[ViewVC] Diff of: cvs/AnyEvent/lib/AnyEvent.pm

Comparing AnyEvent/lib/AnyEvent.pm (file contents):
Revision 1.56 by root, Thu Apr 24 03:10:03 2008 UTC vs.
Revision 1.102 by root, Sun Apr 27 21:16:26 2008 UTC

…		…
1	=head1 NAME	1	=head1 NAME
2		2
3	AnyEvent - provide framework for multiple event loops	3	AnyEvent - provide framework for multiple event loops
4		4
5	EV, Event, Coro::EV, Coro::Event, Glib, Tk, Perl, Event::Lib, Qt - various supported event loops	5	EV, Event, Coro::EV, Coro::Event, Glib, Tk, Perl, Event::Lib, Qt, POE - various supported event loops
6		6
7	=head1 SYNOPSIS	7	=head1 SYNOPSIS
8		8
9	use AnyEvent;	9	use AnyEvent;
10		10
66		66
67	Of course, if you want lots of policy (this can arguably be somewhat	67	Of course, if you want lots of policy (this can arguably be somewhat
68	useful) and you want to force your users to use the one and only event	68	useful) and you want to force your users to use the one and only event
69	model, you should I<not> use this module.	69	model, you should I<not> use this module.
70		70
71
72	=head1 DESCRIPTION	71	=head1 DESCRIPTION
73		72
74	L<AnyEvent> provides an identical interface to multiple event loops. This	73	L<AnyEvent> provides an identical interface to multiple event loops. This
75	allows module authors to utilise an event loop without forcing module	74	allows module authors to utilise an event loop without forcing module
76	users to use the same event loop (as only a single event loop can coexist	75	users to use the same event loop (as only a single event loop can coexist
…		…
80	module.	79	module.
81		80
82	During the first call of any watcher-creation method, the module tries	81	During the first call of any watcher-creation method, the module tries
83	to detect the currently loaded event loop by probing whether one of the	82	to detect the currently loaded event loop by probing whether one of the
84	following modules is already loaded: L<Coro::EV>, L<Coro::Event>, L<EV>,	83	following modules is already loaded: L<Coro::EV>, L<Coro::Event>, L<EV>,
85	L<Event>, L<Glib>, L<Tk>. The first one found is used. If none are found,	84	L<Event>, L<Glib>, L<AnyEvent::Impl::Perl>, L<Tk>, L<Event::Lib>, L<Qt>,
86	the module tries to load these modules in the stated order. The first one	85	L<POE>. The first one found is used. If none are found, the module tries
		86	to load these modules (excluding Tk, Event::Lib, Qt and POE as the pure perl
		87	adaptor should always succeed) in the order given. The first one that can
87	that can be successfully loaded will be used. If, after this, still none	88	be successfully loaded will be used. If, after this, still none could be
88	could be found, AnyEvent will fall back to a pure-perl event loop, which	89	found, AnyEvent will fall back to a pure-perl event loop, which is not
89	is not very efficient, but should work everywhere.	90	very efficient, but should work everywhere.
90		91
91	Because AnyEvent first checks for modules that are already loaded, loading	92	Because AnyEvent first checks for modules that are already loaded, loading
92	an event model explicitly before first using AnyEvent will likely make	93	an event model explicitly before first using AnyEvent will likely make
93	that model the default. For example:	94	that model the default. For example:
94		95
…		…
134		135
135	Note that C<my $w; $w => combination. This is necessary because in Perl,	136	Note that C<my $w; $w => combination. This is necessary because in Perl,
136	my variables are only visible after the statement in which they are	137	my variables are only visible after the statement in which they are
137	declared.	138	declared.
138		139
139	=head2 IO WATCHERS	140	=head2 I/O WATCHERS
140		141
141	You can create an I/O watcher by calling the C<< AnyEvent->io >> method	142	You can create an I/O watcher by calling the C<< AnyEvent->io >> method
142	with the following mandatory key-value pairs as arguments:	143	with the following mandatory key-value pairs as arguments:
143		144
144	C<fh> the Perl I<file handle> (I<not> file descriptor) to watch for	145	C<fh> the Perl I<file handle> (I<not> file descriptor) to watch
145	events. C<poll> must be a string that is either C<r> or C<w>, which	146	for events. C<poll> must be a string that is either C<r> or C<w>,
146	creates a watcher waiting for "r"eadable or "w"ritable events,	147	which creates a watcher waiting for "r"eadable or "w"ritable events,
147	respectively. C<cb> is the callback to invoke each time the file handle	148	respectively. C<cb> is the callback to invoke each time the file handle
148	becomes ready.	149	becomes ready.
149		150
150	As long as the I/O watcher exists it will keep the file descriptor or a	151	Although the callback might get passed parameters, their value and
151	copy of it alive/open.	152	presence is undefined and you cannot rely on them. Portable AnyEvent
		153	callbacks cannot use arguments passed to I/O watcher callbacks.
152		154
		155	The I/O watcher might use the underlying file descriptor or a copy of it.
153	It is not allowed to close a file handle as long as any watcher is active	156	You must not close a file handle as long as any watcher is active on the
154	on the underlying file descriptor.	157	underlying file descriptor.
155		158
156	Some event loops issue spurious readyness notifications, so you should	159	Some event loops issue spurious readyness notifications, so you should
157	always use non-blocking calls when reading/writing from/to your file	160	always use non-blocking calls when reading/writing from/to your file
158	handles.	161	handles.
159		162
…		…
170		173
171	You can create a time watcher by calling the C<< AnyEvent->timer >>	174	You can create a time watcher by calling the C<< AnyEvent->timer >>
172	method with the following mandatory arguments:	175	method with the following mandatory arguments:
173		176
174	C<after> specifies after how many seconds (fractional values are	177	C<after> specifies after how many seconds (fractional values are
175	supported) should the timer activate. C<cb> the callback to invoke in that	178	supported) the callback should be invoked. C<cb> is the callback to invoke
176	case.	179	in that case.
		180
		181	Although the callback might get passed parameters, their value and
		182	presence is undefined and you cannot rely on them. Portable AnyEvent
		183	callbacks cannot use arguments passed to time watcher callbacks.
177		184
178	The timer callback will be invoked at most once: if you want a repeating	185	The timer callback will be invoked at most once: if you want a repeating
179	timer you have to create a new watcher (this is a limitation by both Tk	186	timer you have to create a new watcher (this is a limitation by both Tk
180	and Glib).	187	and Glib).
181		188
…		…
206		213
207	There are two ways to handle timers: based on real time (relative, "fire	214	There are two ways to handle timers: based on real time (relative, "fire
208	in 10 seconds") and based on wallclock time (absolute, "fire at 12	215	in 10 seconds") and based on wallclock time (absolute, "fire at 12
209	o'clock").	216	o'clock").
210		217
211	While most event loops expect timers to specified in a relative way, they use	218	While most event loops expect timers to specified in a relative way, they
212	absolute time internally. This makes a difference when your clock "jumps",	219	use absolute time internally. This makes a difference when your clock
213	for example, when ntp decides to set your clock backwards from the wrong 2014-01-01 to	220	"jumps", for example, when ntp decides to set your clock backwards from
214	2008-01-01, a watcher that you created to fire "after" a second might actually take	221	the wrong date of 2014-01-01 to 2008-01-01, a watcher that is supposed to
215	six years to finally fire.	222	fire "after" a second might actually take six years to finally fire.
216		223
217	AnyEvent cannot compensate for this. The only event loop that is conscious	224	AnyEvent cannot compensate for this. The only event loop that is conscious
218	about these issues is L<EV>, which offers both relative (ev_timer) and	225	about these issues is L<EV>, which offers both relative (ev_timer, based
219	absolute (ev_periodic) timers.	226	on true relative time) and absolute (ev_periodic, based on wallclock time)
		227	timers.
220		228
221	AnyEvent always prefers relative timers, if available, matching the	229	AnyEvent always prefers relative timers, if available, matching the
222	AnyEvent API.	230	AnyEvent API.
223		231
224	=head2 SIGNAL WATCHERS	232	=head2 SIGNAL WATCHERS
225		233
226	You can watch for signals using a signal watcher, C<signal> is the signal	234	You can watch for signals using a signal watcher, C<signal> is the signal
227	I<name> without any C<SIG> prefix, C<cb> is the Perl callback to	235	I<name> without any C<SIG> prefix, C<cb> is the Perl callback to
228	be invoked whenever a signal occurs.	236	be invoked whenever a signal occurs.
229		237
		238	Although the callback might get passed parameters, their value and
		239	presence is undefined and you cannot rely on them. Portable AnyEvent
		240	callbacks cannot use arguments passed to signal watcher callbacks.
		241
230	Multiple signals occurances can be clumped together into one callback	242	Multiple signal occurances can be clumped together into one callback
231	invocation, and callback invocation will be synchronous. synchronous means	243	invocation, and callback invocation will be synchronous. synchronous means
232	that it might take a while until the signal gets handled by the process,	244	that it might take a while until the signal gets handled by the process,
233	but it is guarenteed not to interrupt any other callbacks.	245	but it is guarenteed not to interrupt any other callbacks.
234		246
235	The main advantage of using these watchers is that you can share a signal	247	The main advantage of using these watchers is that you can share a signal
…		…
248		260
249	The child process is specified by the C<pid> argument (if set to C<0>, it	261	The child process is specified by the C<pid> argument (if set to C<0>, it
250	watches for any child process exit). The watcher will trigger as often	262	watches for any child process exit). The watcher will trigger as often
251	as status change for the child are received. This works by installing a	263	as status change for the child are received. This works by installing a
252	signal handler for C<SIGCHLD>. The callback will be called with the pid	264	signal handler for C<SIGCHLD>. The callback will be called with the pid
253	and exit status (as returned by waitpid).	265	and exit status (as returned by waitpid), so unlike other watcher types,
		266	you I<can> rely on child watcher callback arguments.
254		267
255	Example: wait for pid 1333	268	There is a slight catch to child watchers, however: you usually start them
		269	I<after> the child process was created, and this means the process could
		270	have exited already (and no SIGCHLD will be sent anymore).
		271
		272	Not all event models handle this correctly (POE doesn't), but even for
		273	event models that I<do> handle this correctly, they usually need to be
		274	loaded before the process exits (i.e. before you fork in the first place).
		275
		276	This means you cannot create a child watcher as the very first thing in an
		277	AnyEvent program, you I<have> to create at least one watcher before you
		278	C<fork> the child (alternatively, you can call C<AnyEvent::detect>).
		279
		280	Example: fork a process and wait for it
		281
		282	my $done = AnyEvent->condvar;
		283
		284	AnyEvent::detect; # force event module to be initialised
		285
		286	my $pid = fork or exit 5;
256		287
257	my $w = AnyEvent->child (	288	my $w = AnyEvent->child (
258	pid => 1333,	289	pid => $pid,
259	cb => sub {	290	cb => sub {
260	my ($pid, $status) = @_;	291	my ($pid, $status) = @_;
261	warn "pid $pid exited with status $status";	292	warn "pid $pid exited with status $status";
		293	$done->broadcast;
262	},	294	},
263	);	295	);
		296
		297	# do something else, then wait for process exit
		298	$done->wait;
264		299
265	=head2 CONDITION VARIABLES	300	=head2 CONDITION VARIABLES
266		301
267	Condition variables can be created by calling the C<< AnyEvent->condvar >>	302	Condition variables can be created by calling the C<< AnyEvent->condvar >>
268	method without any arguments.	303	method without any arguments.
…		…
356	AnyEvent::Impl::CoroEV based on Coro::EV, best choice.	391	AnyEvent::Impl::CoroEV based on Coro::EV, best choice.
357	AnyEvent::Impl::CoroEvent based on Coro::Event, second best choice.	392	AnyEvent::Impl::CoroEvent based on Coro::Event, second best choice.
358	AnyEvent::Impl::EV based on EV (an interface to libev, best choice).	393	AnyEvent::Impl::EV based on EV (an interface to libev, best choice).
359	AnyEvent::Impl::Event based on Event, second best choice.	394	AnyEvent::Impl::Event based on Event, second best choice.
360	AnyEvent::Impl::Glib based on Glib, third-best choice.	395	AnyEvent::Impl::Glib based on Glib, third-best choice.
		396	AnyEvent::Impl::Perl pure-perl implementation, inefficient but portable.
361	AnyEvent::Impl::Tk based on Tk, very bad choice.	397	AnyEvent::Impl::Tk based on Tk, very bad choice.
362	AnyEvent::Impl::Perl pure-perl implementation, inefficient but portable.
363	AnyEvent::Impl::Qt based on Qt, cannot be autoprobed (see its docs).	398	AnyEvent::Impl::Qt based on Qt, cannot be autoprobed (see its docs).
364	AnyEvent::Impl::EventLib based on Event::Lib, leaks memory and worse.	399	AnyEvent::Impl::EventLib based on Event::Lib, leaks memory and worse.
		400	AnyEvent::Impl::POE based on POE, not generic enough for full support.
		401
		402	There is no support for WxWidgets, as WxWidgets has no support for
		403	watching file handles. However, you can use WxWidgets through the
		404	POE Adaptor, as POE has a Wx backend that simply polls 20 times per
		405	second, which was considered to be too horrible to even consider for
		406	AnyEvent. Likewise, other POE backends can be used by AnyEvent by using
		407	it's adaptor.
		408
		409	AnyEvent knows about L<Prima> and L<Wx> and will try to use L<POE> when
		410	autodetecting them.
365		411
366	=item AnyEvent::detect	412	=item AnyEvent::detect
367		413
368	Returns C<$AnyEvent::MODEL>, forcing autodetection of the event model	414	Returns C<$AnyEvent::MODEL>, forcing autodetection of the event model
369	if necessary. You should only call this function right before you would	415	if necessary. You should only call this function right before you would
…		…
411		457
412	You can chose to use a rather inefficient pure-perl implementation by	458	You can chose to use a rather inefficient pure-perl implementation by
413	loading the C<AnyEvent::Impl::Perl> module, which gives you similar	459	loading the C<AnyEvent::Impl::Perl> module, which gives you similar
414	behaviour everywhere, but letting AnyEvent chose is generally better.	460	behaviour everywhere, but letting AnyEvent chose is generally better.
415		461
		462	=head1 OTHER MODULES
		463
		464	The following is a non-exhaustive list of additional modules that use
		465	AnyEvent and can therefore be mixed easily with other AnyEvent modules
		466	in the same program. Some of the modules come with AnyEvent, some are
		467	available via CPAN.
		468
		469	=over 4
		470
		471	=item L<AnyEvent::Util>
		472
		473	Contains various utility functions that replace often-used but blocking
		474	functions such as C<inet_aton> by event-/callback-based versions.
		475
		476	=item L<AnyEvent::Handle>
		477
		478	Provide read and write buffers and manages watchers for reads and writes.
		479
		480	=item L<AnyEvent::Socket>
		481
		482	Provides a means to do non-blocking connects, accepts etc.
		483
		484	=item L<AnyEvent::HTTPD>
		485
		486	Provides a simple web application server framework.
		487
		488	=item L<AnyEvent::DNS>
		489
		490	Provides asynchronous DNS resolver capabilities, beyond what
		491	L<AnyEvent::Util> offers.
		492
		493	=item L<AnyEvent::FastPing>
		494
		495	The fastest ping in the west.
		496
		497	=item L<Net::IRC3>
		498
		499	AnyEvent based IRC client module family.
		500
		501	=item L<Net::XMPP2>
		502
		503	AnyEvent based XMPP (Jabber protocol) module family.
		504
		505	=item L<Net::FCP>
		506
		507	AnyEvent-based implementation of the Freenet Client Protocol, birthplace
		508	of AnyEvent.
		509
		510	=item L<Event::ExecFlow>
		511
		512	High level API for event-based execution flow control.
		513
		514	=item L<Coro>
		515
		516	Has special support for AnyEvent.
		517
		518	=item L<IO::Lambda>
		519
		520	The lambda approach to I/O - don't ask, look there. Can use AnyEvent.
		521
		522	=item L<IO::AIO>
		523
		524	Truly asynchronous I/O, should be in the toolbox of every event
		525	programmer. Can be trivially made to use AnyEvent.
		526
		527	=item L<BDB>
		528
		529	Truly asynchronous Berkeley DB access. Can be trivially made to use
		530	AnyEvent.
		531
		532	=back
		533
416	=cut	534	=cut
417		535
418	package AnyEvent;	536	package AnyEvent;
419		537
420	no warnings;	538	no warnings;
421	use strict;	539	use strict;
422		540
423	use Carp;	541	use Carp;
424		542
425	our $VERSION = '3.12';	543	our $VERSION = '3.3';
426	our $MODEL;	544	our $MODEL;
427		545
428	our $AUTOLOAD;	546	our $AUTOLOAD;
429	our @ISA;	547	our @ISA;
430		548
…		…
437	[Coro::Event:: => AnyEvent::Impl::CoroEvent::],	555	[Coro::Event:: => AnyEvent::Impl::CoroEvent::],
438	[EV:: => AnyEvent::Impl::EV::],	556	[EV:: => AnyEvent::Impl::EV::],
439	[Event:: => AnyEvent::Impl::Event::],	557	[Event:: => AnyEvent::Impl::Event::],
440	[Glib:: => AnyEvent::Impl::Glib::],	558	[Glib:: => AnyEvent::Impl::Glib::],
441	[Tk:: => AnyEvent::Impl::Tk::],	559	[Tk:: => AnyEvent::Impl::Tk::],
		560	[Wx:: => AnyEvent::Impl::POE::],
		561	[Prima:: => AnyEvent::Impl::POE::],
442	[AnyEvent::Impl::Perl:: => AnyEvent::Impl::Perl::],	562	[AnyEvent::Impl::Perl:: => AnyEvent::Impl::Perl::],
443	);	563	# everything below here will not be autoprobed as the pureperl backend should work everywhere
444	my @models_detect = (	564	[Event::Lib:: => AnyEvent::Impl::EventLib::], # too buggy
445	[Qt:: => AnyEvent::Impl::Qt::], # requires special main program	565	[Qt:: => AnyEvent::Impl::Qt::], # requires special main program
446	[Event::Lib:: => AnyEvent::Impl::EventLib::], # too buggy	566	[POE::Kernel:: => AnyEvent::Impl::POE::], # lasciate ogni speranza
447	);	567	);
448		568
449	our %method = map +($_ => 1), qw(io timer signal child condvar broadcast wait one_event DESTROY);	569	our %method = map +($_ => 1), qw(io timer signal child condvar broadcast wait one_event DESTROY);
450		570
451	sub detect() {	571	sub detect() {
…		…
455	if ($ENV{PERL_ANYEVENT_MODEL} =~ /^([a-zA-Z]+)$/) {	575	if ($ENV{PERL_ANYEVENT_MODEL} =~ /^([a-zA-Z]+)$/) {
456	my $model = "AnyEvent::Impl::$1";	576	my $model = "AnyEvent::Impl::$1";
457	if (eval "require $model") {	577	if (eval "require $model") {
458	$MODEL = $model;	578	$MODEL = $model;
459	warn "AnyEvent: loaded model '$model' (forced by \$PERL_ANYEVENT_MODEL), using it.\n" if $verbose > 1;	579	warn "AnyEvent: loaded model '$model' (forced by \$PERL_ANYEVENT_MODEL), using it.\n" if $verbose > 1;
		580	} else {
		581	warn "AnyEvent: unable to load model '$model' (from \$PERL_ANYEVENT_MODEL):\n$@" if $verbose;
460	}	582	}
461	}	583	}
462		584
463	# check for already loaded models	585	# check for already loaded models
464	unless ($MODEL) {	586	unless ($MODEL) {
465	for (@REGISTRY, @models, @models_detect) {	587	for (@REGISTRY, @models) {
466	my ($package, $model) = @$_;	588	my ($package, $model) = @$_;
467	if (${"$package\::VERSION"} > 0) {	589	if (${"$package\::VERSION"} > 0) {
468	if (eval "require $model") {	590	if (eval "require $model") {
469	$MODEL = $model;	591	$MODEL = $model;
470	warn "AnyEvent: autodetected model '$model', using it.\n" if $verbose > 1;	592	warn "AnyEvent: autodetected model '$model', using it.\n" if $verbose > 1;
…		…
657		779
658	=over 4	780	=over 4
659		781
660	=item C<PERL_ANYEVENT_VERBOSE>	782	=item C<PERL_ANYEVENT_VERBOSE>
661		783
		784	By default, AnyEvent will be completely silent except in fatal
		785	conditions. You can set this environment variable to make AnyEvent more
		786	talkative.
		787
		788	When set to C<1> or higher, causes AnyEvent to warn about unexpected
		789	conditions, such as not being able to load the event model specified by
		790	C<PERL_ANYEVENT_MODEL>.
		791
662	When set to C<2> or higher, cause AnyEvent to report to STDERR which event	792	When set to C<2> or higher, cause AnyEvent to report to STDERR which event
663	model it chooses.	793	model it chooses.
664		794
665	=item C<PERL_ANYEVENT_MODEL>	795	=item C<PERL_ANYEVENT_MODEL>
666		796
…		…
680		810
681	=back	811	=back
682		812
683	=head1 EXAMPLE PROGRAM	813	=head1 EXAMPLE PROGRAM
684		814
685	The following program uses an IO watcher to read data from STDIN, a timer	815	The following program uses an I/O watcher to read data from STDIN, a timer
686	to display a message once per second, and a condition variable to quit the	816	to display a message once per second, and a condition variable to quit the
687	program when the user enters quit:	817	program when the user enters quit:
688		818
689	use AnyEvent;	819	use AnyEvent;
690		820
…		…
834	$quit->broadcast;	964	$quit->broadcast;
835	});	965	});
836		966
837	$quit->wait;	967	$quit->wait;
838		968
		969
		970	=head1 BENCHMARKS
		971
		972	To give you an idea of the performance and overheads that AnyEvent adds
		973	over the event loops themselves and to give you an impression of the speed
		974	of various event loops I prepared some benchmarks.
		975
		976	=head2 BENCHMARKING ANYEVENT OVERHEAD
		977
		978	Here is a benchmark of various supported event models used natively and
		979	through anyevent. The benchmark creates a lot of timers (with a zero
		980	timeout) and I/O watchers (watching STDOUT, a pty, to become writable,
		981	which it is), lets them fire exactly once and destroys them again.
		982
		983	Source code for this benchmark is found as F<eg/bench> in the AnyEvent
		984	distribution.
		985
		986	=head3 Explanation of the columns
		987
		988	I<watcher> is the number of event watchers created/destroyed. Since
		989	different event models feature vastly different performances, each event
		990	loop was given a number of watchers so that overall runtime is acceptable
		991	and similar between tested event loop (and keep them from crashing): Glib
		992	would probably take thousands of years if asked to process the same number
		993	of watchers as EV in this benchmark.
		994
		995	I<bytes> is the number of bytes (as measured by the resident set size,
		996	RSS) consumed by each watcher. This method of measuring captures both C
		997	and Perl-based overheads.
		998
		999	I<create> is the time, in microseconds (millionths of seconds), that it
		1000	takes to create a single watcher. The callback is a closure shared between
		1001	all watchers, to avoid adding memory overhead. That means closure creation
		1002	and memory usage is not included in the figures.
		1003
		1004	I<invoke> is the time, in microseconds, used to invoke a simple
		1005	callback. The callback simply counts down a Perl variable and after it was
		1006	invoked "watcher" times, it would C<< ->broadcast >> a condvar once to
		1007	signal the end of this phase.
		1008
		1009	I<destroy> is the time, in microseconds, that it takes to destroy a single
		1010	watcher.
		1011
		1012	=head3 Results
		1013
		1014	name watchers bytes create invoke destroy comment
		1015	EV/EV 400000 244 0.56 0.46 0.31 EV native interface
		1016	EV/Any 100000 244 2.50 0.46 0.29 EV + AnyEvent watchers
		1017	CoroEV/Any 100000 244 2.49 0.44 0.29 coroutines + Coro::Signal
		1018	Perl/Any 100000 513 4.92 0.87 1.12 pure perl implementation
		1019	Event/Event 16000 516 31.88 31.30 0.85 Event native interface
		1020	Event/Any 16000 590 35.75 31.42 1.08 Event + AnyEvent watchers
		1021	Glib/Any 16000 1357 98.22 12.41 54.00 quadratic behaviour
		1022	Tk/Any 2000 1860 26.97 67.98 14.00 SEGV with >> 2000 watchers
		1023	POE/Event 2000 6644 108.64 736.02 14.73 via POE::Loop::Event
		1024	POE/Select 2000 6343 94.13 809.12 565.96 via POE::Loop::Select
		1025
		1026	=head3 Discussion
		1027
		1028	The benchmark does I<not> measure scalability of the event loop very
		1029	well. For example, a select-based event loop (such as the pure perl one)
		1030	can never compete with an event loop that uses epoll when the number of
		1031	file descriptors grows high. In this benchmark, all events become ready at
		1032	the same time, so select/poll-based implementations get an unnatural speed
		1033	boost.
		1034
		1035	Also, note that the number of watchers usually has a nonlinear effect on
		1036	overall speed, that is, creating twice as many watchers doesn't take twice
		1037	the time - usually it takes longer. This puts event loops tested with a
		1038	higher number of watchers at a disadvantage.
		1039
		1040	To put the range of results into perspective, consider that on the
		1041	benchmark machine, handling an event takes roughly 1600 CPU cycles with
		1042	EV, 3100 CPU cycles with AnyEvent's pure perl loop and almost 3000000 CPU
		1043	cycles with POE.
		1044
		1045	C<EV> is the sole leader regarding speed and memory use, which are both
		1046	maximal/minimal, respectively. Even when going through AnyEvent, it uses
		1047	far less memory than any other event loop and is still faster than Event
		1048	natively.
		1049
		1050	The pure perl implementation is hit in a few sweet spots (both the
		1051	constant timeout and the use of a single fd hit optimisations in the perl
		1052	interpreter and the backend itself). Nevertheless this shows that it
		1053	adds very little overhead in itself. Like any select-based backend its
		1054	performance becomes really bad with lots of file descriptors (and few of
		1055	them active), of course, but this was not subject of this benchmark.
		1056
		1057	The C<Event> module has a relatively high setup and callback invocation
		1058	cost, but overall scores in on the third place.
		1059
		1060	C<Glib>'s memory usage is quite a bit higher, but it features a
		1061	faster callback invocation and overall ends up in the same class as
		1062	C<Event>. However, Glib scales extremely badly, doubling the number of
		1063	watchers increases the processing time by more than a factor of four,
		1064	making it completely unusable when using larger numbers of watchers
		1065	(note that only a single file descriptor was used in the benchmark, so
		1066	inefficiencies of C<poll> do not account for this).
		1067
		1068	The C<Tk> adaptor works relatively well. The fact that it crashes with
		1069	more than 2000 watchers is a big setback, however, as correctness takes
		1070	precedence over speed. Nevertheless, its performance is surprising, as the
		1071	file descriptor is dup()ed for each watcher. This shows that the dup()
		1072	employed by some adaptors is not a big performance issue (it does incur a
		1073	hidden memory cost inside the kernel which is not reflected in the figures
		1074	above).
		1075
		1076	C<POE>, regardless of underlying event loop (whether using its pure
		1077	perl select-based backend or the Event module, the POE-EV backend
		1078	couldn't be tested because it wasn't working) shows abysmal performance
		1079	and memory usage: Watchers use almost 30 times as much memory as
		1080	EV watchers, and 10 times as much memory as Event (the high memory
		1081	requirements are caused by requiring a session for each watcher). Watcher
		1082	invocation speed is almost 900 times slower than with AnyEvent's pure perl
		1083	implementation. The design of the POE adaptor class in AnyEvent can not
		1084	really account for this, as session creation overhead is small compared
		1085	to execution of the state machine, which is coded pretty optimally within
		1086	L<AnyEvent::Impl::POE>. POE simply seems to be abysmally slow.
		1087
		1088	=head3 Summary
		1089
		1090	=over 4
		1091
		1092	=item * Using EV through AnyEvent is faster than any other event loop
		1093	(even when used without AnyEvent), but most event loops have acceptable
		1094	performance with or without AnyEvent.
		1095
		1096	=item * The overhead AnyEvent adds is usually much smaller than the overhead of
		1097	the actual event loop, only with extremely fast event loops such as EV
		1098	adds AnyEvent significant overhead.
		1099
		1100	=item * You should avoid POE like the plague if you want performance or
		1101	reasonable memory usage.
		1102
		1103	=back
		1104
		1105	=head2 BENCHMARKING THE LARGE SERVER CASE
		1106
		1107	This benchmark atcually benchmarks the event loop itself. It works by
		1108	creating a number of "servers": each server consists of a socketpair, a
		1109	timeout watcher that gets reset on activity (but never fires), and an I/O
		1110	watcher waiting for input on one side of the socket. Each time the socket
		1111	watcher reads a byte it will write that byte to a random other "server".
		1112
		1113	The effect is that there will be a lot of I/O watchers, only part of which
		1114	are active at any one point (so there is a constant number of active
		1115	fds for each loop iterstaion, but which fds these are is random). The
		1116	timeout is reset each time something is read because that reflects how
		1117	most timeouts work (and puts extra pressure on the event loops).
		1118
		1119	In this benchmark, we use 10000 socketpairs (20000 sockets), of which 100
		1120	(1%) are active. This mirrors the activity of large servers with many
		1121	connections, most of which are idle at any one point in time.
		1122
		1123	Source code for this benchmark is found as F<eg/bench2> in the AnyEvent
		1124	distribution.
		1125
		1126	=head3 Explanation of the columns
		1127
		1128	I<sockets> is the number of sockets, and twice the number of "servers" (as
		1129	each server has a read and write socket end).
		1130
		1131	I<create> is the time it takes to create a socketpair (which is
		1132	nontrivial) and two watchers: an I/O watcher and a timeout watcher.
		1133
		1134	I<request>, the most important value, is the time it takes to handle a
		1135	single "request", that is, reading the token from the pipe and forwarding
		1136	it to another server. This includes deleting the old timeout and creating
		1137	a new one that moves the timeout into the future.
		1138
		1139	=head3 Results
		1140
		1141	name sockets create request
		1142	EV 20000 69.01 11.16
		1143	Perl 20000 73.32 35.87
		1144	Event 20000 212.62 257.32
		1145	Glib 20000 651.16 1896.30
		1146	POE 20000 349.67 12317.24 uses POE::Loop::Event
		1147
		1148	=head3 Discussion
		1149
		1150	This benchmark I<does> measure scalability and overall performance of the
		1151	particular event loop.
		1152
		1153	EV is again fastest. Since it is using epoll on my system, the setup time
		1154	is relatively high, though.
		1155
		1156	Perl surprisingly comes second. It is much faster than the C-based event
		1157	loops Event and Glib.
		1158
		1159	Event suffers from high setup time as well (look at its code and you will
		1160	understand why). Callback invocation also has a high overhead compared to
		1161	the C<< $_->() for .. >>-style loop that the Perl event loop uses. Event
		1162	uses select or poll in basically all documented configurations.
		1163
		1164	Glib is hit hard by its quadratic behaviour w.r.t. many watchers. It
		1165	clearly fails to perform with many filehandles or in busy servers.
		1166
		1167	POE is still completely out of the picture, taking over 1000 times as long
		1168	as EV, and over 100 times as long as the Perl implementation, even though
		1169	it uses a C-based event loop in this case.
		1170
		1171	=head3 Summary
		1172
		1173	=over 4
		1174
		1175	=item * The pure perl implementation performs extremely well, considering
		1176	that it uses select.
		1177
		1178	=item * Avoid Glib or POE in large projects where performance matters.
		1179
		1180	=back
		1181
		1182	=head2 BENCHMARKING SMALL SERVERS
		1183
		1184	While event loops should scale (and select-based ones do not...) even to
		1185	large servers, most programs we (or I :) actually write have only a few
		1186	I/O watchers.
		1187
		1188	In this benchmark, I use the same benchmark program as in the large server
		1189	case, but it uses only eight "servers", of which three are active at any
		1190	one time. This should reflect performance for a small server relatively
		1191	well.
		1192
		1193	The columns are identical to the previous table.
		1194
		1195	=head3 Results
		1196
		1197	name sockets create request
		1198	EV 16 20.00 6.54
		1199	Perl 16 25.75 12.62
		1200	Event 16 81.27 35.86
		1201	Glib 16 32.63 15.48
		1202	POE 16 261.87 276.28 uses POE::Loop::Event
		1203
		1204	=head3 Discussion
		1205
		1206	The benchmark tries to test the performance of a typical small
		1207	server. While knowing how various event loops perform is interesting, keep
		1208	in mind that their overhead in this case is usually not as important, due
		1209	to the small absolute number of watchers (that is, you need efficiency and
		1210	speed most when you have lots of watchers, not when you only have a few of
		1211	them).
		1212
		1213	EV is again fastest.
		1214
		1215	Perl again comes second. It is noticably faster than the C-based event
		1216	loops Event and Glib, although the difference is too small to really
		1217	matter.
		1218
		1219	POE also performs much better in this case, but is is still far behind the
		1220	others.
		1221
		1222	=head3 Summary
		1223
		1224	=over 4
		1225
		1226	=item * C-based event loops perform very well with small number of
		1227	watchers, as the management overhead dominates.
		1228
		1229	=back
		1230
		1231
839	=head1 FORK	1232	=head1 FORK
840		1233
841	Most event libraries are not fork-safe. The ones who are usually are	1234	Most event libraries are not fork-safe. The ones who are usually are
842	because they are so inefficient. Only L<EV> is fully fork-aware.	1235	because they are so inefficient. Only L<EV> is fully fork-aware.
843		1236
844	If you have to fork, you must either do so I<before> creating your first	1237	If you have to fork, you must either do so I<before> creating your first
845	watcher OR you must not use AnyEvent at all in the child.	1238	watcher OR you must not use AnyEvent at all in the child.
		1239
846		1240
847	=head1 SECURITY CONSIDERATIONS	1241	=head1 SECURITY CONSIDERATIONS
848		1242
849	AnyEvent can be forced to load any event model via	1243	AnyEvent can be forced to load any event model via
850	$ENV{PERL_ANYEVENT_MODEL}. While this cannot (to my knowledge) be used to	1244	$ENV{PERL_ANYEVENT_MODEL}. While this cannot (to my knowledge) be used to
…		…
858		1252
859	BEGIN { delete $ENV{PERL_ANYEVENT_MODEL} }	1253	BEGIN { delete $ENV{PERL_ANYEVENT_MODEL} }
860		1254
861	use AnyEvent;	1255	use AnyEvent;
862		1256
		1257
863	=head1 SEE ALSO	1258	=head1 SEE ALSO
864		1259
865	Event modules: L<Coro::EV>, L<EV>, L<EV::Glib>, L<Glib::EV>,	1260	Event modules: L<Coro::EV>, L<EV>, L<EV::Glib>, L<Glib::EV>,
866	L<Coro::Event>, L<Event>, L<Glib::Event>, L<Glib>, L<Coro>, L<Tk>,	1261	L<Coro::Event>, L<Event>, L<Glib::Event>, L<Glib>, L<Coro>, L<Tk>,
867	L<Event::Lib>, L<Qt>.	1262	L<Event::Lib>, L<Qt>, L<POE>.
868		1263
869	Implementations: L<AnyEvent::Impl::CoroEV>, L<AnyEvent::Impl::EV>,	1264	Implementations: L<AnyEvent::Impl::CoroEV>, L<AnyEvent::Impl::EV>,
870	L<AnyEvent::Impl::CoroEvent>, L<AnyEvent::Impl::Event>, L<AnyEvent::Impl::Glib>,	1265	L<AnyEvent::Impl::CoroEvent>, L<AnyEvent::Impl::Event>, L<AnyEvent::Impl::Glib>,
871	L<AnyEvent::Impl::Tk>, L<AnyEvent::Impl::Perl>, L<AnyEvent::Impl::EventLib>,	1266	L<AnyEvent::Impl::Tk>, L<AnyEvent::Impl::Perl>, L<AnyEvent::Impl::EventLib>,
872	L<AnyEvent::Impl::Qt>.	1267	L<AnyEvent::Impl::Qt>, L<AnyEvent::Impl::POE>.
873		1268
874	Nontrivial usage examples: L<Net::FCP>, L<Net::XMPP2>.	1269	Nontrivial usage examples: L<Net::FCP>, L<Net::XMPP2>.
		1270
875		1271
876	=head1 AUTHOR	1272	=head1 AUTHOR
877		1273
878	Marc Lehmann <schmorp@schmorp.de>	1274	Marc Lehmann <schmorp@schmorp.de>
879	http://home.schmorp.de/	1275	http://home.schmorp.de/

Diff Legend

-–
+Removed lines
-+
+Added lines
-<
+Changed lines
->
+Changed lines

Comparing AnyEvent/lib/AnyEvent.pm (file contents): Revision 1.56 by root, Thu Apr 24 03:10:03 2008 UTC vs. Revision 1.102 by root, Sun Apr 27 21:16:26 2008 UTC

Diff Legend

Comparing AnyEvent/lib/AnyEvent.pm (file contents):
Revision 1.56 by root, Thu Apr 24 03:10:03 2008 UTC vs.
Revision 1.102 by root, Sun Apr 27 21:16:26 2008 UTC