[ViewVC] Diff of: cvs/libev/ev.pod

Comparing libev/ev.pod (file contents):
Revision 1.2 by root, Mon Nov 12 08:02:55 2007 UTC vs.
Revision 1.36 by root, Sat Nov 24 07:14:26 2007 UTC

…		…
8		8
9	=head1 DESCRIPTION	9	=head1 DESCRIPTION
10		10
11	Libev is an event loop: you register interest in certain events (such as a	11	Libev is an event loop: you register interest in certain events (such as a
12	file descriptor being readable or a timeout occuring), and it will manage	12	file descriptor being readable or a timeout occuring), and it will manage
13	these event sources and provide your program events.	13	these event sources and provide your program with events.
14		14
15	To do this, it must take more or less complete control over your process	15	To do this, it must take more or less complete control over your process
16	(or thread) by executing the I<event loop> handler, and will then	16	(or thread) by executing the I<event loop> handler, and will then
17	communicate events via a callback mechanism.	17	communicate events via a callback mechanism.
18		18
…		…
25		25
26	Libev supports select, poll, the linux-specific epoll and the bsd-specific	26	Libev supports select, poll, the linux-specific epoll and the bsd-specific
27	kqueue mechanisms for file descriptor events, relative timers, absolute	27	kqueue mechanisms for file descriptor events, relative timers, absolute
28	timers with customised rescheduling, signal events, process status change	28	timers with customised rescheduling, signal events, process status change
29	events (related to SIGCHLD), and event watchers dealing with the event	29	events (related to SIGCHLD), and event watchers dealing with the event
30	loop mechanism itself (idle, prepare and check watchers).	30	loop mechanism itself (idle, prepare and check watchers). It also is quite
		31	fast (see this L<benchmark\|http://libev.schmorp.de/bench.html> comparing
		32	it to libevent for example).
31		33
32	=head1 CONVENTIONS	34	=head1 CONVENTIONS
33		35
34	Libev is very configurable. In this manual the default configuration	36	Libev is very configurable. In this manual the default configuration
35	will be described, which supports multiple event loops. For more info	37	will be described, which supports multiple event loops. For more info
36	about various configuraiton options please have a look at the file	38	about various configuration options please have a look at the file
37	F<README.embed> in the libev distribution. If libev was configured without	39	F<README.embed> in the libev distribution. If libev was configured without
38	support for multiple event loops, then all functions taking an initial	40	support for multiple event loops, then all functions taking an initial
39	argument of name C<loop> (which is always of type C<struct ev_loop *>)	41	argument of name C<loop> (which is always of type C<struct ev_loop *>)
40	will not have this argument.	42	will not have this argument.
41		43
42	=head1 TIME AND OTHER GLOBAL FUNCTIONS	44	=head1 TIME REPRESENTATION
43		45
44	Libev represents time as a single floating point number, representing the	46	Libev represents time as a single floating point number, representing the
45	(fractional) number of seconds since the (POSIX) epoch (somewhere near	47	(fractional) number of seconds since the (POSIX) epoch (somewhere near
46	the beginning of 1970, details are complicated, don't ask). This type is	48	the beginning of 1970, details are complicated, don't ask). This type is
47	called C<ev_tstamp>, which is what you should use too. It usually aliases	49	called C<ev_tstamp>, which is what you should use too. It usually aliases
48	to the double type in C.	50	to the C<double> type in C, and when you need to do any calculations on
		51	it, you should treat it as such.
		52
		53
		54	=head1 GLOBAL FUNCTIONS
		55
		56	These functions can be called anytime, even before initialising the
		57	library in any way.
49		58
50	=over 4	59	=over 4
51		60
52	=item ev_tstamp ev_time ()	61	=item ev_tstamp ev_time ()
53		62
54	Returns the current time as libev would use it.	63	Returns the current time as libev would use it. Please note that the
		64	C<ev_now> function is usually faster and also often returns the timestamp
		65	you actually want to know.
55		66
56	=item int ev_version_major ()	67	=item int ev_version_major ()
57		68
58	=item int ev_version_minor ()	69	=item int ev_version_minor ()
59		70
…		…
61	you linked against by calling the functions C<ev_version_major> and	72	you linked against by calling the functions C<ev_version_major> and
62	C<ev_version_minor>. If you want, you can compare against the global	73	C<ev_version_minor>. If you want, you can compare against the global
63	symbols C<EV_VERSION_MAJOR> and C<EV_VERSION_MINOR>, which specify the	74	symbols C<EV_VERSION_MAJOR> and C<EV_VERSION_MINOR>, which specify the
64	version of the library your program was compiled against.	75	version of the library your program was compiled against.
65		76
66	Usually, its a good idea to terminate if the major versions mismatch,	77	Usually, it's a good idea to terminate if the major versions mismatch,
67	as this indicates an incompatible change. Minor versions are usually	78	as this indicates an incompatible change. Minor versions are usually
68	compatible to older versions, so a larger minor version alone is usually	79	compatible to older versions, so a larger minor version alone is usually
69	not a problem.	80	not a problem.
70		81
		82	Example: make sure we haven't accidentally been linked against the wrong
		83	version:
		84
		85	assert (("libev version mismatch",
		86	ev_version_major () == EV_VERSION_MAJOR
		87	&& ev_version_minor () >= EV_VERSION_MINOR));
		88
		89	=item unsigned int ev_supported_backends ()
		90
		91	Return the set of all backends (i.e. their corresponding C<EV_BACKEND_*>
		92	value) compiled into this binary of libev (independent of their
		93	availability on the system you are running on). See C<ev_default_loop> for
		94	a description of the set values.
		95
		96	Example: make sure we have the epoll method, because yeah this is cool and
		97	a must have and can we have a torrent of it please!!!11
		98
		99	assert (("sorry, no epoll, no sex",
		100	ev_supported_backends () & EVBACKEND_EPOLL));
		101
		102	=item unsigned int ev_recommended_backends ()
		103
		104	Return the set of all backends compiled into this binary of libev and also
		105	recommended for this platform. This set is often smaller than the one
		106	returned by C<ev_supported_backends>, as for example kqueue is broken on
		107	most BSDs and will not be autodetected unless you explicitly request it
		108	(assuming you know what you are doing). This is the set of backends that
		109	libev will probe for if you specify no backends explicitly.
		110
		111	=item unsigned int ev_embeddable_backends ()
		112
		113	Returns the set of backends that are embeddable in other event loops. This
		114	is the theoretical, all-platform, value. To find which backends
		115	might be supported on the current system, you would need to look at
		116	C<ev_embeddable_backends () & ev_supported_backends ()>, likewise for
		117	recommended ones.
		118
		119	See the description of C<ev_embed> watchers for more info.
		120
71	=item ev_set_allocator (void (cb)(void *ptr, long size))	121	=item ev_set_allocator (void (cb)(void *ptr, long size))
72		122
73	Sets the allocation function to use (the prototype is similar to the	123	Sets the allocation function to use (the prototype is similar to the
74	realloc function). It is used to allocate and free memory (no surprises	124	realloc C function, the semantics are identical). It is used to allocate
75	here). If it returns zero when memory needs to be allocated, the library	125	and free memory (no surprises here). If it returns zero when memory
76	might abort or take some potentially destructive action. The default is	126	needs to be allocated, the library might abort or take some potentially
77	your system realloc function.	127	destructive action. The default is your system realloc function.
78		128
79	You could override this function in high-availability programs to, say,	129	You could override this function in high-availability programs to, say,
80	free some memory if it cannot allocate memory, to use a special allocator,	130	free some memory if it cannot allocate memory, to use a special allocator,
81	or even to sleep a while and retry until some memory is available.	131	or even to sleep a while and retry until some memory is available.
		132
		133	Example: replace the libev allocator with one that waits a bit and then
		134	retries: better than mine).
		135
		136	static void *
		137	persistent_realloc (void *ptr, long size)
		138	{
		139	for (;;)
		140	{
		141	void *newptr = realloc (ptr, size);
		142
		143	if (newptr)
		144	return newptr;
		145
		146	sleep (60);
		147	}
		148	}
		149
		150	...
		151	ev_set_allocator (persistent_realloc);
82		152
83	=item ev_set_syserr_cb (void (cb)(const char msg));	153	=item ev_set_syserr_cb (void (cb)(const char msg));
84		154
85	Set the callback function to call on a retryable syscall error (such	155	Set the callback function to call on a retryable syscall error (such
86	as failed select, poll, epoll_wait). The message is a printable string	156	as failed select, poll, epoll_wait). The message is a printable string
87	indicating the system call or subsystem causing the problem. If this	157	indicating the system call or subsystem causing the problem. If this
88	callback is set, then libev will expect it to remedy the sitution, no	158	callback is set, then libev will expect it to remedy the sitution, no
89	matter what, when it returns. That is, libev will geenrally retry the	159	matter what, when it returns. That is, libev will generally retry the
90	requested operation, or, if the condition doesn't go away, do bad stuff	160	requested operation, or, if the condition doesn't go away, do bad stuff
91	(such as abort).	161	(such as abort).
		162
		163	Example: do the same thing as libev does internally:
		164
		165	static void
		166	fatal_error (const char *msg)
		167	{
		168	perror (msg);
		169	abort ();
		170	}
		171
		172	...
		173	ev_set_syserr_cb (fatal_error);
92		174
93	=back	175	=back
94		176
95	=head1 FUNCTIONS CONTROLLING THE EVENT LOOP	177	=head1 FUNCTIONS CONTROLLING THE EVENT LOOP
96		178
97	An event loop is described by a C<struct ev_loop *>. The library knows two	179	An event loop is described by a C<struct ev_loop *>. The library knows two
98	types of such loops, the I<default> loop, which supports signals and child	180	types of such loops, the I<default> loop, which supports signals and child
99	events, and dynamically created loops which do not.	181	events, and dynamically created loops which do not.
100		182
101	If you use threads, a common model is to run the default event loop	183	If you use threads, a common model is to run the default event loop
102	in your main thread (or in a separate thrad) and for each thread you	184	in your main thread (or in a separate thread) and for each thread you
103	create, you also create another event loop. Libev itself does no lockign	185	create, you also create another event loop. Libev itself does no locking
104	whatsoever, so if you mix calls to different event loops, make sure you	186	whatsoever, so if you mix calls to the same event loop in different
105	lock (this is usually a bad idea, though, even if done right).	187	threads, make sure you lock (this is usually a bad idea, though, even if
		188	done correctly, because it's hideous and inefficient).
106		189
107	=over 4	190	=over 4
108		191
109	=item struct ev_loop *ev_default_loop (unsigned int flags)	192	=item struct ev_loop *ev_default_loop (unsigned int flags)
110		193
111	This will initialise the default event loop if it hasn't been initialised	194	This will initialise the default event loop if it hasn't been initialised
112	yet and return it. If the default loop could not be initialised, returns	195	yet and return it. If the default loop could not be initialised, returns
113	false. If it already was initialised it simply returns it (and ignores the	196	false. If it already was initialised it simply returns it (and ignores the
114	flags).	197	flags. If that is troubling you, check C<ev_backend ()> afterwards).
115		198
116	If you don't know what event loop to use, use the one returned from this	199	If you don't know what event loop to use, use the one returned from this
117	function.	200	function.
118		201
119	The flags argument can be used to specify special behaviour or specific	202	The flags argument can be used to specify special behaviour or specific
120	backends to use, and is usually specified as 0 (or EVFLAG_AUTO)	203	backends to use, and is usually specified as C<0> (or C<EVFLAG_AUTO>).
121		204
122	It supports the following flags:	205	The following flags are supported:
123		206
124	=over 4	207	=over 4
125		208
126	=item EVFLAG_AUTO	209	=item C<EVFLAG_AUTO>
127		210
128	The default flags value. Use this if you have no clue (its the right	211	The default flags value. Use this if you have no clue (it's the right
129	thing, believe me).	212	thing, believe me).
130		213
131	=item EVFLAG_NOENV	214	=item C<EVFLAG_NOENV>
132		215
133	If this flag bit is ored into the flag value then libev will I<not> look	216	If this flag bit is ored into the flag value (or the program runs setuid
134	at the environment variable C<LIBEV_FLAGS>. Otherwise (the default), this	217	or setgid) then libev will I<not> look at the environment variable
135	environment variable will override the flags completely. This is useful	218	C<LIBEV_FLAGS>. Otherwise (the default), this environment variable will
		219	override the flags completely if it is found in the environment. This is
136	to try out specific backends to tets their performance, or to work around	220	useful to try out specific backends to test their performance, or to work
137	bugs.	221	around bugs.
138		222
139	=item EVMETHOD_SELECT portable select backend	223	=item C<EVBACKEND_SELECT> (value 1, portable select backend)
140		224
141	=item EVMETHOD_POLL poll backend (everywhere except windows)	225	This is your standard select(2) backend. Not I<completely> standard, as
		226	libev tries to roll its own fd_set with no limits on the number of fds,
		227	but if that fails, expect a fairly low limit on the number of fds when
		228	using this backend. It doesn't scale too well (O(highest_fd)), but its usually
		229	the fastest backend for a low number of fds.
142		230
143	=item EVMETHOD_EPOLL linux only	231	=item C<EVBACKEND_POLL> (value 2, poll backend, available everywhere except on windows)
144		232
145	=item EVMETHOD_KQUEUE some bsds only	233	And this is your standard poll(2) backend. It's more complicated than
		234	select, but handles sparse fds better and has no artificial limit on the
		235	number of fds you can use (except it will slow down considerably with a
		236	lot of inactive fds). It scales similarly to select, i.e. O(total_fds).
146		237
147	=item EVMETHOD_DEVPOLL solaris 8 only	238	=item C<EVBACKEND_EPOLL> (value 4, Linux)
148		239
149	=item EVMETHOD_PORT solaris 10 only	240	For few fds, this backend is a bit little slower than poll and select,
		241	but it scales phenomenally better. While poll and select usually scale like
		242	O(total_fds) where n is the total number of fds (or the highest fd), epoll scales
		243	either O(1) or O(active_fds).
		244
		245	While stopping and starting an I/O watcher in the same iteration will
		246	result in some caching, there is still a syscall per such incident
		247	(because the fd could point to a different file description now), so its
		248	best to avoid that. Also, dup()ed file descriptors might not work very
		249	well if you register events for both fds.
		250
		251	Please note that epoll sometimes generates spurious notifications, so you
		252	need to use non-blocking I/O or other means to avoid blocking when no data
		253	(or space) is available.
		254
		255	=item C<EVBACKEND_KQUEUE> (value 8, most BSD clones)
		256
		257	Kqueue deserves special mention, as at the time of this writing, it
		258	was broken on all BSDs except NetBSD (usually it doesn't work with
		259	anything but sockets and pipes, except on Darwin, where of course its
		260	completely useless). For this reason its not being "autodetected"
		261	unless you explicitly specify it explicitly in the flags (i.e. using
		262	C<EVBACKEND_KQUEUE>).
		263
		264	It scales in the same way as the epoll backend, but the interface to the
		265	kernel is more efficient (which says nothing about its actual speed, of
		266	course). While starting and stopping an I/O watcher does not cause an
		267	extra syscall as with epoll, it still adds up to four event changes per
		268	incident, so its best to avoid that.
		269
		270	=item C<EVBACKEND_DEVPOLL> (value 16, Solaris 8)
		271
		272	This is not implemented yet (and might never be).
		273
		274	=item C<EVBACKEND_PORT> (value 32, Solaris 10)
		275
		276	This uses the Solaris 10 port mechanism. As with everything on Solaris,
		277	it's really slow, but it still scales very well (O(active_fds)).
		278
		279	Please note that solaris ports can result in a lot of spurious
		280	notifications, so you need to use non-blocking I/O or other means to avoid
		281	blocking when no data (or space) is available.
		282
		283	=item C<EVBACKEND_ALL>
		284
		285	Try all backends (even potentially broken ones that wouldn't be tried
		286	with C<EVFLAG_AUTO>). Since this is a mask, you can do stuff such as
		287	C<EVBACKEND_ALL & ~EVBACKEND_KQUEUE>.
		288
		289	=back
150		290
151	If one or more of these are ored into the flags value, then only these	291	If one or more of these are ored into the flags value, then only these
152	backends will be tried (in the reverse order as given here). If one are	292	backends will be tried (in the reverse order as given here). If none are
153	specified, any backend will do.	293	specified, most compiled-in backend will be tried, usually in reverse
		294	order of their flag values :)
154		295
155	=back	296	The most typical usage is like this:
		297
		298	if (!ev_default_loop (0))
		299	fatal ("could not initialise libev, bad $LIBEV_FLAGS in environment?");
		300
		301	Restrict libev to the select and poll backends, and do not allow
		302	environment settings to be taken into account:
		303
		304	ev_default_loop (EVBACKEND_POLL \| EVBACKEND_SELECT \| EVFLAG_NOENV);
		305
		306	Use whatever libev has to offer, but make sure that kqueue is used if
		307	available (warning, breaks stuff, best use only with your own private
		308	event loop and only if you know the OS supports your types of fds):
		309
		310	ev_default_loop (ev_recommended_backends () \| EVBACKEND_KQUEUE);
156		311
157	=item struct ev_loop *ev_loop_new (unsigned int flags)	312	=item struct ev_loop *ev_loop_new (unsigned int flags)
158		313
159	Similar to C<ev_default_loop>, but always creates a new event loop that is	314	Similar to C<ev_default_loop>, but always creates a new event loop that is
160	always distinct from the default loop. Unlike the default loop, it cannot	315	always distinct from the default loop. Unlike the default loop, it cannot
161	handle signal and child watchers, and attempts to do so will be greeted by	316	handle signal and child watchers, and attempts to do so will be greeted by
162	undefined behaviour (or a failed assertion if assertions are enabled).	317	undefined behaviour (or a failed assertion if assertions are enabled).
163		318
		319	Example: try to create a event loop that uses epoll and nothing else.
		320
		321	struct ev_loop *epoller = ev_loop_new (EVBACKEND_EPOLL \| EVFLAG_NOENV);
		322	if (!epoller)
		323	fatal ("no epoll found here, maybe it hides under your chair");
		324
164	=item ev_default_destroy ()	325	=item ev_default_destroy ()
165		326
166	Destroys the default loop again (frees all memory and kernel state	327	Destroys the default loop again (frees all memory and kernel state
167	etc.). This stops all registered event watchers (by not touching them in	328	etc.). This stops all registered event watchers (by not touching them in
168	any way whatsoever, although you cnanot rely on this :).	329	any way whatsoever, although you cannot rely on this :).
169		330
170	=item ev_loop_destroy (loop)	331	=item ev_loop_destroy (loop)
171		332
172	Like C<ev_default_destroy>, but destroys an event loop created by an	333	Like C<ev_default_destroy>, but destroys an event loop created by an
173	earlier call to C<ev_loop_new>.	334	earlier call to C<ev_loop_new>.
…		…
177	This function reinitialises the kernel state for backends that have	338	This function reinitialises the kernel state for backends that have
178	one. Despite the name, you can call it anytime, but it makes most sense	339	one. Despite the name, you can call it anytime, but it makes most sense
179	after forking, in either the parent or child process (or both, but that	340	after forking, in either the parent or child process (or both, but that
180	again makes little sense).	341	again makes little sense).
181		342
182	You I<must> call this function after forking if and only if you want to	343	You I<must> call this function in the child process after forking if and
183	use the event library in both processes. If you just fork+exec, you don't	344	only if you want to use the event library in both processes. If you just
184	have to call it.	345	fork+exec, you don't have to call it.
185		346
186	The function itself is quite fast and its usually not a problem to call	347	The function itself is quite fast and it's usually not a problem to call
187	it just in case after a fork. To make this easy, the function will fit in	348	it just in case after a fork. To make this easy, the function will fit in
188	quite nicely into a call to C<pthread_atfork>:	349	quite nicely into a call to C<pthread_atfork>:
189		350
190	pthread_atfork (0, 0, ev_default_fork);	351	pthread_atfork (0, 0, ev_default_fork);
		352
		353	At the moment, C<EVBACKEND_SELECT> and C<EVBACKEND_POLL> are safe to use
		354	without calling this function, so if you force one of those backends you
		355	do not need to care.
191		356
192	=item ev_loop_fork (loop)	357	=item ev_loop_fork (loop)
193		358
194	Like C<ev_default_fork>, but acts on an event loop created by	359	Like C<ev_default_fork>, but acts on an event loop created by
195	C<ev_loop_new>. Yes, you have to call this on every allocated event loop	360	C<ev_loop_new>. Yes, you have to call this on every allocated event loop
196	after fork, and how you do this is entirely your own problem.	361	after fork, and how you do this is entirely your own problem.
197		362
198	=item unsigned int ev_method (loop)	363	=item unsigned int ev_backend (loop)
199		364
200	Returns one of the C<EVMETHOD_*> flags indicating the event backend in	365	Returns one of the C<EVBACKEND_*> flags indicating the event backend in
201	use.	366	use.
202		367
203	=item ev_tstamp = ev_now (loop)	368	=item ev_tstamp ev_now (loop)
204		369
205	Returns the current "event loop time", which is the time the event loop	370	Returns the current "event loop time", which is the time the event loop
206	got events and started processing them. This timestamp does not change	371	received events and started processing them. This timestamp does not
207	as long as callbacks are being processed, and this is also the base time	372	change as long as callbacks are being processed, and this is also the base
208	used for relative timers. You can treat it as the timestamp of the event	373	time used for relative timers. You can treat it as the timestamp of the
209	occuring (or more correctly, the mainloop finding out about it).	374	event occuring (or more correctly, libev finding out about it).
210		375
211	=item ev_loop (loop, int flags)	376	=item ev_loop (loop, int flags)
212		377
213	Finally, this is it, the event handler. This function usually is called	378	Finally, this is it, the event handler. This function usually is called
214	after you initialised all your watchers and you want to start handling	379	after you initialised all your watchers and you want to start handling
215	events.	380	events.
216		381
217	If the flags argument is specified as 0, it will not return until either	382	If the flags argument is specified as C<0>, it will not return until
218	no event watchers are active anymore or C<ev_unloop> was called.	383	either no event watchers are active anymore or C<ev_unloop> was called.
		384
		385	Please note that an explicit C<ev_unloop> is usually better than
		386	relying on all watchers to be stopped when deciding when a program has
		387	finished (especially in interactive programs), but having a program that
		388	automatically loops as long as it has to and no longer by virtue of
		389	relying on its watchers stopping correctly is a thing of beauty.
219		390
220	A flags value of C<EVLOOP_NONBLOCK> will look for new events, will handle	391	A flags value of C<EVLOOP_NONBLOCK> will look for new events, will handle
221	those events and any outstanding ones, but will not block your process in	392	those events and any outstanding ones, but will not block your process in
222	case there are no events.	393	case there are no events and will return after one iteration of the loop.
223		394
224	A flags value of C<EVLOOP_ONESHOT> will look for new events (waiting if	395	A flags value of C<EVLOOP_ONESHOT> will look for new events (waiting if
225	neccessary) and will handle those and any outstanding ones. It will block	396	neccessary) and will handle those and any outstanding ones. It will block
226	your process until at least one new event arrives.	397	your process until at least one new event arrives, and will return after
		398	one iteration of the loop. This is useful if you are waiting for some
		399	external event in conjunction with something not expressible using other
		400	libev watchers. However, a pair of C<ev_prepare>/C<ev_check> watchers is
		401	usually a better approach for this kind of thing.
227		402
228	This flags value could be used to implement alternative looping	403	Here are the gory details of what C<ev_loop> does:
229	constructs, but the C<prepare> and C<check> watchers provide a better and	404
230	more generic mechanism.	405	* If there are no active watchers (reference count is zero), return.
		406	- Queue prepare watchers and then call all outstanding watchers.
		407	- If we have been forked, recreate the kernel state.
		408	- Update the kernel state with all outstanding changes.
		409	- Update the "event loop time".
		410	- Calculate for how long to block.
		411	- Block the process, waiting for any events.
		412	- Queue all outstanding I/O (fd) events.
		413	- Update the "event loop time" and do time jump handling.
		414	- Queue all outstanding timers.
		415	- Queue all outstanding periodics.
		416	- If no events are pending now, queue all idle watchers.
		417	- Queue all check watchers.
		418	- Call all queued watchers in reverse order (i.e. check watchers first).
		419	Signals and child watchers are implemented as I/O watchers, and will
		420	be handled here by queueing them when their watcher gets executed.
		421	- If ev_unloop has been called or EVLOOP_ONESHOT or EVLOOP_NONBLOCK
		422	were used, return, otherwise continue with step *.
		423
		424	Example: queue some jobs and then loop until no events are outsanding
		425	anymore.
		426
		427	... queue jobs here, make sure they register event watchers as long
		428	... as they still have work to do (even an idle watcher will do..)
		429	ev_loop (my_loop, 0);
		430	... jobs done. yeah!
231		431
232	=item ev_unloop (loop, how)	432	=item ev_unloop (loop, how)
233		433
234	Can be used to make a call to C<ev_loop> return early. The C<how> argument	434	Can be used to make a call to C<ev_loop> return early (but only after it
		435	has processed all outstanding events). The C<how> argument must be either
235	must be either C<EVUNLOOP_ONCE>, which will make the innermost C<ev_loop>	436	C<EVUNLOOP_ONE>, which will make the innermost C<ev_loop> call return, or
236	call return, or C<EVUNLOOP_ALL>, which will make all nested C<ev_loop>	437	C<EVUNLOOP_ALL>, which will make all nested C<ev_loop> calls return.
237	calls return.
238		438
239	=item ev_ref (loop)	439	=item ev_ref (loop)
240		440
241	=item ev_unref (loop)	441	=item ev_unref (loop)
242		442
243	Ref/unref can be used to add or remove a refcount on the event loop: Every	443	Ref/unref can be used to add or remove a reference count on the event
244	watcher keeps one reference. If you have a long-runing watcher you never	444	loop: Every watcher keeps one reference, and as long as the reference
245	unregister that should not keep ev_loop from running, ev_unref() after	445	count is nonzero, C<ev_loop> will not return on its own. If you have
246	starting, and ev_ref() before stopping it. Libev itself uses this for	446	a watcher you never unregister that should not keep C<ev_loop> from
247	example for its internal signal pipe: It is not visible to you as a user	447	returning, ev_unref() after starting, and ev_ref() before stopping it. For
248	and should not keep C<ev_loop> from exiting if the work is done. It is	448	example, libev itself uses this for its internal signal pipe: It is not
249	also an excellent way to do this for generic recurring timers or from	449	visible to the libev user and should not keep C<ev_loop> from exiting if
250	within third-party libraries. Just remember to unref after start and ref	450	no event watchers registered by it are active. It is also an excellent
251	before stop.	451	way to do this for generic recurring timers or from within third-party
		452	libraries. Just remember to I<unref after start> and I<ref before stop>.
		453
		454	Example: create a signal watcher, but keep it from keeping C<ev_loop>
		455	running when nothing else is active.
		456
		457	struct dv_signal exitsig;
		458	ev_signal_init (&exitsig, sig_cb, SIGINT);
		459	ev_signal_start (myloop, &exitsig);
		460	evf_unref (myloop);
		461
		462	Example: for some weird reason, unregister the above signal handler again.
		463
		464	ev_ref (myloop);
		465	ev_signal_stop (myloop, &exitsig);
252		466
253	=back	467	=back
254		468
255	=head1 ANATOMY OF A WATCHER	469	=head1 ANATOMY OF A WATCHER
256		470
257	A watcher is a structure that you create and register to record your	471	A watcher is a structure that you create and register to record your
258	interest in some event. For instance, if you want to wait for STDIN to	472	interest in some event. For instance, if you want to wait for STDIN to
259	become readable, you would create an ev_io watcher for that:	473	become readable, you would create an C<ev_io> watcher for that:
260		474
261	static void my_cb (struct ev_loop loop, struct ev_io w, int revents)	475	static void my_cb (struct ev_loop loop, struct ev_io w, int revents)
262	{	476	{
263	ev_io_stop (w);	477	ev_io_stop (w);
264	ev_unloop (loop, EVUNLOOP_ALL);	478	ev_unloop (loop, EVUNLOOP_ALL);
…		…
291	*) >>), and you can stop watching for events at any time by calling the	505	*) >>), and you can stop watching for events at any time by calling the
292	corresponding stop function (C<< ev_<type>_stop (loop, watcher *) >>.	506	corresponding stop function (C<< ev_<type>_stop (loop, watcher *) >>.
293		507
294	As long as your watcher is active (has been started but not stopped) you	508	As long as your watcher is active (has been started but not stopped) you
295	must not touch the values stored in it. Most specifically you must never	509	must not touch the values stored in it. Most specifically you must never
296	reinitialise it or call its set method.	510	reinitialise it or call its C<set> macro.
297
298	You cna check wether an event is active by calling the C<ev_is_active
299	(watcher *)> macro. To see wether an event is outstanding (but the
300	callback for it has not been called yet) you cna use the C<ev_is_pending
301	(watcher *)> macro.
302		511
303	Each and every callback receives the event loop pointer as first, the	512	Each and every callback receives the event loop pointer as first, the
304	registered watcher structure as second, and a bitset of received events as	513	registered watcher structure as second, and a bitset of received events as
305	third argument.	514	third argument.
306		515
307	The rceeived events usually include a single bit per event type received	516	The received events usually include a single bit per event type received
308	(you can receive multiple events at the same time). The possible bit masks	517	(you can receive multiple events at the same time). The possible bit masks
309	are:	518	are:
310		519
311	=over 4	520	=over 4
312		521
313	=item EV_READ	522	=item C<EV_READ>
314		523
315	=item EV_WRITE	524	=item C<EV_WRITE>
316		525
317	The file descriptor in the ev_io watcher has become readable and/or	526	The file descriptor in the C<ev_io> watcher has become readable and/or
318	writable.	527	writable.
319		528
320	=item EV_TIMEOUT	529	=item C<EV_TIMEOUT>
321		530
322	The ev_timer watcher has timed out.	531	The C<ev_timer> watcher has timed out.
323		532
324	=item EV_PERIODIC	533	=item C<EV_PERIODIC>
325		534
326	The ev_periodic watcher has timed out.	535	The C<ev_periodic> watcher has timed out.
327		536
328	=item EV_SIGNAL	537	=item C<EV_SIGNAL>
329		538
330	The signal specified in the ev_signal watcher has been received by a thread.	539	The signal specified in the C<ev_signal> watcher has been received by a thread.
331		540
332	=item EV_CHILD	541	=item C<EV_CHILD>
333		542
334	The pid specified in the ev_child watcher has received a status change.	543	The pid specified in the C<ev_child> watcher has received a status change.
335		544
336	=item EV_IDLE	545	=item C<EV_IDLE>
337		546
338	The ev_idle watcher has determined that you have nothing better to do.	547	The C<ev_idle> watcher has determined that you have nothing better to do.
339		548
340	=item EV_PREPARE	549	=item C<EV_PREPARE>
341		550
342	=item EV_CHECK	551	=item C<EV_CHECK>
343		552
344	All ev_prepare watchers are invoked just I<before> C<ev_loop> starts	553	All C<ev_prepare> watchers are invoked just I<before> C<ev_loop> starts
345	to gather new events, and all ev_check watchers are invoked just after	554	to gather new events, and all C<ev_check> watchers are invoked just after
346	C<ev_loop> has gathered them, but before it invokes any callbacks for any	555	C<ev_loop> has gathered them, but before it invokes any callbacks for any
347	received events. Callbacks of both watcher types can start and stop as	556	received events. Callbacks of both watcher types can start and stop as
348	many watchers as they want, and all of them will be taken into account	557	many watchers as they want, and all of them will be taken into account
349	(for example, a ev_prepare watcher might start an idle watcher to keep	558	(for example, a C<ev_prepare> watcher might start an idle watcher to keep
350	C<ev_loop> from blocking).	559	C<ev_loop> from blocking).
351		560
352	=item EV_ERROR	561	=item C<EV_ERROR>
353		562
354	An unspecified error has occured, the watcher has been stopped. This might	563	An unspecified error has occured, the watcher has been stopped. This might
355	happen because the watcher could not be properly started because libev	564	happen because the watcher could not be properly started because libev
356	ran out of memory, a file descriptor was found to be closed or any other	565	ran out of memory, a file descriptor was found to be closed or any other
357	problem. You best act on it by reporting the problem and somehow coping	566	problem. You best act on it by reporting the problem and somehow coping
…		…
363	with the error from read() or write(). This will not work in multithreaded	572	with the error from read() or write(). This will not work in multithreaded
364	programs, though, so beware.	573	programs, though, so beware.
365		574
366	=back	575	=back
367		576
		577	=head2 SUMMARY OF GENERIC WATCHER FUNCTIONS
		578
		579	In the following description, C<TYPE> stands for the watcher type,
		580	e.g. C<timer> for C<ev_timer> watchers and C<io> for C<ev_io> watchers.
		581
		582	=over 4
		583
		584	=item C<ev_init> (ev_TYPE *watcher, callback)
		585
		586	This macro initialises the generic portion of a watcher. The contents
		587	of the watcher object can be arbitrary (so C<malloc> will do). Only
		588	the generic parts of the watcher are initialised, you I<need> to call
		589	the type-specific C<ev_TYPE_set> macro afterwards to initialise the
		590	type-specific parts. For each type there is also a C<ev_TYPE_init> macro
		591	which rolls both calls into one.
		592
		593	You can reinitialise a watcher at any time as long as it has been stopped
		594	(or never started) and there are no pending events outstanding.
		595
		596	The callbakc is always of type C<void ()(ev_loop loop, ev_TYPE *watcher,
		597	int revents)>.
		598
		599	=item C<ev_TYPE_set> (ev_TYPE *, [args])
		600
		601	This macro initialises the type-specific parts of a watcher. You need to
		602	call C<ev_init> at least once before you call this macro, but you can
		603	call C<ev_TYPE_set> any number of times. You must not, however, call this
		604	macro on a watcher that is active (it can be pending, however, which is a
		605	difference to the C<ev_init> macro).
		606
		607	Although some watcher types do not have type-specific arguments
		608	(e.g. C<ev_prepare>) you still need to call its C<set> macro.
		609
		610	=item C<ev_TYPE_init> (ev_TYPE *watcher, callback, [args])
		611
		612	This convinience macro rolls both C<ev_init> and C<ev_TYPE_set> macro
		613	calls into a single call. This is the most convinient method to initialise
		614	a watcher. The same limitations apply, of course.
		615
		616	=item C<ev_TYPE_start> (loop , ev_TYPE watcher)
		617
		618	Starts (activates) the given watcher. Only active watchers will receive
		619	events. If the watcher is already active nothing will happen.
		620
		621	=item C<ev_TYPE_stop> (loop , ev_TYPE watcher)
		622
		623	Stops the given watcher again (if active) and clears the pending
		624	status. It is possible that stopped watchers are pending (for example,
		625	non-repeating timers are being stopped when they become pending), but
		626	C<ev_TYPE_stop> ensures that the watcher is neither active nor pending. If
		627	you want to free or reuse the memory used by the watcher it is therefore a
		628	good idea to always call its C<ev_TYPE_stop> function.
		629
		630	=item bool ev_is_active (ev_TYPE *watcher)
		631
		632	Returns a true value iff the watcher is active (i.e. it has been started
		633	and not yet been stopped). As long as a watcher is active you must not modify
		634	it.
		635
		636	=item bool ev_is_pending (ev_TYPE *watcher)
		637
		638	Returns a true value iff the watcher is pending, (i.e. it has outstanding
		639	events but its callback has not yet been invoked). As long as a watcher
		640	is pending (but not active) you must not call an init function on it (but
		641	C<ev_TYPE_set> is safe) and you must make sure the watcher is available to
		642	libev (e.g. you cnanot C<free ()> it).
		643
		644	=item callback = ev_cb (ev_TYPE *watcher)
		645
		646	Returns the callback currently set on the watcher.
		647
		648	=item ev_cb_set (ev_TYPE *watcher, callback)
		649
		650	Change the callback. You can change the callback at virtually any time
		651	(modulo threads).
		652
		653	=back
		654
		655
368	=head2 ASSOCIATING CUSTOM DATA WITH A WATCHER	656	=head2 ASSOCIATING CUSTOM DATA WITH A WATCHER
369		657
370	Each watcher has, by default, a member C<void *data> that you can change	658	Each watcher has, by default, a member C<void *data> that you can change
371	and read at any time, libev will completely ignore it. This cna be used	659	and read at any time, libev will completely ignore it. This can be used
372	to associate arbitrary data with your watcher. If you need more data and	660	to associate arbitrary data with your watcher. If you need more data and
373	don't want to allocate memory and store a pointer to it in that data	661	don't want to allocate memory and store a pointer to it in that data
374	member, you can also "subclass" the watcher type and provide your own	662	member, you can also "subclass" the watcher type and provide your own
375	data:	663	data:
376		664
…		…
398	=head1 WATCHER TYPES	686	=head1 WATCHER TYPES
399		687
400	This section describes each watcher in detail, but will not repeat	688	This section describes each watcher in detail, but will not repeat
401	information given in the last section.	689	information given in the last section.
402		690
		691
403	=head2 struct ev_io - is my file descriptor readable or writable	692	=head2 C<ev_io> - is this file descriptor readable or writable
404		693
405	I/O watchers check wether a file descriptor is readable or writable	694	I/O watchers check whether a file descriptor is readable or writable
406	in each iteration of the event loop (This behaviour is called	695	in each iteration of the event loop (This behaviour is called
407	level-triggering because you keep receiving events as long as the	696	level-triggering because you keep receiving events as long as the
408	condition persists. Remember you cna stop the watcher if you don't want to	697	condition persists. Remember you can stop the watcher if you don't want to
409	act on the event and neither want to receive future events).	698	act on the event and neither want to receive future events).
410		699
		700	In general you can register as many read and/or write event watchers per
		701	fd as you want (as long as you don't confuse yourself). Setting all file
		702	descriptors to non-blocking mode is also usually a good idea (but not
		703	required if you know what you are doing).
		704
		705	You have to be careful with dup'ed file descriptors, though. Some backends
		706	(the linux epoll backend is a notable example) cannot handle dup'ed file
		707	descriptors correctly if you register interest in two or more fds pointing
		708	to the same underlying file/socket etc. description (that is, they share
		709	the same underlying "file open").
		710
		711	If you must do this, then force the use of a known-to-be-good backend
		712	(at the time of this writing, this includes only C<EVBACKEND_SELECT> and
		713	C<EVBACKEND_POLL>).
		714
411	=over 4	715	=over 4
412		716
413	=item ev_io_init (ev_io *, callback, int fd, int events)	717	=item ev_io_init (ev_io *, callback, int fd, int events)
414		718
415	=item ev_io_set (ev_io *, int fd, int events)	719	=item ev_io_set (ev_io *, int fd, int events)
416		720
417	Configures an ev_io watcher. The fd is the file descriptor to rceeive	721	Configures an C<ev_io> watcher. The fd is the file descriptor to rceeive
418	events for and events is either C<EV_READ>, C<EV_WRITE> or C<EV_READ \|	722	events for and events is either C<EV_READ>, C<EV_WRITE> or C<EV_READ \|
419	EV_WRITE> to receive the given events.	723	EV_WRITE> to receive the given events.
420		724
421	=back	725	Please note that most of the more scalable backend mechanisms (for example
		726	epoll and solaris ports) can result in spurious readyness notifications
		727	for file descriptors, so you practically need to use non-blocking I/O (and
		728	treat callback invocation as hint only), or retest separately with a safe
		729	interface before doing I/O (XLib can do this), or force the use of either
		730	C<EVBACKEND_SELECT> or C<EVBACKEND_POLL>, which don't suffer from this
		731	problem. Also note that it is quite easy to have your callback invoked
		732	when the readyness condition is no longer valid even when employing
		733	typical ways of handling events, so its a good idea to use non-blocking
		734	I/O unconditionally.
422		735
		736	=back
		737
		738	Example: call C<stdin_readable_cb> when STDIN_FILENO has become, well
		739	readable, but only once. Since it is likely line-buffered, you could
		740	attempt to read a whole line in the callback:
		741
		742	static void
		743	stdin_readable_cb (struct ev_loop loop, struct ev_io w, int revents)
		744	{
		745	ev_io_stop (loop, w);
		746	.. read from stdin here (or from w->fd) and haqndle any I/O errors
		747	}
		748
		749	...
		750	struct ev_loop *loop = ev_default_init (0);
		751	struct ev_io stdin_readable;
		752	ev_io_init (&stdin_readable, stdin_readable_cb, STDIN_FILENO, EV_READ);
		753	ev_io_start (loop, &stdin_readable);
		754	ev_loop (loop, 0);
		755
		756
423	=head2 struct ev_timer - relative and optionally recurring timeouts	757	=head2 C<ev_timer> - relative and optionally recurring timeouts
424		758
425	Timer watchers are simple relative timers that generate an event after a	759	Timer watchers are simple relative timers that generate an event after a
426	given time, and optionally repeating in regular intervals after that.	760	given time, and optionally repeating in regular intervals after that.
427		761
428	The timers are based on real time, that is, if you register an event that	762	The timers are based on real time, that is, if you register an event that
429	times out after an hour and youreset your system clock to last years	763	times out after an hour and you reset your system clock to last years
430	time, it will still time out after (roughly) and hour. "Roughly" because	764	time, it will still time out after (roughly) and hour. "Roughly" because
431	detecting time jumps is hard, and soem inaccuracies are unavoidable (the	765	detecting time jumps is hard, and some inaccuracies are unavoidable (the
432	monotonic clock option helps a lot here).	766	monotonic clock option helps a lot here).
		767
		768	The relative timeouts are calculated relative to the C<ev_now ()>
		769	time. This is usually the right thing as this timestamp refers to the time
		770	of the event triggering whatever timeout you are modifying/starting. If
		771	you suspect event processing to be delayed and you I<need> to base the timeout
		772	on the current time, use something like this to adjust for this:
		773
		774	ev_timer_set (&timer, after + ev_now () - ev_time (), 0.);
		775
		776	The callback is guarenteed to be invoked only when its timeout has passed,
		777	but if multiple timers become ready during the same loop iteration then
		778	order of execution is undefined.
433		779
434	=over 4	780	=over 4
435		781
436	=item ev_timer_init (ev_timer *, callback, ev_tstamp after, ev_tstamp repeat)	782	=item ev_timer_init (ev_timer *, callback, ev_tstamp after, ev_tstamp repeat)
437		783
…		…
443	later, again, and again, until stopped manually.	789	later, again, and again, until stopped manually.
444		790
445	The timer itself will do a best-effort at avoiding drift, that is, if you	791	The timer itself will do a best-effort at avoiding drift, that is, if you
446	configure a timer to trigger every 10 seconds, then it will trigger at	792	configure a timer to trigger every 10 seconds, then it will trigger at
447	exactly 10 second intervals. If, however, your program cannot keep up with	793	exactly 10 second intervals. If, however, your program cannot keep up with
448	the timer (ecause it takes longer than those 10 seconds to do stuff) the	794	the timer (because it takes longer than those 10 seconds to do stuff) the
449	timer will not fire more than once per event loop iteration.	795	timer will not fire more than once per event loop iteration.
450		796
451	=item ev_timer_again (loop)	797	=item ev_timer_again (loop)
452		798
453	This will act as if the timer timed out and restart it again if it is	799	This will act as if the timer timed out and restart it again if it is
…		…
460		806
461	This sounds a bit complicated, but here is a useful and typical	807	This sounds a bit complicated, but here is a useful and typical
462	example: Imagine you have a tcp connection and you want a so-called idle	808	example: Imagine you have a tcp connection and you want a so-called idle
463	timeout, that is, you want to be called when there have been, say, 60	809	timeout, that is, you want to be called when there have been, say, 60
464	seconds of inactivity on the socket. The easiest way to do this is to	810	seconds of inactivity on the socket. The easiest way to do this is to
465	configure an ev_timer with after=repeat=60 and calling ev_timer_again each	811	configure an C<ev_timer> with after=repeat=60 and calling ev_timer_again each
466	time you successfully read or write some data. If you go into an idle	812	time you successfully read or write some data. If you go into an idle
467	state where you do not expect data to travel on the socket, you can stop	813	state where you do not expect data to travel on the socket, you can stop
468	the timer, and again will automatically restart it if need be.	814	the timer, and again will automatically restart it if need be.
469		815
470	=back	816	=back
471		817
472	=head2 ev_periodic	818	Example: create a timer that fires after 60 seconds.
		819
		820	static void
		821	one_minute_cb (struct ev_loop loop, struct ev_timer w, int revents)
		822	{
		823	.. one minute over, w is actually stopped right here
		824	}
		825
		826	struct ev_timer mytimer;
		827	ev_timer_init (&mytimer, one_minute_cb, 60., 0.);
		828	ev_timer_start (loop, &mytimer);
		829
		830	Example: create a timeout timer that times out after 10 seconds of
		831	inactivity.
		832
		833	static void
		834	timeout_cb (struct ev_loop loop, struct ev_timer w, int revents)
		835	{
		836	.. ten seconds without any activity
		837	}
		838
		839	struct ev_timer mytimer;
		840	ev_timer_init (&mytimer, timeout_cb, 0., 10.); /* note, only repeat used */
		841	ev_timer_again (&mytimer); /* start timer */
		842	ev_loop (loop, 0);
		843
		844	// and in some piece of code that gets executed on any "activity":
		845	// reset the timeout to start ticking again at 10 seconds
		846	ev_timer_again (&mytimer);
		847
		848
		849	=head2 C<ev_periodic> - to cron or not to cron
473		850
474	Periodic watchers are also timers of a kind, but they are very versatile	851	Periodic watchers are also timers of a kind, but they are very versatile
475	(and unfortunately a bit complex).	852	(and unfortunately a bit complex).
476		853
477	Unlike ev_timer's, they are not based on real time (or relative time)	854	Unlike C<ev_timer>'s, they are not based on real time (or relative time)
478	but on wallclock time (absolute time). You can tell a periodic watcher	855	but on wallclock time (absolute time). You can tell a periodic watcher
479	to trigger "at" some specific point in time. For example, if you tell a	856	to trigger "at" some specific point in time. For example, if you tell a
480	periodic watcher to trigger in 10 seconds (by specifiying e.g. c<ev_now ()	857	periodic watcher to trigger in 10 seconds (by specifiying e.g. c<ev_now ()
481	+ 10.>) and then reset your system clock to the last year, then it will	858	+ 10.>) and then reset your system clock to the last year, then it will
482	take a year to trigger the event (unlike an ev_timer, which would trigger	859	take a year to trigger the event (unlike an C<ev_timer>, which would trigger
483	roughly 10 seconds later and of course not if you reset your system time	860	roughly 10 seconds later and of course not if you reset your system time
484	again).	861	again).
485		862
486	They can also be used to implement vastly more complex timers, such as	863	They can also be used to implement vastly more complex timers, such as
487	triggering an event on eahc midnight, local time.	864	triggering an event on eahc midnight, local time.
488		865
		866	As with timers, the callback is guarenteed to be invoked only when the
		867	time (C<at>) has been passed, but if multiple periodic timers become ready
		868	during the same loop iteration then order of execution is undefined.
		869
489	=over 4	870	=over 4
490		871
491	=item ev_periodic_init (ev_periodic *, callback, ev_tstamp at, ev_tstamp interval, reschedule_cb)	872	=item ev_periodic_init (ev_periodic *, callback, ev_tstamp at, ev_tstamp interval, reschedule_cb)
492		873
493	=item ev_periodic_set (ev_periodic *, ev_tstamp after, ev_tstamp repeat, reschedule_cb)	874	=item ev_periodic_set (ev_periodic *, ev_tstamp after, ev_tstamp repeat, reschedule_cb)
494		875
495	Lots of arguments, lets sort it out... There are basically three modes of	876	Lots of arguments, lets sort it out... There are basically three modes of
496	operation, and we will explain them from simplest to complex:	877	operation, and we will explain them from simplest to complex:
497
498		878
499	=over 4	879	=over 4
500		880
501	=item * absolute timer (interval = reschedule_cb = 0)	881	=item * absolute timer (interval = reschedule_cb = 0)
502		882
…		…
516		896
517	ev_periodic_set (&periodic, 0., 3600., 0);	897	ev_periodic_set (&periodic, 0., 3600., 0);
518		898
519	This doesn't mean there will always be 3600 seconds in between triggers,	899	This doesn't mean there will always be 3600 seconds in between triggers,
520	but only that the the callback will be called when the system time shows a	900	but only that the the callback will be called when the system time shows a
521	full hour (UTC), or more correct, when the system time is evenly divisible	901	full hour (UTC), or more correctly, when the system time is evenly divisible
522	by 3600.	902	by 3600.
523		903
524	Another way to think about it (for the mathematically inclined) is that	904	Another way to think about it (for the mathematically inclined) is that
525	ev_periodic will try to run the callback in this mode at the next possible	905	C<ev_periodic> will try to run the callback in this mode at the next possible
526	time where C<time = at (mod interval)>, regardless of any time jumps.	906	time where C<time = at (mod interval)>, regardless of any time jumps.
527		907
528	=item * manual reschedule mode (reschedule_cb = callback)	908	=item * manual reschedule mode (reschedule_cb = callback)
529		909
530	In this mode the values for C<interval> and C<at> are both being	910	In this mode the values for C<interval> and C<at> are both being
531	ignored. Instead, each time the periodic watcher gets scheduled, the	911	ignored. Instead, each time the periodic watcher gets scheduled, the
532	reschedule callback will be called with the watcher as first, and the	912	reschedule callback will be called with the watcher as first, and the
533	current time as second argument.	913	current time as second argument.
534		914
535	NOTE: I<This callback MUST NOT stop or destroy the periodic or any other	915	NOTE: I<This callback MUST NOT stop or destroy any periodic watcher,
536	periodic watcher, ever, or make any event loop modificstions>. If you need	916	ever, or make any event loop modifications>. If you need to stop it,
537	to stop it, return 1e30 (or so, fudge fudge) and stop it afterwards.	917	return C<now + 1e30> (or so, fudge fudge) and stop it afterwards (e.g. by
		918	starting a prepare watcher).
538		919
539	Its prototype is c<ev_tstamp (reschedule_cb)(struct ev_periodic w,	920	Its prototype is C<ev_tstamp (reschedule_cb)(struct ev_periodic w,
540	ev_tstamp now)>, e.g.:	921	ev_tstamp now)>, e.g.:
541		922
542	static ev_tstamp my_rescheduler (struct ev_periodic *w, ev_tstamp now)	923	static ev_tstamp my_rescheduler (struct ev_periodic *w, ev_tstamp now)
543	{	924	{
544	return now + 60.;	925	return now + 60.;
…		…
547	It must return the next time to trigger, based on the passed time value	928	It must return the next time to trigger, based on the passed time value
548	(that is, the lowest time value larger than to the second argument). It	929	(that is, the lowest time value larger than to the second argument). It
549	will usually be called just before the callback will be triggered, but	930	will usually be called just before the callback will be triggered, but
550	might be called at other times, too.	931	might be called at other times, too.
551		932
		933	NOTE: I<< This callback must always return a time that is later than the
		934	passed C<now> value >>. Not even C<now> itself will do, it I<must> be larger.
		935
552	This can be used to create very complex timers, such as a timer that	936	This can be used to create very complex timers, such as a timer that
553	triggers on each midnight, local time. To do this, you would calculate the	937	triggers on each midnight, local time. To do this, you would calculate the
554	next midnight after C<now> and return the timestamp value for this. How you do this	938	next midnight after C<now> and return the timestamp value for this. How
555	is, again, up to you (but it is not trivial).	939	you do this is, again, up to you (but it is not trivial, which is the main
		940	reason I omitted it as an example).
556		941
557	=back	942	=back
558		943
559	=item ev_periodic_again (loop, ev_periodic *)	944	=item ev_periodic_again (loop, ev_periodic *)
560		945
…		…
563	a different time than the last time it was called (e.g. in a crond like	948	a different time than the last time it was called (e.g. in a crond like
564	program when the crontabs have changed).	949	program when the crontabs have changed).
565		950
566	=back	951	=back
567		952
		953	Example: call a callback every hour, or, more precisely, whenever the
		954	system clock is divisible by 3600. The callback invocation times have
		955	potentially a lot of jittering, but good long-term stability.
		956
		957	static void
		958	clock_cb (struct ev_loop loop, struct ev_io w, int revents)
		959	{
		960	... its now a full hour (UTC, or TAI or whatever your clock follows)
		961	}
		962
		963	struct ev_periodic hourly_tick;
		964	ev_periodic_init (&hourly_tick, clock_cb, 0., 3600., 0);
		965	ev_periodic_start (loop, &hourly_tick);
		966
		967	Example: the same as above, but use a reschedule callback to do it:
		968
		969	#include <math.h>
		970
		971	static ev_tstamp
		972	my_scheduler_cb (struct ev_periodic *w, ev_tstamp now)
		973	{
		974	return fmod (now, 3600.) + 3600.;
		975	}
		976
		977	ev_periodic_init (&hourly_tick, clock_cb, 0., 0., my_scheduler_cb);
		978
		979	Example: call a callback every hour, starting now:
		980
		981	struct ev_periodic hourly_tick;
		982	ev_periodic_init (&hourly_tick, clock_cb,
		983	fmod (ev_now (loop), 3600.), 3600., 0);
		984	ev_periodic_start (loop, &hourly_tick);
		985
		986
568	=head2 ev_signal - signal me when a signal gets signalled	987	=head2 C<ev_signal> - signal me when a signal gets signalled
569		988
570	Signal watchers will trigger an event when the process receives a specific	989	Signal watchers will trigger an event when the process receives a specific
571	signal one or more times. Even though signals are very asynchronous, libev	990	signal one or more times. Even though signals are very asynchronous, libev
572	will try its best to deliver signals synchronously, i.e. as part of the	991	will try it's best to deliver signals synchronously, i.e. as part of the
573	normal event processing, like any other event.	992	normal event processing, like any other event.
574		993
575	You cna configure as many watchers as you like per signal. Only when the	994	You can configure as many watchers as you like per signal. Only when the
576	first watcher gets started will libev actually register a signal watcher	995	first watcher gets started will libev actually register a signal watcher
577	with the kernel (thus it coexists with your own signal handlers as long	996	with the kernel (thus it coexists with your own signal handlers as long
578	as you don't register any with libev). Similarly, when the last signal	997	as you don't register any with libev). Similarly, when the last signal
579	watcher for a signal is stopped libev will reset the signal handler to	998	watcher for a signal is stopped libev will reset the signal handler to
580	SIG_DFL (regardless of what it was set to before).	999	SIG_DFL (regardless of what it was set to before).
…		…
588	Configures the watcher to trigger on the given signal number (usually one	1007	Configures the watcher to trigger on the given signal number (usually one
589	of the C<SIGxxx> constants).	1008	of the C<SIGxxx> constants).
590		1009
591	=back	1010	=back
592		1011
		1012
593	=head2 ev_child - wait for pid status changes	1013	=head2 C<ev_child> - wait for pid status changes
594		1014
595	Child watchers trigger when your process receives a SIGCHLD in response to	1015	Child watchers trigger when your process receives a SIGCHLD in response to
596	some child status changes (most typically when a child of yours dies).	1016	some child status changes (most typically when a child of yours dies).
597		1017
598	=over 4	1018	=over 4
…		…
602	=item ev_child_set (ev_child *, int pid)	1022	=item ev_child_set (ev_child *, int pid)
603		1023
604	Configures the watcher to wait for status changes of process C<pid> (or	1024	Configures the watcher to wait for status changes of process C<pid> (or
605	I<any> process if C<pid> is specified as C<0>). The callback can look	1025	I<any> process if C<pid> is specified as C<0>). The callback can look
606	at the C<rstatus> member of the C<ev_child> watcher structure to see	1026	at the C<rstatus> member of the C<ev_child> watcher structure to see
607	the status word (use the macros from C<sys/wait.h>). The C<rpid> member	1027	the status word (use the macros from C<sys/wait.h> and see your systems
608	contains the pid of the process causing the status change.	1028	C<waitpid> documentation). The C<rpid> member contains the pid of the
		1029	process causing the status change.
609		1030
610	=back	1031	=back
611		1032
		1033	Example: try to exit cleanly on SIGINT and SIGTERM.
		1034
		1035	static void
		1036	sigint_cb (struct ev_loop loop, struct ev_signal w, int revents)
		1037	{
		1038	ev_unloop (loop, EVUNLOOP_ALL);
		1039	}
		1040
		1041	struct ev_signal signal_watcher;
		1042	ev_signal_init (&signal_watcher, sigint_cb, SIGINT);
		1043	ev_signal_start (loop, &sigint_cb);
		1044
		1045
612	=head2 ev_idle - when you've got nothing better to do	1046	=head2 C<ev_idle> - when you've got nothing better to do
613		1047
614	Idle watchers trigger events when there are no other I/O or timer (or	1048	Idle watchers trigger events when there are no other events are pending
615	periodic) events pending. That is, as long as your process is busy	1049	(prepare, check and other idle watchers do not count). That is, as long
616	handling sockets or timeouts it will not be called. But when your process	1050	as your process is busy handling sockets or timeouts (or even signals,
617	is idle all idle watchers are being called again and again - until	1051	imagine) it will not be triggered. But when your process is idle all idle
		1052	watchers are being called again and again, once per event loop iteration -
618	stopped, that is, or your process receives more events.	1053	until stopped, that is, or your process receives more events and becomes
		1054	busy.
619		1055
620	The most noteworthy effect is that as long as any idle watchers are	1056	The most noteworthy effect is that as long as any idle watchers are
621	active, the process will not block when waiting for new events.	1057	active, the process will not block when waiting for new events.
622		1058
623	Apart from keeping your process non-blocking (which is a useful	1059	Apart from keeping your process non-blocking (which is a useful
…		…
633	kind. There is a C<ev_idle_set> macro, but using it is utterly pointless,	1069	kind. There is a C<ev_idle_set> macro, but using it is utterly pointless,
634	believe me.	1070	believe me.
635		1071
636	=back	1072	=back
637		1073
638	=head2 prepare and check - your hooks into the event loop	1074	Example: dynamically allocate an C<ev_idle>, start it, and in the
		1075	callback, free it. Alos, use no error checking, as usual.
639		1076
		1077	static void
		1078	idle_cb (struct ev_loop loop, struct ev_idle w, int revents)
		1079	{
		1080	free (w);
		1081	// now do something you wanted to do when the program has
		1082	// no longer asnything immediate to do.
		1083	}
		1084
		1085	struct ev_idle *idle_watcher = malloc (sizeof (struct ev_idle));
		1086	ev_idle_init (idle_watcher, idle_cb);
		1087	ev_idle_start (loop, idle_cb);
		1088
		1089
		1090	=head2 C<ev_prepare> and C<ev_check> - customise your event loop
		1091
640	Prepare and check watchers usually (but not always) are used in	1092	Prepare and check watchers are usually (but not always) used in tandem:
641	tandom. Prepare watchers get invoked before the process blocks and check	1093	prepare watchers get invoked before the process blocks and check watchers
642	watchers afterwards.	1094	afterwards.
643		1095
644	Their main purpose is to integrate other event mechanisms into libev. This	1096	Their main purpose is to integrate other event mechanisms into libev and
645	could be used, for example, to track variable changes, implement your own	1097	their use is somewhat advanced. This could be used, for example, to track
646	watchers, integrate net-snmp or a coroutine library and lots more.	1098	variable changes, implement your own watchers, integrate net-snmp or a
		1099	coroutine library and lots more.
647		1100
648	This is done by examining in each prepare call which file descriptors need	1101	This is done by examining in each prepare call which file descriptors need
649	to be watched by the other library, registering ev_io watchers for them	1102	to be watched by the other library, registering C<ev_io> watchers for
650	and starting an ev_timer watcher for any timeouts (many libraries provide	1103	them and starting an C<ev_timer> watcher for any timeouts (many libraries
651	just this functionality). Then, in the check watcher you check for any	1104	provide just this functionality). Then, in the check watcher you check for
652	events that occured (by making your callbacks set soem flags for example)	1105	any events that occured (by checking the pending status of all watchers
653	and call back into the library.	1106	and stopping them) and call back into the library. The I/O and timer
		1107	callbacks will never actually be called (but must be valid nevertheless,
		1108	because you never know, you know?).
654		1109
655	As another example, the perl Coro module uses these hooks to integrate	1110	As another example, the Perl Coro module uses these hooks to integrate
656	coroutines into libev programs, by yielding to other active coroutines	1111	coroutines into libev programs, by yielding to other active coroutines
657	during each prepare and only letting the process block if no coroutines	1112	during each prepare and only letting the process block if no coroutines
658	are ready to run.	1113	are ready to run (it's actually more complicated: it only runs coroutines
		1114	with priority higher than or equal to the event loop and one coroutine
		1115	of lower priority, but only once, using idle watchers to keep the event
		1116	loop from blocking if lower-priority coroutines are active, thus mapping
		1117	low-priority coroutines to idle/background tasks).
659		1118
660	=over 4	1119	=over 4
661		1120
662	=item ev_prepare_init (ev_prepare *, callback)	1121	=item ev_prepare_init (ev_prepare *, callback)
663		1122
664	=item ev_check_init (ev_check *, callback)	1123	=item ev_check_init (ev_check *, callback)
665		1124
666	Initialises and configures the prepare or check watcher - they have no	1125	Initialises and configures the prepare or check watcher - they have no
667	parameters of any kind. There are C<ev_prepare_set> and C<ev_check_set>	1126	parameters of any kind. There are C<ev_prepare_set> and C<ev_check_set>
668	macros, but using them is utterly, utterly pointless.	1127	macros, but using them is utterly, utterly and completely pointless.
669		1128
670	=back	1129	=back
		1130
		1131	Example: TODO.
		1132
		1133
		1134	=head2 C<ev_embed> - when one backend isn't enough
		1135
		1136	This is a rather advanced watcher type that lets you embed one event loop
		1137	into another (currently only C<ev_io> events are supported in the embedded
		1138	loop, other types of watchers might be handled in a delayed or incorrect
		1139	fashion and must not be used).
		1140
		1141	There are primarily two reasons you would want that: work around bugs and
		1142	prioritise I/O.
		1143
		1144	As an example for a bug workaround, the kqueue backend might only support
		1145	sockets on some platform, so it is unusable as generic backend, but you
		1146	still want to make use of it because you have many sockets and it scales
		1147	so nicely. In this case, you would create a kqueue-based loop and embed it
		1148	into your default loop (which might use e.g. poll). Overall operation will
		1149	be a bit slower because first libev has to poll and then call kevent, but
		1150	at least you can use both at what they are best.
		1151
		1152	As for prioritising I/O: rarely you have the case where some fds have
		1153	to be watched and handled very quickly (with low latency), and even
		1154	priorities and idle watchers might have too much overhead. In this case
		1155	you would put all the high priority stuff in one loop and all the rest in
		1156	a second one, and embed the second one in the first.
		1157
		1158	As long as the watcher is active, the callback will be invoked every time
		1159	there might be events pending in the embedded loop. The callback must then
		1160	call C<ev_embed_sweep (mainloop, watcher)> to make a single sweep and invoke
		1161	their callbacks (you could also start an idle watcher to give the embedded
		1162	loop strictly lower priority for example). You can also set the callback
		1163	to C<0>, in which case the embed watcher will automatically execute the
		1164	embedded loop sweep.
		1165
		1166	As long as the watcher is started it will automatically handle events. The
		1167	callback will be invoked whenever some events have been handled. You can
		1168	set the callback to C<0> to avoid having to specify one if you are not
		1169	interested in that.
		1170
		1171	Also, there have not currently been made special provisions for forking:
		1172	when you fork, you not only have to call C<ev_loop_fork> on both loops,
		1173	but you will also have to stop and restart any C<ev_embed> watchers
		1174	yourself.
		1175
		1176	Unfortunately, not all backends are embeddable, only the ones returned by
		1177	C<ev_embeddable_backends> are, which, unfortunately, does not include any
		1178	portable one.
		1179
		1180	So when you want to use this feature you will always have to be prepared
		1181	that you cannot get an embeddable loop. The recommended way to get around
		1182	this is to have a separate variables for your embeddable loop, try to
		1183	create it, and if that fails, use the normal loop for everything:
		1184
		1185	struct ev_loop *loop_hi = ev_default_init (0);
		1186	struct ev_loop *loop_lo = 0;
		1187	struct ev_embed embed;
		1188
		1189	// see if there is a chance of getting one that works
		1190	// (remember that a flags value of 0 means autodetection)
		1191	loop_lo = ev_embeddable_backends () & ev_recommended_backends ()
		1192	? ev_loop_new (ev_embeddable_backends () & ev_recommended_backends ())
		1193	: 0;
		1194
		1195	// if we got one, then embed it, otherwise default to loop_hi
		1196	if (loop_lo)
		1197	{
		1198	ev_embed_init (&embed, 0, loop_lo);
		1199	ev_embed_start (loop_hi, &embed);
		1200	}
		1201	else
		1202	loop_lo = loop_hi;
		1203
		1204	=over 4
		1205
		1206	=item ev_embed_init (ev_embed , callback, struct ev_loop embedded_loop)
		1207
		1208	=item ev_embed_set (ev_embed , callback, struct ev_loop embedded_loop)
		1209
		1210	Configures the watcher to embed the given loop, which must be
		1211	embeddable. If the callback is C<0>, then C<ev_embed_sweep> will be
		1212	invoked automatically, otherwise it is the responsibility of the callback
		1213	to invoke it (it will continue to be called until the sweep has been done,
		1214	if you do not want thta, you need to temporarily stop the embed watcher).
		1215
		1216	=item ev_embed_sweep (loop, ev_embed *)
		1217
		1218	Make a single, non-blocking sweep over the embedded loop. This works
		1219	similarly to C<ev_loop (embedded_loop, EVLOOP_NONBLOCK)>, but in the most
		1220	apropriate way for embedded loops.
		1221
		1222	=back
		1223
671		1224
672	=head1 OTHER FUNCTIONS	1225	=head1 OTHER FUNCTIONS
673		1226
674	There are some other fucntions of possible interest. Described. Here. Now.	1227	There are some other functions of possible interest. Described. Here. Now.
675		1228
676	=over 4	1229	=over 4
677		1230
678	=item ev_once (loop, int fd, int events, ev_tstamp timeout, callback)	1231	=item ev_once (loop, int fd, int events, ev_tstamp timeout, callback)
679		1232
680	This function combines a simple timer and an I/O watcher, calls your	1233	This function combines a simple timer and an I/O watcher, calls your
681	callback on whichever event happens first and automatically stop both	1234	callback on whichever event happens first and automatically stop both
682	watchers. This is useful if you want to wait for a single event on an fd	1235	watchers. This is useful if you want to wait for a single event on an fd
683	or timeout without havign to allocate/configure/start/stop/free one or	1236	or timeout without having to allocate/configure/start/stop/free one or
684	more watchers yourself.	1237	more watchers yourself.
685		1238
686	If C<fd> is less than 0, then no I/O watcher will be started and events is	1239	If C<fd> is less than 0, then no I/O watcher will be started and events
687	ignored. Otherwise, an ev_io watcher for the given C<fd> and C<events> set	1240	is being ignored. Otherwise, an C<ev_io> watcher for the given C<fd> and
688	will be craeted and started.	1241	C<events> set will be craeted and started.
689		1242
690	If C<timeout> is less than 0, then no timeout watcher will be	1243	If C<timeout> is less than 0, then no timeout watcher will be
691	started. Otherwise an ev_timer watcher with after = C<timeout> (and repeat	1244	started. Otherwise an C<ev_timer> watcher with after = C<timeout> (and
692	= 0) will be started.	1245	repeat = 0) will be started. While C<0> is a valid timeout, it is of
		1246	dubious value.
693		1247
694	The callback has the type C<void (cb)(int revents, void arg)> and	1248	The callback has the type C<void (cb)(int revents, void arg)> and gets
695	gets passed an events set (normally a combination of EV_ERROR, EV_READ,	1249	passed an C<revents> set like normal event callbacks (a combination of
696	EV_WRITE or EV_TIMEOUT) and the C<arg> value passed to C<ev_once>:	1250	C<EV_ERROR>, C<EV_READ>, C<EV_WRITE> or C<EV_TIMEOUT>) and the C<arg>
		1251	value passed to C<ev_once>:
697		1252
698	static void stdin_ready (int revents, void *arg)	1253	static void stdin_ready (int revents, void *arg)
699	{	1254	{
700	if (revents & EV_TIMEOUT)	1255	if (revents & EV_TIMEOUT)
701	/* doh, nothing entered */	1256	/* doh, nothing entered */;
702	else if (revents & EV_READ)	1257	else if (revents & EV_READ)
703	/* stdin might have data for us, joy! */	1258	/* stdin might have data for us, joy! */;
704	}	1259	}
705		1260
706	ev_once (STDIN_FILENO, EV_READm 10., stdin_ready, 0);	1261	ev_once (STDIN_FILENO, EV_READ, 10., stdin_ready, 0);
707		1262
708	=item ev_feed_event (loop, watcher, int events)	1263	=item ev_feed_event (ev_loop , watcher , int revents)
709		1264
710	Feeds the given event set into the event loop, as if the specified event	1265	Feeds the given event set into the event loop, as if the specified event
711	has happened for the specified watcher (which must be a pointer to an	1266	had happened for the specified watcher (which must be a pointer to an
712	initialised but not necessarily active event watcher).	1267	initialised but not necessarily started event watcher).
713		1268
714	=item ev_feed_fd_event (loop, int fd, int revents)	1269	=item ev_feed_fd_event (ev_loop *, int fd, int revents)
715		1270
716	Feed an event on the given fd, as if a file descriptor backend detected it.	1271	Feed an event on the given fd, as if a file descriptor backend detected
		1272	the given events it.
717		1273
718	=item ev_feed_signal_event (loop, int signum)	1274	=item ev_feed_signal_event (ev_loop *loop, int signum)
719		1275
720	Feed an event as if the given signal occured (loop must be the default loop!).	1276	Feed an event as if the given signal occured (C<loop> must be the default
		1277	loop!).
721		1278
722	=back	1279	=back
		1280
		1281
		1282	=head1 LIBEVENT EMULATION
		1283
		1284	Libev offers a compatibility emulation layer for libevent. It cannot
		1285	emulate the internals of libevent, so here are some usage hints:
		1286
		1287	=over 4
		1288
		1289	=item * Use it by including <event.h>, as usual.
		1290
		1291	=item * The following members are fully supported: ev_base, ev_callback,
		1292	ev_arg, ev_fd, ev_res, ev_events.
		1293
		1294	=item * Avoid using ev_flags and the EVLIST_*-macros, while it is
		1295	maintained by libev, it does not work exactly the same way as in libevent (consider
		1296	it a private API).
		1297
		1298	=item * Priorities are not currently supported. Initialising priorities
		1299	will fail and all watchers will have the same priority, even though there
		1300	is an ev_pri field.
		1301
		1302	=item * Other members are not supported.
		1303
		1304	=item * The libev emulation is I<not> ABI compatible to libevent, you need
		1305	to use the libev header file and library.
		1306
		1307	=back
		1308
		1309	=head1 C++ SUPPORT
		1310
		1311	TBD.
723		1312
724	=head1 AUTHOR	1313	=head1 AUTHOR
725		1314
726	Marc Lehmann <libev@schmorp.de>.	1315	Marc Lehmann <libev@schmorp.de>.
727		1316

Diff Legend

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

Comparing libev/ev.pod (file contents): Revision 1.2 by root, Mon Nov 12 08:02:55 2007 UTC vs. Revision 1.36 by root, Sat Nov 24 07:14:26 2007 UTC

Diff Legend

Comparing libev/ev.pod (file contents):
Revision 1.2 by root, Mon Nov 12 08:02:55 2007 UTC vs.
Revision 1.36 by root, Sat Nov 24 07:14:26 2007 UTC