… | |
… | |
12 | ->require ("MyModule") |
12 | ->require ("MyModule") |
13 | ->AnyEvent::Fork::RPC::run ( |
13 | ->AnyEvent::Fork::RPC::run ( |
14 | "MyModule::server", |
14 | "MyModule::server", |
15 | ); |
15 | ); |
16 | |
16 | |
|
|
17 | use AnyEvent; |
|
|
18 | |
17 | my $cv = AE::cv; |
19 | my $cv = AE::cv; |
18 | |
20 | |
19 | $rpc->(1, 2, 3, sub { |
21 | $rpc->(1, 2, 3, sub { |
20 | print "MyModule::server returned @_\n"; |
22 | print "MyModule::server returned @_\n"; |
21 | $cv->send; |
23 | $cv->send; |
… | |
… | |
24 | $cv->recv; |
26 | $cv->recv; |
25 | |
27 | |
26 | =head1 DESCRIPTION |
28 | =head1 DESCRIPTION |
27 | |
29 | |
28 | This module implements a simple RPC protocol and backend for processes |
30 | This module implements a simple RPC protocol and backend for processes |
29 | created via L<AnyEvent::Fork>, allowing you to call a function in the |
31 | created via L<AnyEvent::Fork> or L<AnyEvent::Fork::Remote>, allowing you |
30 | child process and receive its return values (up to 4GB serialised). |
32 | to call a function in the child process and receive its return values (up |
|
|
33 | to 4GB serialised). |
31 | |
34 | |
32 | It implements two different backends: a synchronous one that works like a |
35 | It implements two different backends: a synchronous one that works like a |
33 | normal function call, and an asynchronous one that can run multiple jobs |
36 | normal function call, and an asynchronous one that can run multiple jobs |
34 | concurrently in the child, using AnyEvent. |
37 | concurrently in the child, using AnyEvent. |
35 | |
38 | |
36 | It also implements an asynchronous event mechanism from the child to the |
39 | It also implements an asynchronous event mechanism from the child to the |
37 | parent, that could be used for progress indications or other information. |
40 | parent, that could be used for progress indications or other information. |
38 | |
41 | |
39 | =head1 EXAMPLES |
42 | =head1 EXAMPLES |
40 | |
43 | |
41 | =head2 Synchronous Backend |
44 | =head2 Example 1: Synchronous Backend |
42 | |
45 | |
43 | Here is a simple example that implements a backend that executes C<unlink> |
46 | Here is a simple example that implements a backend that executes C<unlink> |
44 | and C<rmdir> calls, and reports their status back. It also reports the |
47 | and C<rmdir> calls, and reports their status back. It also reports the |
45 | number of requests it has processed every three requests, which is clearly |
48 | number of requests it has processed every three requests, which is clearly |
46 | silly, but illustrates the use of events. |
49 | silly, but illustrates the use of events. |
… | |
… | |
55 | |
58 | |
56 | my $rpc = AnyEvent::Fork |
59 | my $rpc = AnyEvent::Fork |
57 | ->new |
60 | ->new |
58 | ->require ("MyWorker") |
61 | ->require ("MyWorker") |
59 | ->AnyEvent::Fork::RPC::run ("MyWorker::run", |
62 | ->AnyEvent::Fork::RPC::run ("MyWorker::run", |
60 | on_error => sub { warn "FATAL: $_[0]"; exit 1 }, |
63 | on_error => sub { warn "ERROR: $_[0]"; exit 1 }, |
61 | on_event => sub { warn "$_[0] requests handled\n" }, |
64 | on_event => sub { warn "$_[0] requests handled\n" }, |
62 | on_destroy => $done, |
65 | on_destroy => $done, |
63 | ); |
66 | ); |
64 | |
67 | |
65 | for my $id (1..6) { |
68 | for my $id (1..6) { |
… | |
… | |
103 | dies with a fatal error - obviously, you must never let this happen :). |
106 | dies with a fatal error - obviously, you must never let this happen :). |
104 | |
107 | |
105 | Eventually it returns the status value true if the command was successful, |
108 | Eventually it returns the status value true if the command was successful, |
106 | or the status value 0 and the stringified error message. |
109 | or the status value 0 and the stringified error message. |
107 | |
110 | |
108 | On my system, running the first cdoe fragment with the given |
111 | On my system, running the first code fragment with the given |
109 | F<MyWorker.pm> in the current directory yields: |
112 | F<MyWorker.pm> in the current directory yields: |
110 | |
113 | |
111 | /tmp/somepath/1: No such file or directory |
114 | /tmp/somepath/1: No such file or directory |
112 | /tmp/somepath/2: No such file or directory |
115 | /tmp/somepath/2: No such file or directory |
113 | 3 requests handled |
116 | 3 requests handled |
… | |
… | |
134 | |
137 | |
135 | And as a final remark, there is a fine module on CPAN that can |
138 | And as a final remark, there is a fine module on CPAN that can |
136 | asynchronously C<rmdir> and C<unlink> and a lot more, and more efficiently |
139 | asynchronously C<rmdir> and C<unlink> and a lot more, and more efficiently |
137 | than this example, namely L<IO::AIO>. |
140 | than this example, namely L<IO::AIO>. |
138 | |
141 | |
|
|
142 | =head3 Example 1a: the same with the asynchronous backend |
|
|
143 | |
|
|
144 | This example only shows what needs to be changed to use the async backend |
|
|
145 | instead. Doing this is not very useful, the purpose of this example is |
|
|
146 | to show the minimum amount of change that is required to go from the |
|
|
147 | synchronous to the asynchronous backend. |
|
|
148 | |
|
|
149 | To use the async backend in the previous example, you need to add the |
|
|
150 | C<async> parameter to the C<AnyEvent::Fork::RPC::run> call: |
|
|
151 | |
|
|
152 | ->AnyEvent::Fork::RPC::run ("MyWorker::run", |
|
|
153 | async => 1, |
|
|
154 | ... |
|
|
155 | |
|
|
156 | And since the function call protocol is now changed, you need to adopt |
|
|
157 | C<MyWorker::run> to the async API. |
|
|
158 | |
|
|
159 | First, you need to accept the extra initial C<$done> callback: |
|
|
160 | |
|
|
161 | sub run { |
|
|
162 | my ($done, $cmd, $path) = @_; |
|
|
163 | |
|
|
164 | And since a response is now generated when C<$done> is called, as opposed |
|
|
165 | to when the function returns, we need to call the C<$done> function with |
|
|
166 | the status: |
|
|
167 | |
|
|
168 | $done->($status or (0, "$!")); |
|
|
169 | |
|
|
170 | A few remarks are in order. First, it's quite pointless to use the async |
|
|
171 | backend for this example - but it I<is> possible. Second, you can call |
|
|
172 | C<$done> before or after returning from the function. Third, having both |
|
|
173 | returned from the function and having called the C<$done> callback, the |
|
|
174 | child process may exit at any time, so you should call C<$done> only when |
|
|
175 | you really I<are> done. |
|
|
176 | |
|
|
177 | =head2 Example 2: Asynchronous Backend |
|
|
178 | |
|
|
179 | This example implements multiple count-downs in the child, using |
|
|
180 | L<AnyEvent> timers. While this is a bit silly (one could use timers in te |
|
|
181 | parent just as well), it illustrates the ability to use AnyEvent in the |
|
|
182 | child and the fact that responses can arrive in a different order then the |
|
|
183 | requests. |
|
|
184 | |
|
|
185 | It also shows how to embed the actual child code into a C<__DATA__> |
|
|
186 | section, so it doesn't need any external files at all. |
|
|
187 | |
|
|
188 | And when your parent process is often busy, and you have stricter timing |
|
|
189 | requirements, then running timers in a child process suddenly doesn't look |
|
|
190 | so silly anymore. |
|
|
191 | |
|
|
192 | Without further ado, here is the code: |
|
|
193 | |
|
|
194 | use AnyEvent; |
|
|
195 | use AnyEvent::Fork; |
|
|
196 | use AnyEvent::Fork::RPC; |
|
|
197 | |
|
|
198 | my $done = AE::cv; |
|
|
199 | |
|
|
200 | my $rpc = AnyEvent::Fork |
|
|
201 | ->new |
|
|
202 | ->require ("AnyEvent::Fork::RPC::Async") |
|
|
203 | ->eval (do { local $/; <DATA> }) |
|
|
204 | ->AnyEvent::Fork::RPC::run ("run", |
|
|
205 | async => 1, |
|
|
206 | on_error => sub { warn "ERROR: $_[0]"; exit 1 }, |
|
|
207 | on_event => sub { print $_[0] }, |
|
|
208 | on_destroy => $done, |
|
|
209 | ); |
|
|
210 | |
|
|
211 | for my $count (3, 2, 1) { |
|
|
212 | $rpc->($count, sub { |
|
|
213 | warn "job $count finished\n"; |
|
|
214 | }); |
|
|
215 | } |
|
|
216 | |
|
|
217 | undef $rpc; |
|
|
218 | |
|
|
219 | $done->recv; |
|
|
220 | |
|
|
221 | __DATA__ |
|
|
222 | |
|
|
223 | # this ends up in main, as we don't use a package declaration |
|
|
224 | |
|
|
225 | use AnyEvent; |
|
|
226 | |
|
|
227 | sub run { |
|
|
228 | my ($done, $count) = @_; |
|
|
229 | |
|
|
230 | my $n; |
|
|
231 | |
|
|
232 | AnyEvent::Fork::RPC::event "starting to count up to $count\n"; |
|
|
233 | |
|
|
234 | my $w; $w = AE::timer 1, 1, sub { |
|
|
235 | ++$n; |
|
|
236 | |
|
|
237 | AnyEvent::Fork::RPC::event "count $n of $count\n"; |
|
|
238 | |
|
|
239 | if ($n == $count) { |
|
|
240 | undef $w; |
|
|
241 | $done->(); |
|
|
242 | } |
|
|
243 | }; |
|
|
244 | } |
|
|
245 | |
|
|
246 | The parent part (the one before the C<__DATA__> section) isn't very |
|
|
247 | different from the earlier examples. It sets async mode, preloads |
|
|
248 | the backend module (so the C<AnyEvent::Fork::RPC::event> function is |
|
|
249 | declared), uses a slightly different C<on_event> handler (which we use |
|
|
250 | simply for logging purposes) and then, instead of loading a module with |
|
|
251 | the actual worker code, it C<eval>'s the code from the data section in the |
|
|
252 | child process. |
|
|
253 | |
|
|
254 | It then starts three countdowns, from 3 to 1 seconds downwards, destroys |
|
|
255 | the rpc object so the example finishes eventually, and then just waits for |
|
|
256 | the stuff to trickle in. |
|
|
257 | |
|
|
258 | The worker code uses the event function to log some progress messages, but |
|
|
259 | mostly just creates a recurring one-second timer. |
|
|
260 | |
|
|
261 | The timer callback increments a counter, logs a message, and eventually, |
|
|
262 | when the count has been reached, calls the finish callback. |
|
|
263 | |
|
|
264 | On my system, this results in the following output. Since all timers fire |
|
|
265 | at roughly the same time, the actual order isn't guaranteed, but the order |
|
|
266 | shown is very likely what you would get, too. |
|
|
267 | |
|
|
268 | starting to count up to 3 |
|
|
269 | starting to count up to 2 |
|
|
270 | starting to count up to 1 |
|
|
271 | count 1 of 3 |
|
|
272 | count 1 of 2 |
|
|
273 | count 1 of 1 |
|
|
274 | job 1 finished |
|
|
275 | count 2 of 2 |
|
|
276 | job 2 finished |
|
|
277 | count 2 of 3 |
|
|
278 | count 3 of 3 |
|
|
279 | job 3 finished |
|
|
280 | |
|
|
281 | While the overall ordering isn't guaranteed, the async backend still |
|
|
282 | guarantees that events and responses are delivered to the parent process |
|
|
283 | in the exact same ordering as they were generated in the child process. |
|
|
284 | |
|
|
285 | And unless your system is I<very> busy, it should clearly show that the |
|
|
286 | job started last will finish first, as it has the lowest count. |
|
|
287 | |
|
|
288 | This concludes the async example. Since L<AnyEvent::Fork> does not |
|
|
289 | actually fork, you are free to use about any module in the child, not just |
|
|
290 | L<AnyEvent>, but also L<IO::AIO>, or L<Tk> for example. |
|
|
291 | |
|
|
292 | =head2 Example 3: Asynchronous backend with Coro |
|
|
293 | |
|
|
294 | With L<Coro> you can create a nice asynchronous backend implementation by |
|
|
295 | defining an rpc server function that creates a new Coro thread for every |
|
|
296 | request that calls a function "normally", i.e. the parameters from the |
|
|
297 | parent process are passed to it, and any return values are returned to the |
|
|
298 | parent process, e.g.: |
|
|
299 | |
|
|
300 | package My::Arith; |
|
|
301 | |
|
|
302 | sub add { |
|
|
303 | return $_[0] + $_[1]; |
|
|
304 | } |
|
|
305 | |
|
|
306 | sub mul { |
|
|
307 | return $_[0] * $_[1]; |
|
|
308 | } |
|
|
309 | |
|
|
310 | sub run { |
|
|
311 | my ($done, $func, @arg) = @_; |
|
|
312 | |
|
|
313 | Coro::async_pool { |
|
|
314 | $done->($func->(@arg)); |
|
|
315 | }; |
|
|
316 | } |
|
|
317 | |
|
|
318 | The C<run> function creates a new thread for every invocation, using the |
|
|
319 | first argument as function name, and calls the C<$done> callback on it's |
|
|
320 | return values. This makes it quite natural to define the C<add> and C<mul> |
|
|
321 | functions to add or multiply two numbers and return the result. |
|
|
322 | |
|
|
323 | Since this is the asynchronous backend, it's quite possible to define RPC |
|
|
324 | function that do I/O or wait for external events - their execution will |
|
|
325 | overlap as needed. |
|
|
326 | |
|
|
327 | The above could be used like this: |
|
|
328 | |
|
|
329 | my $rpc = AnyEvent::Fork |
|
|
330 | ->new |
|
|
331 | ->require ("MyWorker") |
|
|
332 | ->AnyEvent::Fork::RPC::run ("My::Arith::run", |
|
|
333 | on_error => ..., on_event => ..., on_destroy => ..., |
|
|
334 | ); |
|
|
335 | |
|
|
336 | $rpc->(add => 1, 3, Coro::rouse_cb); say Coro::rouse_wait; |
|
|
337 | $rpc->(mul => 3, 2, Coro::rouse_cb); say Coro::rouse_wait; |
|
|
338 | |
|
|
339 | The C<say>'s will print C<4> and C<6>. |
|
|
340 | |
|
|
341 | =head2 Example 4: Forward AnyEvent::Log messages using C<on_event> |
|
|
342 | |
|
|
343 | This partial example shows how to use the C<event> function to forward |
|
|
344 | L<AnyEvent::Log> messages to the parent. |
|
|
345 | |
|
|
346 | For this, the parent needs to provide a suitable C<on_event>: |
|
|
347 | |
|
|
348 | ->AnyEvent::Fork::RPC::run ( |
|
|
349 | on_event => sub { |
|
|
350 | if ($_[0] eq "ae_log") { |
|
|
351 | my (undef, $level, $message) = @_; |
|
|
352 | AE::log $level, $message; |
|
|
353 | } else { |
|
|
354 | # other event types |
|
|
355 | } |
|
|
356 | }, |
|
|
357 | ) |
|
|
358 | |
|
|
359 | In the child, as early as possible, the following code should reconfigure |
|
|
360 | L<AnyEvent::Log> to log via C<AnyEvent::Fork::RPC::event>: |
|
|
361 | |
|
|
362 | $AnyEvent::Log::LOG->log_cb (sub { |
|
|
363 | my ($timestamp, $orig_ctx, $level, $message) = @{+shift}; |
|
|
364 | |
|
|
365 | if (defined &AnyEvent::Fork::RPC::event) { |
|
|
366 | AnyEvent::Fork::RPC::event (ae_log => $level, $message); |
|
|
367 | } else { |
|
|
368 | warn "[$$ before init] $message\n"; |
|
|
369 | } |
|
|
370 | }); |
|
|
371 | |
|
|
372 | There is an important twist - the C<AnyEvent::Fork::RPC::event> function |
|
|
373 | is only defined when the child is fully initialised. If you redirect the |
|
|
374 | log messages in your C<init> function for example, then the C<event> |
|
|
375 | function might not yet be available. This is why the log callback checks |
|
|
376 | whether the fucntion is there using C<defined>, and only then uses it to |
|
|
377 | log the message. |
|
|
378 | |
139 | =head1 PARENT PROCESS USAGE |
379 | =head1 PARENT PROCESS USAGE |
140 | |
380 | |
141 | This module exports nothing, and only implements a single function: |
381 | This module exports nothing, and only implements a single function: |
142 | |
382 | |
143 | =over 4 |
383 | =over 4 |
… | |
… | |
150 | |
390 | |
151 | use Errno (); |
391 | use Errno (); |
152 | use Guard (); |
392 | use Guard (); |
153 | |
393 | |
154 | use AnyEvent; |
394 | use AnyEvent; |
155 | #use AnyEvent::Fork; |
|
|
156 | |
395 | |
157 | our $VERSION = 0.1; |
396 | our $VERSION = 1.1; |
158 | |
397 | |
159 | =item my $rpc = AnyEvent::Fork::RPC::run $fork, $function, [key => value...] |
398 | =item my $rpc = AnyEvent::Fork::RPC::run $fork, $function, [key => value...] |
160 | |
399 | |
161 | The traditional way to call it. But it is way cooler to call it in the |
400 | The traditional way to call it. But it is way cooler to call it in the |
162 | following way: |
401 | following way: |
… | |
… | |
182 | Called on (fatal) errors, with a descriptive (hopefully) message. If |
421 | Called on (fatal) errors, with a descriptive (hopefully) message. If |
183 | this callback is not provided, but C<on_event> is, then the C<on_event> |
422 | this callback is not provided, but C<on_event> is, then the C<on_event> |
184 | callback is called with the first argument being the string C<error>, |
423 | callback is called with the first argument being the string C<error>, |
185 | followed by the error message. |
424 | followed by the error message. |
186 | |
425 | |
187 | If neither handler is provided it prints the error to STDERR and will |
426 | If neither handler is provided, then the error is reported with loglevel |
188 | start failing badly. |
427 | C<error> via C<AE::log>. |
189 | |
428 | |
190 | =item on_event => $cb->(...) |
429 | =item on_event => $cb->(...) |
191 | |
430 | |
192 | Called for every call to the C<AnyEvent::Fork::RPC::event> function in the |
431 | Called for every call to the C<AnyEvent::Fork::RPC::event> function in the |
193 | child, with the arguments of that function passed to the callback. |
432 | child, with the arguments of that function passed to the callback. |
… | |
… | |
198 | |
437 | |
199 | Called when the C<$rpc> object has been destroyed and all requests have |
438 | Called when the C<$rpc> object has been destroyed and all requests have |
200 | been successfully handled. This is useful when you queue some requests and |
439 | been successfully handled. This is useful when you queue some requests and |
201 | want the child to go away after it has handled them. The problem is that |
440 | want the child to go away after it has handled them. The problem is that |
202 | the parent must not exit either until all requests have been handled, and |
441 | the parent must not exit either until all requests have been handled, and |
203 | this cna be accomplished by waiting for this callback. |
442 | this can be accomplished by waiting for this callback. |
204 | |
443 | |
205 | =item init => $function (default none) |
444 | =item init => $function (default none) |
206 | |
445 | |
207 | When specified (by name), this function is called in the child as the very |
446 | When specified (by name), this function is called in the child as the very |
208 | first thing when taking over the process, with all the arguments normally |
447 | first thing when taking over the process, with all the arguments normally |
… | |
… | |
215 | It is called very early - before the serialisers are created or the |
454 | It is called very early - before the serialisers are created or the |
216 | C<$function> name is resolved into a function reference, so it could be |
455 | C<$function> name is resolved into a function reference, so it could be |
217 | used to load any modules that provide the serialiser or function. It can |
456 | used to load any modules that provide the serialiser or function. It can |
218 | not, however, create events. |
457 | not, however, create events. |
219 | |
458 | |
|
|
459 | =item done => $function (default C<CORE::exit>) |
|
|
460 | |
|
|
461 | The function to call when the asynchronous backend detects an end of file |
|
|
462 | condition when reading from the communications socket I<and> there are no |
|
|
463 | outstanding requests. It's ignored by the synchronous backend. |
|
|
464 | |
|
|
465 | By overriding this you can prolong the life of a RPC process after e.g. |
|
|
466 | the parent has exited by running the event loop in the provided function |
|
|
467 | (or simply calling it, for example, when your child process uses L<EV> you |
|
|
468 | could provide L<EV::loop> as C<done> function). |
|
|
469 | |
|
|
470 | Of course, in that case you are responsible for exiting at the appropriate |
|
|
471 | time and not returning from |
|
|
472 | |
220 | =item async => $boolean (default: 0) |
473 | =item async => $boolean (default: 0) |
221 | |
474 | |
222 | The default server used in the child does all I/O blockingly, and only |
475 | The default server used in the child does all I/O blockingly, and only |
223 | allows a single RPC call to execute concurrently. |
476 | allows a single RPC call to execute concurrently. |
224 | |
477 | |
225 | Setting C<async> to a true value switches to another implementation that |
478 | Setting C<async> to a true value switches to another implementation that |
226 | uses L<AnyEvent> in the child and allows multiple concurrent RPC calls. |
479 | uses L<AnyEvent> in the child and allows multiple concurrent RPC calls (it |
|
|
480 | does not support recursion in the event loop however, blocking condvar |
|
|
481 | calls will fail). |
227 | |
482 | |
228 | The actual API in the child is documented in the section that describes |
483 | The actual API in the child is documented in the section that describes |
229 | the calling semantics of the returned C<$rpc> function. |
484 | the calling semantics of the returned C<$rpc> function. |
230 | |
485 | |
231 | If you want to pre-load the actual back-end modules to enable memory |
486 | If you want to pre-load the actual back-end modules to enable memory |
232 | sharing, then you should load C<AnyEvent::Fork::RPC::Sync> for |
487 | sharing, then you should load C<AnyEvent::Fork::RPC::Sync> for |
233 | synchronous, and C<AnyEvent::Fork::RPC::Async> for asynchronous mode. |
488 | synchronous, and C<AnyEvent::Fork::RPC::Async> for asynchronous mode. |
234 | |
489 | |
235 | If you use a template process and want to fork both sync and async |
490 | If you use a template process and want to fork both sync and async |
236 | children, then it is permissible to laod both modules. |
491 | children, then it is permissible to load both modules. |
237 | |
492 | |
238 | =item serialiser => $string (default: '(sub { pack "(w/a*)*", @_ }, sub { unpack "(w/a*)*", shift })') |
493 | =item serialiser => $string (default: $AnyEvent::Fork::RPC::STRING_SERIALISER) |
239 | |
494 | |
240 | All arguments, result data and event data have to be serialised to be |
495 | All arguments, result data and event data have to be serialised to be |
241 | transferred between the processes. For this, they have to be frozen and |
496 | transferred between the processes. For this, they have to be frozen and |
242 | thawed in both parent and child processes. |
497 | thawed in both parent and child processes. |
243 | |
498 | |
244 | By default, only octet strings can be passed between the processes, which |
499 | By default, only octet strings can be passed between the processes, which |
245 | is reasonably fast and efficient. |
500 | is reasonably fast and efficient and requires no extra modules. |
246 | |
501 | |
247 | For more complicated use cases, you can provide your own freeze and thaw |
502 | For more complicated use cases, you can provide your own freeze and thaw |
248 | functions, by specifying a string with perl source code. It's supposed to |
503 | functions, by specifying a string with perl source code. It's supposed to |
249 | return two code references when evaluated: the first receives a list of |
504 | return two code references when evaluated: the first receives a list of |
250 | perl values and must return an octet string. The second receives the octet |
505 | perl values and must return an octet string. The second receives the octet |
… | |
… | |
252 | |
507 | |
253 | If you need an external module for serialisation, then you can either |
508 | If you need an external module for serialisation, then you can either |
254 | pre-load it into your L<AnyEvent::Fork> process, or you can add a C<use> |
509 | pre-load it into your L<AnyEvent::Fork> process, or you can add a C<use> |
255 | or C<require> statement into the serialiser string. Or both. |
510 | or C<require> statement into the serialiser string. Or both. |
256 | |
511 | |
|
|
512 | Here are some examples - some of them are also available as global |
|
|
513 | variables that make them easier to use. |
|
|
514 | |
|
|
515 | =over 4 |
|
|
516 | |
|
|
517 | =item octet strings - C<$AnyEvent::Fork::RPC::STRING_SERIALISER> |
|
|
518 | |
|
|
519 | This serialiser concatenates length-prefixes octet strings, and is the |
|
|
520 | default. That means you can only pass (and return) strings containing |
|
|
521 | character codes 0-255. |
|
|
522 | |
|
|
523 | Implementation: |
|
|
524 | |
|
|
525 | ( |
|
|
526 | sub { pack "(w/a*)*", @_ }, |
|
|
527 | sub { unpack "(w/a*)*", shift } |
|
|
528 | ) |
|
|
529 | |
|
|
530 | =item json - C<$AnyEvent::Fork::RPC::JSON_SERIALISER> |
|
|
531 | |
|
|
532 | This serialiser creates JSON arrays - you have to make sure the L<JSON> |
|
|
533 | module is installed for this serialiser to work. It can be beneficial for |
|
|
534 | sharing when you preload the L<JSON> module in a template process. |
|
|
535 | |
|
|
536 | L<JSON> (with L<JSON::XS> installed) is slower than the octet string |
|
|
537 | serialiser, but usually much faster than L<Storable>, unless big chunks of |
|
|
538 | binary data need to be transferred. |
|
|
539 | |
|
|
540 | Implementation: |
|
|
541 | |
|
|
542 | use JSON (); |
|
|
543 | ( |
|
|
544 | sub { JSON::encode_json \@_ }, |
|
|
545 | sub { @{ JSON::decode_json shift } } |
|
|
546 | ) |
|
|
547 | |
|
|
548 | =item storable - C<$AnyEvent::Fork::RPC::STORABLE_SERIALISER> |
|
|
549 | |
|
|
550 | This serialiser uses L<Storable>, which means it has high chance of |
|
|
551 | serialising just about anything you throw at it, at the cost of having |
|
|
552 | very high overhead per operation. It also comes with perl. It should be |
|
|
553 | used when you need to serialise complex data structures. |
|
|
554 | |
|
|
555 | Implementation: |
|
|
556 | |
|
|
557 | use Storable (); |
|
|
558 | ( |
|
|
559 | sub { Storable::freeze \@_ }, |
|
|
560 | sub { @{ Storable::thaw shift } } |
|
|
561 | ) |
|
|
562 | |
|
|
563 | =item portable storable - C<$AnyEvent::Fork::RPC::NSTORABLE_SERIALISER> |
|
|
564 | |
|
|
565 | This serialiser also uses L<Storable>, but uses it's "network" format |
|
|
566 | to serialise data, which makes it possible to talk to different |
|
|
567 | perl binaries (for example, when talking to a process created with |
|
|
568 | L<AnyEvent::Fork::Remote>). |
|
|
569 | |
|
|
570 | Implementation: |
|
|
571 | |
|
|
572 | use Storable (); |
|
|
573 | ( |
|
|
574 | sub { Storable::nfreeze \@_ }, |
|
|
575 | sub { @{ Storable::thaw shift } } |
|
|
576 | ) |
|
|
577 | |
257 | =back |
578 | =back |
258 | |
579 | |
|
|
580 | =back |
|
|
581 | |
|
|
582 | See the examples section earlier in this document for some actual |
|
|
583 | examples. |
|
|
584 | |
259 | =cut |
585 | =cut |
260 | |
586 | |
261 | our $STRING_SERIALISER = '(sub { pack "(w/a*)*", @_ }, sub { unpack "(w/a*)*", shift })'; |
587 | our $STRING_SERIALISER = '(sub { pack "(w/a*)*", @_ }, sub { unpack "(w/a*)*", shift })'; |
|
|
588 | our $JSON_SERIALISER = 'use JSON (); (sub { JSON::encode_json \@_ }, sub { @{ JSON::decode_json shift } })'; |
|
|
589 | our $STORABLE_SERIALISER = 'use Storable (); (sub { Storable::freeze \@_ }, sub { @{ Storable::thaw shift } })'; |
|
|
590 | our $NSTORABLE_SERIALISER = 'use Storable (); (sub { Storable::nfreeze \@_ }, sub { @{ Storable::thaw shift } })'; |
262 | |
591 | |
263 | sub run { |
592 | sub run { |
264 | my ($self, $function, %arg) = @_; |
593 | my ($self, $function, %arg) = @_; |
265 | |
594 | |
266 | my $serialiser = delete $arg{serialiser} || $STRING_SERIALISER; |
595 | my $serialiser = delete $arg{serialiser} || $STRING_SERIALISER; |
… | |
… | |
269 | my $on_destroy = delete $arg{on_destroy}; |
598 | my $on_destroy = delete $arg{on_destroy}; |
270 | |
599 | |
271 | # default for on_error is to on_event, if specified |
600 | # default for on_error is to on_event, if specified |
272 | $on_error ||= $on_event |
601 | $on_error ||= $on_event |
273 | ? sub { $on_event->(error => shift) } |
602 | ? sub { $on_event->(error => shift) } |
274 | : sub { die "AnyEvent::Fork::RPC: uncaught error: $_[0].\n" }; |
603 | : sub { AE::log die => "AnyEvent::Fork::RPC: uncaught error: $_[0]." }; |
275 | |
604 | |
276 | # default for on_event is to raise an error |
605 | # default for on_event is to raise an error |
277 | $on_event ||= sub { $on_error->("event received, but no on_event handler") }; |
606 | $on_event ||= sub { $on_error->("event received, but no on_event handler") }; |
278 | |
607 | |
279 | my ($f, $t) = eval $serialiser; die $@ if $@; |
608 | my ($f, $t) = eval $serialiser; die $@ if $@; |
280 | |
609 | |
281 | my (@rcb, $fh, $shutdown, $wbuf, $ww, $rw); |
610 | my (@rcb, %rcb, $fh, $shutdown, $wbuf, $ww); |
282 | my ($rlen, $rbuf) = 512 - 16; |
611 | my ($rlen, $rbuf, $rw) = 512 - 16; |
283 | |
612 | |
284 | my $wcb = sub { |
613 | my $wcb = sub { |
285 | my $len = syswrite $fh, $wbuf; |
614 | my $len = syswrite $fh, $wbuf; |
286 | |
615 | |
287 | if (!defined $len) { |
616 | unless (defined $len) { |
288 | if ($! != Errno::EAGAIN && $! != Errno::EWOULDBLOCK) { |
617 | if ($! != Errno::EAGAIN && $! != Errno::EWOULDBLOCK) { |
289 | undef $rw; undef $ww; # it ends here |
618 | undef $rw; undef $ww; # it ends here |
290 | $on_error->("$!"); |
619 | $on_error->("$!"); |
291 | } |
620 | } |
292 | } |
621 | } |
… | |
… | |
300 | }; |
629 | }; |
301 | |
630 | |
302 | my $module = "AnyEvent::Fork::RPC::" . ($arg{async} ? "Async" : "Sync"); |
631 | my $module = "AnyEvent::Fork::RPC::" . ($arg{async} ? "Async" : "Sync"); |
303 | |
632 | |
304 | $self->require ($module) |
633 | $self->require ($module) |
305 | ->send_arg ($function, $arg{init}, $serialiser) |
634 | ->send_arg ($function, $arg{init}, $serialiser, $arg{done} || "CORE::exit") |
306 | ->run ("$module\::run", sub { |
635 | ->run ("$module\::run", sub { |
307 | $fh = shift; |
636 | $fh = shift; |
|
|
637 | |
|
|
638 | my ($id, $len); |
308 | $rw = AE::io $fh, 0, sub { |
639 | $rw = AE::io $fh, 0, sub { |
309 | $rlen = $rlen * 2 + 16 if $rlen - 128 < length $rbuf; |
640 | $rlen = $rlen * 2 + 16 if $rlen - 128 < length $rbuf; |
310 | my $len = sysread $fh, $rbuf, $rlen - length $rbuf, length $rbuf; |
641 | $len = sysread $fh, $rbuf, $rlen - length $rbuf, length $rbuf; |
311 | |
642 | |
312 | if ($len) { |
643 | if ($len) { |
313 | while (5 <= length $rbuf) { |
644 | while (8 <= length $rbuf) { |
314 | $len = unpack "L", $rbuf; |
645 | ($id, $len) = unpack "NN", $rbuf; |
315 | 4 + $len <= length $rbuf |
646 | 8 + $len <= length $rbuf |
316 | or last; |
647 | or last; |
317 | |
648 | |
318 | my @r = $t->(substr $rbuf, 4, $len); |
649 | my @r = $t->(substr $rbuf, 8, $len); |
319 | substr $rbuf, 0, $len + 4, ""; |
650 | substr $rbuf, 0, 8 + $len, ""; |
|
|
651 | |
|
|
652 | if ($id) { |
|
|
653 | if (@rcb) { |
|
|
654 | (shift @rcb)->(@r); |
|
|
655 | } elsif (my $cb = delete $rcb{$id}) { |
|
|
656 | $cb->(@r); |
|
|
657 | } else { |
|
|
658 | undef $rw; undef $ww; |
|
|
659 | $on_error->("unexpected data from child"); |
320 | |
660 | } |
321 | if (pop @r) { |
661 | } else { |
322 | $on_event->(@r); |
662 | $on_event->(@r); |
323 | } elsif (@rcb) { |
|
|
324 | (shift @rcb)->(@r); |
|
|
325 | } else { |
|
|
326 | undef $rw; undef $ww; |
|
|
327 | $on_error->("unexpected data from child"); |
|
|
328 | } |
663 | } |
329 | } |
664 | } |
330 | } elsif (defined $len) { |
665 | } elsif (defined $len) { |
331 | undef $rw; undef $ww; # it ends here |
666 | undef $rw; undef $ww; # it ends here |
332 | |
667 | |
333 | if (@rcb) { |
668 | if (@rcb || %rcb) { |
334 | $on_error->("unexpected eof"); |
669 | $on_error->("unexpected eof"); |
335 | } else { |
670 | } else { |
336 | $on_destroy->(); |
671 | $on_destroy->() |
|
|
672 | if $on_destroy; |
337 | } |
673 | } |
338 | } elsif ($! != Errno::EAGAIN && $! != Errno::EWOULDBLOCK) { |
674 | } elsif ($! != Errno::EAGAIN && $! != Errno::EWOULDBLOCK) { |
339 | undef $rw; undef $ww; # it ends here |
675 | undef $rw; undef $ww; # it ends here |
340 | $on_error->("read: $!"); |
676 | $on_error->("read: $!"); |
341 | } |
677 | } |
… | |
… | |
344 | $ww ||= AE::io $fh, 1, $wcb; |
680 | $ww ||= AE::io $fh, 1, $wcb; |
345 | }); |
681 | }); |
346 | |
682 | |
347 | my $guard = Guard::guard { |
683 | my $guard = Guard::guard { |
348 | $shutdown = 1; |
684 | $shutdown = 1; |
349 | $ww ||= $fh && AE::io $fh, 1, $wcb; |
685 | |
|
|
686 | shutdown $fh, 1 if $fh && !$ww; |
350 | }; |
687 | }; |
351 | |
688 | |
|
|
689 | my $id; |
|
|
690 | |
|
|
691 | $arg{async} |
352 | sub { |
692 | ? sub { |
353 | push @rcb, pop; |
693 | $id = ($id == 0xffffffff ? 0 : $id) + 1; |
|
|
694 | $id = ($id == 0xffffffff ? 0 : $id) + 1 while exists $rcb{$id}; # rarely loops |
354 | |
695 | |
|
|
696 | $rcb{$id} = pop; |
|
|
697 | |
355 | $guard; # keep it alive |
698 | $guard if 0; # keep it alive |
356 | |
699 | |
357 | $wbuf .= pack "L/a*", &$f; |
700 | $wbuf .= pack "NN/a*", $id, &$f; |
358 | $ww ||= $fh && AE::io $fh, 1, $wcb; |
701 | $ww ||= $fh && AE::io $fh, 1, $wcb; |
359 | } |
702 | } |
|
|
703 | : sub { |
|
|
704 | push @rcb, pop; |
|
|
705 | |
|
|
706 | $guard; # keep it alive |
|
|
707 | |
|
|
708 | $wbuf .= pack "N/a*", &$f; |
|
|
709 | $ww ||= $fh && AE::io $fh, 1, $wcb; |
|
|
710 | } |
360 | } |
711 | } |
361 | |
712 | |
362 | =item $rpc->(..., $cb->(...)) |
713 | =item $rpc->(..., $cb->(...)) |
363 | |
714 | |
364 | The RPC object returned by C<AnyEvent::Fork::RPC::run> is actually a code |
715 | The RPC object returned by C<AnyEvent::Fork::RPC::run> is actually a code |
… | |
… | |
379 | |
730 | |
380 | The other thing that can be done with the RPC object is to destroy it. In |
731 | The other thing that can be done with the RPC object is to destroy it. In |
381 | this case, the child process will execute all remaining RPC calls, report |
732 | this case, the child process will execute all remaining RPC calls, report |
382 | their results, and then exit. |
733 | their results, and then exit. |
383 | |
734 | |
|
|
735 | See the examples section earlier in this document for some actual |
|
|
736 | examples. |
|
|
737 | |
384 | =back |
738 | =back |
385 | |
739 | |
386 | =head1 CHILD PROCESS USAGE |
740 | =head1 CHILD PROCESS USAGE |
387 | |
741 | |
388 | The following function is not available in this module. They are only |
742 | The following function is not available in this module. They are only |
… | |
… | |
396 | |
750 | |
397 | Send an event to the parent. Events are a bit like RPC calls made by the |
751 | Send an event to the parent. Events are a bit like RPC calls made by the |
398 | child process to the parent, except that there is no notion of return |
752 | child process to the parent, except that there is no notion of return |
399 | values. |
753 | values. |
400 | |
754 | |
|
|
755 | See the examples section earlier in this document for some actual |
|
|
756 | examples. |
|
|
757 | |
401 | =back |
758 | =back |
402 | |
759 | |
|
|
760 | =head2 PROCESS EXIT |
|
|
761 | |
|
|
762 | If and when the child process exits depends on the backend and |
|
|
763 | configuration. Apart from explicit exits (e.g. by calling C<exit>) or |
|
|
764 | runtime conditions (uncaught exceptions, signals etc.), the backends exit |
|
|
765 | under these conditions: |
|
|
766 | |
|
|
767 | =over 4 |
|
|
768 | |
|
|
769 | =item Synchronous Backend |
|
|
770 | |
|
|
771 | The synchronous backend is very simple: when the process waits for another |
|
|
772 | request to arrive and the writing side (usually in the parent) is closed, |
|
|
773 | it will exit normally, i.e. as if your main program reached the end of the |
|
|
774 | file. |
|
|
775 | |
|
|
776 | That means that if your parent process exits, the RPC process will usually |
|
|
777 | exit as well, either because it is idle anyway, or because it executes a |
|
|
778 | request. In the latter case, you will likely get an error when the RPc |
|
|
779 | process tries to send the results to the parent (because agruably, you |
|
|
780 | shouldn't exit your parent while there are still outstanding requests). |
|
|
781 | |
|
|
782 | The process is usually quiescent when it happens, so it should rarely be a |
|
|
783 | problem, and C<END> handlers can be used to clean up. |
|
|
784 | |
|
|
785 | =item Asynchronous Backend |
|
|
786 | |
|
|
787 | For the asynchronous backend, things are more complicated: Whenever it |
|
|
788 | listens for another request by the parent, it might detect that the socket |
|
|
789 | was closed (e.g. because the parent exited). It will sotp listening for |
|
|
790 | new requests and instead try to write out any remaining data (if any) or |
|
|
791 | simply check whether the socket cna be written to. After this, the RPC |
|
|
792 | process is effectively done - no new requests are incoming, no outstanding |
|
|
793 | request data can be written back. |
|
|
794 | |
|
|
795 | Since chances are high that there are event watchers that the RPC server |
|
|
796 | knows nothing about (why else would one use the async backend if not for |
|
|
797 | the ability to register watchers?), the event loop would often happily |
|
|
798 | continue. |
|
|
799 | |
|
|
800 | This is why the asynchronous backend explicitly calls C<CORE::exit> when |
|
|
801 | it is done (it will raise an exception under other circumstances, which |
|
|
802 | might lead to the process not exiting on it's own). |
|
|
803 | |
|
|
804 | You can override this by specifying a function name to call via the C<done> |
|
|
805 | parameter instead. |
|
|
806 | |
|
|
807 | =back |
|
|
808 | |
|
|
809 | =head1 ADVANCED TOPICS |
|
|
810 | |
|
|
811 | =head2 Choosing a backend |
|
|
812 | |
|
|
813 | So how do you decide which backend to use? Well, that's your problem to |
|
|
814 | solve, but here are some thoughts on the matter: |
|
|
815 | |
|
|
816 | =over 4 |
|
|
817 | |
|
|
818 | =item Synchronous |
|
|
819 | |
|
|
820 | The synchronous backend does not rely on any external modules (well, |
|
|
821 | except L<common::sense>, which works around a bug in how perl's warning |
|
|
822 | system works). This keeps the process very small, for example, on my |
|
|
823 | system, an empty perl interpreter uses 1492kB RSS, which becomes 2020kB |
|
|
824 | after C<use warnings; use strict> (for people who grew up with C64s around |
|
|
825 | them this is probably shocking every single time they see it). The worker |
|
|
826 | process in the first example in this document uses 1792kB. |
|
|
827 | |
|
|
828 | Since the calls are done synchronously, slow jobs will keep newer jobs |
|
|
829 | from executing. |
|
|
830 | |
|
|
831 | The synchronous backend also has no overhead due to running an event loop |
|
|
832 | - reading requests is therefore very efficient, while writing responses is |
|
|
833 | less so, as every response results in a write syscall. |
|
|
834 | |
|
|
835 | If the parent process is busy and a bit slow reading responses, the child |
|
|
836 | waits instead of processing further requests. This also limits the amount |
|
|
837 | of memory needed for buffering, as never more than one response has to be |
|
|
838 | buffered. |
|
|
839 | |
|
|
840 | The API in the child is simple - you just have to define a function that |
|
|
841 | does something and returns something. |
|
|
842 | |
|
|
843 | It's hard to use modules or code that relies on an event loop, as the |
|
|
844 | child cannot execute anything while it waits for more input. |
|
|
845 | |
|
|
846 | =item Asynchronous |
|
|
847 | |
|
|
848 | The asynchronous backend relies on L<AnyEvent>, which tries to be small, |
|
|
849 | but still comes at a price: On my system, the worker from example 1a uses |
|
|
850 | 3420kB RSS (for L<AnyEvent>, which loads L<EV>, which needs L<XSLoader> |
|
|
851 | which in turn loads a lot of other modules such as L<warnings>, L<strict>, |
|
|
852 | L<vars>, L<Exporter>...). |
|
|
853 | |
|
|
854 | It batches requests and responses reasonably efficiently, doing only as |
|
|
855 | few reads and writes as needed, but needs to poll for events via the event |
|
|
856 | loop. |
|
|
857 | |
|
|
858 | Responses are queued when the parent process is busy. This means the child |
|
|
859 | can continue to execute any queued requests. It also means that a child |
|
|
860 | might queue a lot of responses in memory when it generates them and the |
|
|
861 | parent process is slow accepting them. |
|
|
862 | |
|
|
863 | The API is not a straightforward RPC pattern - you have to call a |
|
|
864 | "done" callback to pass return values and signal completion. Also, more |
|
|
865 | importantly, the API starts jobs as fast as possible - when 1000 jobs |
|
|
866 | are queued and the jobs are slow, they will all run concurrently. The |
|
|
867 | child must implement some queueing/limiting mechanism if this causes |
|
|
868 | problems. Alternatively, the parent could limit the amount of rpc calls |
|
|
869 | that are outstanding. |
|
|
870 | |
|
|
871 | Blocking use of condvars is not supported. |
|
|
872 | |
|
|
873 | Using event-based modules such as L<IO::AIO>, L<Gtk2>, L<Tk> and so on is |
|
|
874 | easy. |
|
|
875 | |
|
|
876 | =back |
|
|
877 | |
|
|
878 | =head2 Passing file descriptors |
|
|
879 | |
|
|
880 | Unlike L<AnyEvent::Fork>, this module has no in-built file handle or file |
|
|
881 | descriptor passing abilities. |
|
|
882 | |
|
|
883 | The reason is that passing file descriptors is extraordinary tricky |
|
|
884 | business, and conflicts with efficient batching of messages. |
|
|
885 | |
|
|
886 | There still is a method you can use: Create a |
|
|
887 | C<AnyEvent::Util::portable_socketpair> and C<send_fh> one half of it to |
|
|
888 | the process before you pass control to C<AnyEvent::Fork::RPC::run>. |
|
|
889 | |
|
|
890 | Whenever you want to pass a file descriptor, send an rpc request to the |
|
|
891 | child process (so it expects the descriptor), then send it over the other |
|
|
892 | half of the socketpair. The child should fetch the descriptor from the |
|
|
893 | half it has passed earlier. |
|
|
894 | |
|
|
895 | Here is some (untested) pseudocode to that effect: |
|
|
896 | |
|
|
897 | use AnyEvent::Util; |
|
|
898 | use AnyEvent::Fork; |
|
|
899 | use AnyEvent::Fork::RPC; |
|
|
900 | use IO::FDPass; |
|
|
901 | |
|
|
902 | my ($s1, $s2) = AnyEvent::Util::portable_socketpair; |
|
|
903 | |
|
|
904 | my $rpc = AnyEvent::Fork |
|
|
905 | ->new |
|
|
906 | ->send_fh ($s2) |
|
|
907 | ->require ("MyWorker") |
|
|
908 | ->AnyEvent::Fork::RPC::run ("MyWorker::run" |
|
|
909 | init => "MyWorker::init", |
|
|
910 | ); |
|
|
911 | |
|
|
912 | undef $s2; # no need to keep it around |
|
|
913 | |
|
|
914 | # pass an fd |
|
|
915 | $rpc->("i'll send some fd now, please expect it!", my $cv = AE::cv); |
|
|
916 | |
|
|
917 | IO::FDPass fileno $s1, fileno $handle_to_pass; |
|
|
918 | |
|
|
919 | $cv->recv; |
|
|
920 | |
|
|
921 | The MyWorker module could look like this: |
|
|
922 | |
|
|
923 | package MyWorker; |
|
|
924 | |
|
|
925 | use IO::FDPass; |
|
|
926 | |
|
|
927 | my $s2; |
|
|
928 | |
|
|
929 | sub init { |
|
|
930 | $s2 = $_[0]; |
|
|
931 | } |
|
|
932 | |
|
|
933 | sub run { |
|
|
934 | if ($_[0] eq "i'll send some fd now, please expect it!") { |
|
|
935 | my $fd = IO::FDPass::recv fileno $s2; |
|
|
936 | ... |
|
|
937 | } |
|
|
938 | } |
|
|
939 | |
|
|
940 | Of course, this might be blocking if you pass a lot of file descriptors, |
|
|
941 | so you might want to look into L<AnyEvent::FDpasser> which can handle the |
|
|
942 | gory details. |
|
|
943 | |
|
|
944 | =head1 EXCEPTIONS |
|
|
945 | |
|
|
946 | There are no provisions whatsoever for catching exceptions at this time - |
|
|
947 | in the child, exeptions might kill the process, causing calls to be lost |
|
|
948 | and the parent encountering a fatal error. In the parent, exceptions in |
|
|
949 | the result callback will not be caught and cause undefined behaviour. |
|
|
950 | |
403 | =head1 SEE ALSO |
951 | =head1 SEE ALSO |
404 | |
952 | |
405 | L<AnyEvent::Fork> (to create the processes in the first place), |
953 | L<AnyEvent::Fork>, to create the processes in the first place. |
|
|
954 | |
|
|
955 | L<AnyEvent::Fork::Remote>, likewise, but helpful for remote processes. |
|
|
956 | |
406 | L<AnyEvent::Fork::Pool> (to manage whole pools of processes). |
957 | L<AnyEvent::Fork::Pool>, to manage whole pools of processes. |
407 | |
958 | |
408 | =head1 AUTHOR AND CONTACT INFORMATION |
959 | =head1 AUTHOR AND CONTACT INFORMATION |
409 | |
960 | |
410 | Marc Lehmann <schmorp@schmorp.de> |
961 | Marc Lehmann <schmorp@schmorp.de> |
411 | http://software.schmorp.de/pkg/AnyEvent-Fork-RPC |
962 | http://software.schmorp.de/pkg/AnyEvent-Fork-RPC |