… | |
… | |
4 | |
4 | |
5 | =head1 SYNOPSIS |
5 | =head1 SYNOPSIS |
6 | |
6 | |
7 | use AnyEvent::MP; |
7 | use AnyEvent::MP; |
8 | |
8 | |
9 | NODE # returns this node identifier |
|
|
10 | $NODE # contains this node identifier |
9 | $NODE # contains this node's noderef |
|
|
10 | NODE # returns this node's noderef |
|
|
11 | NODE $port # returns the noderef of the port |
11 | |
12 | |
|
|
13 | $SELF # receiving/own port id in rcv callbacks |
|
|
14 | |
|
|
15 | # initialise the node so it can send/receive messages |
|
|
16 | initialise_node; |
|
|
17 | |
|
|
18 | # ports are message endpoints |
|
|
19 | |
|
|
20 | # sending messages |
12 | snd $port, type => data...; |
21 | snd $port, type => data...; |
|
|
22 | snd $port, @msg; |
|
|
23 | snd @msg_with_first_element_being_a_port; |
13 | |
24 | |
14 | rcv $port, smartmatch => $cb->($port, @msg); |
25 | # creating/using ports, the simple way |
|
|
26 | my $simple_port = port { my @msg = @_; 0 }; |
15 | |
27 | |
16 | # examples: |
28 | # creating/using ports, tagged message matching |
|
|
29 | my $port = port; |
17 | rcv $port2, ping => sub { snd $_[0], "pong"; 0 }; |
30 | rcv $port, ping => sub { snd $_[0], "pong"; 0 }; |
18 | rcv $port1, pong => sub { warn "pong received\n" }; |
31 | rcv $port, pong => sub { warn "pong received\n"; 0 }; |
19 | snd $port2, ping => $port1; |
|
|
20 | |
32 | |
21 | # more, smarter, matches (_any_ is exported by this module) |
33 | # create a port on another node |
22 | rcv $port, [child_died => $pid] => sub { ... |
34 | my $port = spawn $node, $initfunc, @initdata; |
23 | rcv $port, [_any_, _any_, 3] => sub { .. $_[2] is 3 |
35 | |
|
|
36 | # monitoring |
|
|
37 | mon $port, $cb->(@msg) # callback is invoked on death |
|
|
38 | mon $port, $otherport # kill otherport on abnormal death |
|
|
39 | mon $port, $otherport, @msg # send message on death |
|
|
40 | |
|
|
41 | =head1 CURRENT STATUS |
|
|
42 | |
|
|
43 | AnyEvent::MP - stable API, should work |
|
|
44 | AnyEvent::MP::Intro - outdated |
|
|
45 | AnyEvent::MP::Kernel - mostly stable |
|
|
46 | AnyEvent::MP::Global - mostly stable |
|
|
47 | AnyEvent::MP::Node - mostly stable, but internal anyways |
|
|
48 | AnyEvent::MP::Transport - mostly stable, but internal anyways |
|
|
49 | |
|
|
50 | stay tuned. |
24 | |
51 | |
25 | =head1 DESCRIPTION |
52 | =head1 DESCRIPTION |
26 | |
53 | |
27 | This module (-family) implements a simple message passing framework. |
54 | This module (-family) implements a simple message passing framework. |
28 | |
55 | |
29 | Despite its simplicity, you can securely message other processes running |
56 | Despite its simplicity, you can securely message other processes running |
30 | on the same or other hosts. |
57 | on the same or other hosts, and you can supervise entities remotely. |
31 | |
58 | |
|
|
59 | For an introduction to this module family, see the L<AnyEvent::MP::Intro> |
|
|
60 | manual page and the examples under F<eg/>. |
|
|
61 | |
32 | At the moment, this module family is severly brokena nd underdocumented, |
62 | At the moment, this module family is a bit underdocumented. |
33 | so do not use. This was uploaded mainly to resreve the CPAN namespace - |
|
|
34 | stay tuned! |
|
|
35 | |
63 | |
36 | =head1 CONCEPTS |
64 | =head1 CONCEPTS |
37 | |
65 | |
38 | =over 4 |
66 | =over 4 |
39 | |
67 | |
40 | =item port |
68 | =item port |
41 | |
69 | |
42 | A port is something you can send messages to with the C<snd> function, and |
70 | A port is something you can send messages to (with the C<snd> function). |
43 | you can register C<rcv> handlers with. All C<rcv> handlers will receive |
|
|
44 | messages they match, messages will not be queued. |
|
|
45 | |
71 | |
|
|
72 | Ports allow you to register C<rcv> handlers that can match all or just |
|
|
73 | some messages. Messages send to ports will not be queued, regardless of |
|
|
74 | anything was listening for them or not. |
|
|
75 | |
46 | =item port id - C<noderef#portname> |
76 | =item port ID - C<nodeid#portname> |
47 | |
77 | |
48 | A port id is always the noderef, a hash-mark (C<#>) as separator, followed |
78 | A port ID is the concatenation of a node ID, a hash-mark (C<#>) as |
49 | by a port name (a printable string of unspecified format). |
79 | separator, and a port name (a printable string of unspecified format). |
50 | |
80 | |
51 | =item node |
81 | =item node |
52 | |
82 | |
53 | A node is a single process containing at least one port - the node |
83 | A node is a single process containing at least one port - the node port, |
54 | port. You can send messages to node ports to let them create new ports, |
84 | which enables nodes to manage each other remotely, and to create new |
55 | among other things. |
85 | ports. |
56 | |
86 | |
57 | Initially, nodes are either private (single-process only) or hidden |
87 | Nodes are either public (have one or more listening ports) or private |
58 | (connected to a master node only). Only when they epxlicitly "become |
88 | (no listening ports). Private nodes cannot talk to other private nodes |
59 | public" can you send them messages from unrelated other nodes. |
89 | currently. |
60 | |
90 | |
61 | =item noderef - C<host:port,host:port...>, C<id@noderef>, C<id> |
91 | =item node ID - C<[a-za-Z0-9_\-.:]+> |
62 | |
92 | |
63 | A noderef is a string that either uniquely identifies a given node (for |
93 | A node ID is a string that uniquely identifies the node within a |
64 | private and hidden nodes), or contains a recipe on how to reach a given |
94 | network. Depending on the configuration used, node IDs can look like a |
65 | node (for public nodes). |
95 | hostname, a hostname and a port, or a random string. AnyEvent::MP itself |
|
|
96 | doesn't interpret node IDs in any way. |
|
|
97 | |
|
|
98 | =item binds - C<ip:port> |
|
|
99 | |
|
|
100 | Nodes can only talk to each other by creating some kind of connection to |
|
|
101 | each other. To do this, nodes should listen on one or more local transport |
|
|
102 | endpoints - binds. Currently, only standard C<ip:port> specifications can |
|
|
103 | be used, which specify TCP ports to listen on. |
|
|
104 | |
|
|
105 | =item seeds - C<host:port> |
|
|
106 | |
|
|
107 | When a node starts, it knows nothing about the network. To teach the node |
|
|
108 | about the network it first has to contact some other node within the |
|
|
109 | network. This node is called a seed. |
|
|
110 | |
|
|
111 | Seeds are transport endpoint(s) of as many nodes as one wants. Those nodes |
|
|
112 | are expected to be long-running, and at least one of those should always |
|
|
113 | be available. When nodes run out of connections (e.g. due to a network |
|
|
114 | error), they try to re-establish connections to some seednodes again to |
|
|
115 | join the network. |
|
|
116 | |
|
|
117 | Apart from being sued for seeding, seednodes are not special in any way - |
|
|
118 | every public node can be a seednode. |
66 | |
119 | |
67 | =back |
120 | =back |
68 | |
121 | |
69 | =head1 VARIABLES/FUNCTIONS |
122 | =head1 VARIABLES/FUNCTIONS |
70 | |
123 | |
… | |
… | |
72 | |
125 | |
73 | =cut |
126 | =cut |
74 | |
127 | |
75 | package AnyEvent::MP; |
128 | package AnyEvent::MP; |
76 | |
129 | |
77 | use AnyEvent::MP::Base; |
130 | use AnyEvent::MP::Kernel; |
78 | |
131 | |
79 | use common::sense; |
132 | use common::sense; |
80 | |
133 | |
81 | use Carp (); |
134 | use Carp (); |
82 | |
135 | |
83 | use AE (); |
136 | use AE (); |
84 | |
137 | |
85 | use base "Exporter"; |
138 | use base "Exporter"; |
86 | |
139 | |
87 | our $VERSION = '0.02'; |
140 | our $VERSION = $AnyEvent::MP::Kernel::VERSION; |
|
|
141 | |
88 | our @EXPORT = qw( |
142 | our @EXPORT = qw( |
89 | NODE $NODE $PORT snd rcv _any_ |
143 | NODE $NODE *SELF node_of after |
90 | create_port create_port_on |
144 | initialise_node |
91 | become_slave become_public |
145 | snd rcv mon mon_guard kil reg psub spawn |
|
|
146 | port |
92 | ); |
147 | ); |
93 | |
148 | |
|
|
149 | our $SELF; |
|
|
150 | |
|
|
151 | sub _self_die() { |
|
|
152 | my $msg = $@; |
|
|
153 | $msg =~ s/\n+$// unless ref $msg; |
|
|
154 | kil $SELF, die => $msg; |
|
|
155 | } |
|
|
156 | |
94 | =item NODE / $NODE |
157 | =item $thisnode = NODE / $NODE |
95 | |
158 | |
96 | The C<NODE ()> function and the C<$NODE> variable contain the noderef of |
159 | The C<NODE> function returns, and the C<$NODE> variable contains, the node |
97 | the local node. The value is initialised by a call to C<become_public> or |
160 | ID of the node running in the current process. This value is initialised by |
98 | C<become_slave>, after which all local port identifiers become invalid. |
161 | a call to C<initialise_node>. |
99 | |
162 | |
|
|
163 | =item $nodeid = node_of $port |
|
|
164 | |
|
|
165 | Extracts and returns the node ID from a port ID or a node ID. |
|
|
166 | |
|
|
167 | =item initialise_node $profile_name, key => value... |
|
|
168 | |
|
|
169 | Before a node can talk to other nodes on the network (i.e. enter |
|
|
170 | "distributed mode") it has to initialise itself - the minimum a node needs |
|
|
171 | to know is its own name, and optionally it should know the addresses of |
|
|
172 | some other nodes in the network to discover other nodes. |
|
|
173 | |
|
|
174 | This function initialises a node - it must be called exactly once (or |
|
|
175 | never) before calling other AnyEvent::MP functions. |
|
|
176 | |
|
|
177 | The first argument is a profile name. If it is C<undef> or missing, then |
|
|
178 | the current nodename will be used instead (i.e. F<uname -n>). |
|
|
179 | |
|
|
180 | The function first looks up the profile in the aemp configuration (see the |
|
|
181 | L<aemp> commandline utility). the profile is calculated as follows: |
|
|
182 | |
|
|
183 | First, all remaining key => value pairs (all of which are conviniently |
|
|
184 | undocumented at the moment) will be used. Then they will be overwritten by |
|
|
185 | any values specified in the global default configuration (see the F<aemp> |
|
|
186 | utility), then the chain of profiles selected, if any. That means that |
|
|
187 | the values specified in the profile have highest priority and the values |
|
|
188 | specified via C<initialise_node> have lowest priority. |
|
|
189 | |
|
|
190 | If the profile specifies a node ID, then this will become the node ID of |
|
|
191 | this process. If not, then the profile name will be used as node ID. The |
|
|
192 | special node ID of C<anon/> will be replaced by a random node ID. |
|
|
193 | |
|
|
194 | The next step is to look up the binds in the profile, followed by binding |
|
|
195 | aemp protocol listeners on all binds specified (it is possible and valid |
|
|
196 | to have no binds, meaning that the node cannot be contacted form the |
|
|
197 | outside. This means the node cannot talk to other nodes that also have no |
|
|
198 | binds, but it can still talk to all "normal" nodes). |
|
|
199 | |
|
|
200 | If the profile does not specify a binds list, then a default of C<*> is |
|
|
201 | used. |
|
|
202 | |
|
|
203 | Lastly, the seeds list from the profile is passed to the |
|
|
204 | L<AnyEvent::MP::Global> module, which will then use it to keep |
|
|
205 | connectivity with at least on of those seed nodes at any point in time. |
|
|
206 | |
|
|
207 | Example: become a distributed node listening on the guessed noderef, or |
|
|
208 | the one specified via C<aemp> for the current node. This should be the |
|
|
209 | most common form of invocation for "daemon"-type nodes. |
|
|
210 | |
|
|
211 | initialise_node; |
|
|
212 | |
|
|
213 | Example: become an anonymous node. This form is often used for commandline |
|
|
214 | clients. |
|
|
215 | |
|
|
216 | initialise_node "anon/"; |
|
|
217 | |
|
|
218 | Example: become a distributed node. If there is no profile of the given |
|
|
219 | name, or no binds list was specified, resolve C<localhost:4044> and bind |
|
|
220 | on the resulting addresses. |
|
|
221 | |
|
|
222 | initialise_node "localhost:4044"; |
|
|
223 | |
|
|
224 | =item $SELF |
|
|
225 | |
|
|
226 | Contains the current port id while executing C<rcv> callbacks or C<psub> |
|
|
227 | blocks. |
|
|
228 | |
|
|
229 | =item *SELF, SELF, %SELF, @SELF... |
|
|
230 | |
|
|
231 | Due to some quirks in how perl exports variables, it is impossible to |
|
|
232 | just export C<$SELF>, all the symbols named C<SELF> are exported by this |
|
|
233 | module, but only C<$SELF> is currently used. |
|
|
234 | |
100 | =item snd $portid, type => @data |
235 | =item snd $port, type => @data |
101 | |
236 | |
102 | =item snd $portid, @msg |
237 | =item snd $port, @msg |
103 | |
238 | |
104 | Send the given message to the given port ID, which can identify either |
239 | Send the given message to the given port, which can identify either a |
105 | a local or a remote port, and can be either a string or soemthignt hat |
240 | local or a remote port, and must be a port ID. |
106 | stringifies a sa port ID (such as a port object :). |
|
|
107 | |
241 | |
108 | While the message can be about anything, it is highly recommended to use a |
242 | While the message can be almost anything, it is highly recommended to |
109 | string as first element (a portid, or some word that indicates a request |
243 | use a string as first element (a port ID, or some word that indicates a |
110 | type etc.). |
244 | request type etc.) and to consist if only simple perl values (scalars, |
|
|
245 | arrays, hashes) - if you think you need to pass an object, think again. |
111 | |
246 | |
112 | The message data effectively becomes read-only after a call to this |
247 | The message data logically becomes read-only after a call to this |
113 | function: modifying any argument is not allowed and can cause many |
248 | function: modifying any argument (or values referenced by them) is |
114 | problems. |
249 | forbidden, as there can be considerable time between the call to C<snd> |
|
|
250 | and the time the message is actually being serialised - in fact, it might |
|
|
251 | never be copied as within the same process it is simply handed to the |
|
|
252 | receiving port. |
115 | |
253 | |
116 | The type of data you can transfer depends on the transport protocol: when |
254 | The type of data you can transfer depends on the transport protocol: when |
117 | JSON is used, then only strings, numbers and arrays and hashes consisting |
255 | JSON is used, then only strings, numbers and arrays and hashes consisting |
118 | of those are allowed (no objects). When Storable is used, then anything |
256 | of those are allowed (no objects). When Storable is used, then anything |
119 | that Storable can serialise and deserialise is allowed, and for the local |
257 | that Storable can serialise and deserialise is allowed, and for the local |
120 | node, anything can be passed. |
258 | node, anything can be passed. Best rely only on the common denominator of |
|
|
259 | these. |
121 | |
260 | |
122 | =item $local_port = create_port |
261 | =item $local_port = port |
123 | |
262 | |
124 | Create a new local port object. See the next section for allowed methods. |
263 | Create a new local port object and returns its port ID. Initially it has |
|
|
264 | no callbacks set and will throw an error when it receives messages. |
125 | |
265 | |
126 | =cut |
266 | =item $local_port = port { my @msg = @_ } |
127 | |
267 | |
128 | sub create_port { |
268 | Creates a new local port, and returns its ID. Semantically the same as |
129 | my $id = "$AnyEvent::MP::Base::UNIQ." . ++$AnyEvent::MP::Base::ID; |
269 | creating a port and calling C<rcv $port, $callback> on it. |
130 | |
270 | |
131 | my $self = bless { |
271 | The block will be called for every message received on the port, with the |
132 | id => "$NODE#$id", |
272 | global variable C<$SELF> set to the port ID. Runtime errors will cause the |
133 | names => [$id], |
273 | port to be C<kil>ed. The message will be passed as-is, no extra argument |
134 | }, "AnyEvent::MP::Port"; |
274 | (i.e. no port ID) will be passed to the callback. |
135 | |
275 | |
136 | $AnyEvent::MP::Base::PORT{$id} = sub { |
276 | If you want to stop/destroy the port, simply C<kil> it: |
137 | unshift @_, $self; |
|
|
138 | |
277 | |
139 | for (@{ $self->{rc0}{$_[1]} }) { |
278 | my $port = port { |
140 | $_ && &{$_->[0]} |
279 | my @msg = @_; |
141 | && undef $_; |
280 | ... |
|
|
281 | kil $SELF; |
|
|
282 | }; |
|
|
283 | |
|
|
284 | =cut |
|
|
285 | |
|
|
286 | sub rcv($@); |
|
|
287 | |
|
|
288 | sub _kilme { |
|
|
289 | die "received message on port without callback"; |
|
|
290 | } |
|
|
291 | |
|
|
292 | sub port(;&) { |
|
|
293 | my $id = "$UNIQ." . $ID++; |
|
|
294 | my $port = "$NODE#$id"; |
|
|
295 | |
|
|
296 | rcv $port, shift || \&_kilme; |
|
|
297 | |
|
|
298 | $port |
|
|
299 | } |
|
|
300 | |
|
|
301 | =item rcv $local_port, $callback->(@msg) |
|
|
302 | |
|
|
303 | Replaces the default callback on the specified port. There is no way to |
|
|
304 | remove the default callback: use C<sub { }> to disable it, or better |
|
|
305 | C<kil> the port when it is no longer needed. |
|
|
306 | |
|
|
307 | The global C<$SELF> (exported by this module) contains C<$port> while |
|
|
308 | executing the callback. Runtime errors during callback execution will |
|
|
309 | result in the port being C<kil>ed. |
|
|
310 | |
|
|
311 | The default callback received all messages not matched by a more specific |
|
|
312 | C<tag> match. |
|
|
313 | |
|
|
314 | =item rcv $local_port, tag => $callback->(@msg_without_tag), ... |
|
|
315 | |
|
|
316 | Register (or replace) callbacks to be called on messages starting with the |
|
|
317 | given tag on the given port (and return the port), or unregister it (when |
|
|
318 | C<$callback> is C<$undef> or missing). There can only be one callback |
|
|
319 | registered for each tag. |
|
|
320 | |
|
|
321 | The original message will be passed to the callback, after the first |
|
|
322 | element (the tag) has been removed. The callback will use the same |
|
|
323 | environment as the default callback (see above). |
|
|
324 | |
|
|
325 | Example: create a port and bind receivers on it in one go. |
|
|
326 | |
|
|
327 | my $port = rcv port, |
|
|
328 | msg1 => sub { ... }, |
|
|
329 | msg2 => sub { ... }, |
|
|
330 | ; |
|
|
331 | |
|
|
332 | Example: create a port, bind receivers and send it in a message elsewhere |
|
|
333 | in one go: |
|
|
334 | |
|
|
335 | snd $otherport, reply => |
|
|
336 | rcv port, |
|
|
337 | msg1 => sub { ... }, |
|
|
338 | ... |
|
|
339 | ; |
|
|
340 | |
|
|
341 | Example: temporarily register a rcv callback for a tag matching some port |
|
|
342 | (e.g. for a rpc reply) and unregister it after a message was received. |
|
|
343 | |
|
|
344 | rcv $port, $otherport => sub { |
|
|
345 | my @reply = @_; |
|
|
346 | |
|
|
347 | rcv $SELF, $otherport; |
|
|
348 | }; |
|
|
349 | |
|
|
350 | =cut |
|
|
351 | |
|
|
352 | sub rcv($@) { |
|
|
353 | my $port = shift; |
|
|
354 | my ($noderef, $portid) = split /#/, $port, 2; |
|
|
355 | |
|
|
356 | $NODE{$noderef} == $NODE{""} |
|
|
357 | or Carp::croak "$port: rcv can only be called on local ports, caught"; |
|
|
358 | |
|
|
359 | while (@_) { |
|
|
360 | if (ref $_[0]) { |
|
|
361 | if (my $self = $PORT_DATA{$portid}) { |
|
|
362 | "AnyEvent::MP::Port" eq ref $self |
|
|
363 | or Carp::croak "$port: rcv can only be called on message matching ports, caught"; |
|
|
364 | |
|
|
365 | $self->[2] = shift; |
|
|
366 | } else { |
|
|
367 | my $cb = shift; |
|
|
368 | $PORT{$portid} = sub { |
|
|
369 | local $SELF = $port; |
|
|
370 | eval { &$cb }; _self_die if $@; |
|
|
371 | }; |
|
|
372 | } |
|
|
373 | } elsif (defined $_[0]) { |
|
|
374 | my $self = $PORT_DATA{$portid} ||= do { |
|
|
375 | my $self = bless [$PORT{$port} || sub { }, { }, $port], "AnyEvent::MP::Port"; |
|
|
376 | |
|
|
377 | $PORT{$portid} = sub { |
|
|
378 | local $SELF = $port; |
|
|
379 | |
|
|
380 | if (my $cb = $self->[1]{$_[0]}) { |
|
|
381 | shift; |
|
|
382 | eval { &$cb }; _self_die if $@; |
|
|
383 | } else { |
|
|
384 | &{ $self->[0] }; |
|
|
385 | } |
|
|
386 | }; |
|
|
387 | |
|
|
388 | $self |
|
|
389 | }; |
|
|
390 | |
|
|
391 | "AnyEvent::MP::Port" eq ref $self |
|
|
392 | or Carp::croak "$port: rcv can only be called on message matching ports, caught"; |
|
|
393 | |
|
|
394 | my ($tag, $cb) = splice @_, 0, 2; |
|
|
395 | |
|
|
396 | if (defined $cb) { |
|
|
397 | $self->[1]{$tag} = $cb; |
|
|
398 | } else { |
|
|
399 | delete $self->[1]{$tag}; |
|
|
400 | } |
142 | } |
401 | } |
|
|
402 | } |
143 | |
403 | |
144 | for (@{ $self->{rcv}{$_[1]} }) { |
404 | $port |
145 | $_ && [@_[1 .. @{$_->[1]}]] ~~ $_->[1] |
405 | } |
146 | && &{$_->[0]} |
406 | |
147 | && undef $_; |
407 | =item $closure = psub { BLOCK } |
|
|
408 | |
|
|
409 | Remembers C<$SELF> and creates a closure out of the BLOCK. When the |
|
|
410 | closure is executed, sets up the environment in the same way as in C<rcv> |
|
|
411 | callbacks, i.e. runtime errors will cause the port to get C<kil>ed. |
|
|
412 | |
|
|
413 | This is useful when you register callbacks from C<rcv> callbacks: |
|
|
414 | |
|
|
415 | rcv delayed_reply => sub { |
|
|
416 | my ($delay, @reply) = @_; |
|
|
417 | my $timer = AE::timer $delay, 0, psub { |
|
|
418 | snd @reply, $SELF; |
|
|
419 | }; |
|
|
420 | }; |
|
|
421 | |
|
|
422 | =cut |
|
|
423 | |
|
|
424 | sub psub(&) { |
|
|
425 | my $cb = shift; |
|
|
426 | |
|
|
427 | my $port = $SELF |
|
|
428 | or Carp::croak "psub can only be called from within rcv or psub callbacks, not"; |
|
|
429 | |
|
|
430 | sub { |
|
|
431 | local $SELF = $port; |
|
|
432 | |
|
|
433 | if (wantarray) { |
|
|
434 | my @res = eval { &$cb }; |
|
|
435 | _self_die if $@; |
|
|
436 | @res |
|
|
437 | } else { |
|
|
438 | my $res = eval { &$cb }; |
|
|
439 | _self_die if $@; |
|
|
440 | $res |
148 | } |
441 | } |
|
|
442 | } |
|
|
443 | } |
149 | |
444 | |
150 | for (@{ $self->{any} }) { |
445 | =item $guard = mon $port, $cb->(@reason) # call $cb when $port dies |
151 | $_ && [@_[0 .. $#{$_->[1]}]] ~~ $_->[1] |
446 | |
152 | && &{$_->[0]} |
447 | =item $guard = mon $port, $rcvport # kill $rcvport when $port dies |
153 | && undef $_; |
448 | |
|
|
449 | =item $guard = mon $port # kill $SELF when $port dies |
|
|
450 | |
|
|
451 | =item $guard = mon $port, $rcvport, @msg # send a message when $port dies |
|
|
452 | |
|
|
453 | Monitor the given port and do something when the port is killed or |
|
|
454 | messages to it were lost, and optionally return a guard that can be used |
|
|
455 | to stop monitoring again. |
|
|
456 | |
|
|
457 | C<mon> effectively guarantees that, in the absence of hardware failures, |
|
|
458 | after starting the monitor, either all messages sent to the port will |
|
|
459 | arrive, or the monitoring action will be invoked after possible message |
|
|
460 | loss has been detected. No messages will be lost "in between" (after |
|
|
461 | the first lost message no further messages will be received by the |
|
|
462 | port). After the monitoring action was invoked, further messages might get |
|
|
463 | delivered again. |
|
|
464 | |
|
|
465 | Note that monitoring-actions are one-shot: once messages are lost (and a |
|
|
466 | monitoring alert was raised), they are removed and will not trigger again. |
|
|
467 | |
|
|
468 | In the first form (callback), the callback is simply called with any |
|
|
469 | number of C<@reason> elements (no @reason means that the port was deleted |
|
|
470 | "normally"). Note also that I<< the callback B<must> never die >>, so use |
|
|
471 | C<eval> if unsure. |
|
|
472 | |
|
|
473 | In the second form (another port given), the other port (C<$rcvport>) |
|
|
474 | will be C<kil>'ed with C<@reason>, iff a @reason was specified, i.e. on |
|
|
475 | "normal" kils nothing happens, while under all other conditions, the other |
|
|
476 | port is killed with the same reason. |
|
|
477 | |
|
|
478 | The third form (kill self) is the same as the second form, except that |
|
|
479 | C<$rvport> defaults to C<$SELF>. |
|
|
480 | |
|
|
481 | In the last form (message), a message of the form C<@msg, @reason> will be |
|
|
482 | C<snd>. |
|
|
483 | |
|
|
484 | As a rule of thumb, monitoring requests should always monitor a port from |
|
|
485 | a local port (or callback). The reason is that kill messages might get |
|
|
486 | lost, just like any other message. Another less obvious reason is that |
|
|
487 | even monitoring requests can get lost (for exmaple, when the connection |
|
|
488 | to the other node goes down permanently). When monitoring a port locally |
|
|
489 | these problems do not exist. |
|
|
490 | |
|
|
491 | Example: call a given callback when C<$port> is killed. |
|
|
492 | |
|
|
493 | mon $port, sub { warn "port died because of <@_>\n" }; |
|
|
494 | |
|
|
495 | Example: kill ourselves when C<$port> is killed abnormally. |
|
|
496 | |
|
|
497 | mon $port; |
|
|
498 | |
|
|
499 | Example: send us a restart message when another C<$port> is killed. |
|
|
500 | |
|
|
501 | mon $port, $self => "restart"; |
|
|
502 | |
|
|
503 | =cut |
|
|
504 | |
|
|
505 | sub mon { |
|
|
506 | my ($noderef, $port) = split /#/, shift, 2; |
|
|
507 | |
|
|
508 | my $node = $NODE{$noderef} || add_node $noderef; |
|
|
509 | |
|
|
510 | my $cb = @_ ? shift : $SELF || Carp::croak 'mon: called with one argument only, but $SELF not set,'; |
|
|
511 | |
|
|
512 | unless (ref $cb) { |
|
|
513 | if (@_) { |
|
|
514 | # send a kill info message |
|
|
515 | my (@msg) = ($cb, @_); |
|
|
516 | $cb = sub { snd @msg, @_ }; |
|
|
517 | } else { |
|
|
518 | # simply kill other port |
|
|
519 | my $port = $cb; |
|
|
520 | $cb = sub { kil $port, @_ if @_ }; |
154 | } |
521 | } |
|
|
522 | } |
|
|
523 | |
|
|
524 | $node->monitor ($port, $cb); |
|
|
525 | |
|
|
526 | defined wantarray |
|
|
527 | and AnyEvent::Util::guard { $node->unmonitor ($port, $cb) } |
|
|
528 | } |
|
|
529 | |
|
|
530 | =item $guard = mon_guard $port, $ref, $ref... |
|
|
531 | |
|
|
532 | Monitors the given C<$port> and keeps the passed references. When the port |
|
|
533 | is killed, the references will be freed. |
|
|
534 | |
|
|
535 | Optionally returns a guard that will stop the monitoring. |
|
|
536 | |
|
|
537 | This function is useful when you create e.g. timers or other watchers and |
|
|
538 | want to free them when the port gets killed (note the use of C<psub>): |
|
|
539 | |
|
|
540 | $port->rcv (start => sub { |
|
|
541 | my $timer; $timer = mon_guard $port, AE::timer 1, 1, psub { |
|
|
542 | undef $timer if 0.9 < rand; |
|
|
543 | }); |
|
|
544 | }); |
|
|
545 | |
|
|
546 | =cut |
|
|
547 | |
|
|
548 | sub mon_guard { |
|
|
549 | my ($port, @refs) = @_; |
|
|
550 | |
|
|
551 | #TODO: mon-less form? |
|
|
552 | |
|
|
553 | mon $port, sub { 0 && @refs } |
|
|
554 | } |
|
|
555 | |
|
|
556 | =item kil $port[, @reason] |
|
|
557 | |
|
|
558 | Kill the specified port with the given C<@reason>. |
|
|
559 | |
|
|
560 | If no C<@reason> is specified, then the port is killed "normally" (ports |
|
|
561 | monitoring other ports will not necessarily die because a port dies |
|
|
562 | "normally"). |
|
|
563 | |
|
|
564 | Otherwise, linked ports get killed with the same reason (second form of |
|
|
565 | C<mon>, see above). |
|
|
566 | |
|
|
567 | Runtime errors while evaluating C<rcv> callbacks or inside C<psub> blocks |
|
|
568 | will be reported as reason C<< die => $@ >>. |
|
|
569 | |
|
|
570 | Transport/communication errors are reported as C<< transport_error => |
|
|
571 | $message >>. |
|
|
572 | |
|
|
573 | =cut |
|
|
574 | |
|
|
575 | =item $port = spawn $node, $initfunc[, @initdata] |
|
|
576 | |
|
|
577 | Creates a port on the node C<$node> (which can also be a port ID, in which |
|
|
578 | case it's the node where that port resides). |
|
|
579 | |
|
|
580 | The port ID of the newly created port is returned immediately, and it is |
|
|
581 | possible to immediately start sending messages or to monitor the port. |
|
|
582 | |
|
|
583 | After the port has been created, the init function is called on the remote |
|
|
584 | node, in the same context as a C<rcv> callback. This function must be a |
|
|
585 | fully-qualified function name (e.g. C<MyApp::Chat::Server::init>). To |
|
|
586 | specify a function in the main program, use C<::name>. |
|
|
587 | |
|
|
588 | If the function doesn't exist, then the node tries to C<require> |
|
|
589 | the package, then the package above the package and so on (e.g. |
|
|
590 | C<MyApp::Chat::Server>, C<MyApp::Chat>, C<MyApp>) until the function |
|
|
591 | exists or it runs out of package names. |
|
|
592 | |
|
|
593 | The init function is then called with the newly-created port as context |
|
|
594 | object (C<$SELF>) and the C<@initdata> values as arguments. |
|
|
595 | |
|
|
596 | A common idiom is to pass a local port, immediately monitor the spawned |
|
|
597 | port, and in the remote init function, immediately monitor the passed |
|
|
598 | local port. This two-way monitoring ensures that both ports get cleaned up |
|
|
599 | when there is a problem. |
|
|
600 | |
|
|
601 | Example: spawn a chat server port on C<$othernode>. |
|
|
602 | |
|
|
603 | # this node, executed from within a port context: |
|
|
604 | my $server = spawn $othernode, "MyApp::Chat::Server::connect", $SELF; |
|
|
605 | mon $server; |
|
|
606 | |
|
|
607 | # init function on C<$othernode> |
|
|
608 | sub connect { |
|
|
609 | my ($srcport) = @_; |
|
|
610 | |
|
|
611 | mon $srcport; |
|
|
612 | |
|
|
613 | rcv $SELF, sub { |
|
|
614 | ... |
|
|
615 | }; |
|
|
616 | } |
|
|
617 | |
|
|
618 | =cut |
|
|
619 | |
|
|
620 | sub _spawn { |
|
|
621 | my $port = shift; |
|
|
622 | my $init = shift; |
|
|
623 | |
|
|
624 | local $SELF = "$NODE#$port"; |
|
|
625 | eval { |
|
|
626 | &{ load_func $init } |
155 | }; |
627 | }; |
156 | |
628 | _self_die if $@; |
157 | $self |
|
|
158 | } |
629 | } |
159 | |
630 | |
160 | =item $portid = create_miniport { } |
631 | sub spawn(@) { |
|
|
632 | my ($noderef, undef) = split /#/, shift, 2; |
161 | |
633 | |
162 | Creates a "mini port", that is, a port without much #TODO |
634 | my $id = "$RUNIQ." . $ID++; |
163 | |
635 | |
164 | =cut |
636 | $_[0] =~ /::/ |
|
|
637 | or Carp::croak "spawn init function must be a fully-qualified name, caught"; |
165 | |
638 | |
166 | sub create_miniport(&) { |
639 | snd_to_func $noderef, "AnyEvent::MP::_spawn" => $id, @_; |
167 | my $cb = shift; |
|
|
168 | my $id = "$AnyEvent::MP::Base::UNIQ." . ++$AnyEvent::MP::Base::ID; |
|
|
169 | |
640 | |
170 | $AnyEvent::MP::Base::PORT{$id} = sub { |
641 | "$noderef#$id" |
171 | &$cb |
642 | } |
172 | and delete $AnyEvent::MP::Base::PORT{$id}; |
643 | |
|
|
644 | =item after $timeout, @msg |
|
|
645 | |
|
|
646 | =item after $timeout, $callback |
|
|
647 | |
|
|
648 | Either sends the given message, or call the given callback, after the |
|
|
649 | specified number of seconds. |
|
|
650 | |
|
|
651 | This is simply a utility function that comes in handy at times - the |
|
|
652 | AnyEvent::MP author is not convinced of the wisdom of having it, though, |
|
|
653 | so it may go away in the future. |
|
|
654 | |
|
|
655 | =cut |
|
|
656 | |
|
|
657 | sub after($@) { |
|
|
658 | my ($timeout, @action) = @_; |
|
|
659 | |
|
|
660 | my $t; $t = AE::timer $timeout, 0, sub { |
|
|
661 | undef $t; |
|
|
662 | ref $action[0] |
|
|
663 | ? $action[0]() |
|
|
664 | : snd @action; |
173 | }; |
665 | }; |
174 | |
|
|
175 | "$NODE#$id" |
|
|
176 | } |
666 | } |
177 | |
|
|
178 | package AnyEvent::MP::Port; |
|
|
179 | |
667 | |
180 | =back |
668 | =back |
181 | |
669 | |
182 | =head1 METHODS FOR PORT OBJECTS |
670 | =head1 AnyEvent::MP vs. Distributed Erlang |
|
|
671 | |
|
|
672 | AnyEvent::MP got lots of its ideas from distributed Erlang (Erlang node |
|
|
673 | == aemp node, Erlang process == aemp port), so many of the documents and |
|
|
674 | programming techniques employed by Erlang apply to AnyEvent::MP. Here is a |
|
|
675 | sample: |
|
|
676 | |
|
|
677 | http://www.Erlang.se/doc/programming_rules.shtml |
|
|
678 | http://Erlang.org/doc/getting_started/part_frame.html # chapters 3 and 4 |
|
|
679 | http://Erlang.org/download/Erlang-book-part1.pdf # chapters 5 and 6 |
|
|
680 | http://Erlang.org/download/armstrong_thesis_2003.pdf # chapters 4 and 5 |
|
|
681 | |
|
|
682 | Despite the similarities, there are also some important differences: |
183 | |
683 | |
184 | =over 4 |
684 | =over 4 |
185 | |
685 | |
186 | =item "$port" |
686 | =item * Node IDs are arbitrary strings in AEMP. |
187 | |
687 | |
188 | A port object stringifies to its port ID, so can be used directly for |
688 | Erlang relies on special naming and DNS to work everywhere in the same |
189 | C<snd> operations. |
689 | way. AEMP relies on each node somehow knowing its own address(es) (e.g. by |
|
|
690 | configuraiton or DNS), but will otherwise discover other odes itself. |
190 | |
691 | |
191 | =cut |
692 | =item * Erlang has a "remote ports are like local ports" philosophy, AEMP |
|
|
693 | uses "local ports are like remote ports". |
192 | |
694 | |
193 | use overload |
695 | The failure modes for local ports are quite different (runtime errors |
194 | '""' => sub { $_[0]{id} }, |
696 | only) then for remote ports - when a local port dies, you I<know> it dies, |
195 | fallback => 1; |
697 | when a connection to another node dies, you know nothing about the other |
|
|
698 | port. |
196 | |
699 | |
197 | =item $port->rcv (type => $callback->($port, @msg)) |
700 | Erlang pretends remote ports are as reliable as local ports, even when |
|
|
701 | they are not. |
198 | |
702 | |
199 | =item $port->rcv ($smartmatch => $callback->($port, @msg)) |
703 | AEMP encourages a "treat remote ports differently" philosophy, with local |
|
|
704 | ports being the special case/exception, where transport errors cannot |
|
|
705 | occur. |
200 | |
706 | |
201 | =item $port->rcv ([$smartmatch...] => $callback->($port, @msg)) |
707 | =item * Erlang uses processes and a mailbox, AEMP does not queue. |
202 | |
708 | |
203 | Register a callback on the given port. |
709 | Erlang uses processes that selectively receive messages, and therefore |
|
|
710 | needs a queue. AEMP is event based, queuing messages would serve no |
|
|
711 | useful purpose. For the same reason the pattern-matching abilities of |
|
|
712 | AnyEvent::MP are more limited, as there is little need to be able to |
|
|
713 | filter messages without dequeing them. |
204 | |
714 | |
205 | The callback has to return a true value when its work is done, after |
715 | (But see L<Coro::MP> for a more Erlang-like process model on top of AEMP). |
206 | which is will be removed, or a false value in which case it will stay |
|
|
207 | registered. |
|
|
208 | |
716 | |
209 | If the match is an array reference, then it will be matched against the |
717 | =item * Erlang sends are synchronous, AEMP sends are asynchronous. |
210 | first elements of the message, otherwise only the first element is being |
|
|
211 | matched. |
|
|
212 | |
718 | |
213 | Any element in the match that is specified as C<_any_> (a function |
719 | Sending messages in Erlang is synchronous and blocks the process (and |
214 | exported by this module) matches any single element of the message. |
720 | so does not need a queue that can overflow). AEMP sends are immediate, |
|
|
721 | connection establishment is handled in the background. |
215 | |
722 | |
216 | While not required, it is highly recommended that the first matching |
723 | =item * Erlang suffers from silent message loss, AEMP does not. |
217 | element is a string identifying the message. The one-string-only match is |
|
|
218 | also the most efficient match (by far). |
|
|
219 | |
724 | |
220 | =cut |
725 | Erlang makes few guarantees on messages delivery - messages can get lost |
|
|
726 | without any of the processes realising it (i.e. you send messages a, b, |
|
|
727 | and c, and the other side only receives messages a and c). |
221 | |
728 | |
222 | sub rcv($@) { |
729 | AEMP guarantees correct ordering, and the guarantee that after one message |
223 | my ($self, $match, $cb) = @_; |
730 | is lost, all following ones sent to the same port are lost as well, until |
|
|
731 | monitoring raises an error, so there are no silent "holes" in the message |
|
|
732 | sequence. |
224 | |
733 | |
225 | if (!ref $match) { |
734 | =item * Erlang can send messages to the wrong port, AEMP does not. |
226 | push @{ $self->{rc0}{$match} }, [$cb]; |
|
|
227 | } elsif (("ARRAY" eq ref $match && !ref $match->[0])) { |
|
|
228 | my ($type, @match) = @$match; |
|
|
229 | @match |
|
|
230 | ? push @{ $self->{rcv}{$match->[0]} }, [$cb, \@match] |
|
|
231 | : push @{ $self->{rc0}{$match->[0]} }, [$cb]; |
|
|
232 | } else { |
|
|
233 | push @{ $self->{any} }, [$cb, $match]; |
|
|
234 | } |
|
|
235 | } |
|
|
236 | |
735 | |
237 | =item $port->register ($name) |
736 | In Erlang it is quite likely that a node that restarts reuses a process ID |
|
|
737 | known to other nodes for a completely different process, causing messages |
|
|
738 | destined for that process to end up in an unrelated process. |
238 | |
739 | |
239 | Registers the given port under the well known name C<$name>. If the name |
740 | AEMP never reuses port IDs, so old messages or old port IDs floating |
240 | already exists it is replaced. |
741 | around in the network will not be sent to an unrelated port. |
241 | |
742 | |
242 | A port can only be registered under one well known name. |
743 | =item * Erlang uses unprotected connections, AEMP uses secure |
|
|
744 | authentication and can use TLS. |
243 | |
745 | |
244 | =cut |
746 | AEMP can use a proven protocol - TLS - to protect connections and |
|
|
747 | securely authenticate nodes. |
245 | |
748 | |
246 | sub register { |
749 | =item * The AEMP protocol is optimised for both text-based and binary |
247 | my ($self, $name) = @_; |
750 | communications. |
248 | |
751 | |
249 | $self->{wkname} = $name; |
752 | The AEMP protocol, unlike the Erlang protocol, supports both programming |
250 | $AnyEvent::MP::Base::WKP{$name} = "$self"; |
753 | language independent text-only protocols (good for debugging) and binary, |
251 | } |
754 | language-specific serialisers (e.g. Storable). By default, unless TLS is |
|
|
755 | used, the protocol is actually completely text-based. |
252 | |
756 | |
253 | =item $port->destroy |
757 | It has also been carefully designed to be implementable in other languages |
|
|
758 | with a minimum of work while gracefully degrading functionality to make the |
|
|
759 | protocol simple. |
254 | |
760 | |
255 | Explicitly destroy/remove/nuke/vaporise the port. |
761 | =item * AEMP has more flexible monitoring options than Erlang. |
256 | |
762 | |
257 | Ports are normally kept alive by there mere existance alone, and need to |
763 | In Erlang, you can chose to receive I<all> exit signals as messages |
258 | be destroyed explicitly. |
764 | or I<none>, there is no in-between, so monitoring single processes is |
|
|
765 | difficult to implement. Monitoring in AEMP is more flexible than in |
|
|
766 | Erlang, as one can choose between automatic kill, exit message or callback |
|
|
767 | on a per-process basis. |
259 | |
768 | |
260 | =cut |
769 | =item * Erlang tries to hide remote/local connections, AEMP does not. |
261 | |
770 | |
262 | sub destroy { |
771 | Monitoring in Erlang is not an indicator of process death/crashes, in the |
263 | my ($self) = @_; |
772 | same way as linking is (except linking is unreliable in Erlang). |
264 | |
773 | |
265 | delete $AnyEvent::MP::Base::WKP{ $self->{wkname} }; |
774 | In AEMP, you don't "look up" registered port names or send to named ports |
|
|
775 | that might or might not be persistent. Instead, you normally spawn a port |
|
|
776 | on the remote node. The init function monitors you, and you monitor the |
|
|
777 | remote port. Since both monitors are local to the node, they are much more |
|
|
778 | reliable (no need for C<spawn_link>). |
266 | |
779 | |
267 | delete $AnyEvent::MP::Base::PORT{$_} |
780 | This also saves round-trips and avoids sending messages to the wrong port |
268 | for @{ $self->{names} }; |
781 | (hard to do in Erlang). |
269 | } |
|
|
270 | |
782 | |
271 | =back |
783 | =back |
272 | |
784 | |
273 | =head1 FUNCTIONS FOR NODES |
785 | =head1 RATIONALE |
274 | |
786 | |
275 | =over 4 |
787 | =over 4 |
276 | |
788 | |
277 | =item mon $noderef, $callback->($noderef, $status, $) |
789 | =item Why strings for port and node IDs, why not objects? |
278 | |
790 | |
279 | Monitors the given noderef. |
791 | We considered "objects", but found that the actual number of methods |
|
|
792 | that can be called are quite low. Since port and node IDs travel over |
|
|
793 | the network frequently, the serialising/deserialising would add lots of |
|
|
794 | overhead, as well as having to keep a proxy object everywhere. |
280 | |
795 | |
281 | =item become_public endpoint... |
796 | Strings can easily be printed, easily serialised etc. and need no special |
|
|
797 | procedures to be "valid". |
282 | |
798 | |
283 | Tells the node to become a public node, i.e. reachable from other nodes. |
799 | And as a result, a miniport consists of a single closure stored in a |
|
|
800 | global hash - it can't become much cheaper. |
284 | |
801 | |
285 | If no arguments are given, or the first argument is C<undef>, then |
802 | =item Why favour JSON, why not a real serialising format such as Storable? |
286 | AnyEvent::MP tries to bind on port C<4040> on all IP addresses that the |
|
|
287 | local nodename resolves to. |
|
|
288 | |
803 | |
289 | Otherwise the first argument must be an array-reference with transport |
804 | In fact, any AnyEvent::MP node will happily accept Storable as framing |
290 | endpoints ("ip:port", "hostname:port") or port numbers (in which case the |
805 | format, but currently there is no way to make a node use Storable by |
291 | local nodename is used as hostname). The endpoints are all resolved and |
806 | default (although all nodes will accept it). |
292 | will become the node reference. |
|
|
293 | |
807 | |
294 | =cut |
808 | The default framing protocol is JSON because a) JSON::XS is many times |
|
|
809 | faster for small messages and b) most importantly, after years of |
|
|
810 | experience we found that object serialisation is causing more problems |
|
|
811 | than it solves: Just like function calls, objects simply do not travel |
|
|
812 | easily over the network, mostly because they will always be a copy, so you |
|
|
813 | always have to re-think your design. |
|
|
814 | |
|
|
815 | Keeping your messages simple, concentrating on data structures rather than |
|
|
816 | objects, will keep your messages clean, tidy and efficient. |
295 | |
817 | |
296 | =back |
818 | =back |
297 | |
819 | |
298 | =head1 NODE MESSAGES |
|
|
299 | |
|
|
300 | Nodes understand the following messages sent to them. Many of them take |
|
|
301 | arguments called C<@reply>, which will simply be used to compose a reply |
|
|
302 | message - C<$reply[0]> is the port to reply to, C<$reply[1]> the type and |
|
|
303 | the remaining arguments are simply the message data. |
|
|
304 | |
|
|
305 | =over 4 |
|
|
306 | |
|
|
307 | =cut |
|
|
308 | |
|
|
309 | =item wkp => $name, @reply |
|
|
310 | |
|
|
311 | Replies with the port ID of the specified well-known port, or C<undef>. |
|
|
312 | |
|
|
313 | =item devnull => ... |
|
|
314 | |
|
|
315 | Generic data sink/CPU heat conversion. |
|
|
316 | |
|
|
317 | =item relay => $port, @msg |
|
|
318 | |
|
|
319 | Simply forwards the message to the given port. |
|
|
320 | |
|
|
321 | =item eval => $string[ @reply] |
|
|
322 | |
|
|
323 | Evaluates the given string. If C<@reply> is given, then a message of the |
|
|
324 | form C<@reply, $@, @evalres> is sent. |
|
|
325 | |
|
|
326 | Example: crash another node. |
|
|
327 | |
|
|
328 | snd $othernode, eval => "exit"; |
|
|
329 | |
|
|
330 | =item time => @reply |
|
|
331 | |
|
|
332 | Replies the the current node time to C<@reply>. |
|
|
333 | |
|
|
334 | Example: tell the current node to send the current time to C<$myport> in a |
|
|
335 | C<timereply> message. |
|
|
336 | |
|
|
337 | snd $NODE, time => $myport, timereply => 1, 2; |
|
|
338 | # => snd $myport, timereply => 1, 2, <time> |
|
|
339 | |
|
|
340 | =back |
|
|
341 | |
|
|
342 | =head1 SEE ALSO |
820 | =head1 SEE ALSO |
|
|
821 | |
|
|
822 | L<AnyEvent::MP::Intro> - a gentle introduction. |
|
|
823 | |
|
|
824 | L<AnyEvent::MP::Kernel> - more, lower-level, stuff. |
|
|
825 | |
|
|
826 | L<AnyEvent::MP::Global> - network maintainance and port groups, to find |
|
|
827 | your applications. |
343 | |
828 | |
344 | L<AnyEvent>. |
829 | L<AnyEvent>. |
345 | |
830 | |
346 | =head1 AUTHOR |
831 | =head1 AUTHOR |
347 | |
832 | |