--- AnyEvent-MP/MP.pm 2009/08/02 18:26:00 1.14 +++ AnyEvent-MP/MP.pm 2009/08/28 01:07:24 1.66 @@ -6,21 +6,46 @@ use AnyEvent::MP; - NODE # returns this node identifier - $NODE # contains this node identifier + $NODE # contains this node's noderef + NODE # returns this node's noderef + NODE $port # returns the noderef of the port + $SELF # receiving/own port id in rcv callbacks + + # initialise the node so it can send/receive messages + initialise_node; + + # ports are message endpoints + + # sending messages snd $port, type => data...; + snd $port, @msg; + snd @msg_with_first_element_being_a_port; + + # creating/using ports, the simple way + my $simple_port = port { my @msg = @_; 0 }; + + # creating/using ports, tagged message matching + my $port = port; + rcv $port, ping => sub { snd $_[0], "pong"; 0 }; + rcv $port, pong => sub { warn "pong received\n"; 0 }; - rcv $port, smartmatch => $cb->($port, @msg); + # create a port on another node + my $port = spawn $node, $initfunc, @initdata; - # examples: - rcv $port2, ping => sub { snd $_[0], "pong"; 0 }; - rcv $port1, pong => sub { warn "pong received\n" }; - snd $port2, ping => $port1; - - # more, smarter, matches (_any_ is exported by this module) - rcv $port, [child_died => $pid] => sub { ... - rcv $port, [_any_, _any_, 3] => sub { .. $_[2] is 3 + # monitoring + mon $port, $cb->(@msg) # callback is invoked on death + mon $port, $otherport # kill otherport on abnormal death + mon $port, $otherport, @msg # send message on death + +=head1 CURRENT STATUS + + AnyEvent::MP - stable API, should work + AnyEvent::MP::Intro - outdated + AnyEvent::MP::Kernel - WIP + AnyEvent::MP::Transport - mostly stable + + stay tuned. =head1 DESCRIPTION @@ -29,8 +54,11 @@ Despite its simplicity, you can securely message other processes running on the same or other hosts. -At the moment, this module family is severly brokena nd underdocumented, -so do not use. This was uploaded mainly to resreve the CPAN namespace - +For an introduction to this module family, see the L +manual page. + +At the moment, this module family is severly broken and underdocumented, +so do not use. This was uploaded mainly to reserve the CPAN namespace - stay tuned! =head1 CONCEPTS @@ -39,30 +67,54 @@ =item port -A port is something you can send messages to with the C function, and -you can register C handlers with. All C handlers will receive -messages they match, messages will not be queued. +A port is something you can send messages to (with the C function). -=item port id - C - -A port id is always the noderef, a hash-mark (C<#>) as separator, followed -by a port name (a printable string of unspecified format). +Ports allow you to register C handlers that can match all or just +some messages. Messages send to ports will not be queued, regardless of +anything was listening for them or not. + +=item port ID - C + +A port ID is the concatenation of a noderef, a hash-mark (C<#>) as +separator, and a port name (a printable string of unspecified format). An +exception is the the node port, whose ID is identical to its node +reference. =item node -A node is a single process containing at least one port - the node -port. You can send messages to node ports to let them create new ports, -among other things. - -Initially, nodes are either private (single-process only) or hidden -(connected to a master node only). Only when they epxlicitly "become -public" can you send them messages from unrelated other nodes. - -=item noderef - C, C, C - -A noderef is a string that either uniquely identifies a given node (for -private and hidden nodes), or contains a recipe on how to reach a given -node (for public nodes). +A node is a single process containing at least one port - the node port, +which provides nodes to manage each other remotely, and to create new +ports. + +Nodes are either private (single-process only), slaves (can only talk to +public nodes, but do not need an open port) or public nodes (connectable +from any other node). + +=item node ID - C<[a-za-Z0-9_\-.:]+> + +A node ID is a string that uniquely identifies the node within a +network. Depending on the configuration used, node IDs can look like a +hostname, a hostname and a port, or a random string. AnyEvent::MP itself +doesn't interpret node IDs in any way. + +=item binds - C + +Nodes can only talk to each other by creating some kind of connection to +each other. To do this, nodes should listen on one or more local transport +endpoints - binds. Currently, only standard C specifications can +be used, which specify TCP ports to listen on. + +=item seeds - C + +When a node starts, it knows nothing about the network. To teach the node +about the network it first has to contact some other node within the +network. This node is called a seed. + +Seeds are transport endpoint(s) of as many nodes as one wants. Those nodes +are expected to be long-running, and at least one of those should always +be available. When nodes run out of connections (e.g. due to a network +error), they try to re-establish connections to some seednodes again to +join the network. =back @@ -74,7 +126,7 @@ package AnyEvent::MP; -use AnyEvent::MP::Base; +use AnyEvent::MP::Kernel; use common::sense; @@ -84,30 +136,104 @@ use base "Exporter"; -our $VERSION = '0.02'; +our $VERSION = $AnyEvent::MP::Kernel::VERSION; + our @EXPORT = qw( - NODE $NODE $PORT snd rcv _any_ - create_port create_port_on - create_miniport - become_slave become_public + NODE $NODE *SELF node_of after + resolve_node initialise_node + snd rcv mon mon_guard kil reg psub spawn + port ); -=item NODE / $NODE +our $SELF; + +sub _self_die() { + my $msg = $@; + $msg =~ s/\n+$// unless ref $msg; + kil $SELF, die => $msg; +} + +=item $thisnode = NODE / $NODE + +The C function returns, and the C<$NODE> variable contains the node +ID of the node running in the current process. This value is initialised by +a call to C. + +=item $nodeid = node_of $port + +Extracts and returns the node ID part from a port ID or a node ID. + +=item initialise_node $profile_name + +Before a node can talk to other nodes on the network (i.e. enter +"distributed mode") it has to initialise itself - the minimum a node needs +to know is its own name, and optionally it should know the addresses of +some other nodes in the network to discover other nodes. + +This function initialises a node - it must be called exactly once (or +never) before calling other AnyEvent::MP functions. + +The first argument is a profile name. If it is C or missing, then +the current nodename will be used instead (i.e. F). + +The function then looks up the profile in the aemp configuration (see the +L commandline utility). + +If the profile specifies a node ID, then this will become the node ID of +this process. If not, then the profile name will be used as node ID. The +special node ID of C will be replaced by a random node ID. + +The next step is to look up the binds in the profile, followed by binding +aemp protocol listeners on all binds specified (it is possible and valid +to have no binds, meaning that the node cannot be contacted form the +outside. This means the node cannot talk to other nodes that also have no +binds, but it can still talk to all "normal" nodes). + +If the profile does not specify a binds list, then the node ID will be +treated as if it were of the form C, which will be resolved and +used as binds list. + +Lastly, the seeds list from the profile is passed to the +L module, which will then use it to keep +connectivity with at least on of those seed nodes at any point in time. + +Example: become a distributed node listening on the guessed noderef, or +the one specified via C for the current node. This should be the +most common form of invocation for "daemon"-type nodes. + + initialise_node; + +Example: become an anonymous node. This form is often used for commandline +clients. + + initialise_node "anon/"; + +Example: become a distributed node. If there is no profile of the given +name, or no binds list was specified, resolve C and bind +on the resulting addresses. + + initialise_node "localhost:4044"; + +=item $SELF + +Contains the current port id while executing C callbacks or C +blocks. -The C function and the C<$NODE> variable contain the noderef of -the local node. The value is initialised by a call to C or -C, after which all local port identifiers become invalid. +=item SELF, %SELF, @SELF... -=item snd $portid, type => @data +Due to some quirks in how perl exports variables, it is impossible to +just export C<$SELF>, all the symbols called C are exported by this +module, but only C<$SELF> is currently used. -=item snd $portid, @msg +=item snd $port, type => @data + +=item snd $port, @msg Send the given message to the given port ID, which can identify either -a local or a remote port, and can be either a string or soemthignt hat -stringifies a sa port ID (such as a port object :). +a local or a remote port, and must be a port ID. While the message can be about anything, it is highly recommended to use a -string as first element (a portid, or some word that indicates a request +string as first element (a port ID, or some word that indicates a request type etc.). The message data effectively becomes read-only after a call to this @@ -120,224 +246,557 @@ that Storable can serialise and deserialise is allowed, and for the local node, anything can be passed. -=item $local_port = create_port +=item $local_port = port + +Create a new local port object and returns its port ID. Initially it has +no callbacks set and will throw an error when it receives messages. + +=item $local_port = port { my @msg = @_ } + +Creates a new local port, and returns its ID. Semantically the same as +creating a port and calling C on it. + +The block will be called for every message received on the port, with the +global variable C<$SELF> set to the port ID. Runtime errors will cause the +port to be Ced. The message will be passed as-is, no extra argument +(i.e. no port ID) will be passed to the callback. -Create a new local port object. See the next section for allowed methods. +If you want to stop/destroy the port, simply C it: + + my $port = port { + my @msg = @_; + ... + kil $SELF; + }; =cut -sub create_port { - my $id = "$AnyEvent::MP::Base::UNIQ." . ++$AnyEvent::MP::Base::ID; +sub rcv($@); - my $self = bless { - id => "$NODE#$id", - names => [$id], - }, "AnyEvent::MP::Port"; - - $AnyEvent::MP::Base::PORT{$id} = sub { - unshift @_, $self; - - for (@{ $self->{rc0}{$_[1]} }) { - $_ && &{$_->[0]} - && undef $_; - } +sub _kilme { + die "received message on port without callback"; +} - for (@{ $self->{rcv}{$_[1]} }) { - $_ && [@_[1 .. @{$_->[1]}]] ~~ $_->[1] - && &{$_->[0]} - && undef $_; - } +sub port(;&) { + my $id = "$UNIQ." . $ID++; + my $port = "$NODE#$id"; - for (@{ $self->{any} }) { - $_ && [@_[0 .. $#{$_->[1]}]] ~~ $_->[1] - && &{$_->[0]} - && undef $_; - } + rcv $port, shift || \&_kilme; + + $port +} + +=item rcv $local_port, $callback->(@msg) + +Replaces the default callback on the specified port. There is no way to +remove the default callback: use C to disable it, or better +C the port when it is no longer needed. + +The global C<$SELF> (exported by this module) contains C<$port> while +executing the callback. Runtime errors during callback execution will +result in the port being Ced. + +The default callback received all messages not matched by a more specific +C match. + +=item rcv $local_port, tag => $callback->(@msg_without_tag), ... + +Register (or replace) callbacks to be called on messages starting with the +given tag on the given port (and return the port), or unregister it (when +C<$callback> is C<$undef> or missing). There can only be one callback +registered for each tag. + +The original message will be passed to the callback, after the first +element (the tag) has been removed. The callback will use the same +environment as the default callback (see above). + +Example: create a port and bind receivers on it in one go. + + my $port = rcv port, + msg1 => sub { ... }, + msg2 => sub { ... }, + ; + +Example: create a port, bind receivers and send it in a message elsewhere +in one go: + + snd $otherport, reply => + rcv port, + msg1 => sub { ... }, + ... + ; + +Example: temporarily register a rcv callback for a tag matching some port +(e.g. for a rpc reply) and unregister it after a message was received. + + rcv $port, $otherport => sub { + my @reply = @_; + + rcv $SELF, $otherport; }; - $self +=cut + +sub rcv($@) { + my $port = shift; + my ($noderef, $portid) = split /#/, $port, 2; + + $NODE{$noderef} == $NODE{""} + or Carp::croak "$port: rcv can only be called on local ports, caught"; + + while (@_) { + if (ref $_[0]) { + if (my $self = $PORT_DATA{$portid}) { + "AnyEvent::MP::Port" eq ref $self + or Carp::croak "$port: rcv can only be called on message matching ports, caught"; + + $self->[2] = shift; + } else { + my $cb = shift; + $PORT{$portid} = sub { + local $SELF = $port; + eval { &$cb }; _self_die if $@; + }; + } + } elsif (defined $_[0]) { + my $self = $PORT_DATA{$portid} ||= do { + my $self = bless [$PORT{$port} || sub { }, { }, $port], "AnyEvent::MP::Port"; + + $PORT{$portid} = sub { + local $SELF = $port; + + if (my $cb = $self->[1]{$_[0]}) { + shift; + eval { &$cb }; _self_die if $@; + } else { + &{ $self->[0] }; + } + }; + + $self + }; + + "AnyEvent::MP::Port" eq ref $self + or Carp::croak "$port: rcv can only be called on message matching ports, caught"; + + my ($tag, $cb) = splice @_, 0, 2; + + if (defined $cb) { + $self->[1]{$tag} = $cb; + } else { + delete $self->[1]{$tag}; + } + } + } + + $port } -=item $portid = create_miniport { } +=item $closure = psub { BLOCK } -Creates a "mini port", that is, a port without much #TODO +Remembers C<$SELF> and creates a closure out of the BLOCK. When the +closure is executed, sets up the environment in the same way as in C +callbacks, i.e. runtime errors will cause the port to get Ced. + +This is useful when you register callbacks from C callbacks: + + rcv delayed_reply => sub { + my ($delay, @reply) = @_; + my $timer = AE::timer $delay, 0, psub { + snd @reply, $SELF; + }; + }; =cut -sub create_miniport(&) { +sub psub(&) { my $cb = shift; - my $id = "$AnyEvent::MP::Base::UNIQ." . ++$AnyEvent::MP::Base::ID; - $AnyEvent::MP::Base::PORT{$id} = sub { -# unshift @_, "$NODE#$id"; - &$cb - and delete $AnyEvent::MP::Base::PORT{$id}; - }; + my $port = $SELF + or Carp::croak "psub can only be called from within rcv or psub callbacks, not"; - "$NODE#$id" + sub { + local $SELF = $port; + + if (wantarray) { + my @res = eval { &$cb }; + _self_die if $@; + @res + } else { + my $res = eval { &$cb }; + _self_die if $@; + $res + } + } } -package AnyEvent::MP::Port; +=item $guard = mon $port, $cb->(@reason) -=back +=item $guard = mon $port, $rcvport -=head1 METHODS FOR PORT OBJECTS +=item $guard = mon $port -=over 4 +=item $guard = mon $port, $rcvport, @msg -=item "$port" +Monitor the given port and do something when the port is killed or +messages to it were lost, and optionally return a guard that can be used +to stop monitoring again. -A port object stringifies to its port ID, so can be used directly for -C operations. +C effectively guarantees that, in the absence of hardware failures, +that after starting the monitor, either all messages sent to the port +will arrive, or the monitoring action will be invoked after possible +message loss has been detected. No messages will be lost "in between" +(after the first lost message no further messages will be received by the +port). After the monitoring action was invoked, further messages might get +delivered again. -=cut +Note that monitoring-actions are one-shot: once released, they are removed +and will not trigger again. -use overload - '""' => sub { $_[0]{id} }, - fallback => 1; +In the first form (callback), the callback is simply called with any +number of C<@reason> elements (no @reason means that the port was deleted +"normally"). Note also that I<< the callback B never die >>, so use +C if unsure. -=item $port->rcv (type => $callback->($port, @msg)) +In the second form (another port given), the other port (C<$rcvport>) +will be C'ed with C<@reason>, iff a @reason was specified, i.e. on +"normal" kils nothing happens, while under all other conditions, the other +port is killed with the same reason. -=item $port->rcv ($smartmatch => $callback->($port, @msg)) +The third form (kill self) is the same as the second form, except that +C<$rvport> defaults to C<$SELF>. -=item $port->rcv ([$smartmatch...] => $callback->($port, @msg)) +In the last form (message), a message of the form C<@msg, @reason> will be +C. -Register a callback on the given port. +As a rule of thumb, monitoring requests should always monitor a port from +a local port (or callback). The reason is that kill messages might get +lost, just like any other message. Another less obvious reason is that +even monitoring requests can get lost (for exmaple, when the connection +to the other node goes down permanently). When monitoring a port locally +these problems do not exist. -The callback has to return a true value when its work is done, after -which is will be removed, or a false value in which case it will stay -registered. +Example: call a given callback when C<$port> is killed. -If the match is an array reference, then it will be matched against the -first elements of the message, otherwise only the first element is being -matched. + mon $port, sub { warn "port died because of <@_>\n" }; -Any element in the match that is specified as C<_any_> (a function -exported by this module) matches any single element of the message. +Example: kill ourselves when C<$port> is killed abnormally. -While not required, it is highly recommended that the first matching -element is a string identifying the message. The one-string-only match is -also the most efficient match (by far). + mon $port; + +Example: send us a restart message when another C<$port> is killed. + + mon $port, $self => "restart"; =cut -sub rcv($@) { - my ($self, $match, $cb) = @_; +sub mon { + my ($noderef, $port) = split /#/, shift, 2; + + my $node = $NODE{$noderef} || add_node $noderef; - if (!ref $match) { - push @{ $self->{rc0}{$match} }, [$cb]; - } elsif (("ARRAY" eq ref $match && !ref $match->[0])) { - my ($type, @match) = @$match; - @match - ? push @{ $self->{rcv}{$match->[0]} }, [$cb, \@match] - : push @{ $self->{rc0}{$match->[0]} }, [$cb]; - } else { - push @{ $self->{any} }, [$cb, $match]; + my $cb = @_ ? shift : $SELF || Carp::croak 'mon: called with one argument only, but $SELF not set,'; + + unless (ref $cb) { + if (@_) { + # send a kill info message + my (@msg) = ($cb, @_); + $cb = sub { snd @msg, @_ }; + } else { + # simply kill other port + my $port = $cb; + $cb = sub { kil $port, @_ if @_ }; + } } + + $node->monitor ($port, $cb); + + defined wantarray + and AnyEvent::Util::guard { $node->unmonitor ($port, $cb) } } -=item $port->register ($name) +=item $guard = mon_guard $port, $ref, $ref... -Registers the given port under the well known name C<$name>. If the name -already exists it is replaced. +Monitors the given C<$port> and keeps the passed references. When the port +is killed, the references will be freed. -A port can only be registered under one well known name. +Optionally returns a guard that will stop the monitoring. + +This function is useful when you create e.g. timers or other watchers and +want to free them when the port gets killed: + + $port->rcv (start => sub { + my $timer; $timer = mon_guard $port, AE::timer 1, 1, sub { + undef $timer if 0.9 < rand; + }); + }); =cut -sub register { - my ($self, $name) = @_; +sub mon_guard { + my ($port, @refs) = @_; + + #TODO: mon-less form? - $self->{wkname} = $name; - $AnyEvent::MP::Base::WKP{$name} = "$self"; + mon $port, sub { 0 && @refs } } -=item $port->destroy +=item kil $port[, @reason] + +Kill the specified port with the given C<@reason>. + +If no C<@reason> is specified, then the port is killed "normally" (linked +ports will not be kileld, or even notified). -Explicitly destroy/remove/nuke/vaporise the port. +Otherwise, linked ports get killed with the same reason (second form of +C, see below). -Ports are normally kept alive by there mere existance alone, and need to -be destroyed explicitly. +Runtime errors while evaluating C callbacks or inside C blocks +will be reported as reason C<< die => $@ >>. + +Transport/communication errors are reported as C<< transport_error => +$message >>. =cut -sub destroy { - my ($self) = @_; +=item $port = spawn $node, $initfunc[, @initdata] + +Creates a port on the node C<$node> (which can also be a port ID, in which +case it's the node where that port resides). + +The port ID of the newly created port is return immediately, and it is +permissible to immediately start sending messages or monitor the port. + +After the port has been created, the init function is +called. This function must be a fully-qualified function name +(e.g. C). To specify a function in the main +program, use C<::name>. - delete $AnyEvent::MP::Base::WKP{ $self->{wkname} }; +If the function doesn't exist, then the node tries to C +the package, then the package above the package and so on (e.g. +C, C, C) until the function +exists or it runs out of package names. + +The init function is then called with the newly-created port as context +object (C<$SELF>) and the C<@initdata> values as arguments. + +A common idiom is to pass your own port, monitor the spawned port, and +in the init function, monitor the original port. This two-way monitoring +ensures that both ports get cleaned up when there is a problem. + +Example: spawn a chat server port on C<$othernode>. + + # this node, executed from within a port context: + my $server = spawn $othernode, "MyApp::Chat::Server::connect", $SELF; + mon $server; + + # init function on C<$othernode> + sub connect { + my ($srcport) = @_; + + mon $srcport; + + rcv $SELF, sub { + ... + }; + } - delete $AnyEvent::MP::Base::PORT{$_} - for @{ $self->{names} }; +=cut + +sub _spawn { + my $port = shift; + my $init = shift; + + local $SELF = "$NODE#$port"; + eval { + &{ load_func $init } + }; + _self_die if $@; } -=back +sub spawn(@) { + my ($noderef, undef) = split /#/, shift, 2; -=head1 FUNCTIONS FOR NODES + my $id = "$RUNIQ." . $ID++; -=over 4 + $_[0] =~ /::/ + or Carp::croak "spawn init function must be a fully-qualified name, caught"; -=item mon $noderef, $callback->($noderef, $status, $) + snd_to_func $noderef, "AnyEvent::MP::_spawn" => $id, @_; -Monitors the given noderef. + "$noderef#$id" +} -=item become_public endpoint... +=item after $timeout, @msg -Tells the node to become a public node, i.e. reachable from other nodes. +=item after $timeout, $callback -If no arguments are given, or the first argument is C, then -AnyEvent::MP tries to bind on port C<4040> on all IP addresses that the -local nodename resolves to. +Either sends the given message, or call the given callback, after the +specified number of seconds. -Otherwise the first argument must be an array-reference with transport -endpoints ("ip:port", "hostname:port") or port numbers (in which case the -local nodename is used as hostname). The endpoints are all resolved and -will become the node reference. +This is simply a utility function that come sin handy at times. =cut +sub after($@) { + my ($timeout, @action) = @_; + + my $t; $t = AE::timer $timeout, 0, sub { + undef $t; + ref $action[0] + ? $action[0]() + : snd @action; + }; +} + =back -=head1 NODE MESSAGES +=head1 AnyEvent::MP vs. Distributed Erlang + +AnyEvent::MP got lots of its ideas from distributed Erlang (Erlang node +== aemp node, Erlang process == aemp port), so many of the documents and +programming techniques employed by Erlang apply to AnyEvent::MP. Here is a +sample: + + http://www.Erlang.se/doc/programming_rules.shtml + http://Erlang.org/doc/getting_started/part_frame.html # chapters 3 and 4 + http://Erlang.org/download/Erlang-book-part1.pdf # chapters 5 and 6 + http://Erlang.org/download/armstrong_thesis_2003.pdf # chapters 4 and 5 -Nodes understand the following messages sent to them. Many of them take -arguments called C<@reply>, which will simply be used to compose a reply -message - C<$reply[0]> is the port to reply to, C<$reply[1]> the type and -the remaining arguments are simply the message data. +Despite the similarities, there are also some important differences: =over 4 -=cut +=item * Node IDs are arbitrary strings in AEMP. + +Erlang relies on special naming and DNS to work everywhere in the same +way. AEMP relies on each node somehow knowing its own address(es) (e.g. by +configuraiton or DNS), but will otherwise discover other odes itself. + +=item * Erlang has a "remote ports are like local ports" philosophy, AEMP +uses "local ports are like remote ports". + +The failure modes for local ports are quite different (runtime errors +only) then for remote ports - when a local port dies, you I it dies, +when a connection to another node dies, you know nothing about the other +port. + +Erlang pretends remote ports are as reliable as local ports, even when +they are not. + +AEMP encourages a "treat remote ports differently" philosophy, with local +ports being the special case/exception, where transport errors cannot +occur. -=item wkp => $name, @reply +=item * Erlang uses processes and a mailbox, AEMP does not queue. -Replies with the port ID of the specified well-known port, or C. +Erlang uses processes that selectively receive messages, and therefore +needs a queue. AEMP is event based, queuing messages would serve no +useful purpose. For the same reason the pattern-matching abilities of +AnyEvent::MP are more limited, as there is little need to be able to +filter messages without dequeing them. -=item devnull => ... +(But see L for a more Erlang-like process model on top of AEMP). -Generic data sink/CPU heat conversion. +=item * Erlang sends are synchronous, AEMP sends are asynchronous. -=item relay => $port, @msg +Sending messages in Erlang is synchronous and blocks the process (and +so does not need a queue that can overflow). AEMP sends are immediate, +connection establishment is handled in the background. -Simply forwards the message to the given port. +=item * Erlang suffers from silent message loss, AEMP does not. -=item eval => $string[ @reply] +Erlang makes few guarantees on messages delivery - messages can get lost +without any of the processes realising it (i.e. you send messages a, b, +and c, and the other side only receives messages a and c). -Evaluates the given string. If C<@reply> is given, then a message of the -form C<@reply, $@, @evalres> is sent. +AEMP guarantees correct ordering, and the guarantee that after one message +is lost, all following ones sent to the same port are lost as well, until +monitoring raises an error, so there are no silent "holes" in the message +sequence. -Example: crash another node. +=item * Erlang can send messages to the wrong port, AEMP does not. - snd $othernode, eval => "exit"; +In Erlang it is quite likely that a node that restarts reuses a process ID +known to other nodes for a completely different process, causing messages +destined for that process to end up in an unrelated process. -=item time => @reply +AEMP never reuses port IDs, so old messages or old port IDs floating +around in the network will not be sent to an unrelated port. + +=item * Erlang uses unprotected connections, AEMP uses secure +authentication and can use TLS. + +AEMP can use a proven protocol - TLS - to protect connections and +securely authenticate nodes. + +=item * The AEMP protocol is optimised for both text-based and binary +communications. + +The AEMP protocol, unlike the Erlang protocol, supports both programming +language independent text-only protocols (good for debugging) and binary, +language-specific serialisers (e.g. Storable). + +It has also been carefully designed to be implementable in other languages +with a minimum of work while gracefully degrading functionality to make the +protocol simple. + +=item * AEMP has more flexible monitoring options than Erlang. + +In Erlang, you can chose to receive I exit signals as messages +or I, there is no in-between, so monitoring single processes is +difficult to implement. Monitoring in AEMP is more flexible than in +Erlang, as one can choose between automatic kill, exit message or callback +on a per-process basis. + +=item * Erlang tries to hide remote/local connections, AEMP does not. + +Monitoring in Erlang is not an indicator of process death/crashes, +as linking is (except linking is unreliable in Erlang). + +In AEMP, you don't "look up" registered port names or send to named ports +that might or might not be persistent. Instead, you normally spawn a port +on the remote node. The init function monitors the you, and you monitor +the remote port. Since both monitors are local to the node, they are much +more reliable. + +This also saves round-trips and avoids sending messages to the wrong port +(hard to do in Erlang). + +=back + +=head1 RATIONALE + +=over 4 -Replies the the current node time to C<@reply>. +=item Why strings for ports and noderefs, why not objects? -Example: tell the current node to send the current time to C<$myport> in a -C message. +We considered "objects", but found that the actual number of methods +thatc an be called are very low. Since port IDs and noderefs travel over +the network frequently, the serialising/deserialising would add lots of +overhead, as well as having to keep a proxy object. + +Strings can easily be printed, easily serialised etc. and need no special +procedures to be "valid". + +And a a miniport consists of a single closure stored in a global hash - it +can't become much cheaper. + +=item Why favour JSON, why not real serialising format such as Storable? + +In fact, any AnyEvent::MP node will happily accept Storable as framing +format, but currently there is no way to make a node use Storable by +default. + +The default framing protocol is JSON because a) JSON::XS is many times +faster for small messages and b) most importantly, after years of +experience we found that object serialisation is causing more problems +than it gains: Just like function calls, objects simply do not travel +easily over the network, mostly because they will always be a copy, so you +always have to re-think your design. - snd $NODE, time => $myport, timereply => 1, 2; - # => snd $myport, timereply => 1, 2,