--- AnyEvent-MP/MP.pm 2009/08/04 14:10:51 1.21 +++ AnyEvent-MP/MP.pm 2009/08/30 18:51:49 1.69 @@ -6,32 +6,60 @@ 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; - rcv $port, smartmatch => $cb->($port, @msg); + # creating/using ports, the simple way + my $simple_port = port { my @msg = @_; 0 }; - # 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 + # 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 }; + + # create a port on another node + my $port = spawn $node, $initfunc, @initdata; + + # 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# send message on death + +=head1 CURRENT STATUS + + AnyEvent::MP - stable API, should work + AnyEvent::MP::Intro - outdated + AnyEvent::MP::Kernel - mostly stable + AnyEvent::MP::Global - mostly stable + AnyEvent::MP::Node - mostly stable, but internal anyways + AnyEvent::MP::Transport - mostly stable, but internal anyways + + stay tuned. =head1 DESCRIPTION This module (-family) implements a simple message passing framework. Despite its simplicity, you can securely message other processes running -on the same or other hosts. +on the same or other hosts, and you can supervise entities remotely. + +For an introduction to this module family, see the L +manual page and the examples under F. -At the moment, this module family is severly brokena nd underdocumented, -so do not use. This was uploaded mainly to reserve the CPAN namespace - -stay tuned! +At the moment, this module family is a bit underdocumented. =head1 CONCEPTS @@ -39,30 +67,55 @@ =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 +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. -A port id is always the noderef, a hash-mark (C<#>) as separator, followed -by a port name (a printable string of unspecified format). +=item port ID - C + +A port ID is the concatenation of a node ID, a hash-mark (C<#>) as +separator, and a port name (a printable string of unspecified format). =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 enables nodes to manage each other remotely, and to create new +ports. + +Nodes are either public (have one or more listening ports) or private +(no listening ports). Private nodes cannot talk to other private nodes +currently. + +=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. + +Apart from being sued for seeding, seednodes are not special in any way - +every public node can be a seednode. =back @@ -74,7 +127,7 @@ package AnyEvent::MP; -use AnyEvent::MP::Base; +use AnyEvent::MP::Kernel; use common::sense; @@ -84,62 +137,380 @@ use base "Exporter"; -our $VERSION = '0.02'; +our $VERSION = $AnyEvent::MP::Kernel::VERSION; + our @EXPORT = qw( - NODE $NODE $PORT snd rcv mon kil _any_ - create_port create_port_on - miniport - become_slave become_public + NODE $NODE *SELF node_of after + 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 from a port ID or a node ID. + +=item initialise_node $profile_name, key => value... + +Before a node can talk to other nodes on the network (i.e. enter +"distributed mode") it has to initialise itself - the minimum a node needs +to know is its own name, and optionally it should know the addresses of +some other nodes in the network to discover other nodes. + +This function initialises a node - it must be called exactly once (or +never) before calling other AnyEvent::MP functions. + +The first argument is a profile name. If it is C or missing, then +the current nodename will be used instead (i.e. F). + +The function first looks up the profile in the aemp configuration (see the +L commandline utility). the profile is calculated as follows: -The C function and the C<$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. +First, all remaining key => value pairs will be used. Then they will be +overwritten by any values specified in the global default configuration +(see the F utility), then the chain of profiles selected, if +any. That means that the values specified in the profile have highest +priority and the values specified via C have lowest +priority. -=item snd $portid, type => @data +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. -=item snd $portid, @msg +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). -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 :). +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. -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 -type etc.). +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. -The message data effectively becomes read-only after a call to this -function: modifying any argument is not allowed and can cause many -problems. +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 $SELF + +Contains the current port id while executing C callbacks or C +blocks. + +=item *SELF, SELF, %SELF, @SELF... + +Due to some quirks in how perl exports variables, it is impossible to +just export C<$SELF>, all the symbols named C are exported by this +module, but only C<$SELF> is currently used. + +=item snd $port, type => @data + +=item snd $port, @msg + +Send the given message to the given port, which can identify either a +local or a remote port, and must be a port ID. + +While the message can be almost anything, it is highly recommended to +use a string as first element (a port ID, or some word that indicates a +request type etc.) and to consist if only simple perl values (scalars, +arrays, hashes) - if you think you need to pass an object, think again. + +The message data logically becomes read-only after a call to this +function: modifying any argument (or values referenced by them) is +forbidden, as there can be considerable time between the call to C +and the time the message is actually being serialised - in fact, it might +never be copied as within the same process it is simply handed to the +receiving port. The type of data you can transfer depends on the transport protocol: when JSON is used, then only strings, numbers and arrays and hashes consisting of those are allowed (no objects). When Storable is used, then anything that Storable can serialise and deserialise is allowed, and for the local -node, anything can be passed. +node, anything can be passed. Best rely only on the common denominator of +these. + +=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. + +If you want to stop/destroy the port, simply C it: + + my $port = port { + my @msg = @_; + ... + kil $SELF; + }; + +=cut + +sub rcv($@); + +sub _kilme { + die "received message on port without callback"; +} + +sub port(;&) { + my $id = "$UNIQ." . $ID++; + my $port = "$NODE#$id"; + + 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, $otherport; + }; + +=cut + +sub rcv($@) { + 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 $closure = psub { BLOCK } + +Remembers C<$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 psub(&) { + my $cb = shift; + + my $port = $SELF + or Carp::croak "psub can only be called from within rcv or psub callbacks, not"; + + sub { + local $SELF = $port; + + if (wantarray) { + my @res = eval { &$cb }; + _self_die if $@; + @res + } else { + my $res = eval { &$cb }; + _self_die if $@; + $res + } + } +} + +=item $guard = mon $port, $cb->(@reason) # call $cb when $port dies + +=item $guard = mon $port, $rcvport # kill $rcvport when $port dies + +=item $guard = mon $port # kill $SELF when $port dies + +=item $guard = mon $port, $rcvport, @msg # send a message when $port dies -=item $guard = mon $portid, $cb->() +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. -=item $guard = mon $portid, $otherport +C effectively guarantees that, in the absence of hardware failures, +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. -=item $guard = mon $portid, $otherport, @msg +Note that monitoring-actions are one-shot: once messages are lost (and a +monitoring alert was raised), they are removed and will not trigger again. -Monitor the given port and call the given callback when the port is -destroyed or connection to it's node is lost. +In the first form (callback), the callback is simply called with any +number of C<@reason> elements (no @reason means that the port was deleted +"normally"). Note also that I<< the callback B never die >>, so use +C if unsure. -#TODO +In the second form (another port given), the other port (C<$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. + +The third form (kill self) is the same as the second form, except that +C<$rvport> defaults to C<$SELF>. + +In the last form (message), a message of the form C<@msg, @reason> will be +C. + +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. + +Example: call a given callback when C<$port> is killed. + + mon $port, sub { warn "port died because of <@_>\n" }; + +Example: kill ourselves when C<$port> is killed abnormally. + + mon $port; + +Example: send us a restart message when another C<$port> is killed. + + mon $port, $self => "restart"; =cut sub mon { - my ($noderef, $port, $cb) = ((split /#/, shift, 2), shift); + my ($noderef, $port) = split /#/, shift, 2; - my $node = AnyEvent::MP::Base::add_node $noderef; + my $node = $NODE{$noderef} || add_node $noderef; - #TODO: ports must not be references - if (!ref $cb or "AnyEvent::MP::Port" eq ref $cb) { + 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, @_); @@ -147,7 +518,7 @@ } else { # simply kill other port my $port = $cb; - $cb = sub { kil $port, @_ }; + $cb = sub { kil $port, @_ if @_ }; } } @@ -165,10 +536,10 @@ 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: +want to free them when the port gets killed (note the use of C): $port->rcv (start => sub { - my $timer; $timer = mon_guard $port, AE::timer 1, 1, sub { + my $timer; $timer = mon_guard $port, AE::timer 1, 1, psub { undef $timer if 0.9 < rand; }); }); @@ -178,244 +549,283 @@ sub mon_guard { my ($port, @refs) = @_; + #TODO: mon-less form? + mon $port, sub { 0 && @refs } } -=item $local_port = create_port - -Create a new local port object. See the next section for allowed methods. - -=cut - -sub create_port { - my $id = "$AnyEvent::MP::Base::UNIQ." . $AnyEvent::MP::Base::ID++; - - my $self = bless { - id => "$NODE#$id", - }, "AnyEvent::MP::Port"; - - $AnyEvent::MP::Base::PORT{$id} = sub { - unshift @_, $self; - - for (@{ $self->{rc0}{$_[1]} }) { - $_ && &{$_->[0]} - && undef $_; - } - - for (@{ $self->{rcv}{$_[1]} }) { - $_ && [@_[1 .. @{$_->[1]}]] ~~ $_->[1] - && &{$_->[0]} - && undef $_; - } +=item kil $port[, @reason] - for (@{ $self->{any} }) { - $_ && [@_[0 .. $#{$_->[1]}]] ~~ $_->[1] - && &{$_->[0]} - && undef $_; - } - }; +Kill the specified port with the given C<@reason>. - $self -} +If no C<@reason> is specified, then the port is killed "normally" (ports +monitoring other ports will not necessarily die because a port dies +"normally"). -=item $portid = miniport { my @msg = @_; $finished } +Otherwise, linked ports get killed with the same reason (second form of +C, see above). -Creates a "mini port", that is, a very lightweight port without any -pattern matching behind it, and returns its ID. +Runtime errors while evaluating C callbacks or inside C blocks +will be reported as reason C<< die => $@ >>. -The block will be called for every message received on the port. When the -callback returns a true value its job is considered "done" and the port -will be destroyed. Otherwise it will stay alive. +Transport/communication errors are reported as C<< transport_error => +$message >>. -The message will be passed as-is, no extra argument (i.e. no port id) will -be passed to the callback. +=cut -If you need the local port id in the callback, this works nicely: +=item $port = spawn $node, $initfunc[, @initdata] - my $port; $port = miniport { - snd $otherport, reply => $port; - }; +Creates a port on the node C<$node> (which can also be a port ID, in which +case it's the node where that port resides). -=cut +The port ID of the newly created port is returned immediately, and it is +possible to immediately start sending messages or to monitor the port. -sub miniport(&) { - my $cb = shift; - my $id = "$AnyEvent::MP::Base::UNIQ." . $AnyEvent::MP::Base::ID++; +After the port has been created, the init function is called on the remote +node, in the same context as a C callback. This function must be a +fully-qualified function name (e.g. C). To +specify a function in the main program, use C<::name>. - $AnyEvent::MP::Base::PORT{$id} = sub { - &$cb - and kil $id; - }; +If the function doesn't exist, then the node tries to C +the package, then the package above the package and so on (e.g. +C, C, C) until the function +exists or it runs out of package names. - "$NODE#$id" -} +The init function is then called with the newly-created port as context +object (C<$SELF>) and the C<@initdata> values as arguments. -package AnyEvent::MP::Port; +A common idiom is to pass a local port, immediately monitor the spawned +port, and in the remote init function, immediately monitor the passed +local port. This two-way monitoring ensures that both ports get cleaned up +when there is a problem. -=back +Example: spawn a chat server port on C<$othernode>. -=head1 METHODS FOR PORT OBJECTS + # this node, executed from within a port context: + my $server = spawn $othernode, "MyApp::Chat::Server::connect", $SELF; + mon $server; -=over 4 + # init function on C<$othernode> + sub connect { + my ($srcport) = @_; -=item "$port" + mon $srcport; -A port object stringifies to its port ID, so can be used directly for -C operations. + rcv $SELF, sub { + ... + }; + } =cut -use overload - '""' => sub { $_[0]{id} }, - fallback => 1; +sub _spawn { + my $port = shift; + my $init = shift; + + local $SELF = "$NODE#$port"; + eval { + &{ load_func $init } + }; + _self_die if $@; +} -sub TO_JSON { $_[0]{id} } +sub spawn(@) { + my ($noderef, undef) = split /#/, shift, 2; -=item $port->rcv (type => $callback->($port, @msg)) + my $id = "$RUNIQ." . $ID++; -=item $port->rcv ($smartmatch => $callback->($port, @msg)) + $_[0] =~ /::/ + or Carp::croak "spawn init function must be a fully-qualified name, caught"; -=item $port->rcv ([$smartmatch...] => $callback->($port, @msg)) + snd_to_func $noderef, "AnyEvent::MP::_spawn" => $id, @_; -Register a callback on the given port. + "$noderef#$id" +} -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. +=item after $timeout, @msg -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. +=item after $timeout, $callback -Any element in the match that is specified as C<_any_> (a function -exported by this module) matches any single element of the message. +Either sends the given message, or call the given callback, after the +specified number of seconds. -While not required, it is highly recommended that the first matching -element is a string identifying the message. The one-string-only match is -also the most efficient match (by far). +This is simply a utility function that comes in handy at times - the +AnyEvent::MP author is not convinced of the wisdom of having it, though, +so it may go away in the future. =cut -sub rcv($@) { - my ($self, $match, $cb) = @_; +sub after($@) { + my ($timeout, @action) = @_; - 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 $t; $t = AE::timer $timeout, 0, sub { + undef $t; + ref $action[0] + ? $action[0]() + : snd @action; + }; } -=item $port->register ($name) +=back -Registers the given port under the well known name C<$name>. If the name -already exists it is replaced. +=head1 AnyEvent::MP vs. Distributed Erlang -A port can only be registered under one well known name. +AnyEvent::MP got lots of its ideas from distributed Erlang (Erlang node +== aemp node, Erlang process == aemp port), so many of the documents and +programming techniques employed by Erlang apply to AnyEvent::MP. Here is a +sample: + + http://www.Erlang.se/doc/programming_rules.shtml + http://Erlang.org/doc/getting_started/part_frame.html # chapters 3 and 4 + http://Erlang.org/download/Erlang-book-part1.pdf # chapters 5 and 6 + http://Erlang.org/download/armstrong_thesis_2003.pdf # chapters 4 and 5 -=cut +Despite the similarities, there are also some important differences: -sub register { - my ($self, $name) = @_; +=over 4 - $self->{wkname} = $name; - $AnyEvent::MP::Base::WKP{$name} = "$self"; -} +=item * Node IDs are arbitrary strings in AEMP. -=item $port->destroy +Erlang relies on special naming and DNS to work everywhere in the same +way. AEMP relies on each node somehow knowing its own address(es) (e.g. by +configuraiton or DNS), but will otherwise discover other odes itself. -Explicitly destroy/remove/nuke/vaporise the port. +=item * Erlang has a "remote ports are like local ports" philosophy, AEMP +uses "local ports are like remote ports". -Ports are normally kept alive by their mere existance alone, and need to -be destroyed explicitly. +The failure modes for local ports are quite different (runtime errors +only) then for remote ports - when a local port dies, you I it dies, +when a connection to another node dies, you know nothing about the other +port. -=cut +Erlang pretends remote ports are as reliable as local ports, even when +they are not. -sub destroy { - my ($self) = @_; +AEMP encourages a "treat remote ports differently" philosophy, with local +ports being the special case/exception, where transport errors cannot +occur. - delete $AnyEvent::MP::Base::WKP{ $self->{wkname} }; +=item * Erlang uses processes and a mailbox, AEMP does not queue. - AnyEvent::MP::Base::kil $self->{id}; -} +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. -=back +(But see L for a more Erlang-like process model on top of AEMP). -=head1 FUNCTIONS FOR NODES +=item * Erlang sends are synchronous, AEMP sends are asynchronous. -=over 4 +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. -=item mon $noderef, $callback->($noderef, $status, $) +=item * Erlang suffers from silent message loss, AEMP does not. -Monitors the given noderef. +Erlang makes few guarantees on messages delivery - messages can get lost +without any of the processes realising it (i.e. you send messages a, b, +and c, and the other side only receives messages a and c). -=item become_public endpoint... +AEMP guarantees correct ordering, and the guarantee that after one message +is lost, all following ones sent to the same port are lost as well, until +monitoring raises an error, so there are no silent "holes" in the message +sequence. -Tells the node to become a public node, i.e. reachable from other nodes. +=item * Erlang can send messages to the wrong port, AEMP does not. -If no arguments are given, or the first argument is C, then -AnyEvent::MP tries to bind on port C<4040> on all IP addresses that the -local nodename resolves to. +In Erlang it is quite likely that a node that restarts reuses a process ID +known to other nodes for a completely different process, causing messages +destined for that process to end up in an unrelated process. -Otherwise the first argument must be an array-reference with transport -endpoints ("ip:port", "hostname:port") or port numbers (in which case the -local nodename is used as hostname). The endpoints are all resolved and -will become the node reference. +AEMP never reuses port IDs, so old messages or old port IDs floating +around in the network will not be sent to an unrelated port. -=cut +=item * Erlang uses unprotected connections, AEMP uses secure +authentication and can use TLS. -=back +AEMP can use a proven protocol - TLS - to protect connections and +securely authenticate nodes. -=head1 NODE MESSAGES +=item * The AEMP protocol is optimised for both text-based and binary +communications. -Nodes understand the following messages sent to them. Many of them take -arguments called C<@reply>, which will simply be used to compose a reply -message - C<$reply[0]> is the port to reply to, C<$reply[1]> the type and -the remaining arguments are simply the message data. +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). By default, unless TLS is +used, the protocol is actually completely text-based. -=over 4 +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. -=cut +=item * AEMP has more flexible monitoring options than Erlang. -=item wkp => $name, @reply +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. -Replies with the port ID of the specified well-known port, or C. +=item * Erlang tries to hide remote/local connections, AEMP does not. -=item devnull => ... +Monitoring in Erlang is not an indicator of process death/crashes, in the +same way as linking is (except linking is unreliable in Erlang). -Generic data sink/CPU heat conversion. +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 you, and you monitor the +remote port. Since both monitors are local to the node, they are much more +reliable (no need for C). -=item relay => $port, @msg +This also saves round-trips and avoids sending messages to the wrong port +(hard to do in Erlang). -Simply forwards the message to the given port. +=back -=item eval => $string[ @reply] +=head1 RATIONALE -Evaluates the given string. If C<@reply> is given, then a message of the -form C<@reply, $@, @evalres> is sent. +=over 4 -Example: crash another node. +=item Why strings for port and node IDs, why not objects? - snd $othernode, eval => "exit"; +We considered "objects", but found that the actual number of methods +that can be called are quite low. Since port and node IDs travel over +the network frequently, the serialising/deserialising would add lots of +overhead, as well as having to keep a proxy object everywhere. + +Strings can easily be printed, easily serialised etc. and need no special +procedures to be "valid". + +And as a result, a miniport consists of a single closure stored in a +global hash - it can't become much cheaper. + +=item Why favour JSON, why not a real serialising format such as Storable? + +In fact, any AnyEvent::MP node will happily accept Storable as framing +format, but currently there is no way to make a node use Storable by +default (although all nodes will accept it). + +The default framing protocol is JSON because a) JSON::XS is many times +faster for small messages and b) most importantly, after years of +experience we found that object serialisation is causing more problems +than it solves: Just like function calls, objects simply do not travel +easily over the network, mostly because they will always be a copy, so you +always have to re-think your design. -=item time => @reply +Keeping your messages simple, concentrating on data structures rather than +objects, will keep your messages clean, tidy and efficient. -Replies the the current node time to C<@reply>. +=back -Example: tell the current node to send the current time to C<$myport> in a -C message. +=head1 SEE ALSO - snd $NODE, time => $myport, timereply => 1, 2; - # => snd $myport, timereply => 1, 2,