[英]Erlang Supervisor fail to start_child with no errors simple_one_for_one
主管似乎无法默默地开始孩子......
这是主管
-behaviour(supervisor).
-export([start_socket/0, init/1, start_link/1]).
-define(SSL_OPTIONS, [{active, once},
{backlog, 128},
{reuseaddr, true},
{packet, 0},
{cacertfile, "./ssl_key/server/gd_bundle.crt"},
{certfile, "./ssl_key/server/cert.pem"},
{keyfile, "./ssl_key/server/cert.key"},
{password, "**********"}
]).
start_link(Port) ->
Role = list_to_atom(atom_to_list(?MODULE) ++ lists:flatten(io_lib:format("~B", [Port]))),
supervisor:start_link({local, Role}, ?MODULE, [Port]).
init([Port]) ->
R = ssl:listen(Port, ?SSL_OPTIONS),
LSocket = case R of
{ok, LSock} ->
LSock;
Res ->
io:fwrite("gateway_sup Error: ~p~n", [Res])
end,
spawn_link(fun empty_listeners/0),
ChildSpec = [{socket,
{gateway_serv, start_link, [LSocket]},
temporary, 1000, worker, [gateway_serv]}
],
{ok, {{simple_one_for_one, 3600, 3600},
ChildSpec
}}.
empty_listeners() ->
io:fwrite("---------------------- empty_listeners~n"),
[start_socket() || _ <- lists:seq(1,128)],
ok.
start_socket() ->
io:fwrite("++++++++++++++++++++++ start_socket~n"),
supervisor:start_child(?MODULE, []).
和gen_server
-module(gateway_serv).
-behaviour(gen_server).
-export([start_link/1, init/1, handle_call/3, handle_cast/2, handle_info/2, code_change/3, terminate/2]).
start_link(LSocket) ->
io:fwrite("#################~n"),
gen_server:start_link(?MODULE, [LSocket], []).
init([LSocket]) ->
io:fwrite("/////////////////~n"),
gen_server:cast(self(), accept),
{ok, #client{listenSocket=LSocket, pid=self()}}.
handle_cast(accept, G = #client{listenSocket=LSocket}) ->
{ok, AcceptSocket} = ssl:transport_accept(LSocket),
gateway_sup:start_socket(),
case ssl:ssl_accept(AcceptSocket, 30000) of
ok ->
timer:send_after(10000, closingSocket),
ssl:setopts(AcceptSocket, [{active, once}, {mode, list}, {packet, 0}]),
{noreply, G#client{listenSocket=none, socket=AcceptSocket}};
{error, _Reason} ->
{stop, normal, G}
end;
handle_cast(_, G) ->
{noreply, G}.
显然从未调用gen_server的start_link / 1(使用io:fwrite检查)。
似乎无法找出原因......
当您注册主管时,您使用:
Role = list_to_atom(atom_to_list(?MODULE) ++ lists:flatten(io_lib:format("~B", [Port]))),
所以当你打电话时:
start_socket() ->
io:fwrite("++++++++++++++++++++++ start_socket~n"),
supervisor:start_child(?MODULE, []).
你正在打电话给一个不存在的主管。
你应该把它称为:
supervisor:start_child(Role, []).
您可以将Role
作为参数传递给函数。
对我来说似乎很奇怪,你启动empty_listener调用start_socket()调用supervisor:在监督程序的init函数中的start_child,此时主管没有完成初始化阶段。
因此,要求主管启动子女的流程与主管本身之间存在竞争。
我认为这段代码应该在init函数之外:
我做了一个使用这种模式的应用程序,我有两个级别的主管:
main supervisor (one_for_all strategy)
| |
| |
v v
application -------> supervisor (simple_one_for_one strategy)
server start_child worker factory
|
|
v*
many children
编辑:忘记这种竞争条件,
我做了一个测试,在init函数结束之前引入了一个延迟,我已经看到了start_child函数,等待init的结束,没有任何东西丢失。 OTP家伙比我想象的更加谨慎......
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.