… | |
… | |
8 | |
8 | |
9 | $NODE # contains this node's noderef |
9 | $NODE # contains this node's noderef |
10 | NODE # returns this node's noderef |
10 | NODE # returns this node's noderef |
11 | NODE $port # returns the noderef of the port |
11 | NODE $port # returns the noderef of the port |
12 | |
12 | |
|
|
13 | $SELF # receiving/own port id in rcv callbacks |
|
|
14 | |
|
|
15 | # initialise the node so it can send/receive messages |
|
|
16 | initialise_node; # -OR- |
|
|
17 | initialise_node "localhost:4040"; # -OR- |
|
|
18 | initialise_node "slave/", "localhost:4040" |
|
|
19 | |
|
|
20 | # ports are message endpoints |
|
|
21 | |
|
|
22 | # sending messages |
13 | snd $port, type => data...; |
23 | snd $port, type => data...; |
|
|
24 | snd $port, @msg; |
|
|
25 | snd @msg_with_first_element_being_a_port; |
14 | |
26 | |
15 | $SELF # receiving/own port id in rcv callbacks |
27 | # creating/using miniports |
|
|
28 | my $miniport = port { my @msg = @_; 0 }; |
16 | |
29 | |
|
|
30 | # creating/using full ports |
|
|
31 | my $port = port; |
17 | rcv $port, smartmatch => $cb->($port, @msg); |
32 | rcv $port, smartmatch => $cb->(@msg); |
18 | |
|
|
19 | # examples: |
|
|
20 | rcv $port2, ping => sub { snd $_[0], "pong"; 0 }; |
33 | rcv $port, ping => sub { snd $_[0], "pong"; 0 }; |
21 | rcv $port1, pong => sub { warn "pong received\n" }; |
34 | rcv $port, pong => sub { warn "pong received\n"; 0 }; |
22 | snd $port2, ping => $port1; |
|
|
23 | |
35 | |
24 | # more, smarter, matches (_any_ is exported by this module) |
36 | # more, smarter, matches (_any_ is exported by this module) |
25 | rcv $port, [child_died => $pid] => sub { ... |
37 | rcv $port, [child_died => $pid] => sub { ... |
26 | rcv $port, [_any_, _any_, 3] => sub { .. $_[2] is 3 |
38 | rcv $port, [_any_, _any_, 3] => sub { .. $_[2] is 3 |
27 | |
39 | |
|
|
40 | # create a port on another node |
|
|
41 | my $port = spawn $node, $initfunc, @initdata; |
|
|
42 | |
|
|
43 | # monitoring |
|
|
44 | mon $port, $cb->(@msg) # callback is invoked on death |
|
|
45 | mon $port, $otherport # kill otherport on abnormal death |
|
|
46 | mon $port, $otherport, @msg # send message on death |
|
|
47 | |
|
|
48 | =head1 CURRENT STATUS |
|
|
49 | |
|
|
50 | AnyEvent::MP - stable API, should work |
|
|
51 | AnyEvent::MP::Intro - outdated |
|
|
52 | AnyEvent::MP::Kernel - WIP |
|
|
53 | AnyEvent::MP::Transport - mostly stable |
|
|
54 | |
|
|
55 | stay tuned. |
|
|
56 | |
28 | =head1 DESCRIPTION |
57 | =head1 DESCRIPTION |
29 | |
58 | |
30 | This module (-family) implements a simple message passing framework. |
59 | This module (-family) implements a simple message passing framework. |
31 | |
60 | |
32 | Despite its simplicity, you can securely message other processes running |
61 | Despite its simplicity, you can securely message other processes running |
… | |
… | |
35 | For an introduction to this module family, see the L<AnyEvent::MP::Intro> |
64 | For an introduction to this module family, see the L<AnyEvent::MP::Intro> |
36 | manual page. |
65 | manual page. |
37 | |
66 | |
38 | At the moment, this module family is severly broken and underdocumented, |
67 | At the moment, this module family is severly broken and underdocumented, |
39 | so do not use. This was uploaded mainly to reserve the CPAN namespace - |
68 | so do not use. This was uploaded mainly to reserve the CPAN namespace - |
40 | stay tuned! The basic API should be finished, however. |
69 | stay tuned! |
41 | |
70 | |
42 | =head1 CONCEPTS |
71 | =head1 CONCEPTS |
43 | |
72 | |
44 | =over 4 |
73 | =over 4 |
45 | |
74 | |
… | |
… | |
90 | |
119 | |
91 | =cut |
120 | =cut |
92 | |
121 | |
93 | package AnyEvent::MP; |
122 | package AnyEvent::MP; |
94 | |
123 | |
95 | use AnyEvent::MP::Base; |
124 | use AnyEvent::MP::Kernel; |
96 | |
125 | |
97 | use common::sense; |
126 | use common::sense; |
98 | |
127 | |
99 | use Carp (); |
128 | use Carp (); |
100 | |
129 | |
101 | use AE (); |
130 | use AE (); |
102 | |
131 | |
103 | use base "Exporter"; |
132 | use base "Exporter"; |
104 | |
133 | |
105 | our $VERSION = '0.1'; |
134 | our $VERSION = $AnyEvent::MP::Kernel::VERSION; |
|
|
135 | |
106 | our @EXPORT = qw( |
136 | our @EXPORT = qw( |
107 | NODE $NODE *SELF node_of _any_ |
137 | NODE $NODE *SELF node_of _any_ |
108 | resolve_node |
138 | resolve_node initialise_node |
109 | become_slave become_public |
|
|
110 | snd rcv mon kil reg psub |
139 | snd rcv mon kil reg psub spawn |
111 | port |
140 | port |
112 | ); |
141 | ); |
113 | |
142 | |
114 | our $SELF; |
143 | our $SELF; |
115 | |
144 | |
… | |
… | |
124 | The C<NODE> function returns, and the C<$NODE> variable contains |
153 | The C<NODE> function returns, and the C<$NODE> variable contains |
125 | the noderef of the local node. The value is initialised by a call |
154 | the noderef of the local node. The value is initialised by a call |
126 | to C<become_public> or C<become_slave>, after which all local port |
155 | to C<become_public> or C<become_slave>, after which all local port |
127 | identifiers become invalid. |
156 | identifiers become invalid. |
128 | |
157 | |
129 | =item $noderef = node_of $portid |
158 | =item $noderef = node_of $port |
130 | |
159 | |
131 | Extracts and returns the noderef from a portid or a noderef. |
160 | Extracts and returns the noderef from a portid or a noderef. |
|
|
161 | |
|
|
162 | =item initialise_node $noderef, $seednode, $seednode... |
|
|
163 | |
|
|
164 | =item initialise_node "slave/", $master, $master... |
|
|
165 | |
|
|
166 | Before a node can talk to other nodes on the network it has to initialise |
|
|
167 | itself - the minimum a node needs to know is it's own name, and optionally |
|
|
168 | it should know the noderefs of some other nodes in the network. |
|
|
169 | |
|
|
170 | This function initialises a node - it must be called exactly once (or |
|
|
171 | never) before calling other AnyEvent::MP functions. |
|
|
172 | |
|
|
173 | All arguments are noderefs, which can be either resolved or unresolved. |
|
|
174 | |
|
|
175 | There are two types of networked nodes, public nodes and slave nodes: |
|
|
176 | |
|
|
177 | =over 4 |
|
|
178 | |
|
|
179 | =item public nodes |
|
|
180 | |
|
|
181 | For public nodes, C<$noderef> must either be a (possibly unresolved) |
|
|
182 | noderef, in which case it will be resolved, or C<undef> (or missing), in |
|
|
183 | which case the noderef will be guessed. |
|
|
184 | |
|
|
185 | Afterwards, the node will bind itself on all endpoints and try to connect |
|
|
186 | to all additional C<$seednodes> that are specified. Seednodes are optional |
|
|
187 | and can be used to quickly bootstrap the node into an existing network. |
|
|
188 | |
|
|
189 | =item slave nodes |
|
|
190 | |
|
|
191 | When the C<$noderef> is the special string C<slave/>, then the node will |
|
|
192 | become a slave node. Slave nodes cannot be contacted from outside and will |
|
|
193 | route most of their traffic to the master node that they attach to. |
|
|
194 | |
|
|
195 | At least one additional noderef is required: The node will try to connect |
|
|
196 | to all of them and will become a slave attached to the first node it can |
|
|
197 | successfully connect to. |
|
|
198 | |
|
|
199 | =back |
|
|
200 | |
|
|
201 | This function will block until all nodes have been resolved and, for slave |
|
|
202 | nodes, until it has successfully established a connection to a master |
|
|
203 | server. |
|
|
204 | |
|
|
205 | Example: become a public node listening on the default node. |
|
|
206 | |
|
|
207 | initialise_node; |
|
|
208 | |
|
|
209 | Example: become a public node, and try to contact some well-known master |
|
|
210 | servers to become part of the network. |
|
|
211 | |
|
|
212 | initialise_node undef, "master1", "master2"; |
|
|
213 | |
|
|
214 | Example: become a public node listening on port C<4041>. |
|
|
215 | |
|
|
216 | initialise_node 4041; |
|
|
217 | |
|
|
218 | Example: become a public node, only visible on localhost port 4044. |
|
|
219 | |
|
|
220 | initialise_node "locahost:4044"; |
|
|
221 | |
|
|
222 | Example: become a slave node to any of the specified master servers. |
|
|
223 | |
|
|
224 | initialise_node "slave/", "master1", "192.168.13.17", "mp.example.net"; |
132 | |
225 | |
133 | =item $cv = resolve_node $noderef |
226 | =item $cv = resolve_node $noderef |
134 | |
227 | |
135 | Takes an unresolved node reference that may contain hostnames and |
228 | Takes an unresolved node reference that may contain hostnames and |
136 | abbreviated IDs, resolves all of them and returns a resolved node |
229 | abbreviated IDs, resolves all of them and returns a resolved node |
… | |
… | |
168 | |
261 | |
169 | Due to some quirks in how perl exports variables, it is impossible to |
262 | Due to some quirks in how perl exports variables, it is impossible to |
170 | just export C<$SELF>, all the symbols called C<SELF> are exported by this |
263 | just export C<$SELF>, all the symbols called C<SELF> are exported by this |
171 | module, but only C<$SELF> is currently used. |
264 | module, but only C<$SELF> is currently used. |
172 | |
265 | |
173 | =item snd $portid, type => @data |
266 | =item snd $port, type => @data |
174 | |
267 | |
175 | =item snd $portid, @msg |
268 | =item snd $port, @msg |
176 | |
269 | |
177 | Send the given message to the given port ID, which can identify either |
270 | Send the given message to the given port ID, which can identify either |
178 | a local or a remote port, and can be either a string or soemthignt hat |
271 | a local or a remote port, and can be either a string or soemthignt hat |
179 | stringifies a sa port ID (such as a port object :). |
272 | stringifies a sa port ID (such as a port object :). |
180 | |
273 | |
… | |
… | |
190 | JSON is used, then only strings, numbers and arrays and hashes consisting |
283 | JSON is used, then only strings, numbers and arrays and hashes consisting |
191 | of those are allowed (no objects). When Storable is used, then anything |
284 | of those are allowed (no objects). When Storable is used, then anything |
192 | that Storable can serialise and deserialise is allowed, and for the local |
285 | that Storable can serialise and deserialise is allowed, and for the local |
193 | node, anything can be passed. |
286 | node, anything can be passed. |
194 | |
287 | |
195 | =item kil $portid[, @reason] |
288 | =item $local_port = port |
196 | |
289 | |
197 | Kill the specified port with the given C<@reason>. |
290 | Create a new local port object that can be used either as a pattern |
|
|
291 | matching port ("full port") or a single-callback port ("miniport"), |
|
|
292 | depending on how C<rcv> callbacks are bound to the object. |
198 | |
293 | |
199 | If no C<@reason> is specified, then the port is killed "normally" (linked |
294 | =item $port = port { my @msg = @_; $finished } |
200 | ports will not be kileld, or even notified). |
|
|
201 | |
295 | |
202 | Otherwise, linked ports get killed with the same reason (second form of |
296 | Creates a "miniport", that is, a very lightweight port without any pattern |
203 | C<mon>, see below). |
297 | matching behind it, and returns its ID. Semantically the same as creating |
|
|
298 | a port and calling C<rcv $port, $callback> on it. |
204 | |
299 | |
205 | Runtime errors while evaluating C<rcv> callbacks or inside C<psub> blocks |
300 | The block will be called for every message received on the port. When the |
206 | will be reported as reason C<< die => $@ >>. |
301 | callback returns a true value its job is considered "done" and the port |
|
|
302 | will be destroyed. Otherwise it will stay alive. |
207 | |
303 | |
208 | Transport/communication errors are reported as C<< transport_error => |
304 | The message will be passed as-is, no extra argument (i.e. no port id) will |
209 | $message >>. |
305 | be passed to the callback. |
210 | |
306 | |
|
|
307 | If you need the local port id in the callback, this works nicely: |
|
|
308 | |
|
|
309 | my $port; $port = port { |
|
|
310 | snd $otherport, reply => $port; |
|
|
311 | }; |
|
|
312 | |
|
|
313 | =cut |
|
|
314 | |
|
|
315 | sub rcv($@); |
|
|
316 | |
|
|
317 | sub port(;&) { |
|
|
318 | my $id = "$UNIQ." . $ID++; |
|
|
319 | my $port = "$NODE#$id"; |
|
|
320 | |
|
|
321 | if (@_) { |
|
|
322 | rcv $port, shift; |
|
|
323 | } else { |
|
|
324 | $PORT{$id} = sub { }; # nop |
|
|
325 | } |
|
|
326 | |
|
|
327 | $port |
|
|
328 | } |
|
|
329 | |
|
|
330 | =item reg $port, $name |
|
|
331 | |
|
|
332 | =item reg $name |
|
|
333 | |
|
|
334 | Registers the given port (or C<$SELF><<< if missing) under the name |
|
|
335 | C<$name>. If the name already exists it is replaced. |
|
|
336 | |
|
|
337 | A port can only be registered under one well known name. |
|
|
338 | |
|
|
339 | A port automatically becomes unregistered when it is killed. |
|
|
340 | |
|
|
341 | =cut |
|
|
342 | |
|
|
343 | sub reg(@) { |
|
|
344 | my $port = @_ > 1 ? shift : $SELF || Carp::croak 'reg: called with one argument only, but $SELF not set,'; |
|
|
345 | |
|
|
346 | $REG{$_[0]} = $port; |
|
|
347 | } |
|
|
348 | |
|
|
349 | =item rcv $port, $callback->(@msg) |
|
|
350 | |
|
|
351 | Replaces the callback on the specified miniport (after converting it to |
|
|
352 | one if required). |
|
|
353 | |
|
|
354 | =item rcv $port, tagstring => $callback->(@msg), ... |
|
|
355 | |
|
|
356 | =item rcv $port, $smartmatch => $callback->(@msg), ... |
|
|
357 | |
|
|
358 | =item rcv $port, [$smartmatch...] => $callback->(@msg), ... |
|
|
359 | |
|
|
360 | Register callbacks to be called on matching messages on the given full |
|
|
361 | port (after converting it to one if required) and return the port. |
|
|
362 | |
|
|
363 | The callback has to return a true value when its work is done, after |
|
|
364 | which is will be removed, or a false value in which case it will stay |
|
|
365 | registered. |
|
|
366 | |
|
|
367 | The global C<$SELF> (exported by this module) contains C<$port> while |
|
|
368 | executing the callback. |
|
|
369 | |
|
|
370 | Runtime errors during callback execution will result in the port being |
|
|
371 | C<kil>ed. |
|
|
372 | |
|
|
373 | If the match is an array reference, then it will be matched against the |
|
|
374 | first elements of the message, otherwise only the first element is being |
|
|
375 | matched. |
|
|
376 | |
|
|
377 | Any element in the match that is specified as C<_any_> (a function |
|
|
378 | exported by this module) matches any single element of the message. |
|
|
379 | |
|
|
380 | While not required, it is highly recommended that the first matching |
|
|
381 | element is a string identifying the message. The one-string-only match is |
|
|
382 | also the most efficient match (by far). |
|
|
383 | |
|
|
384 | Example: create a port and bind receivers on it in one go. |
|
|
385 | |
|
|
386 | my $port = rcv port, |
|
|
387 | msg1 => sub { ...; 0 }, |
|
|
388 | msg2 => sub { ...; 0 }, |
|
|
389 | ; |
|
|
390 | |
|
|
391 | Example: create a port, bind receivers and send it in a message elsewhere |
|
|
392 | in one go: |
|
|
393 | |
|
|
394 | snd $otherport, reply => |
|
|
395 | rcv port, |
|
|
396 | msg1 => sub { ...; 0 }, |
|
|
397 | ... |
|
|
398 | ; |
|
|
399 | |
|
|
400 | =cut |
|
|
401 | |
|
|
402 | sub rcv($@) { |
|
|
403 | my $port = shift; |
|
|
404 | my ($noderef, $portid) = split /#/, $port, 2; |
|
|
405 | |
|
|
406 | ($NODE{$noderef} || add_node $noderef) == $NODE{""} |
|
|
407 | or Carp::croak "$port: rcv can only be called on local ports, caught"; |
|
|
408 | |
|
|
409 | if (@_ == 1) { |
|
|
410 | my $cb = shift; |
|
|
411 | delete $PORT_DATA{$portid}; |
|
|
412 | $PORT{$portid} = sub { |
|
|
413 | local $SELF = $port; |
|
|
414 | eval { |
|
|
415 | &$cb |
|
|
416 | and kil $port; |
|
|
417 | }; |
|
|
418 | _self_die if $@; |
|
|
419 | }; |
|
|
420 | } else { |
|
|
421 | my $self = $PORT_DATA{$portid} ||= do { |
|
|
422 | my $self = bless { |
|
|
423 | id => $port, |
|
|
424 | }, "AnyEvent::MP::Port"; |
|
|
425 | |
|
|
426 | $PORT{$portid} = sub { |
|
|
427 | local $SELF = $port; |
|
|
428 | |
|
|
429 | eval { |
|
|
430 | for (@{ $self->{rc0}{$_[0]} }) { |
|
|
431 | $_ && &{$_->[0]} |
|
|
432 | && undef $_; |
|
|
433 | } |
|
|
434 | |
|
|
435 | for (@{ $self->{rcv}{$_[0]} }) { |
|
|
436 | $_ && [@_[1 .. @{$_->[1]}]] ~~ $_->[1] |
|
|
437 | && &{$_->[0]} |
|
|
438 | && undef $_; |
|
|
439 | } |
|
|
440 | |
|
|
441 | for (@{ $self->{any} }) { |
|
|
442 | $_ && [@_[0 .. $#{$_->[1]}]] ~~ $_->[1] |
|
|
443 | && &{$_->[0]} |
|
|
444 | && undef $_; |
|
|
445 | } |
|
|
446 | }; |
|
|
447 | _self_die if $@; |
|
|
448 | }; |
|
|
449 | |
|
|
450 | $self |
|
|
451 | }; |
|
|
452 | |
|
|
453 | "AnyEvent::MP::Port" eq ref $self |
|
|
454 | or Carp::croak "$port: rcv can only be called on message matching ports, caught"; |
|
|
455 | |
|
|
456 | while (@_) { |
|
|
457 | my ($match, $cb) = splice @_, 0, 2; |
|
|
458 | |
|
|
459 | if (!ref $match) { |
|
|
460 | push @{ $self->{rc0}{$match} }, [$cb]; |
|
|
461 | } elsif (("ARRAY" eq ref $match && !ref $match->[0])) { |
|
|
462 | my ($type, @match) = @$match; |
|
|
463 | @match |
|
|
464 | ? push @{ $self->{rcv}{$match->[0]} }, [$cb, \@match] |
|
|
465 | : push @{ $self->{rc0}{$match->[0]} }, [$cb]; |
|
|
466 | } else { |
|
|
467 | push @{ $self->{any} }, [$cb, $match]; |
|
|
468 | } |
|
|
469 | } |
|
|
470 | } |
|
|
471 | |
|
|
472 | $port |
|
|
473 | } |
|
|
474 | |
|
|
475 | =item $closure = psub { BLOCK } |
|
|
476 | |
|
|
477 | Remembers C<$SELF> and creates a closure out of the BLOCK. When the |
|
|
478 | closure is executed, sets up the environment in the same way as in C<rcv> |
|
|
479 | callbacks, i.e. runtime errors will cause the port to get C<kil>ed. |
|
|
480 | |
|
|
481 | This is useful when you register callbacks from C<rcv> callbacks: |
|
|
482 | |
|
|
483 | rcv delayed_reply => sub { |
|
|
484 | my ($delay, @reply) = @_; |
|
|
485 | my $timer = AE::timer $delay, 0, psub { |
|
|
486 | snd @reply, $SELF; |
|
|
487 | }; |
|
|
488 | }; |
|
|
489 | |
|
|
490 | =cut |
|
|
491 | |
|
|
492 | sub psub(&) { |
|
|
493 | my $cb = shift; |
|
|
494 | |
|
|
495 | my $port = $SELF |
|
|
496 | or Carp::croak "psub can only be called from within rcv or psub callbacks, not"; |
|
|
497 | |
|
|
498 | sub { |
|
|
499 | local $SELF = $port; |
|
|
500 | |
|
|
501 | if (wantarray) { |
|
|
502 | my @res = eval { &$cb }; |
|
|
503 | _self_die if $@; |
|
|
504 | @res |
|
|
505 | } else { |
|
|
506 | my $res = eval { &$cb }; |
|
|
507 | _self_die if $@; |
|
|
508 | $res |
|
|
509 | } |
|
|
510 | } |
|
|
511 | } |
|
|
512 | |
211 | =item $guard = mon $portid, $cb->(@reason) |
513 | =item $guard = mon $port, $cb->(@reason) |
212 | |
514 | |
213 | =item $guard = mon $portid, $otherport |
515 | =item $guard = mon $port, $rcvport |
214 | |
516 | |
|
|
517 | =item $guard = mon $port |
|
|
518 | |
215 | =item $guard = mon $portid, $otherport, @msg |
519 | =item $guard = mon $port, $rcvport, @msg |
216 | |
520 | |
217 | Monitor the given port and do something when the port is killed. |
521 | Monitor the given port and do something when the port is killed or |
|
|
522 | messages to it were lost, and optionally return a guard that can be used |
|
|
523 | to stop monitoring again. |
218 | |
524 | |
|
|
525 | C<mon> effectively guarantees that, in the absence of hardware failures, |
|
|
526 | that after starting the monitor, either all messages sent to the port |
|
|
527 | will arrive, or the monitoring action will be invoked after possible |
|
|
528 | message loss has been detected. No messages will be lost "in between" |
|
|
529 | (after the first lost message no further messages will be received by the |
|
|
530 | port). After the monitoring action was invoked, further messages might get |
|
|
531 | delivered again. |
|
|
532 | |
219 | In the first form, the callback is simply called with any number |
533 | In the first form (callback), the callback is simply called with any |
220 | of C<@reason> elements (no @reason means that the port was deleted |
534 | number of C<@reason> elements (no @reason means that the port was deleted |
221 | "normally"). Note also that I<< the callback B<must> never die >>, so use |
535 | "normally"). Note also that I<< the callback B<must> never die >>, so use |
222 | C<eval> if unsure. |
536 | C<eval> if unsure. |
223 | |
537 | |
224 | In the second form, the other port will be C<kil>'ed with C<@reason>, iff |
538 | In the second form (another port given), the other port (C<$rcvport>) |
225 | a @reason was specified, i.e. on "normal" kils nothing happens, while |
539 | will be C<kil>'ed with C<@reason>, iff a @reason was specified, i.e. on |
226 | under all other conditions, the other port is killed with the same reason. |
540 | "normal" kils nothing happens, while under all other conditions, the other |
|
|
541 | port is killed with the same reason. |
227 | |
542 | |
|
|
543 | The third form (kill self) is the same as the second form, except that |
|
|
544 | C<$rvport> defaults to C<$SELF>. |
|
|
545 | |
228 | In the last form, a message of the form C<@msg, @reason> will be C<snd>. |
546 | In the last form (message), a message of the form C<@msg, @reason> will be |
|
|
547 | C<snd>. |
|
|
548 | |
|
|
549 | As a rule of thumb, monitoring requests should always monitor a port from |
|
|
550 | a local port (or callback). The reason is that kill messages might get |
|
|
551 | lost, just like any other message. Another less obvious reason is that |
|
|
552 | even monitoring requests can get lost (for exmaple, when the connection |
|
|
553 | to the other node goes down permanently). When monitoring a port locally |
|
|
554 | these problems do not exist. |
229 | |
555 | |
230 | Example: call a given callback when C<$port> is killed. |
556 | Example: call a given callback when C<$port> is killed. |
231 | |
557 | |
232 | mon $port, sub { warn "port died because of <@_>\n" }; |
558 | mon $port, sub { warn "port died because of <@_>\n" }; |
233 | |
559 | |
234 | Example: kill ourselves when C<$port> is killed abnormally. |
560 | Example: kill ourselves when C<$port> is killed abnormally. |
235 | |
561 | |
236 | mon $port, $self; |
562 | mon $port; |
237 | |
563 | |
238 | Example: send us a restart message another C<$port> is killed. |
564 | Example: send us a restart message when another C<$port> is killed. |
239 | |
565 | |
240 | mon $port, $self => "restart"; |
566 | mon $port, $self => "restart"; |
241 | |
567 | |
242 | =cut |
568 | =cut |
243 | |
569 | |
244 | sub mon { |
570 | sub mon { |
245 | my ($noderef, $port) = split /#/, shift, 2; |
571 | my ($noderef, $port) = split /#/, shift, 2; |
246 | |
572 | |
247 | my $node = $NODE{$noderef} || add_node $noderef; |
573 | my $node = $NODE{$noderef} || add_node $noderef; |
248 | |
574 | |
249 | my $cb = shift; |
575 | my $cb = @_ ? shift : $SELF || Carp::croak 'mon: called with one argument only, but $SELF not set,'; |
250 | |
576 | |
251 | unless (ref $cb) { |
577 | unless (ref $cb) { |
252 | if (@_) { |
578 | if (@_) { |
253 | # send a kill info message |
579 | # send a kill info message |
254 | my (@msg) = ($cb, @_); |
580 | my (@msg) = ($cb, @_); |
… | |
… | |
285 | =cut |
611 | =cut |
286 | |
612 | |
287 | sub mon_guard { |
613 | sub mon_guard { |
288 | my ($port, @refs) = @_; |
614 | my ($port, @refs) = @_; |
289 | |
615 | |
|
|
616 | #TODO: mon-less form? |
|
|
617 | |
290 | mon $port, sub { 0 && @refs } |
618 | mon $port, sub { 0 && @refs } |
291 | } |
619 | } |
292 | |
620 | |
293 | =item lnk $port1, $port2 |
621 | =item kil $port[, @reason] |
294 | |
622 | |
295 | Link two ports. This is simply a shorthand for: |
623 | Kill the specified port with the given C<@reason>. |
296 | |
624 | |
297 | mon $port1, $port2; |
625 | If no C<@reason> is specified, then the port is killed "normally" (linked |
298 | mon $port2, $port1; |
626 | ports will not be kileld, or even notified). |
299 | |
627 | |
300 | It means that if either one is killed abnormally, the other one gets |
628 | Otherwise, linked ports get killed with the same reason (second form of |
301 | killed as well. |
629 | C<mon>, see below). |
302 | |
630 | |
303 | =item $local_port = port |
631 | Runtime errors while evaluating C<rcv> callbacks or inside C<psub> blocks |
|
|
632 | will be reported as reason C<< die => $@ >>. |
304 | |
633 | |
305 | Create a new local port object that supports message matching. |
634 | Transport/communication errors are reported as C<< transport_error => |
|
|
635 | $message >>. |
306 | |
636 | |
307 | =item $portid = port { my @msg = @_; $finished } |
|
|
308 | |
|
|
309 | Creates a "mini port", that is, a very lightweight port without any |
|
|
310 | pattern matching behind it, and returns its ID. |
|
|
311 | |
|
|
312 | The block will be called for every message received on the port. When the |
|
|
313 | callback returns a true value its job is considered "done" and the port |
|
|
314 | will be destroyed. Otherwise it will stay alive. |
|
|
315 | |
|
|
316 | The message will be passed as-is, no extra argument (i.e. no port id) will |
|
|
317 | be passed to the callback. |
|
|
318 | |
|
|
319 | If you need the local port id in the callback, this works nicely: |
|
|
320 | |
|
|
321 | my $port; $port = miniport { |
|
|
322 | snd $otherport, reply => $port; |
|
|
323 | }; |
|
|
324 | |
|
|
325 | =cut |
637 | =cut |
326 | |
638 | |
327 | sub port(;&) { |
639 | =item $port = spawn $node, $initfunc[, @initdata] |
328 | my $id = "$UNIQ." . $ID++; |
|
|
329 | my $port = "$NODE#$id"; |
|
|
330 | |
640 | |
331 | if (@_) { |
641 | Creates a port on the node C<$node> (which can also be a port ID, in which |
332 | my $cb = shift; |
642 | case it's the node where that port resides). |
333 | $PORT{$id} = sub { |
643 | |
334 | local $SELF = $port; |
644 | The port ID of the newly created port is return immediately, and it is |
335 | eval { |
645 | permissible to immediately start sending messages or monitor the port. |
336 | &$cb |
646 | |
337 | and kil $id; |
647 | After the port has been created, the init function is |
|
|
648 | called. This function must be a fully-qualified function name |
|
|
649 | (e.g. C<MyApp::Chat::Server::init>). To specify a function in the main |
|
|
650 | program, use C<::name>. |
|
|
651 | |
|
|
652 | If the function doesn't exist, then the node tries to C<require> |
|
|
653 | the package, then the package above the package and so on (e.g. |
|
|
654 | C<MyApp::Chat::Server>, C<MyApp::Chat>, C<MyApp>) until the function |
|
|
655 | exists or it runs out of package names. |
|
|
656 | |
|
|
657 | The init function is then called with the newly-created port as context |
|
|
658 | object (C<$SELF>) and the C<@initdata> values as arguments. |
|
|
659 | |
|
|
660 | A common idiom is to pass your own port, monitor the spawned port, and |
|
|
661 | in the init function, monitor the original port. This two-way monitoring |
|
|
662 | ensures that both ports get cleaned up when there is a problem. |
|
|
663 | |
|
|
664 | Example: spawn a chat server port on C<$othernode>. |
|
|
665 | |
|
|
666 | # this node, executed from within a port context: |
|
|
667 | my $server = spawn $othernode, "MyApp::Chat::Server::connect", $SELF; |
|
|
668 | mon $server; |
|
|
669 | |
|
|
670 | # init function on C<$othernode> |
|
|
671 | sub connect { |
|
|
672 | my ($srcport) = @_; |
|
|
673 | |
|
|
674 | mon $srcport; |
|
|
675 | |
|
|
676 | rcv $SELF, sub { |
338 | }; |
677 | ... |
339 | _self_die if $@; |
|
|
340 | }; |
|
|
341 | } else { |
|
|
342 | my $self = bless { |
|
|
343 | id => "$NODE#$id", |
|
|
344 | }, "AnyEvent::MP::Port"; |
|
|
345 | |
|
|
346 | $PORT_DATA{$id} = $self; |
|
|
347 | $PORT{$id} = sub { |
|
|
348 | local $SELF = $port; |
|
|
349 | |
|
|
350 | eval { |
|
|
351 | for (@{ $self->{rc0}{$_[0]} }) { |
|
|
352 | $_ && &{$_->[0]} |
|
|
353 | && undef $_; |
|
|
354 | } |
|
|
355 | |
|
|
356 | for (@{ $self->{rcv}{$_[0]} }) { |
|
|
357 | $_ && [@_[1 .. @{$_->[1]}]] ~~ $_->[1] |
|
|
358 | && &{$_->[0]} |
|
|
359 | && undef $_; |
|
|
360 | } |
|
|
361 | |
|
|
362 | for (@{ $self->{any} }) { |
|
|
363 | $_ && [@_[0 .. $#{$_->[1]}]] ~~ $_->[1] |
|
|
364 | && &{$_->[0]} |
|
|
365 | && undef $_; |
|
|
366 | } |
|
|
367 | }; |
|
|
368 | _self_die if $@; |
|
|
369 | }; |
678 | }; |
370 | } |
679 | } |
371 | |
680 | |
372 | $port |
681 | =cut |
|
|
682 | |
|
|
683 | sub _spawn { |
|
|
684 | my $port = shift; |
|
|
685 | my $init = shift; |
|
|
686 | |
|
|
687 | local $SELF = "$NODE#$port"; |
|
|
688 | eval { |
|
|
689 | &{ load_func $init } |
|
|
690 | }; |
|
|
691 | _self_die if $@; |
373 | } |
692 | } |
374 | |
693 | |
375 | =item reg $portid, $name |
694 | sub spawn(@) { |
|
|
695 | my ($noderef, undef) = split /#/, shift, 2; |
376 | |
696 | |
377 | Registers the given port under the name C<$name>. If the name already |
697 | my $id = "$RUNIQ." . $ID++; |
378 | exists it is replaced. |
|
|
379 | |
698 | |
380 | A port can only be registered under one well known name. |
699 | $_[0] =~ /::/ |
|
|
700 | or Carp::croak "spawn init function must be a fully-qualified name, caught"; |
381 | |
701 | |
382 | A port automatically becomes unregistered when it is killed. |
702 | ($NODE{$noderef} || add_node $noderef) |
|
|
703 | ->send (["", "AnyEvent::MP::_spawn" => $id, @_]); |
383 | |
704 | |
384 | =cut |
705 | "$noderef#$id" |
385 | |
|
|
386 | sub reg(@) { |
|
|
387 | my ($portid, $name) = @_; |
|
|
388 | |
|
|
389 | $REG{$name} = $portid; |
|
|
390 | } |
706 | } |
391 | |
|
|
392 | =item rcv $portid, tagstring => $callback->(@msg), ... |
|
|
393 | |
|
|
394 | =item rcv $portid, $smartmatch => $callback->(@msg), ... |
|
|
395 | |
|
|
396 | =item rcv $portid, [$smartmatch...] => $callback->(@msg), ... |
|
|
397 | |
|
|
398 | Register callbacks to be called on matching messages on the given port. |
|
|
399 | |
|
|
400 | The callback has to return a true value when its work is done, after |
|
|
401 | which is will be removed, or a false value in which case it will stay |
|
|
402 | registered. |
|
|
403 | |
|
|
404 | The global C<$SELF> (exported by this module) contains C<$portid> while |
|
|
405 | executing the callback. |
|
|
406 | |
|
|
407 | Runtime errors wdurign callback execution will result in the port being |
|
|
408 | C<kil>ed. |
|
|
409 | |
|
|
410 | If the match is an array reference, then it will be matched against the |
|
|
411 | first elements of the message, otherwise only the first element is being |
|
|
412 | matched. |
|
|
413 | |
|
|
414 | Any element in the match that is specified as C<_any_> (a function |
|
|
415 | exported by this module) matches any single element of the message. |
|
|
416 | |
|
|
417 | While not required, it is highly recommended that the first matching |
|
|
418 | element is a string identifying the message. The one-string-only match is |
|
|
419 | also the most efficient match (by far). |
|
|
420 | |
|
|
421 | =cut |
|
|
422 | |
|
|
423 | sub rcv($@) { |
|
|
424 | my ($noderef, $port) = split /#/, shift, 2; |
|
|
425 | |
|
|
426 | ($NODE{$noderef} || add_node $noderef) == $NODE{""} |
|
|
427 | or Carp::croak "$noderef#$port: rcv can only be called on local ports, caught"; |
|
|
428 | |
|
|
429 | my $self = $PORT_DATA{$port} |
|
|
430 | or Carp::croak "$noderef#$port: rcv can only be called on message matching ports, caught"; |
|
|
431 | |
|
|
432 | "AnyEvent::MP::Port" eq ref $self |
|
|
433 | or Carp::croak "$noderef#$port: rcv can only be called on message matching ports, caught"; |
|
|
434 | |
|
|
435 | while (@_) { |
|
|
436 | my ($match, $cb) = splice @_, 0, 2; |
|
|
437 | |
|
|
438 | if (!ref $match) { |
|
|
439 | push @{ $self->{rc0}{$match} }, [$cb]; |
|
|
440 | } elsif (("ARRAY" eq ref $match && !ref $match->[0])) { |
|
|
441 | my ($type, @match) = @$match; |
|
|
442 | @match |
|
|
443 | ? push @{ $self->{rcv}{$match->[0]} }, [$cb, \@match] |
|
|
444 | : push @{ $self->{rc0}{$match->[0]} }, [$cb]; |
|
|
445 | } else { |
|
|
446 | push @{ $self->{any} }, [$cb, $match]; |
|
|
447 | } |
|
|
448 | } |
|
|
449 | } |
|
|
450 | |
|
|
451 | =item $closure = psub { BLOCK } |
|
|
452 | |
|
|
453 | Remembers C<$SELF> and creates a closure out of the BLOCK. When the |
|
|
454 | closure is executed, sets up the environment in the same way as in C<rcv> |
|
|
455 | callbacks, i.e. runtime errors will cause the port to get C<kil>ed. |
|
|
456 | |
|
|
457 | This is useful when you register callbacks from C<rcv> callbacks: |
|
|
458 | |
|
|
459 | rcv delayed_reply => sub { |
|
|
460 | my ($delay, @reply) = @_; |
|
|
461 | my $timer = AE::timer $delay, 0, psub { |
|
|
462 | snd @reply, $SELF; |
|
|
463 | }; |
|
|
464 | }; |
|
|
465 | |
|
|
466 | =cut |
|
|
467 | |
|
|
468 | sub psub(&) { |
|
|
469 | my $cb = shift; |
|
|
470 | |
|
|
471 | my $port = $SELF |
|
|
472 | or Carp::croak "psub can only be called from within rcv or psub callbacks, not"; |
|
|
473 | |
|
|
474 | sub { |
|
|
475 | local $SELF = $port; |
|
|
476 | |
|
|
477 | if (wantarray) { |
|
|
478 | my @res = eval { &$cb }; |
|
|
479 | _self_die if $@; |
|
|
480 | @res |
|
|
481 | } else { |
|
|
482 | my $res = eval { &$cb }; |
|
|
483 | _self_die if $@; |
|
|
484 | $res |
|
|
485 | } |
|
|
486 | } |
|
|
487 | } |
|
|
488 | |
|
|
489 | =back |
|
|
490 | |
|
|
491 | =head1 FUNCTIONS FOR NODES |
|
|
492 | |
|
|
493 | =over 4 |
|
|
494 | |
|
|
495 | =item become_public $noderef |
|
|
496 | |
|
|
497 | Tells the node to become a public node, i.e. reachable from other nodes. |
|
|
498 | |
|
|
499 | The first argument is the (unresolved) node reference of the local node |
|
|
500 | (if missing then the empty string is used). |
|
|
501 | |
|
|
502 | It is quite common to not specify anything, in which case the local node |
|
|
503 | tries to listen on the default port, or to only specify a port number, in |
|
|
504 | which case AnyEvent::MP tries to guess the local addresses. |
|
|
505 | |
|
|
506 | =cut |
|
|
507 | |
707 | |
508 | =back |
708 | =back |
509 | |
709 | |
510 | =head1 NODE MESSAGES |
710 | =head1 NODE MESSAGES |
511 | |
711 | |
… | |
… | |
553 | |
753 | |
554 | =back |
754 | =back |
555 | |
755 | |
556 | =head1 AnyEvent::MP vs. Distributed Erlang |
756 | =head1 AnyEvent::MP vs. Distributed Erlang |
557 | |
757 | |
558 | AnyEvent::MP got lots of its ideas from distributed erlang (erlang node |
758 | AnyEvent::MP got lots of its ideas from distributed Erlang (Erlang node |
559 | == aemp node, erlang process == aemp port), so many of the documents and |
759 | == aemp node, Erlang process == aemp port), so many of the documents and |
560 | programming techniques employed by erlang apply to AnyEvent::MP. Here is a |
760 | programming techniques employed by Erlang apply to AnyEvent::MP. Here is a |
561 | sample: |
761 | sample: |
562 | |
762 | |
563 | http://www.erlang.se/doc/programming_rules.shtml |
763 | http://www.Erlang.se/doc/programming_rules.shtml |
564 | http://erlang.org/doc/getting_started/part_frame.html # chapters 3 and 4 |
764 | http://Erlang.org/doc/getting_started/part_frame.html # chapters 3 and 4 |
565 | http://erlang.org/download/erlang-book-part1.pdf # chapters 5 and 6 |
765 | http://Erlang.org/download/Erlang-book-part1.pdf # chapters 5 and 6 |
566 | http://erlang.org/download/armstrong_thesis_2003.pdf # chapters 4 and 5 |
766 | http://Erlang.org/download/armstrong_thesis_2003.pdf # chapters 4 and 5 |
567 | |
767 | |
568 | Despite the similarities, there are also some important differences: |
768 | Despite the similarities, there are also some important differences: |
569 | |
769 | |
570 | =over 4 |
770 | =over 4 |
571 | |
771 | |
… | |
… | |
582 | |
782 | |
583 | Erlang uses processes that selctively receive messages, and therefore |
783 | Erlang uses processes that selctively receive messages, and therefore |
584 | needs a queue. AEMP is event based, queuing messages would serve no useful |
784 | needs a queue. AEMP is event based, queuing messages would serve no useful |
585 | purpose. |
785 | purpose. |
586 | |
786 | |
587 | (But see L<Coro::MP> for a more erlang-like process model on top of AEMP). |
787 | (But see L<Coro::MP> for a more Erlang-like process model on top of AEMP). |
588 | |
788 | |
589 | =item * Erlang sends are synchronous, AEMP sends are asynchronous. |
789 | =item * Erlang sends are synchronous, AEMP sends are asynchronous. |
590 | |
790 | |
591 | Sending messages in erlang is synchronous and blocks the process. AEMP |
791 | Sending messages in Erlang is synchronous and blocks the process. AEMP |
592 | sends are immediate, connection establishment is handled in the |
792 | sends are immediate, connection establishment is handled in the |
593 | background. |
793 | background. |
594 | |
794 | |
595 | =item * Erlang can silently lose messages, AEMP cannot. |
795 | =item * Erlang can silently lose messages, AEMP cannot. |
596 | |
796 | |
… | |
… | |
599 | and c, and the other side only receives messages a and c). |
799 | and c, and the other side only receives messages a and c). |
600 | |
800 | |
601 | AEMP guarantees correct ordering, and the guarantee that there are no |
801 | AEMP guarantees correct ordering, and the guarantee that there are no |
602 | holes in the message sequence. |
802 | holes in the message sequence. |
603 | |
803 | |
604 | =item * In erlang, processes can be declared dead and later be found to be |
804 | =item * In Erlang, processes can be declared dead and later be found to be |
605 | alive. |
805 | alive. |
606 | |
806 | |
607 | In erlang it can happen that a monitored process is declared dead and |
807 | In Erlang it can happen that a monitored process is declared dead and |
608 | linked processes get killed, but later it turns out that the process is |
808 | linked processes get killed, but later it turns out that the process is |
609 | still alive - and can receive messages. |
809 | still alive - and can receive messages. |
610 | |
810 | |
611 | In AEMP, when port monitoring detects a port as dead, then that port will |
811 | In AEMP, when port monitoring detects a port as dead, then that port will |
612 | eventually be killed - it cannot happen that a node detects a port as dead |
812 | eventually be killed - it cannot happen that a node detects a port as dead |
613 | and then later sends messages to it, finding it is still alive. |
813 | and then later sends messages to it, finding it is still alive. |
614 | |
814 | |
615 | =item * Erlang can send messages to the wrong port, AEMP does not. |
815 | =item * Erlang can send messages to the wrong port, AEMP does not. |
616 | |
816 | |
617 | In erlang it is quite possible that a node that restarts reuses a process |
817 | In Erlang it is quite possible that a node that restarts reuses a process |
618 | ID known to other nodes for a completely different process, causing |
818 | ID known to other nodes for a completely different process, causing |
619 | messages destined for that process to end up in an unrelated process. |
819 | messages destined for that process to end up in an unrelated process. |
620 | |
820 | |
621 | AEMP never reuses port IDs, so old messages or old port IDs floating |
821 | AEMP never reuses port IDs, so old messages or old port IDs floating |
622 | around in the network will not be sent to an unrelated port. |
822 | around in the network will not be sent to an unrelated port. |
… | |
… | |
628 | securely authenticate nodes. |
828 | securely authenticate nodes. |
629 | |
829 | |
630 | =item * The AEMP protocol is optimised for both text-based and binary |
830 | =item * The AEMP protocol is optimised for both text-based and binary |
631 | communications. |
831 | communications. |
632 | |
832 | |
633 | The AEMP protocol, unlike the erlang protocol, supports both |
833 | The AEMP protocol, unlike the Erlang protocol, supports both |
634 | language-independent text-only protocols (good for debugging) and binary, |
834 | language-independent text-only protocols (good for debugging) and binary, |
635 | language-specific serialisers (e.g. Storable). |
835 | language-specific serialisers (e.g. Storable). |
636 | |
836 | |
637 | It has also been carefully designed to be implementable in other languages |
837 | It has also been carefully designed to be implementable in other languages |
638 | with a minimum of work while gracefully degrading fucntionality to make the |
838 | with a minimum of work while gracefully degrading fucntionality to make the |
639 | protocol simple. |
839 | protocol simple. |
640 | |
840 | |
|
|
841 | =item * AEMP has more flexible monitoring options than Erlang. |
|
|
842 | |
|
|
843 | In Erlang, you can chose to receive I<all> exit signals as messages |
|
|
844 | or I<none>, there is no in-between, so monitoring single processes is |
|
|
845 | difficult to implement. Monitoring in AEMP is more flexible than in |
|
|
846 | Erlang, as one can choose between automatic kill, exit message or callback |
|
|
847 | on a per-process basis. |
|
|
848 | |
|
|
849 | =item * Erlang tries to hide remote/local connections, AEMP does not. |
|
|
850 | |
|
|
851 | Monitoring in Erlang is not an indicator of process death/crashes, |
|
|
852 | as linking is (except linking is unreliable in Erlang). |
|
|
853 | |
|
|
854 | In AEMP, you don't "look up" registered port names or send to named ports |
|
|
855 | that might or might not be persistent. Instead, you normally spawn a port |
|
|
856 | on the remote node. The init function monitors the you, and you monitor |
|
|
857 | the remote port. Since both monitors are local to the node, they are much |
|
|
858 | more reliable. |
|
|
859 | |
|
|
860 | This also saves round-trips and avoids sending messages to the wrong port |
|
|
861 | (hard to do in Erlang). |
|
|
862 | |
|
|
863 | =back |
|
|
864 | |
|
|
865 | =head1 RATIONALE |
|
|
866 | |
|
|
867 | =over 4 |
|
|
868 | |
|
|
869 | =item Why strings for ports and noderefs, why not objects? |
|
|
870 | |
|
|
871 | We considered "objects", but found that the actual number of methods |
|
|
872 | thatc an be called are very low. Since port IDs and noderefs travel over |
|
|
873 | the network frequently, the serialising/deserialising would add lots of |
|
|
874 | overhead, as well as having to keep a proxy object. |
|
|
875 | |
|
|
876 | Strings can easily be printed, easily serialised etc. and need no special |
|
|
877 | procedures to be "valid". |
|
|
878 | |
|
|
879 | And a a miniport consists of a single closure stored in a global hash - it |
|
|
880 | can't become much cheaper. |
|
|
881 | |
|
|
882 | =item Why favour JSON, why not real serialising format such as Storable? |
|
|
883 | |
|
|
884 | In fact, any AnyEvent::MP node will happily accept Storable as framing |
|
|
885 | format, but currently there is no way to make a node use Storable by |
|
|
886 | default. |
|
|
887 | |
|
|
888 | The default framing protocol is JSON because a) JSON::XS is many times |
|
|
889 | faster for small messages and b) most importantly, after years of |
|
|
890 | experience we found that object serialisation is causing more problems |
|
|
891 | than it gains: Just like function calls, objects simply do not travel |
|
|
892 | easily over the network, mostly because they will always be a copy, so you |
|
|
893 | always have to re-think your design. |
|
|
894 | |
|
|
895 | Keeping your messages simple, concentrating on data structures rather than |
|
|
896 | objects, will keep your messages clean, tidy and efficient. |
|
|
897 | |
641 | =back |
898 | =back |
642 | |
899 | |
643 | =head1 SEE ALSO |
900 | =head1 SEE ALSO |
644 | |
901 | |
645 | L<AnyEvent>. |
902 | L<AnyEvent>. |