Question

我在erlang中遇到丢失邮件的问题。

当我手动使用时，我正在使用的代码100％正确，只有当我的代码用于'加载测试'时，我会在很多请求中并行测试代码，有些消息从未在接收器部分。记录参数的所有步骤和值时，我发现发送消息的地址是正确的。消息本身也没有问题。

我的问题如下：是否有关于erlang中“丢失消息”的知识，这可能是erlang本身的一些错误吗？

如果需要，我可以发布一些我正在使用的代码，但我认为它不会特别为这个问题增加很多价值。

更新：我的应用程序的主要部分。这是解释我的问题的相当多的代码，但我无法在简化版本中重现我的问题。该应用程序是一个分配系统，即它将并行地保留网格中的单元集合。重要的部分是：globalManager，一个控制整个分配系统的actor。 rowManager将管理整个网格的一行，并在进行预订时锁定该行。当必须保留单元区域时，调用函数request_specific_cells。此函数将向所有必须修改行的行管理器发送预留请求。当行管理器在其行中保留区域时，它将向globalManager发送确认。当所有行管理员都发送确认后，将向发起请求的进程发送确认，当其中一个管理器失败时，全局管理员将发送失败。

    globalManager(Grid) ->
    receive
        {Pid, request_specific_cells, ReservationId, Coordinates, Ctr, XX} ->
            NewGrid = request_specific_cells(Grid, Pid, ReservationId, Coordinates, Ctr, XX);

        {Pid, confirm_region, ResId, Rid, Sid, Region, Section, Ctr, XX} ->
            NewGrid = confirm_region(Grid, Pid, ResId, Rid, Sid, Region, Section, Ctr, XX);

        {Pid, failed_region, Rid, Region, Ctr, XX} ->
            NewGrid = failed_region(Grid, Pid, Rid, Region, Ctr, XX);

        Else ->
            erlang:display({unexpectedMessage, actor, Else}),
            NewGrid = Grid
    end,
    globalManager(NewGrid).


request_specific_cells(Grid, Pid, ReservationId, Coordinates, Ctr, XX) ->
    {{Width, Height}, GridRows, MaxAllocationSize, FreeCells, {UnspecificRequests, NextId}, PendingRequests, BlockedRows} = Grid,
    {X, Y, W, H} = Coordinates,
    Rows         = lists:seq(Y,Y+H-1),
    % Is one of the blocks that have to be reserved currently blocked?
    BlockedRow   = lists:foldl(fun(B, Acc) -> Acc xor search_list(B,BlockedRows) end, false, Rows),
    Request      = lists:keyfind(ReservationId, 1, UnspecificRequests),
    {ReservationId, _} = Request,
    % Now we need the addresses of the sections in which the regions has to be reserved.
    SubSectionIds = [ SPid || {_,SPid} <- [ lists:keyfind(Row, 1, GridRows) || Row <- Rows]],
    % Storing request enables us to rollback if one of the registrations fails.
    NewPendingRequests = PendingRequests ++ [{length(PendingRequests), 0, lists:map(fun(S) -> {S,null} end, SubSectionIds)}],
    % Send a registration command with the needed section to each corresponding section manager.
    [SPid ! {self(), request, Pid, ReservationId, length(PendingRequests), Coordinates, Ctr, XX} || SPid<- SubSectionIds],
    NewBlockedRows = Rows ++ BlockedRows,
    {{Width, Height}, GridRows, MaxAllocationSize, FreeCells, {UnspecificRequests, NextId}, NewPendingRequests, NewBlockedRows}
    end.


confirm_region(Grid, Pid, URid, Rid, Sid, Region, Section, Cttr, XX) ->
    {Dimensions, GridRows, MaxAllocationSize, FreeCells, {UnspecificRequests, NextId}, PendingRequests, BlockedRows} = Grid,
    {_,RY,_,_} = Region,
    if
        % All blocks have confirmed the reservation so the entire request is successful
        (Ctr+1) == length(Spids) -> 
                NewUnspecificRequests = lists:keydelete(URid, 1, UnspecificRequests),
                NewPendingRequests = lists:keydelete(Rid, 1, PendingRequests),
                NewSpids = lists:keyreplace(Sid, 1, Spids, {Sid, Section}),
                [Spid ! {self(), confirm_region, Sec} || {Spid, Sec} <- NewSpids],
                Pid ! {self(), request_specific_cells, Rid, success};
        true -> 
                NewUnspecificRequests = UnspecificRequests,
                % Safe the region that has to be marked/rolled back in the row
                NewSpids = lists:keyreplace(Sid, 1, Spids, {Sid, Section}),
                % Increase counter of confirmations
                NewPendingRequests = lists:keyreplace(Rid, 1, PendingRequests, {Rid, Ctr+1, NewSpids})
    end,
    NewBlockedRows = delete_list(RY, BlockedRows)
    {Dimensions, GridRows, MaxAllocationSize, FreeCells, {NewUnspecificRequests, NextId}, NewPendingRequests, NewBlockedRows}.



rowManager(Row) ->
    receive
        {Mid, request, Pid, URid, Rid, Region, Ctr, XX} ->
            NewRow = request_region(Row, Mid, Pid, URid, Rid, Region, Ctr, XX);
        Else ->
            erlang:display({unexpectedMessage, rowManager, Else}),
            NewRow = Row
    end,

    rowManager(NewRow).

request_region(Row, Mid, Pid, URid, Rid, Coordinates, Ctr, XX) ->
    {RY, Content, Modified} = Row,
    {X,_,W,_}    = Coordinates,
    if
        Modified == false -> 
                Free = region_is_empty({X,1,W,1}, Content),
                if
                    Free -> NewModified = true,
                            NewContent = mark_region({X,1,W,1}, Content, reserved),
                            Mid ! {Pid, confirm_region, URid, Rid, self(), Coordinates, {X,1,W,1}, Ctr, XX};
                    true -> NewModified = false,
                            NewContent = Content,
                            Mid ! {Pid, failed_region, Rid, Coordinates, Ctr, XX}
                end;
        true -> NewModified = false,
                NewContent = Content,
                Mid ! {Pid, failed_region, Rid, Coordinates, Ctr, XX}
    end,
    {RY, NewContent, NewModified}.

此代码将由reserver使用：

request_specific_cells(FollowUpPid, ReservationId, {X, Y, Width, Height}, Ctr, XX) ->
   FollowUpPid ! {self(), request_specific_cells, ReservationId, {X, Y, Width, Height}, Ctr, XX},
   receive
      {FollowUpPid, request_specific_cells, ReservationId, SuccessOrFailure} ->
        SuccessOrFailure
end.

我认为这个接收器在收到回答之前就已经死了，因为我知道

Pid ! {self(), request_specific_cells, Rid, success}

来自confirm / 9函数的

始终使用正确的值执行，但并不总是在函数处接收。

Answer 1

如果接收方处于活动状态，Erlang在同一节点内具有强大的消息传递保证。

您的代码中似乎有一些竞争条件。尝试编写具有相同问题的应用程序的较小示例，并将其发布到此处。

消息在erlang中丢失

1 个答案: