--- libev/ev.pod	2007/12/07 20:19:16	1.72
+++ libev/ev.pod	2008/05/21 12:51:38	1.158
@@ -6,56 +6,70 @@
 
   #include <ev.h>
 
-=head1 EXAMPLE PROGRAM
+=head2 EXAMPLE PROGRAM
 
+  // a single header file is required
   #include <ev.h>
 
+  // every watcher type has its own typedef'd struct
+  // with the name ev_<type>
   ev_io stdin_watcher;
   ev_timer timeout_watcher;
 
-  /* called when data readable on stdin */
+  // all watcher callbacks have a similar signature
+  // this callback is called when data is readable on stdin
   static void
   stdin_cb (EV_P_ struct ev_io *w, int revents)
   {
-    /* puts ("stdin ready"); */
-    ev_io_stop (EV_A_ w); /* just a syntax example */
-    ev_unloop (EV_A_ EVUNLOOP_ALL); /* leave all loop calls */
+    puts ("stdin ready");
+    // for one-shot events, one must manually stop the watcher
+    // with its corresponding stop function.
+    ev_io_stop (EV_A_ w);
+
+    // this causes all nested ev_loop's to stop iterating
+    ev_unloop (EV_A_ EVUNLOOP_ALL);
   }
 
+  // another callback, this time for a time-out
   static void
   timeout_cb (EV_P_ struct ev_timer *w, int revents)
   {
-    /* puts ("timeout"); */
-    ev_unloop (EV_A_ EVUNLOOP_ONE); /* leave one loop call */
+    puts ("timeout");
+    // this causes the innermost ev_loop to stop iterating
+    ev_unloop (EV_A_ EVUNLOOP_ONE);
   }
 
   int
   main (void)
   {
+    // use the default event loop unless you have special needs
     struct ev_loop *loop = ev_default_loop (0);
 
-    /* initialise an io watcher, then start it */
+    // initialise an io watcher, then start it
+    // this one will watch for stdin to become readable
     ev_io_init (&stdin_watcher, stdin_cb, /*STDIN_FILENO*/ 0, EV_READ);
     ev_io_start (loop, &stdin_watcher);
 
-    /* simple non-repeating 5.5 second timeout */
+    // initialise a timer watcher, then start it
+    // simple non-repeating 5.5 second timeout
     ev_timer_init (&timeout_watcher, timeout_cb, 5.5, 0.);
     ev_timer_start (loop, &timeout_watcher);
 
-    /* loop till timeout or data ready */
+    // now wait for events to arrive
     ev_loop (loop, 0);
 
+    // unloop was called, so exit
     return 0;
   }
 
 =head1 DESCRIPTION
 
-The newest version of this document is also available as a html-formatted
+The newest version of this document is also available as an html-formatted
 web page you might find easier to navigate when reading it for the first
-time: L<http://cvs.schmorp.de/libev/ev.html>.
+time: L<http://pod.tst.eu/http://cvs.schmorp.de/libev/ev.pod>.
 
 Libev is an event loop: you register interest in certain events (such as a
-file descriptor being readable or a timeout occuring), and it will manage
+file descriptor being readable or a timeout occurring), and it will manage
 these event sources and provide your program with events.
 
 To do this, it must take more or less complete control over your process
@@ -67,7 +81,7 @@
 details of the event, and then hand it over to libev by I<starting> the
 watcher.
 
-=head1 FEATURES
+=head2 FEATURES
 
 Libev supports C<select>, C<poll>, the Linux-specific C<epoll>, the
 BSD-specific C<kqueue> and the Solaris-specific event port mechanisms
@@ -84,23 +98,26 @@
 L<benchmark|http://libev.schmorp.de/bench.html> comparing it to libevent
 for example).
 
-=head1 CONVENTIONS
+=head2 CONVENTIONS
 
-Libev is very configurable. In this manual the default configuration will
-be described, which supports multiple event loops. For more info about
-various configuration options please have a look at B<EMBED> section in
-this manual. If libev was configured without support for multiple event
-loops, then all functions taking an initial argument of name C<loop>
-(which is always of type C<struct ev_loop *>) will not have this argument.
+Libev is very configurable. In this manual the default (and most common)
+configuration will be described, which supports multiple event loops. For
+more info about various configuration options please have a look at
+B<EMBED> section in this manual. If libev was configured without support
+for multiple event loops, then all functions taking an initial argument of
+name C<loop> (which is always of type C<struct ev_loop *>) will not have
+this argument.
 
-=head1 TIME REPRESENTATION
+=head2 TIME REPRESENTATION
 
 Libev represents time as a single floating point number, representing the
 (fractional) number of seconds since the (POSIX) epoch (somewhere near
 the beginning of 1970, details are complicated, don't ask). This type is
 called C<ev_tstamp>, which is what you should use too. It usually aliases
 to the C<double> type in C, and when you need to do any calculations on
-it, you should treat it as such.
+it, you should treat it as some floatingpoint value. Unlike the name
+component C<stamp> might indicate, it is also used for time differences
+throughout libev.
 
 =head1 GLOBAL FUNCTIONS
 
@@ -115,18 +132,27 @@
 C<ev_now> function is usually faster and also often returns the timestamp
 you actually want to know.
 
+=item ev_sleep (ev_tstamp interval)
+
+Sleep for the given interval: The current thread will be blocked until
+either it is interrupted or the given time interval has passed. Basically
+this is a subsecond-resolution C<sleep ()>.
+
 =item int ev_version_major ()
 
 =item int ev_version_minor ()
 
-You can find out the major and minor version numbers of the library
+You can find out the major and minor ABI version numbers of the library
 you linked against by calling the functions C<ev_version_major> and
 C<ev_version_minor>. If you want, you can compare against the global
 symbols C<EV_VERSION_MAJOR> and C<EV_VERSION_MINOR>, which specify the
 version of the library your program was compiled against.
 
+These version numbers refer to the ABI version of the library, not the
+release version.
+
 Usually, it's a good idea to terminate if the major versions mismatch,
-as this indicates an incompatible change.  Minor versions are usually
+as this indicates an incompatible change. Minor versions are usually
 compatible to older versions, so a larger minor version alone is usually
 not a problem.
 
@@ -172,18 +198,21 @@
 =item ev_set_allocator (void *(*cb)(void *ptr, long size))
 
 Sets the allocation function to use (the prototype is similar - the
-semantics is identical - to the realloc C function). It is used to
-allocate and free memory (no surprises here). If it returns zero when
-memory needs to be allocated, the library might abort or take some
-potentially destructive action. The default is your system realloc
-function.
+semantics are identical to the C<realloc> C89/SuS/POSIX function). It is
+used to allocate and free memory (no surprises here). If it returns zero
+when memory needs to be allocated (C<size != 0>), the library might abort
+or take some potentially destructive action.
+
+Since some systems (at least OpenBSD and Darwin) fail to implement
+correct C<realloc> semantics, libev will use a wrapper around the system
+C<realloc> and C<free> functions by default.
 
 You could override this function in high-availability programs to, say,
 free some memory if it cannot allocate memory, to use a special allocator,
 or even to sleep a while and retry until some memory is available.
 
 Example: Replace the libev allocator with one that waits a bit and then
-retries).
+retries (example requires a standards-compliant C<realloc>).
 
    static void *
    persistent_realloc (void *ptr, size_t size)
@@ -232,13 +261,6 @@
 types of such loops, the I<default> loop, which supports signals and child
 events, and dynamically created loops which do not.
 
-If you use threads, a common model is to run the default event loop
-in your main thread (or in a separate thread) and for each thread you
-create, you also create another event loop. Libev itself does no locking
-whatsoever, so if you mix calls to the same event loop in different
-threads, make sure you lock (this is usually a bad idea, though, even if
-done correctly, because it's hideous and inefficient).
-
 =over 4
 
 =item struct ev_loop *ev_default_loop (unsigned int flags)
@@ -251,6 +273,17 @@
 If you don't know what event loop to use, use the one returned from this
 function.
 
+Note that this function is I<not> thread-safe, so if you want to use it
+from multiple threads, you have to lock (note also that this is unlikely,
+as loops cannot bes hared easily between threads anyway).
+
+The default loop is the only loop that can handle C<ev_signal> and
+C<ev_child> watchers, and to do this, it always registers a handler
+for C<SIGCHLD>. If this is a problem for your app you can either
+create a dynamic loop with C<ev_loop_new> that doesn't do that, or you
+can simply overwrite the C<SIGCHLD> signal handler I<after> calling
+C<ev_default_init>.
+
 The flags argument can be used to specify special behaviour or specific
 backends to use, and is usually specified as C<0> (or C<EVFLAG_AUTO>).
 
@@ -281,8 +314,8 @@
 This works by calling C<getpid ()> on every iteration of the loop,
 and thus this might slow down your event loop if you do a lot of loop
 iterations and little real work, but is usually not noticeable (on my
-Linux system for example, C<getpid> is actually a simple 5-insn sequence
-without a syscall and thus I<very> fast, but my Linux system also has
+GNU/Linux system for example, C<getpid> is actually a simple 5-insn sequence
+without a syscall and thus I<very> fast, but my GNU/Linux system also has
 C<pthread_atfork> which is even faster).
 
 The big advantage of this flag is that you can forget about fork (and
@@ -297,73 +330,120 @@
 This is your standard select(2) backend. Not I<completely> standard, as
 libev tries to roll its own fd_set with no limits on the number of fds,
 but if that fails, expect a fairly low limit on the number of fds when
-using this backend. It doesn't scale too well (O(highest_fd)), but its usually
-the fastest backend for a low number of fds.
+using this backend. It doesn't scale too well (O(highest_fd)), but its
+usually the fastest backend for a low number of (low-numbered :) fds.
+
+To get good performance out of this backend you need a high amount of
+parallelity (most of the file descriptors should be busy). If you are
+writing a server, you should C<accept ()> in a loop to accept as many
+connections as possible during one iteration. You might also want to have
+a look at C<ev_set_io_collect_interval ()> to increase the amount of
+readiness notifications you get per iteration.
 
 =item C<EVBACKEND_POLL>    (value 2, poll backend, available everywhere except on windows)
 
-And this is your standard poll(2) backend. It's more complicated than
-select, but handles sparse fds better and has no artificial limit on the
-number of fds you can use (except it will slow down considerably with a
-lot of inactive fds). It scales similarly to select, i.e. O(total_fds).
+And this is your standard poll(2) backend. It's more complicated
+than select, but handles sparse fds better and has no artificial
+limit on the number of fds you can use (except it will slow down
+considerably with a lot of inactive fds). It scales similarly to select,
+i.e. O(total_fds). See the entry for C<EVBACKEND_SELECT>, above, for
+performance tips.
 
 =item C<EVBACKEND_EPOLL>   (value 4, Linux)
 
 For few fds, this backend is a bit little slower than poll and select,
-but it scales phenomenally better. While poll and select usually scale like
-O(total_fds) where n is the total number of fds (or the highest fd), epoll scales
-either O(1) or O(active_fds).
+but it scales phenomenally better. While poll and select usually scale
+like O(total_fds) where n is the total number of fds (or the highest fd),
+epoll scales either O(1) or O(active_fds). The epoll design has a number
+of shortcomings, such as silently dropping events in some hard-to-detect
+cases and requiring a syscall per fd change, no fork support and bad
+support for dup.
 
-While stopping and starting an I/O watcher in the same iteration will
-result in some caching, there is still a syscall per such incident
+While stopping, setting and starting an I/O watcher in the same iteration
+will result in some caching, there is still a syscall per such incident
 (because the fd could point to a different file description now), so its
-best to avoid that. Also, dup()ed file descriptors might not work very
-well if you register events for both fds.
+best to avoid that. Also, C<dup ()>'ed file descriptors might not work
+very well if you register events for both fds.
 
 Please note that epoll sometimes generates spurious notifications, so you
 need to use non-blocking I/O or other means to avoid blocking when no data
 (or space) is available.
 
+Best performance from this backend is achieved by not unregistering all
+watchers for a file descriptor until it has been closed, if possible, i.e.
+keep at least one watcher active per fd at all times.
+
+While nominally embeddeble in other event loops, this feature is broken in
+all kernel versions tested so far.
+
 =item C<EVBACKEND_KQUEUE>  (value 8, most BSD clones)
 
 Kqueue deserves special mention, as at the time of this writing, it
-was broken on all BSDs except NetBSD (usually it doesn't work with
-anything but sockets and pipes, except on Darwin, where of course its
-completely useless). For this reason its not being "autodetected"
+was broken on all BSDs except NetBSD (usually it doesn't work reliably
+with anything but sockets and pipes, except on Darwin, where of course
+it's completely useless). For this reason it's not being "autodetected"
 unless you explicitly specify it explicitly in the flags (i.e. using
-C<EVBACKEND_KQUEUE>).
+C<EVBACKEND_KQUEUE>) or libev was compiled on a known-to-be-good (-enough)
+system like NetBSD.
+
+You still can embed kqueue into a normal poll or select backend and use it
+only for sockets (after having made sure that sockets work with kqueue on
+the target platform). See C<ev_embed> watchers for more info.
 
 It scales in the same way as the epoll backend, but the interface to the
 kernel is more efficient (which says nothing about its actual speed, of
-course). While starting and stopping an I/O watcher does not cause an
-extra syscall as with epoll, it still adds up to four event changes per
-incident, so its best to avoid that.
+course). While stopping, setting and starting an I/O watcher does never
+cause an extra syscall as with C<EVBACKEND_EPOLL>, it still adds up to
+two event changes per incident, support for C<fork ()> is very bad and it
+drops fds silently in similarly hard-to-detect cases.
+
+This backend usually performs well under most conditions.
+
+While nominally embeddable in other event loops, this doesn't work
+everywhere, so you might need to test for this. And since it is broken
+almost everywhere, you should only use it when you have a lot of sockets
+(for which it usually works), by embedding it into another event loop
+(e.g. C<EVBACKEND_SELECT> or C<EVBACKEND_POLL>) and using it only for
+sockets.
 
 =item C<EVBACKEND_DEVPOLL> (value 16, Solaris 8)
 
-This is not implemented yet (and might never be).
+This is not implemented yet (and might never be, unless you send me an
+implementation). According to reports, C</dev/poll> only supports sockets
+and is not embeddable, which would limit the usefulness of this backend
+immensely.
 
 =item C<EVBACKEND_PORT>    (value 32, Solaris 10)
 
-This uses the Solaris 10 port mechanism. As with everything on Solaris,
+This uses the Solaris 10 event port mechanism. As with everything on Solaris,
 it's really slow, but it still scales very well (O(active_fds)).
 
-Please note that solaris ports can result in a lot of spurious
+Please note that solaris event ports can deliver a lot of spurious
 notifications, so you need to use non-blocking I/O or other means to avoid
 blocking when no data (or space) is available.
 
+While this backend scales well, it requires one system call per active
+file descriptor per loop iteration. For small and medium numbers of file
+descriptors a "slow" C<EVBACKEND_SELECT> or C<EVBACKEND_POLL> backend
+might perform better.
+
+On the positive side, ignoring the spurious readiness notifications, this
+backend actually performed to specification in all tests and is fully
+embeddable, which is a rare feat among the OS-specific backends.
+
 =item C<EVBACKEND_ALL>
 
 Try all backends (even potentially broken ones that wouldn't be tried
 with C<EVFLAG_AUTO>). Since this is a mask, you can do stuff such as
 C<EVBACKEND_ALL & ~EVBACKEND_KQUEUE>.
 
+It is definitely not recommended to use this flag.
+
 =back
 
 If one or more of these are ored into the flags value, then only these
-backends will be tried (in the reverse order as given here). If none are
-specified, most compiled-in backend will be tried, usually in reverse
-order of their flag values :)
+backends will be tried (in the reverse order as listed here). If none are
+specified, all backends in C<ev_recommended_backends ()> will be tried.
 
 The most typical usage is like this:
 
@@ -388,6 +468,10 @@
 handle signal and child watchers, and attempts to do so will be greeted by
 undefined behaviour (or a failed assertion if assertions are enabled).
 
+Note that this function I<is> thread-safe, and the recommended way to use
+libev with threads is indeed to create one loop per thread, and using the
+default loop in the "main" or "initial" thread.
+
 Example: Try to create a event loop that uses epoll and nothing else.
 
   struct ev_loop *epoller = ev_loop_new (EVBACKEND_EPOLL | EVFLAG_NOENV);
@@ -401,9 +485,18 @@
 sense, so e.g. C<ev_is_active> might still return true. It is your
 responsibility to either stop all watchers cleanly yoursef I<before>
 calling this function, or cope with the fact afterwards (which is usually
-the easiest thing, youc na just ignore the watchers and/or C<free ()> them
+the easiest thing, you can just ignore the watchers and/or C<free ()> them
 for example).
 
+Note that certain global state, such as signal state, will not be freed by
+this function, and related watchers (such as signal and child watchers)
+would need to be stopped manually.
+
+In general it is not advisable to call this function except in the
+rare occasion where you really need to free e.g. the signal handling
+pipe fds. If you need dynamically allocated loops it is better to use
+C<ev_loop_new> and C<ev_loop_destroy>).
+
 =item ev_loop_destroy (loop)
 
 Like C<ev_default_destroy>, but destroys an event loop created by an
@@ -411,14 +504,16 @@
 
 =item ev_default_fork ()
 
-This function reinitialises the kernel state for backends that have
-one. Despite the name, you can call it anytime, but it makes most sense
-after forking, in either the parent or child process (or both, but that
-again makes little sense).
-
-You I<must> call this function in the child process after forking if and
-only if you want to use the event library in both processes. If you just
-fork+exec, you don't have to call it.
+This function sets a flag that causes subsequent C<ev_loop> iterations
+to reinitialise the kernel state for backends that have one. Despite the
+name, you can call it anytime, but it makes most sense after forking, in
+the child process (or both child and parent, but that again makes little
+sense). You I<must> call it in the child before using any of the libev
+functions, and it will only take effect at the next C<ev_loop> iteration.
+
+On the other hand, you only need to call this function in the child
+process if and only if you want to use the event library in the child. If
+you just fork+exec, you don't have to call it at all.
 
 The function itself is quite fast and it's usually not a problem to call
 it just in case after a fork. To make this easy, the function will fit in
@@ -426,16 +521,16 @@
 
     pthread_atfork (0, 0, ev_default_fork);
 
-At the moment, C<EVBACKEND_SELECT> and C<EVBACKEND_POLL> are safe to use
-without calling this function, so if you force one of those backends you
-do not need to care.
-
 =item ev_loop_fork (loop)
 
 Like C<ev_default_fork>, but acts on an event loop created by
 C<ev_loop_new>. Yes, you have to call this on every allocated event loop
 after fork, and how you do this is entirely your own problem.
 
+=item int ev_is_default_loop (loop)
+
+Returns true when the given loop actually is the default loop, false otherwise.
+
 =item unsigned int ev_loop_count (loop)
 
 Returns the count of loop iterations for the loop, which is identical to
@@ -457,7 +552,7 @@
 received events and started processing them. This timestamp does not
 change as long as callbacks are being processed, and this is also the base
 time used for relative timers. You can treat it as the timestamp of the
-event occuring (or more correctly, libev finding out about it).
+event occurring (or more correctly, libev finding out about it).
 
 =item ev_loop (loop, int flags)
 
@@ -488,12 +583,17 @@
 
 Here are the gory details of what C<ev_loop> does:
 
-   * If there are no active watchers (reference count is zero), return.
-   - Queue prepare watchers and then call all outstanding watchers.
+   - Before the first iteration, call any pending watchers.
+   * If EVFLAG_FORKCHECK was used, check for a fork.
+   - If a fork was detected, queue and call all fork watchers.
+   - Queue and call all prepare watchers.
    - If we have been forked, recreate the kernel state.
    - Update the kernel state with all outstanding changes.
    - Update the "event loop time".
-   - Calculate for how long to block.
+   - Calculate for how long to sleep or block, if at all
+     (active idle watchers, EVLOOP_NONBLOCK or not having
+     any active watchers at all will result in not sleeping).
+   - Sleep if the I/O and timer collect interval say so.
    - Block the process, waiting for any events.
    - Queue all outstanding I/O (fd) events.
    - Update the "event loop time" and do time jump handling.
@@ -504,10 +604,11 @@
    - Call all queued watchers in reverse order (i.e. check watchers first).
      Signals and child watchers are implemented as I/O watchers, and will
      be handled here by queueing them when their watcher gets executed.
-   - If ev_unloop has been called or EVLOOP_ONESHOT or EVLOOP_NONBLOCK
-     were used, return, otherwise continue with step *.
+   - If ev_unloop has been called, or EVLOOP_ONESHOT or EVLOOP_NONBLOCK
+     were used, or there are no active watchers, return, otherwise
+     continue with step *.
 
-Example: Queue some jobs and then loop until no events are outsanding
+Example: Queue some jobs and then loop until no events are outstanding
 anymore.
 
    ... queue jobs here, make sure they register event watchers as long
@@ -522,6 +623,8 @@
 C<EVUNLOOP_ONE>, which will make the innermost C<ev_loop> call return, or
 C<EVUNLOOP_ALL>, which will make all nested C<ev_loop> calls return.
 
+This "unloop state" will be cleared when entering C<ev_loop> again.
+
 =item ev_ref (loop)
 
 =item ev_unref (loop)
@@ -535,7 +638,9 @@
 visible to the libev user and should not keep C<ev_loop> from exiting if
 no event watchers registered by it are active. It is also an excellent
 way to do this for generic recurring timers or from within third-party
-libraries. Just remember to I<unref after start> and I<ref before stop>.
+libraries. Just remember to I<unref after start> and I<ref before stop>
+(but only if the watcher wasn't active before, or was active before,
+respectively).
 
 Example: Create a signal watcher, but keep it from keeping C<ev_loop>
 running when nothing else is active.
@@ -550,6 +655,42 @@
   ev_ref (loop);
   ev_signal_stop (loop, &exitsig);
 
+=item ev_set_io_collect_interval (loop, ev_tstamp interval)
+
+=item ev_set_timeout_collect_interval (loop, ev_tstamp interval)
+
+These advanced functions influence the time that libev will spend waiting
+for events. Both are by default C<0>, meaning that libev will try to
+invoke timer/periodic callbacks and I/O callbacks with minimum latency.
+
+Setting these to a higher value (the C<interval> I<must> be >= C<0>)
+allows libev to delay invocation of I/O and timer/periodic callbacks to
+increase efficiency of loop iterations.
+
+The background is that sometimes your program runs just fast enough to
+handle one (or very few) event(s) per loop iteration. While this makes
+the program responsive, it also wastes a lot of CPU time to poll for new
+events, especially with backends like C<select ()> which have a high
+overhead for the actual polling but can deliver many events at once.
+
+By setting a higher I<io collect interval> you allow libev to spend more
+time collecting I/O events, so you can handle more events per iteration,
+at the cost of increasing latency. Timeouts (both C<ev_periodic> and
+C<ev_timer>) will be not affected. Setting this to a non-null value will
+introduce an additional C<ev_sleep ()> call into most loop iterations.
+
+Likewise, by setting a higher I<timeout collect interval> you allow libev
+to spend more time collecting timeouts, at the expense of increased
+latency (the watcher callback will be called later). C<ev_io> watchers
+will not be affected. Setting this to a non-null value will not introduce
+any overhead in libev.
+
+Many (busy) programs can usually benefit by setting the io collect
+interval to a value near C<0.1> or so, which is often enough for
+interactive servers (of course not for games), likewise for timeouts. It
+usually doesn't make much sense to set it to a lower value than C<0.01>,
+as this approsaches the timing granularity of most systems.
+
 =back
 
 
@@ -658,6 +799,10 @@
 The event loop has been resumed in the child process after fork (see
 C<ev_fork>).
 
+=item C<EV_ASYNC>
+
+The given async watcher has been asynchronously notified (see C<ev_async>).
+
 =item C<EV_ERROR>
 
 An unspecified error has occured, the watcher has been stopped. This might
@@ -738,8 +883,9 @@
 Returns a true value iff the watcher is pending, (i.e. it has outstanding
 events but its callback has not yet been invoked). As long as a watcher
 is pending (but not active) you must not call an init function on it (but
-C<ev_TYPE_set> is safe) and you must make sure the watcher is available to
-libev (e.g. you cnanot C<free ()> it).
+C<ev_TYPE_set> is safe), you must not change its priority, and you must
+make sure the watcher is available to libev (e.g. you cannot C<free ()>
+it).
 
 =item callback ev_cb (ev_TYPE *watcher)
 
@@ -768,6 +914,9 @@
 If you need to suppress invocation when higher priority events are pending
 you need to look at C<ev_idle> watchers, which provide this functionality.
 
+You I<must not> change the priority of a watcher as long as it is active or
+pending.
+
 The default priority used by watchers when no priority has been set is
 always C<0>, which is supposed to not be too high and not be too low :).
 
@@ -775,6 +924,18 @@
 fine, as long as you do not mind that the priority value you query might
 or might not have been adjusted to be within valid range.
 
+=item ev_invoke (loop, ev_TYPE *watcher, int revents)
+
+Invoke the C<watcher> with the given C<loop> and C<revents>. Neither
+C<loop> nor C<revents> need to be valid as long as the watcher callback
+can deal with that fact.
+
+=item int ev_clear_pending (loop, ev_TYPE *watcher)
+
+If the watcher is pending, this function returns clears its pending status
+and returns its C<revents> bitset (as if its callback was invoked). If the
+watcher isn't pending it does nothing and returns C<0>.
+
 =back
 
 
@@ -868,18 +1029,12 @@
 descriptors to non-blocking mode is also usually a good idea (but not
 required if you know what you are doing).
 
-You have to be careful with dup'ed file descriptors, though. Some backends
-(the linux epoll backend is a notable example) cannot handle dup'ed file
-descriptors correctly if you register interest in two or more fds pointing
-to the same underlying file/socket/etc. description (that is, they share
-the same underlying "file open").
-
 If you must do this, then force the use of a known-to-be-good backend
 (at the time of this writing, this includes only C<EVBACKEND_SELECT> and
 C<EVBACKEND_POLL>).
 
 Another thing you have to watch out for is that it is quite easy to
-receive "spurious" readyness notifications, that is your callback might
+receive "spurious" readiness notifications, that is your callback might
 be called with C<EV_READ> but a subsequent C<read>(2) will actually block
 because there is no data. Not only are some backends known to create a
 lot of those (for example solaris ports), it is very easy to get into
@@ -893,6 +1048,64 @@
 such as poll (fortunately in our Xlib example, Xlib already does this on
 its own, so its quite safe to use).
 
+=head3 The special problem of disappearing file descriptors
+
+Some backends (e.g. kqueue, epoll) need to be told about closing a file
+descriptor (either by calling C<close> explicitly or by any other means,
+such as C<dup>). The reason is that you register interest in some file
+descriptor, but when it goes away, the operating system will silently drop
+this interest. If another file descriptor with the same number then is
+registered with libev, there is no efficient way to see that this is, in
+fact, a different file descriptor.
+
+To avoid having to explicitly tell libev about such cases, libev follows
+the following policy:  Each time C<ev_io_set> is being called, libev
+will assume that this is potentially a new file descriptor, otherwise
+it is assumed that the file descriptor stays the same. That means that
+you I<have> to call C<ev_io_set> (or C<ev_io_init>) when you change the
+descriptor even if the file descriptor number itself did not change.
+
+This is how one would do it normally anyway, the important point is that
+the libev application should not optimise around libev but should leave
+optimisations to libev.
+
+=head3 The special problem of dup'ed file descriptors
+
+Some backends (e.g. epoll), cannot register events for file descriptors,
+but only events for the underlying file descriptions. That means when you
+have C<dup ()>'ed file descriptors or weirder constellations, and register
+events for them, only one file descriptor might actually receive events.
+
+There is no workaround possible except not registering events
+for potentially C<dup ()>'ed file descriptors, or to resort to
+C<EVBACKEND_SELECT> or C<EVBACKEND_POLL>.
+
+=head3 The special problem of fork
+
+Some backends (epoll, kqueue) do not support C<fork ()> at all or exhibit
+useless behaviour. Libev fully supports fork, but needs to be told about
+it in the child.
+
+To support fork in your programs, you either have to call
+C<ev_default_fork ()> or C<ev_loop_fork ()> after a fork in the child,
+enable C<EVFLAG_FORKCHECK>, or resort to C<EVBACKEND_SELECT> or
+C<EVBACKEND_POLL>.
+
+=head3 The special problem of SIGPIPE
+
+While not really specific to libev, it is easy to forget about SIGPIPE:
+when reading from a pipe whose other end has been closed, your program
+gets send a SIGPIPE, which, by default, aborts your program. For most
+programs this is sensible behaviour, for daemons, this is usually
+undesirable.
+
+So when you encounter spurious, unexplained daemon exits, make sure you
+ignore SIGPIPE (and maybe make sure you log the exit status of your daemon
+somewhere, as that would have given you a big clue).
+
+
+=head3 Watcher-Specific Functions
+
 =over 4
 
 =item ev_io_init (ev_io *, callback, int fd, int events)
@@ -913,6 +1126,8 @@
 
 =back
 
+=head3 Examples
+
 Example: Call C<stdin_readable_cb> when STDIN_FILENO has become, well
 readable, but only once. Since it is likely line-buffered, you could
 attempt to read a whole line in the callback.
@@ -938,8 +1153,8 @@
 given time, and optionally repeating in regular intervals after that.
 
 The timers are based on real time, that is, if you register an event that
-times out after an hour and you reset your system clock to last years
-time, it will still time out after (roughly) and hour. "Roughly" because
+times out after an hour and you reset your system clock to january last
+year, it will still time out after (roughly) and hour. "Roughly" because
 detecting time jumps is hard, and some inaccuracies are unavoidable (the
 monotonic clock option helps a lot here).
 
@@ -951,28 +1166,31 @@
 
    ev_timer_set (&timer, after + ev_now () - ev_time (), 0.);
 
-The callback is guarenteed to be invoked only when its timeout has passed,
+The callback is guarenteed to be invoked only after its timeout has passed,
 but if multiple timers become ready during the same loop iteration then
 order of execution is undefined.
 
+=head3 Watcher-Specific Functions and Data Members
+
 =over 4
 
 =item ev_timer_init (ev_timer *, callback, ev_tstamp after, ev_tstamp repeat)
 
 =item ev_timer_set (ev_timer *, ev_tstamp after, ev_tstamp repeat)
 
-Configure the timer to trigger after C<after> seconds. If C<repeat> is
-C<0.>, then it will automatically be stopped. If it is positive, then the
-timer will automatically be configured to trigger again C<repeat> seconds
-later, again, and again, until stopped manually.
-
-The timer itself will do a best-effort at avoiding drift, that is, if you
-configure a timer to trigger every 10 seconds, then it will trigger at
-exactly 10 second intervals. If, however, your program cannot keep up with
-the timer (because it takes longer than those 10 seconds to do stuff) the
-timer will not fire more than once per event loop iteration.
+Configure the timer to trigger after C<after> seconds. If C<repeat>
+is C<0.>, then it will automatically be stopped once the timeout is
+reached. If it is positive, then the timer will automatically be
+configured to trigger again C<repeat> seconds later, again, and again,
+until stopped manually.
+
+The timer itself will do a best-effort at avoiding drift, that is, if
+you configure a timer to trigger every 10 seconds, then it will normally
+trigger at exactly 10 second intervals. If, however, your program cannot
+keep up with the timer (because it takes longer than those 10 seconds to
+do stuff) the timer will not fire more than once per event loop iteration.
 
-=item ev_timer_again (loop)
+=item ev_timer_again (loop, ev_timer *)
 
 This will act as if the timer timed out and restart it again if it is
 repeating. The exact semantics are:
@@ -1017,6 +1235,8 @@
 
 =back
 
+=head3 Examples
+
 Example: Create a timer that fires after 60 seconds.
 
   static void
@@ -1055,20 +1275,23 @@
 
 Unlike C<ev_timer>'s, they are not based on real time (or relative time)
 but on wallclock time (absolute time). You can tell a periodic watcher
-to trigger "at" some specific point in time. For example, if you tell a
+to trigger after some specific point in time. For example, if you tell a
 periodic watcher to trigger in 10 seconds (by specifiying e.g. C<ev_now ()
-+ 10.>) and then reset your system clock to the last year, then it will
-take a year to trigger the event (unlike an C<ev_timer>, which would trigger
-roughly 10 seconds later and of course not if you reset your system time
-again).
-
-They can also be used to implement vastly more complex timers, such as
-triggering an event on eahc midnight, local time.
++ 10.>, that is, an absolute time not a delay) and then reset your system
+clock to january of the previous year, then it will take more than year
+to trigger the event (unlike an C<ev_timer>, which would still trigger
+roughly 10 seconds later as it uses a relative timeout).
+
+C<ev_periodic>s can also be used to implement vastly more complex timers,
+such as triggering an event on each "midnight, local time", or other
+complicated, rules.
 
 As with timers, the callback is guarenteed to be invoked only when the
-time (C<at>) has been passed, but if multiple periodic timers become ready
+time (C<at>) has passed, but if multiple periodic timers become ready
 during the same loop iteration then order of execution is undefined.
 
+=head3 Watcher-Specific Functions and Data Members
+
 =over 4
 
 =item ev_periodic_init (ev_periodic *, callback, ev_tstamp at, ev_tstamp interval, reschedule_cb)
@@ -1080,21 +1303,22 @@
 
 =over 4
 
-=item * absolute timer (interval = reschedule_cb = 0)
+=item * absolute timer (at = time, interval = reschedule_cb = 0)
 
-In this configuration the watcher triggers an event at the wallclock time
-C<at> and doesn't repeat. It will not adjust when a time jump occurs,
-that is, if it is to be run at January 1st 2011 then it will run when the
-system time reaches or surpasses this time.
+In this configuration the watcher triggers an event after the wallclock
+time C<at> has passed and doesn't repeat. It will not adjust when a time
+jump occurs, that is, if it is to be run at January 1st 2011 then it will
+run when the system time reaches or surpasses this time.
 
-=item * non-repeating interval timer (interval > 0, reschedule_cb = 0)
+=item * repeating interval timer (at = offset, interval > 0, reschedule_cb = 0)
 
 In this mode the watcher will always be scheduled to time out at the next
-C<at + N * interval> time (for some integer N) and then repeat, regardless
-of any time jumps.
+C<at + N * interval> time (for some integer N, which can also be negative)
+and then repeat, regardless of any time jumps.
 
 This can be used to create timers that do not drift with respect to system
-time:
+time, for example, here is a C<ev_periodic> that triggers each hour, on
+the hour:
 
    ev_periodic_set (&periodic, 0., 3600., 0);
 
@@ -1107,7 +1331,16 @@
 C<ev_periodic> will try to run the callback in this mode at the next possible
 time where C<time = at (mod interval)>, regardless of any time jumps.
 
-=item * manual reschedule mode (reschedule_cb = callback)
+For numerical stability it is preferable that the C<at> value is near
+C<ev_now ()> (the current time), but there is no range requirement for
+this value, and in fact is often specified as zero.
+
+Note also that there is an upper limit to how often a timer can fire (cpu
+speed for example), so if C<interval> is very small then timing stability
+will of course detoriate. Libev itself tries to be exact to be about one
+millisecond (if the OS supports it and the machine is fast enough).
+
+=item * manual reschedule mode (at and interval ignored, reschedule_cb = callback)
 
 In this mode the values for C<interval> and C<at> are both being
 ignored. Instead, each time the periodic watcher gets scheduled, the
@@ -1115,12 +1348,14 @@
 current time as second argument.
 
 NOTE: I<This callback MUST NOT stop or destroy any periodic watcher,
-ever, or make any event loop modifications>. If you need to stop it,
-return C<now + 1e30> (or so, fudge fudge) and stop it afterwards (e.g. by
-starting a prepare watcher).
+ever, or make ANY event loop modifications whatsoever>.
+
+If you need to stop it, return C<now + 1e30> (or so, fudge fudge) and stop
+it afterwards (e.g. by starting an C<ev_prepare> watcher, which is the
+only event loop modification you are allowed to do).
 
-Its prototype is C<ev_tstamp (*reschedule_cb)(struct ev_periodic *w,
-ev_tstamp now)>, e.g.:
+The callback prototype is C<ev_tstamp (*reschedule_cb)(struct ev_periodic
+*w, ev_tstamp now)>, e.g.:
 
    static ev_tstamp my_rescheduler (struct ev_periodic *w, ev_tstamp now)
    {
@@ -1132,11 +1367,11 @@
 will usually be called just before the callback will be triggered, but
 might be called at other times, too.
 
-NOTE: I<< This callback must always return a time that is later than the
-passed C<now> value >>. Not even C<now> itself will do, it I<must> be larger.
+NOTE: I<< This callback must always return a time that is higher than or
+equal to the passed C<now> value >>.
 
 This can be used to create very complex timers, such as a timer that
-triggers on each midnight, local time. To do this, you would calculate the
+triggers on "next midnight, local time". To do this, you would calculate the
 next midnight after C<now> and return the timestamp value for this. How
 you do this is, again, up to you (but it is not trivial, which is the main
 reason I omitted it as an example).
@@ -1150,6 +1385,19 @@
 a different time than the last time it was called (e.g. in a crond like
 program when the crontabs have changed).
 
+=item ev_tstamp ev_periodic_at (ev_periodic *)
+
+When active, returns the absolute time that the watcher is supposed to
+trigger next.
+
+=item ev_tstamp offset [read-write]
+
+When repeating, this contains the offset value, otherwise this is the
+absolute point in time (the C<at> value passed to C<ev_periodic_set>).
+
+Can be modified any time, but changes only take effect when the periodic
+timer fires or C<ev_periodic_again> is being called.
+
 =item ev_tstamp interval [read-write]
 
 The current interval value. Can be modified any time, but changes only
@@ -1164,6 +1412,8 @@
 
 =back
 
+=head3 Examples
+
 Example: Call a callback every hour, or, more precisely, whenever the
 system clock is divisible by 3600. The callback invocation times have
 potentially a lot of jittering, but good long-term stability.
@@ -1212,6 +1462,14 @@
 watcher for a signal is stopped libev will reset the signal handler to
 SIG_DFL (regardless of what it was set to before).
 
+If possible and supported, libev will install its handlers with
+C<SA_RESTART> behaviour enabled, so syscalls should not be unduly
+interrupted. If you have a problem with syscalls getting interrupted by
+signals you can block all signals in an C<ev_check> watcher and unblock
+them in an C<ev_prepare> watcher.
+
+=head3 Watcher-Specific Functions and Data Members
+
 =over 4
 
 =item ev_signal_init (ev_signal *, callback, int signum)
@@ -1227,24 +1485,67 @@
 
 =back
 
+=head3 Examples
+
+Example: Try to exit cleanly on SIGINT and SIGTERM.
+
+  static void
+  sigint_cb (struct ev_loop *loop, struct ev_signal *w, int revents)
+  {
+    ev_unloop (loop, EVUNLOOP_ALL);
+  }
+
+  struct ev_signal signal_watcher;
+  ev_signal_init (&signal_watcher, sigint_cb, SIGINT);
+  ev_signal_start (loop, &sigint_cb);
+
 
 =head2 C<ev_child> - watch out for process status changes
 
 Child watchers trigger when your process receives a SIGCHLD in response to
-some child status changes (most typically when a child of yours dies).
+some child status changes (most typically when a child of yours dies). It
+is permissible to install a child watcher I<after> the child has been
+forked (which implies it might have already exited), as long as the event
+loop isn't entered (or is continued from a watcher).
+
+Only the default event loop is capable of handling signals, and therefore
+you can only rgeister child watchers in the default event loop.
+
+=head3 Process Interaction
+
+Libev grabs C<SIGCHLD> as soon as the default event loop is
+initialised. This is necessary to guarantee proper behaviour even if
+the first child watcher is started after the child exits. The occurance
+of C<SIGCHLD> is recorded asynchronously, but child reaping is done
+synchronously as part of the event loop processing. Libev always reaps all
+children, even ones not watched.
+
+=head3 Overriding the Built-In Processing
+
+Libev offers no special support for overriding the built-in child
+processing, but if your application collides with libev's default child
+handler, you can override it easily by installing your own handler for
+C<SIGCHLD> after initialising the default loop, and making sure the
+default loop never gets destroyed. You are encouraged, however, to use an
+event-based approach to child reaping and thus use libev's support for
+that, so other libev users can use C<ev_child> watchers freely.
+
+=head3 Watcher-Specific Functions and Data Members
 
 =over 4
 
-=item ev_child_init (ev_child *, callback, int pid)
+=item ev_child_init (ev_child *, callback, int pid, int trace)
 
-=item ev_child_set (ev_child *, int pid)
+=item ev_child_set (ev_child *, int pid, int trace)
 
 Configures the watcher to wait for status changes of process C<pid> (or
 I<any> process if C<pid> is specified as C<0>). The callback can look
 at the C<rstatus> member of the C<ev_child> watcher structure to see
 the status word (use the macros from C<sys/wait.h> and see your systems
 C<waitpid> documentation). The C<rpid> member contains the pid of the
-process causing the status change.
+process causing the status change. C<trace> must be either C<0> (only
+activate the watcher when the process terminates) or C<1> (additionally
+activate the watcher when the process is stopped or continued).
 
 =item int pid [read-only]
 
@@ -1261,17 +1562,34 @@
 
 =back
 
-Example: Try to exit cleanly on SIGINT and SIGTERM.
+=head3 Examples
+
+Example: C<fork()> a new process and install a child handler to wait for
+its completion.
+
+  ev_child cw;
 
   static void
-  sigint_cb (struct ev_loop *loop, struct ev_signal *w, int revents)
+  child_cb (EV_P_ struct ev_child *w, int revents)
   {
-    ev_unloop (loop, EVUNLOOP_ALL);
+    ev_child_stop (EV_A_ w);
+    printf ("process %d exited with status %x\n", w->rpid, w->rstatus);
   }
 
-  struct ev_signal signal_watcher;
-  ev_signal_init (&signal_watcher, sigint_cb, SIGINT);
-  ev_signal_start (loop, &sigint_cb);
+  pid_t pid = fork ();
+
+  if (pid < 0)
+    // error
+  else if (pid == 0)
+    {
+      // the forked child executes here
+      exit (1);
+    }
+  else
+    {
+      ev_child_init (&cw, child_cb, pid, 0);
+      ev_child_start (EV_DEFAULT_ &cw);
+    }
 
 
 =head2 C<ev_stat> - did the file attributes just change?
@@ -1304,11 +1622,67 @@
 
 At the time of this writing, only the Linux inotify interface is
 implemented (implementing kqueue support is left as an exercise for the
-reader). Inotify will be used to give hints only and should not change the
-semantics of C<ev_stat> watchers, which means that libev sometimes needs
-to fall back to regular polling again even with inotify, but changes are
-usually detected immediately, and if the file exists there will be no
-polling.
+reader, note, however, that the author sees no way of implementing ev_stat
+semantics with kqueue). Inotify will be used to give hints only and should
+not change the semantics of C<ev_stat> watchers, which means that libev
+sometimes needs to fall back to regular polling again even with inotify,
+but changes are usually detected immediately, and if the file exists there
+will be no polling.
+
+=head3 ABI Issues (Largefile Support)
+
+Libev by default (unless the user overrides this) uses the default
+compilation environment, which means that on systems with optionally
+disabled large file support, you get the 32 bit version of the stat
+structure. When using the library from programs that change the ABI to
+use 64 bit file offsets the programs will fail. In that case you have to
+compile libev with the same flags to get binary compatibility. This is
+obviously the case with any flags that change the ABI, but the problem is
+most noticably with ev_stat and largefile support.
+
+=head3 Inotify
+
+When C<inotify (7)> support has been compiled into libev (generally only
+available on Linux) and present at runtime, it will be used to speed up
+change detection where possible. The inotify descriptor will be created lazily
+when the first C<ev_stat> watcher is being started.
+
+Inotify presence does not change the semantics of C<ev_stat> watchers
+except that changes might be detected earlier, and in some cases, to avoid
+making regular C<stat> calls. Even in the presence of inotify support
+there are many cases where libev has to resort to regular C<stat> polling.
+
+(There is no support for kqueue, as apparently it cannot be used to
+implement this functionality, due to the requirement of having a file
+descriptor open on the object at all times).
+
+=head3 The special problem of stat time resolution
+
+The C<stat ()> syscall only supports full-second resolution portably, and
+even on systems where the resolution is higher, many filesystems still
+only support whole seconds.
+
+That means that, if the time is the only thing that changes, you can
+easily miss updates: on the first update, C<ev_stat> detects a change and
+calls your callback, which does something. When there is another update
+within the same second, C<ev_stat> will be unable to detect it as the stat
+data does not change.
+
+The solution to this is to delay acting on a change for slightly more
+than a second (or till slightly after the next full second boundary), using
+a roughly one-second-delay C<ev_timer> (e.g. C<ev_timer_set (w, 0., 1.02);
+ev_timer_again (loop, w)>).
+
+The C<.02> offset is added to work around small timing inconsistencies
+of some operating systems (where the second counter of the current time
+might be be delayed. One such system is the Linux kernel, where a call to
+C<gettimeofday> might return a timestamp with a full second later than
+a subsequent C<time> call - if the equivalent of C<time ()> is used to
+update file times then there will be a small window where the kernel uses
+the previous second to update file times but libev might already execute
+the timer callback).
+
+=head3 Watcher-Specific Functions and Data Members
 
 =over 4
 
@@ -1322,28 +1696,32 @@
 a suitable value. The memory pointed to by C<path> must point to the same
 path for as long as the watcher is active.
 
-The callback will be receive C<EV_STAT> when a change was detected,
-relative to the attributes at the time the watcher was started (or the
-last change was detected).
+The callback will receive C<EV_STAT> when a change was detected, relative
+to the attributes at the time the watcher was started (or the last change
+was detected).
 
-=item ev_stat_stat (ev_stat *)
+=item ev_stat_stat (loop, ev_stat *)
 
 Updates the stat buffer immediately with new values. If you change the
-watched path in your callback, you could call this fucntion to avoid
-detecting this change (while introducing a race condition). Can also be
-useful simply to find out the new values.
+watched path in your callback, you could call this function to avoid
+detecting this change (while introducing a race condition if you are not
+the only one changing the path). Can also be useful simply to find out the
+new values.
 
 =item ev_statdata attr [read-only]
 
-The most-recently detected attributes of the file. Although the type is of
+The most-recently detected attributes of the file. Although the type is
 C<ev_statdata>, this is usually the (or one of the) C<struct stat> types
-suitable for your system. If the C<st_nlink> member is C<0>, then there
-was some error while C<stat>ing the file.
+suitable for your system, but you can only rely on the POSIX-standardised
+members to be present. If the C<st_nlink> member is C<0>, then there was
+some error while C<stat>ing the file.
 
 =item ev_statdata prev [read-only]
 
 The previous attributes of the file. The callback gets invoked whenever
-C<prev> != C<attr>.
+C<prev> != C<attr>, or, more precisely, one or more of these members
+differ: C<st_dev>, C<st_ino>, C<st_mode>, C<st_nlink>, C<st_uid>,
+C<st_gid>, C<st_rdev>, C<st_size>, C<st_atime>, C<st_mtime>, C<st_ctime>.
 
 =item ev_tstamp interval [read-only]
 
@@ -1355,6 +1733,8 @@
 
 =back
 
+=head3 Examples
+
 Example: Watch C</etc/passwd> for attribute changes.
 
   static void
@@ -1376,9 +1756,37 @@
   ...
   ev_stat passwd;
 
-  ev_stat_init (&passwd, passwd_cb, "/etc/passwd");
+  ev_stat_init (&passwd, passwd_cb, "/etc/passwd", 0.);
   ev_stat_start (loop, &passwd);
 
+Example: Like above, but additionally use a one-second delay so we do not
+miss updates (however, frequent updates will delay processing, too, so
+one might do the work both on C<ev_stat> callback invocation I<and> on
+C<ev_timer> callback invocation).
+
+  static ev_stat passwd;
+  static ev_timer timer;
+
+  static void
+  timer_cb (EV_P_ ev_timer *w, int revents)
+  {
+    ev_timer_stop (EV_A_ w);
+
+    /* now it's one second after the most recent passwd change */
+  }
+
+  static void
+  stat_cb (EV_P_ ev_stat *w, int revents)
+  {
+    /* reset the one-second timer */
+    ev_timer_again (EV_A_ &timer);
+  }
+
+  ...
+  ev_stat_init (&passwd, stat_cb, "/etc/passwd", 0.);
+  ev_stat_start (loop, &passwd);
+  ev_timer_init (&timer, timer_cb, 0., 1.02);
+
 
 =head2 C<ev_idle> - when you've got nothing better to do...
 
@@ -1401,6 +1809,8 @@
 "pseudo-background processing", or delay processing stuff to after the
 event loop has handled all outstanding events.
 
+=head3 Watcher-Specific Functions and Data Members
+
 =over 4
 
 =item ev_idle_init (ev_signal *, callback)
@@ -1411,6 +1821,8 @@
 
 =back
 
+=head3 Examples
+
 Example: Dynamically allocate an C<ev_idle> watcher, start it, and in the
 callback, free it. Also, use no error checking, as usual.
 
@@ -1419,7 +1831,7 @@
   {
     free (w);
     // now do something you wanted to do when the program has
-    // no longer asnything immediate to do.
+    // no longer anything immediate to do.
   }
 
   struct ev_idle *idle_watcher = malloc (sizeof (struct ev_idle));
@@ -1467,6 +1879,18 @@
 loop from blocking if lower-priority coroutines are active, thus mapping
 low-priority coroutines to idle/background tasks).
 
+It is recommended to give C<ev_check> watchers highest (C<EV_MAXPRI>)
+priority, to ensure that they are being run before any other watchers
+after the poll. Also, C<ev_check> watchers (and C<ev_prepare> watchers,
+too) should not activate ("feed") events into libev. While libev fully
+supports this, they might get executed before other C<ev_check> watchers
+did their job. As C<ev_check> watchers are often used to embed other
+(non-libev) event loops those other event loops might be in an unusable
+state until their C<ev_check> watcher ran (always remind yourself to
+coexist peacefully with others).
+
+=head3 Watcher-Specific Functions and Data Members
+
 =over 4
 
 =item ev_prepare_init (ev_prepare *, callback)
@@ -1479,10 +1903,20 @@
 
 =back
 
-Example: To include a library such as adns, you would add IO watchers
-and a timeout watcher in a prepare handler, as required by libadns, and
-in a check watcher, destroy them and call into libadns. What follows is
-pseudo-code only of course:
+=head3 Examples
+
+There are a number of principal ways to embed other event loops or modules
+into libev. Here are some ideas on how to include libadns into libev
+(there is a Perl module named C<EV::ADNS> that does this, which you could
+use as a working example. Another Perl module named C<EV::Glib> embeds a
+Glib main context into libev, and finally, C<Glib::EV> embeds EV into the
+Glib event loop).
+
+Method 1: Add IO watchers and a timeout watcher in a prepare handler,
+and in a check watcher, destroy them and call into libadns. What follows
+is pseudo-code only of course. This requires you to either use a low
+priority for the check watcher or use C<ev_clear_pending> explicitly, as
+the callbacks for the IO/timeout watchers might not have been called yet.
 
   static ev_io iow [nfd];
   static ev_timer tw;
@@ -1490,11 +1924,6 @@
   static void
   io_cb (ev_loop *loop, ev_io *w, int revents)
   {
-    // set the relevant poll flags
-    // could also call adns_processreadable etc. here
-    struct pollfd *fd = (struct pollfd *)w->data;
-    if (revents & EV_READ ) fd->revents |= fd->events & POLLIN;
-    if (revents & EV_WRITE) fd->revents |= fd->events & POLLOUT;
   }
 
   // create io watchers for each fd and a timer before blocking
@@ -1510,7 +1939,7 @@
     ev_timer_init (&tw, 0, timeout * 1e-3);
     ev_timer_start (loop, &tw);
 
-    // create on ev_io per pollfd
+    // create one ev_io per pollfd
     for (int i = 0; i < nfd; ++i)
       {
         ev_io_init (iow + i, io_cb, fds [i].fd,
@@ -1518,7 +1947,6 @@
            | (fds [i].events & POLLOUT ? EV_WRITE : 0)));
 
         fds [i].revents = 0;
-        iow [i].data = fds + i;
         ev_io_start (loop, iow + i);
       }
   }
@@ -1530,11 +1958,80 @@
     ev_timer_stop (loop, &tw);
 
     for (int i = 0; i < nfd; ++i)
-      ev_io_stop (loop, iow + i);
+      {
+        // set the relevant poll flags
+        // could also call adns_processreadable etc. here
+        struct pollfd *fd = fds + i;
+        int revents = ev_clear_pending (iow + i);
+        if (revents & EV_READ ) fd->revents |= fd->events & POLLIN;
+        if (revents & EV_WRITE) fd->revents |= fd->events & POLLOUT;
+
+        // now stop the watcher
+        ev_io_stop (loop, iow + i);
+      }
 
     adns_afterpoll (adns, fds, nfd, timeval_from (ev_now (loop));
   }
 
+Method 2: This would be just like method 1, but you run C<adns_afterpoll>
+in the prepare watcher and would dispose of the check watcher.
+
+Method 3: If the module to be embedded supports explicit event
+notification (adns does), you can also make use of the actual watcher
+callbacks, and only destroy/create the watchers in the prepare watcher.
+
+  static void
+  timer_cb (EV_P_ ev_timer *w, int revents)
+  {
+    adns_state ads = (adns_state)w->data;
+    update_now (EV_A);
+
+    adns_processtimeouts (ads, &tv_now);
+  }
+
+  static void
+  io_cb (EV_P_ ev_io *w, int revents)
+  {
+    adns_state ads = (adns_state)w->data;
+    update_now (EV_A);
+
+    if (revents & EV_READ ) adns_processreadable  (ads, w->fd, &tv_now);
+    if (revents & EV_WRITE) adns_processwriteable (ads, w->fd, &tv_now);
+  }
+
+  // do not ever call adns_afterpoll
+
+Method 4: Do not use a prepare or check watcher because the module you
+want to embed is too inflexible to support it. Instead, youc na override
+their poll function.  The drawback with this solution is that the main
+loop is now no longer controllable by EV. The C<Glib::EV> module does
+this.
+
+  static gint
+  event_poll_func (GPollFD *fds, guint nfds, gint timeout)
+  {
+    int got_events = 0;
+
+    for (n = 0; n < nfds; ++n)
+      // create/start io watcher that sets the relevant bits in fds[n] and increment got_events
+
+    if (timeout >= 0)
+      // create/start timer
+
+    // poll
+    ev_loop (EV_A_ 0);
+
+    // stop timer again
+    if (timeout >= 0)
+      ev_timer_stop (EV_A_ &to);
+
+    // stop io watchers again - their callbacks should have set
+    for (n = 0; n < nfds; ++n)
+      ev_io_stop (EV_A_ iow [n]);
+
+    return got_events;
+  }
+
 
 =head2 C<ev_embed> - when one backend isn't enough...
 
@@ -1585,26 +2082,9 @@
 So when you want to use this feature you will always have to be prepared
 that you cannot get an embeddable loop. The recommended way to get around
 this is to have a separate variables for your embeddable loop, try to
-create it, and if that fails, use the normal loop for everything:
-
-  struct ev_loop *loop_hi = ev_default_init (0);
-  struct ev_loop *loop_lo = 0;
-  struct ev_embed embed;
-  
-  // see if there is a chance of getting one that works
-  // (remember that a flags value of 0 means autodetection)
-  loop_lo = ev_embeddable_backends () & ev_recommended_backends ()
-    ? ev_loop_new (ev_embeddable_backends () & ev_recommended_backends ())
-    : 0;
+create it, and if that fails, use the normal loop for everything.
 
-  // if we got one, then embed it, otherwise default to loop_hi
-  if (loop_lo)
-    {
-      ev_embed_init (&embed, 0, loop_lo);
-      ev_embed_start (loop_hi, &embed);
-    }
-  else
-    loop_lo = loop_hi;
+=head3 Watcher-Specific Functions and Data Members
 
 =over 4
 
@@ -1624,12 +2104,60 @@
 similarly to C<ev_loop (embedded_loop, EVLOOP_NONBLOCK)>, but in the most
 apropriate way for embedded loops.
 
-=item struct ev_loop *loop [read-only]
+=item struct ev_loop *other [read-only]
 
 The embedded event loop.
 
 =back
 
+=head3 Examples
+
+Example: Try to get an embeddable event loop and embed it into the default
+event loop. If that is not possible, use the default loop. The default
+loop is stored in C<loop_hi>, while the mebeddable loop is stored in
+C<loop_lo> (which is C<loop_hi> in the acse no embeddable loop can be
+used).
+
+  struct ev_loop *loop_hi = ev_default_init (0);
+  struct ev_loop *loop_lo = 0;
+  struct ev_embed embed;
+  
+  // see if there is a chance of getting one that works
+  // (remember that a flags value of 0 means autodetection)
+  loop_lo = ev_embeddable_backends () & ev_recommended_backends ()
+    ? ev_loop_new (ev_embeddable_backends () & ev_recommended_backends ())
+    : 0;
+
+  // if we got one, then embed it, otherwise default to loop_hi
+  if (loop_lo)
+    {
+      ev_embed_init (&embed, 0, loop_lo);
+      ev_embed_start (loop_hi, &embed);
+    }
+  else
+    loop_lo = loop_hi;
+
+Example: Check if kqueue is available but not recommended and create
+a kqueue backend for use with sockets (which usually work with any
+kqueue implementation). Store the kqueue/socket-only event loop in
+C<loop_socket>. (One might optionally use C<EVFLAG_NOENV>, too).
+
+  struct ev_loop *loop = ev_default_init (0);
+  struct ev_loop *loop_socket = 0;
+  struct ev_embed embed;
+  
+  if (ev_supported_backends () & ~ev_recommended_backends () & EVBACKEND_KQUEUE)
+    if ((loop_socket = ev_loop_new (EVBACKEND_KQUEUE))
+      {
+        ev_embed_init (&embed, 0, loop_socket);
+        ev_embed_start (loop, &embed);
+      }
+
+  if (!loop_socket)
+    loop_socket = loop;
+
+  // now use loop_socket for all sockets, and loop for everything else
+
 
 =head2 C<ev_fork> - the audacity to resume the event loop after a fork
 
@@ -1641,6 +2169,8 @@
 C<ev_default_fork> cheats and calls it in the wrong process, the fork
 handlers will be invoked, too, of course.
 
+=head3 Watcher-Specific Functions and Data Members
+
 =over 4
 
 =item ev_fork_init (ev_signal *, callback)
@@ -1652,6 +2182,151 @@
 =back
 
 
+=head2 C<ev_async> - how to wake up another event loop
+
+In general, you cannot use an C<ev_loop> from multiple threads or other
+asynchronous sources such as signal handlers (as opposed to multiple event
+loops - those are of course safe to use in different threads).
+
+Sometimes, however, you need to wake up another event loop you do not
+control, for example because it belongs to another thread. This is what
+C<ev_async> watchers do: as long as the C<ev_async> watcher is active, you
+can signal it by calling C<ev_async_send>, which is thread- and signal
+safe.
+
+This functionality is very similar to C<ev_signal> watchers, as signals,
+too, are asynchronous in nature, and signals, too, will be compressed
+(i.e. the number of callback invocations may be less than the number of
+C<ev_async_sent> calls).
+
+Unlike C<ev_signal> watchers, C<ev_async> works with any event loop, not
+just the default loop.
+
+=head3 Queueing
+
+C<ev_async> does not support queueing of data in any way. The reason
+is that the author does not know of a simple (or any) algorithm for a
+multiple-writer-single-reader queue that works in all cases and doesn't
+need elaborate support such as pthreads.
+
+That means that if you want to queue data, you have to provide your own
+queue. But at least I can tell you would implement locking around your
+queue:
+
+=over 4
+
+=item queueing from a signal handler context
+
+To implement race-free queueing, you simply add to the queue in the signal
+handler but you block the signal handler in the watcher callback. Here is an example that does that for
+some fictitiuous SIGUSR1 handler:
+
+   static ev_async mysig;
+
+   static void
+   sigusr1_handler (void)
+   {
+     sometype data;
+
+     // no locking etc.
+     queue_put (data);
+     ev_async_send (EV_DEFAULT_ &mysig);
+   }
+
+   static void
+   mysig_cb (EV_P_ ev_async *w, int revents)
+   {
+     sometype data;
+     sigset_t block, prev;
+
+     sigemptyset (&block);
+     sigaddset (&block, SIGUSR1);
+     sigprocmask (SIG_BLOCK, &block, &prev);
+
+     while (queue_get (&data))
+       process (data);
+
+     if (sigismember (&prev, SIGUSR1)
+       sigprocmask (SIG_UNBLOCK, &block, 0);
+   }
+
+(Note: pthreads in theory requires you to use C<pthread_setmask>
+instead of C<sigprocmask> when you use threads, but libev doesn't do it
+either...).
+
+=item queueing from a thread context
+
+The strategy for threads is different, as you cannot (easily) block
+threads but you can easily preempt them, so to queue safely you need to
+employ a traditional mutex lock, such as in this pthread example:
+
+   static ev_async mysig;
+   static pthread_mutex_t mymutex = PTHREAD_MUTEX_INITIALIZER;
+
+   static void
+   otherthread (void)
+   {
+     // only need to lock the actual queueing operation
+     pthread_mutex_lock (&mymutex);
+     queue_put (data);
+     pthread_mutex_unlock (&mymutex);
+
+     ev_async_send (EV_DEFAULT_ &mysig);
+   }
+
+   static void
+   mysig_cb (EV_P_ ev_async *w, int revents)
+   {
+     pthread_mutex_lock (&mymutex);
+
+     while (queue_get (&data))
+       process (data);
+
+     pthread_mutex_unlock (&mymutex);
+   }
+
+=back
+
+
+=head3 Watcher-Specific Functions and Data Members
+
+=over 4
+
+=item ev_async_init (ev_async *, callback)
+
+Initialises and configures the async watcher - it has no parameters of any
+kind. There is a C<ev_asynd_set> macro, but using it is utterly pointless,
+believe me.
+
+=item ev_async_send (loop, ev_async *)
+
+Sends/signals/activates the given C<ev_async> watcher, that is, feeds
+an C<EV_ASYNC> event on the watcher into the event loop. Unlike
+C<ev_feed_event>, this call is safe to do in other threads, signal or
+similar contexts (see the dicusssion of C<EV_ATOMIC_T> in the embedding
+section below on what exactly this means).
+
+This call incurs the overhead of a syscall only once per loop iteration,
+so while the overhead might be noticable, it doesn't apply to repeated
+calls to C<ev_async_send>.
+
+=item bool = ev_async_pending (ev_async *)
+
+Returns a non-zero value when C<ev_async_send> has been called on the
+watcher but the event has not yet been processed (or even noted) by the
+event loop.
+
+C<ev_async_send> sets a flag in the watcher and wakes up the loop. When
+the loop iterates next and checks for the watcher to have become active,
+it will reset the flag again. C<ev_async_pending> can be used to very
+quickly check wether invoking the loop might be a good idea.
+
+Not that this does I<not> check wether the watcher itself is pending, only
+wether it has been requested to make this watcher pending.
+
+=back
+
+
 =head1 OTHER FUNCTIONS
 
 There are some other functions of possible interest. Described. Here. Now.
@@ -1729,6 +2404,9 @@
 will fail and all watchers will have the same priority, even though there
 is an ev_pri field.
 
+=item * In libevent, the last base created gets the signals, in libev, the
+first base created (== the default loop) gets the signals.
+
 =item * Other members are not supported.
 
 =item * The libev emulation is I<not> ABI compatible to libevent, you need
@@ -1830,14 +2508,21 @@
   ev::io iow;
   iow.set <myclass, &myclass::io_cb> (&obj);
 
-=item w->set (void (*function)(watcher &w, int), void *data = 0)
+=item w->set<function> (void *data = 0)
 
 Also sets a callback, but uses a static method or plain function as
 callback. The optional C<data> argument will be stored in the watcher's
 C<data> member and is free for you to use.
 
+The prototype of the C<function> must be C<void (*)(ev::TYPE &w, int)>.
+
 See the method-C<set> above for more details.
 
+Example:
+
+  static void io_cb (ev::io &w, int revents) { }
+  iow.set <io_cb> ();
+
 =item w->set (struct ev_loop *)
 
 Associates a different C<struct ev_loop> with this watcher. You can only
@@ -1859,16 +2544,16 @@
 
 Stops the watcher if it is active. Again, no C<loop> argument.
 
-=item w->again ()       C<ev::timer>, C<ev::periodic> only
+=item w->again () (C<ev::timer>, C<ev::periodic> only)
 
 For C<ev::timer> and C<ev::periodic>, this invokes the corresponding
 C<ev_TYPE_again> function.
 
-=item w->sweep ()       C<ev::embed> only
+=item w->sweep () (C<ev::embed> only)
 
 Invokes C<ev_embed_sweep>.
 
-=item w->update ()      C<ev::stat> only
+=item w->update () (C<ev::stat> only)
 
 Invokes C<ev_stat_stat>.
 
@@ -1881,26 +2566,59 @@
 
   class myclass
   {
-    ev_io   io;   void io_cb   (ev::io   &w, int revents);
-    ev_idle idle  void idle_cb (ev::idle &w, int revents);
+    ev::io   io;  void io_cb   (ev::io   &w, int revents);
+    ev:idle idle  void idle_cb (ev::idle &w, int revents);
 
-    myclass ();
-  }
+    myclass (int fd)
+    {
+      io  .set <myclass, &myclass::io_cb  > (this);
+      idle.set <myclass, &myclass::idle_cb> (this);
 
-  myclass::myclass (int fd)
-  {
-    io  .set <myclass, &myclass::io_cb  > (this);
-    idle.set <myclass, &myclass::idle_cb> (this);
+      io.start (fd, ev::READ);
+    }
+  };
 
-    io.start (fd, ev::READ);
-  }
+
+=head1 OTHER LANGUAGE BINDINGS
+
+Libev does not offer other language bindings itself, but bindings for a
+numbe rof languages exist in the form of third-party packages. If you know
+any interesting language binding in addition to the ones listed here, drop
+me a note.
+
+=over 4
+
+=item Perl
+
+The EV module implements the full libev API and is actually used to test
+libev. EV is developed together with libev. Apart from the EV core module,
+there are additional modules that implement libev-compatible interfaces
+to C<libadns> (C<EV::ADNS>), C<Net::SNMP> (C<Net::SNMP::EV>) and the
+C<libglib> event core (C<Glib::EV> and C<EV::Glib>).
+
+It can be found and installed via CPAN, its homepage is found at
+L<http://software.schmorp.de/pkg/EV>.
+
+=item Ruby
+
+Tony Arcieri has written a ruby extension that offers access to a subset
+of the libev API and adds filehandle abstractions, asynchronous DNS and
+more on top of it. It can be found via gem servers. Its homepage is at
+L<http://rev.rubyforge.org/>.
+
+=item D
+
+Leandro Lucarella has written a D language binding (F<ev.d>) for libev, to
+be found at L<http://git.llucax.com.ar/?p=software/ev.d.git;a=summary>.
+
+=back
 
 
 =head1 MACRO MAGIC
 
-Libev can be compiled with a variety of options, the most fundemantal is
-C<EV_MULTIPLICITY>. This option determines whether (most) functions and
-callbacks have an initial C<struct ev_loop *> argument.
+Libev can be compiled with a variety of options, the most fundamantal
+of which is C<EV_MULTIPLICITY>. This option determines whether (most)
+functions and callbacks have an initial C<struct ev_loop *> argument.
 
 To make it easier to write programs that cope with either variant, the
 following macros are defined:
@@ -1940,6 +2658,16 @@
 Similar to the other two macros, this gives you the value of the default
 loop, if multiple loops are supported ("ev loop default").
 
+=item C<EV_DEFAULT_UC>, C<EV_DEFAULT_UC_>
+
+Usage identical to C<EV_DEFAULT> and C<EV_DEFAULT_>, but requires that the
+default loop has been initialised (C<UC> == unchecked). Their behaviour
+is undefined when the default loop has not been initialised by a previous
+execution of C<EV_DEFAULT>, C<EV_DEFAULT_> or C<ev_default_init (...)>.
+
+It is often prudent to use C<EV_DEFAULT> when initialising the first
+watcher in a function but use C<EV_DEFAULT_UC> afterwards.
+
 =back
 
 Example: Declare and initialise a check watcher, utilising the above
@@ -1964,7 +2692,7 @@
 Game Server, the EV perl module, the GNU Virtual Private Ethernet (gvpe)
 and rxvt-unicode.
 
-The goal is to enable you to just copy the neecssary files into your
+The goal is to enable you to just copy the necessary files into your
 source directory without having to change even a single line in them, so
 you can easily upgrade by simply copying (or having a checked-out copy of
 libev somewhere in your source tree).
@@ -2044,9 +2772,9 @@
 
 =head2 PREPROCESSOR SYMBOLS/MACROS
 
-Libev can be configured via a variety of preprocessor symbols you have to define
-before including any of its files. The default is not to build for multiplicity
-and only include the select backend.
+Libev can be configured via a variety of preprocessor symbols you have to
+define before including any of its files. The default in the absense of
+autoconf is noted for every option.
 
 =over 4
 
@@ -2064,7 +2792,7 @@
 monotonic clock option at both compiletime and runtime. Otherwise no use
 of the monotonic clock option will be attempted. If you enable this, you
 usually have to link against librt or something similar. Enabling it when
-the functionality isn't available is safe, though, althoguh you have
+the functionality isn't available is safe, though, although you have
 to make sure you link against any libraries where the C<clock_gettime>
 function is hiding in (often F<-lrt>).
 
@@ -2074,8 +2802,21 @@
 realtime clock option at compiletime (and assume its availability at
 runtime if successful). Otherwise no use of the realtime clock option will
 be attempted. This effectively replaces C<gettimeofday> by C<clock_get
-(CLOCK_REALTIME, ...)> and will not normally affect correctness. See tzhe note about libraries
-in the description of C<EV_USE_MONOTONIC>, though.
+(CLOCK_REALTIME, ...)> and will not normally affect correctness. See the
+note about libraries in the description of C<EV_USE_MONOTONIC>, though.
+
+=item EV_USE_NANOSLEEP
+
+If defined to be C<1>, libev will assume that C<nanosleep ()> is available
+and will use it for delays. Otherwise it will use C<select ()>.
+
+=item EV_USE_EVENTFD
+
+If defined to be C<1>, then libev will assume that C<eventfd ()> is
+available and will probe for kernel support at runtime. This will improve
+C<ev_signal> and C<ev_async> performance and reduce resource consumption.
+If undefined, it will be enabled if the headers indicate GNU/Linux + Glibc
+2.7 or newer, otherwise disabled.
 
 =item EV_USE_SELECT
 
@@ -2104,6 +2845,14 @@
 it is assumed that all these functions actually work on fds, even
 on win32. Should not be defined on non-win32 platforms.
 
+=item EV_FD_TO_WIN32_HANDLE
+
+If C<EV_SELECT_IS_WINSOCKET> is enabled, then libev needs a way to map
+file descriptors to socket handles. When not defining this symbol (the
+default), then libev will call C<_get_osfhandle>, which is usually
+correct. In some cases, programs use their own file descriptor management,
+in which case they can provide this function to map fds to socket handles.
+
 =item EV_USE_POLL
 
 If defined to be C<1>, libev will compile in support for the C<poll>(2)
@@ -2114,8 +2863,9 @@
 
 If defined to be C<1>, libev will compile in support for the Linux
 C<epoll>(7) backend. Its availability will be detected at runtime,
-otherwise another method will be used as fallback. This is the
-preferred backend for GNU/Linux systems.
+otherwise another method will be used as fallback. This is the preferred
+backend for GNU/Linux systems. If undefined, it will be enabled if the
+headers indicate GNU/Linux + Glibc 2.4 or newer, otherwise disabled.
 
 =item EV_USE_KQUEUE
 
@@ -2144,13 +2894,25 @@
 
 If defined to be C<1>, libev will compile in support for the Linux inotify
 interface to speed up C<ev_stat> watchers. Its actual availability will
-be detected at runtime.
+be detected at runtime. If undefined, it will be enabled if the headers
+indicate GNU/Linux + Glibc 2.4 or newer, otherwise disabled.
+
+=item EV_ATOMIC_T
+
+Libev requires an integer type (suitable for storing C<0> or C<1>) whose
+access is atomic with respect to other threads or signal contexts. No such
+type is easily found in the C language, so you can provide your own type
+that you know is safe for your purposes. It is used both for signal handler "locking"
+as well as for signal and thread safety in C<ev_async> watchers.
+
+In the absense of this define, libev will use C<sig_atomic_t volatile>
+(from F<signal.h>), which is usually good enough on most platforms.
 
 =item EV_H
 
 The name of the F<ev.h> header file used to include it. The default if
-undefined is C<< <ev.h> >> in F<event.h> and C<"ev.h"> in F<ev.c>. This
-can be used to virtually rename the F<ev.h> header file in case of conflicts.
+undefined is C<"ev.h"> in F<event.h>, F<ev.c> and F<ev++.h>. This can be
+used to virtually rename the F<ev.h> header file in case of conflicts.
 
 =item EV_CONFIG_H
 
@@ -2161,7 +2923,7 @@
 =item EV_EVENT_H
 
 Similarly to C<EV_H>, this macro can be used to override F<event.c>'s idea
-of how the F<event.h> header can be found.
+of how the F<event.h> header can be found, the default is C<"event.h">.
 
 =item EV_PROTOTYPES
 
@@ -2222,11 +2984,17 @@
 If undefined or defined to be C<1>, then fork watchers are supported. If
 defined to be C<0>, then they are not.
 
+=item EV_ASYNC_ENABLE
+
+If undefined or defined to be C<1>, then async watchers are supported. If
+defined to be C<0>, then they are not.
+
 =item EV_MINIMAL
 
 If you need to shave off some kilobytes of code at the expense of some
-speed, define this symbol to C<1>. Currently only used for gcc to override
-some inlining decisions, saves roughly 30% codesize of amd64.
+speed, define this symbol to C<1>. Currently this is used to override some
+inlining decisions, saves roughly 30% codesize of amd64. It also selects a
+much smaller 2-heap for timer management over the default 4-heap.
 
 =item EV_PID_HASHSIZE
 
@@ -2237,12 +3005,34 @@
 
 =item EV_INOTIFY_HASHSIZE
 
-C<ev_staz> watchers use a small hash table to distribute workload by
+C<ev_stat> watchers use a small hash table to distribute workload by
 inotify watch id. The default size is C<16> (or C<1> with C<EV_MINIMAL>),
 usually more than enough. If you need to manage thousands of C<ev_stat>
 watchers you might want to increase this value (I<must> be a power of
 two).
 
+=item EV_USE_4HEAP
+
+Heaps are not very cache-efficient. To improve the cache-efficiency of the
+timer and periodics heap, libev uses a 4-heap when this symbol is defined
+to C<1>. The 4-heap uses more complicated (longer) code but has
+noticably faster performance with many (thousands) of watchers.
+
+The default is C<1> unless C<EV_MINIMAL> is set in which case it is C<0>
+(disabled).
+
+=item EV_HEAP_CACHE_AT
+
+Heaps are not very cache-efficient. To improve the cache-efficiency of the
+timer and periodics heap, libev can cache the timestamp (I<at>) within
+the heap structure (selected by defining C<EV_HEAP_CACHE_AT> to C<1>),
+which uses 8-12 bytes more per watcher and a few hundred bytes more code,
+but avoids random read accesses on heap changes. This improves performance
+noticably with with many (hundreds) of watchers.
+
+The default is C<1> unless C<EV_MINIMAL> is set in which case it is C<0>
+(disabled).
+
 =item EV_COMMON
 
 By default, all watchers have a C<void *data> member. By redefining
@@ -2264,11 +3054,36 @@
 
 Can be used to change the callback member declaration in each watcher,
 and the way callbacks are invoked and set. Must expand to a struct member
-definition and a statement, respectively. See the F<ev.v> header file for
+definition and a statement, respectively. See the F<ev.h> header file for
 their default definitions. One possible use for overriding these is to
 avoid the C<struct ev_loop *> as first argument in all cases, or to use
 method calls instead of plain function calls in C++.
 
+=head2 EXPORTED API SYMBOLS
+
+If you need to re-export the API (e.g. via a dll) and you need a list of
+exported symbols, you can use the provided F<Symbol.*> files which list
+all public symbols, one per line:
+
+  Symbols.ev      for libev proper
+  Symbols.event   for the libevent emulation
+
+This can also be used to rename all public symbols to avoid clashes with
+multiple versions of libev linked together (which is obviously bad in
+itself, but sometimes it is inconvinient to avoid this).
+
+A sed command like this will create wrapper C<#define>'s that you need to
+include before including F<ev.h>:
+
+   <Symbols.ev sed -e "s/.*/#define & myprefix_&/" >wrap.h
+
+This would create a file F<wrap.h> which essentially looks like this:
+
+   #define ev_backend     myprefix_ev_backend
+   #define ev_check_start myprefix_ev_check_start
+   #define ev_check_stop  myprefix_ev_check_stop
+   ...
+
 =head2 EXAMPLES
 
 For a real-world example of a program the includes libev
@@ -2300,6 +3115,63 @@
   #include "ev.c"
 
 
+=head1 THREADS AND COROUTINES
+
+=head2 THREADS
+
+Libev itself is completely threadsafe, but it uses no locking. This
+means that you can use as many loops as you want in parallel, as long as
+only one thread ever calls into one libev function with the same loop
+parameter.
+
+Or put differently: calls with different loop parameters can be done in
+parallel from multiple threads, calls with the same loop parameter must be
+done serially (but can be done from different threads, as long as only one
+thread ever is inside a call at any point in time, e.g. by using a mutex
+per loop).
+
+If you want to know which design is best for your problem, then I cannot
+help you but by giving some generic advice:
+
+=over 4
+
+=item * most applications have a main thread: use the default libev loop
+in that thread, or create a seperate thread running only the default loop.
+
+This helps integrating other libraries or software modules that use libev
+themselves and don't care/know about threading.
+
+=item * one loop per thread is usually a good model.
+
+Doing this is almost never wrong, sometimes a better-performance model
+exists, but it is always a good start.
+
+=item * other models exist, such as the leader/follower pattern, where one
+loop is handed through multiple threads in a kind of round-robbin fashion.
+
+Chosing a model is hard - look around, learn, know that usually you cna do
+better than you currently do :-)
+
+=item * often you need to talk to some other thread which blocks in the
+event loop - C<ev_async> watchers can be used to wake them up from other
+threads safely (or from signal contexts...).
+
+=back
+
+=head2 COROUTINES
+
+Libev is much more accomodating to coroutines ("cooperative threads"):
+libev fully supports nesting calls to it's functions from different
+coroutines (e.g. you can call C<ev_loop> on the same loop from two
+different coroutines and switch freely between both coroutines running the
+loop, as long as you don't confuse yourself). The only exception is that
+you must not do this from C<ev_periodic> reschedule callbacks.
+
+Care has been invested into making sure that libev does not keep local
+state inside C<ev_loop>, and other calls do not usually allow coroutine
+switches.
+
+
 =head1 COMPLEXITIES
 
 In this section the complexities of (many of) the algorithms used inside
@@ -2318,17 +3190,18 @@
 
 This means that, when you have a watcher that triggers in one hour and
 there are 100 watchers that would trigger before that then inserting will
-have to skip those 100 watchers.
+have to skip roughly seven (C<ld 100>) of these watchers.
 
-=item Changing timer/periodic watchers (by autorepeat, again): O(log skipped_other_timers)
+=item Changing timer/periodic watchers (by autorepeat or calling again): O(log skipped_other_timers)
 
-That means that for changing a timer costs less than removing/adding them
+That means that changing a timer costs less than removing/adding them
 as only the relative motion in the event queue has to be paid for.
 
-=item Starting io/check/prepare/idle/signal/child watchers: O(1)
+=item Starting io/check/prepare/idle/signal/child/fork/async watchers: O(1)
 
 These just add the watcher into an array or at the head of a list.
-=item Stopping check/prepare/idle watchers: O(1)
+
+=item Stopping check/prepare/idle/fork/async watchers: O(1)
 
 =item Stopping an io/signal/child watcher: O(number_of_watchers_for_this_(fd/signal/pid % EV_PID_HASHSIZE))
 
@@ -2336,23 +3209,186 @@
 correct watcher to remove. The lists are usually short (you don't usually
 have many watchers waiting for the same fd or signal).
 
-=item Finding the next timer per loop iteration: O(1)
+=item Finding the next timer in each loop iteration: O(1)
+
+By virtue of using a binary or 4-heap, the next timer is always found at a
+fixed position in the storage array.
 
 =item Each change on a file descriptor per loop iteration: O(number_of_watchers_for_this_fd)
 
 A change means an I/O watcher gets started or stopped, which requires
-libev to recalculate its status (and possibly tell the kernel).
+libev to recalculate its status (and possibly tell the kernel, depending
+on backend and wether C<ev_io_set> was used).
 
-=item Activating one watcher: O(1)
+=item Activating one watcher (putting it into the pending state): O(1)
 
 =item Priority handling: O(number_of_priorities)
 
 Priorities are implemented by allocating some space for each
 priority. When doing priority-based operations, libev usually has to
-linearly search all the priorities.
+linearly search all the priorities, but starting/stopping and activating
+watchers becomes O(1) w.r.t. priority handling.
+
+=item Sending an ev_async: O(1)
+
+=item Processing ev_async_send: O(number_of_async_watchers)
+
+=item Processing signals: O(max_signal_number)
+
+Sending involves a syscall I<iff> there were no other C<ev_async_send>
+calls in the current loop iteration. Checking for async and signal events
+involves iterating over all running async watchers or all signal numbers.
+
+=back
+
+
+=head1 Win32 platform limitations and workarounds
+
+Win32 doesn't support any of the standards (e.g. POSIX) that libev
+requires, and its I/O model is fundamentally incompatible with the POSIX
+model. Libev still offers limited functionality on this platform in
+the form of the C<EVBACKEND_SELECT> backend, and only supports socket
+descriptors. This only applies when using Win32 natively, not when using
+e.g. cygwin.
+
+Lifting these limitations would basically require the full
+re-implementation of the I/O system. If you are into these kinds of
+things, then note that glib does exactly that for you in a very portable
+way (note also that glib is the slowest event library known to man).
+
+There is no supported compilation method available on windows except
+embedding it into other applications.
+
+Due to the many, low, and arbitrary limits on the win32 platform and
+the abysmal performance of winsockets, using a large number of sockets
+is not recommended (and not reasonable). If your program needs to use
+more than a hundred or so sockets, then likely it needs to use a totally
+different implementation for windows, as libev offers the POSIX readiness
+notification model, which cannot be implemented efficiently on windows
+(microsoft monopoly games).
+
+=over 4
+
+=item The winsocket select function
+
+The winsocket C<select> function doesn't follow POSIX in that it requires
+socket I<handles> and not socket I<file descriptors>. This makes select
+very inefficient, and also requires a mapping from file descriptors
+to socket handles. See the discussion of the C<EV_SELECT_USE_FD_SET>,
+C<EV_SELECT_IS_WINSOCKET> and C<EV_FD_TO_WIN32_HANDLE> preprocessor
+symbols for more info.
+
+The configuration for a "naked" win32 using the microsoft runtime
+libraries and raw winsocket select is:
+
+  #define EV_USE_SELECT 1
+  #define EV_SELECT_IS_WINSOCKET 1   /* forces EV_SELECT_USE_FD_SET, too */
+
+Note that winsockets handling of fd sets is O(n), so you can easily get a
+complexity in the O(n²) range when using win32.
+
+=item Limited number of file descriptors
+
+Windows has numerous arbitrary (and low) limits on things.
+
+Early versions of winsocket's select only supported waiting for a maximum
+of C<64> handles (probably owning to the fact that all windows kernels
+can only wait for C<64> things at the same time internally; microsoft
+recommends spawning a chain of threads and wait for 63 handles and the
+previous thread in each. Great).
+
+Newer versions support more handles, but you need to define C<FD_SETSIZE>
+to some high number (e.g. C<2048>) before compiling the winsocket select
+call (which might be in libev or elsewhere, for example, perl does its own
+select emulation on windows).
+
+Another limit is the number of file descriptors in the microsoft runtime
+libraries, which by default is C<64> (there must be a hidden I<64> fetish
+or something like this inside microsoft). You can increase this by calling
+C<_setmaxstdio>, which can increase this limit to C<2048> (another
+arbitrary limit), but is broken in many versions of the microsoft runtime
+libraries.
+
+This might get you to about C<512> or C<2048> sockets (depending on
+windows version and/or the phase of the moon). To get more, you need to
+wrap all I/O functions and provide your own fd management, but the cost of
+calling select (O(n²)) will likely make this unworkable.
+
+=back
+
+
+=head1 PORTABILITY REQUIREMENTS
+
+In addition to a working ISO-C implementation, libev relies on a few
+additional extensions:
+
+=over 4
+
+=item C<sig_atomic_t volatile> must be thread-atomic as well
+
+The type C<sig_atomic_t volatile> (or whatever is defined as
+C<EV_ATOMIC_T>) must be atomic w.r.t. accesses from different
+threads. This is not part of the specification for C<sig_atomic_t>, but is
+believed to be sufficiently portable.
+
+=item C<sigprocmask> must work in a threaded environment
+
+Libev uses C<sigprocmask> to temporarily block signals. This is not
+allowed in a threaded program (C<pthread_sigmask> has to be used). Typical
+pthread implementations will either allow C<sigprocmask> in the "main
+thread" or will block signals process-wide, both behaviours would
+be compatible with libev. Interaction between C<sigprocmask> and
+C<pthread_sigmask> could complicate things, however.
+
+The most portable way to handle signals is to block signals in all threads
+except the initial one, and run the default loop in the initial thread as
+well.
+
+=item C<long> must be large enough for common memory allocation sizes
+
+To improve portability and simplify using libev, libev uses C<long>
+internally instead of C<size_t> when allocating its data structures. On
+non-POSIX systems (Microsoft...) this might be unexpectedly low, but
+is still at least 31 bits everywhere, which is enough for hundreds of
+millions of watchers.
+
+=item C<double> must hold a time value in seconds with enough accuracy
+
+The type C<double> is used to represent timestamps. It is required to
+have at least 51 bits of mantissa (and 9 bits of exponent), which is good
+enough for at least into the year 4000. This requirement is fulfilled by
+implementations implementing IEEE 754 (basically all existing ones).
 
 =back
 
+If you know of other additional requirements drop me a note.
+
+
+=head1 VALGRIND
+
+Valgrind has a special section here because it is a popular tool that is
+highly useful, but valgrind reports are very hard to interpret.
+
+If you think you found a bug (memory leak, uninitialised data access etc.)
+in libev, then check twice: If valgrind reports something like:
+
+   ==2274==    definitely lost: 0 bytes in 0 blocks.
+   ==2274==      possibly lost: 0 bytes in 0 blocks.
+   ==2274==    still reachable: 256 bytes in 1 blocks.
+
+then there is no memory leak. Similarly, under some circumstances,
+valgrind might report kernel bugs as if it were a bug in libev, or it
+might be confused (it is a very good tool, but only a tool).
+
+If you are unsure about something, feel free to contact the mailing list
+with the full valgrind report and an explanation on why you think this is
+a bug in libev. However, don't be annoyed when you get a brisk "this is
+no bug" answer and take the chance of learning how to interpret valgrind
+properly.
+
+If you need, for some reason, empty reports from valgrind for your project
+I suggest using suppression lists.
+
 
 =head1 AUTHOR