId), is_binary(Response) ->
     ok;
-async_call_reply(Pid, PacketId, Response) when is_pid(Pid), is_integer(PacketId), is_binary(Response) ->
-    gen_server:cast(Pid, {async_call_reply, PacketId, Response}).
+rpc_reply(Pid, PacketId, Reply) when is_pid(Pid), is_integer(PacketId), is_binary(Reply) ->
+    gen_server:cast(Pid, {rpc_reply, PacketId, Reply}).
 
 %% 关闭的时候不一定能成功，可能关闭的时候；transport进程已经退出了
 -spec stop(Pid :: pid() | undefined) -> ok.
@@ -123,34 +112,31 @@ handle_cast(connect, State = #state{host = Host, port = Port, parent_pid = Paren
     end;
 
 %% auth校验
-handle_cast({auth_request, AuthRequestBin}, State = #state{parent_pid = ParentPid, socket = Socket, packet_id = PacketId}) ->
-    ok = ssl:send(Socket, <<?PACKET_REQUEST, PacketId:32, ?METHOD_AUTH, AuthRequestBin/binary>>),
+handle_cast({auth_request, AuthRequestBin}, State = #state{parent_pid = ParentPid, socket = Socket}) ->
+    PacketId = 1,
+    ok = ssl:send(Socket, <<?PACKET_REQUEST, PacketId:32, AuthRequestBin/binary>>),
     %% 需要等待auth返回的结果
     receive
         {ssl, Socket, <<?PACKET_RESPONSE, PacketId:32, ReplyBin/binary>>} ->
-            ParentPid ! {auth_reply, {ok, ReplyBin}},
-            {noreply, State#state{packet_id = PacketId + 1}};
+            {ok, #auth_reply{} = Reply} = message_codec:decode(ReplyBin),
+            ParentPid ! {auth_reply, {ok, Reply}},
+            {noreply, State};
         {ssl, Socket, Info} ->
             lager:warning("[efka_transport] get invalid auth_reply: ~p", [Info]),
             ParentPid ! {auth_reply, {error, invalid_auth_reply}},
-            {noreply, State#state{packet_id = PacketId + 1}}
+            {noreply, State}
     after 5000 ->
         ParentPid ! {auth_reply, {error, timeout}},
-        {noreply, State#state{packet_id = PacketId + 1}}
+        {noreply, State}
     end;
 
-%% 提交请求
-handle_cast({request, Ref, Method, ReqBin}, State = #state{socket = Socket, packet_id = PacketId, inflight = Inflight}) ->
-    ok = ssl:send(Socket, <<?PACKET_REQUEST, PacketId:32, Method:8, ReqBin/binary>>),
-    {noreply, State#state{packet_id = PacketId + 1, inflight = maps:put(PacketId, Ref, Inflight)}};
-
-handle_cast({send, Method, Packet}, State = #state{socket = Socket}) ->
-    ok = ssl:send(Socket, <<?PACKET_REQUEST, Method:8, Packet/binary>>),
+handle_cast({send, Packet}, State = #state{socket = Socket}) ->
+    ok = ssl:send(Socket, <<?PACKET_CAST, Packet/binary>>),
     {noreply, State};
 
 %% 服务push的消息的回复
-handle_cast({async_call_reply, PacketId, Response}, State = #state{socket = Socket}) ->
-    ok = ssl:send(Socket, <<?PACKET_ASYNC_CALL_REPLY, PacketId:32, Response/binary>>),
+handle_cast({rpc_reply, PacketId, Reply}, State = #state{socket = Socket}) ->
+    ok = ssl:send(Socket, <<?PACKET_RESPONSE, PacketId:32, Reply/binary>>),
     {noreply, State}.
 
 %% @private
@@ -160,29 +146,16 @@ handle_cast({async_call_reply, PacketId, Response}, State = #state{socket = Sock
     {noreply, NewState :: #state{}, timeout() | hibernate} |
     {stop, Reason :: term(), NewState :: #state{}}).
 %% 服务器主动推送的数据，有packetId的是要求返回的；为0的表示不需要返回值
-handle_info({ssl, Socket, <<?PACKET_COMMAND, CommandType:8, Command/binary>>}, State = #state{socket = Socket, parent_pid = ParentPid}) ->
-    ParentPid ! {server_command, CommandType, Command},
+handle_info({ssl, Socket, <<?PACKET_CAST, CastBin/binary>>}, State = #state{socket = Socket, parent_pid = ParentPid}) ->
+    {ok, CastRequest} = message_codec:decode(CastBin),
+    ParentPid ! {server_cast, CastRequest},
     {noreply, State};
 
-handle_info({ssl, Socket, <<?PACKET_PUB, PubBin/binary>>}, State = #state{socket = Socket, parent_pid = ParentPid}) ->
-    #pub{topic = Topic, content = Content} = message_pb:decode_msg(PubBin, pub),
-    ParentPid ! {server_pub, Topic, Content},
+handle_info({ssl, Socket, <<?PACKET_REQUEST, PacketId:32, RPCRequestBin/binary>>}, State = #state{socket = Socket, parent_pid = ParentPid}) ->
+    {ok, RPCRequest} = message_codec:decode(RPCRequestBin),
+    ParentPid ! {server_rpc, PacketId, RPCRequest},
     {noreply, State};
 
-handle_info({ssl, Socket, <<?PACKET_ASYNC_CALL, PacketId:32, AsyncCallBin/binary>>}, State = #state{socket = Socket, parent_pid = ParentPid}) ->
-    ParentPid ! {server_async_call, PacketId, AsyncCallBin},
-    {noreply, State};
-
-%% efka:request <-> iot:response
-handle_info({ssl, Socket, <<?PACKET_RESPONSE, PacketId:32, ReplyBin/binary>>}, State = #state{socket = Socket, inflight = Inflight, parent_pid = ParentPid}) ->
-    case maps:take(PacketId, Inflight) of
-        error ->
-            {noreply, State};
-        {Ref, NInflight} ->
-            ParentPid ! {server_reply, Ref, ReplyBin},
-            {noreply, State#state{inflight = NInflight}}
-    end;
-
 handle_info({ssl_error, Socket, Reason}, State = #state{socket = Socket}) ->
     lager:debug("[efka_transport] ssl error: ~p", [Reason]),
     {stop, normal, State};
@@ -190,8 +163,7 @@ handle_info({ssl_error, Socket, Reason}, State = #state{socket = Socket}) ->
 handle_info({ssl_closed, Socket}, State = #state{socket = Socket}) ->
     {stop, normal, State};
 
-handle_info({timeout, _, ping_ticker}, State = #state{socket = Socket}) ->
-    ok = ssl:send(Socket, <<?PACKET_PING>>),
+handle_info({timeout, _, ping_ticker}, State) ->
     ping_ticker(),
     {noreply, State};
 

apps/efka/src/efka_util.erl

@@ -14,6 +14,7 @@
 -export([timestamp/0, number_format/2, timestamp_ms/0, float_to_binary/2, int_format/2]).
 -export([chunks/2, rand_bytes/1, uuid/0, md5/1, sha_uuid/0]).
 -export([json_data/1, json_error/2]).
+-export([starts_with/2, file_md5/1]).
 
 get_file_md5(FilePath) when is_list(FilePath) ->
     {ok, FileData} = file:read_file(FilePath),
@@ -103,3 +104,28 @@ sha_uuid() ->
     Salt = crypto:strong_rand_bytes(32),
     Str = string:lowercase(binary:encode_hex(crypto:hash(sha256, Salt))),
     binary:part(Str, 1, 32).
+
+-spec starts_with(Binary :: binary(), Prefix :: binary()) -> boolean().
+starts_with(Binary, Prefix) when is_binary(Binary), is_binary(Prefix) ->
+    PrefixSize = byte_size(Prefix),
+    case Binary of
+        <<Prefix:PrefixSize/binary, _Rest/binary>> -> true;
+        _ -> false
+    end.
+
+-spec file_md5(FilePath :: string()) -> Md5 :: string().
+file_md5(FilePath) when is_list(FilePath) ->
+    {ok, F} = file:open(FilePath, [read, binary]),
+    Digest = md5_loop(F, crypto:hash_init(md5)),
+    file:close(F),
+    lists:flatten(io_lib:format("~32.16.0b", [binary:decode_unsigned(Digest)])).
+
+md5_loop(F, Context) ->
+    %% 每次读取 1MB，可调整块大小
+    case file:read(F, 1024 * 1024) of
+        eof ->
+            crypto:hash_final(Context);
+        {ok, Bin} ->
+            md5_loop(F, crypto:hash_update(Context, Bin))
+    end.
+

apps/efka/src/message/message_codec.erl

@@ -0,0 +1,141 @@
+%%%-------------------------------------------------------------------
+%%% @author anlicheng
+%%% @copyright (C) 2025, <COMPANY>
+%%% @doc
+%%%
+%%% @end
+%%% Created : 17. 9月 2025 16:05
+%%%-------------------------------------------------------------------
+-module(message_codec).
+-author("anlicheng").
+-include("message.hrl").
+
+-define(I8, 1).
+-define(I16, 2).
+-define(I32, 3).
+-define(Bytes, 4).
+
+%% API
+-export([encode/2, decode/1]).
+
+-spec encode(MessageType :: integer(), Message :: any()) -> binary().
+encode(MessageType, Message) when is_integer(MessageType) ->
+    Bin = encode0(Message),
+    <<MessageType, Bin/binary>>.
+encode0(#auth_request{uuid = UUID, username = Username, salt = Salt, token = Token, timestamp = Timestamp}) ->
+    iolist_to_binary([
+        marshal(?Bytes, UUID),
+        marshal(?Bytes, Username),
+        marshal(?Bytes, Salt),
+        marshal(?Bytes, Token),
+        marshal(?I32, Timestamp)
+    ]);
+encode0(#auth_reply{code = Code, payload = Payload}) ->
+    iolist_to_binary([
+        marshal(?I32, Code),
+        marshal(?Bytes, Payload)
+    ]);
+encode0(#jsonrpc_reply{result = Result, error = undefined}) ->
+    ResultBin = erlang:term_to_binary(#{<<"result">> => Result}),
+    iolist_to_binary([
+        marshal(?Bytes, ResultBin)
+    ]);
+encode0(#jsonrpc_reply{result = undefined, error = Error}) ->
+    ResultBin = erlang:term_to_binary(#{<<"error">> => Error}),
+    iolist_to_binary([
+        marshal(?Bytes, ResultBin)
+    ]);
+encode0(#pub{topic = Topic, qos = Qos, content = Content}) ->
+    iolist_to_binary([
+        marshal(?Bytes, Topic),
+        marshal(?I8, Qos),
+        marshal(?Bytes, Content)
+    ]);
+encode0(#command{command_type = CommandType, command = Command}) ->
+    iolist_to_binary([
+        marshal(?I32, CommandType),
+        marshal(?Bytes, Command)
+    ]);
+
+encode0(#jsonrpc_request{method = Method, params = Params}) ->
+    ReqBody = erlang:term_to_binary(#{<<"method">> => Method, <<"params">> => Params}),
+    iolist_to_binary([
+        marshal(?Bytes, ReqBody)
+    ]);
+encode0(#data{route_key = RouteKey, metric = Metric}) ->
+    iolist_to_binary([
+        marshal(?Bytes, RouteKey),
+        marshal(?Bytes, Metric)
+    ]);
+encode0(#task_event_stream{task_id = TaskId, type = Type, stream = Stream}) ->
+    iolist_to_binary([
+        marshal(?I32, TaskId),
+        marshal(?Bytes, Type),
+        marshal(?Bytes, Stream)
+    ]).
+
+-spec decode(Bin :: binary()) -> {ok, Message :: any()} | error.
+decode(<<PacketType:8, Packet/binary>>) ->
+    case unmarshal(Packet) of
+        {ok, Fields} ->
+            decode0(PacketType, Fields);
+        error ->
+            error
+    end.
+decode0(?MESSAGE_AUTH_REQUEST, [UUID, Username, Salt, Token, Timestamp]) ->
+    {ok, #auth_request{uuid = UUID, username = Username, salt = Salt, token = Token, timestamp = Timestamp}};
+decode0(?MESSAGE_JSONRPC_REPLY, [ReplyBin]) ->
+    case erlang:binary_to_term(ReplyBin) of
+        #{<<"result">> := Result} ->
+            {ok, #jsonrpc_reply{result = Result}};
+        #{<<"error">> := Error} ->
+            {ok, #jsonrpc_reply{error = Error}};
+        _ ->
+            error
+    end;
+decode0(?MESSAGE_PUB, [Topic, Qos, Content]) ->
+    {ok, #pub{topic = Topic, qos = Qos, content = Content}};
+decode0(?MESSAGE_COMMAND, [CommandType, Command]) ->
+    {ok, #command{command_type = CommandType, command = Command}};
+decode0(?MESSAGE_AUTH_REPLY, [Code, Payload]) ->
+    {ok, #auth_reply{code = Code, payload = Payload}};
+decode0(?MESSAGE_JSONRPC_REQUEST, [ReqBody]) ->
+    #{<<"method">> := Method, <<"params">> := Params} = erlang:binary_to_term(ReqBody),
+    {ok, #jsonrpc_request{method = Method, params = Params}};
+decode0(?MESSAGE_DATA, [RouteKey, Metric]) ->
+    {ok, #data{route_key = RouteKey, metric = Metric}};
+decode0(?MESSAGE_EVENT_STREAM, [TaskId, Type, Stream]) ->
+    {ok, #task_event_stream{task_id = TaskId, type = Type, stream = Stream}};
+decode0(_, _) ->
+    error.
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%% helper methods
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+-spec marshal(Type :: integer(), Field :: any()) -> binary().
+marshal(?I8, Field) when is_integer(Field) ->
+    <<?I8, Field:8>>;
+marshal(?I16, Field) when is_integer(Field) ->
+    <<?I16, Field:16>>;
+marshal(?I32, Field) when is_integer(Field) ->
+    <<?I32, Field:32>>;
+marshal(?Bytes, Field) when is_binary(Field) ->
+    Len = byte_size(Field),
+    <<?Bytes, Len:16, Field/binary>>.
+
+-spec unmarshal(Bin :: binary()) -> {ok, Components :: [any()]} | error.
+unmarshal(Bin) when is_binary(Bin) ->
+    unmarshal(Bin, []).
+unmarshal(<<>>, Acc) ->
+    {ok, lists:reverse(Acc)};
+unmarshal(<<?I8, F:8, Rest/binary>>, Acc) ->
+    unmarshal(Rest, [F|Acc]);
+unmarshal(<<?I16, F:16, Rest/binary>>, Acc) ->
+    unmarshal(Rest, [F|Acc]);
+unmarshal(<<?I32, F:32, Rest/binary>>, Acc) ->
+    unmarshal(Rest, [F|Acc]);
+unmarshal(<<?Bytes, Len:16, F:Len/binary, Rest/binary>>, Acc) ->
+    unmarshal(Rest, [F|Acc]);
+unmarshal(_, _) ->
+    error.

apps/efka/src/mnesia/cache_model.erl

@@ -1,74 +0,0 @@
-%%%-------------------------------------------------------------------
-%%% @author aresei
-%%% @copyright (C) 2023, <COMPANY>
-%%% @doc
-%%%
-%%% @end
-%%% Created : 04. 7月 2023 12:31
-%%%-------------------------------------------------------------------
--module(cache_model).
--author("aresei").
--include("efka_tables.hrl").
--include_lib("stdlib/include/qlc.hrl").
-
--define(TAB, cache).
-
-%% API
--export([create_table/0]).
--export([insert/2, get_all_cache/0, fetch_next/0, delete/1, next_id/0]).
--export([first_key/0]).
-
-create_table() ->
-    %% id生成器
-    {atomic, ok} = mnesia:create_table(cache, [
-        {attributes, record_info(fields, cache)},
-        {record_name, cache},
-        {disc_copies, [node()]},
-        {type, ordered_set}
-    ]).
-
-next_id() ->
-    id_generator_model:next_id(?TAB).
-
--spec insert(Method :: integer(), Data :: binary()) -> ok | {error, Reason :: any()}.
-insert(Method, Data) when is_integer(Method), is_binary(Data) ->
-    Cache = #cache{id = next_id(), method = Method, data = Data},
-    case mnesia:transaction(fun() -> mnesia:write(?TAB, Cache, write) end) of
-        {'atomic', ok} ->
-            ok;
-        {'aborted', Reason} ->
-            {error, Reason}
-    end.
-
-fetch_next() ->
-    case mnesia:dirty_first(?TAB) of
-        '$end_of_table' ->
-            error;
-        Id ->
-            [Entry] = mnesia:dirty_read(?TAB, Id),
-            {ok, Entry}
-    end.
-
-delete(Id) when is_integer(Id) ->
-    case mnesia:transaction(fun() -> mnesia:delete(?TAB, Id, write) end) of
-        {'atomic', ok} ->
-            ok;
-        {'aborted', Reason} ->
-            {error, Reason}
-    end.
-
--spec get_all_cache() -> [#cache{}].
-get_all_cache() ->
-    Fun = fun() ->
-        Q = qlc:q([E || E <- mnesia:table(?TAB)]),
-        qlc:e(Q)
-          end,
-    case mnesia:transaction(Fun) of
-        {'atomic', Res} ->
-            Res;
-        {'aborted', _} ->
-            []
-    end.
-
-first_key() ->
-    mnesia:dirty_first(?TAB).

apps/efka/src/mnesia/id_generator_model.erl

@@ -1,26 +0,0 @@
-%%%-------------------------------------------------------------------
-%%% @author anlicheng
-%%% @copyright (C) 2025, <COMPANY>
-%%% @doc
-%%%
-%%% @end
-%%% Created : 06. 5月 2025 10:32
-%%%-------------------------------------------------------------------
--module(id_generator_model).
--author("anlicheng").
--include("efka_tables.hrl").
-
-%% API
--export([create_table/0, next_id/1]).
-
-create_table() ->
-    %% id生成器
-    {atomic, ok} = mnesia:create_table(id_generator, [
-        {attributes, record_info(fields, id_generator)},
-        {record_name, id_generator},
-        {disc_copies, [node()]},
-        {type, ordered_set}
-    ]).
-
-next_id(Tab) when is_atom(Tab) ->
-    mnesia:dirty_update_counter(id_generator, Tab, 1).

apps/efka/src/mnesia/service_model.erl

@@ -1,140 +0,0 @@
-%%%-------------------------------------------------------------------
-%%% @author aresei
-%%% @copyright (C) 2023, <COMPANY>
-%%% @doc
-%%%
-%%% @end
-%%% Created : 04. 7月 2023 12:31
-%%%-------------------------------------------------------------------
--module(service_model).
--author("aresei").
--include("efka_tables.hrl").
--include_lib("stdlib/include/qlc.hrl").
-
--define(TAB, service).
-
-%% API
--export([create_table/0]).
--export([insert/1, get_all_services/0, get_all_service_ids/0, get_running_services/0]).
--export([get_config_json/1, set_config/2, get_service/1, get_status/1, change_status/2]).
--export([display_services/0]).
-
-create_table() ->
-    %% id生成器
-    {atomic, ok} = mnesia:create_table(service, [
-        {attributes, record_info(fields, service)},
-        {record_name, service},
-        {disc_copies, [node()]},
-        {type, ordered_set}
-    ]).
-
-insert(Service = #service{}) ->
-    case mnesia:transaction(fun() -> mnesia:write(?TAB, Service, write) end) of
-        {'atomic', Res} ->
-            Res;
-        {'aborted', Reason} ->
-            {error, Reason}
-    end.
-
-change_status(ServiceId, NewStatus) when is_binary(ServiceId), is_integer(NewStatus) ->
-    Fun = fun() ->
-        case mnesia:read(?TAB, ServiceId, write) of
-            [] ->
-                mnesia:abort(<<"service not found">>);
-            [Service] ->
-                mnesia:write(?TAB, Service#service{status = NewStatus}, write)
-        end
-          end,
-    case mnesia:transaction(Fun) of
-        {'atomic', ok} ->
-            ok;
-        {'aborted', Reason} ->
-            {error, Reason}
-    end.
-
--spec set_config(ServiceId :: binary(), ConfigJson :: binary()) -> ok | {error, Reason :: any()}.
-set_config(ServiceId, ConfigJson) when is_binary(ServiceId), is_binary(ConfigJson) ->
-    Fun = fun() ->
-        case mnesia:read(?TAB, ServiceId, write) of
-            [] ->
-                mnesia:abort(<<"service not found">>);
-            [S] ->
-                mnesia:write(?TAB, S#service{config_json = ConfigJson}, write)
-        end
-          end,
-    case mnesia:transaction(Fun) of
-        {'atomic', ok} ->
-            ok;
-        {'aborted', Reason} ->
-            {error, Reason}
-    end.
-
--spec get_config_json(ServiceId :: binary()) -> error | {ok, ConfigJson :: binary()}.
-get_config_json(ServiceId) when is_binary(ServiceId) ->
-    case mnesia:dirty_read(?TAB, ServiceId) of
-        [] ->
-            error;
-        [#service{config_json = ConfigJson}] ->
-            {ok, ConfigJson}
-    end.
-
--spec get_status(ServiceId :: binary()) -> Status :: integer().
-get_status(ServiceId) when is_binary(ServiceId) ->
-    case mnesia:dirty_read(?TAB, ServiceId) of
-        [] ->
-            0;
-        [#service{status = Status}] ->
-            Status
-    end.
-
--spec get_service(ServiceId :: binary()) -> error | {ok, Service :: #service{}}.
-get_service(ServiceId) when is_binary(ServiceId) ->
-    case mnesia:dirty_read(?TAB, ServiceId) of
-        [] ->
-            error;
-        [Service] ->
-            {ok, Service}
-    end.
-
--spec get_all_services() -> [#service{}].
-get_all_services() ->
-    Fun = fun() ->
-        Q = qlc:q([E || E <- mnesia:table(?TAB)]),
-        qlc:e(Q)
-          end,
-
-    case mnesia:transaction(Fun) of
-        {'atomic', Res} ->
-            Res;
-        {'aborted', _} ->
-            []
-    end.
-
--spec get_all_service_ids() -> [ServiceId :: binary()].
-get_all_service_ids() ->
-    mnesia:dirty_all_keys(?TAB).
-
--spec get_running_services() -> {ok, [#service{}]} | {error, Reason :: term()}.
-get_running_services() ->
-    F = fun() ->
-        Q = qlc:q([E || E <- mnesia:table(?TAB), E#service.status == 1]),
-        qlc:e(Q)
-        end,
-    case mnesia:transaction(F) of
-        {atomic, Services} ->
-            {ok, Services};
-        {aborted, Error} ->
-            {error, Error}
-    end.
-
-display_services() ->
-    F = fun() ->
-        Q = qlc:q([E || E <- mnesia:table(?TAB)]),
-        qlc:e(Q)
-        end,
-    case mnesia:transaction(F) of
-        {atomic, Services} ->
-            {ok, Services};
-        {aborted, Error} ->
-            {error, Error}
-    end.

apps/efka/src/mnesia/task_log_model.erl

@@ -1,46 +0,0 @@
-%%%-------------------------------------------------------------------
-%%% @author aresei
-%%% @copyright (C) 2023, <COMPANY>
-%%% @doc
-%%%
-%%% @end
-%%% Created : 04. 7月 2023 12:31
-%%%-------------------------------------------------------------------
--module(task_log_model).
--author("aresei").
--include("efka_tables.hrl").
--include_lib("stdlib/include/qlc.hrl").
-
--define(TAB, task_log).
-
-%% API
--export([create_table/0]).
--export([insert/2, get_logs/1]).
-
-create_table() ->
-    %% id生成器
-    {atomic, ok} = mnesia:create_table(task_log, [
-        {attributes, record_info(fields, task_log)},
-        {record_name, task_log},
-        {disc_copies, [node()]},
-        {type, ordered_set}
-    ]).
-
--spec insert(TaskId :: integer(), Logs :: [binary()]) -> ok | {error, Reason :: term()}.
-insert(TaskId, Logs) when is_integer(TaskId), is_list(Logs) ->
-    TaskLog = #task_log{task_id = TaskId, logs = Logs},
-    case mnesia:transaction(fun() -> mnesia:write(?TAB, TaskLog, write) end) of
-        {'atomic', Res} ->
-            Res;
-        {'aborted', Reason} ->
-            {error, Reason}
-    end.
-
--spec get_logs(TaskId :: integer()) -> Logs :: [binary()].
-get_logs(TaskId) when is_integer(TaskId) ->
-    case mnesia:dirty_read(?TAB, TaskId) of
-        [] ->
-            [];
-        [#task_log{logs = Logs}] ->
-            Logs
-    end.

apps/efka/src/models/cache_model.erl

@@ -8,13 +8,12 @@
 %%%-------------------------------------------------------------------
 -module(cache_model).
 -author("anlicheng").
--include("efka_tables.hrl").
 
 -behaviour(gen_server).
 
 %% API
 -export([start_link/0]).
--export([insert/2, fetch_next/0, delete/1, get_all_cache/0]).
+-export([insert/1, fetch_next/0, delete/1, get_all_cache/0]).
 
 %% gen_server callbacks
 -export([init/1, handle_call/3, handle_cast/2, handle_info/2, terminate/2, code_change/3]).
@@ -30,10 +29,9 @@
 %%% API
 %%%===================================================================
 
--spec insert(Method :: integer(), Data :: binary()) -> ok | {error, Reason :: any()}.
-insert(Method, Data) when is_integer(Method), is_binary(Data) ->
-    Cache = #cache{id = generate_id(), method = Method, data = Data},
-    gen_server:call(?SERVER, {insert, Cache}).
+-spec insert(Data :: binary()) -> ok | {error, Reason :: any()}.
+insert(Data) when is_binary(Data) ->
+    gen_server:call(?SERVER, {insert, {generate_id(), Data}}).
 
 fetch_next() ->
     gen_server:call(?SERVER, fetch_next).
@@ -41,7 +39,7 @@ fetch_next() ->
 delete(Id) when is_integer(Id) ->
     gen_server:call(?SERVER, {delete, Id}).
 
--spec get_all_cache() -> [#cache{}].
+-spec get_all_cache() -> [binary()].
 get_all_cache() ->
     gen_server:call(?SERVER, get_all_cache).
 
@@ -63,7 +61,7 @@ start_link() ->
 init([]) ->
     {ok, DetsDir} = application:get_env(efka, dets_dir),
     File = DetsDir ++ "cache.dets",
-    {ok, ?TAB} = dets:open_file(?TAB, [{file, File}, {type, bag}, {keypos, 2}]),
+    {ok, ?TAB} = dets:open_file(?TAB, [{file, File}, {type, bag}, {keypos, 1}]),
     {ok, #state{}}.
 
 %% @private

apps/efka/src/models/service_model.erl

@@ -14,6 +14,7 @@
 
 %% API
 -export([start_link/0]).
+-export([insert/1, change_status/2, get_status/1, get_service/1, get_all_services/0, get_running_services/0]).
 
 %% gen_server callbacks
 -export([init/1, handle_call/3, handle_cast/2, handle_info/2, terminate/2, code_change/3]).
@@ -35,14 +36,6 @@ insert(Service = #service{}) ->
 change_status(ServiceId, NewStatus) when is_binary(ServiceId), is_integer(NewStatus) ->
     gen_server:call(?SERVER, {change_status, ServiceId, NewStatus}).
 
--spec set_config(ServiceId :: binary(), ConfigJson :: binary()) -> ok | {error, Reason :: any()}.
-set_config(ServiceId, ConfigJson) when is_binary(ServiceId), is_binary(ConfigJson) ->
-    gen_server:call(?SERVER, {set_config, ServiceId, ConfigJson}).
-
--spec get_config_json(ServiceId :: binary()) -> error | {ok, ConfigJson :: binary()}.
-get_config_json(ServiceId) when is_binary(ServiceId) ->
-    gen_server:call(?SERVER, {get_config_json, ServiceId}).
-
 -spec get_status(ServiceId :: binary()) -> Status :: integer().
 get_status(ServiceId) when is_binary(ServiceId) ->
     gen_server:call(?SERVER, {get_status, ServiceId}).
@@ -55,11 +48,7 @@ get_service(ServiceId) when is_binary(ServiceId) ->
 get_all_services() ->
     gen_server:call(?SERVER, get_all_services).
 
--spec get_all_service_ids() -> [ServiceId :: binary()].
-get_all_service_ids() ->
-    gen_server:call(?SERVER, get_all_service_ids).
-
--spec get_running_services() -> {ok, [#service{}]} | {error, Reason :: term()}.
+-spec get_running_services() -> {ok, [#service{}]}.
 get_running_services() ->
     gen_server:call(?SERVER, get_running_services).
 
@@ -81,7 +70,7 @@ start_link() ->
 init([]) ->
     {ok, DetsDir} = application:get_env(efka, dets_dir),
     File = DetsDir ++ "service.dets",
-    {ok, ?TAB} = dets:open_file(?TAB, [{file, File}, {type, bag}, {keypos, 2}]),
+    {ok, ?TAB} = dets:open_file(?TAB, [{file, File}, {type, set}, {keypos, 2}]),
     {ok, #state{}}.
 
 %% @private
@@ -94,8 +83,18 @@ init([]) ->
     {noreply, NewState :: #state{}, timeout() | hibernate} |
     {stop, Reason :: term(), Reply :: term(), NewState :: #state{}} |
     {stop, Reason :: term(), NewState :: #state{}}).
-handle_call({insert, Service}, _From, State = #state{}) ->
-    ok = dets:insert(?TAB, Service),
+handle_call({insert, Service = #service{service_id = ServiceId}}, _From, State = #state{}) ->
+    case dets:lookup(?TAB, ServiceId) of
+        [] ->
+            ok = dets:insert(?TAB, Service);
+        [OldService] ->
+            NewService = OldService#service{
+                meta_data = Service#service.meta_data,
+                container_name = Service#service.container_name,
+                update_ts = Service#service.update_ts
+            },
+            ok = dets:insert(?TAB, NewService)
+    end,
     {reply, ok, State};
 
 handle_call({change_status, ServiceId, NewStatus}, _From, State = #state{}) ->
@@ -108,24 +107,6 @@ handle_call({change_status, ServiceId, NewStatus}, _From, State = #state{}) ->
             {reply, ok, State}
     end;
 
-handle_call({set_config, ServiceId, ConfigJson}, _From, State = #state{}) ->
-    case dets:lookup(?TAB, ServiceId) of
-        [] ->
-            {reply, {error, <<"service not found">>}, State};
-        [OldService] ->
-            NewService = OldService#service{config_json = ConfigJson},
-            ok = dets:insert(?TAB, NewService),
-            {reply, ok, State}
-    end;
-
-handle_call({get_config_json, ServiceId}, _From, State = #state{}) ->
-    case dets:lookup(?TAB, ServiceId) of
-        [] ->
-            {reply, error, State};
-        [#service{config_json = ConfigJson}] ->
-            {reply, {ok, ConfigJson}, State}
-    end;
-
 handle_call({get_status, ServiceId}, _From, State = #state{}) ->
     case dets:lookup(?TAB, ServiceId) of
         [] ->
@@ -141,7 +122,7 @@ handle_call(get_all_services, _From, State = #state{}) ->
 handle_call(get_running_services, _From, State = #state{}) ->
     Items = dets:foldl(fun(Record, Acc) -> [Record|Acc] end, [], ?TAB),
     RunningItems = lists:filter(fun(#service{status = Status}) -> Status =:= 1 end, lists:reverse(Items)),
-    {reply, RunningItems, State};
+    {reply, {ok, RunningItems}, State};
 
 handle_call(_Request, _From, State = #state{}) ->
     {reply, ok, State}.

apps/efka/src/tests/docker_commands_tests.erl

@@ -0,0 +1,104 @@
+%%%-------------------------------------------------------------------
+%%% @author anlicheng
+%%% @copyright (C) 2025, <COMPANY>
+%%% @doc
+%%%
+%%% @end
+%%% Created : 23. 9月 2025 17:23
+%%%-------------------------------------------------------------------
+-module(docker_commands_tests).
+-author("anlicheng").
+
+%% API
+-export([test_pull/0, test_commands/0, test_create_container/0]).
+
+test_pull() ->
+    Image = <<"docker.1ms.run/library/nginx:latest">>,
+    docker_commands:pull_image(Image, fun(Msg) -> lager:debug("msg is: ~p", [Msg]) end).
+
+test_commands() ->
+    Id = <<"redpanda-console">>,
+    StopRes = docker_commands:stop_container(Id),
+    lager:debug("stop res: ~p", [StopRes]),
+    StartRes = docker_commands:start_container(Id),
+    lager:debug("start res: ~p", [StartRes]).
+
+test_create_container() ->
+    M = #{
+        <<"image">> => <<"docker.1ms.run/library/nginx:latest">>,
+        <<"container_name">> => <<"my_nginx_new1">>,
+        <<"command">> => [
+            <<"nginx">>,
+            <<"-g">>,
+            <<"daemon off;">>
+        ],
+        <<"entrypoint">> => [
+            <<"/docker-entrypoint.sh">>
+        ],
+        <<"envs">> => [
+            <<"ENV1=val1">>,
+            <<"ENV2=val2">>
+        ],
+        <<"env_file">> => [
+            <<"./env.list">>
+        ],
+        <<"ports">> => [
+            <<"8080:80">>,
+            <<"443:443">>
+        ],
+        <<"expose">> => [
+            <<"80">>,
+            <<"443">>
+        ],
+        <<"volumes">> => [
+            <<"/host/data:/data">>,
+            <<"/host/log:/var/log">>
+        ],
+        <<"networks">> => [
+            <<"mynet">>
+        ],
+        <<"labels">> => #{
+            <<"role">> => <<"web">>,
+            <<"env">> => <<"prod">>
+        },
+        <<"restart">> => <<"always">>,
+        <<"user">> => <<"www-data">>,
+        <<"working_dir">> => <<"/app">>,
+        <<"hostname">> => <<"myhost">>,
+        <<"privileged">> => true,
+        <<"cap_add">> => [
+            <<"NET_ADMIN">>
+        ],
+        <<"cap_drop">> => [
+            <<"MKNOD">>
+        ],
+        <<"devices">> => [
+            <<"/dev/snd:/dev/snd">>
+        ],
+        <<"mem_limit">> => <<"512m">>,
+        <<"mem_reservation">> => <<"256m">>,
+        <<"cpu_shares">> => 512,
+        <<"cpus">> => 1.5,
+        <<"ulimits">> => #{
+            <<"nofile">> => <<"1024:2048">>
+        },
+        <<"sysctls">> => #{
+            <<"net.ipv4.ip_forward">> => <<"1">>
+        },
+        <<"tmpfs">> => [
+            <<"/tmp">>
+        ],
+        <<"extra_hosts">> => [
+            <<"host1:192.168.0.1">>
+        ],
+        <<"healthcheck">> => #{
+            <<"test">> => [
+                <<"CMD-SHELL">>,
+                <<"curl -f http://localhost || exit 1">>
+            ],
+            <<"interval">> => <<"30s">>,
+            <<"timeout">> => <<"10s">>,
+            <<"retries">> => 3
+        }
+    },
+    docker_commands:create_container(<<"my_nginx_xx3">>, "/usr/local/code/efka/", M).

config/sys.config

@@ -2,12 +2,21 @@
   {efka, [
     {root_dir, "/usr/local/code/efka"},
 
-    {dets_dir, "/tmp/db/"},
+    {dets_dir, "/usr/local/code/tmp/dets/"},
+
+    {upload_dir, "/usr/local/code/tmp/upload/"},
 
     {tcp_server, [
       {port, 18088}
     ]},
 
+    {http_server, [
+      {port, 18080},
+      {acceptors, 10},
+      {max_connections, 1024},
+      {backlog, 256}
+    ]},
+
     {tls_server, [
       {host, "localhost"},
       {port, 443}

message_pb.proto

@@ -19,23 +19,34 @@ message AuthReply {
 // service_id主动订阅消息, 基于广播通讯
 message Pub {
     string topic = 1;
-    string content = 2;
+    bytes content = 2;
+}
+
+message Command {
+    string command_type = 1;
+    bytes command = 2;
 }
 
 ///// 服务器主动推送的消息
 
-message AsyncCallReply {
-    // 0: 表示失败，1: 成功
-    uint32 code = 1;
-    string result = 2;
-    string message = 3;
+// 部署逻辑
+message RPCDeploy {
+    uint32 task_id = 1;
+    // json
+    string config = 2;
 }
 
-// 部署逻辑
-message Deploy {
-    uint32 task_id = 1;
-    string service_id = 2;
-    string tar_url = 3;
+message RPCStartContainer {
+    string container_name = 1;
+}
+
+message RPCStopContainer {
+    string container_name = 1;
+}
+
+message RPCConfigContainer {
+    string container_name = 1;
+    bytes config = 2;
 }
 
 // 获取task的logs
@@ -43,18 +54,11 @@ message FetchTaskLog {
     uint32 task_id = 1;
 }
 
-// 需要响应, 云端主动发起的调用; 提供给用户
-message Invoke {
-    string service_id = 1;
-    string payload = 2;
-    uint32 timeout = 3;
-}
-
 // 参数配置
-message PushServiceConfig {
-    string service_id = 1;
-    string config_json = 2;
-    uint32 timeout = 3;
+message ContainerConfig {
+    string container_name = 1;
+    // 任意的数据格式
+    bytes config = 2;
 }
 
 /////// EFKA主动上报的消息类型
@@ -63,8 +67,15 @@ message PushServiceConfig {
 message Data {
     string service_id = 1;
     string device_uuid = 2;
+    string route_key = 3;
     // measurement[,tag_key=tag_value...] field_key=field_value[,field_key2=field_value2...] [timestamp]
-    string metric = 3;
+    bytes metric = 4;
+}
+
+message Event {
+    string service_id = 1;
+    uint32 event_type = 2;
+    string params = 3;
 }
 
 //#{<<"adcode">> => 0,<<"boot_time">> => 18256077,<<"city">> => <<>>,
@@ -98,23 +109,3 @@ message Ping {
     // 接口信息的定义: 每个接口的信息, 采用json格式传输，没有办法提前定义
     string interfaces = 13;
 }
-
-// Inform消息
-message ServiceInform {
-    string service_id = 1;
-    string props = 2;
-    uint32 status = 3;
-    uint32 timestamp = 4;
-}
-
-message Event {
-    string service_id = 1;
-    uint32 event_type = 2;
-    string params = 3;
-}
-
-// 告警信息
-message Alarm {
-    string service_id = 1;
-    string params = 2;
-}

rebar.config

@@ -2,8 +2,8 @@
 {deps, [
     {sync, ".*", {git, "https://github.com/rustyio/sync.git", {branch, "master"}}},
     {jiffy, ".*", {git, "https://github.com/davisp/jiffy.git", {tag, "1.1.2"}}},
-    {gpb, ".*", {git, "https://github.com/tomas-abrahamsson/gpb.git", {tag, "4.20.0"}}},
-    {jiffy, ".*", {git, "https://github.com/davisp/jiffy.git", {tag, "1.1.1"}}},
+    {cowboy, ".*", {git, "https://github.com/ninenines/cowboy.git", {tag, "2.10.0"}}},
+    {gun, ".*", {git, "https://github.com/ninenines/gun.git", {tag, "2.2.0"}}},
     {parse_trans, ".*", {git, "https://github.com/uwiger/parse_trans", {tag, "3.0.0"}}},
     {lager, ".*", {git,"https://github.com/erlang-lager/lager.git", {tag, "3.9.2"}}}
 ]}.