ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/libev/ev.pod

Comparing libev/ev.pod (file contents):
Revision 1.27 by root, Wed Nov 14 05:02:07 2007 UTC vs.
Revision 1.61 by root, Thu Nov 29 12:21:05 2007 UTC

…		…
3	libev - a high performance full-featured event loop written in C	3	libev - a high performance full-featured event loop written in C
4		4
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	#include <ev.h>	7	#include <ev.h>
		8
		9	=head1 EXAMPLE PROGRAM
		10
		11	#include <ev.h>
		12
		13	ev_io stdin_watcher;
		14	ev_timer timeout_watcher;
		15
		16	/* called when data readable on stdin */
		17	static void
		18	stdin_cb (EV_P_ struct ev_io *w, int revents)
		19	{
		20	/* puts ("stdin ready"); */
		21	ev_io_stop (EV_A_ w); /* just a syntax example */
		22	ev_unloop (EV_A_ EVUNLOOP_ALL); /* leave all loop calls */
		23	}
		24
		25	static void
		26	timeout_cb (EV_P_ struct ev_timer *w, int revents)
		27	{
		28	/* puts ("timeout"); */
		29	ev_unloop (EV_A_ EVUNLOOP_ONE); /* leave one loop call */
		30	}
		31
		32	int
		33	main (void)
		34	{
		35	struct ev_loop *loop = ev_default_loop (0);
		36
		37	/* initialise an io watcher, then start it */
		38	ev_io_init (&stdin_watcher, stdin_cb, /*STDIN_FILENO*/ 0, EV_READ);
		39	ev_io_start (loop, &stdin_watcher);
		40
		41	/* simple non-repeating 5.5 second timeout */
		42	ev_timer_init (&timeout_watcher, timeout_cb, 5.5, 0.);
		43	ev_timer_start (loop, &timeout_watcher);
		44
		45	/* loop till timeout or data ready */
		46	ev_loop (loop, 0);
		47
		48	return 0;
		49	}
8		50
9	=head1 DESCRIPTION	51	=head1 DESCRIPTION
10		52
11	Libev is an event loop: you register interest in certain events (such as a	53	Libev is an event loop: you register interest in certain events (such as a
12	file descriptor being readable or a timeout occuring), and it will manage	54	file descriptor being readable or a timeout occuring), and it will manage
…		…
21	details of the event, and then hand it over to libev by I<starting> the	63	details of the event, and then hand it over to libev by I<starting> the
22	watcher.	64	watcher.
23		65
24	=head1 FEATURES	66	=head1 FEATURES
25		67
26	Libev supports select, poll, the linux-specific epoll and the bsd-specific	68	Libev supports C<select>, C<poll>, the Linux-specific C<epoll>, the
27	kqueue mechanisms for file descriptor events, relative timers, absolute	69	BSD-specific C<kqueue> and the Solaris-specific event port mechanisms
28	timers with customised rescheduling, signal events, process status change	70	for file descriptor events (C<ev_io>), the Linux C<inotify> interface
29	events (related to SIGCHLD), and event watchers dealing with the event	71	(for C<ev_stat>), relative timers (C<ev_timer>), absolute timers
30	loop mechanism itself (idle, prepare and check watchers). It also is quite	72	with customised rescheduling (C<ev_periodic>), synchronous signals
		73	(C<ev_signal>), process status change events (C<ev_child>), and event
		74	watchers dealing with the event loop mechanism itself (C<ev_idle>,
		75	C<ev_embed>, C<ev_prepare> and C<ev_check> watchers) as well as
		76	file watchers (C<ev_stat>) and even limited support for fork events
		77	(C<ev_fork>).
		78
		79	It also is quite fast (see this
31	fast (see this L<benchmark|http://libev.schmorp.de/bench.html> comparing	80	L<benchmark|http://libev.schmorp.de/bench.html> comparing it to libevent
32	it to libevent for example).	81	for example).
33		82
34	=head1 CONVENTIONS	83	=head1 CONVENTIONS
35		84
36	Libev is very configurable. In this manual the default configuration	85	Libev is very configurable. In this manual the default configuration will
37	will be described, which supports multiple event loops. For more info	86	be described, which supports multiple event loops. For more info about
38	about various configuration options please have a look at the file	87	various configuration options please have a look at B<EMBED> section in
39	F<README.embed> in the libev distribution. If libev was configured without	88	this manual. If libev was configured without support for multiple event
40	support for multiple event loops, then all functions taking an initial	89	loops, then all functions taking an initial argument of name C<loop>
41	argument of name C<loop> (which is always of type C<struct ev_loop *>)	90	(which is always of type C<struct ev_loop *>) will not have this argument.
42	will not have this argument.
43		91
44	=head1 TIME REPRESENTATION	92	=head1 TIME REPRESENTATION
45		93
46	Libev represents time as a single floating point number, representing the	94	Libev represents time as a single floating point number, representing the
47	(fractional) number of seconds since the (POSIX) epoch (somewhere near	95	(fractional) number of seconds since the (POSIX) epoch (somewhere near
48	the beginning of 1970, details are complicated, don't ask). This type is	96	the beginning of 1970, details are complicated, don't ask). This type is
49	called C<ev_tstamp>, which is what you should use too. It usually aliases	97	called C<ev_tstamp>, which is what you should use too. It usually aliases
50	to the double type in C.	98	to the C<double> type in C, and when you need to do any calculations on
		99	it, you should treat it as such.
51		100
52	=head1 GLOBAL FUNCTIONS	101	=head1 GLOBAL FUNCTIONS
53		102
54	These functions can be called anytime, even before initialising the	103	These functions can be called anytime, even before initialising the
55	library in any way.	104	library in any way.
…		…
75	Usually, it's a good idea to terminate if the major versions mismatch,	124	Usually, it's a good idea to terminate if the major versions mismatch,
76	as this indicates an incompatible change. Minor versions are usually	125	as this indicates an incompatible change. Minor versions are usually
77	compatible to older versions, so a larger minor version alone is usually	126	compatible to older versions, so a larger minor version alone is usually
78	not a problem.	127	not a problem.
79		128
		129	Example: Make sure we haven't accidentally been linked against the wrong
		130	version.
		131
		132	assert (("libev version mismatch",
		133	ev_version_major () == EV_VERSION_MAJOR
		134	&& ev_version_minor () >= EV_VERSION_MINOR));
		135
		136	=item unsigned int ev_supported_backends ()
		137
		138	Return the set of all backends (i.e. their corresponding C<EV_BACKEND_*>
		139	value) compiled into this binary of libev (independent of their
		140	availability on the system you are running on). See C<ev_default_loop> for
		141	a description of the set values.
		142
		143	Example: make sure we have the epoll method, because yeah this is cool and
		144	a must have and can we have a torrent of it please!!!11
		145
		146	assert (("sorry, no epoll, no sex",
		147	ev_supported_backends () & EVBACKEND_EPOLL));
		148
		149	=item unsigned int ev_recommended_backends ()
		150
		151	Return the set of all backends compiled into this binary of libev and also
		152	recommended for this platform. This set is often smaller than the one
		153	returned by C<ev_supported_backends>, as for example kqueue is broken on
		154	most BSDs and will not be autodetected unless you explicitly request it
		155	(assuming you know what you are doing). This is the set of backends that
		156	libev will probe for if you specify no backends explicitly.
		157
		158	=item unsigned int ev_embeddable_backends ()
		159
		160	Returns the set of backends that are embeddable in other event loops. This
		161	is the theoretical, all-platform, value. To find which backends
		162	might be supported on the current system, you would need to look at
		163	C<ev_embeddable_backends () & ev_supported_backends ()>, likewise for
		164	recommended ones.
		165
		166	See the description of C<ev_embed> watchers for more info.
		167
80	=item ev_set_allocator (void *(*cb)(void *ptr, long size))	168	=item ev_set_allocator (void *(*cb)(void *ptr, long size))
81		169
82	Sets the allocation function to use (the prototype is similar to the	170	Sets the allocation function to use (the prototype is similar - the
83	realloc C function, the semantics are identical). It is used to allocate	171	semantics is identical - to the realloc C function). It is used to
84	and free memory (no surprises here). If it returns zero when memory	172	allocate and free memory (no surprises here). If it returns zero when
85	needs to be allocated, the library might abort or take some potentially	173	memory needs to be allocated, the library might abort or take some
86	destructive action. The default is your system realloc function.	174	potentially destructive action. The default is your system realloc
		175	function.
87		176
88	You could override this function in high-availability programs to, say,	177	You could override this function in high-availability programs to, say,
89	free some memory if it cannot allocate memory, to use a special allocator,	178	free some memory if it cannot allocate memory, to use a special allocator,
90	or even to sleep a while and retry until some memory is available.	179	or even to sleep a while and retry until some memory is available.
		180
		181	Example: Replace the libev allocator with one that waits a bit and then
		182	retries).
		183
		184	static void *
		185	persistent_realloc (void *ptr, size_t size)
		186	{
		187	for (;;)
		188	{
		189	void *newptr = realloc (ptr, size);
		190
		191	if (newptr)
		192	return newptr;
		193
		194	sleep (60);
		195	}
		196	}
		197
		198	...
		199	ev_set_allocator (persistent_realloc);
91		200
92	=item ev_set_syserr_cb (void (*cb)(const char *msg));	201	=item ev_set_syserr_cb (void (*cb)(const char *msg));
93		202
94	Set the callback function to call on a retryable syscall error (such	203	Set the callback function to call on a retryable syscall error (such
95	as failed select, poll, epoll_wait). The message is a printable string	204	as failed select, poll, epoll_wait). The message is a printable string
…		…
97	callback is set, then libev will expect it to remedy the sitution, no	206	callback is set, then libev will expect it to remedy the sitution, no
98	matter what, when it returns. That is, libev will generally retry the	207	matter what, when it returns. That is, libev will generally retry the
99	requested operation, or, if the condition doesn't go away, do bad stuff	208	requested operation, or, if the condition doesn't go away, do bad stuff
100	(such as abort).	209	(such as abort).
101		210
		211	Example: This is basically the same thing that libev does internally, too.
		212
		213	static void
		214	fatal_error (const char *msg)
		215	{
		216	perror (msg);
		217	abort ();
		218	}
		219
		220	...
		221	ev_set_syserr_cb (fatal_error);
		222
102	=back	223	=back
103		224
104	=head1 FUNCTIONS CONTROLLING THE EVENT LOOP	225	=head1 FUNCTIONS CONTROLLING THE EVENT LOOP
105		226
106	An event loop is described by a C<struct ev_loop *>. The library knows two	227	An event loop is described by a C<struct ev_loop *>. The library knows two
…		…
119	=item struct ev_loop *ev_default_loop (unsigned int flags)	240	=item struct ev_loop *ev_default_loop (unsigned int flags)
120		241
121	This will initialise the default event loop if it hasn't been initialised	242	This will initialise the default event loop if it hasn't been initialised
122	yet and return it. If the default loop could not be initialised, returns	243	yet and return it. If the default loop could not be initialised, returns
123	false. If it already was initialised it simply returns it (and ignores the	244	false. If it already was initialised it simply returns it (and ignores the
124	flags).	245	flags. If that is troubling you, check C<ev_backend ()> afterwards).
125		246
126	If you don't know what event loop to use, use the one returned from this	247	If you don't know what event loop to use, use the one returned from this
127	function.	248	function.
128		249
129	The flags argument can be used to specify special behaviour or specific	250	The flags argument can be used to specify special behaviour or specific
130	backends to use, and is usually specified as 0 (or EVFLAG_AUTO).	251	backends to use, and is usually specified as C<0> (or C<EVFLAG_AUTO>).
131		252
132	It supports the following flags:	253	The following flags are supported:
133		254
134	=over 4	255	=over 4
135		256
136	=item C<EVFLAG_AUTO>	257	=item C<EVFLAG_AUTO>
137		258
…		…
145	C<LIBEV_FLAGS>. Otherwise (the default), this environment variable will	266	C<LIBEV_FLAGS>. Otherwise (the default), this environment variable will
146	override the flags completely if it is found in the environment. This is	267	override the flags completely if it is found in the environment. This is
147	useful to try out specific backends to test their performance, or to work	268	useful to try out specific backends to test their performance, or to work
148	around bugs.	269	around bugs.
149		270
150	=item C<EVMETHOD_SELECT> (portable select backend)	271	=item C<EVBACKEND_SELECT> (value 1, portable select backend)
151		272
		273	This is your standard select(2) backend. Not I<completely> standard, as
		274	libev tries to roll its own fd_set with no limits on the number of fds,
		275	but if that fails, expect a fairly low limit on the number of fds when
		276	using this backend. It doesn't scale too well (O(highest_fd)), but its usually
		277	the fastest backend for a low number of fds.
		278
152	=item C<EVMETHOD_POLL> (poll backend, available everywhere except on windows)	279	=item C<EVBACKEND_POLL> (value 2, poll backend, available everywhere except on windows)
153		280
154	=item C<EVMETHOD_EPOLL> (linux only)	281	And this is your standard poll(2) backend. It's more complicated than
		282	select, but handles sparse fds better and has no artificial limit on the
		283	number of fds you can use (except it will slow down considerably with a
		284	lot of inactive fds). It scales similarly to select, i.e. O(total_fds).
155		285
156	=item C<EVMETHOD_KQUEUE> (some bsds only)	286	=item C<EVBACKEND_EPOLL> (value 4, Linux)
157		287
158	=item C<EVMETHOD_DEVPOLL> (solaris 8 only)	288	For few fds, this backend is a bit little slower than poll and select,
		289	but it scales phenomenally better. While poll and select usually scale like
		290	O(total_fds) where n is the total number of fds (or the highest fd), epoll scales
		291	either O(1) or O(active_fds).
159		292
160	=item C<EVMETHOD_PORT> (solaris 10 only)	293	While stopping and starting an I/O watcher in the same iteration will
		294	result in some caching, there is still a syscall per such incident
		295	(because the fd could point to a different file description now), so its
		296	best to avoid that. Also, dup()ed file descriptors might not work very
		297	well if you register events for both fds.
		298
		299	Please note that epoll sometimes generates spurious notifications, so you
		300	need to use non-blocking I/O or other means to avoid blocking when no data
		301	(or space) is available.
		302
		303	=item C<EVBACKEND_KQUEUE> (value 8, most BSD clones)
		304
		305	Kqueue deserves special mention, as at the time of this writing, it
		306	was broken on all BSDs except NetBSD (usually it doesn't work with
		307	anything but sockets and pipes, except on Darwin, where of course its
		308	completely useless). For this reason its not being "autodetected"
		309	unless you explicitly specify it explicitly in the flags (i.e. using
		310	C<EVBACKEND_KQUEUE>).
		311
		312	It scales in the same way as the epoll backend, but the interface to the
		313	kernel is more efficient (which says nothing about its actual speed, of
		314	course). While starting and stopping an I/O watcher does not cause an
		315	extra syscall as with epoll, it still adds up to four event changes per
		316	incident, so its best to avoid that.
		317
		318	=item C<EVBACKEND_DEVPOLL> (value 16, Solaris 8)
		319
		320	This is not implemented yet (and might never be).
		321
		322	=item C<EVBACKEND_PORT> (value 32, Solaris 10)
		323
		324	This uses the Solaris 10 port mechanism. As with everything on Solaris,
		325	it's really slow, but it still scales very well (O(active_fds)).
		326
		327	Please note that solaris ports can result in a lot of spurious
		328	notifications, so you need to use non-blocking I/O or other means to avoid
		329	blocking when no data (or space) is available.
		330
		331	=item C<EVBACKEND_ALL>
		332
		333	Try all backends (even potentially broken ones that wouldn't be tried
		334	with C<EVFLAG_AUTO>). Since this is a mask, you can do stuff such as
		335	C<EVBACKEND_ALL & ~EVBACKEND_KQUEUE>.
		336
		337	=back
161		338
162	If one or more of these are ored into the flags value, then only these	339	If one or more of these are ored into the flags value, then only these
163	backends will be tried (in the reverse order as given here). If one are	340	backends will be tried (in the reverse order as given here). If none are
164	specified, any backend will do.	341	specified, most compiled-in backend will be tried, usually in reverse
		342	order of their flag values :)
165		343
166	=back	344	The most typical usage is like this:
		345
		346	if (!ev_default_loop (0))
		347	fatal ("could not initialise libev, bad $LIBEV_FLAGS in environment?");
		348
		349	Restrict libev to the select and poll backends, and do not allow
		350	environment settings to be taken into account:
		351
		352	ev_default_loop (EVBACKEND_POLL | EVBACKEND_SELECT | EVFLAG_NOENV);
		353
		354	Use whatever libev has to offer, but make sure that kqueue is used if
		355	available (warning, breaks stuff, best use only with your own private
		356	event loop and only if you know the OS supports your types of fds):
		357
		358	ev_default_loop (ev_recommended_backends () | EVBACKEND_KQUEUE);
167		359
168	=item struct ev_loop *ev_loop_new (unsigned int flags)	360	=item struct ev_loop *ev_loop_new (unsigned int flags)
169		361
170	Similar to C<ev_default_loop>, but always creates a new event loop that is	362	Similar to C<ev_default_loop>, but always creates a new event loop that is
171	always distinct from the default loop. Unlike the default loop, it cannot	363	always distinct from the default loop. Unlike the default loop, it cannot
172	handle signal and child watchers, and attempts to do so will be greeted by	364	handle signal and child watchers, and attempts to do so will be greeted by
173	undefined behaviour (or a failed assertion if assertions are enabled).	365	undefined behaviour (or a failed assertion if assertions are enabled).
174		366
		367	Example: Try to create a event loop that uses epoll and nothing else.
		368
		369	struct ev_loop *epoller = ev_loop_new (EVBACKEND_EPOLL | EVFLAG_NOENV);
		370	if (!epoller)
		371	fatal ("no epoll found here, maybe it hides under your chair");
		372
175	=item ev_default_destroy ()	373	=item ev_default_destroy ()
176		374
177	Destroys the default loop again (frees all memory and kernel state	375	Destroys the default loop again (frees all memory and kernel state
178	etc.). This stops all registered event watchers (by not touching them in	376	etc.). None of the active event watchers will be stopped in the normal
179	any way whatsoever, although you cannot rely on this :).	377	sense, so e.g. C<ev_is_active> might still return true. It is your
		378	responsibility to either stop all watchers cleanly yoursef I<before>
		379	calling this function, or cope with the fact afterwards (which is usually
		380	the easiest thing, youc na just ignore the watchers and/or C<free ()> them
		381	for example).
180		382
181	=item ev_loop_destroy (loop)	383	=item ev_loop_destroy (loop)
182		384
183	Like C<ev_default_destroy>, but destroys an event loop created by an	385	Like C<ev_default_destroy>, but destroys an event loop created by an
184	earlier call to C<ev_loop_new>.	386	earlier call to C<ev_loop_new>.
…		…
188	This function reinitialises the kernel state for backends that have	390	This function reinitialises the kernel state for backends that have
189	one. Despite the name, you can call it anytime, but it makes most sense	391	one. Despite the name, you can call it anytime, but it makes most sense
190	after forking, in either the parent or child process (or both, but that	392	after forking, in either the parent or child process (or both, but that
191	again makes little sense).	393	again makes little sense).
192		394
193	You I<must> call this function after forking if and only if you want to	395	You I<must> call this function in the child process after forking if and
194	use the event library in both processes. If you just fork+exec, you don't	396	only if you want to use the event library in both processes. If you just
195	have to call it.	397	fork+exec, you don't have to call it.
196		398
197	The function itself is quite fast and it's usually not a problem to call	399	The function itself is quite fast and it's usually not a problem to call
198	it just in case after a fork. To make this easy, the function will fit in	400	it just in case after a fork. To make this easy, the function will fit in
199	quite nicely into a call to C<pthread_atfork>:	401	quite nicely into a call to C<pthread_atfork>:
200		402
201	pthread_atfork (0, 0, ev_default_fork);	403	pthread_atfork (0, 0, ev_default_fork);
202		404
		405	At the moment, C<EVBACKEND_SELECT> and C<EVBACKEND_POLL> are safe to use
		406	without calling this function, so if you force one of those backends you
		407	do not need to care.
		408
203	=item ev_loop_fork (loop)	409	=item ev_loop_fork (loop)
204		410
205	Like C<ev_default_fork>, but acts on an event loop created by	411	Like C<ev_default_fork>, but acts on an event loop created by
206	C<ev_loop_new>. Yes, you have to call this on every allocated event loop	412	C<ev_loop_new>. Yes, you have to call this on every allocated event loop
207	after fork, and how you do this is entirely your own problem.	413	after fork, and how you do this is entirely your own problem.
208		414
209	=item unsigned int ev_method (loop)	415	=item unsigned int ev_backend (loop)
210		416
211	Returns one of the C<EVMETHOD_*> flags indicating the event backend in	417	Returns one of the C<EVBACKEND_*> flags indicating the event backend in
212	use.	418	use.
213		419
214	=item ev_tstamp ev_now (loop)	420	=item ev_tstamp ev_now (loop)
215		421
216	Returns the current "event loop time", which is the time the event loop	422	Returns the current "event loop time", which is the time the event loop
217	got events and started processing them. This timestamp does not change	423	received events and started processing them. This timestamp does not
218	as long as callbacks are being processed, and this is also the base time	424	change as long as callbacks are being processed, and this is also the base
219	used for relative timers. You can treat it as the timestamp of the event	425	time used for relative timers. You can treat it as the timestamp of the
220	occuring (or more correctly, the mainloop finding out about it).	426	event occuring (or more correctly, libev finding out about it).
221		427
222	=item ev_loop (loop, int flags)	428	=item ev_loop (loop, int flags)
223		429
224	Finally, this is it, the event handler. This function usually is called	430	Finally, this is it, the event handler. This function usually is called
225	after you initialised all your watchers and you want to start handling	431	after you initialised all your watchers and you want to start handling
226	events.	432	events.
227		433
228	If the flags argument is specified as 0, it will not return until either	434	If the flags argument is specified as C<0>, it will not return until
229	no event watchers are active anymore or C<ev_unloop> was called.	435	either no event watchers are active anymore or C<ev_unloop> was called.
		436
		437	Please note that an explicit C<ev_unloop> is usually better than
		438	relying on all watchers to be stopped when deciding when a program has
		439	finished (especially in interactive programs), but having a program that
		440	automatically loops as long as it has to and no longer by virtue of
		441	relying on its watchers stopping correctly is a thing of beauty.
230		442
231	A flags value of C<EVLOOP_NONBLOCK> will look for new events, will handle	443	A flags value of C<EVLOOP_NONBLOCK> will look for new events, will handle
232	those events and any outstanding ones, but will not block your process in	444	those events and any outstanding ones, but will not block your process in
233	case there are no events and will return after one iteration of the loop.	445	case there are no events and will return after one iteration of the loop.
234		446
235	A flags value of C<EVLOOP_ONESHOT> will look for new events (waiting if	447	A flags value of C<EVLOOP_ONESHOT> will look for new events (waiting if
236	neccessary) and will handle those and any outstanding ones. It will block	448	neccessary) and will handle those and any outstanding ones. It will block
237	your process until at least one new event arrives, and will return after	449	your process until at least one new event arrives, and will return after
238	one iteration of the loop.	450	one iteration of the loop. This is useful if you are waiting for some
		451	external event in conjunction with something not expressible using other
		452	libev watchers. However, a pair of C<ev_prepare>/C<ev_check> watchers is
		453	usually a better approach for this kind of thing.
239		454
240	This flags value could be used to implement alternative looping
241	constructs, but the C<prepare> and C<check> watchers provide a better and
242	more generic mechanism.
243
244	Here are the gory details of what ev_loop does:	455	Here are the gory details of what C<ev_loop> does:
245		456
246	1. If there are no active watchers (reference count is zero), return.	457	* If there are no active watchers (reference count is zero), return.
247	2. Queue and immediately call all prepare watchers.	458	- Queue prepare watchers and then call all outstanding watchers.
248	3. If we have been forked, recreate the kernel state.	459	- If we have been forked, recreate the kernel state.
249	4. Update the kernel state with all outstanding changes.	460	- Update the kernel state with all outstanding changes.
250	5. Update the "event loop time".	461	- Update the "event loop time".
251	6. Calculate for how long to block.	462	- Calculate for how long to block.
252	7. Block the process, waiting for events.	463	- Block the process, waiting for any events.
		464	- Queue all outstanding I/O (fd) events.
253	8. Update the "event loop time" and do time jump handling.	465	- Update the "event loop time" and do time jump handling.
254	9. Queue all outstanding timers.	466	- Queue all outstanding timers.
255	10. Queue all outstanding periodics.	467	- Queue all outstanding periodics.
256	11. If no events are pending now, queue all idle watchers.	468	- If no events are pending now, queue all idle watchers.
257	12. Queue all check watchers.	469	- Queue all check watchers.
258	13. Call all queued watchers in reverse order (i.e. check watchers first).	470	- Call all queued watchers in reverse order (i.e. check watchers first).
		471	Signals and child watchers are implemented as I/O watchers, and will
		472	be handled here by queueing them when their watcher gets executed.
259	14. If ev_unloop has been called or EVLOOP_ONESHOT or EVLOOP_NONBLOCK	473	- If ev_unloop has been called or EVLOOP_ONESHOT or EVLOOP_NONBLOCK
260	was used, return, otherwise continue with step #1.	474	were used, return, otherwise continue with step *.
		475
		476	Example: Queue some jobs and then loop until no events are outsanding
		477	anymore.
		478
		479	... queue jobs here, make sure they register event watchers as long
		480	... as they still have work to do (even an idle watcher will do..)
		481	ev_loop (my_loop, 0);
		482	... jobs done. yeah!
261		483
262	=item ev_unloop (loop, how)	484	=item ev_unloop (loop, how)
263		485
264	Can be used to make a call to C<ev_loop> return early (but only after it	486	Can be used to make a call to C<ev_loop> return early (but only after it
265	has processed all outstanding events). The C<how> argument must be either	487	has processed all outstanding events). The C<how> argument must be either
…		…
279	visible to the libev user and should not keep C<ev_loop> from exiting if	501	visible to the libev user and should not keep C<ev_loop> from exiting if
280	no event watchers registered by it are active. It is also an excellent	502	no event watchers registered by it are active. It is also an excellent
281	way to do this for generic recurring timers or from within third-party	503	way to do this for generic recurring timers or from within third-party
282	libraries. Just remember to I<unref after start> and I<ref before stop>.	504	libraries. Just remember to I<unref after start> and I<ref before stop>.
283		505
		506	Example: Create a signal watcher, but keep it from keeping C<ev_loop>
		507	running when nothing else is active.
		508
		509	struct ev_signal exitsig;
		510	ev_signal_init (&exitsig, sig_cb, SIGINT);
		511	ev_signal_start (loop, &exitsig);
		512	evf_unref (loop);
		513
		514	Example: For some weird reason, unregister the above signal handler again.
		515
		516	ev_ref (loop);
		517	ev_signal_stop (loop, &exitsig);
		518
284	=back	519	=back
		520
285		521
286	=head1 ANATOMY OF A WATCHER	522	=head1 ANATOMY OF A WATCHER
287		523
288	A watcher is a structure that you create and register to record your	524	A watcher is a structure that you create and register to record your
289	interest in some event. For instance, if you want to wait for STDIN to	525	interest in some event. For instance, if you want to wait for STDIN to
…		…
322	*) >>), and you can stop watching for events at any time by calling the	558	*) >>), and you can stop watching for events at any time by calling the
323	corresponding stop function (C<< ev_<type>_stop (loop, watcher *) >>.	559	corresponding stop function (C<< ev_<type>_stop (loop, watcher *) >>.
324		560
325	As long as your watcher is active (has been started but not stopped) you	561	As long as your watcher is active (has been started but not stopped) you
326	must not touch the values stored in it. Most specifically you must never	562	must not touch the values stored in it. Most specifically you must never
327	reinitialise it or call its set method.	563	reinitialise it or call its C<set> macro.
328
329	You can check whether an event is active by calling the C<ev_is_active
330	(watcher *)> macro. To see whether an event is outstanding (but the
331	callback for it has not been called yet) you can use the C<ev_is_pending
332	(watcher *)> macro.
333		564
334	Each and every callback receives the event loop pointer as first, the	565	Each and every callback receives the event loop pointer as first, the
335	registered watcher structure as second, and a bitset of received events as	566	registered watcher structure as second, and a bitset of received events as
336	third argument.	567	third argument.
337		568
…		…
361	The signal specified in the C<ev_signal> watcher has been received by a thread.	592	The signal specified in the C<ev_signal> watcher has been received by a thread.
362		593
363	=item C<EV_CHILD>	594	=item C<EV_CHILD>
364		595
365	The pid specified in the C<ev_child> watcher has received a status change.	596	The pid specified in the C<ev_child> watcher has received a status change.
		597
		598	=item C<EV_STAT>
		599
		600	The path specified in the C<ev_stat> watcher changed its attributes somehow.
366		601
367	=item C<EV_IDLE>	602	=item C<EV_IDLE>
368		603
369	The C<ev_idle> watcher has determined that you have nothing better to do.	604	The C<ev_idle> watcher has determined that you have nothing better to do.
370		605
…		…
378	received events. Callbacks of both watcher types can start and stop as	613	received events. Callbacks of both watcher types can start and stop as
379	many watchers as they want, and all of them will be taken into account	614	many watchers as they want, and all of them will be taken into account
380	(for example, a C<ev_prepare> watcher might start an idle watcher to keep	615	(for example, a C<ev_prepare> watcher might start an idle watcher to keep
381	C<ev_loop> from blocking).	616	C<ev_loop> from blocking).
382		617
		618	=item C<EV_EMBED>
		619
		620	The embedded event loop specified in the C<ev_embed> watcher needs attention.
		621
		622	=item C<EV_FORK>
		623
		624	The event loop has been resumed in the child process after fork (see
		625	C<ev_fork>).
		626
383	=item C<EV_ERROR>	627	=item C<EV_ERROR>
384		628
385	An unspecified error has occured, the watcher has been stopped. This might	629	An unspecified error has occured, the watcher has been stopped. This might
386	happen because the watcher could not be properly started because libev	630	happen because the watcher could not be properly started because libev
387	ran out of memory, a file descriptor was found to be closed or any other	631	ran out of memory, a file descriptor was found to be closed or any other
…		…
393	your callbacks is well-written it can just attempt the operation and cope	637	your callbacks is well-written it can just attempt the operation and cope
394	with the error from read() or write(). This will not work in multithreaded	638	with the error from read() or write(). This will not work in multithreaded
395	programs, though, so beware.	639	programs, though, so beware.
396		640
397	=back	641	=back
		642
		643	=head2 GENERIC WATCHER FUNCTIONS
		644
		645	In the following description, C<TYPE> stands for the watcher type,
		646	e.g. C<timer> for C<ev_timer> watchers and C<io> for C<ev_io> watchers.
		647
		648	=over 4
		649
		650	=item C<ev_init> (ev_TYPE *watcher, callback)
		651
		652	This macro initialises the generic portion of a watcher. The contents
		653	of the watcher object can be arbitrary (so C<malloc> will do). Only
		654	the generic parts of the watcher are initialised, you I<need> to call
		655	the type-specific C<ev_TYPE_set> macro afterwards to initialise the
		656	type-specific parts. For each type there is also a C<ev_TYPE_init> macro
		657	which rolls both calls into one.
		658
		659	You can reinitialise a watcher at any time as long as it has been stopped
		660	(or never started) and there are no pending events outstanding.
		661
		662	The callback is always of type C<void (*)(ev_loop *loop, ev_TYPE *watcher,
		663	int revents)>.
		664
		665	=item C<ev_TYPE_set> (ev_TYPE *, [args])
		666
		667	This macro initialises the type-specific parts of a watcher. You need to
		668	call C<ev_init> at least once before you call this macro, but you can
		669	call C<ev_TYPE_set> any number of times. You must not, however, call this
		670	macro on a watcher that is active (it can be pending, however, which is a
		671	difference to the C<ev_init> macro).
		672
		673	Although some watcher types do not have type-specific arguments
		674	(e.g. C<ev_prepare>) you still need to call its C<set> macro.
		675
		676	=item C<ev_TYPE_init> (ev_TYPE *watcher, callback, [args])
		677
		678	This convinience macro rolls both C<ev_init> and C<ev_TYPE_set> macro
		679	calls into a single call. This is the most convinient method to initialise
		680	a watcher. The same limitations apply, of course.
		681
		682	=item C<ev_TYPE_start> (loop *, ev_TYPE *watcher)
		683
		684	Starts (activates) the given watcher. Only active watchers will receive
		685	events. If the watcher is already active nothing will happen.
		686
		687	=item C<ev_TYPE_stop> (loop *, ev_TYPE *watcher)
		688
		689	Stops the given watcher again (if active) and clears the pending
		690	status. It is possible that stopped watchers are pending (for example,
		691	non-repeating timers are being stopped when they become pending), but
		692	C<ev_TYPE_stop> ensures that the watcher is neither active nor pending. If
		693	you want to free or reuse the memory used by the watcher it is therefore a
		694	good idea to always call its C<ev_TYPE_stop> function.
		695
		696	=item bool ev_is_active (ev_TYPE *watcher)
		697
		698	Returns a true value iff the watcher is active (i.e. it has been started
		699	and not yet been stopped). As long as a watcher is active you must not modify
		700	it.
		701
		702	=item bool ev_is_pending (ev_TYPE *watcher)
		703
		704	Returns a true value iff the watcher is pending, (i.e. it has outstanding
		705	events but its callback has not yet been invoked). As long as a watcher
		706	is pending (but not active) you must not call an init function on it (but
		707	C<ev_TYPE_set> is safe) and you must make sure the watcher is available to
		708	libev (e.g. you cnanot C<free ()> it).
		709
		710	=item callback ev_cb (ev_TYPE *watcher)
		711
		712	Returns the callback currently set on the watcher.
		713
		714	=item ev_cb_set (ev_TYPE *watcher, callback)
		715
		716	Change the callback. You can change the callback at virtually any time
		717	(modulo threads).
		718
		719	=back
		720
398		721
399	=head2 ASSOCIATING CUSTOM DATA WITH A WATCHER	722	=head2 ASSOCIATING CUSTOM DATA WITH A WATCHER
400		723
401	Each watcher has, by default, a member C<void *data> that you can change	724	Each watcher has, by default, a member C<void *data> that you can change
402	and read at any time, libev will completely ignore it. This can be used	725	and read at any time, libev will completely ignore it. This can be used
…		…
420	{	743	{
421	struct my_io *w = (struct my_io *)w_;	744	struct my_io *w = (struct my_io *)w_;
422	...	745	...
423	}	746	}
424		747
425	More interesting and less C-conformant ways of catsing your callback type	748	More interesting and less C-conformant ways of casting your callback type
426	have been omitted....	749	instead have been omitted.
		750
		751	Another common scenario is having some data structure with multiple
		752	watchers:
		753
		754	struct my_biggy
		755	{
		756	int some_data;
		757	ev_timer t1;
		758	ev_timer t2;
		759	}
		760
		761	In this case getting the pointer to C<my_biggy> is a bit more complicated,
		762	you need to use C<offsetof>:
		763
		764	#include <stddef.h>
		765
		766	static void
		767	t1_cb (EV_P_ struct ev_timer *w, int revents)
		768	{
		769	struct my_biggy big = (struct my_biggy *
		770	(((char *)w) - offsetof (struct my_biggy, t1));
		771	}
		772
		773	static void
		774	t2_cb (EV_P_ struct ev_timer *w, int revents)
		775	{
		776	struct my_biggy big = (struct my_biggy *
		777	(((char *)w) - offsetof (struct my_biggy, t2));
		778	}
427		779
428		780
429	=head1 WATCHER TYPES	781	=head1 WATCHER TYPES
430		782
431	This section describes each watcher in detail, but will not repeat	783	This section describes each watcher in detail, but will not repeat
432	information given in the last section.	784	information given in the last section. Any initialisation/set macros,
		785	functions and members specific to the watcher type are explained.
433		786
		787	Members are additionally marked with either I<[read-only]>, meaning that,
		788	while the watcher is active, you can look at the member and expect some
		789	sensible content, but you must not modify it (you can modify it while the
		790	watcher is stopped to your hearts content), or I<[read-write]>, which
		791	means you can expect it to have some sensible content while the watcher
		792	is active, but you can also modify it. Modifying it may not do something
		793	sensible or take immediate effect (or do anything at all), but libev will
		794	not crash or malfunction in any way.
		795
		796
434	=head2 C<ev_io> - is this file descriptor readable or writable	797	=head2 C<ev_io> - is this file descriptor readable or writable?
435		798
436	I/O watchers check whether a file descriptor is readable or writable	799	I/O watchers check whether a file descriptor is readable or writable
437	in each iteration of the event loop (This behaviour is called	800	in each iteration of the event loop, or, more precisely, when reading
438	level-triggering because you keep receiving events as long as the	801	would not block the process and writing would at least be able to write
439	condition persists. Remember you can stop the watcher if you don't want to	802	some data. This behaviour is called level-triggering because you keep
440	act on the event and neither want to receive future events).	803	receiving events as long as the condition persists. Remember you can stop
		804	the watcher if you don't want to act on the event and neither want to
		805	receive future events.
441		806
442	In general you can register as many read and/or write event watchers per	807	In general you can register as many read and/or write event watchers per
443	fd as you want (as long as you don't confuse yourself). Setting all file	808	fd as you want (as long as you don't confuse yourself). Setting all file
444	descriptors to non-blocking mode is also usually a good idea (but not	809	descriptors to non-blocking mode is also usually a good idea (but not
445	required if you know what you are doing).	810	required if you know what you are doing).
446		811
447	You have to be careful with dup'ed file descriptors, though. Some backends	812	You have to be careful with dup'ed file descriptors, though. Some backends
448	(the linux epoll backend is a notable example) cannot handle dup'ed file	813	(the linux epoll backend is a notable example) cannot handle dup'ed file
449	descriptors correctly if you register interest in two or more fds pointing	814	descriptors correctly if you register interest in two or more fds pointing
450	to the same underlying file/socket etc. description (that is, they share	815	to the same underlying file/socket/etc. description (that is, they share
451	the same underlying "file open").	816	the same underlying "file open").
452		817
453	If you must do this, then force the use of a known-to-be-good backend	818	If you must do this, then force the use of a known-to-be-good backend
454	(at the time of this writing, this includes only EVMETHOD_SELECT and	819	(at the time of this writing, this includes only C<EVBACKEND_SELECT> and
455	EVMETHOD_POLL).	820	C<EVBACKEND_POLL>).
		821
		822	Another thing you have to watch out for is that it is quite easy to
		823	receive "spurious" readyness notifications, that is your callback might
		824	be called with C<EV_READ> but a subsequent C<read>(2) will actually block
		825	because there is no data. Not only are some backends known to create a
		826	lot of those (for example solaris ports), it is very easy to get into
		827	this situation even with a relatively standard program structure. Thus
		828	it is best to always use non-blocking I/O: An extra C<read>(2) returning
		829	C<EAGAIN> is far preferable to a program hanging until some data arrives.
		830
		831	If you cannot run the fd in non-blocking mode (for example you should not
		832	play around with an Xlib connection), then you have to seperately re-test
		833	wether a file descriptor is really ready with a known-to-be good interface
		834	such as poll (fortunately in our Xlib example, Xlib already does this on
		835	its own, so its quite safe to use).
456		836
457	=over 4	837	=over 4
458		838
459	=item ev_io_init (ev_io *, callback, int fd, int events)	839	=item ev_io_init (ev_io *, callback, int fd, int events)
460		840
461	=item ev_io_set (ev_io *, int fd, int events)	841	=item ev_io_set (ev_io *, int fd, int events)
462		842
463	Configures an C<ev_io> watcher. The fd is the file descriptor to rceeive	843	Configures an C<ev_io> watcher. The C<fd> is the file descriptor to
464	events for and events is either C<EV_READ>, C<EV_WRITE> or C<EV_READ |	844	rceeive events for and events is either C<EV_READ>, C<EV_WRITE> or
465	EV_WRITE> to receive the given events.	845	C<EV_READ | EV_WRITE> to receive the given events.
		846
		847	=item int fd [read-only]
		848
		849	The file descriptor being watched.
		850
		851	=item int events [read-only]
		852
		853	The events being watched.
466		854
467	=back	855	=back
468		856
		857	Example: Call C<stdin_readable_cb> when STDIN_FILENO has become, well
		858	readable, but only once. Since it is likely line-buffered, you could
		859	attempt to read a whole line in the callback.
		860
		861	static void
		862	stdin_readable_cb (struct ev_loop *loop, struct ev_io *w, int revents)
		863	{
		864	ev_io_stop (loop, w);
		865	.. read from stdin here (or from w->fd) and haqndle any I/O errors
		866	}
		867
		868	...
		869	struct ev_loop *loop = ev_default_init (0);
		870	struct ev_io stdin_readable;
		871	ev_io_init (&stdin_readable, stdin_readable_cb, STDIN_FILENO, EV_READ);
		872	ev_io_start (loop, &stdin_readable);
		873	ev_loop (loop, 0);
		874
		875
469	=head2 C<ev_timer> - relative and optionally recurring timeouts	876	=head2 C<ev_timer> - relative and optionally repeating timeouts
470		877
471	Timer watchers are simple relative timers that generate an event after a	878	Timer watchers are simple relative timers that generate an event after a
472	given time, and optionally repeating in regular intervals after that.	879	given time, and optionally repeating in regular intervals after that.
473		880
474	The timers are based on real time, that is, if you register an event that	881	The timers are based on real time, that is, if you register an event that
475	times out after an hour and you reset your system clock to last years	882	times out after an hour and you reset your system clock to last years
476	time, it will still time out after (roughly) and hour. "Roughly" because	883	time, it will still time out after (roughly) and hour. "Roughly" because
477	detecting time jumps is hard, and soem inaccuracies are unavoidable (the	884	detecting time jumps is hard, and some inaccuracies are unavoidable (the
478	monotonic clock option helps a lot here).	885	monotonic clock option helps a lot here).
479		886
480	The relative timeouts are calculated relative to the C<ev_now ()>	887	The relative timeouts are calculated relative to the C<ev_now ()>
481	time. This is usually the right thing as this timestamp refers to the time	888	time. This is usually the right thing as this timestamp refers to the time
482	of the event triggering whatever timeout you are modifying/starting. If	889	of the event triggering whatever timeout you are modifying/starting. If
483	you suspect event processing to be delayed and you *need* to base the timeout	890	you suspect event processing to be delayed and you I<need> to base the timeout
484	on the current time, use something like this to adjust for this:	891	on the current time, use something like this to adjust for this:
485		892
486	ev_timer_set (&timer, after + ev_now () - ev_time (), 0.);	893	ev_timer_set (&timer, after + ev_now () - ev_time (), 0.);
		894
		895	The callback is guarenteed to be invoked only when its timeout has passed,
		896	but if multiple timers become ready during the same loop iteration then
		897	order of execution is undefined.
487		898
488	=over 4	899	=over 4
489		900
490	=item ev_timer_init (ev_timer *, callback, ev_tstamp after, ev_tstamp repeat)	901	=item ev_timer_init (ev_timer *, callback, ev_tstamp after, ev_tstamp repeat)
491		902
…		…
505	=item ev_timer_again (loop)	916	=item ev_timer_again (loop)
506		917
507	This will act as if the timer timed out and restart it again if it is	918	This will act as if the timer timed out and restart it again if it is
508	repeating. The exact semantics are:	919	repeating. The exact semantics are:
509		920
		921	If the timer is pending, its pending status is cleared.
		922
510	If the timer is started but nonrepeating, stop it.	923	If the timer is started but nonrepeating, stop it (as if it timed out).
511		924
512	If the timer is repeating, either start it if necessary (with the repeat	925	If the timer is repeating, either start it if necessary (with the
513	value), or reset the running timer to the repeat value.	926	C<repeat> value), or reset the running timer to the C<repeat> value.
514		927
515	This sounds a bit complicated, but here is a useful and typical	928	This sounds a bit complicated, but here is a useful and typical
516	example: Imagine you have a tcp connection and you want a so-called idle	929	example: Imagine you have a tcp connection and you want a so-called idle
517	timeout, that is, you want to be called when there have been, say, 60	930	timeout, that is, you want to be called when there have been, say, 60
518	seconds of inactivity on the socket. The easiest way to do this is to	931	seconds of inactivity on the socket. The easiest way to do this is to
519	configure an C<ev_timer> with after=repeat=60 and calling ev_timer_again each	932	configure an C<ev_timer> with a C<repeat> value of C<60> and then call
520	time you successfully read or write some data. If you go into an idle	933	C<ev_timer_again> each time you successfully read or write some data. If
521	state where you do not expect data to travel on the socket, you can stop	934	you go into an idle state where you do not expect data to travel on the
522	the timer, and again will automatically restart it if need be.	935	socket, you can C<ev_timer_stop> the timer, and C<ev_timer_again> will
		936	automatically restart it if need be.
		937
		938	That means you can ignore the C<after> value and C<ev_timer_start>
		939	altogether and only ever use the C<repeat> value and C<ev_timer_again>:
		940
		941	ev_timer_init (timer, callback, 0., 5.);
		942	ev_timer_again (loop, timer);
		943	...
		944	timer->again = 17.;
		945	ev_timer_again (loop, timer);
		946	...
		947	timer->again = 10.;
		948	ev_timer_again (loop, timer);
		949
		950	This is more slightly efficient then stopping/starting the timer each time
		951	you want to modify its timeout value.
		952
		953	=item ev_tstamp repeat [read-write]
		954
		955	The current C<repeat> value. Will be used each time the watcher times out
		956	or C<ev_timer_again> is called and determines the next timeout (if any),
		957	which is also when any modifications are taken into account.
523		958
524	=back	959	=back
525		960
		961	Example: Create a timer that fires after 60 seconds.
		962
		963	static void
		964	one_minute_cb (struct ev_loop *loop, struct ev_timer *w, int revents)
		965	{
		966	.. one minute over, w is actually stopped right here
		967	}
		968
		969	struct ev_timer mytimer;
		970	ev_timer_init (&mytimer, one_minute_cb, 60., 0.);
		971	ev_timer_start (loop, &mytimer);
		972
		973	Example: Create a timeout timer that times out after 10 seconds of
		974	inactivity.
		975
		976	static void
		977	timeout_cb (struct ev_loop *loop, struct ev_timer *w, int revents)
		978	{
		979	.. ten seconds without any activity
		980	}
		981
		982	struct ev_timer mytimer;
		983	ev_timer_init (&mytimer, timeout_cb, 0., 10.); /* note, only repeat used */
		984	ev_timer_again (&mytimer); /* start timer */
		985	ev_loop (loop, 0);
		986
		987	// and in some piece of code that gets executed on any "activity":
		988	// reset the timeout to start ticking again at 10 seconds
		989	ev_timer_again (&mytimer);
		990
		991
526	=head2 C<ev_periodic> - to cron or not to cron	992	=head2 C<ev_periodic> - to cron or not to cron?
527		993
528	Periodic watchers are also timers of a kind, but they are very versatile	994	Periodic watchers are also timers of a kind, but they are very versatile
529	(and unfortunately a bit complex).	995	(and unfortunately a bit complex).
530		996
531	Unlike C<ev_timer>'s, they are not based on real time (or relative time)	997	Unlike C<ev_timer>'s, they are not based on real time (or relative time)
532	but on wallclock time (absolute time). You can tell a periodic watcher	998	but on wallclock time (absolute time). You can tell a periodic watcher
533	to trigger "at" some specific point in time. For example, if you tell a	999	to trigger "at" some specific point in time. For example, if you tell a
534	periodic watcher to trigger in 10 seconds (by specifiying e.g. c<ev_now ()	1000	periodic watcher to trigger in 10 seconds (by specifiying e.g. C<ev_now ()
535	+ 10.>) and then reset your system clock to the last year, then it will	1001	+ 10.>) and then reset your system clock to the last year, then it will
536	take a year to trigger the event (unlike an C<ev_timer>, which would trigger	1002	take a year to trigger the event (unlike an C<ev_timer>, which would trigger
537	roughly 10 seconds later and of course not if you reset your system time	1003	roughly 10 seconds later and of course not if you reset your system time
538	again).	1004	again).
539		1005
540	They can also be used to implement vastly more complex timers, such as	1006	They can also be used to implement vastly more complex timers, such as
541	triggering an event on eahc midnight, local time.	1007	triggering an event on eahc midnight, local time.
542		1008
		1009	As with timers, the callback is guarenteed to be invoked only when the
		1010	time (C<at>) has been passed, but if multiple periodic timers become ready
		1011	during the same loop iteration then order of execution is undefined.
		1012
543	=over 4	1013	=over 4
544		1014
545	=item ev_periodic_init (ev_periodic *, callback, ev_tstamp at, ev_tstamp interval, reschedule_cb)	1015	=item ev_periodic_init (ev_periodic *, callback, ev_tstamp at, ev_tstamp interval, reschedule_cb)
546		1016
547	=item ev_periodic_set (ev_periodic *, ev_tstamp after, ev_tstamp repeat, reschedule_cb)	1017	=item ev_periodic_set (ev_periodic *, ev_tstamp after, ev_tstamp repeat, reschedule_cb)
548		1018
549	Lots of arguments, lets sort it out... There are basically three modes of	1019	Lots of arguments, lets sort it out... There are basically three modes of
550	operation, and we will explain them from simplest to complex:	1020	operation, and we will explain them from simplest to complex:
551
552		1021
553	=over 4	1022	=over 4
554		1023
555	=item * absolute timer (interval = reschedule_cb = 0)	1024	=item * absolute timer (interval = reschedule_cb = 0)
556		1025
…		…
620	Simply stops and restarts the periodic watcher again. This is only useful	1089	Simply stops and restarts the periodic watcher again. This is only useful
621	when you changed some parameters or the reschedule callback would return	1090	when you changed some parameters or the reschedule callback would return
622	a different time than the last time it was called (e.g. in a crond like	1091	a different time than the last time it was called (e.g. in a crond like
623	program when the crontabs have changed).	1092	program when the crontabs have changed).
624		1093
		1094	=item ev_tstamp interval [read-write]
		1095
		1096	The current interval value. Can be modified any time, but changes only
		1097	take effect when the periodic timer fires or C<ev_periodic_again> is being
		1098	called.
		1099
		1100	=item ev_tstamp (*reschedule_cb)(struct ev_periodic *w, ev_tstamp now) [read-write]
		1101
		1102	The current reschedule callback, or C<0>, if this functionality is
		1103	switched off. Can be changed any time, but changes only take effect when
		1104	the periodic timer fires or C<ev_periodic_again> is being called.
		1105
625	=back	1106	=back
626		1107
		1108	Example: Call a callback every hour, or, more precisely, whenever the
		1109	system clock is divisible by 3600. The callback invocation times have
		1110	potentially a lot of jittering, but good long-term stability.
		1111
		1112	static void
		1113	clock_cb (struct ev_loop *loop, struct ev_io *w, int revents)
		1114	{
		1115	... its now a full hour (UTC, or TAI or whatever your clock follows)
		1116	}
		1117
		1118	struct ev_periodic hourly_tick;
		1119	ev_periodic_init (&hourly_tick, clock_cb, 0., 3600., 0);
		1120	ev_periodic_start (loop, &hourly_tick);
		1121
		1122	Example: The same as above, but use a reschedule callback to do it:
		1123
		1124	#include <math.h>
		1125
		1126	static ev_tstamp
		1127	my_scheduler_cb (struct ev_periodic *w, ev_tstamp now)
		1128	{
		1129	return fmod (now, 3600.) + 3600.;
		1130	}
		1131
		1132	ev_periodic_init (&hourly_tick, clock_cb, 0., 0., my_scheduler_cb);
		1133
		1134	Example: Call a callback every hour, starting now:
		1135
		1136	struct ev_periodic hourly_tick;
		1137	ev_periodic_init (&hourly_tick, clock_cb,
		1138	fmod (ev_now (loop), 3600.), 3600., 0);
		1139	ev_periodic_start (loop, &hourly_tick);
		1140
		1141
627	=head2 C<ev_signal> - signal me when a signal gets signalled	1142	=head2 C<ev_signal> - signal me when a signal gets signalled!
628		1143
629	Signal watchers will trigger an event when the process receives a specific	1144	Signal watchers will trigger an event when the process receives a specific
630	signal one or more times. Even though signals are very asynchronous, libev	1145	signal one or more times. Even though signals are very asynchronous, libev
631	will try it's best to deliver signals synchronously, i.e. as part of the	1146	will try it's best to deliver signals synchronously, i.e. as part of the
632	normal event processing, like any other event.	1147	normal event processing, like any other event.
…		…
645	=item ev_signal_set (ev_signal *, int signum)	1160	=item ev_signal_set (ev_signal *, int signum)
646		1161
647	Configures the watcher to trigger on the given signal number (usually one	1162	Configures the watcher to trigger on the given signal number (usually one
648	of the C<SIGxxx> constants).	1163	of the C<SIGxxx> constants).
649		1164
		1165	=item int signum [read-only]
		1166
		1167	The signal the watcher watches out for.
		1168
650	=back	1169	=back
651		1170
		1171
652	=head2 C<ev_child> - wait for pid status changes	1172	=head2 C<ev_child> - watch out for process status changes
653		1173
654	Child watchers trigger when your process receives a SIGCHLD in response to	1174	Child watchers trigger when your process receives a SIGCHLD in response to
655	some child status changes (most typically when a child of yours dies).	1175	some child status changes (most typically when a child of yours dies).
656		1176
657	=over 4	1177	=over 4
…		…
665	at the C<rstatus> member of the C<ev_child> watcher structure to see	1185	at the C<rstatus> member of the C<ev_child> watcher structure to see
666	the status word (use the macros from C<sys/wait.h> and see your systems	1186	the status word (use the macros from C<sys/wait.h> and see your systems
667	C<waitpid> documentation). The C<rpid> member contains the pid of the	1187	C<waitpid> documentation). The C<rpid> member contains the pid of the
668	process causing the status change.	1188	process causing the status change.
669		1189
		1190	=item int pid [read-only]
		1191
		1192	The process id this watcher watches out for, or C<0>, meaning any process id.
		1193
		1194	=item int rpid [read-write]
		1195
		1196	The process id that detected a status change.
		1197
		1198	=item int rstatus [read-write]
		1199
		1200	The process exit/trace status caused by C<rpid> (see your systems
		1201	C<waitpid> and C<sys/wait.h> documentation for details).
		1202
670	=back	1203	=back
671		1204
		1205	Example: Try to exit cleanly on SIGINT and SIGTERM.
		1206
		1207	static void
		1208	sigint_cb (struct ev_loop *loop, struct ev_signal *w, int revents)
		1209	{
		1210	ev_unloop (loop, EVUNLOOP_ALL);
		1211	}
		1212
		1213	struct ev_signal signal_watcher;
		1214	ev_signal_init (&signal_watcher, sigint_cb, SIGINT);
		1215	ev_signal_start (loop, &sigint_cb);
		1216
		1217
		1218	=head2 C<ev_stat> - did the file attributes just change?
		1219
		1220	This watches a filesystem path for attribute changes. That is, it calls
		1221	C<stat> regularly (or when the OS says it changed) and sees if it changed
		1222	compared to the last time, invoking the callback if it did.
		1223
		1224	The path does not need to exist: changing from "path exists" to "path does
		1225	not exist" is a status change like any other. The condition "path does
		1226	not exist" is signified by the C<st_nlink> field being zero (which is
		1227	otherwise always forced to be at least one) and all the other fields of
		1228	the stat buffer having unspecified contents.
		1229
		1230	The path I<should> be absolute and I<must not> end in a slash. If it is
		1231	relative and your working directory changes, the behaviour is undefined.
		1232
		1233	Since there is no standard to do this, the portable implementation simply
		1234	calls C<stat (2)> regularly on the path to see if it changed somehow. You
		1235	can specify a recommended polling interval for this case. If you specify
		1236	a polling interval of C<0> (highly recommended!) then a I<suitable,
		1237	unspecified default> value will be used (which you can expect to be around
		1238	five seconds, although this might change dynamically). Libev will also
		1239	impose a minimum interval which is currently around C<0.1>, but thats
		1240	usually overkill.
		1241
		1242	This watcher type is not meant for massive numbers of stat watchers,
		1243	as even with OS-supported change notifications, this can be
		1244	resource-intensive.
		1245
		1246	At the time of this writing, only the Linux inotify interface is
		1247	implemented (implementing kqueue support is left as an exercise for the
		1248	reader). Inotify will be used to give hints only and should not change the
		1249	semantics of C<ev_stat> watchers, which means that libev sometimes needs
		1250	to fall back to regular polling again even with inotify, but changes are
		1251	usually detected immediately, and if the file exists there will be no
		1252	polling.
		1253
		1254	=over 4
		1255
		1256	=item ev_stat_init (ev_stat *, callback, const char *path, ev_tstamp interval)
		1257
		1258	=item ev_stat_set (ev_stat *, const char *path, ev_tstamp interval)
		1259
		1260	Configures the watcher to wait for status changes of the given
		1261	C<path>. The C<interval> is a hint on how quickly a change is expected to
		1262	be detected and should normally be specified as C<0> to let libev choose
		1263	a suitable value. The memory pointed to by C<path> must point to the same
		1264	path for as long as the watcher is active.
		1265
		1266	The callback will be receive C<EV_STAT> when a change was detected,
		1267	relative to the attributes at the time the watcher was started (or the
		1268	last change was detected).
		1269
		1270	=item ev_stat_stat (ev_stat *)
		1271
		1272	Updates the stat buffer immediately with new values. If you change the
		1273	watched path in your callback, you could call this fucntion to avoid
		1274	detecting this change (while introducing a race condition). Can also be
		1275	useful simply to find out the new values.
		1276
		1277	=item ev_statdata attr [read-only]
		1278
		1279	The most-recently detected attributes of the file. Although the type is of
		1280	C<ev_statdata>, this is usually the (or one of the) C<struct stat> types
		1281	suitable for your system. If the C<st_nlink> member is C<0>, then there
		1282	was some error while C<stat>ing the file.
		1283
		1284	=item ev_statdata prev [read-only]
		1285
		1286	The previous attributes of the file. The callback gets invoked whenever
		1287	C<prev> != C<attr>.
		1288
		1289	=item ev_tstamp interval [read-only]
		1290
		1291	The specified interval.
		1292
		1293	=item const char *path [read-only]
		1294
		1295	The filesystem path that is being watched.
		1296
		1297	=back
		1298
		1299	Example: Watch C</etc/passwd> for attribute changes.
		1300
		1301	static void
		1302	passwd_cb (struct ev_loop *loop, ev_stat *w, int revents)
		1303	{
		1304	/* /etc/passwd changed in some way */
		1305	if (w->attr.st_nlink)
		1306	{
		1307	printf ("passwd current size %ld\n", (long)w->attr.st_size);
		1308	printf ("passwd current atime %ld\n", (long)w->attr.st_mtime);
		1309	printf ("passwd current mtime %ld\n", (long)w->attr.st_mtime);
		1310	}
		1311	else
		1312	/* you shalt not abuse printf for puts */
		1313	puts ("wow, /etc/passwd is not there, expect problems. "
		1314	"if this is windows, they already arrived\n");
		1315	}
		1316
		1317	...
		1318	ev_stat passwd;
		1319
		1320	ev_stat_init (&passwd, passwd_cb, "/etc/passwd");
		1321	ev_stat_start (loop, &passwd);
		1322
		1323
672	=head2 C<ev_idle> - when you've got nothing better to do	1324	=head2 C<ev_idle> - when you've got nothing better to do...
673		1325
674	Idle watchers trigger events when there are no other events are pending	1326	Idle watchers trigger events when there are no other events are pending
675	(prepare, check and other idle watchers do not count). That is, as long	1327	(prepare, check and other idle watchers do not count). That is, as long
676	as your process is busy handling sockets or timeouts (or even signals,	1328	as your process is busy handling sockets or timeouts (or even signals,
677	imagine) it will not be triggered. But when your process is idle all idle	1329	imagine) it will not be triggered. But when your process is idle all idle
…		…
695	kind. There is a C<ev_idle_set> macro, but using it is utterly pointless,	1347	kind. There is a C<ev_idle_set> macro, but using it is utterly pointless,
696	believe me.	1348	believe me.
697		1349
698	=back	1350	=back
699		1351
		1352	Example: Dynamically allocate an C<ev_idle> watcher, start it, and in the
		1353	callback, free it. Also, use no error checking, as usual.
		1354
		1355	static void
		1356	idle_cb (struct ev_loop *loop, struct ev_idle *w, int revents)
		1357	{
		1358	free (w);
		1359	// now do something you wanted to do when the program has
		1360	// no longer asnything immediate to do.
		1361	}
		1362
		1363	struct ev_idle *idle_watcher = malloc (sizeof (struct ev_idle));
		1364	ev_idle_init (idle_watcher, idle_cb);
		1365	ev_idle_start (loop, idle_cb);
		1366
		1367
700	=head2 C<ev_prepare> and C<ev_check> - customise your event loop	1368	=head2 C<ev_prepare> and C<ev_check> - customise your event loop!
701		1369
702	Prepare and check watchers are usually (but not always) used in tandem:	1370	Prepare and check watchers are usually (but not always) used in tandem:
703	prepare watchers get invoked before the process blocks and check watchers	1371	prepare watchers get invoked before the process blocks and check watchers
704	afterwards.	1372	afterwards.
705		1373
		1374	You I<must not> call C<ev_loop> or similar functions that enter
		1375	the current event loop from either C<ev_prepare> or C<ev_check>
		1376	watchers. Other loops than the current one are fine, however. The
		1377	rationale behind this is that you do not need to check for recursion in
		1378	those watchers, i.e. the sequence will always be C<ev_prepare>, blocking,
		1379	C<ev_check> so if you have one watcher of each kind they will always be
		1380	called in pairs bracketing the blocking call.
		1381
706	Their main purpose is to integrate other event mechanisms into libev. This	1382	Their main purpose is to integrate other event mechanisms into libev and
707	could be used, for example, to track variable changes, implement your own	1383	their use is somewhat advanced. This could be used, for example, to track
708	watchers, integrate net-snmp or a coroutine library and lots more.	1384	variable changes, implement your own watchers, integrate net-snmp or a
		1385	coroutine library and lots more. They are also occasionally useful if
		1386	you cache some data and want to flush it before blocking (for example,
		1387	in X programs you might want to do an C<XFlush ()> in an C<ev_prepare>
		1388	watcher).
709		1389
710	This is done by examining in each prepare call which file descriptors need	1390	This is done by examining in each prepare call which file descriptors need
711	to be watched by the other library, registering C<ev_io> watchers for	1391	to be watched by the other library, registering C<ev_io> watchers for
712	them and starting an C<ev_timer> watcher for any timeouts (many libraries	1392	them and starting an C<ev_timer> watcher for any timeouts (many libraries
713	provide just this functionality). Then, in the check watcher you check for	1393	provide just this functionality). Then, in the check watcher you check for
…		…
735	parameters of any kind. There are C<ev_prepare_set> and C<ev_check_set>	1415	parameters of any kind. There are C<ev_prepare_set> and C<ev_check_set>
736	macros, but using them is utterly, utterly and completely pointless.	1416	macros, but using them is utterly, utterly and completely pointless.
737		1417
738	=back	1418	=back
739		1419
		1420	Example: To include a library such as adns, you would add IO watchers
		1421	and a timeout watcher in a prepare handler, as required by libadns, and
		1422	in a check watcher, destroy them and call into libadns. What follows is
		1423	pseudo-code only of course:
		1424
		1425	static ev_io iow [nfd];
		1426	static ev_timer tw;
		1427
		1428	static void
		1429	io_cb (ev_loop *loop, ev_io *w, int revents)
		1430	{
		1431	// set the relevant poll flags
		1432	// could also call adns_processreadable etc. here
		1433	struct pollfd *fd = (struct pollfd *)w->data;
		1434	if (revents & EV_READ ) fd->revents |= fd->events & POLLIN;
		1435	if (revents & EV_WRITE) fd->revents |= fd->events & POLLOUT;
		1436	}
		1437
		1438	// create io watchers for each fd and a timer before blocking
		1439	static void
		1440	adns_prepare_cb (ev_loop *loop, ev_prepare *w, int revents)
		1441	{
		1442	int timeout = 3600000;truct pollfd fds [nfd];
		1443	// actual code will need to loop here and realloc etc.
		1444	adns_beforepoll (ads, fds, &nfd, &timeout, timeval_from (ev_time ()));
		1445
		1446	/* the callback is illegal, but won't be called as we stop during check */
		1447	ev_timer_init (&tw, 0, timeout * 1e-3);
		1448	ev_timer_start (loop, &tw);
		1449
		1450	// create on ev_io per pollfd
		1451	for (int i = 0; i < nfd; ++i)
		1452	{
		1453	ev_io_init (iow + i, io_cb, fds [i].fd,
		1454	((fds [i].events & POLLIN ? EV_READ : 0)
		1455	| (fds [i].events & POLLOUT ? EV_WRITE : 0)));
		1456
		1457	fds [i].revents = 0;
		1458	iow [i].data = fds + i;
		1459	ev_io_start (loop, iow + i);
		1460	}
		1461	}
		1462
		1463	// stop all watchers after blocking
		1464	static void
		1465	adns_check_cb (ev_loop *loop, ev_check *w, int revents)
		1466	{
		1467	ev_timer_stop (loop, &tw);
		1468
		1469	for (int i = 0; i < nfd; ++i)
		1470	ev_io_stop (loop, iow + i);
		1471
		1472	adns_afterpoll (adns, fds, nfd, timeval_from (ev_now (loop));
		1473	}
		1474
		1475
		1476	=head2 C<ev_embed> - when one backend isn't enough...
		1477
		1478	This is a rather advanced watcher type that lets you embed one event loop
		1479	into another (currently only C<ev_io> events are supported in the embedded
		1480	loop, other types of watchers might be handled in a delayed or incorrect
		1481	fashion and must not be used).
		1482
		1483	There are primarily two reasons you would want that: work around bugs and
		1484	prioritise I/O.
		1485
		1486	As an example for a bug workaround, the kqueue backend might only support
		1487	sockets on some platform, so it is unusable as generic backend, but you
		1488	still want to make use of it because you have many sockets and it scales
		1489	so nicely. In this case, you would create a kqueue-based loop and embed it
		1490	into your default loop (which might use e.g. poll). Overall operation will
		1491	be a bit slower because first libev has to poll and then call kevent, but
		1492	at least you can use both at what they are best.
		1493
		1494	As for prioritising I/O: rarely you have the case where some fds have
		1495	to be watched and handled very quickly (with low latency), and even
		1496	priorities and idle watchers might have too much overhead. In this case
		1497	you would put all the high priority stuff in one loop and all the rest in
		1498	a second one, and embed the second one in the first.
		1499
		1500	As long as the watcher is active, the callback will be invoked every time
		1501	there might be events pending in the embedded loop. The callback must then
		1502	call C<ev_embed_sweep (mainloop, watcher)> to make a single sweep and invoke
		1503	their callbacks (you could also start an idle watcher to give the embedded
		1504	loop strictly lower priority for example). You can also set the callback
		1505	to C<0>, in which case the embed watcher will automatically execute the
		1506	embedded loop sweep.
		1507
		1508	As long as the watcher is started it will automatically handle events. The
		1509	callback will be invoked whenever some events have been handled. You can
		1510	set the callback to C<0> to avoid having to specify one if you are not
		1511	interested in that.
		1512
		1513	Also, there have not currently been made special provisions for forking:
		1514	when you fork, you not only have to call C<ev_loop_fork> on both loops,
		1515	but you will also have to stop and restart any C<ev_embed> watchers
		1516	yourself.
		1517
		1518	Unfortunately, not all backends are embeddable, only the ones returned by
		1519	C<ev_embeddable_backends> are, which, unfortunately, does not include any
		1520	portable one.
		1521
		1522	So when you want to use this feature you will always have to be prepared
		1523	that you cannot get an embeddable loop. The recommended way to get around
		1524	this is to have a separate variables for your embeddable loop, try to
		1525	create it, and if that fails, use the normal loop for everything:
		1526
		1527	struct ev_loop *loop_hi = ev_default_init (0);
		1528	struct ev_loop *loop_lo = 0;
		1529	struct ev_embed embed;
		1530
		1531	// see if there is a chance of getting one that works
		1532	// (remember that a flags value of 0 means autodetection)
		1533	loop_lo = ev_embeddable_backends () & ev_recommended_backends ()
		1534	? ev_loop_new (ev_embeddable_backends () & ev_recommended_backends ())
		1535	: 0;
		1536
		1537	// if we got one, then embed it, otherwise default to loop_hi
		1538	if (loop_lo)
		1539	{
		1540	ev_embed_init (&embed, 0, loop_lo);
		1541	ev_embed_start (loop_hi, &embed);
		1542	}
		1543	else
		1544	loop_lo = loop_hi;
		1545
		1546	=over 4
		1547
		1548	=item ev_embed_init (ev_embed *, callback, struct ev_loop *embedded_loop)
		1549
		1550	=item ev_embed_set (ev_embed *, callback, struct ev_loop *embedded_loop)
		1551
		1552	Configures the watcher to embed the given loop, which must be
		1553	embeddable. If the callback is C<0>, then C<ev_embed_sweep> will be
		1554	invoked automatically, otherwise it is the responsibility of the callback
		1555	to invoke it (it will continue to be called until the sweep has been done,
		1556	if you do not want thta, you need to temporarily stop the embed watcher).
		1557
		1558	=item ev_embed_sweep (loop, ev_embed *)
		1559
		1560	Make a single, non-blocking sweep over the embedded loop. This works
		1561	similarly to C<ev_loop (embedded_loop, EVLOOP_NONBLOCK)>, but in the most
		1562	apropriate way for embedded loops.
		1563
		1564	=item struct ev_loop *loop [read-only]
		1565
		1566	The embedded event loop.
		1567
		1568	=back
		1569
		1570
		1571	=head2 C<ev_fork> - the audacity to resume the event loop after a fork
		1572
		1573	Fork watchers are called when a C<fork ()> was detected (usually because
		1574	whoever is a good citizen cared to tell libev about it by calling
		1575	C<ev_default_fork> or C<ev_loop_fork>). The invocation is done before the
		1576	event loop blocks next and before C<ev_check> watchers are being called,
		1577	and only in the child after the fork. If whoever good citizen calling
		1578	C<ev_default_fork> cheats and calls it in the wrong process, the fork
		1579	handlers will be invoked, too, of course.
		1580
		1581	=over 4
		1582
		1583	=item ev_fork_init (ev_signal *, callback)
		1584
		1585	Initialises and configures the fork watcher - it has no parameters of any
		1586	kind. There is a C<ev_fork_set> macro, but using it is utterly pointless,
		1587	believe me.
		1588
		1589	=back
		1590
		1591
740	=head1 OTHER FUNCTIONS	1592	=head1 OTHER FUNCTIONS
741		1593
742	There are some other functions of possible interest. Described. Here. Now.	1594	There are some other functions of possible interest. Described. Here. Now.
743		1595
744	=over 4	1596	=over 4
…		…
773	/* stdin might have data for us, joy! */;	1625	/* stdin might have data for us, joy! */;
774	}	1626	}
775		1627
776	ev_once (STDIN_FILENO, EV_READ, 10., stdin_ready, 0);	1628	ev_once (STDIN_FILENO, EV_READ, 10., stdin_ready, 0);
777		1629
778	=item ev_feed_event (loop, watcher, int events)	1630	=item ev_feed_event (ev_loop *, watcher *, int revents)
779		1631
780	Feeds the given event set into the event loop, as if the specified event	1632	Feeds the given event set into the event loop, as if the specified event
781	had happened for the specified watcher (which must be a pointer to an	1633	had happened for the specified watcher (which must be a pointer to an
782	initialised but not necessarily started event watcher).	1634	initialised but not necessarily started event watcher).
783		1635
784	=item ev_feed_fd_event (loop, int fd, int revents)	1636	=item ev_feed_fd_event (ev_loop *, int fd, int revents)
785		1637
786	Feed an event on the given fd, as if a file descriptor backend detected	1638	Feed an event on the given fd, as if a file descriptor backend detected
787	the given events it.	1639	the given events it.
788		1640
789	=item ev_feed_signal_event (loop, int signum)	1641	=item ev_feed_signal_event (ev_loop *loop, int signum)
790		1642
791	Feed an event as if the given signal occured (loop must be the default loop!).	1643	Feed an event as if the given signal occured (C<loop> must be the default
		1644	loop!).
792		1645
793	=back	1646	=back
		1647
794		1648
795	=head1 LIBEVENT EMULATION	1649	=head1 LIBEVENT EMULATION
796		1650
797	Libev offers a compatibility emulation layer for libevent. It cannot	1651	Libev offers a compatibility emulation layer for libevent. It cannot
798	emulate the internals of libevent, so here are some usage hints:	1652	emulate the internals of libevent, so here are some usage hints:
…		…
819		1673
820	=back	1674	=back
821		1675
822	=head1 C++ SUPPORT	1676	=head1 C++ SUPPORT
823		1677
824	TBD.	1678	Libev comes with some simplistic wrapper classes for C++ that mainly allow
		1679	you to use some convinience methods to start/stop watchers and also change
		1680	the callback model to a model using method callbacks on objects.
		1681
		1682	To use it,
		1683
		1684	#include <ev++.h>
		1685
		1686	(it is not installed by default). This automatically includes F<ev.h>
		1687	and puts all of its definitions (many of them macros) into the global
		1688	namespace. All C++ specific things are put into the C<ev> namespace.
		1689
		1690	It should support all the same embedding options as F<ev.h>, most notably
		1691	C<EV_MULTIPLICITY>.
		1692
		1693	Here is a list of things available in the C<ev> namespace:
		1694
		1695	=over 4
		1696
		1697	=item C<ev::READ>, C<ev::WRITE> etc.
		1698
		1699	These are just enum values with the same values as the C<EV_READ> etc.
		1700	macros from F<ev.h>.
		1701
		1702	=item C<ev::tstamp>, C<ev::now>
		1703
		1704	Aliases to the same types/functions as with the C<ev_> prefix.
		1705
		1706	=item C<ev::io>, C<ev::timer>, C<ev::periodic>, C<ev::idle>, C<ev::sig> etc.
		1707
		1708	For each C<ev_TYPE> watcher in F<ev.h> there is a corresponding class of
		1709	the same name in the C<ev> namespace, with the exception of C<ev_signal>
		1710	which is called C<ev::sig> to avoid clashes with the C<signal> macro
		1711	defines by many implementations.
		1712
		1713	All of those classes have these methods:
		1714
		1715	=over 4
		1716
		1717	=item ev::TYPE::TYPE (object *, object::method *)
		1718
		1719	=item ev::TYPE::TYPE (object *, object::method *, struct ev_loop *)
		1720
		1721	=item ev::TYPE::~TYPE
		1722
		1723	The constructor takes a pointer to an object and a method pointer to
		1724	the event handler callback to call in this class. The constructor calls
		1725	C<ev_init> for you, which means you have to call the C<set> method
		1726	before starting it. If you do not specify a loop then the constructor
		1727	automatically associates the default loop with this watcher.
		1728
		1729	The destructor automatically stops the watcher if it is active.
		1730
		1731	=item w->set (struct ev_loop *)
		1732
		1733	Associates a different C<struct ev_loop> with this watcher. You can only
		1734	do this when the watcher is inactive (and not pending either).
		1735
		1736	=item w->set ([args])
		1737
		1738	Basically the same as C<ev_TYPE_set>, with the same args. Must be
		1739	called at least once. Unlike the C counterpart, an active watcher gets
		1740	automatically stopped and restarted.
		1741
		1742	=item w->start ()
		1743
		1744	Starts the watcher. Note that there is no C<loop> argument as the
		1745	constructor already takes the loop.
		1746
		1747	=item w->stop ()
		1748
		1749	Stops the watcher if it is active. Again, no C<loop> argument.
		1750
		1751	=item w->again () C<ev::timer>, C<ev::periodic> only
		1752
		1753	For C<ev::timer> and C<ev::periodic>, this invokes the corresponding
		1754	C<ev_TYPE_again> function.
		1755
		1756	=item w->sweep () C<ev::embed> only
		1757
		1758	Invokes C<ev_embed_sweep>.
		1759
		1760	=item w->update () C<ev::stat> only
		1761
		1762	Invokes C<ev_stat_stat>.
		1763
		1764	=back
		1765
		1766	=back
		1767
		1768	Example: Define a class with an IO and idle watcher, start one of them in
		1769	the constructor.
		1770
		1771	class myclass
		1772	{
		1773	ev_io io; void io_cb (ev::io &w, int revents);
		1774	ev_idle idle void idle_cb (ev::idle &w, int revents);
		1775
		1776	myclass ();
		1777	}
		1778
		1779	myclass::myclass (int fd)
		1780	: io (this, &myclass::io_cb),
		1781	idle (this, &myclass::idle_cb)
		1782	{
		1783	io.start (fd, ev::READ);
		1784	}
		1785
		1786
		1787	=head1 MACRO MAGIC
		1788
		1789	Libev can be compiled with a variety of options, the most fundemantal is
		1790	C<EV_MULTIPLICITY>. This option determines wether (most) functions and
		1791	callbacks have an initial C<struct ev_loop *> argument.
		1792
		1793	To make it easier to write programs that cope with either variant, the
		1794	following macros are defined:
		1795
		1796	=over 4
		1797
		1798	=item C<EV_A>, C<EV_A_>
		1799
		1800	This provides the loop I<argument> for functions, if one is required ("ev
		1801	loop argument"). The C<EV_A> form is used when this is the sole argument,
		1802	C<EV_A_> is used when other arguments are following. Example:
		1803
		1804	ev_unref (EV_A);
		1805	ev_timer_add (EV_A_ watcher);
		1806	ev_loop (EV_A_ 0);
		1807
		1808	It assumes the variable C<loop> of type C<struct ev_loop *> is in scope,
		1809	which is often provided by the following macro.
		1810
		1811	=item C<EV_P>, C<EV_P_>
		1812
		1813	This provides the loop I<parameter> for functions, if one is required ("ev
		1814	loop parameter"). The C<EV_P> form is used when this is the sole parameter,
		1815	C<EV_P_> is used when other parameters are following. Example:
		1816
		1817	// this is how ev_unref is being declared
		1818	static void ev_unref (EV_P);
		1819
		1820	// this is how you can declare your typical callback
		1821	static void cb (EV_P_ ev_timer *w, int revents)
		1822
		1823	It declares a parameter C<loop> of type C<struct ev_loop *>, quite
		1824	suitable for use with C<EV_A>.
		1825
		1826	=item C<EV_DEFAULT>, C<EV_DEFAULT_>
		1827
		1828	Similar to the other two macros, this gives you the value of the default
		1829	loop, if multiple loops are supported ("ev loop default").
		1830
		1831	=back
		1832
		1833	Example: Declare and initialise a check watcher, working regardless of
		1834	wether multiple loops are supported or not.
		1835
		1836	static void
		1837	check_cb (EV_P_ ev_timer *w, int revents)
		1838	{
		1839	ev_check_stop (EV_A_ w);
		1840	}
		1841
		1842	ev_check check;
		1843	ev_check_init (&check, check_cb);
		1844	ev_check_start (EV_DEFAULT_ &check);
		1845	ev_loop (EV_DEFAULT_ 0);
		1846
		1847
		1848	=head1 EMBEDDING
		1849
		1850	Libev can (and often is) directly embedded into host
		1851	applications. Examples of applications that embed it include the Deliantra
		1852	Game Server, the EV perl module, the GNU Virtual Private Ethernet (gvpe)
		1853	and rxvt-unicode.
		1854
		1855	The goal is to enable you to just copy the neecssary files into your
		1856	source directory without having to change even a single line in them, so
		1857	you can easily upgrade by simply copying (or having a checked-out copy of
		1858	libev somewhere in your source tree).
		1859
		1860	=head2 FILESETS
		1861
		1862	Depending on what features you need you need to include one or more sets of files
		1863	in your app.
		1864
		1865	=head3 CORE EVENT LOOP
		1866
		1867	To include only the libev core (all the C<ev_*> functions), with manual
		1868	configuration (no autoconf):
		1869
		1870	#define EV_STANDALONE 1
		1871	#include "ev.c"
		1872
		1873	This will automatically include F<ev.h>, too, and should be done in a
		1874	single C source file only to provide the function implementations. To use
		1875	it, do the same for F<ev.h> in all files wishing to use this API (best
		1876	done by writing a wrapper around F<ev.h> that you can include instead and
		1877	where you can put other configuration options):
		1878
		1879	#define EV_STANDALONE 1
		1880	#include "ev.h"
		1881
		1882	Both header files and implementation files can be compiled with a C++
		1883	compiler (at least, thats a stated goal, and breakage will be treated
		1884	as a bug).
		1885
		1886	You need the following files in your source tree, or in a directory
		1887	in your include path (e.g. in libev/ when using -Ilibev):
		1888
		1889	ev.h
		1890	ev.c
		1891	ev_vars.h
		1892	ev_wrap.h
		1893
		1894	ev_win32.c required on win32 platforms only
		1895
		1896	ev_select.c only when select backend is enabled (which is by default)
		1897	ev_poll.c only when poll backend is enabled (disabled by default)
		1898	ev_epoll.c only when the epoll backend is enabled (disabled by default)
		1899	ev_kqueue.c only when the kqueue backend is enabled (disabled by default)
		1900	ev_port.c only when the solaris port backend is enabled (disabled by default)
		1901
		1902	F<ev.c> includes the backend files directly when enabled, so you only need
		1903	to compile this single file.
		1904
		1905	=head3 LIBEVENT COMPATIBILITY API
		1906
		1907	To include the libevent compatibility API, also include:
		1908
		1909	#include "event.c"
		1910
		1911	in the file including F<ev.c>, and:
		1912
		1913	#include "event.h"
		1914
		1915	in the files that want to use the libevent API. This also includes F<ev.h>.
		1916
		1917	You need the following additional files for this:
		1918
		1919	event.h
		1920	event.c
		1921
		1922	=head3 AUTOCONF SUPPORT
		1923
		1924	Instead of using C<EV_STANDALONE=1> and providing your config in
		1925	whatever way you want, you can also C<m4_include([libev.m4])> in your
		1926	F<configure.ac> and leave C<EV_STANDALONE> undefined. F<ev.c> will then
		1927	include F<config.h> and configure itself accordingly.
		1928
		1929	For this of course you need the m4 file:
		1930
		1931	libev.m4
		1932
		1933	=head2 PREPROCESSOR SYMBOLS/MACROS
		1934
		1935	Libev can be configured via a variety of preprocessor symbols you have to define
		1936	before including any of its files. The default is not to build for multiplicity
		1937	and only include the select backend.
		1938
		1939	=over 4
		1940
		1941	=item EV_STANDALONE
		1942
		1943	Must always be C<1> if you do not use autoconf configuration, which
		1944	keeps libev from including F<config.h>, and it also defines dummy
		1945	implementations for some libevent functions (such as logging, which is not
		1946	supported). It will also not define any of the structs usually found in
		1947	F<event.h> that are not directly supported by the libev core alone.
		1948
		1949	=item EV_USE_MONOTONIC
		1950
		1951	If defined to be C<1>, libev will try to detect the availability of the
		1952	monotonic clock option at both compiletime and runtime. Otherwise no use
		1953	of the monotonic clock option will be attempted. If you enable this, you
		1954	usually have to link against librt or something similar. Enabling it when
		1955	the functionality isn't available is safe, though, althoguh you have
		1956	to make sure you link against any libraries where the C<clock_gettime>
		1957	function is hiding in (often F<-lrt>).
		1958
		1959	=item EV_USE_REALTIME
		1960
		1961	If defined to be C<1>, libev will try to detect the availability of the
		1962	realtime clock option at compiletime (and assume its availability at
		1963	runtime if successful). Otherwise no use of the realtime clock option will
		1964	be attempted. This effectively replaces C<gettimeofday> by C<clock_get
		1965	(CLOCK_REALTIME, ...)> and will not normally affect correctness. See tzhe note about libraries
		1966	in the description of C<EV_USE_MONOTONIC>, though.
		1967
		1968	=item EV_USE_SELECT
		1969
		1970	If undefined or defined to be C<1>, libev will compile in support for the
		1971	C<select>(2) backend. No attempt at autodetection will be done: if no
		1972	other method takes over, select will be it. Otherwise the select backend
		1973	will not be compiled in.
		1974
		1975	=item EV_SELECT_USE_FD_SET
		1976
		1977	If defined to C<1>, then the select backend will use the system C<fd_set>
		1978	structure. This is useful if libev doesn't compile due to a missing
		1979	C<NFDBITS> or C<fd_mask> definition or it misguesses the bitset layout on
		1980	exotic systems. This usually limits the range of file descriptors to some
		1981	low limit such as 1024 or might have other limitations (winsocket only
		1982	allows 64 sockets). The C<FD_SETSIZE> macro, set before compilation, might
		1983	influence the size of the C<fd_set> used.
		1984
		1985	=item EV_SELECT_IS_WINSOCKET
		1986
		1987	When defined to C<1>, the select backend will assume that
		1988	select/socket/connect etc. don't understand file descriptors but
		1989	wants osf handles on win32 (this is the case when the select to
		1990	be used is the winsock select). This means that it will call
		1991	C<_get_osfhandle> on the fd to convert it to an OS handle. Otherwise,
		1992	it is assumed that all these functions actually work on fds, even
		1993	on win32. Should not be defined on non-win32 platforms.
		1994
		1995	=item EV_USE_POLL
		1996
		1997	If defined to be C<1>, libev will compile in support for the C<poll>(2)
		1998	backend. Otherwise it will be enabled on non-win32 platforms. It
		1999	takes precedence over select.
		2000
		2001	=item EV_USE_EPOLL
		2002
		2003	If defined to be C<1>, libev will compile in support for the Linux
		2004	C<epoll>(7) backend. Its availability will be detected at runtime,
		2005	otherwise another method will be used as fallback. This is the
		2006	preferred backend for GNU/Linux systems.
		2007
		2008	=item EV_USE_KQUEUE
		2009
		2010	If defined to be C<1>, libev will compile in support for the BSD style
		2011	C<kqueue>(2) backend. Its actual availability will be detected at runtime,
		2012	otherwise another method will be used as fallback. This is the preferred
		2013	backend for BSD and BSD-like systems, although on most BSDs kqueue only
		2014	supports some types of fds correctly (the only platform we found that
		2015	supports ptys for example was NetBSD), so kqueue might be compiled in, but
		2016	not be used unless explicitly requested. The best way to use it is to find
		2017	out whether kqueue supports your type of fd properly and use an embedded
		2018	kqueue loop.
		2019
		2020	=item EV_USE_PORT
		2021
		2022	If defined to be C<1>, libev will compile in support for the Solaris
		2023	10 port style backend. Its availability will be detected at runtime,
		2024	otherwise another method will be used as fallback. This is the preferred
		2025	backend for Solaris 10 systems.
		2026
		2027	=item EV_USE_DEVPOLL
		2028
		2029	reserved for future expansion, works like the USE symbols above.
		2030
		2031	=item EV_USE_INOTIFY
		2032
		2033	If defined to be C<1>, libev will compile in support for the Linux inotify
		2034	interface to speed up C<ev_stat> watchers. Its actual availability will
		2035	be detected at runtime.
		2036
		2037	=item EV_H
		2038
		2039	The name of the F<ev.h> header file used to include it. The default if
		2040	undefined is C<< <ev.h> >> in F<event.h> and C<"ev.h"> in F<ev.c>. This
		2041	can be used to virtually rename the F<ev.h> header file in case of conflicts.
		2042
		2043	=item EV_CONFIG_H
		2044
		2045	If C<EV_STANDALONE> isn't C<1>, this variable can be used to override
		2046	F<ev.c>'s idea of where to find the F<config.h> file, similarly to
		2047	C<EV_H>, above.
		2048
		2049	=item EV_EVENT_H
		2050
		2051	Similarly to C<EV_H>, this macro can be used to override F<event.c>'s idea
		2052	of how the F<event.h> header can be found.
		2053
		2054	=item EV_PROTOTYPES
		2055
		2056	If defined to be C<0>, then F<ev.h> will not define any function
		2057	prototypes, but still define all the structs and other symbols. This is
		2058	occasionally useful if you want to provide your own wrapper functions
		2059	around libev functions.
		2060
		2061	=item EV_MULTIPLICITY
		2062
		2063	If undefined or defined to C<1>, then all event-loop-specific functions
		2064	will have the C<struct ev_loop *> as first argument, and you can create
		2065	additional independent event loops. Otherwise there will be no support
		2066	for multiple event loops and there is no first event loop pointer
		2067	argument. Instead, all functions act on the single default loop.
		2068
		2069	=item EV_PERIODIC_ENABLE
		2070
		2071	If undefined or defined to be C<1>, then periodic timers are supported. If
		2072	defined to be C<0>, then they are not. Disabling them saves a few kB of
		2073	code.
		2074
		2075	=item EV_EMBED_ENABLE
		2076
		2077	If undefined or defined to be C<1>, then embed watchers are supported. If
		2078	defined to be C<0>, then they are not.
		2079
		2080	=item EV_STAT_ENABLE
		2081
		2082	If undefined or defined to be C<1>, then stat watchers are supported. If
		2083	defined to be C<0>, then they are not.
		2084
		2085	=item EV_FORK_ENABLE
		2086
		2087	If undefined or defined to be C<1>, then fork watchers are supported. If
		2088	defined to be C<0>, then they are not.
		2089
		2090	=item EV_MINIMAL
		2091
		2092	If you need to shave off some kilobytes of code at the expense of some
		2093	speed, define this symbol to C<1>. Currently only used for gcc to override
		2094	some inlining decisions, saves roughly 30% codesize of amd64.
		2095
		2096	=item EV_PID_HASHSIZE
		2097
		2098	C<ev_child> watchers use a small hash table to distribute workload by
		2099	pid. The default size is C<16> (or C<1> with C<EV_MINIMAL>), usually more
		2100	than enough. If you need to manage thousands of children you might want to
		2101	increase this value (I<must> be a power of two).
		2102
		2103	=item EV_INOTIFY_HASHSIZE
		2104
		2105	C<ev_staz> watchers use a small hash table to distribute workload by
		2106	inotify watch id. The default size is C<16> (or C<1> with C<EV_MINIMAL>),
		2107	usually more than enough. If you need to manage thousands of C<ev_stat>
		2108	watchers you might want to increase this value (I<must> be a power of
		2109	two).
		2110
		2111	=item EV_COMMON
		2112
		2113	By default, all watchers have a C<void *data> member. By redefining
		2114	this macro to a something else you can include more and other types of
		2115	members. You have to define it each time you include one of the files,
		2116	though, and it must be identical each time.
		2117
		2118	For example, the perl EV module uses something like this:
		2119
		2120	#define EV_COMMON \
		2121	SV *self; /* contains this struct */ \
		2122	SV *cb_sv, *fh /* note no trailing ";" */
		2123
		2124	=item EV_CB_DECLARE (type)
		2125
		2126	=item EV_CB_INVOKE (watcher, revents)
		2127
		2128	=item ev_set_cb (ev, cb)
		2129
		2130	Can be used to change the callback member declaration in each watcher,
		2131	and the way callbacks are invoked and set. Must expand to a struct member
		2132	definition and a statement, respectively. See the F<ev.v> header file for
		2133	their default definitions. One possible use for overriding these is to
		2134	avoid the C<struct ev_loop *> as first argument in all cases, or to use
		2135	method calls instead of plain function calls in C++.
		2136
		2137	=head2 EXAMPLES
		2138
		2139	For a real-world example of a program the includes libev
		2140	verbatim, you can have a look at the EV perl module
		2141	(L<http://software.schmorp.de/pkg/EV.html>). It has the libev files in
		2142	the F<libev/> subdirectory and includes them in the F<EV/EVAPI.h> (public
		2143	interface) and F<EV.xs> (implementation) files. Only the F<EV.xs> file
		2144	will be compiled. It is pretty complex because it provides its own header
		2145	file.
		2146
		2147	The usage in rxvt-unicode is simpler. It has a F<ev_cpp.h> header file
		2148	that everybody includes and which overrides some autoconf choices:
		2149
		2150	#define EV_USE_POLL 0
		2151	#define EV_MULTIPLICITY 0
		2152	#define EV_PERIODICS 0
		2153	#define EV_CONFIG_H <config.h>
		2154
		2155	#include "ev++.h"
		2156
		2157	And a F<ev_cpp.C> implementation file that contains libev proper and is compiled:
		2158
		2159	#include "ev_cpp.h"
		2160	#include "ev.c"
		2161
		2162
		2163	=head1 COMPLEXITIES
		2164
		2165	In this section the complexities of (many of) the algorithms used inside
		2166	libev will be explained. For complexity discussions about backends see the
		2167	documentation for C<ev_default_init>.
		2168
		2169	=over 4
		2170
		2171	=item Starting and stopping timer/periodic watchers: O(log skipped_other_timers)
		2172
		2173	=item Changing timer/periodic watchers (by autorepeat, again): O(log skipped_other_timers)
		2174
		2175	=item Starting io/check/prepare/idle/signal/child watchers: O(1)
		2176
		2177	=item Stopping check/prepare/idle watchers: O(1)
		2178
		2179	=item Stopping an io/signal/child watcher: O(number_of_watchers_for_this_(fd/signal/pid % EV_PID_HASHSIZE))
		2180
		2181	=item Finding the next timer per loop iteration: O(1)
		2182
		2183	=item Each change on a file descriptor per loop iteration: O(number_of_watchers_for_this_fd)
		2184
		2185	=item Activating one watcher: O(1)
		2186
		2187	=back
		2188
825		2189
826	=head1 AUTHOR	2190	=head1 AUTHOR
827		2191
828	Marc Lehmann <libev@schmorp.de>.	2192	Marc Lehmann <libev@schmorp.de>.
829		2193

Diff Legend

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