ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/libev/ev.pod

Comparing libev/ev.pod (file contents):
Revision 1.78 by root, Sun Dec 9 19:42:57 2007 UTC vs.
Revision 1.179 by root, Sat Sep 13 19:14:21 2008 UTC

…		…
2		2
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		8
9	=head1 EXAMPLE PROGRAM	9	=head2 EXAMPLE PROGRAM
10		10
		11	// a single header file is required
11	#include <ev.h>	12	#include <ev.h>
12		13
		14	// every watcher type has its own typedef'd struct
		15	// with the name ev_<type>
13	ev_io stdin_watcher;	16	ev_io stdin_watcher;
14	ev_timer timeout_watcher;	17	ev_timer timeout_watcher;
15		18
16	/* called when data readable on stdin */	19	// all watcher callbacks have a similar signature
		20	// this callback is called when data is readable on stdin
17	static void	21	static void
18	stdin_cb (EV_P_ struct ev_io *w, int revents)	22	stdin_cb (EV_P_ struct ev_io *w, int revents)
19	{	23	{
20	/* puts ("stdin ready"); */	24	puts ("stdin ready");
21	ev_io_stop (EV_A_ w); /* just a syntax example */	25	// for one-shot events, one must manually stop the watcher
22	ev_unloop (EV_A_ EVUNLOOP_ALL); /* leave all loop calls */	26	// with its corresponding stop function.
		27	ev_io_stop (EV_A_ w);
		28
		29	// this causes all nested ev_loop's to stop iterating
		30	ev_unloop (EV_A_ EVUNLOOP_ALL);
23	}	31	}
24		32
		33	// another callback, this time for a time-out
25	static void	34	static void
26	timeout_cb (EV_P_ struct ev_timer *w, int revents)	35	timeout_cb (EV_P_ struct ev_timer *w, int revents)
27	{	36	{
28	/* puts ("timeout"); */	37	puts ("timeout");
29	ev_unloop (EV_A_ EVUNLOOP_ONE); /* leave one loop call */	38	// this causes the innermost ev_loop to stop iterating
		39	ev_unloop (EV_A_ EVUNLOOP_ONE);
30	}	40	}
31		41
32	int	42	int
33	main (void)	43	main (void)
34	{	44	{
		45	// use the default event loop unless you have special needs
35	struct ev_loop *loop = ev_default_loop (0);	46	struct ev_loop *loop = ev_default_loop (0);
36		47
37	/* initialise an io watcher, then start it */	48	// initialise an io watcher, then start it
		49	// this one will watch for stdin to become readable
38	ev_io_init (&stdin_watcher, stdin_cb, /*STDIN_FILENO*/ 0, EV_READ);	50	ev_io_init (&stdin_watcher, stdin_cb, /*STDIN_FILENO*/ 0, EV_READ);
39	ev_io_start (loop, &stdin_watcher);	51	ev_io_start (loop, &stdin_watcher);
40		52
		53	// initialise a timer watcher, then start it
41	/* simple non-repeating 5.5 second timeout */	54	// simple non-repeating 5.5 second timeout
42	ev_timer_init (&timeout_watcher, timeout_cb, 5.5, 0.);	55	ev_timer_init (&timeout_watcher, timeout_cb, 5.5, 0.);
43	ev_timer_start (loop, &timeout_watcher);	56	ev_timer_start (loop, &timeout_watcher);
44		57
45	/* loop till timeout or data ready */	58	// now wait for events to arrive
46	ev_loop (loop, 0);	59	ev_loop (loop, 0);
47		60
		61	// unloop was called, so exit
48	return 0;	62	return 0;
49	}	63	}
50		64
51	=head1 DESCRIPTION	65	=head1 DESCRIPTION
52		66
53	The newest version of this document is also available as a html-formatted	67	The newest version of this document is also available as an html-formatted
54	web page you might find easier to navigate when reading it for the first	68	web page you might find easier to navigate when reading it for the first
55	time: L<http://cvs.schmorp.de/libev/ev.html>.	69	time: L<http://pod.tst.eu/http://cvs.schmorp.de/libev/ev.pod>.
56		70
57	Libev is an event loop: you register interest in certain events (such as a	71	Libev is an event loop: you register interest in certain events (such as a
58	file descriptor being readable or a timeout occuring), and it will manage	72	file descriptor being readable or a timeout occurring), and it will manage
59	these event sources and provide your program with events.	73	these event sources and provide your program with events.
60		74
61	To do this, it must take more or less complete control over your process	75	To do this, it must take more or less complete control over your process
62	(or thread) by executing the I<event loop> handler, and will then	76	(or thread) by executing the I<event loop> handler, and will then
63	communicate events via a callback mechanism.	77	communicate events via a callback mechanism.
…		…
65	You register interest in certain events by registering so-called I<event	79	You register interest in certain events by registering so-called I<event
66	watchers>, which are relatively small C structures you initialise with the	80	watchers>, which are relatively small C structures you initialise with the
67	details of the event, and then hand it over to libev by I<starting> the	81	details of the event, and then hand it over to libev by I<starting> the
68	watcher.	82	watcher.
69		83
70	=head1 FEATURES	84	=head2 FEATURES
71		85
72	Libev supports C<select>, C<poll>, the Linux-specific C<epoll>, the	86	Libev supports C<select>, C<poll>, the Linux-specific C<epoll>, the
73	BSD-specific C<kqueue> and the Solaris-specific event port mechanisms	87	BSD-specific C<kqueue> and the Solaris-specific event port mechanisms
74	for file descriptor events (C<ev_io>), the Linux C<inotify> interface	88	for file descriptor events (C<ev_io>), the Linux C<inotify> interface
75	(for C<ev_stat>), relative timers (C<ev_timer>), absolute timers	89	(for C<ev_stat>), relative timers (C<ev_timer>), absolute timers
…		…
82		96
83	It also is quite fast (see this	97	It also is quite fast (see this
84	L<benchmark|http://libev.schmorp.de/bench.html> comparing it to libevent	98	L<benchmark|http://libev.schmorp.de/bench.html> comparing it to libevent
85	for example).	99	for example).
86		100
87	=head1 CONVENTIONS	101	=head2 CONVENTIONS
88		102
89	Libev is very configurable. In this manual the default configuration will	103	Libev is very configurable. In this manual the default (and most common)
90	be described, which supports multiple event loops. For more info about	104	configuration will be described, which supports multiple event loops. For
91	various configuration options please have a look at B<EMBED> section in	105	more info about various configuration options please have a look at
92	this manual. If libev was configured without support for multiple event	106	B<EMBED> section in this manual. If libev was configured without support
93	loops, then all functions taking an initial argument of name C<loop>	107	for multiple event loops, then all functions taking an initial argument of
94	(which is always of type C<struct ev_loop *>) will not have this argument.	108	name C<loop> (which is always of type C<struct ev_loop *>) will not have
		109	this argument.
95		110
96	=head1 TIME REPRESENTATION	111	=head2 TIME REPRESENTATION
97		112
98	Libev represents time as a single floating point number, representing the	113	Libev represents time as a single floating point number, representing the
99	(fractional) number of seconds since the (POSIX) epoch (somewhere near	114	(fractional) number of seconds since the (POSIX) epoch (somewhere near
100	the beginning of 1970, details are complicated, don't ask). This type is	115	the beginning of 1970, details are complicated, don't ask). This type is
101	called C<ev_tstamp>, which is what you should use too. It usually aliases	116	called C<ev_tstamp>, which is what you should use too. It usually aliases
102	to the C<double> type in C, and when you need to do any calculations on	117	to the C<double> type in C, and when you need to do any calculations on
103	it, you should treat it as such.	118	it, you should treat it as some floating point value. Unlike the name
		119	component C<stamp> might indicate, it is also used for time differences
		120	throughout libev.
		121
		122	=head1 ERROR HANDLING
		123
		124	Libev knows three classes of errors: operating system errors, usage errors
		125	and internal errors (bugs).
		126
		127	When libev catches an operating system error it cannot handle (for example
		128	a system call indicating a condition libev cannot fix), it calls the callback
		129	set via C<ev_set_syserr_cb>, which is supposed to fix the problem or
		130	abort. The default is to print a diagnostic message and to call C<abort
		131	()>.
		132
		133	When libev detects a usage error such as a negative timer interval, then
		134	it will print a diagnostic message and abort (via the C<assert> mechanism,
		135	so C<NDEBUG> will disable this checking): these are programming errors in
		136	the libev caller and need to be fixed there.
		137
		138	Libev also has a few internal error-checking C<assert>ions, and also has
		139	extensive consistency checking code. These do not trigger under normal
		140	circumstances, as they indicate either a bug in libev or worse.
		141
104		142
105	=head1 GLOBAL FUNCTIONS	143	=head1 GLOBAL FUNCTIONS
106		144
107	These functions can be called anytime, even before initialising the	145	These functions can be called anytime, even before initialising the
108	library in any way.	146	library in any way.
…		…
113		151
114	Returns the current time as libev would use it. Please note that the	152	Returns the current time as libev would use it. Please note that the
115	C<ev_now> function is usually faster and also often returns the timestamp	153	C<ev_now> function is usually faster and also often returns the timestamp
116	you actually want to know.	154	you actually want to know.
117		155
		156	=item ev_sleep (ev_tstamp interval)
		157
		158	Sleep for the given interval: The current thread will be blocked until
		159	either it is interrupted or the given time interval has passed. Basically
		160	this is a sub-second-resolution C<sleep ()>.
		161
118	=item int ev_version_major ()	162	=item int ev_version_major ()
119		163
120	=item int ev_version_minor ()	164	=item int ev_version_minor ()
121		165
122	You can find out the major and minor version numbers of the library	166	You can find out the major and minor ABI version numbers of the library
123	you linked against by calling the functions C<ev_version_major> and	167	you linked against by calling the functions C<ev_version_major> and
124	C<ev_version_minor>. If you want, you can compare against the global	168	C<ev_version_minor>. If you want, you can compare against the global
125	symbols C<EV_VERSION_MAJOR> and C<EV_VERSION_MINOR>, which specify the	169	symbols C<EV_VERSION_MAJOR> and C<EV_VERSION_MINOR>, which specify the
126	version of the library your program was compiled against.	170	version of the library your program was compiled against.
127		171
		172	These version numbers refer to the ABI version of the library, not the
		173	release version.
		174
128	Usually, it's a good idea to terminate if the major versions mismatch,	175	Usually, it's a good idea to terminate if the major versions mismatch,
129	as this indicates an incompatible change. Minor versions are usually	176	as this indicates an incompatible change. Minor versions are usually
130	compatible to older versions, so a larger minor version alone is usually	177	compatible to older versions, so a larger minor version alone is usually
131	not a problem.	178	not a problem.
132		179
133	Example: Make sure we haven't accidentally been linked against the wrong	180	Example: Make sure we haven't accidentally been linked against the wrong
134	version.	181	version.
135		182
136	assert (("libev version mismatch",	183	assert (("libev version mismatch",
137	ev_version_major () == EV_VERSION_MAJOR	184	ev_version_major () == EV_VERSION_MAJOR
138	&& ev_version_minor () >= EV_VERSION_MINOR));	185	&& ev_version_minor () >= EV_VERSION_MINOR));
139		186
140	=item unsigned int ev_supported_backends ()	187	=item unsigned int ev_supported_backends ()
141		188
142	Return the set of all backends (i.e. their corresponding C<EV_BACKEND_*>	189	Return the set of all backends (i.e. their corresponding C<EV_BACKEND_*>
143	value) compiled into this binary of libev (independent of their	190	value) compiled into this binary of libev (independent of their
…		…
145	a description of the set values.	192	a description of the set values.
146		193
147	Example: make sure we have the epoll method, because yeah this is cool and	194	Example: make sure we have the epoll method, because yeah this is cool and
148	a must have and can we have a torrent of it please!!!11	195	a must have and can we have a torrent of it please!!!11
149		196
150	assert (("sorry, no epoll, no sex",	197	assert (("sorry, no epoll, no sex",
151	ev_supported_backends () & EVBACKEND_EPOLL));	198	ev_supported_backends () & EVBACKEND_EPOLL));
152		199
153	=item unsigned int ev_recommended_backends ()	200	=item unsigned int ev_recommended_backends ()
154		201
155	Return the set of all backends compiled into this binary of libev and also	202	Return the set of all backends compiled into this binary of libev and also
156	recommended for this platform. This set is often smaller than the one	203	recommended for this platform. This set is often smaller than the one
157	returned by C<ev_supported_backends>, as for example kqueue is broken on	204	returned by C<ev_supported_backends>, as for example kqueue is broken on
158	most BSDs and will not be autodetected unless you explicitly request it	205	most BSDs and will not be auto-detected unless you explicitly request it
159	(assuming you know what you are doing). This is the set of backends that	206	(assuming you know what you are doing). This is the set of backends that
160	libev will probe for if you specify no backends explicitly.	207	libev will probe for if you specify no backends explicitly.
161		208
162	=item unsigned int ev_embeddable_backends ()	209	=item unsigned int ev_embeddable_backends ()
163		210
…		…
170	See the description of C<ev_embed> watchers for more info.	217	See the description of C<ev_embed> watchers for more info.
171		218
172	=item ev_set_allocator (void *(*cb)(void *ptr, long size))	219	=item ev_set_allocator (void *(*cb)(void *ptr, long size))
173		220
174	Sets the allocation function to use (the prototype is similar - the	221	Sets the allocation function to use (the prototype is similar - the
175	semantics is identical - to the realloc C function). It is used to	222	semantics are identical to the C<realloc> C89/SuS/POSIX function). It is
176	allocate and free memory (no surprises here). If it returns zero when	223	used to allocate and free memory (no surprises here). If it returns zero
177	memory needs to be allocated, the library might abort or take some	224	when memory needs to be allocated (C<size != 0>), the library might abort
178	potentially destructive action. The default is your system realloc	225	or take some potentially destructive action.
179	function.	226
		227	Since some systems (at least OpenBSD and Darwin) fail to implement
		228	correct C<realloc> semantics, libev will use a wrapper around the system
		229	C<realloc> and C<free> functions by default.
180		230
181	You could override this function in high-availability programs to, say,	231	You could override this function in high-availability programs to, say,
182	free some memory if it cannot allocate memory, to use a special allocator,	232	free some memory if it cannot allocate memory, to use a special allocator,
183	or even to sleep a while and retry until some memory is available.	233	or even to sleep a while and retry until some memory is available.
184		234
185	Example: Replace the libev allocator with one that waits a bit and then	235	Example: Replace the libev allocator with one that waits a bit and then
186	retries).	236	retries (example requires a standards-compliant C<realloc>).
187		237
188	static void *	238	static void *
189	persistent_realloc (void *ptr, size_t size)	239	persistent_realloc (void *ptr, size_t size)
190	{	240	{
191	for (;;)	241	for (;;)
…		…
202	...	252	...
203	ev_set_allocator (persistent_realloc);	253	ev_set_allocator (persistent_realloc);
204		254
205	=item ev_set_syserr_cb (void (*cb)(const char *msg));	255	=item ev_set_syserr_cb (void (*cb)(const char *msg));
206		256
207	Set the callback function to call on a retryable syscall error (such	257	Set the callback function to call on a retryable system call error (such
208	as failed select, poll, epoll_wait). The message is a printable string	258	as failed select, poll, epoll_wait). The message is a printable string
209	indicating the system call or subsystem causing the problem. If this	259	indicating the system call or subsystem causing the problem. If this
210	callback is set, then libev will expect it to remedy the sitution, no	260	callback is set, then libev will expect it to remedy the situation, no
211	matter what, when it returns. That is, libev will generally retry the	261	matter what, when it returns. That is, libev will generally retry the
212	requested operation, or, if the condition doesn't go away, do bad stuff	262	requested operation, or, if the condition doesn't go away, do bad stuff
213	(such as abort).	263	(such as abort).
214		264
215	Example: This is basically the same thing that libev does internally, too.	265	Example: This is basically the same thing that libev does internally, too.
…		…
229	=head1 FUNCTIONS CONTROLLING THE EVENT LOOP	279	=head1 FUNCTIONS CONTROLLING THE EVENT LOOP
230		280
231	An event loop is described by a C<struct ev_loop *>. The library knows two	281	An event loop is described by a C<struct ev_loop *>. The library knows two
232	types of such loops, the I<default> loop, which supports signals and child	282	types of such loops, the I<default> loop, which supports signals and child
233	events, and dynamically created loops which do not.	283	events, and dynamically created loops which do not.
234
235	If you use threads, a common model is to run the default event loop
236	in your main thread (or in a separate thread) and for each thread you
237	create, you also create another event loop. Libev itself does no locking
238	whatsoever, so if you mix calls to the same event loop in different
239	threads, make sure you lock (this is usually a bad idea, though, even if
240	done correctly, because it's hideous and inefficient).
241		284
242	=over 4	285	=over 4
243		286
244	=item struct ev_loop *ev_default_loop (unsigned int flags)	287	=item struct ev_loop *ev_default_loop (unsigned int flags)
245		288
…		…
249	flags. If that is troubling you, check C<ev_backend ()> afterwards).	292	flags. If that is troubling you, check C<ev_backend ()> afterwards).
250		293
251	If you don't know what event loop to use, use the one returned from this	294	If you don't know what event loop to use, use the one returned from this
252	function.	295	function.
253		296
		297	Note that this function is I<not> thread-safe, so if you want to use it
		298	from multiple threads, you have to lock (note also that this is unlikely,
		299	as loops cannot bes hared easily between threads anyway).
		300
		301	The default loop is the only loop that can handle C<ev_signal> and
		302	C<ev_child> watchers, and to do this, it always registers a handler
		303	for C<SIGCHLD>. If this is a problem for your application you can either
		304	create a dynamic loop with C<ev_loop_new> that doesn't do that, or you
		305	can simply overwrite the C<SIGCHLD> signal handler I<after> calling
		306	C<ev_default_init>.
		307
254	The flags argument can be used to specify special behaviour or specific	308	The flags argument can be used to specify special behaviour or specific
255	backends to use, and is usually specified as C<0> (or C<EVFLAG_AUTO>).	309	backends to use, and is usually specified as C<0> (or C<EVFLAG_AUTO>).
256		310
257	The following flags are supported:	311	The following flags are supported:
258		312
…		…
263	The default flags value. Use this if you have no clue (it's the right	317	The default flags value. Use this if you have no clue (it's the right
264	thing, believe me).	318	thing, believe me).
265		319
266	=item C<EVFLAG_NOENV>	320	=item C<EVFLAG_NOENV>
267		321
268	If this flag bit is ored into the flag value (or the program runs setuid	322	If this flag bit is or'ed into the flag value (or the program runs setuid
269	or setgid) then libev will I<not> look at the environment variable	323	or setgid) then libev will I<not> look at the environment variable
270	C<LIBEV_FLAGS>. Otherwise (the default), this environment variable will	324	C<LIBEV_FLAGS>. Otherwise (the default), this environment variable will
271	override the flags completely if it is found in the environment. This is	325	override the flags completely if it is found in the environment. This is
272	useful to try out specific backends to test their performance, or to work	326	useful to try out specific backends to test their performance, or to work
273	around bugs.	327	around bugs.
…		…
279	enabling this flag.	333	enabling this flag.
280		334
281	This works by calling C<getpid ()> on every iteration of the loop,	335	This works by calling C<getpid ()> on every iteration of the loop,
282	and thus this might slow down your event loop if you do a lot of loop	336	and thus this might slow down your event loop if you do a lot of loop
283	iterations and little real work, but is usually not noticeable (on my	337	iterations and little real work, but is usually not noticeable (on my
284	Linux system for example, C<getpid> is actually a simple 5-insn sequence	338	GNU/Linux system for example, C<getpid> is actually a simple 5-insn sequence
285	without a syscall and thus I<very> fast, but my Linux system also has	339	without a system call and thus I<very> fast, but my GNU/Linux system also has
286	C<pthread_atfork> which is even faster).	340	C<pthread_atfork> which is even faster).
287		341
288	The big advantage of this flag is that you can forget about fork (and	342	The big advantage of this flag is that you can forget about fork (and
289	forget about forgetting to tell libev about forking) when you use this	343	forget about forgetting to tell libev about forking) when you use this
290	flag.	344	flag.
291		345
292	This flag setting cannot be overriden or specified in the C<LIBEV_FLAGS>	346	This flag setting cannot be overridden or specified in the C<LIBEV_FLAGS>
293	environment variable.	347	environment variable.
294		348
295	=item C<EVBACKEND_SELECT> (value 1, portable select backend)	349	=item C<EVBACKEND_SELECT> (value 1, portable select backend)
296		350
297	This is your standard select(2) backend. Not I<completely> standard, as	351	This is your standard select(2) backend. Not I<completely> standard, as
298	libev tries to roll its own fd_set with no limits on the number of fds,	352	libev tries to roll its own fd_set with no limits on the number of fds,
299	but if that fails, expect a fairly low limit on the number of fds when	353	but if that fails, expect a fairly low limit on the number of fds when
300	using this backend. It doesn't scale too well (O(highest_fd)), but its usually	354	using this backend. It doesn't scale too well (O(highest_fd)), but its
301	the fastest backend for a low number of fds.	355	usually the fastest backend for a low number of (low-numbered :) fds.
		356
		357	To get good performance out of this backend you need a high amount of
		358	parallelism (most of the file descriptors should be busy). If you are
		359	writing a server, you should C<accept ()> in a loop to accept as many
		360	connections as possible during one iteration. You might also want to have
		361	a look at C<ev_set_io_collect_interval ()> to increase the amount of
		362	readiness notifications you get per iteration.
		363
		364	This backend maps C<EV_READ> to the C<readfds> set and C<EV_WRITE> to the
		365	C<writefds> set (and to work around Microsoft Windows bugs, also onto the
		366	C<exceptfds> set on that platform).
302		367
303	=item C<EVBACKEND_POLL> (value 2, poll backend, available everywhere except on windows)	368	=item C<EVBACKEND_POLL> (value 2, poll backend, available everywhere except on windows)
304		369
305	And this is your standard poll(2) backend. It's more complicated than	370	And this is your standard poll(2) backend. It's more complicated
306	select, but handles sparse fds better and has no artificial limit on the	371	than select, but handles sparse fds better and has no artificial
307	number of fds you can use (except it will slow down considerably with a	372	limit on the number of fds you can use (except it will slow down
308	lot of inactive fds). It scales similarly to select, i.e. O(total_fds).	373	considerably with a lot of inactive fds). It scales similarly to select,
		374	i.e. O(total_fds). See the entry for C<EVBACKEND_SELECT>, above, for
		375	performance tips.
		376
		377	This backend maps C<EV_READ> to C<POLLIN | POLLERR | POLLHUP>, and
		378	C<EV_WRITE> to C<POLLOUT | POLLERR | POLLHUP>.
309		379
310	=item C<EVBACKEND_EPOLL> (value 4, Linux)	380	=item C<EVBACKEND_EPOLL> (value 4, Linux)
311		381
312	For few fds, this backend is a bit little slower than poll and select,	382	For few fds, this backend is a bit little slower than poll and select,
313	but it scales phenomenally better. While poll and select usually scale like	383	but it scales phenomenally better. While poll and select usually scale
314	O(total_fds) where n is the total number of fds (or the highest fd), epoll scales	384	like O(total_fds) where n is the total number of fds (or the highest fd),
315	either O(1) or O(active_fds).	385	epoll scales either O(1) or O(active_fds). The epoll design has a number
		386	of shortcomings, such as silently dropping events in some hard-to-detect
		387	cases and requiring a system call per fd change, no fork support and bad
		388	support for dup.
316		389
317	While stopping and starting an I/O watcher in the same iteration will	390	While stopping, setting and starting an I/O watcher in the same iteration
318	result in some caching, there is still a syscall per such incident	391	will result in some caching, there is still a system call per such incident
319	(because the fd could point to a different file description now), so its	392	(because the fd could point to a different file description now), so its
320	best to avoid that. Also, dup()ed file descriptors might not work very	393	best to avoid that. Also, C<dup ()>'ed file descriptors might not work
321	well if you register events for both fds.	394	very well if you register events for both fds.
322		395
323	Please note that epoll sometimes generates spurious notifications, so you	396	Please note that epoll sometimes generates spurious notifications, so you
324	need to use non-blocking I/O or other means to avoid blocking when no data	397	need to use non-blocking I/O or other means to avoid blocking when no data
325	(or space) is available.	398	(or space) is available.
326		399
		400	Best performance from this backend is achieved by not unregistering all
		401	watchers for a file descriptor until it has been closed, if possible, i.e.
		402	keep at least one watcher active per fd at all times.
		403
		404	While nominally embeddable in other event loops, this feature is broken in
		405	all kernel versions tested so far.
		406
		407	This backend maps C<EV_READ> and C<EV_WRITE> in the same way as
		408	C<EVBACKEND_POLL>.
		409
327	=item C<EVBACKEND_KQUEUE> (value 8, most BSD clones)	410	=item C<EVBACKEND_KQUEUE> (value 8, most BSD clones)
328		411
329	Kqueue deserves special mention, as at the time of this writing, it	412	Kqueue deserves special mention, as at the time of this writing, it
330	was broken on all BSDs except NetBSD (usually it doesn't work with	413	was broken on all BSDs except NetBSD (usually it doesn't work reliably
331	anything but sockets and pipes, except on Darwin, where of course its	414	with anything but sockets and pipes, except on Darwin, where of course
332	completely useless). For this reason its not being "autodetected"	415	it's completely useless). For this reason it's not being "auto-detected"
333	unless you explicitly specify it explicitly in the flags (i.e. using	416	unless you explicitly specify it explicitly in the flags (i.e. using
334	C<EVBACKEND_KQUEUE>).	417	C<EVBACKEND_KQUEUE>) or libev was compiled on a known-to-be-good (-enough)
		418	system like NetBSD.
		419
		420	You still can embed kqueue into a normal poll or select backend and use it
		421	only for sockets (after having made sure that sockets work with kqueue on
		422	the target platform). See C<ev_embed> watchers for more info.
335		423
336	It scales in the same way as the epoll backend, but the interface to the	424	It scales in the same way as the epoll backend, but the interface to the
337	kernel is more efficient (which says nothing about its actual speed, of	425	kernel is more efficient (which says nothing about its actual speed, of
338	course). While starting and stopping an I/O watcher does not cause an	426	course). While stopping, setting and starting an I/O watcher does never
339	extra syscall as with epoll, it still adds up to four event changes per	427	cause an extra system call as with C<EVBACKEND_EPOLL>, it still adds up to
340	incident, so its best to avoid that.	428	two event changes per incident, support for C<fork ()> is very bad and it
		429	drops fds silently in similarly hard-to-detect cases.
		430
		431	This backend usually performs well under most conditions.
		432
		433	While nominally embeddable in other event loops, this doesn't work
		434	everywhere, so you might need to test for this. And since it is broken
		435	almost everywhere, you should only use it when you have a lot of sockets
		436	(for which it usually works), by embedding it into another event loop
		437	(e.g. C<EVBACKEND_SELECT> or C<EVBACKEND_POLL>) and using it only for
		438	sockets.
		439
		440	This backend maps C<EV_READ> into an C<EVFILT_READ> kevent with
		441	C<NOTE_EOF>, and C<EV_WRITE> into an C<EVFILT_WRITE> kevent with
		442	C<NOTE_EOF>.
341		443
342	=item C<EVBACKEND_DEVPOLL> (value 16, Solaris 8)	444	=item C<EVBACKEND_DEVPOLL> (value 16, Solaris 8)
343		445
344	This is not implemented yet (and might never be).	446	This is not implemented yet (and might never be, unless you send me an
		447	implementation). According to reports, C</dev/poll> only supports sockets
		448	and is not embeddable, which would limit the usefulness of this backend
		449	immensely.
345		450
346	=item C<EVBACKEND_PORT> (value 32, Solaris 10)	451	=item C<EVBACKEND_PORT> (value 32, Solaris 10)
347		452
348	This uses the Solaris 10 port mechanism. As with everything on Solaris,	453	This uses the Solaris 10 event port mechanism. As with everything on Solaris,
349	it's really slow, but it still scales very well (O(active_fds)).	454	it's really slow, but it still scales very well (O(active_fds)).
350		455
351	Please note that solaris ports can result in a lot of spurious	456	Please note that Solaris event ports can deliver a lot of spurious
352	notifications, so you need to use non-blocking I/O or other means to avoid	457	notifications, so you need to use non-blocking I/O or other means to avoid
353	blocking when no data (or space) is available.	458	blocking when no data (or space) is available.
		459
		460	While this backend scales well, it requires one system call per active
		461	file descriptor per loop iteration. For small and medium numbers of file
		462	descriptors a "slow" C<EVBACKEND_SELECT> or C<EVBACKEND_POLL> backend
		463	might perform better.
		464
		465	On the positive side, ignoring the spurious readiness notifications, this
		466	backend actually performed to specification in all tests and is fully
		467	embeddable, which is a rare feat among the OS-specific backends.
		468
		469	This backend maps C<EV_READ> and C<EV_WRITE> in the same way as
		470	C<EVBACKEND_POLL>.
354		471
355	=item C<EVBACKEND_ALL>	472	=item C<EVBACKEND_ALL>
356		473
357	Try all backends (even potentially broken ones that wouldn't be tried	474	Try all backends (even potentially broken ones that wouldn't be tried
358	with C<EVFLAG_AUTO>). Since this is a mask, you can do stuff such as	475	with C<EVFLAG_AUTO>). Since this is a mask, you can do stuff such as
359	C<EVBACKEND_ALL & ~EVBACKEND_KQUEUE>.	476	C<EVBACKEND_ALL & ~EVBACKEND_KQUEUE>.
360		477
		478	It is definitely not recommended to use this flag.
		479
361	=back	480	=back
362		481
363	If one or more of these are ored into the flags value, then only these	482	If one or more of these are or'ed into the flags value, then only these
364	backends will be tried (in the reverse order as given here). If none are	483	backends will be tried (in the reverse order as listed here). If none are
365	specified, most compiled-in backend will be tried, usually in reverse	484	specified, all backends in C<ev_recommended_backends ()> will be tried.
366	order of their flag values :)
367		485
368	The most typical usage is like this:	486	The most typical usage is like this:
369		487
370	if (!ev_default_loop (0))	488	if (!ev_default_loop (0))
371	fatal ("could not initialise libev, bad $LIBEV_FLAGS in environment?");	489	fatal ("could not initialise libev, bad $LIBEV_FLAGS in environment?");
372		490
373	Restrict libev to the select and poll backends, and do not allow	491	Restrict libev to the select and poll backends, and do not allow
374	environment settings to be taken into account:	492	environment settings to be taken into account:
375		493
376	ev_default_loop (EVBACKEND_POLL | EVBACKEND_SELECT | EVFLAG_NOENV);	494	ev_default_loop (EVBACKEND_POLL | EVBACKEND_SELECT | EVFLAG_NOENV);
377		495
378	Use whatever libev has to offer, but make sure that kqueue is used if	496	Use whatever libev has to offer, but make sure that kqueue is used if
379	available (warning, breaks stuff, best use only with your own private	497	available (warning, breaks stuff, best use only with your own private
380	event loop and only if you know the OS supports your types of fds):	498	event loop and only if you know the OS supports your types of fds):
381		499
382	ev_default_loop (ev_recommended_backends () | EVBACKEND_KQUEUE);	500	ev_default_loop (ev_recommended_backends () | EVBACKEND_KQUEUE);
383		501
384	=item struct ev_loop *ev_loop_new (unsigned int flags)	502	=item struct ev_loop *ev_loop_new (unsigned int flags)
385		503
386	Similar to C<ev_default_loop>, but always creates a new event loop that is	504	Similar to C<ev_default_loop>, but always creates a new event loop that is
387	always distinct from the default loop. Unlike the default loop, it cannot	505	always distinct from the default loop. Unlike the default loop, it cannot
388	handle signal and child watchers, and attempts to do so will be greeted by	506	handle signal and child watchers, and attempts to do so will be greeted by
389	undefined behaviour (or a failed assertion if assertions are enabled).	507	undefined behaviour (or a failed assertion if assertions are enabled).
390		508
		509	Note that this function I<is> thread-safe, and the recommended way to use
		510	libev with threads is indeed to create one loop per thread, and using the
		511	default loop in the "main" or "initial" thread.
		512
391	Example: Try to create a event loop that uses epoll and nothing else.	513	Example: Try to create a event loop that uses epoll and nothing else.
392		514
393	struct ev_loop *epoller = ev_loop_new (EVBACKEND_EPOLL | EVFLAG_NOENV);	515	struct ev_loop *epoller = ev_loop_new (EVBACKEND_EPOLL | EVFLAG_NOENV);
394	if (!epoller)	516	if (!epoller)
395	fatal ("no epoll found here, maybe it hides under your chair");	517	fatal ("no epoll found here, maybe it hides under your chair");
396		518
397	=item ev_default_destroy ()	519	=item ev_default_destroy ()
398		520
399	Destroys the default loop again (frees all memory and kernel state	521	Destroys the default loop again (frees all memory and kernel state
400	etc.). None of the active event watchers will be stopped in the normal	522	etc.). None of the active event watchers will be stopped in the normal
401	sense, so e.g. C<ev_is_active> might still return true. It is your	523	sense, so e.g. C<ev_is_active> might still return true. It is your
402	responsibility to either stop all watchers cleanly yoursef I<before>	524	responsibility to either stop all watchers cleanly yourself I<before>
403	calling this function, or cope with the fact afterwards (which is usually	525	calling this function, or cope with the fact afterwards (which is usually
404	the easiest thing, youc na just ignore the watchers and/or C<free ()> them	526	the easiest thing, you can just ignore the watchers and/or C<free ()> them
405	for example).	527	for example).
		528
		529	Note that certain global state, such as signal state, will not be freed by
		530	this function, and related watchers (such as signal and child watchers)
		531	would need to be stopped manually.
		532
		533	In general it is not advisable to call this function except in the
		534	rare occasion where you really need to free e.g. the signal handling
		535	pipe fds. If you need dynamically allocated loops it is better to use
		536	C<ev_loop_new> and C<ev_loop_destroy>).
406		537
407	=item ev_loop_destroy (loop)	538	=item ev_loop_destroy (loop)
408		539
409	Like C<ev_default_destroy>, but destroys an event loop created by an	540	Like C<ev_default_destroy>, but destroys an event loop created by an
410	earlier call to C<ev_loop_new>.	541	earlier call to C<ev_loop_new>.
411		542
412	=item ev_default_fork ()	543	=item ev_default_fork ()
413		544
		545	This function sets a flag that causes subsequent C<ev_loop> iterations
414	This function reinitialises the kernel state for backends that have	546	to reinitialise the kernel state for backends that have one. Despite the
415	one. Despite the name, you can call it anytime, but it makes most sense	547	name, you can call it anytime, but it makes most sense after forking, in
416	after forking, in either the parent or child process (or both, but that	548	the child process (or both child and parent, but that again makes little
417	again makes little sense).	549	sense). You I<must> call it in the child before using any of the libev
		550	functions, and it will only take effect at the next C<ev_loop> iteration.
418		551
419	You I<must> call this function in the child process after forking if and	552	On the other hand, you only need to call this function in the child
420	only if you want to use the event library in both processes. If you just	553	process if and only if you want to use the event library in the child. If
421	fork+exec, you don't have to call it.	554	you just fork+exec, you don't have to call it at all.
422		555
423	The function itself is quite fast and it's usually not a problem to call	556	The function itself is quite fast and it's usually not a problem to call
424	it just in case after a fork. To make this easy, the function will fit in	557	it just in case after a fork. To make this easy, the function will fit in
425	quite nicely into a call to C<pthread_atfork>:	558	quite nicely into a call to C<pthread_atfork>:
426		559
427	pthread_atfork (0, 0, ev_default_fork);	560	pthread_atfork (0, 0, ev_default_fork);
428		561
429	At the moment, C<EVBACKEND_SELECT> and C<EVBACKEND_POLL> are safe to use
430	without calling this function, so if you force one of those backends you
431	do not need to care.
432
433	=item ev_loop_fork (loop)	562	=item ev_loop_fork (loop)
434		563
435	Like C<ev_default_fork>, but acts on an event loop created by	564	Like C<ev_default_fork>, but acts on an event loop created by
436	C<ev_loop_new>. Yes, you have to call this on every allocated event loop	565	C<ev_loop_new>. Yes, you have to call this on every allocated event loop
437	after fork, and how you do this is entirely your own problem.	566	after fork, and how you do this is entirely your own problem.
		567
		568	=item int ev_is_default_loop (loop)
		569
		570	Returns true when the given loop actually is the default loop, false otherwise.
438		571
439	=item unsigned int ev_loop_count (loop)	572	=item unsigned int ev_loop_count (loop)
440		573
441	Returns the count of loop iterations for the loop, which is identical to	574	Returns the count of loop iterations for the loop, which is identical to
442	the number of times libev did poll for new events. It starts at C<0> and	575	the number of times libev did poll for new events. It starts at C<0> and
…		…
455		588
456	Returns the current "event loop time", which is the time the event loop	589	Returns the current "event loop time", which is the time the event loop
457	received events and started processing them. This timestamp does not	590	received events and started processing them. This timestamp does not
458	change as long as callbacks are being processed, and this is also the base	591	change as long as callbacks are being processed, and this is also the base
459	time used for relative timers. You can treat it as the timestamp of the	592	time used for relative timers. You can treat it as the timestamp of the
460	event occuring (or more correctly, libev finding out about it).	593	event occurring (or more correctly, libev finding out about it).
		594
		595	=item ev_now_update (loop)
		596
		597	Establishes the current time by querying the kernel, updating the time
		598	returned by C<ev_now ()> in the progress. This is a costly operation and
		599	is usually done automatically within C<ev_loop ()>.
		600
		601	This function is rarely useful, but when some event callback runs for a
		602	very long time without entering the event loop, updating libev's idea of
		603	the current time is a good idea.
		604
		605	See also "The special problem of time updates" in the C<ev_timer> section.
461		606
462	=item ev_loop (loop, int flags)	607	=item ev_loop (loop, int flags)
463		608
464	Finally, this is it, the event handler. This function usually is called	609	Finally, this is it, the event handler. This function usually is called
465	after you initialised all your watchers and you want to start handling	610	after you initialised all your watchers and you want to start handling
…		…
477	A flags value of C<EVLOOP_NONBLOCK> will look for new events, will handle	622	A flags value of C<EVLOOP_NONBLOCK> will look for new events, will handle
478	those events and any outstanding ones, but will not block your process in	623	those events and any outstanding ones, but will not block your process in
479	case there are no events and will return after one iteration of the loop.	624	case there are no events and will return after one iteration of the loop.
480		625
481	A flags value of C<EVLOOP_ONESHOT> will look for new events (waiting if	626	A flags value of C<EVLOOP_ONESHOT> will look for new events (waiting if
482	neccessary) and will handle those and any outstanding ones. It will block	627	necessary) and will handle those and any outstanding ones. It will block
483	your process until at least one new event arrives, and will return after	628	your process until at least one new event arrives, and will return after
484	one iteration of the loop. This is useful if you are waiting for some	629	one iteration of the loop. This is useful if you are waiting for some
485	external event in conjunction with something not expressible using other	630	external event in conjunction with something not expressible using other
486	libev watchers. However, a pair of C<ev_prepare>/C<ev_check> watchers is	631	libev watchers. However, a pair of C<ev_prepare>/C<ev_check> watchers is
487	usually a better approach for this kind of thing.	632	usually a better approach for this kind of thing.
488		633
489	Here are the gory details of what C<ev_loop> does:	634	Here are the gory details of what C<ev_loop> does:
490		635
491	- Before the first iteration, call any pending watchers.	636	- Before the first iteration, call any pending watchers.
492	* If there are no active watchers (reference count is zero), return.	637	* If EVFLAG_FORKCHECK was used, check for a fork.
493	- Queue all prepare watchers and then call all outstanding watchers.	638	- If a fork was detected (by any means), queue and call all fork watchers.
		639	- Queue and call all prepare watchers.
494	- If we have been forked, recreate the kernel state.	640	- If we have been forked, detach and recreate the kernel state
		641	as to not disturb the other process.
495	- Update the kernel state with all outstanding changes.	642	- Update the kernel state with all outstanding changes.
496	- Update the "event loop time".	643	- Update the "event loop time" (ev_now ()).
497	- Calculate for how long to block.	644	- Calculate for how long to sleep or block, if at all
		645	(active idle watchers, EVLOOP_NONBLOCK or not having
		646	any active watchers at all will result in not sleeping).
		647	- Sleep if the I/O and timer collect interval say so.
498	- Block the process, waiting for any events.	648	- Block the process, waiting for any events.
499	- Queue all outstanding I/O (fd) events.	649	- Queue all outstanding I/O (fd) events.
500	- Update the "event loop time" and do time jump handling.	650	- Update the "event loop time" (ev_now ()), and do time jump adjustments.
501	- Queue all outstanding timers.	651	- Queue all outstanding timers.
502	- Queue all outstanding periodics.	652	- Queue all outstanding periodics.
503	- If no events are pending now, queue all idle watchers.	653	- Unless any events are pending now, queue all idle watchers.
504	- Queue all check watchers.	654	- Queue all check watchers.
505	- Call all queued watchers in reverse order (i.e. check watchers first).	655	- Call all queued watchers in reverse order (i.e. check watchers first).
506	Signals and child watchers are implemented as I/O watchers, and will	656	Signals and child watchers are implemented as I/O watchers, and will
507	be handled here by queueing them when their watcher gets executed.	657	be handled here by queueing them when their watcher gets executed.
508	- If ev_unloop has been called or EVLOOP_ONESHOT or EVLOOP_NONBLOCK	658	- If ev_unloop has been called, or EVLOOP_ONESHOT or EVLOOP_NONBLOCK
509	were used, return, otherwise continue with step *.	659	were used, or there are no active watchers, return, otherwise
		660	continue with step *.
510		661
511	Example: Queue some jobs and then loop until no events are outsanding	662	Example: Queue some jobs and then loop until no events are outstanding
512	anymore.	663	anymore.
513		664
514	... queue jobs here, make sure they register event watchers as long	665	... queue jobs here, make sure they register event watchers as long
515	... as they still have work to do (even an idle watcher will do..)	666	... as they still have work to do (even an idle watcher will do..)
516	ev_loop (my_loop, 0);	667	ev_loop (my_loop, 0);
517	... jobs done. yeah!	668	... jobs done or somebody called unloop. yeah!
518		669
519	=item ev_unloop (loop, how)	670	=item ev_unloop (loop, how)
520		671
521	Can be used to make a call to C<ev_loop> return early (but only after it	672	Can be used to make a call to C<ev_loop> return early (but only after it
522	has processed all outstanding events). The C<how> argument must be either	673	has processed all outstanding events). The C<how> argument must be either
523	C<EVUNLOOP_ONE>, which will make the innermost C<ev_loop> call return, or	674	C<EVUNLOOP_ONE>, which will make the innermost C<ev_loop> call return, or
524	C<EVUNLOOP_ALL>, which will make all nested C<ev_loop> calls return.	675	C<EVUNLOOP_ALL>, which will make all nested C<ev_loop> calls return.
		676
		677	This "unloop state" will be cleared when entering C<ev_loop> again.
525		678
526	=item ev_ref (loop)	679	=item ev_ref (loop)
527		680
528	=item ev_unref (loop)	681	=item ev_unref (loop)
529		682
…		…
534	returning, ev_unref() after starting, and ev_ref() before stopping it. For	687	returning, ev_unref() after starting, and ev_ref() before stopping it. For
535	example, libev itself uses this for its internal signal pipe: It is not	688	example, libev itself uses this for its internal signal pipe: It is not
536	visible to the libev user and should not keep C<ev_loop> from exiting if	689	visible to the libev user and should not keep C<ev_loop> from exiting if
537	no event watchers registered by it are active. It is also an excellent	690	no event watchers registered by it are active. It is also an excellent
538	way to do this for generic recurring timers or from within third-party	691	way to do this for generic recurring timers or from within third-party
539	libraries. Just remember to I<unref after start> and I<ref before stop>.	692	libraries. Just remember to I<unref after start> and I<ref before stop>
		693	(but only if the watcher wasn't active before, or was active before,
		694	respectively).
540		695
541	Example: Create a signal watcher, but keep it from keeping C<ev_loop>	696	Example: Create a signal watcher, but keep it from keeping C<ev_loop>
542	running when nothing else is active.	697	running when nothing else is active.
543		698
544	struct ev_signal exitsig;	699	struct ev_signal exitsig;
545	ev_signal_init (&exitsig, sig_cb, SIGINT);	700	ev_signal_init (&exitsig, sig_cb, SIGINT);
546	ev_signal_start (loop, &exitsig);	701	ev_signal_start (loop, &exitsig);
547	evf_unref (loop);	702	evf_unref (loop);
548		703
549	Example: For some weird reason, unregister the above signal handler again.	704	Example: For some weird reason, unregister the above signal handler again.
550		705
551	ev_ref (loop);	706	ev_ref (loop);
552	ev_signal_stop (loop, &exitsig);	707	ev_signal_stop (loop, &exitsig);
		708
		709	=item ev_set_io_collect_interval (loop, ev_tstamp interval)
		710
		711	=item ev_set_timeout_collect_interval (loop, ev_tstamp interval)
		712
		713	These advanced functions influence the time that libev will spend waiting
		714	for events. Both time intervals are by default C<0>, meaning that libev
		715	will try to invoke timer/periodic callbacks and I/O callbacks with minimum
		716	latency.
		717
		718	Setting these to a higher value (the C<interval> I<must> be >= C<0>)
		719	allows libev to delay invocation of I/O and timer/periodic callbacks
		720	to increase efficiency of loop iterations (or to increase power-saving
		721	opportunities).
		722
		723	The background is that sometimes your program runs just fast enough to
		724	handle one (or very few) event(s) per loop iteration. While this makes
		725	the program responsive, it also wastes a lot of CPU time to poll for new
		726	events, especially with backends like C<select ()> which have a high
		727	overhead for the actual polling but can deliver many events at once.
		728
		729	By setting a higher I<io collect interval> you allow libev to spend more
		730	time collecting I/O events, so you can handle more events per iteration,
		731	at the cost of increasing latency. Timeouts (both C<ev_periodic> and
		732	C<ev_timer>) will be not affected. Setting this to a non-null value will
		733	introduce an additional C<ev_sleep ()> call into most loop iterations.
		734
		735	Likewise, by setting a higher I<timeout collect interval> you allow libev
		736	to spend more time collecting timeouts, at the expense of increased
		737	latency (the watcher callback will be called later). C<ev_io> watchers
		738	will not be affected. Setting this to a non-null value will not introduce
		739	any overhead in libev.
		740
		741	Many (busy) programs can usually benefit by setting the I/O collect
		742	interval to a value near C<0.1> or so, which is often enough for
		743	interactive servers (of course not for games), likewise for timeouts. It
		744	usually doesn't make much sense to set it to a lower value than C<0.01>,
		745	as this approaches the timing granularity of most systems.
		746
		747	Setting the I<timeout collect interval> can improve the opportunity for
		748	saving power, as the program will "bundle" timer callback invocations that
		749	are "near" in time together, by delaying some, thus reducing the number of
		750	times the process sleeps and wakes up again. Another useful technique to
		751	reduce iterations/wake-ups is to use C<ev_periodic> watchers and make sure
		752	they fire on, say, one-second boundaries only.
		753
		754	=item ev_loop_verify (loop)
		755
		756	This function only does something when C<EV_VERIFY> support has been
		757	compiled in. It tries to go through all internal structures and checks
		758	them for validity. If anything is found to be inconsistent, it will print
		759	an error message to standard error and call C<abort ()>.
		760
		761	This can be used to catch bugs inside libev itself: under normal
		762	circumstances, this function will never abort as of course libev keeps its
		763	data structures consistent.
553		764
554	=back	765	=back
555		766
556		767
557	=head1 ANATOMY OF A WATCHER	768	=head1 ANATOMY OF A WATCHER
558		769
559	A watcher is a structure that you create and register to record your	770	A watcher is a structure that you create and register to record your
560	interest in some event. For instance, if you want to wait for STDIN to	771	interest in some event. For instance, if you want to wait for STDIN to
561	become readable, you would create an C<ev_io> watcher for that:	772	become readable, you would create an C<ev_io> watcher for that:
562		773
563	static void my_cb (struct ev_loop *loop, struct ev_io *w, int revents)	774	static void my_cb (struct ev_loop *loop, struct ev_io *w, int revents)
564	{	775	{
565	ev_io_stop (w);	776	ev_io_stop (w);
566	ev_unloop (loop, EVUNLOOP_ALL);	777	ev_unloop (loop, EVUNLOOP_ALL);
567	}	778	}
568		779
569	struct ev_loop *loop = ev_default_loop (0);	780	struct ev_loop *loop = ev_default_loop (0);
570	struct ev_io stdin_watcher;	781	struct ev_io stdin_watcher;
571	ev_init (&stdin_watcher, my_cb);	782	ev_init (&stdin_watcher, my_cb);
572	ev_io_set (&stdin_watcher, STDIN_FILENO, EV_READ);	783	ev_io_set (&stdin_watcher, STDIN_FILENO, EV_READ);
573	ev_io_start (loop, &stdin_watcher);	784	ev_io_start (loop, &stdin_watcher);
574	ev_loop (loop, 0);	785	ev_loop (loop, 0);
575		786
576	As you can see, you are responsible for allocating the memory for your	787	As you can see, you are responsible for allocating the memory for your
577	watcher structures (and it is usually a bad idea to do this on the stack,	788	watcher structures (and it is usually a bad idea to do this on the stack,
578	although this can sometimes be quite valid).	789	although this can sometimes be quite valid).
579		790
580	Each watcher structure must be initialised by a call to C<ev_init	791	Each watcher structure must be initialised by a call to C<ev_init
581	(watcher *, callback)>, which expects a callback to be provided. This	792	(watcher *, callback)>, which expects a callback to be provided. This
582	callback gets invoked each time the event occurs (or, in the case of io	793	callback gets invoked each time the event occurs (or, in the case of I/O
583	watchers, each time the event loop detects that the file descriptor given	794	watchers, each time the event loop detects that the file descriptor given
584	is readable and/or writable).	795	is readable and/or writable).
585		796
586	Each watcher type has its own C<< ev_<type>_set (watcher *, ...) >> macro	797	Each watcher type has its own C<< ev_<type>_set (watcher *, ...) >> macro
587	with arguments specific to this watcher type. There is also a macro	798	with arguments specific to this watcher type. There is also a macro
…		…
657	=item C<EV_FORK>	868	=item C<EV_FORK>
658		869
659	The event loop has been resumed in the child process after fork (see	870	The event loop has been resumed in the child process after fork (see
660	C<ev_fork>).	871	C<ev_fork>).
661		872
		873	=item C<EV_ASYNC>
		874
		875	The given async watcher has been asynchronously notified (see C<ev_async>).
		876
662	=item C<EV_ERROR>	877	=item C<EV_ERROR>
663		878
664	An unspecified error has occured, the watcher has been stopped. This might	879	An unspecified error has occurred, the watcher has been stopped. This might
665	happen because the watcher could not be properly started because libev	880	happen because the watcher could not be properly started because libev
666	ran out of memory, a file descriptor was found to be closed or any other	881	ran out of memory, a file descriptor was found to be closed or any other
667	problem. You best act on it by reporting the problem and somehow coping	882	problem. You best act on it by reporting the problem and somehow coping
668	with the watcher being stopped.	883	with the watcher being stopped.
669		884
670	Libev will usually signal a few "dummy" events together with an error,	885	Libev will usually signal a few "dummy" events together with an error,
671	for example it might indicate that a fd is readable or writable, and if	886	for example it might indicate that a fd is readable or writable, and if
672	your callbacks is well-written it can just attempt the operation and cope	887	your callbacks is well-written it can just attempt the operation and cope
673	with the error from read() or write(). This will not work in multithreaded	888	with the error from read() or write(). This will not work in multi-threaded
674	programs, though, so beware.	889	programs, though, so beware.
675		890
676	=back	891	=back
677		892
678	=head2 GENERIC WATCHER FUNCTIONS	893	=head2 GENERIC WATCHER FUNCTIONS
…		…
708	Although some watcher types do not have type-specific arguments	923	Although some watcher types do not have type-specific arguments
709	(e.g. C<ev_prepare>) you still need to call its C<set> macro.	924	(e.g. C<ev_prepare>) you still need to call its C<set> macro.
710		925
711	=item C<ev_TYPE_init> (ev_TYPE *watcher, callback, [args])	926	=item C<ev_TYPE_init> (ev_TYPE *watcher, callback, [args])
712		927
713	This convinience macro rolls both C<ev_init> and C<ev_TYPE_set> macro	928	This convenience macro rolls both C<ev_init> and C<ev_TYPE_set> macro
714	calls into a single call. This is the most convinient method to initialise	929	calls into a single call. This is the most convenient method to initialise
715	a watcher. The same limitations apply, of course.	930	a watcher. The same limitations apply, of course.
716		931
717	=item C<ev_TYPE_start> (loop *, ev_TYPE *watcher)	932	=item C<ev_TYPE_start> (loop *, ev_TYPE *watcher)
718		933
719	Starts (activates) the given watcher. Only active watchers will receive	934	Starts (activates) the given watcher. Only active watchers will receive
…		…
802	to associate arbitrary data with your watcher. If you need more data and	1017	to associate arbitrary data with your watcher. If you need more data and
803	don't want to allocate memory and store a pointer to it in that data	1018	don't want to allocate memory and store a pointer to it in that data
804	member, you can also "subclass" the watcher type and provide your own	1019	member, you can also "subclass" the watcher type and provide your own
805	data:	1020	data:
806		1021
807	struct my_io	1022	struct my_io
808	{	1023	{
809	struct ev_io io;	1024	struct ev_io io;
810	int otherfd;	1025	int otherfd;
811	void *somedata;	1026	void *somedata;
812	struct whatever *mostinteresting;	1027	struct whatever *mostinteresting;
813	}	1028	};
		1029
		1030	...
		1031	struct my_io w;
		1032	ev_io_init (&w.io, my_cb, fd, EV_READ);
814		1033
815	And since your callback will be called with a pointer to the watcher, you	1034	And since your callback will be called with a pointer to the watcher, you
816	can cast it back to your own type:	1035	can cast it back to your own type:
817		1036
818	static void my_cb (struct ev_loop *loop, struct ev_io *w_, int revents)	1037	static void my_cb (struct ev_loop *loop, struct ev_io *w_, int revents)
819	{	1038	{
820	struct my_io *w = (struct my_io *)w_;	1039	struct my_io *w = (struct my_io *)w_;
821	...	1040	...
822	}	1041	}
823		1042
824	More interesting and less C-conformant ways of casting your callback type	1043	More interesting and less C-conformant ways of casting your callback type
825	instead have been omitted.	1044	instead have been omitted.
826		1045
827	Another common scenario is having some data structure with multiple	1046	Another common scenario is to use some data structure with multiple
828	watchers:	1047	embedded watchers:
829		1048
830	struct my_biggy	1049	struct my_biggy
831	{	1050	{
832	int some_data;	1051	int some_data;
833	ev_timer t1;	1052	ev_timer t1;
834	ev_timer t2;	1053	ev_timer t2;
835	}	1054	}
836		1055
837	In this case getting the pointer to C<my_biggy> is a bit more complicated,	1056	In this case getting the pointer to C<my_biggy> is a bit more
838	you need to use C<offsetof>:	1057	complicated: Either you store the address of your C<my_biggy> struct
		1058	in the C<data> member of the watcher, or you need to use some pointer
		1059	arithmetic using C<offsetof> inside your watchers:
839		1060
840	#include <stddef.h>	1061	#include <stddef.h>
841		1062
842	static void	1063	static void
843	t1_cb (EV_P_ struct ev_timer *w, int revents)	1064	t1_cb (EV_P_ struct ev_timer *w, int revents)
844	{	1065	{
845	struct my_biggy big = (struct my_biggy *	1066	struct my_biggy big = (struct my_biggy *
846	(((char *)w) - offsetof (struct my_biggy, t1));	1067	(((char *)w) - offsetof (struct my_biggy, t1));
847	}	1068	}
848		1069
849	static void	1070	static void
850	t2_cb (EV_P_ struct ev_timer *w, int revents)	1071	t2_cb (EV_P_ struct ev_timer *w, int revents)
851	{	1072	{
852	struct my_biggy big = (struct my_biggy *	1073	struct my_biggy big = (struct my_biggy *
853	(((char *)w) - offsetof (struct my_biggy, t2));	1074	(((char *)w) - offsetof (struct my_biggy, t2));
854	}	1075	}
855		1076
856		1077
857	=head1 WATCHER TYPES	1078	=head1 WATCHER TYPES
858		1079
859	This section describes each watcher in detail, but will not repeat	1080	This section describes each watcher in detail, but will not repeat
…		…
883	In general you can register as many read and/or write event watchers per	1104	In general you can register as many read and/or write event watchers per
884	fd as you want (as long as you don't confuse yourself). Setting all file	1105	fd as you want (as long as you don't confuse yourself). Setting all file
885	descriptors to non-blocking mode is also usually a good idea (but not	1106	descriptors to non-blocking mode is also usually a good idea (but not
886	required if you know what you are doing).	1107	required if you know what you are doing).
887		1108
888	You have to be careful with dup'ed file descriptors, though. Some backends
889	(the linux epoll backend is a notable example) cannot handle dup'ed file
890	descriptors correctly if you register interest in two or more fds pointing
891	to the same underlying file/socket/etc. description (that is, they share
892	the same underlying "file open").
893
894	If you must do this, then force the use of a known-to-be-good backend	1109	If you must do this, then force the use of a known-to-be-good backend
895	(at the time of this writing, this includes only C<EVBACKEND_SELECT> and	1110	(at the time of this writing, this includes only C<EVBACKEND_SELECT> and
896	C<EVBACKEND_POLL>).	1111	C<EVBACKEND_POLL>).
897		1112
898	Another thing you have to watch out for is that it is quite easy to	1113	Another thing you have to watch out for is that it is quite easy to
899	receive "spurious" readyness notifications, that is your callback might	1114	receive "spurious" readiness notifications, that is your callback might
900	be called with C<EV_READ> but a subsequent C<read>(2) will actually block	1115	be called with C<EV_READ> but a subsequent C<read>(2) will actually block
901	because there is no data. Not only are some backends known to create a	1116	because there is no data. Not only are some backends known to create a
902	lot of those (for example solaris ports), it is very easy to get into	1117	lot of those (for example Solaris ports), it is very easy to get into
903	this situation even with a relatively standard program structure. Thus	1118	this situation even with a relatively standard program structure. Thus
904	it is best to always use non-blocking I/O: An extra C<read>(2) returning	1119	it is best to always use non-blocking I/O: An extra C<read>(2) returning
905	C<EAGAIN> is far preferable to a program hanging until some data arrives.	1120	C<EAGAIN> is far preferable to a program hanging until some data arrives.
906		1121
907	If you cannot run the fd in non-blocking mode (for example you should not	1122	If you cannot run the fd in non-blocking mode (for example you should not
908	play around with an Xlib connection), then you have to seperately re-test	1123	play around with an Xlib connection), then you have to separately re-test
909	whether a file descriptor is really ready with a known-to-be good interface	1124	whether a file descriptor is really ready with a known-to-be good interface
910	such as poll (fortunately in our Xlib example, Xlib already does this on	1125	such as poll (fortunately in our Xlib example, Xlib already does this on
911	its own, so its quite safe to use).	1126	its own, so its quite safe to use).
912		1127
		1128	=head3 The special problem of disappearing file descriptors
		1129
		1130	Some backends (e.g. kqueue, epoll) need to be told about closing a file
		1131	descriptor (either by calling C<close> explicitly or by any other means,
		1132	such as C<dup>). The reason is that you register interest in some file
		1133	descriptor, but when it goes away, the operating system will silently drop
		1134	this interest. If another file descriptor with the same number then is
		1135	registered with libev, there is no efficient way to see that this is, in
		1136	fact, a different file descriptor.
		1137
		1138	To avoid having to explicitly tell libev about such cases, libev follows
		1139	the following policy: Each time C<ev_io_set> is being called, libev
		1140	will assume that this is potentially a new file descriptor, otherwise
		1141	it is assumed that the file descriptor stays the same. That means that
		1142	you I<have> to call C<ev_io_set> (or C<ev_io_init>) when you change the
		1143	descriptor even if the file descriptor number itself did not change.
		1144
		1145	This is how one would do it normally anyway, the important point is that
		1146	the libev application should not optimise around libev but should leave
		1147	optimisations to libev.
		1148
		1149	=head3 The special problem of dup'ed file descriptors
		1150
		1151	Some backends (e.g. epoll), cannot register events for file descriptors,
		1152	but only events for the underlying file descriptions. That means when you
		1153	have C<dup ()>'ed file descriptors or weirder constellations, and register
		1154	events for them, only one file descriptor might actually receive events.
		1155
		1156	There is no workaround possible except not registering events
		1157	for potentially C<dup ()>'ed file descriptors, or to resort to
		1158	C<EVBACKEND_SELECT> or C<EVBACKEND_POLL>.
		1159
		1160	=head3 The special problem of fork
		1161
		1162	Some backends (epoll, kqueue) do not support C<fork ()> at all or exhibit
		1163	useless behaviour. Libev fully supports fork, but needs to be told about
		1164	it in the child.
		1165
		1166	To support fork in your programs, you either have to call
		1167	C<ev_default_fork ()> or C<ev_loop_fork ()> after a fork in the child,
		1168	enable C<EVFLAG_FORKCHECK>, or resort to C<EVBACKEND_SELECT> or
		1169	C<EVBACKEND_POLL>.
		1170
		1171	=head3 The special problem of SIGPIPE
		1172
		1173	While not really specific to libev, it is easy to forget about SIGPIPE:
		1174	when writing to a pipe whose other end has been closed, your program gets
		1175	send a SIGPIPE, which, by default, aborts your program. For most programs
		1176	this is sensible behaviour, for daemons, this is usually undesirable.
		1177
		1178	So when you encounter spurious, unexplained daemon exits, make sure you
		1179	ignore SIGPIPE (and maybe make sure you log the exit status of your daemon
		1180	somewhere, as that would have given you a big clue).
		1181
		1182
		1183	=head3 Watcher-Specific Functions
		1184
913	=over 4	1185	=over 4
914		1186
915	=item ev_io_init (ev_io *, callback, int fd, int events)	1187	=item ev_io_init (ev_io *, callback, int fd, int events)
916		1188
917	=item ev_io_set (ev_io *, int fd, int events)	1189	=item ev_io_set (ev_io *, int fd, int events)
918		1190
919	Configures an C<ev_io> watcher. The C<fd> is the file descriptor to	1191	Configures an C<ev_io> watcher. The C<fd> is the file descriptor to
920	rceeive events for and events is either C<EV_READ>, C<EV_WRITE> or	1192	receive events for and events is either C<EV_READ>, C<EV_WRITE> or
921	C<EV_READ | EV_WRITE> to receive the given events.	1193	C<EV_READ | EV_WRITE> to receive the given events.
922		1194
923	=item int fd [read-only]	1195	=item int fd [read-only]
924		1196
925	The file descriptor being watched.	1197	The file descriptor being watched.
…		…
927	=item int events [read-only]	1199	=item int events [read-only]
928		1200
929	The events being watched.	1201	The events being watched.
930		1202
931	=back	1203	=back
		1204
		1205	=head3 Examples
932		1206
933	Example: Call C<stdin_readable_cb> when STDIN_FILENO has become, well	1207	Example: Call C<stdin_readable_cb> when STDIN_FILENO has become, well
934	readable, but only once. Since it is likely line-buffered, you could	1208	readable, but only once. Since it is likely line-buffered, you could
935	attempt to read a whole line in the callback.	1209	attempt to read a whole line in the callback.
936		1210
937	static void	1211	static void
938	stdin_readable_cb (struct ev_loop *loop, struct ev_io *w, int revents)	1212	stdin_readable_cb (struct ev_loop *loop, struct ev_io *w, int revents)
939	{	1213	{
940	ev_io_stop (loop, w);	1214	ev_io_stop (loop, w);
941	.. read from stdin here (or from w->fd) and haqndle any I/O errors	1215	.. read from stdin here (or from w->fd) and haqndle any I/O errors
942	}	1216	}
943		1217
944	...	1218	...
945	struct ev_loop *loop = ev_default_init (0);	1219	struct ev_loop *loop = ev_default_init (0);
946	struct ev_io stdin_readable;	1220	struct ev_io stdin_readable;
947	ev_io_init (&stdin_readable, stdin_readable_cb, STDIN_FILENO, EV_READ);	1221	ev_io_init (&stdin_readable, stdin_readable_cb, STDIN_FILENO, EV_READ);
948	ev_io_start (loop, &stdin_readable);	1222	ev_io_start (loop, &stdin_readable);
949	ev_loop (loop, 0);	1223	ev_loop (loop, 0);
950		1224
951		1225
952	=head2 C<ev_timer> - relative and optionally repeating timeouts	1226	=head2 C<ev_timer> - relative and optionally repeating timeouts
953		1227
954	Timer watchers are simple relative timers that generate an event after a	1228	Timer watchers are simple relative timers that generate an event after a
955	given time, and optionally repeating in regular intervals after that.	1229	given time, and optionally repeating in regular intervals after that.
956		1230
957	The timers are based on real time, that is, if you register an event that	1231	The timers are based on real time, that is, if you register an event that
958	times out after an hour and you reset your system clock to last years	1232	times out after an hour and you reset your system clock to January last
959	time, it will still time out after (roughly) and hour. "Roughly" because	1233	year, it will still time out after (roughly) and hour. "Roughly" because
960	detecting time jumps is hard, and some inaccuracies are unavoidable (the	1234	detecting time jumps is hard, and some inaccuracies are unavoidable (the
961	monotonic clock option helps a lot here).	1235	monotonic clock option helps a lot here).
		1236
		1237	The callback is guaranteed to be invoked only after its timeout has passed,
		1238	but if multiple timers become ready during the same loop iteration then
		1239	order of execution is undefined.
		1240
		1241	=head3 The special problem of time updates
		1242
		1243	Establishing the current time is a costly operation (it usually takes at
		1244	least two system calls): EV therefore updates its idea of the current
		1245	time only before and after C<ev_loop> polls for new events, which causes
		1246	a growing difference between C<ev_now ()> and C<ev_time ()> when handling
		1247	lots of events.
962		1248
963	The relative timeouts are calculated relative to the C<ev_now ()>	1249	The relative timeouts are calculated relative to the C<ev_now ()>
964	time. This is usually the right thing as this timestamp refers to the time	1250	time. This is usually the right thing as this timestamp refers to the time
965	of the event triggering whatever timeout you are modifying/starting. If	1251	of the event triggering whatever timeout you are modifying/starting. If
966	you suspect event processing to be delayed and you I<need> to base the timeout	1252	you suspect event processing to be delayed and you I<need> to base the
967	on the current time, use something like this to adjust for this:	1253	timeout on the current time, use something like this to adjust for this:
968		1254
969	ev_timer_set (&timer, after + ev_now () - ev_time (), 0.);	1255	ev_timer_set (&timer, after + ev_now () - ev_time (), 0.);
970		1256
971	The callback is guarenteed to be invoked only when its timeout has passed,	1257	If the event loop is suspended for a long time, you can also force an
972	but if multiple timers become ready during the same loop iteration then	1258	update of the time returned by C<ev_now ()> by calling C<ev_now_update
973	order of execution is undefined.	1259	()>.
		1260
		1261	=head3 Watcher-Specific Functions and Data Members
974		1262
975	=over 4	1263	=over 4
976		1264
977	=item ev_timer_init (ev_timer *, callback, ev_tstamp after, ev_tstamp repeat)	1265	=item ev_timer_init (ev_timer *, callback, ev_tstamp after, ev_tstamp repeat)
978		1266
979	=item ev_timer_set (ev_timer *, ev_tstamp after, ev_tstamp repeat)	1267	=item ev_timer_set (ev_timer *, ev_tstamp after, ev_tstamp repeat)
980		1268
981	Configure the timer to trigger after C<after> seconds. If C<repeat> is	1269	Configure the timer to trigger after C<after> seconds. If C<repeat>
982	C<0.>, then it will automatically be stopped. If it is positive, then the	1270	is C<0.>, then it will automatically be stopped once the timeout is
983	timer will automatically be configured to trigger again C<repeat> seconds	1271	reached. If it is positive, then the timer will automatically be
984	later, again, and again, until stopped manually.	1272	configured to trigger again C<repeat> seconds later, again, and again,
		1273	until stopped manually.
985		1274
986	The timer itself will do a best-effort at avoiding drift, that is, if you	1275	The timer itself will do a best-effort at avoiding drift, that is, if
987	configure a timer to trigger every 10 seconds, then it will trigger at	1276	you configure a timer to trigger every 10 seconds, then it will normally
988	exactly 10 second intervals. If, however, your program cannot keep up with	1277	trigger at exactly 10 second intervals. If, however, your program cannot
989	the timer (because it takes longer than those 10 seconds to do stuff) the	1278	keep up with the timer (because it takes longer than those 10 seconds to
990	timer will not fire more than once per event loop iteration.	1279	do stuff) the timer will not fire more than once per event loop iteration.
991		1280
992	=item ev_timer_again (loop)	1281	=item ev_timer_again (loop, ev_timer *)
993		1282
994	This will act as if the timer timed out and restart it again if it is	1283	This will act as if the timer timed out and restart it again if it is
995	repeating. The exact semantics are:	1284	repeating. The exact semantics are:
996		1285
997	If the timer is pending, its pending status is cleared.	1286	If the timer is pending, its pending status is cleared.
998		1287
999	If the timer is started but nonrepeating, stop it (as if it timed out).	1288	If the timer is started but non-repeating, stop it (as if it timed out).
1000		1289
1001	If the timer is repeating, either start it if necessary (with the	1290	If the timer is repeating, either start it if necessary (with the
1002	C<repeat> value), or reset the running timer to the C<repeat> value.	1291	C<repeat> value), or reset the running timer to the C<repeat> value.
1003		1292
1004	This sounds a bit complicated, but here is a useful and typical	1293	This sounds a bit complicated, but here is a useful and typical
1005	example: Imagine you have a tcp connection and you want a so-called idle	1294	example: Imagine you have a TCP connection and you want a so-called idle
1006	timeout, that is, you want to be called when there have been, say, 60	1295	timeout, that is, you want to be called when there have been, say, 60
1007	seconds of inactivity on the socket. The easiest way to do this is to	1296	seconds of inactivity on the socket. The easiest way to do this is to
1008	configure an C<ev_timer> with a C<repeat> value of C<60> and then call	1297	configure an C<ev_timer> with a C<repeat> value of C<60> and then call
1009	C<ev_timer_again> each time you successfully read or write some data. If	1298	C<ev_timer_again> each time you successfully read or write some data. If
1010	you go into an idle state where you do not expect data to travel on the	1299	you go into an idle state where you do not expect data to travel on the
…		…
1032	or C<ev_timer_again> is called and determines the next timeout (if any),	1321	or C<ev_timer_again> is called and determines the next timeout (if any),
1033	which is also when any modifications are taken into account.	1322	which is also when any modifications are taken into account.
1034		1323
1035	=back	1324	=back
1036		1325
		1326	=head3 Examples
		1327
1037	Example: Create a timer that fires after 60 seconds.	1328	Example: Create a timer that fires after 60 seconds.
1038		1329
1039	static void	1330	static void
1040	one_minute_cb (struct ev_loop *loop, struct ev_timer *w, int revents)	1331	one_minute_cb (struct ev_loop *loop, struct ev_timer *w, int revents)
1041	{	1332	{
1042	.. one minute over, w is actually stopped right here	1333	.. one minute over, w is actually stopped right here
1043	}	1334	}
1044		1335
1045	struct ev_timer mytimer;	1336	struct ev_timer mytimer;
1046	ev_timer_init (&mytimer, one_minute_cb, 60., 0.);	1337	ev_timer_init (&mytimer, one_minute_cb, 60., 0.);
1047	ev_timer_start (loop, &mytimer);	1338	ev_timer_start (loop, &mytimer);
1048		1339
1049	Example: Create a timeout timer that times out after 10 seconds of	1340	Example: Create a timeout timer that times out after 10 seconds of
1050	inactivity.	1341	inactivity.
1051		1342
1052	static void	1343	static void
1053	timeout_cb (struct ev_loop *loop, struct ev_timer *w, int revents)	1344	timeout_cb (struct ev_loop *loop, struct ev_timer *w, int revents)
1054	{	1345	{
1055	.. ten seconds without any activity	1346	.. ten seconds without any activity
1056	}	1347	}
1057		1348
1058	struct ev_timer mytimer;	1349	struct ev_timer mytimer;
1059	ev_timer_init (&mytimer, timeout_cb, 0., 10.); /* note, only repeat used */	1350	ev_timer_init (&mytimer, timeout_cb, 0., 10.); /* note, only repeat used */
1060	ev_timer_again (&mytimer); /* start timer */	1351	ev_timer_again (&mytimer); /* start timer */
1061	ev_loop (loop, 0);	1352	ev_loop (loop, 0);
1062		1353
1063	// and in some piece of code that gets executed on any "activity":	1354	// and in some piece of code that gets executed on any "activity":
1064	// reset the timeout to start ticking again at 10 seconds	1355	// reset the timeout to start ticking again at 10 seconds
1065	ev_timer_again (&mytimer);	1356	ev_timer_again (&mytimer);
1066		1357
1067		1358
1068	=head2 C<ev_periodic> - to cron or not to cron?	1359	=head2 C<ev_periodic> - to cron or not to cron?
1069		1360
1070	Periodic watchers are also timers of a kind, but they are very versatile	1361	Periodic watchers are also timers of a kind, but they are very versatile
1071	(and unfortunately a bit complex).	1362	(and unfortunately a bit complex).
1072		1363
1073	Unlike C<ev_timer>'s, they are not based on real time (or relative time)	1364	Unlike C<ev_timer>'s, they are not based on real time (or relative time)
1074	but on wallclock time (absolute time). You can tell a periodic watcher	1365	but on wall clock time (absolute time). You can tell a periodic watcher
1075	to trigger "at" some specific point in time. For example, if you tell a	1366	to trigger after some specific point in time. For example, if you tell a
1076	periodic watcher to trigger in 10 seconds (by specifiying e.g. C<ev_now ()	1367	periodic watcher to trigger in 10 seconds (by specifying e.g. C<ev_now ()
1077	+ 10.>) and then reset your system clock to the last year, then it will	1368	+ 10.>, that is, an absolute time not a delay) and then reset your system
		1369	clock to January of the previous year, then it will take more than year
1078	take a year to trigger the event (unlike an C<ev_timer>, which would trigger	1370	to trigger the event (unlike an C<ev_timer>, which would still trigger
1079	roughly 10 seconds later).	1371	roughly 10 seconds later as it uses a relative timeout).
1080		1372
1081	They can also be used to implement vastly more complex timers, such as	1373	C<ev_periodic>s can also be used to implement vastly more complex timers,
1082	triggering an event on each midnight, local time or other, complicated,	1374	such as triggering an event on each "midnight, local time", or other
1083	rules.	1375	complicated, rules.
1084		1376
1085	As with timers, the callback is guarenteed to be invoked only when the	1377	As with timers, the callback is guaranteed to be invoked only when the
1086	time (C<at>) has been passed, but if multiple periodic timers become ready	1378	time (C<at>) has passed, but if multiple periodic timers become ready
1087	during the same loop iteration then order of execution is undefined.	1379	during the same loop iteration then order of execution is undefined.
		1380
		1381	=head3 Watcher-Specific Functions and Data Members
1088		1382
1089	=over 4	1383	=over 4
1090		1384
1091	=item ev_periodic_init (ev_periodic *, callback, ev_tstamp at, ev_tstamp interval, reschedule_cb)	1385	=item ev_periodic_init (ev_periodic *, callback, ev_tstamp at, ev_tstamp interval, reschedule_cb)
1092		1386
…		…
1097		1391
1098	=over 4	1392	=over 4
1099		1393
1100	=item * absolute timer (at = time, interval = reschedule_cb = 0)	1394	=item * absolute timer (at = time, interval = reschedule_cb = 0)
1101		1395
1102	In this configuration the watcher triggers an event at the wallclock time	1396	In this configuration the watcher triggers an event after the wall clock
1103	C<at> and doesn't repeat. It will not adjust when a time jump occurs,	1397	time C<at> has passed and doesn't repeat. It will not adjust when a time
1104	that is, if it is to be run at January 1st 2011 then it will run when the	1398	jump occurs, that is, if it is to be run at January 1st 2011 then it will
1105	system time reaches or surpasses this time.	1399	run when the system time reaches or surpasses this time.
1106		1400
1107	=item * non-repeating interval timer (at = offset, interval > 0, reschedule_cb = 0)	1401	=item * repeating interval timer (at = offset, interval > 0, reschedule_cb = 0)
1108		1402
1109	In this mode the watcher will always be scheduled to time out at the next	1403	In this mode the watcher will always be scheduled to time out at the next
1110	C<at + N * interval> time (for some integer N, which can also be negative)	1404	C<at + N * interval> time (for some integer N, which can also be negative)
1111	and then repeat, regardless of any time jumps.	1405	and then repeat, regardless of any time jumps.
1112		1406
1113	This can be used to create timers that do not drift with respect to system	1407	This can be used to create timers that do not drift with respect to system
1114	time:	1408	time, for example, here is a C<ev_periodic> that triggers each hour, on
		1409	the hour:
1115		1410
1116	ev_periodic_set (&periodic, 0., 3600., 0);	1411	ev_periodic_set (&periodic, 0., 3600., 0);
1117		1412
1118	This doesn't mean there will always be 3600 seconds in between triggers,	1413	This doesn't mean there will always be 3600 seconds in between triggers,
1119	but only that the the callback will be called when the system time shows a	1414	but only that the callback will be called when the system time shows a
1120	full hour (UTC), or more correctly, when the system time is evenly divisible	1415	full hour (UTC), or more correctly, when the system time is evenly divisible
1121	by 3600.	1416	by 3600.
1122		1417
1123	Another way to think about it (for the mathematically inclined) is that	1418	Another way to think about it (for the mathematically inclined) is that
1124	C<ev_periodic> will try to run the callback in this mode at the next possible	1419	C<ev_periodic> will try to run the callback in this mode at the next possible
1125	time where C<time = at (mod interval)>, regardless of any time jumps.	1420	time where C<time = at (mod interval)>, regardless of any time jumps.
1126		1421
1127	For numerical stability it is preferable that the C<at> value is near	1422	For numerical stability it is preferable that the C<at> value is near
1128	C<ev_now ()> (the current time), but there is no range requirement for	1423	C<ev_now ()> (the current time), but there is no range requirement for
1129	this value.	1424	this value, and in fact is often specified as zero.
		1425
		1426	Note also that there is an upper limit to how often a timer can fire (CPU
		1427	speed for example), so if C<interval> is very small then timing stability
		1428	will of course deteriorate. Libev itself tries to be exact to be about one
		1429	millisecond (if the OS supports it and the machine is fast enough).
1130		1430
1131	=item * manual reschedule mode (at and interval ignored, reschedule_cb = callback)	1431	=item * manual reschedule mode (at and interval ignored, reschedule_cb = callback)
1132		1432
1133	In this mode the values for C<interval> and C<at> are both being	1433	In this mode the values for C<interval> and C<at> are both being
1134	ignored. Instead, each time the periodic watcher gets scheduled, the	1434	ignored. Instead, each time the periodic watcher gets scheduled, the
1135	reschedule callback will be called with the watcher as first, and the	1435	reschedule callback will be called with the watcher as first, and the
1136	current time as second argument.	1436	current time as second argument.
1137		1437
1138	NOTE: I<This callback MUST NOT stop or destroy any periodic watcher,	1438	NOTE: I<This callback MUST NOT stop or destroy any periodic watcher,
1139	ever, or make any event loop modifications>. If you need to stop it,	1439	ever, or make ANY event loop modifications whatsoever>.
1140	return C<now + 1e30> (or so, fudge fudge) and stop it afterwards (e.g. by
1141	starting an C<ev_prepare> watcher, which is legal).
1142		1440
		1441	If you need to stop it, return C<now + 1e30> (or so, fudge fudge) and stop
		1442	it afterwards (e.g. by starting an C<ev_prepare> watcher, which is the
		1443	only event loop modification you are allowed to do).
		1444
1143	Its prototype is C<ev_tstamp (*reschedule_cb)(struct ev_periodic *w,	1445	The callback prototype is C<ev_tstamp (*reschedule_cb)(struct ev_periodic
1144	ev_tstamp now)>, e.g.:	1446	*w, ev_tstamp now)>, e.g.:
1145		1447
1146	static ev_tstamp my_rescheduler (struct ev_periodic *w, ev_tstamp now)	1448	static ev_tstamp my_rescheduler (struct ev_periodic *w, ev_tstamp now)
1147	{	1449	{
1148	return now + 60.;	1450	return now + 60.;
1149	}	1451	}
…		…
1151	It must return the next time to trigger, based on the passed time value	1453	It must return the next time to trigger, based on the passed time value
1152	(that is, the lowest time value larger than to the second argument). It	1454	(that is, the lowest time value larger than to the second argument). It
1153	will usually be called just before the callback will be triggered, but	1455	will usually be called just before the callback will be triggered, but
1154	might be called at other times, too.	1456	might be called at other times, too.
1155		1457
1156	NOTE: I<< This callback must always return a time that is later than the	1458	NOTE: I<< This callback must always return a time that is higher than or
1157	passed C<now> value >>. Not even C<now> itself will do, it I<must> be larger.	1459	equal to the passed C<now> value >>.
1158		1460
1159	This can be used to create very complex timers, such as a timer that	1461	This can be used to create very complex timers, such as a timer that
1160	triggers on each midnight, local time. To do this, you would calculate the	1462	triggers on "next midnight, local time". To do this, you would calculate the
1161	next midnight after C<now> and return the timestamp value for this. How	1463	next midnight after C<now> and return the timestamp value for this. How
1162	you do this is, again, up to you (but it is not trivial, which is the main	1464	you do this is, again, up to you (but it is not trivial, which is the main
1163	reason I omitted it as an example).	1465	reason I omitted it as an example).
1164		1466
1165	=back	1467	=back
…		…
1169	Simply stops and restarts the periodic watcher again. This is only useful	1471	Simply stops and restarts the periodic watcher again. This is only useful
1170	when you changed some parameters or the reschedule callback would return	1472	when you changed some parameters or the reschedule callback would return
1171	a different time than the last time it was called (e.g. in a crond like	1473	a different time than the last time it was called (e.g. in a crond like
1172	program when the crontabs have changed).	1474	program when the crontabs have changed).
1173		1475
		1476	=item ev_tstamp ev_periodic_at (ev_periodic *)
		1477
		1478	When active, returns the absolute time that the watcher is supposed to
		1479	trigger next.
		1480
1174	=item ev_tstamp offset [read-write]	1481	=item ev_tstamp offset [read-write]
1175		1482
1176	When repeating, this contains the offset value, otherwise this is the	1483	When repeating, this contains the offset value, otherwise this is the
1177	absolute point in time (the C<at> value passed to C<ev_periodic_set>).	1484	absolute point in time (the C<at> value passed to C<ev_periodic_set>).
1178		1485
…		…
1191	switched off. Can be changed any time, but changes only take effect when	1498	switched off. Can be changed any time, but changes only take effect when
1192	the periodic timer fires or C<ev_periodic_again> is being called.	1499	the periodic timer fires or C<ev_periodic_again> is being called.
1193		1500
1194	=back	1501	=back
1195		1502
		1503	=head3 Examples
		1504
1196	Example: Call a callback every hour, or, more precisely, whenever the	1505	Example: Call a callback every hour, or, more precisely, whenever the
1197	system clock is divisible by 3600. The callback invocation times have	1506	system clock is divisible by 3600. The callback invocation times have
1198	potentially a lot of jittering, but good long-term stability.	1507	potentially a lot of jitter, but good long-term stability.
1199		1508
1200	static void	1509	static void
1201	clock_cb (struct ev_loop *loop, struct ev_io *w, int revents)	1510	clock_cb (struct ev_loop *loop, struct ev_io *w, int revents)
1202	{	1511	{
1203	... its now a full hour (UTC, or TAI or whatever your clock follows)	1512	... its now a full hour (UTC, or TAI or whatever your clock follows)
1204	}	1513	}
1205		1514
1206	struct ev_periodic hourly_tick;	1515	struct ev_periodic hourly_tick;
1207	ev_periodic_init (&hourly_tick, clock_cb, 0., 3600., 0);	1516	ev_periodic_init (&hourly_tick, clock_cb, 0., 3600., 0);
1208	ev_periodic_start (loop, &hourly_tick);	1517	ev_periodic_start (loop, &hourly_tick);
1209		1518
1210	Example: The same as above, but use a reschedule callback to do it:	1519	Example: The same as above, but use a reschedule callback to do it:
1211		1520
1212	#include <math.h>	1521	#include <math.h>
1213		1522
1214	static ev_tstamp	1523	static ev_tstamp
1215	my_scheduler_cb (struct ev_periodic *w, ev_tstamp now)	1524	my_scheduler_cb (struct ev_periodic *w, ev_tstamp now)
1216	{	1525	{
1217	return fmod (now, 3600.) + 3600.;	1526	return fmod (now, 3600.) + 3600.;
1218	}	1527	}
1219		1528
1220	ev_periodic_init (&hourly_tick, clock_cb, 0., 0., my_scheduler_cb);	1529	ev_periodic_init (&hourly_tick, clock_cb, 0., 0., my_scheduler_cb);
1221		1530
1222	Example: Call a callback every hour, starting now:	1531	Example: Call a callback every hour, starting now:
1223		1532
1224	struct ev_periodic hourly_tick;	1533	struct ev_periodic hourly_tick;
1225	ev_periodic_init (&hourly_tick, clock_cb,	1534	ev_periodic_init (&hourly_tick, clock_cb,
1226	fmod (ev_now (loop), 3600.), 3600., 0);	1535	fmod (ev_now (loop), 3600.), 3600., 0);
1227	ev_periodic_start (loop, &hourly_tick);	1536	ev_periodic_start (loop, &hourly_tick);
1228		1537
1229		1538
1230	=head2 C<ev_signal> - signal me when a signal gets signalled!	1539	=head2 C<ev_signal> - signal me when a signal gets signalled!
1231		1540
1232	Signal watchers will trigger an event when the process receives a specific	1541	Signal watchers will trigger an event when the process receives a specific
…		…
1239	with the kernel (thus it coexists with your own signal handlers as long	1548	with the kernel (thus it coexists with your own signal handlers as long
1240	as you don't register any with libev). Similarly, when the last signal	1549	as you don't register any with libev). Similarly, when the last signal
1241	watcher for a signal is stopped libev will reset the signal handler to	1550	watcher for a signal is stopped libev will reset the signal handler to
1242	SIG_DFL (regardless of what it was set to before).	1551	SIG_DFL (regardless of what it was set to before).
1243		1552
		1553	If possible and supported, libev will install its handlers with
		1554	C<SA_RESTART> behaviour enabled, so system calls should not be unduly
		1555	interrupted. If you have a problem with system calls getting interrupted by
		1556	signals you can block all signals in an C<ev_check> watcher and unblock
		1557	them in an C<ev_prepare> watcher.
		1558
		1559	=head3 Watcher-Specific Functions and Data Members
		1560
1244	=over 4	1561	=over 4
1245		1562
1246	=item ev_signal_init (ev_signal *, callback, int signum)	1563	=item ev_signal_init (ev_signal *, callback, int signum)
1247		1564
1248	=item ev_signal_set (ev_signal *, int signum)	1565	=item ev_signal_set (ev_signal *, int signum)
…		…
1254		1571
1255	The signal the watcher watches out for.	1572	The signal the watcher watches out for.
1256		1573
1257	=back	1574	=back
1258		1575
		1576	=head3 Examples
		1577
		1578	Example: Try to exit cleanly on SIGINT and SIGTERM.
		1579
		1580	static void
		1581	sigint_cb (struct ev_loop *loop, struct ev_signal *w, int revents)
		1582	{
		1583	ev_unloop (loop, EVUNLOOP_ALL);
		1584	}
		1585
		1586	struct ev_signal signal_watcher;
		1587	ev_signal_init (&signal_watcher, sigint_cb, SIGINT);
		1588	ev_signal_start (loop, &sigint_cb);
		1589
1259		1590
1260	=head2 C<ev_child> - watch out for process status changes	1591	=head2 C<ev_child> - watch out for process status changes
1261		1592
1262	Child watchers trigger when your process receives a SIGCHLD in response to	1593	Child watchers trigger when your process receives a SIGCHLD in response to
1263	some child status changes (most typically when a child of yours dies).	1594	some child status changes (most typically when a child of yours dies). It
		1595	is permissible to install a child watcher I<after> the child has been
		1596	forked (which implies it might have already exited), as long as the event
		1597	loop isn't entered (or is continued from a watcher).
		1598
		1599	Only the default event loop is capable of handling signals, and therefore
		1600	you can only register child watchers in the default event loop.
		1601
		1602	=head3 Process Interaction
		1603
		1604	Libev grabs C<SIGCHLD> as soon as the default event loop is
		1605	initialised. This is necessary to guarantee proper behaviour even if
		1606	the first child watcher is started after the child exits. The occurrence
		1607	of C<SIGCHLD> is recorded asynchronously, but child reaping is done
		1608	synchronously as part of the event loop processing. Libev always reaps all
		1609	children, even ones not watched.
		1610
		1611	=head3 Overriding the Built-In Processing
		1612
		1613	Libev offers no special support for overriding the built-in child
		1614	processing, but if your application collides with libev's default child
		1615	handler, you can override it easily by installing your own handler for
		1616	C<SIGCHLD> after initialising the default loop, and making sure the
		1617	default loop never gets destroyed. You are encouraged, however, to use an
		1618	event-based approach to child reaping and thus use libev's support for
		1619	that, so other libev users can use C<ev_child> watchers freely.
		1620
		1621	=head3 Stopping the Child Watcher
		1622
		1623	Currently, the child watcher never gets stopped, even when the
		1624	child terminates, so normally one needs to stop the watcher in the
		1625	callback. Future versions of libev might stop the watcher automatically
		1626	when a child exit is detected.
		1627
		1628	=head3 Watcher-Specific Functions and Data Members
1264		1629
1265	=over 4	1630	=over 4
1266		1631
1267	=item ev_child_init (ev_child *, callback, int pid)	1632	=item ev_child_init (ev_child *, callback, int pid, int trace)
1268		1633
1269	=item ev_child_set (ev_child *, int pid)	1634	=item ev_child_set (ev_child *, int pid, int trace)
1270		1635
1271	Configures the watcher to wait for status changes of process C<pid> (or	1636	Configures the watcher to wait for status changes of process C<pid> (or
1272	I<any> process if C<pid> is specified as C<0>). The callback can look	1637	I<any> process if C<pid> is specified as C<0>). The callback can look
1273	at the C<rstatus> member of the C<ev_child> watcher structure to see	1638	at the C<rstatus> member of the C<ev_child> watcher structure to see
1274	the status word (use the macros from C<sys/wait.h> and see your systems	1639	the status word (use the macros from C<sys/wait.h> and see your systems
1275	C<waitpid> documentation). The C<rpid> member contains the pid of the	1640	C<waitpid> documentation). The C<rpid> member contains the pid of the
1276	process causing the status change.	1641	process causing the status change. C<trace> must be either C<0> (only
		1642	activate the watcher when the process terminates) or C<1> (additionally
		1643	activate the watcher when the process is stopped or continued).
1277		1644
1278	=item int pid [read-only]	1645	=item int pid [read-only]
1279		1646
1280	The process id this watcher watches out for, or C<0>, meaning any process id.	1647	The process id this watcher watches out for, or C<0>, meaning any process id.
1281		1648
…		…
1288	The process exit/trace status caused by C<rpid> (see your systems	1655	The process exit/trace status caused by C<rpid> (see your systems
1289	C<waitpid> and C<sys/wait.h> documentation for details).	1656	C<waitpid> and C<sys/wait.h> documentation for details).
1290		1657
1291	=back	1658	=back
1292		1659
1293	Example: Try to exit cleanly on SIGINT and SIGTERM.	1660	=head3 Examples
1294		1661
		1662	Example: C<fork()> a new process and install a child handler to wait for
		1663	its completion.
		1664
		1665	ev_child cw;
		1666
1295	static void	1667	static void
1296	sigint_cb (struct ev_loop *loop, struct ev_signal *w, int revents)	1668	child_cb (EV_P_ struct ev_child *w, int revents)
1297	{	1669	{
1298	ev_unloop (loop, EVUNLOOP_ALL);	1670	ev_child_stop (EV_A_ w);
		1671	printf ("process %d exited with status %x\n", w->rpid, w->rstatus);
1299	}	1672	}
1300		1673
1301	struct ev_signal signal_watcher;	1674	pid_t pid = fork ();
1302	ev_signal_init (&signal_watcher, sigint_cb, SIGINT);	1675
1303	ev_signal_start (loop, &sigint_cb);	1676	if (pid < 0)
		1677	// error
		1678	else if (pid == 0)
		1679	{
		1680	// the forked child executes here
		1681	exit (1);
		1682	}
		1683	else
		1684	{
		1685	ev_child_init (&cw, child_cb, pid, 0);
		1686	ev_child_start (EV_DEFAULT_ &cw);
		1687	}
1304		1688
1305		1689
1306	=head2 C<ev_stat> - did the file attributes just change?	1690	=head2 C<ev_stat> - did the file attributes just change?
1307		1691
1308	This watches a filesystem path for attribute changes. That is, it calls	1692	This watches a file system path for attribute changes. That is, it calls
1309	C<stat> regularly (or when the OS says it changed) and sees if it changed	1693	C<stat> regularly (or when the OS says it changed) and sees if it changed
1310	compared to the last time, invoking the callback if it did.	1694	compared to the last time, invoking the callback if it did.
1311		1695
1312	The path does not need to exist: changing from "path exists" to "path does	1696	The path does not need to exist: changing from "path exists" to "path does
1313	not exist" is a status change like any other. The condition "path does	1697	not exist" is a status change like any other. The condition "path does
…		…
1331	as even with OS-supported change notifications, this can be	1715	as even with OS-supported change notifications, this can be
1332	resource-intensive.	1716	resource-intensive.
1333		1717
1334	At the time of this writing, only the Linux inotify interface is	1718	At the time of this writing, only the Linux inotify interface is
1335	implemented (implementing kqueue support is left as an exercise for the	1719	implemented (implementing kqueue support is left as an exercise for the
		1720	reader, note, however, that the author sees no way of implementing ev_stat
1336	reader). Inotify will be used to give hints only and should not change the	1721	semantics with kqueue). Inotify will be used to give hints only and should
1337	semantics of C<ev_stat> watchers, which means that libev sometimes needs	1722	not change the semantics of C<ev_stat> watchers, which means that libev
1338	to fall back to regular polling again even with inotify, but changes are	1723	sometimes needs to fall back to regular polling again even with inotify,
1339	usually detected immediately, and if the file exists there will be no	1724	but changes are usually detected immediately, and if the file exists there
1340	polling.	1725	will be no polling.
		1726
		1727	=head3 ABI Issues (Largefile Support)
		1728
		1729	Libev by default (unless the user overrides this) uses the default
		1730	compilation environment, which means that on systems with large file
		1731	support disabled by default, you get the 32 bit version of the stat
		1732	structure. When using the library from programs that change the ABI to
		1733	use 64 bit file offsets the programs will fail. In that case you have to
		1734	compile libev with the same flags to get binary compatibility. This is
		1735	obviously the case with any flags that change the ABI, but the problem is
		1736	most noticeably disabled with ev_stat and large file support.
		1737
		1738	The solution for this is to lobby your distribution maker to make large
		1739	file interfaces available by default (as e.g. FreeBSD does) and not
		1740	optional. Libev cannot simply switch on large file support because it has
		1741	to exchange stat structures with application programs compiled using the
		1742	default compilation environment.
		1743
		1744	=head3 Inotify
		1745
		1746	When C<inotify (7)> support has been compiled into libev (generally only
		1747	available on Linux) and present at runtime, it will be used to speed up
		1748	change detection where possible. The inotify descriptor will be created lazily
		1749	when the first C<ev_stat> watcher is being started.
		1750
		1751	Inotify presence does not change the semantics of C<ev_stat> watchers
		1752	except that changes might be detected earlier, and in some cases, to avoid
		1753	making regular C<stat> calls. Even in the presence of inotify support
		1754	there are many cases where libev has to resort to regular C<stat> polling.
		1755
		1756	(There is no support for kqueue, as apparently it cannot be used to
		1757	implement this functionality, due to the requirement of having a file
		1758	descriptor open on the object at all times).
		1759
		1760	=head3 The special problem of stat time resolution
		1761
		1762	The C<stat ()> system call only supports full-second resolution portably, and
		1763	even on systems where the resolution is higher, many file systems still
		1764	only support whole seconds.
		1765
		1766	That means that, if the time is the only thing that changes, you can
		1767	easily miss updates: on the first update, C<ev_stat> detects a change and
		1768	calls your callback, which does something. When there is another update
		1769	within the same second, C<ev_stat> will be unable to detect it as the stat
		1770	data does not change.
		1771
		1772	The solution to this is to delay acting on a change for slightly more
		1773	than a second (or till slightly after the next full second boundary), using
		1774	a roughly one-second-delay C<ev_timer> (e.g. C<ev_timer_set (w, 0., 1.02);
		1775	ev_timer_again (loop, w)>).
		1776
		1777	The C<.02> offset is added to work around small timing inconsistencies
		1778	of some operating systems (where the second counter of the current time
		1779	might be be delayed. One such system is the Linux kernel, where a call to
		1780	C<gettimeofday> might return a timestamp with a full second later than
		1781	a subsequent C<time> call - if the equivalent of C<time ()> is used to
		1782	update file times then there will be a small window where the kernel uses
		1783	the previous second to update file times but libev might already execute
		1784	the timer callback).
		1785
		1786	=head3 Watcher-Specific Functions and Data Members
1341		1787
1342	=over 4	1788	=over 4
1343		1789
1344	=item ev_stat_init (ev_stat *, callback, const char *path, ev_tstamp interval)	1790	=item ev_stat_init (ev_stat *, callback, const char *path, ev_tstamp interval)
1345		1791
…		…
1349	C<path>. The C<interval> is a hint on how quickly a change is expected to	1795	C<path>. The C<interval> is a hint on how quickly a change is expected to
1350	be detected and should normally be specified as C<0> to let libev choose	1796	be detected and should normally be specified as C<0> to let libev choose
1351	a suitable value. The memory pointed to by C<path> must point to the same	1797	a suitable value. The memory pointed to by C<path> must point to the same
1352	path for as long as the watcher is active.	1798	path for as long as the watcher is active.
1353		1799
1354	The callback will be receive C<EV_STAT> when a change was detected,	1800	The callback will receive C<EV_STAT> when a change was detected, relative
1355	relative to the attributes at the time the watcher was started (or the	1801	to the attributes at the time the watcher was started (or the last change
1356	last change was detected).	1802	was detected).
1357		1803
1358	=item ev_stat_stat (ev_stat *)	1804	=item ev_stat_stat (loop, ev_stat *)
1359		1805
1360	Updates the stat buffer immediately with new values. If you change the	1806	Updates the stat buffer immediately with new values. If you change the
1361	watched path in your callback, you could call this fucntion to avoid	1807	watched path in your callback, you could call this function to avoid
1362	detecting this change (while introducing a race condition). Can also be	1808	detecting this change (while introducing a race condition if you are not
1363	useful simply to find out the new values.	1809	the only one changing the path). Can also be useful simply to find out the
		1810	new values.
1364		1811
1365	=item ev_statdata attr [read-only]	1812	=item ev_statdata attr [read-only]
1366		1813
1367	The most-recently detected attributes of the file. Although the type is of	1814	The most-recently detected attributes of the file. Although the type is
1368	C<ev_statdata>, this is usually the (or one of the) C<struct stat> types	1815	C<ev_statdata>, this is usually the (or one of the) C<struct stat> types
1369	suitable for your system. If the C<st_nlink> member is C<0>, then there	1816	suitable for your system, but you can only rely on the POSIX-standardised
		1817	members to be present. If the C<st_nlink> member is C<0>, then there was
1370	was some error while C<stat>ing the file.	1818	some error while C<stat>ing the file.
1371		1819
1372	=item ev_statdata prev [read-only]	1820	=item ev_statdata prev [read-only]
1373		1821
1374	The previous attributes of the file. The callback gets invoked whenever	1822	The previous attributes of the file. The callback gets invoked whenever
1375	C<prev> != C<attr>.	1823	C<prev> != C<attr>, or, more precisely, one or more of these members
		1824	differ: C<st_dev>, C<st_ino>, C<st_mode>, C<st_nlink>, C<st_uid>,
		1825	C<st_gid>, C<st_rdev>, C<st_size>, C<st_atime>, C<st_mtime>, C<st_ctime>.
1376		1826
1377	=item ev_tstamp interval [read-only]	1827	=item ev_tstamp interval [read-only]
1378		1828
1379	The specified interval.	1829	The specified interval.
1380		1830
1381	=item const char *path [read-only]	1831	=item const char *path [read-only]
1382		1832
1383	The filesystem path that is being watched.	1833	The file system path that is being watched.
1384		1834
1385	=back	1835	=back
1386		1836
		1837	=head3 Examples
		1838
1387	Example: Watch C</etc/passwd> for attribute changes.	1839	Example: Watch C</etc/passwd> for attribute changes.
1388		1840
1389	static void	1841	static void
1390	passwd_cb (struct ev_loop *loop, ev_stat *w, int revents)	1842	passwd_cb (struct ev_loop *loop, ev_stat *w, int revents)
1391	{	1843	{
1392	/* /etc/passwd changed in some way */	1844	/* /etc/passwd changed in some way */
1393	if (w->attr.st_nlink)	1845	if (w->attr.st_nlink)
1394	{	1846	{
1395	printf ("passwd current size %ld\n", (long)w->attr.st_size);	1847	printf ("passwd current size %ld\n", (long)w->attr.st_size);
1396	printf ("passwd current atime %ld\n", (long)w->attr.st_mtime);	1848	printf ("passwd current atime %ld\n", (long)w->attr.st_mtime);
1397	printf ("passwd current mtime %ld\n", (long)w->attr.st_mtime);	1849	printf ("passwd current mtime %ld\n", (long)w->attr.st_mtime);
1398	}	1850	}
1399	else	1851	else
1400	/* you shalt not abuse printf for puts */	1852	/* you shalt not abuse printf for puts */
1401	puts ("wow, /etc/passwd is not there, expect problems. "	1853	puts ("wow, /etc/passwd is not there, expect problems. "
1402	"if this is windows, they already arrived\n");	1854	"if this is windows, they already arrived\n");
1403	}	1855	}
1404		1856
1405	...	1857	...
1406	ev_stat passwd;	1858	ev_stat passwd;
1407		1859
1408	ev_stat_init (&passwd, passwd_cb, "/etc/passwd");	1860	ev_stat_init (&passwd, passwd_cb, "/etc/passwd", 0.);
1409	ev_stat_start (loop, &passwd);	1861	ev_stat_start (loop, &passwd);
		1862
		1863	Example: Like above, but additionally use a one-second delay so we do not
		1864	miss updates (however, frequent updates will delay processing, too, so
		1865	one might do the work both on C<ev_stat> callback invocation I<and> on
		1866	C<ev_timer> callback invocation).
		1867
		1868	static ev_stat passwd;
		1869	static ev_timer timer;
		1870
		1871	static void
		1872	timer_cb (EV_P_ ev_timer *w, int revents)
		1873	{
		1874	ev_timer_stop (EV_A_ w);
		1875
		1876	/* now it's one second after the most recent passwd change */
		1877	}
		1878
		1879	static void
		1880	stat_cb (EV_P_ ev_stat *w, int revents)
		1881	{
		1882	/* reset the one-second timer */
		1883	ev_timer_again (EV_A_ &timer);
		1884	}
		1885
		1886	...
		1887	ev_stat_init (&passwd, stat_cb, "/etc/passwd", 0.);
		1888	ev_stat_start (loop, &passwd);
		1889	ev_timer_init (&timer, timer_cb, 0., 1.02);
1410		1890
1411		1891
1412	=head2 C<ev_idle> - when you've got nothing better to do...	1892	=head2 C<ev_idle> - when you've got nothing better to do...
1413		1893
1414	Idle watchers trigger events when no other events of the same or higher	1894	Idle watchers trigger events when no other events of the same or higher
…		…
1428	Apart from keeping your process non-blocking (which is a useful	1908	Apart from keeping your process non-blocking (which is a useful
1429	effect on its own sometimes), idle watchers are a good place to do	1909	effect on its own sometimes), idle watchers are a good place to do
1430	"pseudo-background processing", or delay processing stuff to after the	1910	"pseudo-background processing", or delay processing stuff to after the
1431	event loop has handled all outstanding events.	1911	event loop has handled all outstanding events.
1432		1912
		1913	=head3 Watcher-Specific Functions and Data Members
		1914
1433	=over 4	1915	=over 4
1434		1916
1435	=item ev_idle_init (ev_signal *, callback)	1917	=item ev_idle_init (ev_signal *, callback)
1436		1918
1437	Initialises and configures the idle watcher - it has no parameters of any	1919	Initialises and configures the idle watcher - it has no parameters of any
1438	kind. There is a C<ev_idle_set> macro, but using it is utterly pointless,	1920	kind. There is a C<ev_idle_set> macro, but using it is utterly pointless,
1439	believe me.	1921	believe me.
1440		1922
1441	=back	1923	=back
1442		1924
		1925	=head3 Examples
		1926
1443	Example: Dynamically allocate an C<ev_idle> watcher, start it, and in the	1927	Example: Dynamically allocate an C<ev_idle> watcher, start it, and in the
1444	callback, free it. Also, use no error checking, as usual.	1928	callback, free it. Also, use no error checking, as usual.
1445		1929
1446	static void	1930	static void
1447	idle_cb (struct ev_loop *loop, struct ev_idle *w, int revents)	1931	idle_cb (struct ev_loop *loop, struct ev_idle *w, int revents)
1448	{	1932	{
1449	free (w);	1933	free (w);
1450	// now do something you wanted to do when the program has	1934	// now do something you wanted to do when the program has
1451	// no longer asnything immediate to do.	1935	// no longer anything immediate to do.
1452	}	1936	}
1453		1937
1454	struct ev_idle *idle_watcher = malloc (sizeof (struct ev_idle));	1938	struct ev_idle *idle_watcher = malloc (sizeof (struct ev_idle));
1455	ev_idle_init (idle_watcher, idle_cb);	1939	ev_idle_init (idle_watcher, idle_cb);
1456	ev_idle_start (loop, idle_cb);	1940	ev_idle_start (loop, idle_cb);
1457		1941
1458		1942
1459	=head2 C<ev_prepare> and C<ev_check> - customise your event loop!	1943	=head2 C<ev_prepare> and C<ev_check> - customise your event loop!
1460		1944
1461	Prepare and check watchers are usually (but not always) used in tandem:	1945	Prepare and check watchers are usually (but not always) used in tandem:
…		…
1480		1964
1481	This is done by examining in each prepare call which file descriptors need	1965	This is done by examining in each prepare call which file descriptors need
1482	to be watched by the other library, registering C<ev_io> watchers for	1966	to be watched by the other library, registering C<ev_io> watchers for
1483	them and starting an C<ev_timer> watcher for any timeouts (many libraries	1967	them and starting an C<ev_timer> watcher for any timeouts (many libraries
1484	provide just this functionality). Then, in the check watcher you check for	1968	provide just this functionality). Then, in the check watcher you check for
1485	any events that occured (by checking the pending status of all watchers	1969	any events that occurred (by checking the pending status of all watchers
1486	and stopping them) and call back into the library. The I/O and timer	1970	and stopping them) and call back into the library. The I/O and timer
1487	callbacks will never actually be called (but must be valid nevertheless,	1971	callbacks will never actually be called (but must be valid nevertheless,
1488	because you never know, you know?).	1972	because you never know, you know?).
1489		1973
1490	As another example, the Perl Coro module uses these hooks to integrate	1974	As another example, the Perl Coro module uses these hooks to integrate
…		…
1498		1982
1499	It is recommended to give C<ev_check> watchers highest (C<EV_MAXPRI>)	1983	It is recommended to give C<ev_check> watchers highest (C<EV_MAXPRI>)
1500	priority, to ensure that they are being run before any other watchers	1984	priority, to ensure that they are being run before any other watchers
1501	after the poll. Also, C<ev_check> watchers (and C<ev_prepare> watchers,	1985	after the poll. Also, C<ev_check> watchers (and C<ev_prepare> watchers,
1502	too) should not activate ("feed") events into libev. While libev fully	1986	too) should not activate ("feed") events into libev. While libev fully
1503	supports this, they will be called before other C<ev_check> watchers did	1987	supports this, they might get executed before other C<ev_check> watchers
1504	their job. As C<ev_check> watchers are often used to embed other event	1988	did their job. As C<ev_check> watchers are often used to embed other
1505	loops those other event loops might be in an unusable state until their	1989	(non-libev) event loops those other event loops might be in an unusable
1506	C<ev_check> watcher ran (always remind yourself to coexist peacefully with	1990	state until their C<ev_check> watcher ran (always remind yourself to
1507	others).	1991	coexist peacefully with others).
		1992
		1993	=head3 Watcher-Specific Functions and Data Members
1508		1994
1509	=over 4	1995	=over 4
1510		1996
1511	=item ev_prepare_init (ev_prepare *, callback)	1997	=item ev_prepare_init (ev_prepare *, callback)
1512		1998
…		…
1516	parameters of any kind. There are C<ev_prepare_set> and C<ev_check_set>	2002	parameters of any kind. There are C<ev_prepare_set> and C<ev_check_set>
1517	macros, but using them is utterly, utterly and completely pointless.	2003	macros, but using them is utterly, utterly and completely pointless.
1518		2004
1519	=back	2005	=back
1520		2006
		2007	=head3 Examples
		2008
1521	There are a number of principal ways to embed other event loops or modules	2009	There are a number of principal ways to embed other event loops or modules
1522	into libev. Here are some ideas on how to include libadns into libev	2010	into libev. Here are some ideas on how to include libadns into libev
1523	(there is a Perl module named C<EV::ADNS> that does this, which you could	2011	(there is a Perl module named C<EV::ADNS> that does this, which you could
1524	use for an actually working example. Another Perl module named C<EV::Glib>	2012	use as a working example. Another Perl module named C<EV::Glib> embeds a
1525	embeds a Glib main context into libev, and finally, C<Glib::EV> embeds EV	2013	Glib main context into libev, and finally, C<Glib::EV> embeds EV into the
1526	into the Glib event loop).	2014	Glib event loop).
1527		2015
1528	Method 1: Add IO watchers and a timeout watcher in a prepare handler,	2016	Method 1: Add IO watchers and a timeout watcher in a prepare handler,
1529	and in a check watcher, destroy them and call into libadns. What follows	2017	and in a check watcher, destroy them and call into libadns. What follows
1530	is pseudo-code only of course. This requires you to either use a low	2018	is pseudo-code only of course. This requires you to either use a low
1531	priority for the check watcher or use C<ev_clear_pending> explicitly, as	2019	priority for the check watcher or use C<ev_clear_pending> explicitly, as
1532	the callbacks for the IO/timeout watchers might not have been called yet.	2020	the callbacks for the IO/timeout watchers might not have been called yet.
1533		2021
1534	static ev_io iow [nfd];	2022	static ev_io iow [nfd];
1535	static ev_timer tw;	2023	static ev_timer tw;
1536		2024
1537	static void	2025	static void
1538	io_cb (ev_loop *loop, ev_io *w, int revents)	2026	io_cb (ev_loop *loop, ev_io *w, int revents)
1539	{	2027	{
1540	}	2028	}
1541		2029
1542	// create io watchers for each fd and a timer before blocking	2030	// create io watchers for each fd and a timer before blocking
1543	static void	2031	static void
1544	adns_prepare_cb (ev_loop *loop, ev_prepare *w, int revents)	2032	adns_prepare_cb (ev_loop *loop, ev_prepare *w, int revents)
1545	{	2033	{
1546	int timeout = 3600000;	2034	int timeout = 3600000;
1547	struct pollfd fds [nfd];	2035	struct pollfd fds [nfd];
1548	// actual code will need to loop here and realloc etc.	2036	// actual code will need to loop here and realloc etc.
1549	adns_beforepoll (ads, fds, &nfd, &timeout, timeval_from (ev_time ()));	2037	adns_beforepoll (ads, fds, &nfd, &timeout, timeval_from (ev_time ()));
1550		2038
1551	/* the callback is illegal, but won't be called as we stop during check */	2039	/* the callback is illegal, but won't be called as we stop during check */
1552	ev_timer_init (&tw, 0, timeout * 1e-3);	2040	ev_timer_init (&tw, 0, timeout * 1e-3);
1553	ev_timer_start (loop, &tw);	2041	ev_timer_start (loop, &tw);
1554		2042
1555	// create one ev_io per pollfd	2043	// create one ev_io per pollfd
1556	for (int i = 0; i < nfd; ++i)	2044	for (int i = 0; i < nfd; ++i)
1557	{	2045	{
1558	ev_io_init (iow + i, io_cb, fds [i].fd,	2046	ev_io_init (iow + i, io_cb, fds [i].fd,
1559	((fds [i].events & POLLIN ? EV_READ : 0)	2047	((fds [i].events & POLLIN ? EV_READ : 0)
1560	| (fds [i].events & POLLOUT ? EV_WRITE : 0)));	2048	| (fds [i].events & POLLOUT ? EV_WRITE : 0)));
1561		2049
1562	fds [i].revents = 0;	2050	fds [i].revents = 0;
1563	ev_io_start (loop, iow + i);	2051	ev_io_start (loop, iow + i);
1564	}	2052	}
1565	}	2053	}
1566		2054
1567	// stop all watchers after blocking	2055	// stop all watchers after blocking
1568	static void	2056	static void
1569	adns_check_cb (ev_loop *loop, ev_check *w, int revents)	2057	adns_check_cb (ev_loop *loop, ev_check *w, int revents)
1570	{	2058	{
1571	ev_timer_stop (loop, &tw);	2059	ev_timer_stop (loop, &tw);
1572		2060
1573	for (int i = 0; i < nfd; ++i)	2061	for (int i = 0; i < nfd; ++i)
1574	{	2062	{
1575	// set the relevant poll flags	2063	// set the relevant poll flags
1576	// could also call adns_processreadable etc. here	2064	// could also call adns_processreadable etc. here
1577	struct pollfd *fd = fds + i;	2065	struct pollfd *fd = fds + i;
1578	int revents = ev_clear_pending (iow + i);	2066	int revents = ev_clear_pending (iow + i);
1579	if (revents & EV_READ ) fd->revents |= fd->events & POLLIN;	2067	if (revents & EV_READ ) fd->revents |= fd->events & POLLIN;
1580	if (revents & EV_WRITE) fd->revents |= fd->events & POLLOUT;	2068	if (revents & EV_WRITE) fd->revents |= fd->events & POLLOUT;
1581		2069
1582	// now stop the watcher	2070	// now stop the watcher
1583	ev_io_stop (loop, iow + i);	2071	ev_io_stop (loop, iow + i);
1584	}	2072	}
1585		2073
1586	adns_afterpoll (adns, fds, nfd, timeval_from (ev_now (loop));	2074	adns_afterpoll (adns, fds, nfd, timeval_from (ev_now (loop));
1587	}	2075	}
1588		2076
1589	Method 2: This would be just like method 1, but you run C<adns_afterpoll>	2077	Method 2: This would be just like method 1, but you run C<adns_afterpoll>
1590	in the prepare watcher and would dispose of the check watcher.	2078	in the prepare watcher and would dispose of the check watcher.
1591		2079
1592	Method 3: If the module to be embedded supports explicit event	2080	Method 3: If the module to be embedded supports explicit event
1593	notification (adns does), you can also make use of the actual watcher	2081	notification (libadns does), you can also make use of the actual watcher
1594	callbacks, and only destroy/create the watchers in the prepare watcher.	2082	callbacks, and only destroy/create the watchers in the prepare watcher.
1595		2083
1596	static void	2084	static void
1597	timer_cb (EV_P_ ev_timer *w, int revents)	2085	timer_cb (EV_P_ ev_timer *w, int revents)
1598	{	2086	{
1599	adns_state ads = (adns_state)w->data;	2087	adns_state ads = (adns_state)w->data;
1600	update_now (EV_A);	2088	update_now (EV_A);
1601		2089
1602	adns_processtimeouts (ads, &tv_now);	2090	adns_processtimeouts (ads, &tv_now);
1603	}	2091	}
1604		2092
1605	static void	2093	static void
1606	io_cb (EV_P_ ev_io *w, int revents)	2094	io_cb (EV_P_ ev_io *w, int revents)
1607	{	2095	{
1608	adns_state ads = (adns_state)w->data;	2096	adns_state ads = (adns_state)w->data;
1609	update_now (EV_A);	2097	update_now (EV_A);
1610		2098
1611	if (revents & EV_READ ) adns_processreadable (ads, w->fd, &tv_now);	2099	if (revents & EV_READ ) adns_processreadable (ads, w->fd, &tv_now);
1612	if (revents & EV_WRITE) adns_processwriteable (ads, w->fd, &tv_now);	2100	if (revents & EV_WRITE) adns_processwriteable (ads, w->fd, &tv_now);
1613	}	2101	}
1614		2102
1615	// do not ever call adns_afterpoll	2103	// do not ever call adns_afterpoll
1616		2104
1617	Method 4: Do not use a prepare or check watcher because the module you	2105	Method 4: Do not use a prepare or check watcher because the module you
1618	want to embed is too inflexible to support it. Instead, youc na override	2106	want to embed is too inflexible to support it. Instead, you can override
1619	their poll function. The drawback with this solution is that the main	2107	their poll function. The drawback with this solution is that the main
1620	loop is now no longer controllable by EV. The C<Glib::EV> module does	2108	loop is now no longer controllable by EV. The C<Glib::EV> module does
1621	this.	2109	this.
1622		2110
1623	static gint	2111	static gint
1624	event_poll_func (GPollFD *fds, guint nfds, gint timeout)	2112	event_poll_func (GPollFD *fds, guint nfds, gint timeout)
1625	{	2113	{
1626	int got_events = 0;	2114	int got_events = 0;
1627		2115
1628	for (n = 0; n < nfds; ++n)	2116	for (n = 0; n < nfds; ++n)
1629	// create/start io watcher that sets the relevant bits in fds[n] and increment got_events	2117	// create/start io watcher that sets the relevant bits in fds[n] and increment got_events
1630		2118
1631	if (timeout >= 0)	2119	if (timeout >= 0)
1632	// create/start timer	2120	// create/start timer
1633		2121
1634	// poll	2122	// poll
1635	ev_loop (EV_A_ 0);	2123	ev_loop (EV_A_ 0);
1636		2124
1637	// stop timer again	2125	// stop timer again
1638	if (timeout >= 0)	2126	if (timeout >= 0)
1639	ev_timer_stop (EV_A_ &to);	2127	ev_timer_stop (EV_A_ &to);
1640		2128
1641	// stop io watchers again - their callbacks should have set	2129	// stop io watchers again - their callbacks should have set
1642	for (n = 0; n < nfds; ++n)	2130	for (n = 0; n < nfds; ++n)
1643	ev_io_stop (EV_A_ iow [n]);	2131	ev_io_stop (EV_A_ iow [n]);
1644		2132
1645	return got_events;	2133	return got_events;
1646	}	2134	}
1647		2135
1648		2136
1649	=head2 C<ev_embed> - when one backend isn't enough...	2137	=head2 C<ev_embed> - when one backend isn't enough...
1650		2138
1651	This is a rather advanced watcher type that lets you embed one event loop	2139	This is a rather advanced watcher type that lets you embed one event loop
…		…
1693	portable one.	2181	portable one.
1694		2182
1695	So when you want to use this feature you will always have to be prepared	2183	So when you want to use this feature you will always have to be prepared
1696	that you cannot get an embeddable loop. The recommended way to get around	2184	that you cannot get an embeddable loop. The recommended way to get around
1697	this is to have a separate variables for your embeddable loop, try to	2185	this is to have a separate variables for your embeddable loop, try to
1698	create it, and if that fails, use the normal loop for everything:	2186	create it, and if that fails, use the normal loop for everything.
1699		2187
1700	struct ev_loop *loop_hi = ev_default_init (0);	2188	=head3 Watcher-Specific Functions and Data Members
1701	struct ev_loop *loop_lo = 0;
1702	struct ev_embed embed;
1703
1704	// see if there is a chance of getting one that works
1705	// (remember that a flags value of 0 means autodetection)
1706	loop_lo = ev_embeddable_backends () & ev_recommended_backends ()
1707	? ev_loop_new (ev_embeddable_backends () & ev_recommended_backends ())
1708	: 0;
1709
1710	// if we got one, then embed it, otherwise default to loop_hi
1711	if (loop_lo)
1712	{
1713	ev_embed_init (&embed, 0, loop_lo);
1714	ev_embed_start (loop_hi, &embed);
1715	}
1716	else
1717	loop_lo = loop_hi;
1718		2189
1719	=over 4	2190	=over 4
1720		2191
1721	=item ev_embed_init (ev_embed *, callback, struct ev_loop *embedded_loop)	2192	=item ev_embed_init (ev_embed *, callback, struct ev_loop *embedded_loop)
1722		2193
…		…
1724		2195
1725	Configures the watcher to embed the given loop, which must be	2196	Configures the watcher to embed the given loop, which must be
1726	embeddable. If the callback is C<0>, then C<ev_embed_sweep> will be	2197	embeddable. If the callback is C<0>, then C<ev_embed_sweep> will be
1727	invoked automatically, otherwise it is the responsibility of the callback	2198	invoked automatically, otherwise it is the responsibility of the callback
1728	to invoke it (it will continue to be called until the sweep has been done,	2199	to invoke it (it will continue to be called until the sweep has been done,
1729	if you do not want thta, you need to temporarily stop the embed watcher).	2200	if you do not want that, you need to temporarily stop the embed watcher).
1730		2201
1731	=item ev_embed_sweep (loop, ev_embed *)	2202	=item ev_embed_sweep (loop, ev_embed *)
1732		2203
1733	Make a single, non-blocking sweep over the embedded loop. This works	2204	Make a single, non-blocking sweep over the embedded loop. This works
1734	similarly to C<ev_loop (embedded_loop, EVLOOP_NONBLOCK)>, but in the most	2205	similarly to C<ev_loop (embedded_loop, EVLOOP_NONBLOCK)>, but in the most
1735	apropriate way for embedded loops.	2206	appropriate way for embedded loops.
1736		2207
1737	=item struct ev_loop *loop [read-only]	2208	=item struct ev_loop *other [read-only]
1738		2209
1739	The embedded event loop.	2210	The embedded event loop.
1740		2211
1741	=back	2212	=back
		2213
		2214	=head3 Examples
		2215
		2216	Example: Try to get an embeddable event loop and embed it into the default
		2217	event loop. If that is not possible, use the default loop. The default
		2218	loop is stored in C<loop_hi>, while the embeddable loop is stored in
		2219	C<loop_lo> (which is C<loop_hi> in the case no embeddable loop can be
		2220	used).
		2221
		2222	struct ev_loop *loop_hi = ev_default_init (0);
		2223	struct ev_loop *loop_lo = 0;
		2224	struct ev_embed embed;
		2225
		2226	// see if there is a chance of getting one that works
		2227	// (remember that a flags value of 0 means autodetection)
		2228	loop_lo = ev_embeddable_backends () & ev_recommended_backends ()
		2229	? ev_loop_new (ev_embeddable_backends () & ev_recommended_backends ())
		2230	: 0;
		2231
		2232	// if we got one, then embed it, otherwise default to loop_hi
		2233	if (loop_lo)
		2234	{
		2235	ev_embed_init (&embed, 0, loop_lo);
		2236	ev_embed_start (loop_hi, &embed);
		2237	}
		2238	else
		2239	loop_lo = loop_hi;
		2240
		2241	Example: Check if kqueue is available but not recommended and create
		2242	a kqueue backend for use with sockets (which usually work with any
		2243	kqueue implementation). Store the kqueue/socket-only event loop in
		2244	C<loop_socket>. (One might optionally use C<EVFLAG_NOENV>, too).
		2245
		2246	struct ev_loop *loop = ev_default_init (0);
		2247	struct ev_loop *loop_socket = 0;
		2248	struct ev_embed embed;
		2249
		2250	if (ev_supported_backends () & ~ev_recommended_backends () & EVBACKEND_KQUEUE)
		2251	if ((loop_socket = ev_loop_new (EVBACKEND_KQUEUE))
		2252	{
		2253	ev_embed_init (&embed, 0, loop_socket);
		2254	ev_embed_start (loop, &embed);
		2255	}
		2256
		2257	if (!loop_socket)
		2258	loop_socket = loop;
		2259
		2260	// now use loop_socket for all sockets, and loop for everything else
1742		2261
1743		2262
1744	=head2 C<ev_fork> - the audacity to resume the event loop after a fork	2263	=head2 C<ev_fork> - the audacity to resume the event loop after a fork
1745		2264
1746	Fork watchers are called when a C<fork ()> was detected (usually because	2265	Fork watchers are called when a C<fork ()> was detected (usually because
…		…
1749	event loop blocks next and before C<ev_check> watchers are being called,	2268	event loop blocks next and before C<ev_check> watchers are being called,
1750	and only in the child after the fork. If whoever good citizen calling	2269	and only in the child after the fork. If whoever good citizen calling
1751	C<ev_default_fork> cheats and calls it in the wrong process, the fork	2270	C<ev_default_fork> cheats and calls it in the wrong process, the fork
1752	handlers will be invoked, too, of course.	2271	handlers will be invoked, too, of course.
1753		2272
		2273	=head3 Watcher-Specific Functions and Data Members
		2274
1754	=over 4	2275	=over 4
1755		2276
1756	=item ev_fork_init (ev_signal *, callback)	2277	=item ev_fork_init (ev_signal *, callback)
1757		2278
1758	Initialises and configures the fork watcher - it has no parameters of any	2279	Initialises and configures the fork watcher - it has no parameters of any
1759	kind. There is a C<ev_fork_set> macro, but using it is utterly pointless,	2280	kind. There is a C<ev_fork_set> macro, but using it is utterly pointless,
1760	believe me.	2281	believe me.
		2282
		2283	=back
		2284
		2285
		2286	=head2 C<ev_async> - how to wake up another event loop
		2287
		2288	In general, you cannot use an C<ev_loop> from multiple threads or other
		2289	asynchronous sources such as signal handlers (as opposed to multiple event
		2290	loops - those are of course safe to use in different threads).
		2291
		2292	Sometimes, however, you need to wake up another event loop you do not
		2293	control, for example because it belongs to another thread. This is what
		2294	C<ev_async> watchers do: as long as the C<ev_async> watcher is active, you
		2295	can signal it by calling C<ev_async_send>, which is thread- and signal
		2296	safe.
		2297
		2298	This functionality is very similar to C<ev_signal> watchers, as signals,
		2299	too, are asynchronous in nature, and signals, too, will be compressed
		2300	(i.e. the number of callback invocations may be less than the number of
		2301	C<ev_async_sent> calls).
		2302
		2303	Unlike C<ev_signal> watchers, C<ev_async> works with any event loop, not
		2304	just the default loop.
		2305
		2306	=head3 Queueing
		2307
		2308	C<ev_async> does not support queueing of data in any way. The reason
		2309	is that the author does not know of a simple (or any) algorithm for a
		2310	multiple-writer-single-reader queue that works in all cases and doesn't
		2311	need elaborate support such as pthreads.
		2312
		2313	That means that if you want to queue data, you have to provide your own
		2314	queue. But at least I can tell you would implement locking around your
		2315	queue:
		2316
		2317	=over 4
		2318
		2319	=item queueing from a signal handler context
		2320
		2321	To implement race-free queueing, you simply add to the queue in the signal
		2322	handler but you block the signal handler in the watcher callback. Here is an example that does that for
		2323	some fictitious SIGUSR1 handler:
		2324
		2325	static ev_async mysig;
		2326
		2327	static void
		2328	sigusr1_handler (void)
		2329	{
		2330	sometype data;
		2331
		2332	// no locking etc.
		2333	queue_put (data);
		2334	ev_async_send (EV_DEFAULT_ &mysig);
		2335	}
		2336
		2337	static void
		2338	mysig_cb (EV_P_ ev_async *w, int revents)
		2339	{
		2340	sometype data;
		2341	sigset_t block, prev;
		2342
		2343	sigemptyset (&block);
		2344	sigaddset (&block, SIGUSR1);
		2345	sigprocmask (SIG_BLOCK, &block, &prev);
		2346
		2347	while (queue_get (&data))
		2348	process (data);
		2349
		2350	if (sigismember (&prev, SIGUSR1)
		2351	sigprocmask (SIG_UNBLOCK, &block, 0);
		2352	}
		2353
		2354	(Note: pthreads in theory requires you to use C<pthread_setmask>
		2355	instead of C<sigprocmask> when you use threads, but libev doesn't do it
		2356	either...).
		2357
		2358	=item queueing from a thread context
		2359
		2360	The strategy for threads is different, as you cannot (easily) block
		2361	threads but you can easily preempt them, so to queue safely you need to
		2362	employ a traditional mutex lock, such as in this pthread example:
		2363
		2364	static ev_async mysig;
		2365	static pthread_mutex_t mymutex = PTHREAD_MUTEX_INITIALIZER;
		2366
		2367	static void
		2368	otherthread (void)
		2369	{
		2370	// only need to lock the actual queueing operation
		2371	pthread_mutex_lock (&mymutex);
		2372	queue_put (data);
		2373	pthread_mutex_unlock (&mymutex);
		2374
		2375	ev_async_send (EV_DEFAULT_ &mysig);
		2376	}
		2377
		2378	static void
		2379	mysig_cb (EV_P_ ev_async *w, int revents)
		2380	{
		2381	pthread_mutex_lock (&mymutex);
		2382
		2383	while (queue_get (&data))
		2384	process (data);
		2385
		2386	pthread_mutex_unlock (&mymutex);
		2387	}
		2388
		2389	=back
		2390
		2391
		2392	=head3 Watcher-Specific Functions and Data Members
		2393
		2394	=over 4
		2395
		2396	=item ev_async_init (ev_async *, callback)
		2397
		2398	Initialises and configures the async watcher - it has no parameters of any
		2399	kind. There is a C<ev_asynd_set> macro, but using it is utterly pointless,
		2400	believe me.
		2401
		2402	=item ev_async_send (loop, ev_async *)
		2403
		2404	Sends/signals/activates the given C<ev_async> watcher, that is, feeds
		2405	an C<EV_ASYNC> event on the watcher into the event loop. Unlike
		2406	C<ev_feed_event>, this call is safe to do in other threads, signal or
		2407	similar contexts (see the discussion of C<EV_ATOMIC_T> in the embedding
		2408	section below on what exactly this means).
		2409
		2410	This call incurs the overhead of a system call only once per loop iteration,
		2411	so while the overhead might be noticeable, it doesn't apply to repeated
		2412	calls to C<ev_async_send>.
		2413
		2414	=item bool = ev_async_pending (ev_async *)
		2415
		2416	Returns a non-zero value when C<ev_async_send> has been called on the
		2417	watcher but the event has not yet been processed (or even noted) by the
		2418	event loop.
		2419
		2420	C<ev_async_send> sets a flag in the watcher and wakes up the loop. When
		2421	the loop iterates next and checks for the watcher to have become active,
		2422	it will reset the flag again. C<ev_async_pending> can be used to very
		2423	quickly check whether invoking the loop might be a good idea.
		2424
		2425	Not that this does I<not> check whether the watcher itself is pending, only
		2426	whether it has been requested to make this watcher pending.
1761		2427
1762	=back	2428	=back
1763		2429
1764		2430
1765	=head1 OTHER FUNCTIONS	2431	=head1 OTHER FUNCTIONS
…		…
1776	or timeout without having to allocate/configure/start/stop/free one or	2442	or timeout without having to allocate/configure/start/stop/free one or
1777	more watchers yourself.	2443	more watchers yourself.
1778		2444
1779	If C<fd> is less than 0, then no I/O watcher will be started and events	2445	If C<fd> is less than 0, then no I/O watcher will be started and events
1780	is being ignored. Otherwise, an C<ev_io> watcher for the given C<fd> and	2446	is being ignored. Otherwise, an C<ev_io> watcher for the given C<fd> and
1781	C<events> set will be craeted and started.	2447	C<events> set will be created and started.
1782		2448
1783	If C<timeout> is less than 0, then no timeout watcher will be	2449	If C<timeout> is less than 0, then no timeout watcher will be
1784	started. Otherwise an C<ev_timer> watcher with after = C<timeout> (and	2450	started. Otherwise an C<ev_timer> watcher with after = C<timeout> (and
1785	repeat = 0) will be started. While C<0> is a valid timeout, it is of	2451	repeat = 0) will be started. While C<0> is a valid timeout, it is of
1786	dubious value.	2452	dubious value.
…		…
1788	The callback has the type C<void (*cb)(int revents, void *arg)> and gets	2454	The callback has the type C<void (*cb)(int revents, void *arg)> and gets
1789	passed an C<revents> set like normal event callbacks (a combination of	2455	passed an C<revents> set like normal event callbacks (a combination of
1790	C<EV_ERROR>, C<EV_READ>, C<EV_WRITE> or C<EV_TIMEOUT>) and the C<arg>	2456	C<EV_ERROR>, C<EV_READ>, C<EV_WRITE> or C<EV_TIMEOUT>) and the C<arg>
1791	value passed to C<ev_once>:	2457	value passed to C<ev_once>:
1792		2458
1793	static void stdin_ready (int revents, void *arg)	2459	static void stdin_ready (int revents, void *arg)
1794	{	2460	{
1795	if (revents & EV_TIMEOUT)	2461	if (revents & EV_TIMEOUT)
1796	/* doh, nothing entered */;	2462	/* doh, nothing entered */;
1797	else if (revents & EV_READ)	2463	else if (revents & EV_READ)
1798	/* stdin might have data for us, joy! */;	2464	/* stdin might have data for us, joy! */;
1799	}	2465	}
1800		2466
1801	ev_once (STDIN_FILENO, EV_READ, 10., stdin_ready, 0);	2467	ev_once (STDIN_FILENO, EV_READ, 10., stdin_ready, 0);
1802		2468
1803	=item ev_feed_event (ev_loop *, watcher *, int revents)	2469	=item ev_feed_event (ev_loop *, watcher *, int revents)
1804		2470
1805	Feeds the given event set into the event loop, as if the specified event	2471	Feeds the given event set into the event loop, as if the specified event
1806	had happened for the specified watcher (which must be a pointer to an	2472	had happened for the specified watcher (which must be a pointer to an
…		…
1811	Feed an event on the given fd, as if a file descriptor backend detected	2477	Feed an event on the given fd, as if a file descriptor backend detected
1812	the given events it.	2478	the given events it.
1813		2479
1814	=item ev_feed_signal_event (ev_loop *loop, int signum)	2480	=item ev_feed_signal_event (ev_loop *loop, int signum)
1815		2481
1816	Feed an event as if the given signal occured (C<loop> must be the default	2482	Feed an event as if the given signal occurred (C<loop> must be the default
1817	loop!).	2483	loop!).
1818		2484
1819	=back	2485	=back
1820		2486
1821		2487
…		…
1837		2503
1838	=item * Priorities are not currently supported. Initialising priorities	2504	=item * Priorities are not currently supported. Initialising priorities
1839	will fail and all watchers will have the same priority, even though there	2505	will fail and all watchers will have the same priority, even though there
1840	is an ev_pri field.	2506	is an ev_pri field.
1841		2507
		2508	=item * In libevent, the last base created gets the signals, in libev, the
		2509	first base created (== the default loop) gets the signals.
		2510
1842	=item * Other members are not supported.	2511	=item * Other members are not supported.
1843		2512
1844	=item * The libev emulation is I<not> ABI compatible to libevent, you need	2513	=item * The libev emulation is I<not> ABI compatible to libevent, you need
1845	to use the libev header file and library.	2514	to use the libev header file and library.
1846		2515
1847	=back	2516	=back
1848		2517
1849	=head1 C++ SUPPORT	2518	=head1 C++ SUPPORT
1850		2519
1851	Libev comes with some simplistic wrapper classes for C++ that mainly allow	2520	Libev comes with some simplistic wrapper classes for C++ that mainly allow
1852	you to use some convinience methods to start/stop watchers and also change	2521	you to use some convenience methods to start/stop watchers and also change
1853	the callback model to a model using method callbacks on objects.	2522	the callback model to a model using method callbacks on objects.
1854		2523
1855	To use it,	2524	To use it,
1856		2525
1857	#include <ev++.h>	2526	#include <ev++.h>
1858		2527
1859	This automatically includes F<ev.h> and puts all of its definitions (many	2528	This automatically includes F<ev.h> and puts all of its definitions (many
1860	of them macros) into the global namespace. All C++ specific things are	2529	of them macros) into the global namespace. All C++ specific things are
1861	put into the C<ev> namespace. It should support all the same embedding	2530	put into the C<ev> namespace. It should support all the same embedding
1862	options as F<ev.h>, most notably C<EV_MULTIPLICITY>.	2531	options as F<ev.h>, most notably C<EV_MULTIPLICITY>.
…		…
1929	your compiler is good :), then the method will be fully inlined into the	2598	your compiler is good :), then the method will be fully inlined into the
1930	thunking function, making it as fast as a direct C callback.	2599	thunking function, making it as fast as a direct C callback.
1931		2600
1932	Example: simple class declaration and watcher initialisation	2601	Example: simple class declaration and watcher initialisation
1933		2602
1934	struct myclass	2603	struct myclass
1935	{	2604	{
1936	void io_cb (ev::io &w, int revents) { }	2605	void io_cb (ev::io &w, int revents) { }
1937	}	2606	}
1938		2607
1939	myclass obj;	2608	myclass obj;
1940	ev::io iow;	2609	ev::io iow;
1941	iow.set <myclass, &myclass::io_cb> (&obj);	2610	iow.set <myclass, &myclass::io_cb> (&obj);
1942		2611
1943	=item w->set<function> (void *data = 0)	2612	=item w->set<function> (void *data = 0)
1944		2613
1945	Also sets a callback, but uses a static method or plain function as	2614	Also sets a callback, but uses a static method or plain function as
1946	callback. The optional C<data> argument will be stored in the watcher's	2615	callback. The optional C<data> argument will be stored in the watcher's
…		…
1950		2619
1951	See the method-C<set> above for more details.	2620	See the method-C<set> above for more details.
1952		2621
1953	Example:	2622	Example:
1954		2623
1955	static void io_cb (ev::io &w, int revents) { }	2624	static void io_cb (ev::io &w, int revents) { }
1956	iow.set <io_cb> ();	2625	iow.set <io_cb> ();
1957		2626
1958	=item w->set (struct ev_loop *)	2627	=item w->set (struct ev_loop *)
1959		2628
1960	Associates a different C<struct ev_loop> with this watcher. You can only	2629	Associates a different C<struct ev_loop> with this watcher. You can only
1961	do this when the watcher is inactive (and not pending either).	2630	do this when the watcher is inactive (and not pending either).
1962		2631
1963	=item w->set ([args])	2632	=item w->set ([arguments])
1964		2633
1965	Basically the same as C<ev_TYPE_set>, with the same args. Must be	2634	Basically the same as C<ev_TYPE_set>, with the same arguments. Must be
1966	called at least once. Unlike the C counterpart, an active watcher gets	2635	called at least once. Unlike the C counterpart, an active watcher gets
1967	automatically stopped and restarted when reconfiguring it with this	2636	automatically stopped and restarted when reconfiguring it with this
1968	method.	2637	method.
1969		2638
1970	=item w->start ()	2639	=item w->start ()
…		…
1974		2643
1975	=item w->stop ()	2644	=item w->stop ()
1976		2645
1977	Stops the watcher if it is active. Again, no C<loop> argument.	2646	Stops the watcher if it is active. Again, no C<loop> argument.
1978		2647
1979	=item w->again () C<ev::timer>, C<ev::periodic> only	2648	=item w->again () (C<ev::timer>, C<ev::periodic> only)
1980		2649
1981	For C<ev::timer> and C<ev::periodic>, this invokes the corresponding	2650	For C<ev::timer> and C<ev::periodic>, this invokes the corresponding
1982	C<ev_TYPE_again> function.	2651	C<ev_TYPE_again> function.
1983		2652
1984	=item w->sweep () C<ev::embed> only	2653	=item w->sweep () (C<ev::embed> only)
1985		2654
1986	Invokes C<ev_embed_sweep>.	2655	Invokes C<ev_embed_sweep>.
1987		2656
1988	=item w->update () C<ev::stat> only	2657	=item w->update () (C<ev::stat> only)
1989		2658
1990	Invokes C<ev_stat_stat>.	2659	Invokes C<ev_stat_stat>.
1991		2660
1992	=back	2661	=back
1993		2662
1994	=back	2663	=back
1995		2664
1996	Example: Define a class with an IO and idle watcher, start one of them in	2665	Example: Define a class with an IO and idle watcher, start one of them in
1997	the constructor.	2666	the constructor.
1998		2667
1999	class myclass	2668	class myclass
2000	{	2669	{
2001	ev_io io; void io_cb (ev::io &w, int revents);	2670	ev::io io; void io_cb (ev::io &w, int revents);
2002	ev_idle idle void idle_cb (ev::idle &w, int revents);	2671	ev:idle idle void idle_cb (ev::idle &w, int revents);
2003		2672
2004	myclass ();	2673	myclass (int fd)
2005	}	2674	{
2006
2007	myclass::myclass (int fd)
2008	{
2009	io .set <myclass, &myclass::io_cb > (this);	2675	io .set <myclass, &myclass::io_cb > (this);
2010	idle.set <myclass, &myclass::idle_cb> (this);	2676	idle.set <myclass, &myclass::idle_cb> (this);
2011		2677
2012	io.start (fd, ev::READ);	2678	io.start (fd, ev::READ);
		2679	}
2013	}	2680	};
		2681
		2682
		2683	=head1 OTHER LANGUAGE BINDINGS
		2684
		2685	Libev does not offer other language bindings itself, but bindings for a
		2686	number of languages exist in the form of third-party packages. If you know
		2687	any interesting language binding in addition to the ones listed here, drop
		2688	me a note.
		2689
		2690	=over 4
		2691
		2692	=item Perl
		2693
		2694	The EV module implements the full libev API and is actually used to test
		2695	libev. EV is developed together with libev. Apart from the EV core module,
		2696	there are additional modules that implement libev-compatible interfaces
		2697	to C<libadns> (C<EV::ADNS>), C<Net::SNMP> (C<Net::SNMP::EV>) and the
		2698	C<libglib> event core (C<Glib::EV> and C<EV::Glib>).
		2699
		2700	It can be found and installed via CPAN, its homepage is at
		2701	L<http://software.schmorp.de/pkg/EV>.
		2702
		2703	=item Python
		2704
		2705	Python bindings can be found at L<http://code.google.com/p/pyev/>. It
		2706	seems to be quite complete and well-documented. Note, however, that the
		2707	patch they require for libev is outright dangerous as it breaks the ABI
		2708	for everybody else, and therefore, should never be applied in an installed
		2709	libev (if python requires an incompatible ABI then it needs to embed
		2710	libev).
		2711
		2712	=item Ruby
		2713
		2714	Tony Arcieri has written a ruby extension that offers access to a subset
		2715	of the libev API and adds file handle abstractions, asynchronous DNS and
		2716	more on top of it. It can be found via gem servers. Its homepage is at
		2717	L<http://rev.rubyforge.org/>.
		2718
		2719	=item D
		2720
		2721	Leandro Lucarella has written a D language binding (F<ev.d>) for libev, to
		2722	be found at L<http://proj.llucax.com.ar/wiki/evd>.
		2723
		2724	=back
2014		2725
2015		2726
2016	=head1 MACRO MAGIC	2727	=head1 MACRO MAGIC
2017		2728
2018	Libev can be compiled with a variety of options, the most fundemantal is	2729	Libev can be compiled with a variety of options, the most fundamental
2019	C<EV_MULTIPLICITY>. This option determines whether (most) functions and	2730	of which is C<EV_MULTIPLICITY>. This option determines whether (most)
2020	callbacks have an initial C<struct ev_loop *> argument.	2731	functions and callbacks have an initial C<struct ev_loop *> argument.
2021		2732
2022	To make it easier to write programs that cope with either variant, the	2733	To make it easier to write programs that cope with either variant, the
2023	following macros are defined:	2734	following macros are defined:
2024		2735
2025	=over 4	2736	=over 4
…		…
2028		2739
2029	This provides the loop I<argument> for functions, if one is required ("ev	2740	This provides the loop I<argument> for functions, if one is required ("ev
2030	loop argument"). The C<EV_A> form is used when this is the sole argument,	2741	loop argument"). The C<EV_A> form is used when this is the sole argument,
2031	C<EV_A_> is used when other arguments are following. Example:	2742	C<EV_A_> is used when other arguments are following. Example:
2032		2743
2033	ev_unref (EV_A);	2744	ev_unref (EV_A);
2034	ev_timer_add (EV_A_ watcher);	2745	ev_timer_add (EV_A_ watcher);
2035	ev_loop (EV_A_ 0);	2746	ev_loop (EV_A_ 0);
2036		2747
2037	It assumes the variable C<loop> of type C<struct ev_loop *> is in scope,	2748	It assumes the variable C<loop> of type C<struct ev_loop *> is in scope,
2038	which is often provided by the following macro.	2749	which is often provided by the following macro.
2039		2750
2040	=item C<EV_P>, C<EV_P_>	2751	=item C<EV_P>, C<EV_P_>
2041		2752
2042	This provides the loop I<parameter> for functions, if one is required ("ev	2753	This provides the loop I<parameter> for functions, if one is required ("ev
2043	loop parameter"). The C<EV_P> form is used when this is the sole parameter,	2754	loop parameter"). The C<EV_P> form is used when this is the sole parameter,
2044	C<EV_P_> is used when other parameters are following. Example:	2755	C<EV_P_> is used when other parameters are following. Example:
2045		2756
2046	// this is how ev_unref is being declared	2757	// this is how ev_unref is being declared
2047	static void ev_unref (EV_P);	2758	static void ev_unref (EV_P);
2048		2759
2049	// this is how you can declare your typical callback	2760	// this is how you can declare your typical callback
2050	static void cb (EV_P_ ev_timer *w, int revents)	2761	static void cb (EV_P_ ev_timer *w, int revents)
2051		2762
2052	It declares a parameter C<loop> of type C<struct ev_loop *>, quite	2763	It declares a parameter C<loop> of type C<struct ev_loop *>, quite
2053	suitable for use with C<EV_A>.	2764	suitable for use with C<EV_A>.
2054		2765
2055	=item C<EV_DEFAULT>, C<EV_DEFAULT_>	2766	=item C<EV_DEFAULT>, C<EV_DEFAULT_>
2056		2767
2057	Similar to the other two macros, this gives you the value of the default	2768	Similar to the other two macros, this gives you the value of the default
2058	loop, if multiple loops are supported ("ev loop default").	2769	loop, if multiple loops are supported ("ev loop default").
		2770
		2771	=item C<EV_DEFAULT_UC>, C<EV_DEFAULT_UC_>
		2772
		2773	Usage identical to C<EV_DEFAULT> and C<EV_DEFAULT_>, but requires that the
		2774	default loop has been initialised (C<UC> == unchecked). Their behaviour
		2775	is undefined when the default loop has not been initialised by a previous
		2776	execution of C<EV_DEFAULT>, C<EV_DEFAULT_> or C<ev_default_init (...)>.
		2777
		2778	It is often prudent to use C<EV_DEFAULT> when initialising the first
		2779	watcher in a function but use C<EV_DEFAULT_UC> afterwards.
2059		2780
2060	=back	2781	=back
2061		2782
2062	Example: Declare and initialise a check watcher, utilising the above	2783	Example: Declare and initialise a check watcher, utilising the above
2063	macros so it will work regardless of whether multiple loops are supported	2784	macros so it will work regardless of whether multiple loops are supported
2064	or not.	2785	or not.
2065		2786
2066	static void	2787	static void
2067	check_cb (EV_P_ ev_timer *w, int revents)	2788	check_cb (EV_P_ ev_timer *w, int revents)
2068	{	2789	{
2069	ev_check_stop (EV_A_ w);	2790	ev_check_stop (EV_A_ w);
2070	}	2791	}
2071		2792
2072	ev_check check;	2793	ev_check check;
2073	ev_check_init (&check, check_cb);	2794	ev_check_init (&check, check_cb);
2074	ev_check_start (EV_DEFAULT_ &check);	2795	ev_check_start (EV_DEFAULT_ &check);
2075	ev_loop (EV_DEFAULT_ 0);	2796	ev_loop (EV_DEFAULT_ 0);
2076		2797
2077	=head1 EMBEDDING	2798	=head1 EMBEDDING
2078		2799
2079	Libev can (and often is) directly embedded into host	2800	Libev can (and often is) directly embedded into host
2080	applications. Examples of applications that embed it include the Deliantra	2801	applications. Examples of applications that embed it include the Deliantra
2081	Game Server, the EV perl module, the GNU Virtual Private Ethernet (gvpe)	2802	Game Server, the EV perl module, the GNU Virtual Private Ethernet (gvpe)
2082	and rxvt-unicode.	2803	and rxvt-unicode.
2083		2804
2084	The goal is to enable you to just copy the neecssary files into your	2805	The goal is to enable you to just copy the necessary files into your
2085	source directory without having to change even a single line in them, so	2806	source directory without having to change even a single line in them, so
2086	you can easily upgrade by simply copying (or having a checked-out copy of	2807	you can easily upgrade by simply copying (or having a checked-out copy of
2087	libev somewhere in your source tree).	2808	libev somewhere in your source tree).
2088		2809
2089	=head2 FILESETS	2810	=head2 FILESETS
2090		2811
2091	Depending on what features you need you need to include one or more sets of files	2812	Depending on what features you need you need to include one or more sets of files
2092	in your app.	2813	in your application.
2093		2814
2094	=head3 CORE EVENT LOOP	2815	=head3 CORE EVENT LOOP
2095		2816
2096	To include only the libev core (all the C<ev_*> functions), with manual	2817	To include only the libev core (all the C<ev_*> functions), with manual
2097	configuration (no autoconf):	2818	configuration (no autoconf):
2098		2819
2099	#define EV_STANDALONE 1	2820	#define EV_STANDALONE 1
2100	#include "ev.c"	2821	#include "ev.c"
2101		2822
2102	This will automatically include F<ev.h>, too, and should be done in a	2823	This will automatically include F<ev.h>, too, and should be done in a
2103	single C source file only to provide the function implementations. To use	2824	single C source file only to provide the function implementations. To use
2104	it, do the same for F<ev.h> in all files wishing to use this API (best	2825	it, do the same for F<ev.h> in all files wishing to use this API (best
2105	done by writing a wrapper around F<ev.h> that you can include instead and	2826	done by writing a wrapper around F<ev.h> that you can include instead and
2106	where you can put other configuration options):	2827	where you can put other configuration options):
2107		2828
2108	#define EV_STANDALONE 1	2829	#define EV_STANDALONE 1
2109	#include "ev.h"	2830	#include "ev.h"
2110		2831
2111	Both header files and implementation files can be compiled with a C++	2832	Both header files and implementation files can be compiled with a C++
2112	compiler (at least, thats a stated goal, and breakage will be treated	2833	compiler (at least, thats a stated goal, and breakage will be treated
2113	as a bug).	2834	as a bug).
2114		2835
2115	You need the following files in your source tree, or in a directory	2836	You need the following files in your source tree, or in a directory
2116	in your include path (e.g. in libev/ when using -Ilibev):	2837	in your include path (e.g. in libev/ when using -Ilibev):
2117		2838
2118	ev.h	2839	ev.h
2119	ev.c	2840	ev.c
2120	ev_vars.h	2841	ev_vars.h
2121	ev_wrap.h	2842	ev_wrap.h
2122		2843
2123	ev_win32.c required on win32 platforms only	2844	ev_win32.c required on win32 platforms only
2124		2845
2125	ev_select.c only when select backend is enabled (which is enabled by default)	2846	ev_select.c only when select backend is enabled (which is enabled by default)
2126	ev_poll.c only when poll backend is enabled (disabled by default)	2847	ev_poll.c only when poll backend is enabled (disabled by default)
2127	ev_epoll.c only when the epoll backend is enabled (disabled by default)	2848	ev_epoll.c only when the epoll backend is enabled (disabled by default)
2128	ev_kqueue.c only when the kqueue backend is enabled (disabled by default)	2849	ev_kqueue.c only when the kqueue backend is enabled (disabled by default)
2129	ev_port.c only when the solaris port backend is enabled (disabled by default)	2850	ev_port.c only when the solaris port backend is enabled (disabled by default)
2130		2851
2131	F<ev.c> includes the backend files directly when enabled, so you only need	2852	F<ev.c> includes the backend files directly when enabled, so you only need
2132	to compile this single file.	2853	to compile this single file.
2133		2854
2134	=head3 LIBEVENT COMPATIBILITY API	2855	=head3 LIBEVENT COMPATIBILITY API
2135		2856
2136	To include the libevent compatibility API, also include:	2857	To include the libevent compatibility API, also include:
2137		2858
2138	#include "event.c"	2859	#include "event.c"
2139		2860
2140	in the file including F<ev.c>, and:	2861	in the file including F<ev.c>, and:
2141		2862
2142	#include "event.h"	2863	#include "event.h"
2143		2864
2144	in the files that want to use the libevent API. This also includes F<ev.h>.	2865	in the files that want to use the libevent API. This also includes F<ev.h>.
2145		2866
2146	You need the following additional files for this:	2867	You need the following additional files for this:
2147		2868
2148	event.h	2869	event.h
2149	event.c	2870	event.c
2150		2871
2151	=head3 AUTOCONF SUPPORT	2872	=head3 AUTOCONF SUPPORT
2152		2873
2153	Instead of using C<EV_STANDALONE=1> and providing your config in	2874	Instead of using C<EV_STANDALONE=1> and providing your configuration in
2154	whatever way you want, you can also C<m4_include([libev.m4])> in your	2875	whatever way you want, you can also C<m4_include([libev.m4])> in your
2155	F<configure.ac> and leave C<EV_STANDALONE> undefined. F<ev.c> will then	2876	F<configure.ac> and leave C<EV_STANDALONE> undefined. F<ev.c> will then
2156	include F<config.h> and configure itself accordingly.	2877	include F<config.h> and configure itself accordingly.
2157		2878
2158	For this of course you need the m4 file:	2879	For this of course you need the m4 file:
2159		2880
2160	libev.m4	2881	libev.m4
2161		2882
2162	=head2 PREPROCESSOR SYMBOLS/MACROS	2883	=head2 PREPROCESSOR SYMBOLS/MACROS
2163		2884
2164	Libev can be configured via a variety of preprocessor symbols you have to define	2885	Libev can be configured via a variety of preprocessor symbols you have to
2165	before including any of its files. The default is not to build for multiplicity	2886	define before including any of its files. The default in the absence of
2166	and only include the select backend.	2887	autoconf is noted for every option.
2167		2888
2168	=over 4	2889	=over 4
2169		2890
2170	=item EV_STANDALONE	2891	=item EV_STANDALONE
2171		2892
…		…
2176	F<event.h> that are not directly supported by the libev core alone.	2897	F<event.h> that are not directly supported by the libev core alone.
2177		2898
2178	=item EV_USE_MONOTONIC	2899	=item EV_USE_MONOTONIC
2179		2900
2180	If defined to be C<1>, libev will try to detect the availability of the	2901	If defined to be C<1>, libev will try to detect the availability of the
2181	monotonic clock option at both compiletime and runtime. Otherwise no use	2902	monotonic clock option at both compile time and runtime. Otherwise no use
2182	of the monotonic clock option will be attempted. If you enable this, you	2903	of the monotonic clock option will be attempted. If you enable this, you
2183	usually have to link against librt or something similar. Enabling it when	2904	usually have to link against librt or something similar. Enabling it when
2184	the functionality isn't available is safe, though, althoguh you have	2905	the functionality isn't available is safe, though, although you have
2185	to make sure you link against any libraries where the C<clock_gettime>	2906	to make sure you link against any libraries where the C<clock_gettime>
2186	function is hiding in (often F<-lrt>).	2907	function is hiding in (often F<-lrt>).
2187		2908
2188	=item EV_USE_REALTIME	2909	=item EV_USE_REALTIME
2189		2910
2190	If defined to be C<1>, libev will try to detect the availability of the	2911	If defined to be C<1>, libev will try to detect the availability of the
2191	realtime clock option at compiletime (and assume its availability at	2912	real-time clock option at compile time (and assume its availability at
2192	runtime if successful). Otherwise no use of the realtime clock option will	2913	runtime if successful). Otherwise no use of the real-time clock option will
2193	be attempted. This effectively replaces C<gettimeofday> by C<clock_get	2914	be attempted. This effectively replaces C<gettimeofday> by C<clock_get
2194	(CLOCK_REALTIME, ...)> and will not normally affect correctness. See tzhe note about libraries	2915	(CLOCK_REALTIME, ...)> and will not normally affect correctness. See the
2195	in the description of C<EV_USE_MONOTONIC>, though.	2916	note about libraries in the description of C<EV_USE_MONOTONIC>, though.
		2917
		2918	=item EV_USE_NANOSLEEP
		2919
		2920	If defined to be C<1>, libev will assume that C<nanosleep ()> is available
		2921	and will use it for delays. Otherwise it will use C<select ()>.
		2922
		2923	=item EV_USE_EVENTFD
		2924
		2925	If defined to be C<1>, then libev will assume that C<eventfd ()> is
		2926	available and will probe for kernel support at runtime. This will improve
		2927	C<ev_signal> and C<ev_async> performance and reduce resource consumption.
		2928	If undefined, it will be enabled if the headers indicate GNU/Linux + Glibc
		2929	2.7 or newer, otherwise disabled.
2196		2930
2197	=item EV_USE_SELECT	2931	=item EV_USE_SELECT
2198		2932
2199	If undefined or defined to be C<1>, libev will compile in support for the	2933	If undefined or defined to be C<1>, libev will compile in support for the
2200	C<select>(2) backend. No attempt at autodetection will be done: if no	2934	C<select>(2) backend. No attempt at auto-detection will be done: if no
2201	other method takes over, select will be it. Otherwise the select backend	2935	other method takes over, select will be it. Otherwise the select backend
2202	will not be compiled in.	2936	will not be compiled in.
2203		2937
2204	=item EV_SELECT_USE_FD_SET	2938	=item EV_SELECT_USE_FD_SET
2205		2939
2206	If defined to C<1>, then the select backend will use the system C<fd_set>	2940	If defined to C<1>, then the select backend will use the system C<fd_set>
2207	structure. This is useful if libev doesn't compile due to a missing	2941	structure. This is useful if libev doesn't compile due to a missing
2208	C<NFDBITS> or C<fd_mask> definition or it misguesses the bitset layout on	2942	C<NFDBITS> or C<fd_mask> definition or it mis-guesses the bitset layout on
2209	exotic systems. This usually limits the range of file descriptors to some	2943	exotic systems. This usually limits the range of file descriptors to some
2210	low limit such as 1024 or might have other limitations (winsocket only	2944	low limit such as 1024 or might have other limitations (winsocket only
2211	allows 64 sockets). The C<FD_SETSIZE> macro, set before compilation, might	2945	allows 64 sockets). The C<FD_SETSIZE> macro, set before compilation, might
2212	influence the size of the C<fd_set> used.	2946	influence the size of the C<fd_set> used.
2213		2947
…		…
2219	be used is the winsock select). This means that it will call	2953	be used is the winsock select). This means that it will call
2220	C<_get_osfhandle> on the fd to convert it to an OS handle. Otherwise,	2954	C<_get_osfhandle> on the fd to convert it to an OS handle. Otherwise,
2221	it is assumed that all these functions actually work on fds, even	2955	it is assumed that all these functions actually work on fds, even
2222	on win32. Should not be defined on non-win32 platforms.	2956	on win32. Should not be defined on non-win32 platforms.
2223		2957
		2958	=item EV_FD_TO_WIN32_HANDLE
		2959
		2960	If C<EV_SELECT_IS_WINSOCKET> is enabled, then libev needs a way to map
		2961	file descriptors to socket handles. When not defining this symbol (the
		2962	default), then libev will call C<_get_osfhandle>, which is usually
		2963	correct. In some cases, programs use their own file descriptor management,
		2964	in which case they can provide this function to map fds to socket handles.
		2965
2224	=item EV_USE_POLL	2966	=item EV_USE_POLL
2225		2967
2226	If defined to be C<1>, libev will compile in support for the C<poll>(2)	2968	If defined to be C<1>, libev will compile in support for the C<poll>(2)
2227	backend. Otherwise it will be enabled on non-win32 platforms. It	2969	backend. Otherwise it will be enabled on non-win32 platforms. It
2228	takes precedence over select.	2970	takes precedence over select.
2229		2971
2230	=item EV_USE_EPOLL	2972	=item EV_USE_EPOLL
2231		2973
2232	If defined to be C<1>, libev will compile in support for the Linux	2974	If defined to be C<1>, libev will compile in support for the Linux
2233	C<epoll>(7) backend. Its availability will be detected at runtime,	2975	C<epoll>(7) backend. Its availability will be detected at runtime,
2234	otherwise another method will be used as fallback. This is the	2976	otherwise another method will be used as fallback. This is the preferred
2235	preferred backend for GNU/Linux systems.	2977	backend for GNU/Linux systems. If undefined, it will be enabled if the
		2978	headers indicate GNU/Linux + Glibc 2.4 or newer, otherwise disabled.
2236		2979
2237	=item EV_USE_KQUEUE	2980	=item EV_USE_KQUEUE
2238		2981
2239	If defined to be C<1>, libev will compile in support for the BSD style	2982	If defined to be C<1>, libev will compile in support for the BSD style
2240	C<kqueue>(2) backend. Its actual availability will be detected at runtime,	2983	C<kqueue>(2) backend. Its actual availability will be detected at runtime,
…		…
2253	otherwise another method will be used as fallback. This is the preferred	2996	otherwise another method will be used as fallback. This is the preferred
2254	backend for Solaris 10 systems.	2997	backend for Solaris 10 systems.
2255		2998
2256	=item EV_USE_DEVPOLL	2999	=item EV_USE_DEVPOLL
2257		3000
2258	reserved for future expansion, works like the USE symbols above.	3001	Reserved for future expansion, works like the USE symbols above.
2259		3002
2260	=item EV_USE_INOTIFY	3003	=item EV_USE_INOTIFY
2261		3004
2262	If defined to be C<1>, libev will compile in support for the Linux inotify	3005	If defined to be C<1>, libev will compile in support for the Linux inotify
2263	interface to speed up C<ev_stat> watchers. Its actual availability will	3006	interface to speed up C<ev_stat> watchers. Its actual availability will
2264	be detected at runtime.	3007	be detected at runtime. If undefined, it will be enabled if the headers
		3008	indicate GNU/Linux + Glibc 2.4 or newer, otherwise disabled.
		3009
		3010	=item EV_ATOMIC_T
		3011
		3012	Libev requires an integer type (suitable for storing C<0> or C<1>) whose
		3013	access is atomic with respect to other threads or signal contexts. No such
		3014	type is easily found in the C language, so you can provide your own type
		3015	that you know is safe for your purposes. It is used both for signal handler "locking"
		3016	as well as for signal and thread safety in C<ev_async> watchers.
		3017
		3018	In the absence of this define, libev will use C<sig_atomic_t volatile>
		3019	(from F<signal.h>), which is usually good enough on most platforms.
2265		3020
2266	=item EV_H	3021	=item EV_H
2267		3022
2268	The name of the F<ev.h> header file used to include it. The default if	3023	The name of the F<ev.h> header file used to include it. The default if
2269	undefined is C<< <ev.h> >> in F<event.h> and C<"ev.h"> in F<ev.c>. This	3024	undefined is C<"ev.h"> in F<event.h>, F<ev.c> and F<ev++.h>. This can be
2270	can be used to virtually rename the F<ev.h> header file in case of conflicts.	3025	used to virtually rename the F<ev.h> header file in case of conflicts.
2271		3026
2272	=item EV_CONFIG_H	3027	=item EV_CONFIG_H
2273		3028
2274	If C<EV_STANDALONE> isn't C<1>, this variable can be used to override	3029	If C<EV_STANDALONE> isn't C<1>, this variable can be used to override
2275	F<ev.c>'s idea of where to find the F<config.h> file, similarly to	3030	F<ev.c>'s idea of where to find the F<config.h> file, similarly to
2276	C<EV_H>, above.	3031	C<EV_H>, above.
2277		3032
2278	=item EV_EVENT_H	3033	=item EV_EVENT_H
2279		3034
2280	Similarly to C<EV_H>, this macro can be used to override F<event.c>'s idea	3035	Similarly to C<EV_H>, this macro can be used to override F<event.c>'s idea
2281	of how the F<event.h> header can be found.	3036	of how the F<event.h> header can be found, the default is C<"event.h">.
2282		3037
2283	=item EV_PROTOTYPES	3038	=item EV_PROTOTYPES
2284		3039
2285	If defined to be C<0>, then F<ev.h> will not define any function	3040	If defined to be C<0>, then F<ev.h> will not define any function
2286	prototypes, but still define all the structs and other symbols. This is	3041	prototypes, but still define all the structs and other symbols. This is
…		…
2307	When doing priority-based operations, libev usually has to linearly search	3062	When doing priority-based operations, libev usually has to linearly search
2308	all the priorities, so having many of them (hundreds) uses a lot of space	3063	all the priorities, so having many of them (hundreds) uses a lot of space
2309	and time, so using the defaults of five priorities (-2 .. +2) is usually	3064	and time, so using the defaults of five priorities (-2 .. +2) is usually
2310	fine.	3065	fine.
2311		3066
2312	If your embedding app does not need any priorities, defining these both to	3067	If your embedding application does not need any priorities, defining these both to
2313	C<0> will save some memory and cpu.	3068	C<0> will save some memory and CPU.
2314		3069
2315	=item EV_PERIODIC_ENABLE	3070	=item EV_PERIODIC_ENABLE
2316		3071
2317	If undefined or defined to be C<1>, then periodic timers are supported. If	3072	If undefined or defined to be C<1>, then periodic timers are supported. If
2318	defined to be C<0>, then they are not. Disabling them saves a few kB of	3073	defined to be C<0>, then they are not. Disabling them saves a few kB of
…		…
2337	=item EV_FORK_ENABLE	3092	=item EV_FORK_ENABLE
2338		3093
2339	If undefined or defined to be C<1>, then fork watchers are supported. If	3094	If undefined or defined to be C<1>, then fork watchers are supported. If
2340	defined to be C<0>, then they are not.	3095	defined to be C<0>, then they are not.
2341		3096
		3097	=item EV_ASYNC_ENABLE
		3098
		3099	If undefined or defined to be C<1>, then async watchers are supported. If
		3100	defined to be C<0>, then they are not.
		3101
2342	=item EV_MINIMAL	3102	=item EV_MINIMAL
2343		3103
2344	If you need to shave off some kilobytes of code at the expense of some	3104	If you need to shave off some kilobytes of code at the expense of some
2345	speed, define this symbol to C<1>. Currently only used for gcc to override	3105	speed, define this symbol to C<1>. Currently this is used to override some
2346	some inlining decisions, saves roughly 30% codesize of amd64.	3106	inlining decisions, saves roughly 30% code size on amd64. It also selects a
		3107	much smaller 2-heap for timer management over the default 4-heap.
2347		3108
2348	=item EV_PID_HASHSIZE	3109	=item EV_PID_HASHSIZE
2349		3110
2350	C<ev_child> watchers use a small hash table to distribute workload by	3111	C<ev_child> watchers use a small hash table to distribute workload by
2351	pid. The default size is C<16> (or C<1> with C<EV_MINIMAL>), usually more	3112	pid. The default size is C<16> (or C<1> with C<EV_MINIMAL>), usually more
2352	than enough. If you need to manage thousands of children you might want to	3113	than enough. If you need to manage thousands of children you might want to
2353	increase this value (I<must> be a power of two).	3114	increase this value (I<must> be a power of two).
2354		3115
2355	=item EV_INOTIFY_HASHSIZE	3116	=item EV_INOTIFY_HASHSIZE
2356		3117
2357	C<ev_staz> watchers use a small hash table to distribute workload by	3118	C<ev_stat> watchers use a small hash table to distribute workload by
2358	inotify watch id. The default size is C<16> (or C<1> with C<EV_MINIMAL>),	3119	inotify watch id. The default size is C<16> (or C<1> with C<EV_MINIMAL>),
2359	usually more than enough. If you need to manage thousands of C<ev_stat>	3120	usually more than enough. If you need to manage thousands of C<ev_stat>
2360	watchers you might want to increase this value (I<must> be a power of	3121	watchers you might want to increase this value (I<must> be a power of
2361	two).	3122	two).
2362		3123
		3124	=item EV_USE_4HEAP
		3125
		3126	Heaps are not very cache-efficient. To improve the cache-efficiency of the
		3127	timer and periodics heap, libev uses a 4-heap when this symbol is defined
		3128	to C<1>. The 4-heap uses more complicated (longer) code but has
		3129	noticeably faster performance with many (thousands) of watchers.
		3130
		3131	The default is C<1> unless C<EV_MINIMAL> is set in which case it is C<0>
		3132	(disabled).
		3133
		3134	=item EV_HEAP_CACHE_AT
		3135
		3136	Heaps are not very cache-efficient. To improve the cache-efficiency of the
		3137	timer and periodics heap, libev can cache the timestamp (I<at>) within
		3138	the heap structure (selected by defining C<EV_HEAP_CACHE_AT> to C<1>),
		3139	which uses 8-12 bytes more per watcher and a few hundred bytes more code,
		3140	but avoids random read accesses on heap changes. This improves performance
		3141	noticeably with with many (hundreds) of watchers.
		3142
		3143	The default is C<1> unless C<EV_MINIMAL> is set in which case it is C<0>
		3144	(disabled).
		3145
		3146	=item EV_VERIFY
		3147
		3148	Controls how much internal verification (see C<ev_loop_verify ()>) will
		3149	be done: If set to C<0>, no internal verification code will be compiled
		3150	in. If set to C<1>, then verification code will be compiled in, but not
		3151	called. If set to C<2>, then the internal verification code will be
		3152	called once per loop, which can slow down libev. If set to C<3>, then the
		3153	verification code will be called very frequently, which will slow down
		3154	libev considerably.
		3155
		3156	The default is C<1>, unless C<EV_MINIMAL> is set, in which case it will be
		3157	C<0.>
		3158
2363	=item EV_COMMON	3159	=item EV_COMMON
2364		3160
2365	By default, all watchers have a C<void *data> member. By redefining	3161	By default, all watchers have a C<void *data> member. By redefining
2366	this macro to a something else you can include more and other types of	3162	this macro to a something else you can include more and other types of
2367	members. You have to define it each time you include one of the files,	3163	members. You have to define it each time you include one of the files,
2368	though, and it must be identical each time.	3164	though, and it must be identical each time.
2369		3165
2370	For example, the perl EV module uses something like this:	3166	For example, the perl EV module uses something like this:
2371		3167
2372	#define EV_COMMON \	3168	#define EV_COMMON \
2373	SV *self; /* contains this struct */ \	3169	SV *self; /* contains this struct */ \
2374	SV *cb_sv, *fh /* note no trailing ";" */	3170	SV *cb_sv, *fh /* note no trailing ";" */
2375		3171
2376	=item EV_CB_DECLARE (type)	3172	=item EV_CB_DECLARE (type)
2377		3173
2378	=item EV_CB_INVOKE (watcher, revents)	3174	=item EV_CB_INVOKE (watcher, revents)
2379		3175
2380	=item ev_set_cb (ev, cb)	3176	=item ev_set_cb (ev, cb)
2381		3177
2382	Can be used to change the callback member declaration in each watcher,	3178	Can be used to change the callback member declaration in each watcher,
2383	and the way callbacks are invoked and set. Must expand to a struct member	3179	and the way callbacks are invoked and set. Must expand to a struct member
2384	definition and a statement, respectively. See the F<ev.v> header file for	3180	definition and a statement, respectively. See the F<ev.h> header file for
2385	their default definitions. One possible use for overriding these is to	3181	their default definitions. One possible use for overriding these is to
2386	avoid the C<struct ev_loop *> as first argument in all cases, or to use	3182	avoid the C<struct ev_loop *> as first argument in all cases, or to use
2387	method calls instead of plain function calls in C++.	3183	method calls instead of plain function calls in C++.
		3184
		3185	=head2 EXPORTED API SYMBOLS
		3186
		3187	If you need to re-export the API (e.g. via a DLL) and you need a list of
		3188	exported symbols, you can use the provided F<Symbol.*> files which list
		3189	all public symbols, one per line:
		3190
		3191	Symbols.ev for libev proper
		3192	Symbols.event for the libevent emulation
		3193
		3194	This can also be used to rename all public symbols to avoid clashes with
		3195	multiple versions of libev linked together (which is obviously bad in
		3196	itself, but sometimes it is inconvenient to avoid this).
		3197
		3198	A sed command like this will create wrapper C<#define>'s that you need to
		3199	include before including F<ev.h>:
		3200
		3201	<Symbols.ev sed -e "s/.*/#define & myprefix_&/" >wrap.h
		3202
		3203	This would create a file F<wrap.h> which essentially looks like this:
		3204
		3205	#define ev_backend myprefix_ev_backend
		3206	#define ev_check_start myprefix_ev_check_start
		3207	#define ev_check_stop myprefix_ev_check_stop
		3208	...
2388		3209
2389	=head2 EXAMPLES	3210	=head2 EXAMPLES
2390		3211
2391	For a real-world example of a program the includes libev	3212	For a real-world example of a program the includes libev
2392	verbatim, you can have a look at the EV perl module	3213	verbatim, you can have a look at the EV perl module
…		…
2397	file.	3218	file.
2398		3219
2399	The usage in rxvt-unicode is simpler. It has a F<ev_cpp.h> header file	3220	The usage in rxvt-unicode is simpler. It has a F<ev_cpp.h> header file
2400	that everybody includes and which overrides some configure choices:	3221	that everybody includes and which overrides some configure choices:
2401		3222
2402	#define EV_MINIMAL 1	3223	#define EV_MINIMAL 1
2403	#define EV_USE_POLL 0	3224	#define EV_USE_POLL 0
2404	#define EV_MULTIPLICITY 0	3225	#define EV_MULTIPLICITY 0
2405	#define EV_PERIODIC_ENABLE 0	3226	#define EV_PERIODIC_ENABLE 0
2406	#define EV_STAT_ENABLE 0	3227	#define EV_STAT_ENABLE 0
2407	#define EV_FORK_ENABLE 0	3228	#define EV_FORK_ENABLE 0
2408	#define EV_CONFIG_H <config.h>	3229	#define EV_CONFIG_H <config.h>
2409	#define EV_MINPRI 0	3230	#define EV_MINPRI 0
2410	#define EV_MAXPRI 0	3231	#define EV_MAXPRI 0
2411		3232
2412	#include "ev++.h"	3233	#include "ev++.h"
2413		3234
2414	And a F<ev_cpp.C> implementation file that contains libev proper and is compiled:	3235	And a F<ev_cpp.C> implementation file that contains libev proper and is compiled:
2415		3236
2416	#include "ev_cpp.h"	3237	#include "ev_cpp.h"
2417	#include "ev.c"	3238	#include "ev.c"
		3239
		3240
		3241	=head1 THREADS AND COROUTINES
		3242
		3243	=head2 THREADS
		3244
		3245	Libev itself is completely thread-safe, but it uses no locking. This
		3246	means that you can use as many loops as you want in parallel, as long as
		3247	only one thread ever calls into one libev function with the same loop
		3248	parameter.
		3249
		3250	Or put differently: calls with different loop parameters can be done in
		3251	parallel from multiple threads, calls with the same loop parameter must be
		3252	done serially (but can be done from different threads, as long as only one
		3253	thread ever is inside a call at any point in time, e.g. by using a mutex
		3254	per loop).
		3255
		3256	If you want to know which design (one loop, locking, or multiple loops
		3257	without or something else still) is best for your problem, then I cannot
		3258	help you. I can give some generic advice however:
		3259
		3260	=over 4
		3261
		3262	=item * most applications have a main thread: use the default libev loop
		3263	in that thread, or create a separate thread running only the default loop.
		3264
		3265	This helps integrating other libraries or software modules that use libev
		3266	themselves and don't care/know about threading.
		3267
		3268	=item * one loop per thread is usually a good model.
		3269
		3270	Doing this is almost never wrong, sometimes a better-performance model
		3271	exists, but it is always a good start.
		3272
		3273	=item * other models exist, such as the leader/follower pattern, where one
		3274	loop is handed through multiple threads in a kind of round-robin fashion.
		3275
		3276	Choosing a model is hard - look around, learn, know that usually you can do
		3277	better than you currently do :-)
		3278
		3279	=item * often you need to talk to some other thread which blocks in the
		3280	event loop - C<ev_async> watchers can be used to wake them up from other
		3281	threads safely (or from signal contexts...).
		3282
		3283	=back
		3284
		3285	=head2 COROUTINES
		3286
		3287	Libev is much more accommodating to coroutines ("cooperative threads"):
		3288	libev fully supports nesting calls to it's functions from different
		3289	coroutines (e.g. you can call C<ev_loop> on the same loop from two
		3290	different coroutines and switch freely between both coroutines running the
		3291	loop, as long as you don't confuse yourself). The only exception is that
		3292	you must not do this from C<ev_periodic> reschedule callbacks.
		3293
		3294	Care has been invested into making sure that libev does not keep local
		3295	state inside C<ev_loop>, and other calls do not usually allow coroutine
		3296	switches.
2418		3297
2419		3298
2420	=head1 COMPLEXITIES	3299	=head1 COMPLEXITIES
2421		3300
2422	In this section the complexities of (many of) the algorithms used inside	3301	In this section the complexities of (many of) the algorithms used inside
…		…
2433		3312
2434	=item Starting and stopping timer/periodic watchers: O(log skipped_other_timers)	3313	=item Starting and stopping timer/periodic watchers: O(log skipped_other_timers)
2435		3314
2436	This means that, when you have a watcher that triggers in one hour and	3315	This means that, when you have a watcher that triggers in one hour and
2437	there are 100 watchers that would trigger before that then inserting will	3316	there are 100 watchers that would trigger before that then inserting will
2438	have to skip those 100 watchers.	3317	have to skip roughly seven (C<ld 100>) of these watchers.
2439		3318
2440	=item Changing timer/periodic watchers (by autorepeat, again): O(log skipped_other_timers)	3319	=item Changing timer/periodic watchers (by autorepeat or calling again): O(log skipped_other_timers)
2441		3320
2442	That means that for changing a timer costs less than removing/adding them	3321	That means that changing a timer costs less than removing/adding them
2443	as only the relative motion in the event queue has to be paid for.	3322	as only the relative motion in the event queue has to be paid for.
2444		3323
2445	=item Starting io/check/prepare/idle/signal/child watchers: O(1)	3324	=item Starting io/check/prepare/idle/signal/child/fork/async watchers: O(1)
2446		3325
2447	These just add the watcher into an array or at the head of a list.	3326	These just add the watcher into an array or at the head of a list.
		3327
2448	=item Stopping check/prepare/idle watchers: O(1)	3328	=item Stopping check/prepare/idle/fork/async watchers: O(1)
2449		3329
2450	=item Stopping an io/signal/child watcher: O(number_of_watchers_for_this_(fd/signal/pid % EV_PID_HASHSIZE))	3330	=item Stopping an io/signal/child watcher: O(number_of_watchers_for_this_(fd/signal/pid % EV_PID_HASHSIZE))
2451		3331
2452	These watchers are stored in lists then need to be walked to find the	3332	These watchers are stored in lists then need to be walked to find the
2453	correct watcher to remove. The lists are usually short (you don't usually	3333	correct watcher to remove. The lists are usually short (you don't usually
2454	have many watchers waiting for the same fd or signal).	3334	have many watchers waiting for the same fd or signal).
2455		3335
2456	=item Finding the next timer per loop iteration: O(1)	3336	=item Finding the next timer in each loop iteration: O(1)
		3337
		3338	By virtue of using a binary or 4-heap, the next timer is always found at a
		3339	fixed position in the storage array.
2457		3340
2458	=item Each change on a file descriptor per loop iteration: O(number_of_watchers_for_this_fd)	3341	=item Each change on a file descriptor per loop iteration: O(number_of_watchers_for_this_fd)
2459		3342
2460	A change means an I/O watcher gets started or stopped, which requires	3343	A change means an I/O watcher gets started or stopped, which requires
2461	libev to recalculate its status (and possibly tell the kernel).	3344	libev to recalculate its status (and possibly tell the kernel, depending
		3345	on backend and whether C<ev_io_set> was used).
2462		3346
2463	=item Activating one watcher: O(1)	3347	=item Activating one watcher (putting it into the pending state): O(1)
2464		3348
2465	=item Priority handling: O(number_of_priorities)	3349	=item Priority handling: O(number_of_priorities)
2466		3350
2467	Priorities are implemented by allocating some space for each	3351	Priorities are implemented by allocating some space for each
2468	priority. When doing priority-based operations, libev usually has to	3352	priority. When doing priority-based operations, libev usually has to
2469	linearly search all the priorities.	3353	linearly search all the priorities, but starting/stopping and activating
		3354	watchers becomes O(1) w.r.t. priority handling.
		3355
		3356	=item Sending an ev_async: O(1)
		3357
		3358	=item Processing ev_async_send: O(number_of_async_watchers)
		3359
		3360	=item Processing signals: O(max_signal_number)
		3361
		3362	Sending involves a system call I<iff> there were no other C<ev_async_send>
		3363	calls in the current loop iteration. Checking for async and signal events
		3364	involves iterating over all running async watchers or all signal numbers.
2470		3365
2471	=back	3366	=back
2472		3367
2473		3368
		3369	=head1 WIN32 PLATFORM LIMITATIONS AND WORKAROUNDS
		3370
		3371	Win32 doesn't support any of the standards (e.g. POSIX) that libev
		3372	requires, and its I/O model is fundamentally incompatible with the POSIX
		3373	model. Libev still offers limited functionality on this platform in
		3374	the form of the C<EVBACKEND_SELECT> backend, and only supports socket
		3375	descriptors. This only applies when using Win32 natively, not when using
		3376	e.g. cygwin.
		3377
		3378	Lifting these limitations would basically require the full
		3379	re-implementation of the I/O system. If you are into these kinds of
		3380	things, then note that glib does exactly that for you in a very portable
		3381	way (note also that glib is the slowest event library known to man).
		3382
		3383	There is no supported compilation method available on windows except
		3384	embedding it into other applications.
		3385
		3386	Not a libev limitation but worth mentioning: windows apparently doesn't
		3387	accept large writes: instead of resulting in a partial write, windows will
		3388	either accept everything or return C<ENOBUFS> if the buffer is too large,
		3389	so make sure you only write small amounts into your sockets (less than a
		3390	megabyte seems safe, but thsi apparently depends on the amount of memory
		3391	available).
		3392
		3393	Due to the many, low, and arbitrary limits on the win32 platform and
		3394	the abysmal performance of winsockets, using a large number of sockets
		3395	is not recommended (and not reasonable). If your program needs to use
		3396	more than a hundred or so sockets, then likely it needs to use a totally
		3397	different implementation for windows, as libev offers the POSIX readiness
		3398	notification model, which cannot be implemented efficiently on windows
		3399	(Microsoft monopoly games).
		3400
		3401	A typical way to use libev under windows is to embed it (see the embedding
		3402	section for details) and use the following F<evwrap.h> header file instead
		3403	of F<ev.h>:
		3404
		3405	#define EV_STANDALONE /* keeps ev from requiring config.h */
		3406	#define EV_SELECT_IS_WINSOCKET 1 /* configure libev for windows select */
		3407
		3408	#include "ev.h"
		3409
		3410	And compile the following F<evwrap.c> file into your project (make sure
		3411	you do I<not> compile the F<ev.c> or any other embedded soruce files!):
		3412
		3413	#include "evwrap.h"
		3414	#include "ev.c"
		3415
		3416	=over 4
		3417
		3418	=item The winsocket select function
		3419
		3420	The winsocket C<select> function doesn't follow POSIX in that it
		3421	requires socket I<handles> and not socket I<file descriptors> (it is
		3422	also extremely buggy). This makes select very inefficient, and also
		3423	requires a mapping from file descriptors to socket handles (the Microsoft
		3424	C runtime provides the function C<_open_osfhandle> for this). See the
		3425	discussion of the C<EV_SELECT_USE_FD_SET>, C<EV_SELECT_IS_WINSOCKET> and
		3426	C<EV_FD_TO_WIN32_HANDLE> preprocessor symbols for more info.
		3427
		3428	The configuration for a "naked" win32 using the Microsoft runtime
		3429	libraries and raw winsocket select is:
		3430
		3431	#define EV_USE_SELECT 1
		3432	#define EV_SELECT_IS_WINSOCKET 1 /* forces EV_SELECT_USE_FD_SET, too */
		3433
		3434	Note that winsockets handling of fd sets is O(n), so you can easily get a
		3435	complexity in the O(n²) range when using win32.
		3436
		3437	=item Limited number of file descriptors
		3438
		3439	Windows has numerous arbitrary (and low) limits on things.
		3440
		3441	Early versions of winsocket's select only supported waiting for a maximum
		3442	of C<64> handles (probably owning to the fact that all windows kernels
		3443	can only wait for C<64> things at the same time internally; Microsoft
		3444	recommends spawning a chain of threads and wait for 63 handles and the
		3445	previous thread in each. Great).
		3446
		3447	Newer versions support more handles, but you need to define C<FD_SETSIZE>
		3448	to some high number (e.g. C<2048>) before compiling the winsocket select
		3449	call (which might be in libev or elsewhere, for example, perl does its own
		3450	select emulation on windows).
		3451
		3452	Another limit is the number of file descriptors in the Microsoft runtime
		3453	libraries, which by default is C<64> (there must be a hidden I<64> fetish
		3454	or something like this inside Microsoft). You can increase this by calling
		3455	C<_setmaxstdio>, which can increase this limit to C<2048> (another
		3456	arbitrary limit), but is broken in many versions of the Microsoft runtime
		3457	libraries.
		3458
		3459	This might get you to about C<512> or C<2048> sockets (depending on
		3460	windows version and/or the phase of the moon). To get more, you need to
		3461	wrap all I/O functions and provide your own fd management, but the cost of
		3462	calling select (O(n²)) will likely make this unworkable.
		3463
		3464	=back
		3465
		3466
		3467	=head1 PORTABILITY REQUIREMENTS
		3468
		3469	In addition to a working ISO-C implementation, libev relies on a few
		3470	additional extensions:
		3471
		3472	=over 4
		3473
		3474	=item C<void (*)(ev_watcher_type *, int revents)> must have compatible
		3475	calling conventions regardless of C<ev_watcher_type *>.
		3476
		3477	Libev assumes not only that all watcher pointers have the same internal
		3478	structure (guaranteed by POSIX but not by ISO C for example), but it also
		3479	assumes that the same (machine) code can be used to call any watcher
		3480	callback: The watcher callbacks have different type signatures, but libev
		3481	calls them using an C<ev_watcher *> internally.
		3482
		3483	=item C<sig_atomic_t volatile> must be thread-atomic as well
		3484
		3485	The type C<sig_atomic_t volatile> (or whatever is defined as
		3486	C<EV_ATOMIC_T>) must be atomic w.r.t. accesses from different
		3487	threads. This is not part of the specification for C<sig_atomic_t>, but is
		3488	believed to be sufficiently portable.
		3489
		3490	=item C<sigprocmask> must work in a threaded environment
		3491
		3492	Libev uses C<sigprocmask> to temporarily block signals. This is not
		3493	allowed in a threaded program (C<pthread_sigmask> has to be used). Typical
		3494	pthread implementations will either allow C<sigprocmask> in the "main
		3495	thread" or will block signals process-wide, both behaviours would
		3496	be compatible with libev. Interaction between C<sigprocmask> and
		3497	C<pthread_sigmask> could complicate things, however.
		3498
		3499	The most portable way to handle signals is to block signals in all threads
		3500	except the initial one, and run the default loop in the initial thread as
		3501	well.
		3502
		3503	=item C<long> must be large enough for common memory allocation sizes
		3504
		3505	To improve portability and simplify using libev, libev uses C<long>
		3506	internally instead of C<size_t> when allocating its data structures. On
		3507	non-POSIX systems (Microsoft...) this might be unexpectedly low, but
		3508	is still at least 31 bits everywhere, which is enough for hundreds of
		3509	millions of watchers.
		3510
		3511	=item C<double> must hold a time value in seconds with enough accuracy
		3512
		3513	The type C<double> is used to represent timestamps. It is required to
		3514	have at least 51 bits of mantissa (and 9 bits of exponent), which is good
		3515	enough for at least into the year 4000. This requirement is fulfilled by
		3516	implementations implementing IEEE 754 (basically all existing ones).
		3517
		3518	=back
		3519
		3520	If you know of other additional requirements drop me a note.
		3521
		3522
		3523	=head1 COMPILER WARNINGS
		3524
		3525	Depending on your compiler and compiler settings, you might get no or a
		3526	lot of warnings when compiling libev code. Some people are apparently
		3527	scared by this.
		3528
		3529	However, these are unavoidable for many reasons. For one, each compiler
		3530	has different warnings, and each user has different tastes regarding
		3531	warning options. "Warn-free" code therefore cannot be a goal except when
		3532	targeting a specific compiler and compiler-version.
		3533
		3534	Another reason is that some compiler warnings require elaborate
		3535	workarounds, or other changes to the code that make it less clear and less
		3536	maintainable.
		3537
		3538	And of course, some compiler warnings are just plain stupid, or simply
		3539	wrong (because they don't actually warn about the condition their message
		3540	seems to warn about).
		3541
		3542	While libev is written to generate as few warnings as possible,
		3543	"warn-free" code is not a goal, and it is recommended not to build libev
		3544	with any compiler warnings enabled unless you are prepared to cope with
		3545	them (e.g. by ignoring them). Remember that warnings are just that:
		3546	warnings, not errors, or proof of bugs.
		3547
		3548
		3549	=head1 VALGRIND
		3550
		3551	Valgrind has a special section here because it is a popular tool that is
		3552	highly useful, but valgrind reports are very hard to interpret.
		3553
		3554	If you think you found a bug (memory leak, uninitialised data access etc.)
		3555	in libev, then check twice: If valgrind reports something like:
		3556
		3557	==2274== definitely lost: 0 bytes in 0 blocks.
		3558	==2274== possibly lost: 0 bytes in 0 blocks.
		3559	==2274== still reachable: 256 bytes in 1 blocks.
		3560
		3561	Then there is no memory leak. Similarly, under some circumstances,
		3562	valgrind might report kernel bugs as if it were a bug in libev, or it
		3563	might be confused (it is a very good tool, but only a tool).
		3564
		3565	If you are unsure about something, feel free to contact the mailing list
		3566	with the full valgrind report and an explanation on why you think this is
		3567	a bug in libev. However, don't be annoyed when you get a brisk "this is
		3568	no bug" answer and take the chance of learning how to interpret valgrind
		3569	properly.
		3570
		3571	If you need, for some reason, empty reports from valgrind for your project
		3572	I suggest using suppression lists.
		3573
		3574
2474	=head1 AUTHOR	3575	=head1 AUTHOR
2475		3576
2476	Marc Lehmann <libev@schmorp.de>.	3577	Marc Lehmann <libev@schmorp.de>.
2477		3578

Diff Legend

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