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

Comparing AnyEvent/lib/AnyEvent.pm (file contents):
Revision 1.80 by root, Fri Apr 25 09:11:59 2008 UTC vs.
Revision 1.104 by root, Wed Apr 30 11:40:22 2008 UTC

…		…
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>, L<AnyEvent::Impl::Perl>, L<Event::Lib>, L<Qt>,	84	L<Event>, L<Glib>, L<AnyEvent::Impl::Perl>, L<Tk>, L<Event::Lib>, L<Qt>,
86	L<POE>. The first one found is used. If none are found, the module tries	85	L<POE>. The first one found is used. If none are found, the module tries
87	to load these modules (excluding Event::Lib, Qt and POE as the pure perl	86	to load these modules (excluding Tk, Event::Lib, Qt and POE as the pure perl
88	adaptor should always succeed) in the order given. The first one that can	87	adaptor should always succeed) in the order given. The first one that can
89	be successfully loaded will be used. If, after this, still none could be	88	be successfully loaded will be used. If, after this, still none could be
90	found, AnyEvent will fall back to a pure-perl event loop, which is not	89	found, AnyEvent will fall back to a pure-perl event loop, which is not
91	very efficient, but should work everywhere.	90	very efficient, but should work everywhere.
92		91
…		…
141	=head2 I/O WATCHERS	140	=head2 I/O WATCHERS
142		141
143	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
144	with the following mandatory key-value pairs as arguments:	143	with the following mandatory key-value pairs as arguments:
145		144
146	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
147	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>,
148	creates a watcher waiting for "r"eadable or "w"ritable events,	147	which creates a watcher waiting for "r"eadable or "w"ritable events,
149	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
150	becomes ready.	149	becomes ready.
151		150
152	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
153	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.
154		154
		155	The I/O watcher might use the underlying file descriptor or a copy of it.
155	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
156	on the underlying file descriptor.	157	underlying file descriptor.
157		158
158	Some event loops issue spurious readyness notifications, so you should	159	Some event loops issue spurious readyness notifications, so you should
159	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
160	handles.	161	handles.
161		162
…		…
172		173
173	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 >>
174	method with the following mandatory arguments:	175	method with the following mandatory arguments:
175		176
176	C<after> specifies after how many seconds (fractional values are	177	C<after> specifies after how many seconds (fractional values are
177	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
178	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.
179		184
180	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
181	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
182	and Glib).	187	and Glib).
183		188
…		…
228		233
229	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
230	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
231	be invoked whenever a signal occurs.	236	be invoked whenever a signal occurs.
232		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
233	Multiple signal occurances can be clumped together into one callback	242	Multiple signal occurances can be clumped together into one callback
234	invocation, and callback invocation will be synchronous. synchronous means	243	invocation, and callback invocation will be synchronous. synchronous means
235	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,
236	but it is guarenteed not to interrupt any other callbacks.	245	but it is guarenteed not to interrupt any other callbacks.
237		246
…		…
251		260
252	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
253	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
254	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
255	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
256	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.
257		267
258	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;
259		287
260	my $w = AnyEvent->child (	288	my $w = AnyEvent->child (
261	pid => 1333,	289	pid => $pid,
262	cb => sub {	290	cb => sub {
263	my ($pid, $status) = @_;	291	my ($pid, $status) = @_;
264	warn "pid $pid exited with status $status";	292	warn "pid $pid exited with status $status";
		293	$done->broadcast;
265	},	294	},
266	);	295	);
		296
		297	# do something else, then wait for process exit
		298	$done->wait;
267		299
268	=head2 CONDITION VARIABLES	300	=head2 CONDITION VARIABLES
269		301
270	Condition variables can be created by calling the C<< AnyEvent->condvar >>	302	Condition variables can be created by calling the C<< AnyEvent->condvar >>
271	method without any arguments.	303	method without any arguments.
…		…
358		390
359	AnyEvent::Impl::CoroEV based on Coro::EV, best choice.	391	AnyEvent::Impl::CoroEV based on Coro::EV, best choice.
360	AnyEvent::Impl::CoroEvent based on Coro::Event, second best choice.	392	AnyEvent::Impl::CoroEvent based on Coro::Event, second best choice.
361	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).
362	AnyEvent::Impl::Event based on Event, second best choice.	394	AnyEvent::Impl::Event based on Event, second best choice.
		395	AnyEvent::Impl::Perl pure-perl implementation, fast and portable.
363	AnyEvent::Impl::Glib based on Glib, third-best choice.	396	AnyEvent::Impl::Glib based on Glib, third-best choice.
364	AnyEvent::Impl::Tk based on Tk, very bad choice.	397	AnyEvent::Impl::Tk based on Tk, very bad choice.
365	AnyEvent::Impl::Perl pure-perl implementation, inefficient but portable.
366	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).
367	AnyEvent::Impl::EventLib based on Event::Lib, leaks memory and worse.	399	AnyEvent::Impl::EventLib based on Event::Lib, leaks memory and worse.
368	AnyEvent::Impl::POE based on POE, not generic enough for full support.	400	AnyEvent::Impl::POE based on POE, not generic enough for full support.
369		401
370	There is no support for WxWidgets, as WxWidgets has no support for	402	There is no support for WxWidgets, as WxWidgets has no support for
…		…
425		457
426	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
427	loading the C<AnyEvent::Impl::Perl> module, which gives you similar	459	loading the C<AnyEvent::Impl::Perl> module, which gives you similar
428	behaviour everywhere, but letting AnyEvent chose is generally better.	460	behaviour everywhere, but letting AnyEvent chose is generally better.
429		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
430	=cut	534	=cut
431		535
432	package AnyEvent;	536	package AnyEvent;
433		537
434	no warnings;	538	no warnings;
…		…
449	my @models = (	553	my @models = (
450	[Coro::EV:: => AnyEvent::Impl::CoroEV::],	554	[Coro::EV:: => AnyEvent::Impl::CoroEV::],
451	[Coro::Event:: => AnyEvent::Impl::CoroEvent::],	555	[Coro::Event:: => AnyEvent::Impl::CoroEvent::],
452	[EV:: => AnyEvent::Impl::EV::],	556	[EV:: => AnyEvent::Impl::EV::],
453	[Event:: => AnyEvent::Impl::Event::],	557	[Event:: => AnyEvent::Impl::Event::],
454	[Glib:: => AnyEvent::Impl::Glib::],
455	[Tk:: => AnyEvent::Impl::Tk::],	558	[Tk:: => AnyEvent::Impl::Tk::],
456	[Wx:: => AnyEvent::Impl::POE::],	559	[Wx:: => AnyEvent::Impl::POE::],
457	[Prima:: => AnyEvent::Impl::POE::],	560	[Prima:: => AnyEvent::Impl::POE::],
458	[AnyEvent::Impl::Perl:: => AnyEvent::Impl::Perl::],	561	[AnyEvent::Impl::Perl:: => AnyEvent::Impl::Perl::],
459	# everything below here will not be autoprobed as the pureperl backend should work everywhere	562	# everything below here will not be autoprobed as the pureperl backend should work everywhere
		563	[Glib:: => AnyEvent::Impl::Glib::],
460	[Event::Lib:: => AnyEvent::Impl::EventLib::], # too buggy	564	[Event::Lib:: => AnyEvent::Impl::EventLib::], # too buggy
461	[Qt:: => AnyEvent::Impl::Qt::], # requires special main program	565	[Qt:: => AnyEvent::Impl::Qt::], # requires special main program
462	[POE::Kernel:: => AnyEvent::Impl::POE::], # lasciate ogni speranza	566	[POE::Kernel:: => AnyEvent::Impl::POE::], # lasciate ogni speranza
463	);	567	);
464		568
…		…
861	});	965	});
862		966
863	$quit->wait;	967	$quit->wait;
864		968
865		969
866	=head1 BENCHMARK	970	=head1 BENCHMARKS
867		971
868	To give you an idea of the performance and overheads that AnyEvent adds	972	To give you an idea of the performance and overheads that AnyEvent adds
869	over the event loops themselves (and to give you an impression of the	973	over the event loops themselves and to give you an impression of the speed
870	speed of various event loops), here is a benchmark of various supported	974	of various event loops I prepared some benchmarks.
871	event models natively and with anyevent. The benchmark creates a lot of	975
872	timers (with a zero timeout) and I/O watchers (watching STDOUT, a pty, to	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,
873	become writable, which it is), lets them fire exactly once and destroys	981	which it is), lets them fire exactly once and destroys them again.
874	them again.
875		982
876	Rewriting the benchmark to use many different sockets instead of using	983	Source code for this benchmark is found as F<eg/bench> in the AnyEvent
877	the same filehandle for all I/O watchers results in a much longer runtime	984	distribution.
878	(socket creation is expensive), but qualitatively the same figures, so it
879	was not used.
880		985
881	=head2 Explanation of the columns	986	=head3 Explanation of the columns
882		987
883	I<watcher> is the number of event watchers created/destroyed. Since	988	I<watcher> is the number of event watchers created/destroyed. Since
884	different event models feature vastly different performances, each event	989	different event models feature vastly different performances, each event
885	loop was given a number of watchers so that overall runtime is acceptable	990	loop was given a number of watchers so that overall runtime is acceptable
886	and similar between tested event loop (and keep them from crashing): Glib	991	and similar between tested event loop (and keep them from crashing): Glib
…		…
902	signal the end of this phase.	1007	signal the end of this phase.
903		1008
904	I<destroy> is the time, in microseconds, that it takes to destroy a single	1009	I<destroy> is the time, in microseconds, that it takes to destroy a single
905	watcher.	1010	watcher.
906		1011
907	=head2 Results	1012	=head3 Results
908		1013
909	name watchers bytes create invoke destroy comment	1014	name watchers bytes create invoke destroy comment
910	EV/EV 400000 244 0.56 0.46 0.31 EV native interface	1015	EV/EV 400000 244 0.56 0.46 0.31 EV native interface
911	EV/Any 100000 610 3.52 0.91 0.75 EV + AnyEvent watchers	1016	EV/Any 100000 244 2.50 0.46 0.29 EV + AnyEvent watchers
912	CoroEV/Any 100000 610 3.49 0.92 0.75 coroutines + Coro::Signal	1017	CoroEV/Any 100000 244 2.49 0.44 0.29 coroutines + Coro::Signal
913	Perl/Any 100000 513 4.91 0.92 1.15 pure perl implementation	1018	Perl/Any 100000 513 4.92 0.87 1.12 pure perl implementation
914	Event/Event 16000 523 28.05 21.38 0.86 Event native interface	1019	Event/Event 16000 516 31.88 31.30 0.85 Event native interface
915	Event/Any 16000 943 34.43 20.48 1.39 Event + AnyEvent watchers	1020	Event/Any 16000 590 35.75 31.42 1.08 Event + AnyEvent watchers
916	Glib/Any 16000 1357 96.99 12.55 55.51 quadratic behaviour	1021	Glib/Any 16000 1357 98.22 12.41 54.00 quadratic behaviour
917	Tk/Any 2000 1855 27.01 66.61 14.03 SEGV with >> 2000 watchers	1022	Tk/Any 2000 1860 26.97 67.98 14.00 SEGV with >> 2000 watchers
918	POE/Event 2000 6644 108.15 768.19 14.33 via POE::Loop::Event	1023	POE/Event 2000 6644 108.64 736.02 14.73 via POE::Loop::Event
919	POE/Select 2000 6343 94.69 807.65 562.69 via POE::Loop::Select	1024	POE/Select 2000 6343 94.13 809.12 565.96 via POE::Loop::Select
920		1025
921	=head2 Discussion	1026	=head3 Discussion
922		1027
923	The benchmark does I<not> measure scalability of the event loop very	1028	The benchmark does I<not> measure scalability of the event loop very
924	well. For example, a select-based event loop (such as the pure perl one)	1029	well. For example, a select-based event loop (such as the pure perl one)
925	can never compete with an event loop that uses epoll when the number of	1030	can never compete with an event loop that uses epoll when the number of
926	file descriptors grows high. In this benchmark, all events become ready at	1031	file descriptors grows high. In this benchmark, all events become ready at
927	the same time, so select/poll-based implementations get an unnatural speed	1032	the same time, so select/poll-based implementations get an unnatural speed
928	boost.	1033	boost.
929		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
930	C<EV> is the sole leader regarding speed and memory use, which are both	1045	C<EV> is the sole leader regarding speed and memory use, which are both
931	maximal/minimal, respectively. Even when going through AnyEvent, there are	1046	maximal/minimal, respectively. Even when going through AnyEvent, it uses
932	only two event loops that use slightly less memory (the C<Event> module	1047	far less memory than any other event loop and is still faster than Event
933	natively and the pure perl backend), and no faster event models, not even	1048	natively.
934	C<Event> natively.
935		1049
936	The pure perl implementation is hit in a few sweet spots (both the	1050	The pure perl implementation is hit in a few sweet spots (both the
937	zero timeout and the use of a single fd hit optimisations in the perl	1051	constant timeout and the use of a single fd hit optimisations in the perl
938	interpreter and the backend itself, and all watchers become ready at the	1052	interpreter and the backend itself). Nevertheless this shows that it
939	same time). Nevertheless this shows that it adds very little overhead in	1053	adds very little overhead in itself. Like any select-based backend its
940	itself. Like any select-based backend its performance becomes really bad	1054	performance becomes really bad with lots of file descriptors (and few of
941	with lots of file descriptors (and few of them active), of course, but	1055	them active), of course, but this was not subject of this benchmark.
942	this was not subject of this benchmark.
943		1056
944	The C<Event> module has a relatively high setup and callback invocation cost,	1057	The C<Event> module has a relatively high setup and callback invocation
945	but overall scores on the third place.	1058	cost, but overall scores in on the third place.
946		1059
947	C<Glib>'s memory usage is quite a bit bit higher, but it features a	1060	C<Glib>'s memory usage is quite a bit higher, but it features a
948	faster callback invocation and overall ends up in the same class as	1061	faster callback invocation and overall ends up in the same class as
949	C<Event>. However, Glib scales extremely badly, doubling the number of	1062	C<Event>. However, Glib scales extremely badly, doubling the number of
950	watchers increases the processing time by more than a factor of four,	1063	watchers increases the processing time by more than a factor of four,
951	making it completely unusable when using larger numbers of watchers	1064	making it completely unusable when using larger numbers of watchers
952	(note that only a single file descriptor was used in the benchmark, so	1065	(note that only a single file descriptor was used in the benchmark, so
…		…
955	The C<Tk> adaptor works relatively well. The fact that it crashes with	1068	The C<Tk> adaptor works relatively well. The fact that it crashes with
956	more than 2000 watchers is a big setback, however, as correctness takes	1069	more than 2000 watchers is a big setback, however, as correctness takes
957	precedence over speed. Nevertheless, its performance is surprising, as the	1070	precedence over speed. Nevertheless, its performance is surprising, as the
958	file descriptor is dup()ed for each watcher. This shows that the dup()	1071	file descriptor is dup()ed for each watcher. This shows that the dup()
959	employed by some adaptors is not a big performance issue (it does incur a	1072	employed by some adaptors is not a big performance issue (it does incur a
960	hidden memory cost inside the kernel, though, that is not reflected in the	1073	hidden memory cost inside the kernel which is not reflected in the figures
961	figures above).	1074	above).
962		1075
963	C<POE>, regardless of underlying event loop (wether using its pure perl	1076	C<POE>, regardless of underlying event loop (whether using its pure perl
964	select-based backend or the Event module) shows abysmal performance and	1077	select-based backend or the Event module, the POE-EV backend couldn't
		1078	be tested because it wasn't working) shows abysmal performance and
965	memory usage: Watchers use almost 30 times as much memory as EV watchers,	1079	memory usage with AnyEvent: Watchers use almost 30 times as much memory
966	and 10 times as much memory as both Event or EV via AnyEvent. Watcher	1080	as 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
967	invocation is almost 900 times slower than with AnyEvent's pure perl	1082	invocation speed is almost 900 times slower than with AnyEvent's pure perl
		1083	implementation.
		1084
968	implementation. The design of the POE adaptor class in AnyEvent can not	1085	The design of the POE adaptor class in AnyEvent can not really account
969	really account for this, as session creation overhead is small compared	1086	for the performance issues, though, as session creation overhead is
970	to execution of the state machine, which is coded pretty optimally within	1087	small compared to execution of the state machine, which is coded pretty
971	L<AnyEvent::Impl::POE>. POE simply seems to be abysmally slow.	1088	optimally within L<AnyEvent::Impl::POE> (and while everybody agrees that
		1089	using multiple sessions is not a good approach, especially regarding
		1090	memory usage, even the author of POE could not come up with a faster
		1091	design).
972		1092
973	=head2 Summary	1093	=head3 Summary
974		1094
		1095	=over 4
		1096
975	Using EV through AnyEvent is faster than any other event loop, but most	1097	=item * Using EV through AnyEvent is faster than any other event loop
976	event loops have acceptable performance with or without AnyEvent.	1098	(even when used without AnyEvent), but most event loops have acceptable
		1099	performance with or without AnyEvent.
977		1100
978	The overhead AnyEvent adds is usually much smaller than the overhead of	1101	=item * The overhead AnyEvent adds is usually much smaller than the overhead of
979	the actual event loop, only with extremely fast event loops such as the EV	1102	the actual event loop, only with extremely fast event loops such as EV
980	adds AnyEvent significant overhead.	1103	adds AnyEvent significant overhead.
981		1104
982	And you should simply avoid POE like the plague if you want performance or	1105	=item * You should avoid POE like the plague if you want performance or
983	reasonable memory usage.	1106	reasonable memory usage.
984		1107
		1108	=back
		1109
		1110	=head2 BENCHMARKING THE LARGE SERVER CASE
		1111
		1112	This benchmark atcually benchmarks the event loop itself. It works by
		1113	creating a number of "servers": each server consists of a socketpair, a
		1114	timeout watcher that gets reset on activity (but never fires), and an I/O
		1115	watcher waiting for input on one side of the socket. Each time the socket
		1116	watcher reads a byte it will write that byte to a random other "server".
		1117
		1118	The effect is that there will be a lot of I/O watchers, only part of which
		1119	are active at any one point (so there is a constant number of active
		1120	fds for each loop iterstaion, but which fds these are is random). The
		1121	timeout is reset each time something is read because that reflects how
		1122	most timeouts work (and puts extra pressure on the event loops).
		1123
		1124	In this benchmark, we use 10000 socketpairs (20000 sockets), of which 100
		1125	(1%) are active. This mirrors the activity of large servers with many
		1126	connections, most of which are idle at any one point in time.
		1127
		1128	Source code for this benchmark is found as F<eg/bench2> in the AnyEvent
		1129	distribution.
		1130
		1131	=head3 Explanation of the columns
		1132
		1133	I<sockets> is the number of sockets, and twice the number of "servers" (as
		1134	each server has a read and write socket end).
		1135
		1136	I<create> is the time it takes to create a socketpair (which is
		1137	nontrivial) and two watchers: an I/O watcher and a timeout watcher.
		1138
		1139	I<request>, the most important value, is the time it takes to handle a
		1140	single "request", that is, reading the token from the pipe and forwarding
		1141	it to another server. This includes deleting the old timeout and creating
		1142	a new one that moves the timeout into the future.
		1143
		1144	=head3 Results
		1145
		1146	name sockets create request
		1147	EV 20000 69.01 11.16
		1148	Perl 20000 73.32 35.87
		1149	Event 20000 212.62 257.32
		1150	Glib 20000 651.16 1896.30
		1151	POE 20000 349.67 12317.24 uses POE::Loop::Event
		1152
		1153	=head3 Discussion
		1154
		1155	This benchmark I<does> measure scalability and overall performance of the
		1156	particular event loop.
		1157
		1158	EV is again fastest. Since it is using epoll on my system, the setup time
		1159	is relatively high, though.
		1160
		1161	Perl surprisingly comes second. It is much faster than the C-based event
		1162	loops Event and Glib.
		1163
		1164	Event suffers from high setup time as well (look at its code and you will
		1165	understand why). Callback invocation also has a high overhead compared to
		1166	the C<< $_->() for .. >>-style loop that the Perl event loop uses. Event
		1167	uses select or poll in basically all documented configurations.
		1168
		1169	Glib is hit hard by its quadratic behaviour w.r.t. many watchers. It
		1170	clearly fails to perform with many filehandles or in busy servers.
		1171
		1172	POE is still completely out of the picture, taking over 1000 times as long
		1173	as EV, and over 100 times as long as the Perl implementation, even though
		1174	it uses a C-based event loop in this case.
		1175
		1176	=head3 Summary
		1177
		1178	=over 4
		1179
		1180	=item * The pure perl implementation performs extremely well.
		1181
		1182	=item * Avoid Glib or POE in large projects where performance matters.
		1183
		1184	=back
		1185
		1186	=head2 BENCHMARKING SMALL SERVERS
		1187
		1188	While event loops should scale (and select-based ones do not...) even to
		1189	large servers, most programs we (or I :) actually write have only a few
		1190	I/O watchers.
		1191
		1192	In this benchmark, I use the same benchmark program as in the large server
		1193	case, but it uses only eight "servers", of which three are active at any
		1194	one time. This should reflect performance for a small server relatively
		1195	well.
		1196
		1197	The columns are identical to the previous table.
		1198
		1199	=head3 Results
		1200
		1201	name sockets create request
		1202	EV 16 20.00 6.54
		1203	Perl 16 25.75 12.62
		1204	Event 16 81.27 35.86
		1205	Glib 16 32.63 15.48
		1206	POE 16 261.87 276.28 uses POE::Loop::Event
		1207
		1208	=head3 Discussion
		1209
		1210	The benchmark tries to test the performance of a typical small
		1211	server. While knowing how various event loops perform is interesting, keep
		1212	in mind that their overhead in this case is usually not as important, due
		1213	to the small absolute number of watchers (that is, you need efficiency and
		1214	speed most when you have lots of watchers, not when you only have a few of
		1215	them).
		1216
		1217	EV is again fastest.
		1218
		1219	Perl again comes second. It is noticably faster than the C-based event
		1220	loops Event and Glib, although the difference is too small to really
		1221	matter.
		1222
		1223	POE also performs much better in this case, but is is still far behind the
		1224	others.
		1225
		1226	=head3 Summary
		1227
		1228	=over 4
		1229
		1230	=item * C-based event loops perform very well with small number of
		1231	watchers, as the management overhead dominates.
		1232
		1233	=back
		1234
985		1235
986	=head1 FORK	1236	=head1 FORK
987		1237
988	Most event libraries are not fork-safe. The ones who are usually are	1238	Most event libraries are not fork-safe. The ones who are usually are
989	because they are so inefficient. Only L<EV> is fully fork-aware.	1239	because they rely on inefficient but fork-safe C<select> or C<poll>
		1240	calls. Only L<EV> is fully fork-aware.
990		1241
991	If you have to fork, you must either do so I<before> creating your first	1242	If you have to fork, you must either do so I<before> creating your first
992	watcher OR you must not use AnyEvent at all in the child.	1243	watcher OR you must not use AnyEvent at all in the child.
993		1244
994		1245

Diff Legend

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

Comparing AnyEvent/lib/AnyEvent.pm (file contents): Revision 1.80 by root, Fri Apr 25 09:11:59 2008 UTC vs. Revision 1.104 by root, Wed Apr 30 11:40:22 2008 UTC

Diff Legend

Comparing AnyEvent/lib/AnyEvent.pm (file contents):
Revision 1.80 by root, Fri Apr 25 09:11:59 2008 UTC vs.
Revision 1.104 by root, Wed Apr 30 11:40:22 2008 UTC