… | |
… | |
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 ports, the simple way |
|
|
28 | my $simple_port = port { my @msg = @_; 0 }; |
16 | |
29 | |
17 | rcv $port, smartmatch => $cb->($port, @msg); |
30 | # creating/using ports, tagged message matching |
18 | |
31 | my $port = port; |
19 | # examples: |
|
|
20 | rcv $port2, ping => sub { snd $_[0], "pong"; 0 }; |
32 | rcv $port, ping => sub { snd $_[0], "pong"; 0 }; |
21 | rcv $port1, pong => sub { warn "pong received\n" }; |
33 | rcv $port, pong => sub { warn "pong received\n"; 0 }; |
22 | snd $port2, ping => $port1; |
|
|
23 | |
34 | |
24 | # more, smarter, matches (_any_ is exported by this module) |
35 | # create a port on another node |
25 | rcv $port, [child_died => $pid] => sub { ... |
36 | my $port = spawn $node, $initfunc, @initdata; |
26 | rcv $port, [_any_, _any_, 3] => sub { .. $_[2] is 3 |
37 | |
|
|
38 | # monitoring |
|
|
39 | mon $port, $cb->(@msg) # callback is invoked on death |
|
|
40 | mon $port, $otherport # kill otherport on abnormal death |
|
|
41 | mon $port, $otherport, @msg # send message on death |
|
|
42 | |
|
|
43 | =head1 CURRENT STATUS |
|
|
44 | |
|
|
45 | AnyEvent::MP - stable API, should work |
|
|
46 | AnyEvent::MP::Intro - outdated |
|
|
47 | AnyEvent::MP::Kernel - WIP |
|
|
48 | AnyEvent::MP::Transport - mostly stable |
|
|
49 | |
|
|
50 | stay tuned. |
27 | |
51 | |
28 | =head1 DESCRIPTION |
52 | =head1 DESCRIPTION |
29 | |
53 | |
30 | This module (-family) implements a simple message passing framework. |
54 | This module (-family) implements a simple message passing framework. |
31 | |
55 | |
… | |
… | |
35 | For an introduction to this module family, see the L<AnyEvent::MP::Intro> |
59 | For an introduction to this module family, see the L<AnyEvent::MP::Intro> |
36 | manual page. |
60 | manual page. |
37 | |
61 | |
38 | At the moment, this module family is severly broken and underdocumented, |
62 | 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 - |
63 | so do not use. This was uploaded mainly to reserve the CPAN namespace - |
40 | stay tuned! The basic API should be finished, however. |
64 | stay tuned! |
41 | |
65 | |
42 | =head1 CONCEPTS |
66 | =head1 CONCEPTS |
43 | |
67 | |
44 | =over 4 |
68 | =over 4 |
45 | |
69 | |
46 | =item port |
70 | =item port |
47 | |
71 | |
48 | A port is something you can send messages to (with the C<snd> function). |
72 | A port is something you can send messages to (with the C<snd> function). |
49 | |
73 | |
50 | Some ports allow you to register C<rcv> handlers that can match specific |
74 | Ports allow you to register C<rcv> handlers that can match all or just |
51 | messages. All C<rcv> handlers will receive messages they match, messages |
75 | some messages. Messages will not be queued. |
52 | will not be queued. |
|
|
53 | |
76 | |
54 | =item port id - C<noderef#portname> |
77 | =item port id - C<noderef#portname> |
55 | |
78 | |
56 | A port id is normaly the concatenation of a noderef, a hash-mark (C<#>) as |
79 | A port ID is the concatenation of a noderef, a hash-mark (C<#>) as |
57 | separator, and a port name (a printable string of unspecified format). An |
80 | separator, and a port name (a printable string of unspecified format). An |
58 | exception is the the node port, whose ID is identical to its node |
81 | exception is the the node port, whose ID is identical to its node |
59 | reference. |
82 | reference. |
60 | |
83 | |
61 | =item node |
84 | =item node |
62 | |
85 | |
63 | A node is a single process containing at least one port - the node |
86 | A node is a single process containing at least one port - the node port, |
64 | port. You can send messages to node ports to find existing ports or to |
87 | which provides nodes to manage each other remotely, and to create new |
65 | create new ports, among other things. |
88 | ports. |
66 | |
89 | |
67 | Nodes are either private (single-process only), slaves (connected to a |
90 | Nodes are either private (single-process only), slaves (connected to a |
68 | master node only) or public nodes (connectable from unrelated nodes). |
91 | master node only) or public nodes (connectable from unrelated nodes). |
69 | |
92 | |
70 | =item noderef - C<host:port,host:port...>, C<id@noderef>, C<id> |
93 | =item noderef - C<host:port,host:port...>, C<id@noderef>, C<id> |
… | |
… | |
90 | |
113 | |
91 | =cut |
114 | =cut |
92 | |
115 | |
93 | package AnyEvent::MP; |
116 | package AnyEvent::MP; |
94 | |
117 | |
95 | use AnyEvent::MP::Base; |
118 | use AnyEvent::MP::Kernel; |
96 | |
119 | |
97 | use common::sense; |
120 | use common::sense; |
98 | |
121 | |
99 | use Carp (); |
122 | use Carp (); |
100 | |
123 | |
101 | use AE (); |
124 | use AE (); |
102 | |
125 | |
103 | use base "Exporter"; |
126 | use base "Exporter"; |
104 | |
127 | |
105 | our $VERSION = '0.1'; |
128 | our $VERSION = $AnyEvent::MP::Kernel::VERSION; |
|
|
129 | |
106 | our @EXPORT = qw( |
130 | our @EXPORT = qw( |
107 | NODE $NODE *SELF node_of _any_ |
131 | NODE $NODE *SELF node_of _any_ |
108 | resolve_node initialise_node |
132 | resolve_node initialise_node |
109 | snd rcv mon kil reg psub |
133 | snd rcv mon kil reg psub spawn |
110 | port |
134 | port |
111 | ); |
135 | ); |
112 | |
136 | |
113 | our $SELF; |
137 | our $SELF; |
114 | |
138 | |
… | |
… | |
118 | kil $SELF, die => $msg; |
142 | kil $SELF, die => $msg; |
119 | } |
143 | } |
120 | |
144 | |
121 | =item $thisnode = NODE / $NODE |
145 | =item $thisnode = NODE / $NODE |
122 | |
146 | |
123 | The C<NODE> function returns, and the C<$NODE> variable contains |
147 | The C<NODE> function returns, and the C<$NODE> variable contains the |
124 | the noderef of the local node. The value is initialised by a call |
148 | noderef of the local node. The value is initialised by a call to |
125 | to C<become_public> or C<become_slave>, after which all local port |
149 | C<initialise_node>. |
126 | identifiers become invalid. |
|
|
127 | |
150 | |
128 | =item $noderef = node_of $port |
151 | =item $noderef = node_of $port |
129 | |
152 | |
130 | Extracts and returns the noderef from a portid or a noderef. |
153 | Extracts and returns the noderef from a port ID or a noderef. |
131 | |
154 | |
132 | =item initialise_node $noderef, $seednode, $seednode... |
155 | =item initialise_node $noderef, $seednode, $seednode... |
133 | |
156 | |
134 | =item initialise_node "slave/", $master, $master... |
157 | =item initialise_node "slave/", $master, $master... |
135 | |
158 | |
… | |
… | |
138 | it should know the noderefs of some other nodes in the network. |
161 | it should know the noderefs of some other nodes in the network. |
139 | |
162 | |
140 | This function initialises a node - it must be called exactly once (or |
163 | This function initialises a node - it must be called exactly once (or |
141 | never) before calling other AnyEvent::MP functions. |
164 | never) before calling other AnyEvent::MP functions. |
142 | |
165 | |
143 | All arguments are noderefs, which can be either resolved or unresolved. |
166 | All arguments (optionally except for the first) are noderefs, which can be |
|
|
167 | either resolved or unresolved. |
|
|
168 | |
|
|
169 | The first argument will be looked up in the configuration database first |
|
|
170 | (if it is C<undef> then the current nodename will be used instead) to find |
|
|
171 | the relevant configuration profile (see L<aemp>). If none is found then |
|
|
172 | the default configuration is used. The configuration supplies additional |
|
|
173 | seed/master nodes and can override the actual noderef. |
144 | |
174 | |
145 | There are two types of networked nodes, public nodes and slave nodes: |
175 | There are two types of networked nodes, public nodes and slave nodes: |
146 | |
176 | |
147 | =over 4 |
177 | =over 4 |
148 | |
178 | |
149 | =item public nodes |
179 | =item public nodes |
150 | |
180 | |
151 | For public nodes, C<$noderef> must either be a (possibly unresolved) |
181 | For public nodes, C<$noderef> (supplied either directly to |
152 | noderef, in which case it will be resolved, or C<undef> (or missing), in |
182 | C<initialise_node> or indirectly via a profile or the nodename) must be a |
153 | which case the noderef will be guessed. |
183 | noderef (possibly unresolved, in which case it will be resolved). |
154 | |
184 | |
155 | Afterwards, the node will bind itself on all endpoints and try to connect |
185 | After resolving, the node will bind itself on all endpoints and try to |
156 | to all additional C<$seednodes> that are specified. Seednodes are optional |
186 | connect to all additional C<$seednodes> that are specified. Seednodes are |
157 | and can be used to quickly bootstrap the node into an existing network. |
187 | optional and can be used to quickly bootstrap the node into an existing |
|
|
188 | network. |
158 | |
189 | |
159 | =item slave nodes |
190 | =item slave nodes |
160 | |
191 | |
161 | When the C<$noderef> is the special string C<slave/>, then the node will |
192 | When the C<$noderef> (either as given or overriden by the config file) |
|
|
193 | is the special string C<slave/>, then the node will become a slave |
162 | become a slave node. Slave nodes cannot be contacted from outside and will |
194 | node. Slave nodes cannot be contacted from outside and will route most of |
163 | route most of their traffic to the master node that they attach to. |
195 | their traffic to the master node that they attach to. |
164 | |
196 | |
165 | At least one additional noderef is required: The node will try to connect |
197 | At least one additional noderef is required (either by specifying it |
166 | to all of them and will become a slave attached to the first node it can |
198 | directly or because it is part of the configuration profile): The node |
167 | successfully connect to. |
199 | will try to connect to all of them and will become a slave attached to the |
|
|
200 | first node it can successfully connect to. |
|
|
201 | |
|
|
202 | Note that slave nodes cannot change their name, and consequently, their |
|
|
203 | master, so if the master goes down, the slave node will not function well |
|
|
204 | anymore until it can re-establish conenciton to its master. This makes |
|
|
205 | slave nodes unsuitable for long-term nodes or fault-tolerant networks. |
168 | |
206 | |
169 | =back |
207 | =back |
170 | |
208 | |
171 | This function will block until all nodes have been resolved and, for slave |
209 | This function will block until all nodes have been resolved and, for slave |
172 | nodes, until it has successfully established a connection to a master |
210 | nodes, until it has successfully established a connection to a master |
173 | server. |
211 | server. |
174 | |
212 | |
|
|
213 | All the seednodes will also be specially marked to automatically retry |
|
|
214 | connecting to them infinitely. |
|
|
215 | |
175 | Example: become a public node listening on the default node. |
216 | Example: become a public node listening on the guessed noderef, or the one |
|
|
217 | specified via C<aemp> for the current node. This should be the most common |
|
|
218 | form of invocation for "daemon"-type nodes. |
176 | |
219 | |
177 | initialise_node; |
220 | initialise_node; |
|
|
221 | |
|
|
222 | Example: become a slave node to any of the the seednodes specified via |
|
|
223 | C<aemp>. This form is often used for commandline clients. |
|
|
224 | |
|
|
225 | initialise_node "slave/"; |
|
|
226 | |
|
|
227 | Example: become a slave node to any of the specified master servers. This |
|
|
228 | form is also often used for commandline clients. |
|
|
229 | |
|
|
230 | initialise_node "slave/", "master1", "192.168.13.17", "mp.example.net"; |
178 | |
231 | |
179 | Example: become a public node, and try to contact some well-known master |
232 | Example: become a public node, and try to contact some well-known master |
180 | servers to become part of the network. |
233 | servers to become part of the network. |
181 | |
234 | |
182 | initialise_node undef, "master1", "master2"; |
235 | initialise_node undef, "master1", "master2"; |
… | |
… | |
185 | |
238 | |
186 | initialise_node 4041; |
239 | initialise_node 4041; |
187 | |
240 | |
188 | Example: become a public node, only visible on localhost port 4044. |
241 | Example: become a public node, only visible on localhost port 4044. |
189 | |
242 | |
190 | initialise_node "locahost:4044"; |
243 | initialise_node "localhost:4044"; |
191 | |
|
|
192 | Example: become a slave node to any of the specified master servers. |
|
|
193 | |
|
|
194 | initialise_node "slave/", "master1", "192.168.13.17", "mp.example.net"; |
|
|
195 | |
244 | |
196 | =item $cv = resolve_node $noderef |
245 | =item $cv = resolve_node $noderef |
197 | |
246 | |
198 | Takes an unresolved node reference that may contain hostnames and |
247 | Takes an unresolved node reference that may contain hostnames and |
199 | abbreviated IDs, resolves all of them and returns a resolved node |
248 | abbreviated IDs, resolves all of them and returns a resolved node |
… | |
… | |
236 | =item snd $port, type => @data |
285 | =item snd $port, type => @data |
237 | |
286 | |
238 | =item snd $port, @msg |
287 | =item snd $port, @msg |
239 | |
288 | |
240 | Send the given message to the given port ID, which can identify either |
289 | Send the given message to the given port ID, which can identify either |
241 | a local or a remote port, and can be either a string or soemthignt hat |
290 | a local or a remote port, and must be a port ID. |
242 | stringifies a sa port ID (such as a port object :). |
|
|
243 | |
291 | |
244 | While the message can be about anything, it is highly recommended to use a |
292 | While the message can be about anything, it is highly recommended to use a |
245 | string as first element (a portid, or some word that indicates a request |
293 | string as first element (a port ID, or some word that indicates a request |
246 | type etc.). |
294 | type etc.). |
247 | |
295 | |
248 | The message data effectively becomes read-only after a call to this |
296 | The message data effectively becomes read-only after a call to this |
249 | function: modifying any argument is not allowed and can cause many |
297 | function: modifying any argument is not allowed and can cause many |
250 | problems. |
298 | problems. |
… | |
… | |
255 | that Storable can serialise and deserialise is allowed, and for the local |
303 | that Storable can serialise and deserialise is allowed, and for the local |
256 | node, anything can be passed. |
304 | node, anything can be passed. |
257 | |
305 | |
258 | =item $local_port = port |
306 | =item $local_port = port |
259 | |
307 | |
260 | Create a new local port object that can be used either as a pattern |
308 | Create a new local port object and returns its port ID. Initially it has |
261 | matching port ("full port") or a single-callback port ("miniport"), |
309 | no callbacks set and will throw an error when it receives messages. |
262 | depending on how C<rcv> callbacks are bound to the object. |
|
|
263 | |
310 | |
264 | =item $port = port { my @msg = @_; $finished } |
311 | =item $local_port = port { my @msg = @_ } |
265 | |
312 | |
266 | Creates a "miniport", that is, a very lightweight port without any pattern |
313 | Creates a new local port, and returns its ID. Semantically the same as |
267 | matching behind it, and returns its ID. Semantically the same as creating |
|
|
268 | a port and calling C<rcv $port, $callback> on it. |
314 | creating a port and calling C<rcv $port, $callback> on it. |
269 | |
315 | |
270 | The block will be called for every message received on the port. When the |
316 | The block will be called for every message received on the port, with the |
271 | callback returns a true value its job is considered "done" and the port |
317 | global variable C<$SELF> set to the port ID. Runtime errors will cause the |
272 | will be destroyed. Otherwise it will stay alive. |
318 | port to be C<kil>ed. The message will be passed as-is, no extra argument |
|
|
319 | (i.e. no port ID) will be passed to the callback. |
273 | |
320 | |
274 | The message will be passed as-is, no extra argument (i.e. no port id) will |
321 | If you want to stop/destroy the port, simply C<kil> it: |
275 | be passed to the callback. |
|
|
276 | |
322 | |
277 | If you need the local port id in the callback, this works nicely: |
323 | my $port = port { |
278 | |
324 | my @msg = @_; |
279 | my $port; $port = port { |
325 | ... |
280 | snd $otherport, reply => $port; |
326 | kil $SELF; |
281 | }; |
327 | }; |
282 | |
328 | |
283 | =cut |
329 | =cut |
284 | |
330 | |
285 | sub rcv($@); |
331 | sub rcv($@); |
|
|
332 | |
|
|
333 | sub _kilme { |
|
|
334 | die "received message on port without callback"; |
|
|
335 | } |
286 | |
336 | |
287 | sub port(;&) { |
337 | sub port(;&) { |
288 | my $id = "$UNIQ." . $ID++; |
338 | my $id = "$UNIQ." . $ID++; |
289 | my $port = "$NODE#$id"; |
339 | my $port = "$NODE#$id"; |
290 | |
340 | |
291 | if (@_) { |
341 | rcv $port, shift || \&_kilme; |
292 | rcv $port, shift; |
|
|
293 | } else { |
|
|
294 | $PORT{$id} = sub { }; # nop |
|
|
295 | } |
|
|
296 | |
342 | |
297 | $port |
343 | $port |
298 | } |
344 | } |
299 | |
345 | |
300 | =item reg $port, $name |
|
|
301 | |
|
|
302 | Registers the given port under the name C<$name>. If the name already |
|
|
303 | exists it is replaced. |
|
|
304 | |
|
|
305 | A port can only be registered under one well known name. |
|
|
306 | |
|
|
307 | A port automatically becomes unregistered when it is killed. |
|
|
308 | |
|
|
309 | =cut |
|
|
310 | |
|
|
311 | sub reg(@) { |
|
|
312 | my ($port, $name) = @_; |
|
|
313 | |
|
|
314 | $REG{$name} = $port; |
|
|
315 | } |
|
|
316 | |
|
|
317 | =item rcv $port, $callback->(@msg) |
346 | =item rcv $local_port, $callback->(@msg) |
318 | |
347 | |
319 | Replaces the callback on the specified miniport (after converting it to |
348 | Replaces the default callback on the specified port. There is no way to |
320 | one if required). |
349 | remove the default callback: use C<sub { }> to disable it, or better |
321 | |
350 | C<kil> the port when it is no longer needed. |
322 | =item rcv $port, tagstring => $callback->(@msg), ... |
|
|
323 | |
|
|
324 | =item rcv $port, $smartmatch => $callback->(@msg), ... |
|
|
325 | |
|
|
326 | =item rcv $port, [$smartmatch...] => $callback->(@msg), ... |
|
|
327 | |
|
|
328 | Register callbacks to be called on matching messages on the given full |
|
|
329 | port (after converting it to one if required). |
|
|
330 | |
|
|
331 | The callback has to return a true value when its work is done, after |
|
|
332 | which is will be removed, or a false value in which case it will stay |
|
|
333 | registered. |
|
|
334 | |
351 | |
335 | The global C<$SELF> (exported by this module) contains C<$port> while |
352 | The global C<$SELF> (exported by this module) contains C<$port> while |
336 | executing the callback. |
353 | executing the callback. Runtime errors during callback execution will |
|
|
354 | result in the port being C<kil>ed. |
337 | |
355 | |
338 | Runtime errors wdurign callback execution will result in the port being |
356 | The default callback received all messages not matched by a more specific |
339 | C<kil>ed. |
357 | C<tag> match. |
340 | |
358 | |
341 | If the match is an array reference, then it will be matched against the |
359 | =item rcv $local_port, tag => $callback->(@msg_without_tag), ... |
342 | first elements of the message, otherwise only the first element is being |
|
|
343 | matched. |
|
|
344 | |
360 | |
345 | Any element in the match that is specified as C<_any_> (a function |
361 | Register (or replace) callbacks to be called on messages starting with the |
346 | exported by this module) matches any single element of the message. |
362 | given tag on the given port (and return the port), or unregister it (when |
|
|
363 | C<$callback> is C<$undef> or missing). There can only be one callback |
|
|
364 | registered for each tag. |
347 | |
365 | |
348 | While not required, it is highly recommended that the first matching |
366 | The original message will be passed to the callback, after the first |
349 | element is a string identifying the message. The one-string-only match is |
367 | element (the tag) has been removed. The callback will use the same |
350 | also the most efficient match (by far). |
368 | environment as the default callback (see above). |
|
|
369 | |
|
|
370 | Example: create a port and bind receivers on it in one go. |
|
|
371 | |
|
|
372 | my $port = rcv port, |
|
|
373 | msg1 => sub { ... }, |
|
|
374 | msg2 => sub { ... }, |
|
|
375 | ; |
|
|
376 | |
|
|
377 | Example: create a port, bind receivers and send it in a message elsewhere |
|
|
378 | in one go: |
|
|
379 | |
|
|
380 | snd $otherport, reply => |
|
|
381 | rcv port, |
|
|
382 | msg1 => sub { ... }, |
|
|
383 | ... |
|
|
384 | ; |
|
|
385 | |
|
|
386 | Example: temporarily register a rcv callback for a tag matching some port |
|
|
387 | (e.g. for a rpc reply) and unregister it after a message was received. |
|
|
388 | |
|
|
389 | rcv $port, $otherport => sub { |
|
|
390 | my @reply = @_; |
|
|
391 | |
|
|
392 | rcv $SELF, $otherport; |
|
|
393 | }; |
351 | |
394 | |
352 | =cut |
395 | =cut |
353 | |
396 | |
354 | sub rcv($@) { |
397 | sub rcv($@) { |
355 | my $port = shift; |
398 | my $port = shift; |
356 | my ($noderef, $portid) = split /#/, $port, 2; |
399 | my ($noderef, $portid) = split /#/, $port, 2; |
357 | |
400 | |
358 | ($NODE{$noderef} || add_node $noderef) == $NODE{""} |
401 | ($NODE{$noderef} || add_node $noderef) == $NODE{""} |
359 | or Carp::croak "$port: rcv can only be called on local ports, caught"; |
402 | or Carp::croak "$port: rcv can only be called on local ports, caught"; |
360 | |
403 | |
361 | if (@_ == 1) { |
404 | while (@_) { |
|
|
405 | if (ref $_[0]) { |
|
|
406 | if (my $self = $PORT_DATA{$portid}) { |
|
|
407 | "AnyEvent::MP::Port" eq ref $self |
|
|
408 | or Carp::croak "$port: rcv can only be called on message matching ports, caught"; |
|
|
409 | |
|
|
410 | $self->[2] = shift; |
|
|
411 | } else { |
362 | my $cb = shift; |
412 | my $cb = shift; |
363 | delete $PORT_DATA{$portid}; |
|
|
364 | $PORT{$portid} = sub { |
413 | $PORT{$portid} = sub { |
365 | local $SELF = $port; |
414 | local $SELF = $port; |
366 | eval { |
415 | eval { &$cb }; _self_die if $@; |
367 | &$cb |
416 | }; |
368 | and kil $port; |
|
|
369 | }; |
417 | } |
370 | _self_die if $@; |
418 | } elsif (defined $_[0]) { |
371 | }; |
|
|
372 | } else { |
|
|
373 | my $self = $PORT_DATA{$portid} ||= do { |
419 | my $self = $PORT_DATA{$portid} ||= do { |
374 | my $self = bless { |
420 | my $self = bless [$PORT{$port} || sub { }, { }, $port], "AnyEvent::MP::Port"; |
375 | id => $port, |
|
|
376 | }, "AnyEvent::MP::Port"; |
|
|
377 | |
421 | |
378 | $PORT{$portid} = sub { |
422 | $PORT{$portid} = sub { |
379 | local $SELF = $port; |
423 | local $SELF = $port; |
380 | |
424 | |
381 | eval { |
|
|
382 | for (@{ $self->{rc0}{$_[0]} }) { |
425 | if (my $cb = $self->[1]{$_[0]}) { |
383 | $_ && &{$_->[0]} |
426 | shift; |
384 | && undef $_; |
427 | eval { &$cb }; _self_die if $@; |
385 | } |
428 | } else { |
386 | |
|
|
387 | for (@{ $self->{rcv}{$_[0]} }) { |
|
|
388 | $_ && [@_[1 .. @{$_->[1]}]] ~~ $_->[1] |
|
|
389 | && &{$_->[0]} |
429 | &{ $self->[0] }; |
390 | && undef $_; |
|
|
391 | } |
|
|
392 | |
|
|
393 | for (@{ $self->{any} }) { |
|
|
394 | $_ && [@_[0 .. $#{$_->[1]}]] ~~ $_->[1] |
|
|
395 | && &{$_->[0]} |
|
|
396 | && undef $_; |
|
|
397 | } |
430 | } |
398 | }; |
431 | }; |
399 | _self_die if $@; |
432 | |
|
|
433 | $self |
400 | }; |
434 | }; |
401 | |
435 | |
402 | $self |
|
|
403 | }; |
|
|
404 | |
|
|
405 | "AnyEvent::MP::Port" eq ref $self |
436 | "AnyEvent::MP::Port" eq ref $self |
406 | or Carp::croak "$port: rcv can only be called on message matching ports, caught"; |
437 | or Carp::croak "$port: rcv can only be called on message matching ports, caught"; |
407 | |
438 | |
408 | while (@_) { |
|
|
409 | my ($match, $cb) = splice @_, 0, 2; |
439 | my ($tag, $cb) = splice @_, 0, 2; |
410 | |
440 | |
411 | if (!ref $match) { |
441 | if (defined $cb) { |
412 | push @{ $self->{rc0}{$match} }, [$cb]; |
442 | $self->[1]{$tag} = $cb; |
413 | } elsif (("ARRAY" eq ref $match && !ref $match->[0])) { |
|
|
414 | my ($type, @match) = @$match; |
|
|
415 | @match |
|
|
416 | ? push @{ $self->{rcv}{$match->[0]} }, [$cb, \@match] |
|
|
417 | : push @{ $self->{rc0}{$match->[0]} }, [$cb]; |
|
|
418 | } else { |
443 | } else { |
419 | push @{ $self->{any} }, [$cb, $match]; |
444 | delete $self->[1]{$tag}; |
420 | } |
445 | } |
421 | } |
446 | } |
422 | } |
447 | } |
423 | |
448 | |
424 | $port |
449 | $port |
… | |
… | |
462 | } |
487 | } |
463 | } |
488 | } |
464 | |
489 | |
465 | =item $guard = mon $port, $cb->(@reason) |
490 | =item $guard = mon $port, $cb->(@reason) |
466 | |
491 | |
467 | =item $guard = mon $port, $otherport |
492 | =item $guard = mon $port, $rcvport |
468 | |
493 | |
|
|
494 | =item $guard = mon $port |
|
|
495 | |
469 | =item $guard = mon $port, $otherport, @msg |
496 | =item $guard = mon $port, $rcvport, @msg |
470 | |
497 | |
471 | Monitor the given port and do something when the port is killed. |
498 | Monitor the given port and do something when the port is killed or |
|
|
499 | messages to it were lost, and optionally return a guard that can be used |
|
|
500 | to stop monitoring again. |
472 | |
501 | |
|
|
502 | C<mon> effectively guarantees that, in the absence of hardware failures, |
|
|
503 | that after starting the monitor, either all messages sent to the port |
|
|
504 | will arrive, or the monitoring action will be invoked after possible |
|
|
505 | message loss has been detected. No messages will be lost "in between" |
|
|
506 | (after the first lost message no further messages will be received by the |
|
|
507 | port). After the monitoring action was invoked, further messages might get |
|
|
508 | delivered again. |
|
|
509 | |
473 | In the first form, the callback is simply called with any number |
510 | In the first form (callback), the callback is simply called with any |
474 | of C<@reason> elements (no @reason means that the port was deleted |
511 | number of C<@reason> elements (no @reason means that the port was deleted |
475 | "normally"). Note also that I<< the callback B<must> never die >>, so use |
512 | "normally"). Note also that I<< the callback B<must> never die >>, so use |
476 | C<eval> if unsure. |
513 | C<eval> if unsure. |
477 | |
514 | |
478 | In the second form, the other port will be C<kil>'ed with C<@reason>, iff |
515 | In the second form (another port given), the other port (C<$rcvport>) |
479 | a @reason was specified, i.e. on "normal" kils nothing happens, while |
516 | will be C<kil>'ed with C<@reason>, iff a @reason was specified, i.e. on |
480 | under all other conditions, the other port is killed with the same reason. |
517 | "normal" kils nothing happens, while under all other conditions, the other |
|
|
518 | port is killed with the same reason. |
481 | |
519 | |
|
|
520 | The third form (kill self) is the same as the second form, except that |
|
|
521 | C<$rvport> defaults to C<$SELF>. |
|
|
522 | |
482 | In the last form, a message of the form C<@msg, @reason> will be C<snd>. |
523 | In the last form (message), a message of the form C<@msg, @reason> will be |
|
|
524 | C<snd>. |
|
|
525 | |
|
|
526 | As a rule of thumb, monitoring requests should always monitor a port from |
|
|
527 | a local port (or callback). The reason is that kill messages might get |
|
|
528 | lost, just like any other message. Another less obvious reason is that |
|
|
529 | even monitoring requests can get lost (for exmaple, when the connection |
|
|
530 | to the other node goes down permanently). When monitoring a port locally |
|
|
531 | these problems do not exist. |
483 | |
532 | |
484 | Example: call a given callback when C<$port> is killed. |
533 | Example: call a given callback when C<$port> is killed. |
485 | |
534 | |
486 | mon $port, sub { warn "port died because of <@_>\n" }; |
535 | mon $port, sub { warn "port died because of <@_>\n" }; |
487 | |
536 | |
488 | Example: kill ourselves when C<$port> is killed abnormally. |
537 | Example: kill ourselves when C<$port> is killed abnormally. |
489 | |
538 | |
490 | mon $port, $self; |
539 | mon $port; |
491 | |
540 | |
492 | Example: send us a restart message another C<$port> is killed. |
541 | Example: send us a restart message when another C<$port> is killed. |
493 | |
542 | |
494 | mon $port, $self => "restart"; |
543 | mon $port, $self => "restart"; |
495 | |
544 | |
496 | =cut |
545 | =cut |
497 | |
546 | |
498 | sub mon { |
547 | sub mon { |
499 | my ($noderef, $port) = split /#/, shift, 2; |
548 | my ($noderef, $port) = split /#/, shift, 2; |
500 | |
549 | |
501 | my $node = $NODE{$noderef} || add_node $noderef; |
550 | my $node = $NODE{$noderef} || add_node $noderef; |
502 | |
551 | |
503 | my $cb = shift; |
552 | my $cb = @_ ? shift : $SELF || Carp::croak 'mon: called with one argument only, but $SELF not set,'; |
504 | |
553 | |
505 | unless (ref $cb) { |
554 | unless (ref $cb) { |
506 | if (@_) { |
555 | if (@_) { |
507 | # send a kill info message |
556 | # send a kill info message |
508 | my (@msg) = ($cb, @_); |
557 | my (@msg) = ($cb, @_); |
… | |
… | |
539 | =cut |
588 | =cut |
540 | |
589 | |
541 | sub mon_guard { |
590 | sub mon_guard { |
542 | my ($port, @refs) = @_; |
591 | my ($port, @refs) = @_; |
543 | |
592 | |
|
|
593 | #TODO: mon-less form? |
|
|
594 | |
544 | mon $port, sub { 0 && @refs } |
595 | mon $port, sub { 0 && @refs } |
545 | } |
596 | } |
546 | |
597 | |
547 | =item lnk $port1, $port2 |
|
|
548 | |
|
|
549 | Link two ports. This is simply a shorthand for: |
|
|
550 | |
|
|
551 | mon $port1, $port2; |
|
|
552 | mon $port2, $port1; |
|
|
553 | |
|
|
554 | It means that if either one is killed abnormally, the other one gets |
|
|
555 | killed as well. |
|
|
556 | |
|
|
557 | =item kil $port[, @reason] |
598 | =item kil $port[, @reason] |
558 | |
599 | |
559 | Kill the specified port with the given C<@reason>. |
600 | Kill the specified port with the given C<@reason>. |
560 | |
601 | |
561 | If no C<@reason> is specified, then the port is killed "normally" (linked |
602 | If no C<@reason> is specified, then the port is killed "normally" (linked |
… | |
… | |
567 | Runtime errors while evaluating C<rcv> callbacks or inside C<psub> blocks |
608 | Runtime errors while evaluating C<rcv> callbacks or inside C<psub> blocks |
568 | will be reported as reason C<< die => $@ >>. |
609 | will be reported as reason C<< die => $@ >>. |
569 | |
610 | |
570 | Transport/communication errors are reported as C<< transport_error => |
611 | Transport/communication errors are reported as C<< transport_error => |
571 | $message >>. |
612 | $message >>. |
|
|
613 | |
|
|
614 | =cut |
|
|
615 | |
|
|
616 | =item $port = spawn $node, $initfunc[, @initdata] |
|
|
617 | |
|
|
618 | Creates a port on the node C<$node> (which can also be a port ID, in which |
|
|
619 | case it's the node where that port resides). |
|
|
620 | |
|
|
621 | The port ID of the newly created port is return immediately, and it is |
|
|
622 | permissible to immediately start sending messages or monitor the port. |
|
|
623 | |
|
|
624 | After the port has been created, the init function is |
|
|
625 | called. This function must be a fully-qualified function name |
|
|
626 | (e.g. C<MyApp::Chat::Server::init>). To specify a function in the main |
|
|
627 | program, use C<::name>. |
|
|
628 | |
|
|
629 | If the function doesn't exist, then the node tries to C<require> |
|
|
630 | the package, then the package above the package and so on (e.g. |
|
|
631 | C<MyApp::Chat::Server>, C<MyApp::Chat>, C<MyApp>) until the function |
|
|
632 | exists or it runs out of package names. |
|
|
633 | |
|
|
634 | The init function is then called with the newly-created port as context |
|
|
635 | object (C<$SELF>) and the C<@initdata> values as arguments. |
|
|
636 | |
|
|
637 | A common idiom is to pass your own port, monitor the spawned port, and |
|
|
638 | in the init function, monitor the original port. This two-way monitoring |
|
|
639 | ensures that both ports get cleaned up when there is a problem. |
|
|
640 | |
|
|
641 | Example: spawn a chat server port on C<$othernode>. |
|
|
642 | |
|
|
643 | # this node, executed from within a port context: |
|
|
644 | my $server = spawn $othernode, "MyApp::Chat::Server::connect", $SELF; |
|
|
645 | mon $server; |
|
|
646 | |
|
|
647 | # init function on C<$othernode> |
|
|
648 | sub connect { |
|
|
649 | my ($srcport) = @_; |
|
|
650 | |
|
|
651 | mon $srcport; |
|
|
652 | |
|
|
653 | rcv $SELF, sub { |
|
|
654 | ... |
|
|
655 | }; |
|
|
656 | } |
|
|
657 | |
|
|
658 | =cut |
|
|
659 | |
|
|
660 | sub _spawn { |
|
|
661 | my $port = shift; |
|
|
662 | my $init = shift; |
|
|
663 | |
|
|
664 | local $SELF = "$NODE#$port"; |
|
|
665 | eval { |
|
|
666 | &{ load_func $init } |
|
|
667 | }; |
|
|
668 | _self_die if $@; |
|
|
669 | } |
|
|
670 | |
|
|
671 | sub spawn(@) { |
|
|
672 | my ($noderef, undef) = split /#/, shift, 2; |
|
|
673 | |
|
|
674 | my $id = "$RUNIQ." . $ID++; |
|
|
675 | |
|
|
676 | $_[0] =~ /::/ |
|
|
677 | or Carp::croak "spawn init function must be a fully-qualified name, caught"; |
|
|
678 | |
|
|
679 | snd_to_func $noderef, "AnyEvent::MP::_spawn" => $id, @_; |
|
|
680 | |
|
|
681 | "$noderef#$id" |
|
|
682 | } |
572 | |
683 | |
573 | =back |
684 | =back |
574 | |
685 | |
575 | =head1 NODE MESSAGES |
686 | =head1 NODE MESSAGES |
576 | |
687 | |
… | |
… | |
618 | |
729 | |
619 | =back |
730 | =back |
620 | |
731 | |
621 | =head1 AnyEvent::MP vs. Distributed Erlang |
732 | =head1 AnyEvent::MP vs. Distributed Erlang |
622 | |
733 | |
623 | AnyEvent::MP got lots of its ideas from distributed erlang (erlang node |
734 | AnyEvent::MP got lots of its ideas from distributed Erlang (Erlang node |
624 | == aemp node, erlang process == aemp port), so many of the documents and |
735 | == aemp node, Erlang process == aemp port), so many of the documents and |
625 | programming techniques employed by erlang apply to AnyEvent::MP. Here is a |
736 | programming techniques employed by Erlang apply to AnyEvent::MP. Here is a |
626 | sample: |
737 | sample: |
627 | |
738 | |
628 | http://www.erlang.se/doc/programming_rules.shtml |
739 | http://www.Erlang.se/doc/programming_rules.shtml |
629 | http://erlang.org/doc/getting_started/part_frame.html # chapters 3 and 4 |
740 | http://Erlang.org/doc/getting_started/part_frame.html # chapters 3 and 4 |
630 | http://erlang.org/download/erlang-book-part1.pdf # chapters 5 and 6 |
741 | http://Erlang.org/download/Erlang-book-part1.pdf # chapters 5 and 6 |
631 | http://erlang.org/download/armstrong_thesis_2003.pdf # chapters 4 and 5 |
742 | http://Erlang.org/download/armstrong_thesis_2003.pdf # chapters 4 and 5 |
632 | |
743 | |
633 | Despite the similarities, there are also some important differences: |
744 | Despite the similarities, there are also some important differences: |
634 | |
745 | |
635 | =over 4 |
746 | =over 4 |
636 | |
747 | |
… | |
… | |
641 | convenience functionality. |
752 | convenience functionality. |
642 | |
753 | |
643 | This means that AEMP requires a less tightly controlled environment at the |
754 | This means that AEMP requires a less tightly controlled environment at the |
644 | cost of longer node references and a slightly higher management overhead. |
755 | cost of longer node references and a slightly higher management overhead. |
645 | |
756 | |
|
|
757 | =item * Erlang has a "remote ports are like local ports" philosophy, AEMP |
|
|
758 | uses "local ports are like remote ports". |
|
|
759 | |
|
|
760 | The failure modes for local ports are quite different (runtime errors |
|
|
761 | only) then for remote ports - when a local port dies, you I<know> it dies, |
|
|
762 | when a connection to another node dies, you know nothing about the other |
|
|
763 | port. |
|
|
764 | |
|
|
765 | Erlang pretends remote ports are as reliable as local ports, even when |
|
|
766 | they are not. |
|
|
767 | |
|
|
768 | AEMP encourages a "treat remote ports differently" philosophy, with local |
|
|
769 | ports being the special case/exception, where transport errors cannot |
|
|
770 | occur. |
|
|
771 | |
646 | =item * Erlang uses processes and a mailbox, AEMP does not queue. |
772 | =item * Erlang uses processes and a mailbox, AEMP does not queue. |
647 | |
773 | |
648 | Erlang uses processes that selctively receive messages, and therefore |
774 | Erlang uses processes that selectively receive messages, and therefore |
649 | needs a queue. AEMP is event based, queuing messages would serve no useful |
775 | needs a queue. AEMP is event based, queuing messages would serve no |
650 | purpose. |
776 | useful purpose. For the same reason the pattern-matching abilities of |
|
|
777 | AnyEvent::MP are more limited, as there is little need to be able to |
|
|
778 | filter messages without dequeing them. |
651 | |
779 | |
652 | (But see L<Coro::MP> for a more erlang-like process model on top of AEMP). |
780 | (But see L<Coro::MP> for a more Erlang-like process model on top of AEMP). |
653 | |
781 | |
654 | =item * Erlang sends are synchronous, AEMP sends are asynchronous. |
782 | =item * Erlang sends are synchronous, AEMP sends are asynchronous. |
655 | |
783 | |
656 | Sending messages in erlang is synchronous and blocks the process. AEMP |
784 | Sending messages in Erlang is synchronous and blocks the process (and |
657 | sends are immediate, connection establishment is handled in the |
785 | so does not need a queue that can overflow). AEMP sends are immediate, |
658 | background. |
786 | connection establishment is handled in the background. |
659 | |
787 | |
660 | =item * Erlang can silently lose messages, AEMP cannot. |
788 | =item * Erlang suffers from silent message loss, AEMP does not. |
661 | |
789 | |
662 | Erlang makes few guarantees on messages delivery - messages can get lost |
790 | Erlang makes few guarantees on messages delivery - messages can get lost |
663 | without any of the processes realising it (i.e. you send messages a, b, |
791 | without any of the processes realising it (i.e. you send messages a, b, |
664 | and c, and the other side only receives messages a and c). |
792 | and c, and the other side only receives messages a and c). |
665 | |
793 | |
666 | AEMP guarantees correct ordering, and the guarantee that there are no |
794 | AEMP guarantees correct ordering, and the guarantee that there are no |
667 | holes in the message sequence. |
795 | holes in the message sequence. |
668 | |
796 | |
669 | =item * In erlang, processes can be declared dead and later be found to be |
797 | =item * In Erlang, processes can be declared dead and later be found to be |
670 | alive. |
798 | alive. |
671 | |
799 | |
672 | In erlang it can happen that a monitored process is declared dead and |
800 | In Erlang it can happen that a monitored process is declared dead and |
673 | linked processes get killed, but later it turns out that the process is |
801 | linked processes get killed, but later it turns out that the process is |
674 | still alive - and can receive messages. |
802 | still alive - and can receive messages. |
675 | |
803 | |
676 | In AEMP, when port monitoring detects a port as dead, then that port will |
804 | In AEMP, when port monitoring detects a port as dead, then that port will |
677 | eventually be killed - it cannot happen that a node detects a port as dead |
805 | eventually be killed - it cannot happen that a node detects a port as dead |
678 | and then later sends messages to it, finding it is still alive. |
806 | and then later sends messages to it, finding it is still alive. |
679 | |
807 | |
680 | =item * Erlang can send messages to the wrong port, AEMP does not. |
808 | =item * Erlang can send messages to the wrong port, AEMP does not. |
681 | |
809 | |
682 | In erlang it is quite possible that a node that restarts reuses a process |
810 | In Erlang it is quite likely that a node that restarts reuses a process ID |
683 | ID known to other nodes for a completely different process, causing |
811 | known to other nodes for a completely different process, causing messages |
684 | messages destined for that process to end up in an unrelated process. |
812 | destined for that process to end up in an unrelated process. |
685 | |
813 | |
686 | AEMP never reuses port IDs, so old messages or old port IDs floating |
814 | AEMP never reuses port IDs, so old messages or old port IDs floating |
687 | around in the network will not be sent to an unrelated port. |
815 | around in the network will not be sent to an unrelated port. |
688 | |
816 | |
689 | =item * Erlang uses unprotected connections, AEMP uses secure |
817 | =item * Erlang uses unprotected connections, AEMP uses secure |
… | |
… | |
693 | securely authenticate nodes. |
821 | securely authenticate nodes. |
694 | |
822 | |
695 | =item * The AEMP protocol is optimised for both text-based and binary |
823 | =item * The AEMP protocol is optimised for both text-based and binary |
696 | communications. |
824 | communications. |
697 | |
825 | |
698 | The AEMP protocol, unlike the erlang protocol, supports both |
826 | The AEMP protocol, unlike the Erlang protocol, supports both |
699 | language-independent text-only protocols (good for debugging) and binary, |
827 | language-independent text-only protocols (good for debugging) and binary, |
700 | language-specific serialisers (e.g. Storable). |
828 | language-specific serialisers (e.g. Storable). |
701 | |
829 | |
702 | It has also been carefully designed to be implementable in other languages |
830 | It has also been carefully designed to be implementable in other languages |
703 | with a minimum of work while gracefully degrading fucntionality to make the |
831 | with a minimum of work while gracefully degrading fucntionality to make the |
704 | protocol simple. |
832 | protocol simple. |
705 | |
833 | |
|
|
834 | =item * AEMP has more flexible monitoring options than Erlang. |
|
|
835 | |
|
|
836 | In Erlang, you can chose to receive I<all> exit signals as messages |
|
|
837 | or I<none>, there is no in-between, so monitoring single processes is |
|
|
838 | difficult to implement. Monitoring in AEMP is more flexible than in |
|
|
839 | Erlang, as one can choose between automatic kill, exit message or callback |
|
|
840 | on a per-process basis. |
|
|
841 | |
|
|
842 | =item * Erlang tries to hide remote/local connections, AEMP does not. |
|
|
843 | |
|
|
844 | Monitoring in Erlang is not an indicator of process death/crashes, |
|
|
845 | as linking is (except linking is unreliable in Erlang). |
|
|
846 | |
|
|
847 | In AEMP, you don't "look up" registered port names or send to named ports |
|
|
848 | that might or might not be persistent. Instead, you normally spawn a port |
|
|
849 | on the remote node. The init function monitors the you, and you monitor |
|
|
850 | the remote port. Since both monitors are local to the node, they are much |
|
|
851 | more reliable. |
|
|
852 | |
|
|
853 | This also saves round-trips and avoids sending messages to the wrong port |
|
|
854 | (hard to do in Erlang). |
|
|
855 | |
|
|
856 | =back |
|
|
857 | |
|
|
858 | =head1 RATIONALE |
|
|
859 | |
|
|
860 | =over 4 |
|
|
861 | |
|
|
862 | =item Why strings for ports and noderefs, why not objects? |
|
|
863 | |
|
|
864 | We considered "objects", but found that the actual number of methods |
|
|
865 | thatc an be called are very low. Since port IDs and noderefs travel over |
|
|
866 | the network frequently, the serialising/deserialising would add lots of |
|
|
867 | overhead, as well as having to keep a proxy object. |
|
|
868 | |
|
|
869 | Strings can easily be printed, easily serialised etc. and need no special |
|
|
870 | procedures to be "valid". |
|
|
871 | |
|
|
872 | And a a miniport consists of a single closure stored in a global hash - it |
|
|
873 | can't become much cheaper. |
|
|
874 | |
|
|
875 | =item Why favour JSON, why not real serialising format such as Storable? |
|
|
876 | |
|
|
877 | In fact, any AnyEvent::MP node will happily accept Storable as framing |
|
|
878 | format, but currently there is no way to make a node use Storable by |
|
|
879 | default. |
|
|
880 | |
|
|
881 | The default framing protocol is JSON because a) JSON::XS is many times |
|
|
882 | faster for small messages and b) most importantly, after years of |
|
|
883 | experience we found that object serialisation is causing more problems |
|
|
884 | than it gains: Just like function calls, objects simply do not travel |
|
|
885 | easily over the network, mostly because they will always be a copy, so you |
|
|
886 | always have to re-think your design. |
|
|
887 | |
|
|
888 | Keeping your messages simple, concentrating on data structures rather than |
|
|
889 | objects, will keep your messages clean, tidy and efficient. |
|
|
890 | |
706 | =back |
891 | =back |
707 | |
892 | |
708 | =head1 SEE ALSO |
893 | =head1 SEE ALSO |
709 | |
894 | |
710 | L<AnyEvent>. |
895 | L<AnyEvent>. |