--- libev/ev.pod	2008/04/24 01:42:11	1.148
+++ libev/ev.pod	2011/01/10 14:24:26	1.351
@@ -4,69 +4,91 @@
 
 =head1 SYNOPSIS
 
-  #include <ev.h>
+   #include <ev.h>
 
 =head2 EXAMPLE PROGRAM
 
-  // a single header file is required
-  #include <ev.h>
+   // 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;
-
-  // 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");
-    // 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");
-    // 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
-    // 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);
-
-    // 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);
-
-    // now wait for events to arrive
-    ev_loop (loop, 0);
-
-    // unloop was called, so exit
-    return 0;
-  }
+   #include <stdio.h> // for puts
 
-=head1 DESCRIPTION
+   // every watcher type has its own typedef'd struct
+   // with the name ev_TYPE
+   ev_io stdin_watcher;
+   ev_timer timeout_watcher;
+
+   // all watcher callbacks have a similar signature
+   // this callback is called when data is readable on stdin
+   static void
+   stdin_cb (EV_P_ ev_io *w, int revents)
+   {
+     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_run's to stop iterating
+     ev_break (EV_A_ EVBREAK_ALL);
+   }
+
+   // another callback, this time for a time-out
+   static void
+   timeout_cb (EV_P_ ev_timer *w, int revents)
+   {
+     puts ("timeout");
+     // this causes the innermost ev_run to stop iterating
+     ev_break (EV_A_ EVBREAK_ONE);
+   }
+
+   int
+   main (void)
+   {
+     // use the default event loop unless you have special needs
+     struct ev_loop *loop = EV_DEFAULT;
+
+     // 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);
+
+     // 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);
+
+     // now wait for events to arrive
+     ev_run (loop, 0);
+
+     // unloop was called, so exit
+     return 0;
+   }
+
+=head1 ABOUT THIS DOCUMENT
+
+This document documents the libev software package.
 
 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>.
+
+While this document tries to be as complete as possible in documenting
+libev, its usage and the rationale behind its design, it is not a tutorial
+on event-based programming, nor will it introduce event-based programming
+with libev.
+
+Familiarity with event based programming techniques in general is assumed
+throughout this document.
+
+=head1 WHAT TO READ WHEN IN A HURRY
+
+This manual tries to be very detailed, but unfortunately, this also makes
+it very long. If you just want to know the basics of libev, I suggest
+reading L<ANATOMY OF A WATCHER>, then the L<EXAMPLE PROGRAM> above and
+look up the missing functions in L<GLOBAL FUNCTIONS> and the C<ev_io> and
+C<ev_timer> sections in L<WATCHER TYPES>.
+
+=head1 ABOUT LIBEV
 
 Libev is an event loop: you register interest in certain events (such as a
 file descriptor being readable or a timeout occurring), and it will manage
@@ -86,13 +108,14 @@
 Libev supports C<select>, C<poll>, the Linux-specific C<epoll>, the
 BSD-specific C<kqueue> and the Solaris-specific event port mechanisms
 for file descriptor events (C<ev_io>), the Linux C<inotify> interface
-(for C<ev_stat>), relative timers (C<ev_timer>), absolute timers
-with customised rescheduling (C<ev_periodic>), synchronous signals
-(C<ev_signal>), process status change events (C<ev_child>), and event
-watchers dealing with the event loop mechanism itself (C<ev_idle>,
-C<ev_embed>, C<ev_prepare> and C<ev_check> watchers) as well as
-file watchers (C<ev_stat>) and even limited support for fork events
-(C<ev_fork>).
+(for C<ev_stat>), Linux eventfd/signalfd (for faster and cleaner
+inter-thread wakeup (C<ev_async>)/signal handling (C<ev_signal>)) relative
+timers (C<ev_timer>), absolute timers with customised rescheduling
+(C<ev_periodic>), synchronous signals (C<ev_signal>), process status
+change events (C<ev_child>), and event watchers dealing with the event
+loop mechanism itself (C<ev_idle>, C<ev_embed>, C<ev_prepare> and
+C<ev_check> watchers) as well as file watchers (C<ev_stat>) and even
+limited support for fork events (C<ev_fork>).
 
 It also is quite fast (see this
 L<benchmark|http://libev.schmorp.de/bench.html> comparing it to libevent
@@ -110,14 +133,36 @@
 
 =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 some floatingpoint value. Unlike the name
-component C<stamp> might indicate, it is also used for time differences
-throughout libev.
+Libev represents time as a single floating point number, representing
+the (fractional) number of seconds since the (POSIX) epoch (in practice
+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. When you need to do
+any calculations on it, you should treat it as some floating point value.
+
+Unlike the name component C<stamp> might indicate, it is also used for
+time differences (e.g. delays) throughout libev.
+
+=head1 ERROR HANDLING
+
+Libev knows three classes of errors: operating system errors, usage errors
+and internal errors (bugs).
+
+When libev catches an operating system error it cannot handle (for example
+a system call indicating a condition libev cannot fix), it calls the callback
+set via C<ev_set_syserr_cb>, which is supposed to fix the problem or
+abort. The default is to print a diagnostic message and to call C<abort
+()>.
+
+When libev detects a usage error such as a negative timer interval, then
+it will print a diagnostic message and abort (via the C<assert> mechanism,
+so C<NDEBUG> will disable this checking): these are programming errors in
+the libev caller and need to be fixed there.
+
+Libev also has a few internal error-checking C<assert>ions, and also has
+extensive consistency checking code. These do not trigger under normal
+circumstances, as they indicate either a bug in libev or worse.
+
 
 =head1 GLOBAL FUNCTIONS
 
@@ -130,13 +175,14 @@
 
 Returns the current time as libev would use it. Please note that the
 C<ev_now> function is usually faster and also often returns the timestamp
-you actually want to know.
+you actually want to know. Also interesting is the combination of
+C<ev_update_now> and C<ev_now>.
 
 =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 ()>.
+this is a sub-second-resolution C<sleep ()>.
 
 =item int ev_version_major ()
 
@@ -157,11 +203,12 @@
 not a problem.
 
 Example: Make sure we haven't accidentally been linked against the wrong
-version.
+version (note, however, that this will not detect other ABI mismatches,
+such as LFS or reentrancy).
 
-  assert (("libev version mismatch",
-           ev_version_major () == EV_VERSION_MAJOR
-           && ev_version_minor () >= EV_VERSION_MINOR));
+   assert (("libev version mismatch",
+            ev_version_major () == EV_VERSION_MAJOR
+            && ev_version_minor () >= EV_VERSION_MINOR));
 
 =item unsigned int ev_supported_backends ()
 
@@ -173,25 +220,26 @@
 Example: make sure we have the epoll method, because yeah this is cool and
 a must have and can we have a torrent of it please!!!11
 
-  assert (("sorry, no epoll, no sex",
-           ev_supported_backends () & EVBACKEND_EPOLL));
+   assert (("sorry, no epoll, no sex",
+            ev_supported_backends () & EVBACKEND_EPOLL));
 
 =item unsigned int ev_recommended_backends ()
 
-Return the set of all backends compiled into this binary of libev and also
-recommended for this platform. This set is often smaller than the one
-returned by C<ev_supported_backends>, as for example kqueue is broken on
-most BSDs and will not be autodetected unless you explicitly request it
-(assuming you know what you are doing). This is the set of backends that
-libev will probe for if you specify no backends explicitly.
+Return the set of all backends compiled into this binary of libev and
+also recommended for this platform, meaning it will work for most file
+descriptor types. This set is often smaller than the one returned by
+C<ev_supported_backends>, as for example kqueue is broken on most BSDs
+and will not be auto-detected unless you explicitly request it (assuming
+you know what you are doing). This is the set of backends that libev will
+probe for if you specify no backends explicitly.
 
 =item unsigned int ev_embeddable_backends ()
 
 Returns the set of backends that are embeddable in other event loops. This
-is the theoretical, all-platform, value. To find which backends
-might be supported on the current system, you would need to look at
-C<ev_embeddable_backends () & ev_supported_backends ()>, likewise for
-recommended ones.
+value is platform-specific but can include backends not available on the
+current system. To find which embeddable backends might be supported on
+the current system, you would need to look at C<ev_embeddable_backends ()
+& ev_supported_backends ()>, likewise for recommended ones.
 
 See the description of C<ev_embed> watchers for more info.
 
@@ -231,12 +279,12 @@
    ...
    ev_set_allocator (persistent_realloc);
 
-=item ev_set_syserr_cb (void (*cb)(const char *msg));
+=item ev_set_syserr_cb (void (*cb)(const char *msg))
 
-Set the callback function to call on a retryable syscall error (such
+Set the callback function to call on a retryable system call error (such
 as failed select, poll, epoll_wait). The message is a printable string
 indicating the system call or subsystem causing the problem. If this
-callback is set, then libev will expect it to remedy the sitution, no
+callback is set, then libev will expect it to remedy the situation, no
 matter what, when it returns. That is, libev will generally retry the
 requested operation, or, if the condition doesn't go away, do bad stuff
 (such as abort).
@@ -253,36 +301,78 @@
    ...
    ev_set_syserr_cb (fatal_error);
 
+=item ev_feed_signal (int signum)
+
+This function can be used to "simulate" a signal receive. It is completely
+safe to call this function at any time, from any context, including signal
+handlers or random threads.
+
+Its main use is to customise signal handling in your process, especially
+in the presence of threads. For example, you could block signals
+by default in all threads (and specifying C<EVFLAG_NOSIGMASK> when
+creating any loops), and in one thread, use C<sigwait> or any other
+mechanism to wait for signals, then "deliver" them to libev by calling
+C<ev_feed_signal>.
+
 =back
 
-=head1 FUNCTIONS CONTROLLING THE EVENT LOOP
+=head1 FUNCTIONS CONTROLLING EVENT LOOPS
 
-An event loop is described by a C<struct ev_loop *>. The library knows two
-types of such loops, the I<default> loop, which supports signals and child
-events, and dynamically created loops which do not.
+An event loop is described by a C<struct ev_loop *> (the C<struct> is
+I<not> optional in this case unless libev 3 compatibility is disabled, as
+libev 3 had an C<ev_loop> function colliding with the struct name).
+
+The library knows two types of such loops, the I<default> loop, which
+supports child process events, and dynamically created event loops which
+do not.
 
 =over 4
 
 =item struct ev_loop *ev_default_loop (unsigned int flags)
 
-This will initialise the default event loop if it hasn't been initialised
-yet and return it. If the default loop could not be initialised, returns
-false. If it already was initialised it simply returns it (and ignores the
-flags. If that is troubling you, check C<ev_backend ()> afterwards).
+This returns the "default" event loop object, which is what you should
+normally use when you just need "the event loop". Event loop objects and
+the C<flags> parameter are described in more detail in the entry for
+C<ev_loop_new>.
+
+If the default loop is already initialised then this function simply
+returns it (and ignores the flags. If that is troubling you, check
+C<ev_backend ()> afterwards). Otherwise it will create it with the given
+flags, which should almost always be C<0>, unless the caller is also the
+one calling C<ev_run> or otherwise qualifies as "the main program".
 
 If you don't know what event loop to use, use the one returned from this
-function.
+function (or via the C<EV_DEFAULT> macro).
 
 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).
+from multiple threads, you have to employ some kind of mutex (note also
+that this case is unlikely, as loops cannot be shared easily between
+threads anyway).
+
+The default loop is the only loop that can handle C<ev_child> watchers,
+and to do this, it always registers a handler for C<SIGCHLD>. If this is
+a problem for your application you can either create a dynamic loop with
+C<ev_loop_new> which doesn't do that, or you can simply overwrite the
+C<SIGCHLD> signal handler I<after> calling C<ev_default_init>.
+
+Example: This is the most typical usage.
+
+   if (!ev_default_loop (0))
+     fatal ("could not initialise libev, bad $LIBEV_FLAGS in environment?");
+
+Example: Restrict libev to the select and poll backends, and do not allow
+environment settings to be taken into account:
+
+   ev_default_loop (EVBACKEND_POLL | EVBACKEND_SELECT | EVFLAG_NOENV);
+
+=item struct ev_loop *ev_loop_new (unsigned int flags)
+
+This will create and initialise a new event loop object. If the loop
+could not be initialised, returns false.
 
-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>.
+This function is thread-safe, and one common 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.
 
 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>).
@@ -298,7 +388,7 @@
 
 =item C<EVFLAG_NOENV>
 
-If this flag bit is ored into the flag value (or the program runs setuid
+If this flag bit is or'ed into the flag value (or the program runs setuid
 or setgid) then libev will I<not> look at the environment variable
 C<LIBEV_FLAGS>. Otherwise (the default), this environment variable will
 override the flags completely if it is found in the environment. This is
@@ -307,24 +397,55 @@
 
 =item C<EVFLAG_FORKCHECK>
 
-Instead of calling C<ev_default_fork> or C<ev_loop_fork> manually after
-a fork, you can also make libev check for a fork in each iteration by
-enabling this flag.
+Instead of calling C<ev_loop_fork> manually after a fork, you can also
+make libev check for a fork in each iteration by enabling this flag.
 
 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
 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
+without a system call 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
 forget about forgetting to tell libev about forking) when you use this
 flag.
 
-This flag setting cannot be overriden or specified in the C<LIBEV_FLAGS>
+This flag setting cannot be overridden or specified in the C<LIBEV_FLAGS>
 environment variable.
 
+=item C<EVFLAG_NOINOTIFY>
+
+When this flag is specified, then libev will not attempt to use the
+I<inotify> API for its C<ev_stat> watchers. Apart from debugging and
+testing, this flag can be useful to conserve inotify file descriptors, as
+otherwise each loop using C<ev_stat> watchers consumes one inotify handle.
+
+=item C<EVFLAG_SIGNALFD>
+
+When this flag is specified, then libev will attempt to use the
+I<signalfd> API for its C<ev_signal> (and C<ev_child>) watchers. This API
+delivers signals synchronously, which makes it both faster and might make
+it possible to get the queued signal data. It can also simplify signal
+handling with threads, as long as you properly block signals in your
+threads that are not interested in handling them.
+
+Signalfd will not be used by default as this changes your signal mask, and
+there are a lot of shoddy libraries and programs (glib's threadpool for
+example) that can't properly initialise their signal masks.
+
+=item C<EVFLAG_NOSIGMASK>
+
+When this flag is specified, then libev will avoid to modify the signal
+mask. Specifically, this means you ahve to make sure signals are unblocked
+when you want to receive them.
+
+This behaviour is useful when you want to do your own signal handling, or
+want to handle signals only in specific threads and want to avoid libev
+unblocking the signals.
+
+This flag's behaviour will become the default in future versions of libev.
+
 =item C<EVBACKEND_SELECT>  (value 1, portable select backend)
 
 This is your standard select(2) backend. Not I<completely> standard, as
@@ -334,11 +455,15 @@
 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
+parallelism (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
-readyness notifications you get per iteration.
+readiness notifications you get per iteration.
+
+This backend maps C<EV_READ> to the C<readfds> set and C<EV_WRITE> to the
+C<writefds> set (and to work around Microsoft Windows bugs, also onto the
+C<exceptfds> set on that platform).
 
 =item C<EVBACKEND_POLL>    (value 2, poll backend, available everywhere except on windows)
 
@@ -349,40 +474,76 @@
 i.e. O(total_fds). See the entry for C<EVBACKEND_SELECT>, above, for
 performance tips.
 
+This backend maps C<EV_READ> to C<POLLIN | POLLERR | POLLHUP>, and
+C<EV_WRITE> to C<POLLOUT | POLLERR | POLLHUP>.
+
 =item C<EVBACKEND_EPOLL>   (value 4, Linux)
 
+Use the linux-specific epoll(7) interface (for both pre- and post-2.6.9
+kernels).
+
 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). 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.
+epoll scales either O(1) or O(active_fds).
+
+The epoll mechanism deserves honorable mention as the most misdesigned
+of the more advanced event mechanisms: mere annoyances include silently
+dropping file descriptors, requiring a system call per change per file
+descriptor (and unnecessary guessing of parameters), problems with dup,
+returning before the timeout value, resulting in additional iterations
+(and only giving 5ms accuracy while select on the same platform gives
+0.1ms) and so on. The biggest issue is fork races, however - if a program
+forks then I<both> parent and child process have to recreate the epoll
+set, which can take considerable time (one syscall per file descriptor)
+and is of course hard to detect.
+
+Epoll is also notoriously buggy - embedding epoll fds I<should> work, but
+of course I<doesn't>, and epoll just loves to report events for totally
+I<different> file descriptors (even already closed ones, so one cannot
+even remove them from the set) than registered in the set (especially
+on SMP systems). Libev tries to counter these spurious notifications by
+employing an additional generation counter and comparing that against the
+events to filter out spurious ones, recreating the set when required. Last
+not least, it also refuses to work with some file descriptors which work
+perfectly fine with C<select> (files, many character devices...).
+
+Epoll is truly the train wreck analog among event poll mechanisms.
 
 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, 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.
+will result in some caching, there is still a system call per such
+incident (because the same I<file descriptor> could point to a different
+I<file description> now), so its best to avoid that. Also, C<dup ()>'ed
+file descriptors might not work very well if you register events for both
+file descriptors.
 
 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.
+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. Stopping and
+starting a watcher (without re-setting it) also usually doesn't cause
+extra overhead. A fork can both result in spurious notifications as well
+as in libev having to destroy and recreate the epoll object, which can
+take considerable time and thus should be avoided.
+
+All this means that, in practice, C<EVBACKEND_SELECT> can be as fast or
+faster than epoll for maybe up to a hundred file descriptors, depending on
+the usage. So sad.
 
-While nominally embeddeble in other event loops, this feature is broken in
+While nominally embeddable in other event loops, this feature is broken in
 all kernel versions tested so far.
 
+This backend maps C<EV_READ> and C<EV_WRITE> in the same way as
+C<EVBACKEND_POLL>.
+
 =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 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
+it's completely useless). Unlike epoll, however, whose brokenness
+is by design, these kqueue bugs can (and eventually will) be fixed
+without API changes to existing programs. For this reason it's not being
+"auto-detected" unless you explicitly specify it in the flags (i.e. using
 C<EVBACKEND_KQUEUE>) or libev was compiled on a known-to-be-good (-enough)
 system like NetBSD.
 
@@ -393,9 +554,10 @@
 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 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.
+cause an extra system call as with C<EVBACKEND_EPOLL>, it still adds up to
+two event changes per incident. Support for C<fork ()> is very bad (but
+sane, unlike epoll) and it drops fds silently in similarly hard-to-detect
+cases
 
 This backend usually performs well under most conditions.
 
@@ -403,8 +565,12 @@
 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.
+(e.g. C<EVBACKEND_SELECT> or C<EVBACKEND_POLL> (but C<poll> is of course
+also broken on OS X)) and, did I mention it, using it only for sockets.
+
+This backend maps C<EV_READ> into an C<EVFILT_READ> kevent with
+C<NOTE_EOF>, and C<EV_WRITE> into an C<EVFILT_WRITE> kevent with
+C<NOTE_EOF>.
 
 =item C<EVBACKEND_DEVPOLL> (value 16, Solaris 8)
 
@@ -418,18 +584,24 @@
 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 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 readyness notifications, this
-backend actually performed to specification in all tests and is fully
-embeddable, which is a rare feat among the OS-specific backends.
+On the positive side, this backend actually performed fully to
+specification in all tests and is fully embeddable, which is a rare feat
+among the OS-specific backends (I vastly prefer correctness over speed
+hacks).
+
+On the negative side, the interface is I<bizarre>, with the event polling
+function sometimes returning events to the caller even though an error
+occured, but with no indication whether it has done so or not (yes, it's
+even documented that way) - deadly for edge-triggered interfaces, but
+fortunately libev seems to be able to work around it.
+
+This backend maps C<EV_READ> and C<EV_WRITE> in the same way as
+C<EVBACKEND_POLL>.
 
 =item C<EVBACKEND_ALL>
 
@@ -437,109 +609,121 @@
 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.
+It is definitely not recommended to use this flag, use whatever
+C<ev_recommended_backends ()> returns, or simply do not specify a backend
+at all.
+
+=item C<EVBACKEND_MASK>
+
+Not a backend at all, but a mask to select all backend bits from a
+C<flags> value, in case you want to mask out any backends from a flags
+value (e.g. when modifying the C<LIBEV_FLAGS> environment variable).
 
 =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 listed here). If none are
-specified, all backends in C<ev_recommended_backends ()> will be tried.
-
-The most typical usage is like this:
-
-  if (!ev_default_loop (0))
-    fatal ("could not initialise libev, bad $LIBEV_FLAGS in environment?");
-
-Restrict libev to the select and poll backends, and do not allow
-environment settings to be taken into account:
-
-  ev_default_loop (EVBACKEND_POLL | EVBACKEND_SELECT | EVFLAG_NOENV);
+If one or more of the backend flags are or'ed into the flags value,
+then only these 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.
 
-Use whatever libev has to offer, but make sure that kqueue is used if
-available (warning, breaks stuff, best use only with your own private
-event loop and only if you know the OS supports your types of fds):
+Example: Try to create a event loop that uses epoll and nothing else.
 
-  ev_default_loop (ev_recommended_backends () | EVBACKEND_KQUEUE);
+   struct ev_loop *epoller = ev_loop_new (EVBACKEND_EPOLL | EVFLAG_NOENV);
+   if (!epoller)
+     fatal ("no epoll found here, maybe it hides under your chair");
 
-=item struct ev_loop *ev_loop_new (unsigned int flags)
+Example: Use whatever libev has to offer, but make sure that kqueue is
+used if available.
 
-Similar to C<ev_default_loop>, but always creates a new event loop that is
-always distinct from the default loop. Unlike the default loop, it cannot
-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 *loop = ev_loop_new (ev_recommended_backends () | EVBACKEND_KQUEUE);
 
-  struct ev_loop *epoller = ev_loop_new (EVBACKEND_EPOLL | EVFLAG_NOENV);
-  if (!epoller)
-    fatal ("no epoll found here, maybe it hides under your chair");
-
-=item ev_default_destroy ()
+=item ev_loop_destroy (loop)
 
-Destroys the default loop again (frees all memory and kernel state
+Destroys an event loop object (frees all memory and kernel state
 etc.). None of the active event watchers will be stopped in the normal
 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>
+responsibility to either stop all watchers cleanly yourself I<before>
 calling this function, or cope with the fact afterwards (which is usually
 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
-earlier call to C<ev_loop_new>.
+Note that certain global state, such as signal state (and installed signal
+handlers), will not be freed by this function, and related watchers (such
+as signal and child watchers) would need to be stopped manually.
+
+This function is normally used on loop objects allocated by
+C<ev_loop_new>, but it can also be used on the default loop returned by
+C<ev_default_loop>, in which case it is not thread-safe.
+
+Note that it is not advisable to call this function on the default loop
+except in the rare occasion where you really need to free its resources.
+If you need dynamically allocated loops it is better to use C<ev_loop_new>
+and C<ev_loop_destroy>.
 
-=item ev_default_fork ()
+=item ev_loop_fork (loop)
 
-This function sets a flag that causes subsequent C<ev_loop> iterations
-to reinitialise the kernel state for backends that have one. Despite the
+This function sets a flag that causes subsequent C<ev_run> 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.
+the child process. You I<must> call it (or use C<EVFLAG_FORKCHECK>) in the
+child before resuming or calling C<ev_run>.
+
+Again, you I<have> to call it on I<any> loop that you want to re-use after 
+a fork, I<even if you do not plan to use the loop in the parent>. This is
+because some kernel interfaces *cough* I<kqueue> *cough* do funny things
+during fork.
 
 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.
+process if and only if you want to use the event loop in the child. If
+you just fork+exec or create a new loop in the child, you don't have to
+call it at all (in fact, C<epoll> is so badly broken that it makes a
+difference, but libev will usually detect this case on its own and do a
+costly reset of the backend).
 
 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
-quite nicely into a call to C<pthread_atfork>:
+it just in case after a fork.
 
-    pthread_atfork (0, 0, ev_default_fork);
+Example: Automate calling C<ev_loop_fork> on the default loop when
+using pthreads.
 
-=item ev_loop_fork (loop)
+   static void
+   post_fork_child (void)
+   {
+     ev_loop_fork (EV_DEFAULT);
+   }
 
-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.
+   ...
+   pthread_atfork (0, 0, post_fork_child);
 
 =item int ev_is_default_loop (loop)
 
-Returns true when the given loop actually is the default loop, false otherwise.
+Returns true when the given loop is, in fact, the default loop, and false
+otherwise.
 
-=item unsigned int ev_loop_count (loop)
+=item unsigned int ev_iteration (loop)
 
-Returns the count of loop iterations for the loop, which is identical to
-the number of times libev did poll for new events. It starts at C<0> and
-happily wraps around with enough iterations.
+Returns the current iteration count for the event loop, which is identical
+to the number of times libev did poll for new events. It starts at C<0>
+and happily wraps around with enough iterations.
 
 This value can sometimes be useful as a generation counter of sorts (it
 "ticks" the number of loop iterations), as it roughly corresponds with
-C<ev_prepare> and C<ev_check> calls.
+C<ev_prepare> and C<ev_check> calls - and is incremented between the
+prepare and check phases.
+
+=item unsigned int ev_depth (loop)
+
+Returns the number of times C<ev_run> was entered minus the number of
+times C<ev_run> was exited normally, in other words, the recursion depth.
+
+Outside C<ev_run>, this number is zero. In a callback, this number is
+C<1>, unless C<ev_run> was invoked recursively (or from another thread),
+in which case it is higher.
+
+Leaving C<ev_run> abnormally (setjmp/longjmp, cancelling the thread,
+throwing an exception etc.), doesn't count as "exit" - consider this
+as a hint to avoid such ungentleman-like behaviour unless it's really
+convenient, in which case it is fully supported.
 
 =item unsigned int ev_backend (loop)
 
@@ -554,76 +738,142 @@
 time used for relative timers. You can treat it as the timestamp of the
 event occurring (or more correctly, libev finding out about it).
 
-=item ev_loop (loop, int flags)
+=item ev_now_update (loop)
+
+Establishes the current time by querying the kernel, updating the time
+returned by C<ev_now ()> in the progress. This is a costly operation and
+is usually done automatically within C<ev_run ()>.
+
+This function is rarely useful, but when some event callback runs for a
+very long time without entering the event loop, updating libev's idea of
+the current time is a good idea.
+
+See also L<The special problem of time updates> in the C<ev_timer> section.
+
+=item ev_suspend (loop)
+
+=item ev_resume (loop)
+
+These two functions suspend and resume an event loop, for use when the
+loop is not used for a while and timeouts should not be processed.
+
+A typical use case would be an interactive program such as a game:  When
+the user presses C<^Z> to suspend the game and resumes it an hour later it
+would be best to handle timeouts as if no time had actually passed while
+the program was suspended. This can be achieved by calling C<ev_suspend>
+in your C<SIGTSTP> handler, sending yourself a C<SIGSTOP> and calling
+C<ev_resume> directly afterwards to resume timer processing.
+
+Effectively, all C<ev_timer> watchers will be delayed by the time spend
+between C<ev_suspend> and C<ev_resume>, and all C<ev_periodic> watchers
+will be rescheduled (that is, they will lose any events that would have
+occurred while suspended).
+
+After calling C<ev_suspend> you B<must not> call I<any> function on the
+given loop other than C<ev_resume>, and you B<must not> call C<ev_resume>
+without a previous call to C<ev_suspend>.
+
+Calling C<ev_suspend>/C<ev_resume> has the side effect of updating the
+event loop time (see C<ev_now_update>).
+
+=item ev_run (loop, int flags)
 
 Finally, this is it, the event handler. This function usually is called
-after you initialised all your watchers and you want to start handling
-events.
+after you have initialised all your watchers and you want to start
+handling events. It will ask the operating system for any new events, call
+the watcher callbacks, an then repeat the whole process indefinitely: This
+is why event loops are called I<loops>.
 
-If the flags argument is specified as C<0>, it will not return until
-either no event watchers are active anymore or C<ev_unloop> was called.
+If the flags argument is specified as C<0>, it will keep handling events
+until either no event watchers are active anymore or C<ev_break> was
+called.
 
-Please note that an explicit C<ev_unloop> is usually better than
+Please note that an explicit C<ev_break> is usually better than
 relying on all watchers to be stopped when deciding when a program has
-finished (especially in interactive programs), but having a program that
-automatically loops as long as it has to and no longer by virtue of
-relying on its watchers stopping correctly is a thing of beauty.
-
-A flags value of C<EVLOOP_NONBLOCK> will look for new events, will handle
-those events and any outstanding ones, but will not block your process in
-case there are no events and will return after one iteration of the loop.
-
-A flags value of C<EVLOOP_ONESHOT> will look for new events (waiting if
-neccessary) and will handle those and any outstanding ones. It will block
-your process until at least one new event arrives, and will return after
-one iteration of the loop. This is useful if you are waiting for some
-external event in conjunction with something not expressible using other
-libev watchers. However, a pair of C<ev_prepare>/C<ev_check> watchers is
+finished (especially in interactive programs), but having a program
+that automatically loops as long as it has to and no longer by virtue
+of relying on its watchers stopping correctly, that is truly a thing of
+beauty.
+
+This function is also I<mostly> exception-safe - you can break out of
+a C<ev_run> call by calling C<longjmp> in a callback, throwing a C++
+exception and so on. This does not decrement the C<ev_depth> value, nor
+will it clear any outstanding C<EVBREAK_ONE> breaks.
+
+A flags value of C<EVRUN_NOWAIT> will look for new events, will handle
+those events and any already outstanding ones, but will not wait and
+block your process in case there are no events and will return after one
+iteration of the loop. This is sometimes useful to poll and handle new
+events while doing lengthy calculations, to keep the program responsive.
+
+A flags value of C<EVRUN_ONCE> will look for new events (waiting if
+necessary) and will handle those and any already outstanding ones. It
+will block your process until at least one new event arrives (which could
+be an event internal to libev itself, so there is no guarantee that a
+user-registered callback will be called), and will return after one
+iteration of the loop.
+
+This is useful if you are waiting for some external event in conjunction
+with something not expressible using other libev watchers (i.e. "roll your
+own C<ev_run>"). However, a pair of C<ev_prepare>/C<ev_check> watchers is
 usually a better approach for this kind of thing.
 
-Here are the gory details of what C<ev_loop> does:
+Here are the gory details of what C<ev_run> does:
 
+   - Increment loop depth.
+   - Reset the ev_break status.
    - 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.
+   LOOP:
+   - If EVFLAG_FORKCHECK was used, check for a fork.
+   - If a fork was detected (by any means), queue and call all fork watchers.
    - Queue and call all prepare watchers.
-   - If we have been forked, recreate the kernel state.
+   - If ev_break was called, goto FINISH.
+   - If we have been forked, detach and recreate the kernel state
+     as to not disturb the other process.
    - Update the kernel state with all outstanding changes.
-   - Update the "event loop time".
+   - Update the "event loop time" (ev_now ()).
    - Calculate for how long to sleep or block, if at all
-     (active idle watchers, EVLOOP_NONBLOCK or not having
+     (active idle watchers, EVRUN_NOWAIT or not having
      any active watchers at all will result in not sleeping).
    - Sleep if the I/O and timer collect interval say so.
+   - Increment loop iteration counter.
    - Block the process, waiting for any events.
    - Queue all outstanding I/O (fd) events.
-   - Update the "event loop time" and do time jump handling.
-   - Queue all outstanding timers.
-   - Queue all outstanding periodics.
-   - If no events are pending now, queue all idle watchers.
+   - Update the "event loop time" (ev_now ()), and do time jump adjustments.
+   - Queue all expired timers.
+   - Queue all expired periodics.
+   - Queue all idle watchers with priority higher than that of pending events.
    - Queue all check watchers.
    - 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, or there are no active watchers, return, otherwise
-     continue with step *.
+   - If ev_break has been called, or EVRUN_ONCE or EVRUN_NOWAIT
+     were used, or there are no active watchers, goto FINISH, otherwise
+     continue with step LOOP.
+   FINISH:
+   - Reset the ev_break status iff it was EVBREAK_ONE.
+   - Decrement the loop depth.
+   - Return.
 
 Example: Queue some jobs and then loop until no events are outstanding
 anymore.
 
    ... queue jobs here, make sure they register event watchers as long
    ... as they still have work to do (even an idle watcher will do..)
-   ev_loop (my_loop, 0);
-   ... jobs done. yeah!
+   ev_run (my_loop, 0);
+   ... jobs done or somebody called unloop. yeah!
 
-=item ev_unloop (loop, how)
+=item ev_break (loop, how)
 
-Can be used to make a call to C<ev_loop> return early (but only after it
+Can be used to make a call to C<ev_run> return early (but only after it
 has processed all outstanding events). The C<how> argument must be either
-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.
+C<EVBREAK_ONE>, which will make the innermost C<ev_run> call return, or
+C<EVBREAK_ALL>, which will make all nested C<ev_run> calls return.
+
+This "break state" will be cleared on the next call to C<ev_run>.
 
-This "unloop state" will be cleared when entering C<ev_loop> again.
+It is safe to call C<ev_break> from outside any C<ev_run> calls, too, in
+which case it will have no effect.
 
 =item ev_ref (loop)
 
@@ -631,45 +881,53 @@
 
 Ref/unref can be used to add or remove a reference count on the event
 loop: Every watcher keeps one reference, and as long as the reference
-count is nonzero, C<ev_loop> will not return on its own. If you have
-a watcher you never unregister that should not keep C<ev_loop> from
-returning, ev_unref() after starting, and ev_ref() before stopping it. For
-example, libev itself uses this for its internal signal pipe: It is not
-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>
-(but only if the watcher wasn't active before, or was active before,
-respectively).
+count is nonzero, C<ev_run> will not return on its own.
+
+This is useful when you have a watcher that you never intend to
+unregister, but that nevertheless should not keep C<ev_run> from
+returning. In such a case, call C<ev_unref> after starting, and C<ev_ref>
+before stopping it.
+
+As an example, libev itself uses this for its internal signal pipe: It
+is not visible to the libev user and should not keep C<ev_run> 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> (but only if the watcher wasn't active before, or was active
+before, respectively. Note also that libev might stop watchers itself
+(e.g. non-repeating timers) in which case you have to C<ev_ref>
+in the callback).
 
-Example: Create a signal watcher, but keep it from keeping C<ev_loop>
+Example: Create a signal watcher, but keep it from keeping C<ev_run>
 running when nothing else is active.
 
-  struct ev_signal exitsig;
-  ev_signal_init (&exitsig, sig_cb, SIGINT);
-  ev_signal_start (loop, &exitsig);
-  evf_unref (loop);
+   ev_signal exitsig;
+   ev_signal_init (&exitsig, sig_cb, SIGINT);
+   ev_signal_start (loop, &exitsig);
+   ev_unref (loop);
 
 Example: For some weird reason, unregister the above signal handler again.
 
-  ev_ref (loop);
-  ev_signal_stop (loop, &exitsig);
+   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.
+for events. Both time intervals 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
+allows libev to delay invocation of I/O and timer/periodic callbacks
+to increase efficiency of loop iterations (or to increase power-saving
+opportunities).
+
+The idea 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.
 
@@ -677,65 +935,176 @@
 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.
+introduce an additional C<ev_sleep ()> call into most loop iterations. The
+sleep time ensures that libev will not poll for I/O events more often then
+once per this interval, on average.
 
 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.
+latency/jitter/inexactness (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
+Many (busy) programs can usually benefit by setting the I/O 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.
+as this approaches the timing granularity of most systems. Note that if
+you do transactions with the outside world and you can't increase the
+parallelity, then this setting will limit your transaction rate (if you
+need to poll once per transaction and the I/O collect interval is 0.01,
+then you can't do more than 100 transactions per second).
+
+Setting the I<timeout collect interval> can improve the opportunity for
+saving power, as the program will "bundle" timer callback invocations that
+are "near" in time together, by delaying some, thus reducing the number of
+times the process sleeps and wakes up again. Another useful technique to
+reduce iterations/wake-ups is to use C<ev_periodic> watchers and make sure
+they fire on, say, one-second boundaries only.
+
+Example: we only need 0.1s timeout granularity, and we wish not to poll
+more often than 100 times per second:
+
+   ev_set_timeout_collect_interval (EV_DEFAULT_UC_ 0.1);
+   ev_set_io_collect_interval (EV_DEFAULT_UC_ 0.01);
+
+=item ev_invoke_pending (loop)
+
+This call will simply invoke all pending watchers while resetting their
+pending state. Normally, C<ev_run> does this automatically when required,
+but when overriding the invoke callback this call comes handy. This
+function can be invoked from a watcher - this can be useful for example
+when you want to do some lengthy calculation and want to pass further
+event handling to another thread (you still have to make sure only one
+thread executes within C<ev_invoke_pending> or C<ev_run> of course).
+
+=item int ev_pending_count (loop)
+
+Returns the number of pending watchers - zero indicates that no watchers
+are pending.
+
+=item ev_set_invoke_pending_cb (loop, void (*invoke_pending_cb)(EV_P))
+
+This overrides the invoke pending functionality of the loop: Instead of
+invoking all pending watchers when there are any, C<ev_run> will call
+this callback instead. This is useful, for example, when you want to
+invoke the actual watchers inside another context (another thread etc.).
+
+If you want to reset the callback, use C<ev_invoke_pending> as new
+callback.
+
+=item ev_set_loop_release_cb (loop, void (*release)(EV_P), void (*acquire)(EV_P))
+
+Sometimes you want to share the same loop between multiple threads. This
+can be done relatively simply by putting mutex_lock/unlock calls around
+each call to a libev function.
+
+However, C<ev_run> can run an indefinite time, so it is not feasible
+to wait for it to return. One way around this is to wake up the event
+loop via C<ev_break> and C<av_async_send>, another way is to set these
+I<release> and I<acquire> callbacks on the loop.
+
+When set, then C<release> will be called just before the thread is
+suspended waiting for new events, and C<acquire> is called just
+afterwards.
+
+Ideally, C<release> will just call your mutex_unlock function, and
+C<acquire> will just call the mutex_lock function again.
+
+While event loop modifications are allowed between invocations of
+C<release> and C<acquire> (that's their only purpose after all), no
+modifications done will affect the event loop, i.e. adding watchers will
+have no effect on the set of file descriptors being watched, or the time
+waited. Use an C<ev_async> watcher to wake up C<ev_run> when you want it
+to take note of any changes you made.
+
+In theory, threads executing C<ev_run> will be async-cancel safe between
+invocations of C<release> and C<acquire>.
+
+See also the locking example in the C<THREADS> section later in this
+document.
+
+=item ev_set_userdata (loop, void *data)
+
+=item void *ev_userdata (loop)
+
+Set and retrieve a single C<void *> associated with a loop. When
+C<ev_set_userdata> has never been called, then C<ev_userdata> returns
+C<0>.
+
+These two functions can be used to associate arbitrary data with a loop,
+and are intended solely for the C<invoke_pending_cb>, C<release> and
+C<acquire> callbacks described above, but of course can be (ab-)used for
+any other purpose as well.
+
+=item ev_verify (loop)
+
+This function only does something when C<EV_VERIFY> support has been
+compiled in, which is the default for non-minimal builds. It tries to go
+through all internal structures and checks them for validity. If anything
+is found to be inconsistent, it will print an error message to standard
+error and call C<abort ()>.
+
+This can be used to catch bugs inside libev itself: under normal
+circumstances, this function will never abort as of course libev keeps its
+data structures consistent.
 
 =back
 
 
 =head1 ANATOMY OF A WATCHER
 
-A watcher is a structure that you create and register to record your
-interest in some event. For instance, if you want to wait for STDIN to
-become readable, you would create an C<ev_io> watcher for that:
-
-  static void my_cb (struct ev_loop *loop, struct ev_io *w, int revents)
-  {
-    ev_io_stop (w);
-    ev_unloop (loop, EVUNLOOP_ALL);
-  }
-
-  struct ev_loop *loop = ev_default_loop (0);
-  struct ev_io stdin_watcher;
-  ev_init (&stdin_watcher, my_cb);
-  ev_io_set (&stdin_watcher, STDIN_FILENO, EV_READ);
-  ev_io_start (loop, &stdin_watcher);
-  ev_loop (loop, 0);
+In the following description, uppercase C<TYPE> in names stands for the
+watcher type, e.g. C<ev_TYPE_start> can mean C<ev_timer_start> for timer
+watchers and C<ev_io_start> for I/O watchers.
+
+A watcher is an opaque structure that you allocate and register to record
+your interest in some event. To make a concrete example, imagine you want
+to wait for STDIN to become readable, you would create an C<ev_io> watcher
+for that:
+
+   static void my_cb (struct ev_loop *loop, ev_io *w, int revents)
+   {
+     ev_io_stop (w);
+     ev_break (loop, EVBREAK_ALL);
+   }
+
+   struct ev_loop *loop = ev_default_loop (0);
+
+   ev_io stdin_watcher;
+
+   ev_init (&stdin_watcher, my_cb);
+   ev_io_set (&stdin_watcher, STDIN_FILENO, EV_READ);
+   ev_io_start (loop, &stdin_watcher);
+
+   ev_run (loop, 0);
 
 As you can see, you are responsible for allocating the memory for your
-watcher structures (and it is usually a bad idea to do this on the stack,
-although this can sometimes be quite valid).
+watcher structures (and it is I<usually> a bad idea to do this on the
+stack).
 
-Each watcher structure must be initialised by a call to C<ev_init
-(watcher *, callback)>, which expects a callback to be provided. This
-callback gets invoked each time the event occurs (or, in the case of io
-watchers, each time the event loop detects that the file descriptor given
-is readable and/or writable).
-
-Each watcher type has its own C<< ev_<type>_set (watcher *, ...) >> macro
-with arguments specific to this watcher type. There is also a macro
-to combine initialisation and setting in one call: C<< ev_<type>_init
-(watcher *, callback, ...) >>.
+Each watcher has an associated watcher structure (called C<struct ev_TYPE>
+or simply C<ev_TYPE>, as typedefs are provided for all watcher structs).
+
+Each watcher structure must be initialised by a call to C<ev_init (watcher
+*, callback)>, which expects a callback to be provided. This callback is
+invoked each time the event occurs (or, in the case of I/O watchers, each
+time the event loop detects that the file descriptor given is readable
+and/or writable).
+
+Each watcher type further has its own C<< ev_TYPE_set (watcher *, ...) >>
+macro to configure it, with arguments specific to the watcher type. There
+is also a macro to combine initialisation and setting in one call: C<<
+ev_TYPE_init (watcher *, callback, ...) >>.
 
 To make the watcher actually watch out for events, you have to start it
-with a watcher-specific start function (C<< ev_<type>_start (loop, watcher
+with a watcher-specific start function (C<< ev_TYPE_start (loop, watcher
 *) >>), and you can stop watching for events at any time by calling the
-corresponding stop function (C<< ev_<type>_stop (loop, watcher *) >>.
+corresponding stop function (C<< ev_TYPE_stop (loop, watcher *) >>.
 
 As long as your watcher is active (has been started but not stopped) you
 must not touch the values stored in it. Most specifically you must never
-reinitialise it or call its C<set> macro.
+reinitialise it or call its C<ev_TYPE_set> macro.
 
 Each and every callback receives the event loop pointer as first, the
 registered watcher structure as second, and a bitset of received events as
@@ -754,7 +1123,7 @@
 The file descriptor in the C<ev_io> watcher has become readable and/or
 writable.
 
-=item C<EV_TIMEOUT>
+=item C<EV_TIMER>
 
 The C<ev_timer> watcher has timed out.
 
@@ -782,13 +1151,13 @@
 
 =item C<EV_CHECK>
 
-All C<ev_prepare> watchers are invoked just I<before> C<ev_loop> starts
+All C<ev_prepare> watchers are invoked just I<before> C<ev_run> starts
 to gather new events, and all C<ev_check> watchers are invoked just after
-C<ev_loop> has gathered them, but before it invokes any callbacks for any
+C<ev_run> has gathered them, but before it invokes any callbacks for any
 received events. Callbacks of both watcher types can start and stop as
 many watchers as they want, and all of them will be taken into account
 (for example, a C<ev_prepare> watcher might start an idle watcher to keep
-C<ev_loop> from blocking).
+C<ev_run> from blocking).
 
 =item C<EV_EMBED>
 
@@ -799,31 +1168,42 @@
 The event loop has been resumed in the child process after fork (see
 C<ev_fork>).
 
+=item C<EV_CLEANUP>
+
+The event loop is about to be destroyed (see C<ev_cleanup>).
+
 =item C<EV_ASYNC>
 
 The given async watcher has been asynchronously notified (see C<ev_async>).
 
+=item C<EV_CUSTOM>
+
+Not ever sent (or otherwise used) by libev itself, but can be freely used
+by libev users to signal watchers (e.g. via C<ev_feed_event>).
+
 =item C<EV_ERROR>
 
-An unspecified error has occured, the watcher has been stopped. This might
+An unspecified error has occurred, the watcher has been stopped. This might
 happen because the watcher could not be properly started because libev
 ran out of memory, a file descriptor was found to be closed or any other
-problem. You best act on it by reporting the problem and somehow coping
-with the watcher being stopped.
+problem. Libev considers these application bugs.
 
-Libev will usually signal a few "dummy" events together with an error,
-for example it might indicate that a fd is readable or writable, and if
-your callbacks is well-written it can just attempt the operation and cope
-with the error from read() or write(). This will not work in multithreaded
-programs, though, so beware.
+You best act on it by reporting the problem and somehow coping with the
+watcher being stopped. Note that well-written programs should not receive
+an error ever, so when your watcher receives it, this usually indicates a
+bug in your program.
+
+Libev will usually signal a few "dummy" events together with an error, for
+example it might indicate that a fd is readable or writable, and if your
+callbacks is well-written it can just attempt the operation and cope with
+the error from read() or write(). This will not work in multi-threaded
+programs, though, as the fd could already be closed and reused for another
+thing, so beware.
 
 =back
 
 =head2 GENERIC WATCHER FUNCTIONS
 
-In the following description, C<TYPE> stands for the watcher type,
-e.g. C<timer> for C<ev_timer> watchers and C<io> for C<ev_io> watchers.
-
 =over 4
 
 =item C<ev_init> (ev_TYPE *watcher, callback)
@@ -838,10 +1218,16 @@
 You can reinitialise a watcher at any time as long as it has been stopped
 (or never started) and there are no pending events outstanding.
 
-The callback is always of type C<void (*)(ev_loop *loop, ev_TYPE *watcher,
+The callback is always of type C<void (*)(struct ev_loop *loop, ev_TYPE *watcher,
 int revents)>.
 
-=item C<ev_TYPE_set> (ev_TYPE *, [args])
+Example: Initialise an C<ev_io> watcher in two steps.
+
+   ev_io w;
+   ev_init (&w, my_cb);
+   ev_io_set (&w, STDIN_FILENO, EV_READ);
+
+=item C<ev_TYPE_set> (ev_TYPE *watcher, [args])
 
 This macro initialises the type-specific parts of a watcher. You need to
 call C<ev_init> at least once before you call this macro, but you can
@@ -852,25 +1238,38 @@
 Although some watcher types do not have type-specific arguments
 (e.g. C<ev_prepare>) you still need to call its C<set> macro.
 
+See C<ev_init>, above, for an example.
+
 =item C<ev_TYPE_init> (ev_TYPE *watcher, callback, [args])
 
-This convinience macro rolls both C<ev_init> and C<ev_TYPE_set> macro
-calls into a single call. This is the most convinient method to initialise
+This convenience macro rolls both C<ev_init> and C<ev_TYPE_set> macro
+calls into a single call. This is the most convenient method to initialise
 a watcher. The same limitations apply, of course.
 
-=item C<ev_TYPE_start> (loop *, ev_TYPE *watcher)
+Example: Initialise and set an C<ev_io> watcher in one step.
+
+   ev_io_init (&w, my_cb, STDIN_FILENO, EV_READ);
+
+=item C<ev_TYPE_start> (loop, ev_TYPE *watcher)
 
 Starts (activates) the given watcher. Only active watchers will receive
 events. If the watcher is already active nothing will happen.
 
-=item C<ev_TYPE_stop> (loop *, ev_TYPE *watcher)
+Example: Start the C<ev_io> watcher that is being abused as example in this
+whole section.
+
+   ev_io_start (EV_DEFAULT_UC, &w);
+
+=item C<ev_TYPE_stop> (loop, ev_TYPE *watcher)
 
-Stops the given watcher again (if active) and clears the pending
-status. It is possible that stopped watchers are pending (for example,
-non-repeating timers are being stopped when they become pending), but
-C<ev_TYPE_stop> ensures that the watcher is neither active nor pending. If
-you want to free or reuse the memory used by the watcher it is therefore a
-good idea to always call its C<ev_TYPE_stop> function.
+Stops the given watcher if active, and clears the pending status (whether
+the watcher was active or not).
+
+It is possible that stopped watchers are pending - for example,
+non-repeating timers are being stopped when they become pending - but
+calling C<ev_TYPE_stop> ensures that the watcher is neither active nor
+pending. If you want to free or reuse the memory used by the watcher it is
+therefore a good idea to always call its C<ev_TYPE_stop> function.
 
 =item bool ev_is_active (ev_TYPE *watcher)
 
@@ -896,7 +1295,7 @@
 Change the callback. You can change the callback at virtually any time
 (modulo threads).
 
-=item ev_set_priority (ev_TYPE *watcher, priority)
+=item ev_set_priority (ev_TYPE *watcher, int priority)
 
 =item int ev_priority (ev_TYPE *watcher)
 
@@ -906,96 +1305,280 @@
 before watchers with lower priority, but priority will not keep watchers
 from being executed (except for C<ev_idle> watchers).
 
-This means that priorities are I<only> used for ordering callback
-invocation after new events have been received. This is useful, for
-example, to reduce latency after idling, or more often, to bind two
-watchers on the same event and make sure one is called first.
-
 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.
 
+Setting a priority outside the range of C<EV_MINPRI> to C<EV_MAXPRI> is
+fine, as long as you do not mind that the priority value you query might
+or might not have been clamped to the valid range.
+
 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 :).
 
-Setting a priority outside the range of C<EV_MINPRI> to C<EV_MAXPRI> is
-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.
+See L<WATCHER PRIORITY MODELS>, below, for a more thorough treatment of
+priorities.
 
 =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.
+can deal with that fact, as both are simply passed through to the
+callback.
 
 =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
+If the watcher is pending, this function 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
+Sometimes it can be useful to "poll" a watcher instead of waiting for its
+callback to be invoked, which can be accomplished with this function.
+
+=item ev_feed_event (loop, ev_TYPE *watcher, int revents)
+
+Feeds the given event set into the event loop, as if the specified event
+had happened for the specified watcher (which must be a pointer to an
+initialised but not necessarily started event watcher). Obviously you must
+not free the watcher as long as it has pending events.
 
+Stopping the watcher, letting libev invoke it, or calling
+C<ev_clear_pending> will clear the pending event, even if the watcher was
+not started in the first place.
+
+See also C<ev_feed_fd_event> and C<ev_feed_signal_event> for related
+functions that do not need a watcher.
+
+=back
 
 =head2 ASSOCIATING CUSTOM DATA WITH A WATCHER
 
 Each watcher has, by default, a member C<void *data> that you can change
-and read at any time, libev will completely ignore it. This can be used
+and read at any time: libev will completely ignore it. This can be used
 to associate arbitrary data with your watcher. If you need more data and
 don't want to allocate memory and store a pointer to it in that data
 member, you can also "subclass" the watcher type and provide your own
 data:
 
-  struct my_io
-  {
-    struct ev_io io;
-    int otherfd;
-    void *somedata;
-    struct whatever *mostinteresting;
-  }
+   struct my_io
+   {
+     ev_io io;
+     int otherfd;
+     void *somedata;
+     struct whatever *mostinteresting;
+   };
+
+   ...
+   struct my_io w;
+   ev_io_init (&w.io, my_cb, fd, EV_READ);
 
 And since your callback will be called with a pointer to the watcher, you
 can cast it back to your own type:
 
-  static void my_cb (struct ev_loop *loop, struct ev_io *w_, int revents)
-  {
-    struct my_io *w = (struct my_io *)w_;
-    ...
-  }
+   static void my_cb (struct ev_loop *loop, ev_io *w_, int revents)
+   {
+     struct my_io *w = (struct my_io *)w_;
+     ...
+   }
 
 More interesting and less C-conformant ways of casting your callback type
 instead have been omitted.
 
-Another common scenario is having some data structure with multiple
-watchers:
+Another common scenario is to use some data structure with multiple
+embedded watchers:
+
+   struct my_biggy
+   {
+     int some_data;
+     ev_timer t1;
+     ev_timer t2;
+   }
+
+In this case getting the pointer to C<my_biggy> is a bit more
+complicated: Either you store the address of your C<my_biggy> struct
+in the C<data> member of the watcher (for woozies), or you need to use
+some pointer arithmetic using C<offsetof> inside your watchers (for real
+programmers):
+
+   #include <stddef.h>
+
+   static void
+   t1_cb (EV_P_ ev_timer *w, int revents)
+   {
+     struct my_biggy big = (struct my_biggy *)
+       (((char *)w) - offsetof (struct my_biggy, t1));
+   }
+
+   static void
+   t2_cb (EV_P_ ev_timer *w, int revents)
+   {
+     struct my_biggy big = (struct my_biggy *)
+       (((char *)w) - offsetof (struct my_biggy, t2));
+   }
+
+=head2 WATCHER STATES
+
+There are various watcher states mentioned throughout this manual -
+active, pending and so on. In this section these states and the rules to
+transition between them will be described in more detail - and while these
+rules might look complicated, they usually do "the right thing".
+
+=over 4
+
+=item initialiased
+
+Before a watcher can be registered with the event looop it has to be
+initialised. This can be done with a call to C<ev_TYPE_init>, or calls to
+C<ev_init> followed by the watcher-specific C<ev_TYPE_set> function.
+
+In this state it is simply some block of memory that is suitable for use
+in an event loop. It can be moved around, freed, reused etc. at will.
+
+=item started/running/active
+
+Once a watcher has been started with a call to C<ev_TYPE_start> it becomes
+property of the event loop, and is actively waiting for events. While in
+this state it cannot be accessed (except in a few documented ways), moved,
+freed or anything else - the only legal thing is to keep a pointer to it,
+and call libev functions on it that are documented to work on active watchers.
+
+=item pending
+
+If a watcher is active and libev determines that an event it is interested
+in has occurred (such as a timer expiring), it will become pending. It will
+stay in this pending state until either it is stopped or its callback is
+about to be invoked, so it is not normally pending inside the watcher
+callback.
+
+The watcher might or might not be active while it is pending (for example,
+an expired non-repeating timer can be pending but no longer active). If it
+is stopped, it can be freely accessed (e.g. by calling C<ev_TYPE_set>),
+but it is still property of the event loop at this time, so cannot be
+moved, freed or reused. And if it is active the rules described in the
+previous item still apply.
+
+It is also possible to feed an event on a watcher that is not active (e.g.
+via C<ev_feed_event>), in which case it becomes pending without being
+active.
+
+=item stopped
+
+A watcher can be stopped implicitly by libev (in which case it might still
+be pending), or explicitly by calling its C<ev_TYPE_stop> function. The
+latter will clear any pending state the watcher might be in, regardless
+of whether it was active or not, so stopping a watcher explicitly before
+freeing it is often a good idea.
+
+While stopped (and not pending) the watcher is essentially in the
+initialised state, that is it can be reused, moved, modified in any way
+you wish.
+
+=back
+
+=head2 WATCHER PRIORITY MODELS
+
+Many event loops support I<watcher priorities>, which are usually small
+integers that influence the ordering of event callback invocation
+between watchers in some way, all else being equal.
+
+In libev, Watcher priorities can be set using C<ev_set_priority>. See its
+description for the more technical details such as the actual priority
+range.
+
+There are two common ways how these these priorities are being interpreted
+by event loops:
+
+In the more common lock-out model, higher priorities "lock out" invocation
+of lower priority watchers, which means as long as higher priority
+watchers receive events, lower priority watchers are not being invoked.
+
+The less common only-for-ordering model uses priorities solely to order
+callback invocation within a single event loop iteration: Higher priority
+watchers are invoked before lower priority ones, but they all get invoked
+before polling for new events.
+
+Libev uses the second (only-for-ordering) model for all its watchers
+except for idle watchers (which use the lock-out model).
+
+The rationale behind this is that implementing the lock-out model for
+watchers is not well supported by most kernel interfaces, and most event
+libraries will just poll for the same events again and again as long as
+their callbacks have not been executed, which is very inefficient in the
+common case of one high-priority watcher locking out a mass of lower
+priority ones.
+
+Static (ordering) priorities are most useful when you have two or more
+watchers handling the same resource: a typical usage example is having an
+C<ev_io> watcher to receive data, and an associated C<ev_timer> to handle
+timeouts. Under load, data might be received while the program handles
+other jobs, but since timers normally get invoked first, the timeout
+handler will be executed before checking for data. In that case, giving
+the timer a lower priority than the I/O watcher ensures that I/O will be
+handled first even under adverse conditions (which is usually, but not
+always, what you want).
+
+Since idle watchers use the "lock-out" model, meaning that idle watchers
+will only be executed when no same or higher priority watchers have
+received events, they can be used to implement the "lock-out" model when
+required.
+
+For example, to emulate how many other event libraries handle priorities,
+you can associate an C<ev_idle> watcher to each such watcher, and in
+the normal watcher callback, you just start the idle watcher. The real
+processing is done in the idle watcher callback. This causes libev to
+continuously poll and process kernel event data for the watcher, but when
+the lock-out case is known to be rare (which in turn is rare :), this is
+workable.
+
+Usually, however, the lock-out model implemented that way will perform
+miserably under the type of load it was designed to handle. In that case,
+it might be preferable to stop the real watcher before starting the
+idle watcher, so the kernel will not have to process the event in case
+the actual processing will be delayed for considerable time.
+
+Here is an example of an I/O watcher that should run at a strictly lower
+priority than the default, and which should only process data when no
+other events are pending:
+
+   ev_idle idle; // actual processing watcher
+   ev_io io;     // actual event watcher
+
+   static void
+   io_cb (EV_P_ ev_io *w, int revents)
+   {
+     // stop the I/O watcher, we received the event, but
+     // are not yet ready to handle it.
+     ev_io_stop (EV_A_ w);
+
+     // start the idle watcher to handle the actual event.
+     // it will not be executed as long as other watchers
+     // with the default priority are receiving events.
+     ev_idle_start (EV_A_ &idle);
+   }
+
+   static void
+   idle_cb (EV_P_ ev_idle *w, int revents)
+   {
+     // actual processing
+     read (STDIN_FILENO, ...);
+
+     // have to start the I/O watcher again, as
+     // we have handled the event
+     ev_io_start (EV_P_ &io);
+   }
 
-  struct my_biggy
-  {
-    int some_data;
-    ev_timer t1;
-    ev_timer t2;
-  }
-
-In this case getting the pointer to C<my_biggy> is a bit more complicated,
-you need to use C<offsetof>:
-
-  #include <stddef.h>
-
-  static void
-  t1_cb (EV_P_ struct ev_timer *w, int revents)
-  {
-    struct my_biggy big = (struct my_biggy *
-      (((char *)w) - offsetof (struct my_biggy, t1));
-  }
-
-  static void
-  t2_cb (EV_P_ struct ev_timer *w, int revents)
-  {
-    struct my_biggy big = (struct my_biggy *
-      (((char *)w) - offsetof (struct my_biggy, t2));
-  }
+   // initialisation
+   ev_idle_init (&idle, idle_cb);
+   ev_io_init (&io, io_cb, STDIN_FILENO, EV_READ);
+   ev_io_start (EV_DEFAULT_ &io);
+
+In the "real" world, it might also be beneficial to start a timer, so that
+low-priority connections can not be locked out forever under load. This
+enables your program to keep a lower latency for important connections
+during short periods of high load, while not completely locking out less
+important ones.
 
 
 =head1 WATCHER TYPES
@@ -1029,30 +1612,36 @@
 descriptors to non-blocking mode is also usually a good idea (but not
 required if you know what you are doing).
 
-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>).
+If you cannot use non-blocking mode, 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>). The same applies to file
+descriptors for which non-blocking operation makes no sense (such as
+files) - libev doesn't guarantee any specific behaviour in that case.
 
 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
+lot of those (for example Solaris ports), it is very easy to get into
 this situation even with a relatively standard program structure. Thus
 it is best to always use non-blocking I/O: An extra C<read>(2) returning
 C<EAGAIN> is far preferable to a program hanging until some data arrives.
 
-If you cannot run the fd in non-blocking mode (for example you should not
-play around with an Xlib connection), then you have to seperately re-test
-whether a file descriptor is really ready with a known-to-be good interface
-such as poll (fortunately in our Xlib example, Xlib already does this on
-its own, so its quite safe to use).
+If you cannot run the fd in non-blocking mode (for example you should
+not play around with an Xlib connection), then you have to separately
+re-test whether a file descriptor is really ready with a known-to-be good
+interface such as poll (fortunately in our Xlib example, Xlib already
+does this on its own, so its quite safe to use). Some people additionally
+use C<SIGALRM> and an interval timer, just to be sure you won't block
+indefinitely.
+
+But really, best use non-blocking mode.
 
 =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 (either due to calling C<close> explicitly or any other means,
+such as C<dup2>). 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
@@ -1093,16 +1682,53 @@
 
 =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.
+While not really specific to libev, it is easy to forget about C<SIGPIPE>:
+when writing to a pipe whose other end has been closed, your program gets
+sent 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 The special problem of accept()ing when you can't
+
+Many implementations of the POSIX C<accept> function (for example,
+found in post-2004 Linux) have the peculiar behaviour of not removing a
+connection from the pending queue in all error cases.
+
+For example, larger servers often run out of file descriptors (because
+of resource limits), causing C<accept> to fail with C<ENFILE> but not
+rejecting the connection, leading to libev signalling readiness on
+the next iteration again (the connection still exists after all), and
+typically causing the program to loop at 100% CPU usage.
+
+Unfortunately, the set of errors that cause this issue differs between
+operating systems, there is usually little the app can do to remedy the
+situation, and no known thread-safe method of removing the connection to
+cope with overload is known (to me).
+
+One of the easiest ways to handle this situation is to just ignore it
+- when the program encounters an overload, it will just loop until the
+situation is over. While this is a form of busy waiting, no OS offers an
+event-based way to handle this situation, so it's the best one can do.
+
+A better way to handle the situation is to log any errors other than
+C<EAGAIN> and C<EWOULDBLOCK>, making sure not to flood the log with such
+messages, and continue as usual, which at least gives the user an idea of
+what could be wrong ("raise the ulimit!"). For extra points one could stop
+the C<ev_io> watcher on the listening fd "for a while", which reduces CPU
+usage.
+
+If your program is single-threaded, then you could also keep a dummy file
+descriptor for overload situations (e.g. by opening F</dev/null>), and
+when you run into C<ENFILE> or C<EMFILE>, close it, run C<accept>,
+close that fd, and create a new dummy fd. This will gracefully refuse
+clients under typical overload conditions.
+
+The last way to handle it is to simply log the error and C<exit>, as
+is often done with C<malloc> failures, but this results in an easy
+opportunity for a DoS attack.
 
 =head3 Watcher-Specific Functions
 
@@ -1113,8 +1739,8 @@
 =item ev_io_set (ev_io *, int fd, int events)
 
 Configures an C<ev_io> watcher. The C<fd> is the file descriptor to
-rceeive events for and events is either C<EV_READ>, C<EV_WRITE> or
-C<EV_READ | EV_WRITE> to receive the given events.
+receive events for and C<events> is either C<EV_READ>, C<EV_WRITE> or
+C<EV_READ | EV_WRITE>, to express the desire to receive the given events.
 
 =item int fd [read-only]
 
@@ -1132,19 +1758,19 @@
 readable, but only once. Since it is likely line-buffered, you could
 attempt to read a whole line in the callback.
 
-  static void
-  stdin_readable_cb (struct ev_loop *loop, struct ev_io *w, int revents)
-  {
-     ev_io_stop (loop, w);
-    .. read from stdin here (or from w->fd) and haqndle any I/O errors
-  }
-
-  ...
-  struct ev_loop *loop = ev_default_init (0);
-  struct ev_io stdin_readable;
-  ev_io_init (&stdin_readable, stdin_readable_cb, STDIN_FILENO, EV_READ);
-  ev_io_start (loop, &stdin_readable);
-  ev_loop (loop, 0);
+   static void
+   stdin_readable_cb (struct ev_loop *loop, ev_io *w, int revents)
+   {
+      ev_io_stop (loop, w);
+     .. read from stdin here (or from w->fd) and handle any I/O errors
+   }
+
+   ...
+   struct ev_loop *loop = ev_default_init (0);
+   ev_io stdin_readable;
+   ev_io_init (&stdin_readable, stdin_readable_cb, STDIN_FILENO, EV_READ);
+   ev_io_start (loop, &stdin_readable);
+   ev_run (loop, 0);
 
 
 =head2 C<ev_timer> - relative and optionally repeating timeouts
@@ -1153,22 +1779,242 @@
 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) one hour. "Roughly" because
 detecting time jumps is hard, and some inaccuracies are unavoidable (the
 monotonic clock option helps a lot here).
 
+The callback is guaranteed to be invoked only I<after> its timeout has
+passed (not I<at>, so on systems with very low-resolution clocks this
+might introduce a small delay). If multiple timers become ready during the
+same loop iteration then the ones with earlier time-out values are invoked
+before ones of the same priority with later time-out values (but this is
+no longer true when a callback calls C<ev_run> recursively).
+
+=head3 Be smart about timeouts
+
+Many real-world problems involve some kind of timeout, usually for error
+recovery. A typical example is an HTTP request - if the other side hangs,
+you want to raise some error after a while.
+
+What follows are some ways to handle this problem, from obvious and
+inefficient to smart and efficient.
+
+In the following, a 60 second activity timeout is assumed - a timeout that
+gets reset to 60 seconds each time there is activity (e.g. each time some
+data or other life sign was received).
+
+=over 4
+
+=item 1. Use a timer and stop, reinitialise and start it on activity.
+
+This is the most obvious, but not the most simple way: In the beginning,
+start the watcher:
+
+   ev_timer_init (timer, callback, 60., 0.);
+   ev_timer_start (loop, timer);
+
+Then, each time there is some activity, C<ev_timer_stop> it, initialise it
+and start it again:
+
+   ev_timer_stop (loop, timer);
+   ev_timer_set (timer, 60., 0.);
+   ev_timer_start (loop, timer);
+
+This is relatively simple to implement, but means that each time there is
+some activity, libev will first have to remove the timer from its internal
+data structure and then add it again. Libev tries to be fast, but it's
+still not a constant-time operation.
+
+=item 2. Use a timer and re-start it with C<ev_timer_again> inactivity.
+
+This is the easiest way, and involves using C<ev_timer_again> instead of
+C<ev_timer_start>.
+
+To implement this, configure an C<ev_timer> with a C<repeat> value
+of C<60> and then call C<ev_timer_again> at start and each time you
+successfully read or write some data. If you go into an idle state where
+you do not expect data to travel on the socket, you can C<ev_timer_stop>
+the timer, and C<ev_timer_again> will automatically restart it if need be.
+
+That means you can ignore both the C<ev_timer_start> function and the
+C<after> argument to C<ev_timer_set>, and only ever use the C<repeat>
+member and C<ev_timer_again>.
+
+At start:
+
+   ev_init (timer, callback);
+   timer->repeat = 60.;
+   ev_timer_again (loop, timer);
+
+Each time there is some activity:
+
+   ev_timer_again (loop, timer);
+
+It is even possible to change the time-out on the fly, regardless of
+whether the watcher is active or not:
+
+   timer->repeat = 30.;
+   ev_timer_again (loop, timer);
+
+This is slightly more efficient then stopping/starting the timer each time
+you want to modify its timeout value, as libev does not have to completely
+remove and re-insert the timer from/into its internal data structure.
+
+It is, however, even simpler than the "obvious" way to do it.
+
+=item 3. Let the timer time out, but then re-arm it as required.
+
+This method is more tricky, but usually most efficient: Most timeouts are
+relatively long compared to the intervals between other activity - in
+our example, within 60 seconds, there are usually many I/O events with
+associated activity resets.
+
+In this case, it would be more efficient to leave the C<ev_timer> alone,
+but remember the time of last activity, and check for a real timeout only
+within the callback:
+
+   ev_tstamp last_activity; // time of last activity
+
+   static void
+   callback (EV_P_ ev_timer *w, int revents)
+   {
+     ev_tstamp now     = ev_now (EV_A);
+     ev_tstamp timeout = last_activity + 60.;
+
+     // if last_activity + 60. is older than now, we did time out
+     if (timeout < now)
+       {
+         // timeout occurred, take action
+       }
+     else
+       {
+         // callback was invoked, but there was some activity, re-arm
+         // the watcher to fire in last_activity + 60, which is
+         // guaranteed to be in the future, so "again" is positive:
+         w->repeat = timeout - now;
+         ev_timer_again (EV_A_ w);
+       }
+   }
+
+To summarise the callback: first calculate the real timeout (defined
+as "60 seconds after the last activity"), then check if that time has
+been reached, which means something I<did>, in fact, time out. Otherwise
+the callback was invoked too early (C<timeout> is in the future), so
+re-schedule the timer to fire at that future time, to see if maybe we have
+a timeout then.
+
+Note how C<ev_timer_again> is used, taking advantage of the
+C<ev_timer_again> optimisation when the timer is already running.
+
+This scheme causes more callback invocations (about one every 60 seconds
+minus half the average time between activity), but virtually no calls to
+libev to change the timeout.
+
+To start the timer, simply initialise the watcher and set C<last_activity>
+to the current time (meaning we just have some activity :), then call the
+callback, which will "do the right thing" and start the timer:
+
+   ev_init (timer, callback);
+   last_activity = ev_now (loop);
+   callback (loop, timer, EV_TIMER);
+
+And when there is some activity, simply store the current time in
+C<last_activity>, no libev calls at all:
+
+   last_activity = ev_now (loop);
+
+This technique is slightly more complex, but in most cases where the
+time-out is unlikely to be triggered, much more efficient.
+
+Changing the timeout is trivial as well (if it isn't hard-coded in the
+callback :) - just change the timeout and invoke the callback, which will
+fix things for you.
+
+=item 4. Wee, just use a double-linked list for your timeouts.
+
+If there is not one request, but many thousands (millions...), all
+employing some kind of timeout with the same timeout value, then one can
+do even better:
+
+When starting the timeout, calculate the timeout value and put the timeout
+at the I<end> of the list.
+
+Then use an C<ev_timer> to fire when the timeout at the I<beginning> of
+the list is expected to fire (for example, using the technique #3).
+
+When there is some activity, remove the timer from the list, recalculate
+the timeout, append it to the end of the list again, and make sure to
+update the C<ev_timer> if it was taken from the beginning of the list.
+
+This way, one can manage an unlimited number of timeouts in O(1) time for
+starting, stopping and updating the timers, at the expense of a major
+complication, and having to use a constant timeout. The constant timeout
+ensures that the list stays sorted.
+
+=back
+
+So which method the best?
+
+Method #2 is a simple no-brain-required solution that is adequate in most
+situations. Method #3 requires a bit more thinking, but handles many cases
+better, and isn't very complicated either. In most case, choosing either
+one is fine, with #3 being better in typical situations.
+
+Method #1 is almost always a bad idea, and buys you nothing. Method #4 is
+rather complicated, but extremely efficient, something that really pays
+off after the first million or so of active timers, i.e. it's usually
+overkill :)
+
+=head3 The special problem of time updates
+
+Establishing the current time is a costly operation (it usually takes at
+least two system calls): EV therefore updates its idea of the current
+time only before and after C<ev_run> collects new events, which causes a
+growing difference between C<ev_now ()> and C<ev_time ()> when handling
+lots of events in one iteration.
+
 The relative timeouts are calculated relative to the C<ev_now ()>
 time. This is usually the right thing as this timestamp refers to the time
 of the event triggering whatever timeout you are modifying/starting. If
-you suspect event processing to be delayed and you I<need> to base the timeout
-on the current time, use something like this to adjust for this:
+you suspect event processing to be delayed and you I<need> to base the
+timeout on the current time, use something like this to adjust for this:
 
    ev_timer_set (&timer, after + ev_now () - ev_time (), 0.);
 
-The callback is guarenteed to be invoked only when its timeout has passed,
-but if multiple timers become ready during the same loop iteration then
-order of execution is undefined.
+If the event loop is suspended for a long time, you can also force an
+update of the time returned by C<ev_now ()> by calling C<ev_now_update
+()>.
+
+=head3 The special problems of suspended animation
+
+When you leave the server world it is quite customary to hit machines that
+can suspend/hibernate - what happens to the clocks during such a suspend?
+
+Some quick tests made with a Linux 2.6.28 indicate that a suspend freezes
+all processes, while the clocks (C<times>, C<CLOCK_MONOTONIC>) continue
+to run until the system is suspended, but they will not advance while the
+system is suspended. That means, on resume, it will be as if the program
+was frozen for a few seconds, but the suspend time will not be counted
+towards C<ev_timer> when a monotonic clock source is used. The real time
+clock advanced as expected, but if it is used as sole clocksource, then a
+long suspend would be detected as a time jump by libev, and timers would
+be adjusted accordingly.
+
+I would not be surprised to see different behaviour in different between
+operating systems, OS versions or even different hardware.
+
+The other form of suspend (job control, or sending a SIGSTOP) will see a
+time jump in the monotonic clocks and the realtime clock. If the program
+is suspended for a very long time, and monotonic clock sources are in use,
+then you can expect C<ev_timer>s to expire as the full suspension time
+will be counted towards the timers. When no monotonic clock source is in
+use, then libev will again assume a timejump and adjust accordingly.
+
+It might be beneficial for this latter case to call C<ev_suspend>
+and C<ev_resume> in code that handles C<SIGTSTP>, to at least get
+deterministic behaviour in this case (you can do nothing against
+C<SIGSTOP>).
 
 =head3 Watcher-Specific Functions and Data Members
 
@@ -1178,16 +2024,17 @@
 
 =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, ev_timer *)
 
@@ -1196,40 +2043,30 @@
 
 If the timer is pending, its pending status is cleared.
 
-If the timer is started but nonrepeating, stop it (as if it timed out).
+If the timer is started but non-repeating, stop it (as if it timed out).
 
 If the timer is repeating, either start it if necessary (with the
 C<repeat> value), or reset the running timer to the C<repeat> value.
 
-This sounds a bit complicated, but here is a useful and typical
-example: Imagine you have a tcp connection and you want a so-called idle
-timeout, that is, you want to be called when there have been, say, 60
-seconds of inactivity on the socket. The easiest way to do this is to
-configure an C<ev_timer> with a C<repeat> value of C<60> and then call
-C<ev_timer_again> each time you successfully read or write some data. If
-you go into an idle state where you do not expect data to travel on the
-socket, you can C<ev_timer_stop> the timer, and C<ev_timer_again> will
-automatically restart it if need be.
-
-That means you can ignore the C<after> value and C<ev_timer_start>
-altogether and only ever use the C<repeat> value and C<ev_timer_again>:
+This sounds a bit complicated, see L<Be smart about timeouts>, above, for a
+usage example.
 
-   ev_timer_init (timer, callback, 0., 5.);
-   ev_timer_again (loop, timer);
-   ...
-   timer->again = 17.;
-   ev_timer_again (loop, timer);
-   ...
-   timer->again = 10.;
-   ev_timer_again (loop, timer);
+=item ev_tstamp ev_timer_remaining (loop, ev_timer *)
 
-This is more slightly efficient then stopping/starting the timer each time
-you want to modify its timeout value.
+Returns the remaining time until a timer fires. If the timer is active,
+then this time is relative to the current event loop time, otherwise it's
+the timeout value currently configured.
+
+That is, after an C<ev_timer_set (w, 5, 7)>, C<ev_timer_remaining> returns
+C<5>. When the timer is started and one second passes, C<ev_timer_remaining>
+will return C<4>. When the timer expires and is restarted, it will return
+roughly C<7> (likely slightly less as callback invocation takes some time,
+too), and so on.
 
 =item ev_tstamp repeat [read-write]
 
 The current C<repeat> value. Will be used each time the watcher times out
-or C<ev_timer_again> is called and determines the next timeout (if any),
+or C<ev_timer_again> is called, and determines the next timeout (if any),
 which is also when any modifications are taken into account.
 
 =back
@@ -1238,33 +2075,33 @@
 
 Example: Create a timer that fires after 60 seconds.
 
-  static void
-  one_minute_cb (struct ev_loop *loop, struct ev_timer *w, int revents)
-  {
-    .. one minute over, w is actually stopped right here
-  }
-
-  struct ev_timer mytimer;
-  ev_timer_init (&mytimer, one_minute_cb, 60., 0.);
-  ev_timer_start (loop, &mytimer);
+   static void
+   one_minute_cb (struct ev_loop *loop, ev_timer *w, int revents)
+   {
+     .. one minute over, w is actually stopped right here
+   }
+
+   ev_timer mytimer;
+   ev_timer_init (&mytimer, one_minute_cb, 60., 0.);
+   ev_timer_start (loop, &mytimer);
 
 Example: Create a timeout timer that times out after 10 seconds of
 inactivity.
 
-  static void
-  timeout_cb (struct ev_loop *loop, struct ev_timer *w, int revents)
-  {
-    .. ten seconds without any activity
-  }
-
-  struct ev_timer mytimer;
-  ev_timer_init (&mytimer, timeout_cb, 0., 10.); /* note, only repeat used */
-  ev_timer_again (&mytimer); /* start timer */
-  ev_loop (loop, 0);
-
-  // and in some piece of code that gets executed on any "activity":
-  // reset the timeout to start ticking again at 10 seconds
-  ev_timer_again (&mytimer);
+   static void
+   timeout_cb (struct ev_loop *loop, ev_timer *w, int revents)
+   {
+     .. ten seconds without any activity
+   }
+
+   ev_timer mytimer;
+   ev_timer_init (&mytimer, timeout_cb, 0., 10.); /* note, only repeat used */
+   ev_timer_again (&mytimer); /* start timer */
+   ev_run (loop, 0);
+
+   // and in some piece of code that gets executed on any "activity":
+   // reset the timeout to start ticking again at 10 seconds
+   ev_timer_again (&mytimer);
 
 
 =head2 C<ev_periodic> - to cron or not to cron?
@@ -1272,82 +2109,104 @@
 Periodic watchers are also timers of a kind, but they are very versatile
 (and unfortunately a bit complex).
 
-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
-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).
-
-They 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
-during the same loop iteration then order of execution is undefined.
+Unlike C<ev_timer>, periodic watchers are not based on real time (or
+relative time, the physical time that passes) but on wall clock time
+(absolute time, the thing you can read on your calender or clock). The
+difference is that wall clock time can run faster or slower than real
+time, and time jumps are not uncommon (e.g. when you adjust your
+wrist-watch).
+
+You can tell a periodic watcher to trigger after some specific point
+in time: for example, if you tell a periodic watcher to trigger "in 10
+seconds" (by specifying e.g. C<ev_now () + 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 a year or more to trigger the event (unlike an
+C<ev_timer>, which would still trigger roughly 10 seconds after starting
+it, as it uses a relative timeout).
+
+C<ev_periodic> watchers can also be used to implement vastly more complex
+timers, such as triggering an event on each "midnight, local time", or
+other complicated rules. This cannot be done with C<ev_timer> watchers, as
+those cannot react to time jumps.
+
+As with timers, the callback is guaranteed to be invoked only when the
+point in time where it is supposed to trigger has passed. If multiple
+timers become ready during the same loop iteration then the ones with
+earlier time-out values are invoked before ones with later time-out values
+(but this is no longer true when a callback calls C<ev_run> recursively).
 
 =head3 Watcher-Specific Functions and Data Members
 
 =over 4
 
-=item ev_periodic_init (ev_periodic *, callback, ev_tstamp at, ev_tstamp interval, reschedule_cb)
+=item ev_periodic_init (ev_periodic *, callback, ev_tstamp offset, ev_tstamp interval, reschedule_cb)
 
-=item ev_periodic_set (ev_periodic *, ev_tstamp after, ev_tstamp repeat, reschedule_cb)
+=item ev_periodic_set (ev_periodic *, ev_tstamp offset, ev_tstamp interval, reschedule_cb)
 
-Lots of arguments, lets sort it out... There are basically three modes of
-operation, and we will explain them from simplest to complex:
+Lots of arguments, let's sort it out... There are basically three modes of
+operation, and we will explain them from simplest to most complex:
 
 =over 4
 
-=item * absolute timer (at = time, interval = reschedule_cb = 0)
+=item * absolute timer (offset = absolute time, interval = 0, 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 wall clock
+time C<offset> has passed. It will not repeat and will not adjust when a
+time jump occurs, that is, if it is to be run at January 1st 2011 then it
+will be stopped and invoked when the system clock reaches or surpasses
+this point in time.
 
-=item * repeating interval timer (at = offset, interval > 0, reschedule_cb = 0)
+=item * repeating interval timer (offset = offset within interval, 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, 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:
+C<offset + N * interval> time (for some integer N, which can also be
+negative) and then repeat, regardless of any time jumps. The C<offset>
+argument is merely an offset into the C<interval> periods.
+
+This can be used to create timers that do not drift with respect to the
+system clock, for example, here is an C<ev_periodic> that triggers each
+hour, on the hour (with respect to UTC):
 
    ev_periodic_set (&periodic, 0., 3600., 0);
 
 This doesn't mean there will always be 3600 seconds in between triggers,
-but only that the the callback will be called when the system time shows a
+but only that the callback will be called when the system time shows a
 full hour (UTC), or more correctly, when the system time is evenly divisible
 by 3600.
 
 Another way to think about it (for the mathematically inclined) is that
 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.
+time where C<time = offset (mod interval)>, regardless of any time jumps.
 
-For numerical stability it is preferable that the C<at> value is near
+For numerical stability it is preferable that the C<offset> value is near
 C<ev_now ()> (the current time), but there is no range requirement for
-this value.
+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 deteriorate. 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)
+=item * manual reschedule mode (offset ignored, interval ignored, reschedule_cb = callback)
 
-In this mode the values for C<interval> and C<at> are both being
+In this mode the values for C<interval> and C<offset> are both being
 ignored. Instead, each time the periodic watcher gets scheduled, the
 reschedule callback will be called with the watcher as first, and the
 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 an C<ev_prepare> watcher, which is legal).
+NOTE: I<This callback MUST NOT stop or destroy any periodic watcher, ever,
+or make ANY other event loop modifications whatsoever, unless explicitly
+allowed by documentation here>.
+
+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)(ev_periodic
+*w, ev_tstamp now)>, e.g.:
 
-   static ev_tstamp my_rescheduler (struct ev_periodic *w, ev_tstamp now)
+   static ev_tstamp
+   my_rescheduler (ev_periodic *w, ev_tstamp now)
    {
      return now + 60.;
    }
@@ -1357,11 +2216,11 @@
 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).
@@ -1375,10 +2234,18 @@
 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. This is not the same as the C<offset> argument to
+C<ev_periodic_set>, but indeed works even in interval and manual
+rescheduling modes.
+
 =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>).
+absolute point in time (the C<offset> value passed to C<ev_periodic_set>,
+although libev might modify this value for better numerical stability).
 
 Can be modified any time, but changes only take effect when the periodic
 timer fires or C<ev_periodic_again> is being called.
@@ -1389,74 +2256,120 @@
 take effect when the periodic timer fires or C<ev_periodic_again> is being
 called.
 
-=item ev_tstamp (*reschedule_cb)(struct ev_periodic *w, ev_tstamp now) [read-write]
+=item ev_tstamp (*reschedule_cb)(ev_periodic *w, ev_tstamp now) [read-write]
 
 The current reschedule callback, or C<0>, if this functionality is
 switched off. Can be changed any time, but changes only take effect when
 the periodic timer fires or C<ev_periodic_again> is being called.
 
-=item ev_tstamp at [read-only]
-
-When active, contains the absolute time that the watcher is supposed to
-trigger next.
-
 =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.
+system time is divisible by 3600. The callback invocation times have
+potentially a lot of jitter, but good long-term stability.
+
+   static void
+   clock_cb (struct ev_loop *loop, ev_periodic *w, int revents)
+   {
+     ... its now a full hour (UTC, or TAI or whatever your clock follows)
+   }
 
-  static void
-  clock_cb (struct ev_loop *loop, struct ev_io *w, int revents)
-  {
-    ... its now a full hour (UTC, or TAI or whatever your clock follows)
-  }
-
-  struct ev_periodic hourly_tick;
-  ev_periodic_init (&hourly_tick, clock_cb, 0., 3600., 0);
-  ev_periodic_start (loop, &hourly_tick);
+   ev_periodic hourly_tick;
+   ev_periodic_init (&hourly_tick, clock_cb, 0., 3600., 0);
+   ev_periodic_start (loop, &hourly_tick);
 
 Example: The same as above, but use a reschedule callback to do it:
 
-  #include <math.h>
+   #include <math.h>
 
-  static ev_tstamp
-  my_scheduler_cb (struct ev_periodic *w, ev_tstamp now)
-  {
-    return fmod (now, 3600.) + 3600.;
-  }
+   static ev_tstamp
+   my_scheduler_cb (ev_periodic *w, ev_tstamp now)
+   {
+     return now + (3600. - fmod (now, 3600.));
+   }
 
-  ev_periodic_init (&hourly_tick, clock_cb, 0., 0., my_scheduler_cb);
+   ev_periodic_init (&hourly_tick, clock_cb, 0., 0., my_scheduler_cb);
 
 Example: Call a callback every hour, starting now:
 
-  struct ev_periodic hourly_tick;
-  ev_periodic_init (&hourly_tick, clock_cb,
-                    fmod (ev_now (loop), 3600.), 3600., 0);
-  ev_periodic_start (loop, &hourly_tick);
+   ev_periodic hourly_tick;
+   ev_periodic_init (&hourly_tick, clock_cb,
+                     fmod (ev_now (loop), 3600.), 3600., 0);
+   ev_periodic_start (loop, &hourly_tick);
   
 
 =head2 C<ev_signal> - signal me when a signal gets signalled!
 
 Signal watchers will trigger an event when the process receives a specific
 signal one or more times. Even though signals are very asynchronous, libev
-will try it's best to deliver signals synchronously, i.e. as part of the
+will try its best to deliver signals synchronously, i.e. as part of the
 normal event processing, like any other event.
 
-You can configure as many watchers as you like per signal. Only when the
-first watcher gets started will libev actually register a signal watcher
-with the kernel (thus it coexists with your own signal handlers as long
-as you don't register any with libev). Similarly, when the last signal
-watcher for a signal is stopped libev will reset the signal handler to
-SIG_DFL (regardless of what it was set to before).
+If you want signals to be delivered truly asynchronously, just use
+C<sigaction> as you would do without libev and forget about sharing
+the signal. You can even use C<ev_async> from a signal handler to
+synchronously wake up an event loop.
+
+You can configure as many watchers as you like for the same signal, but
+only within the same loop, i.e. you can watch for C<SIGINT> in your
+default loop and for C<SIGIO> in another loop, but you cannot watch for
+C<SIGINT> in both the default loop and another loop at the same time. At
+the moment, C<SIGCHLD> is permanently tied to the default loop.
+
+When the first watcher gets started will libev actually register something
+with the kernel (thus it coexists with your own signal handlers as long as
+you don't register any with libev for the same signal).
 
 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.
+C<SA_RESTART> (or equivalent) behaviour enabled, so system calls should
+not be unduly interrupted. If you have a problem with system calls 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 The special problem of inheritance over fork/execve/pthread_create
+
+Both the signal mask (C<sigprocmask>) and the signal disposition
+(C<sigaction>) are unspecified after starting a signal watcher (and after
+stopping it again), that is, libev might or might not block the signal,
+and might or might not set or restore the installed signal handler.
+
+While this does not matter for the signal disposition (libev never
+sets signals to C<SIG_IGN>, so handlers will be reset to C<SIG_DFL> on
+C<execve>), this matters for the signal mask: many programs do not expect
+certain signals to be blocked.
+
+This means that before calling C<exec> (from the child) you should reset
+the signal mask to whatever "default" you expect (all clear is a good
+choice usually).
+
+The simplest way to ensure that the signal mask is reset in the child is
+to install a fork handler with C<pthread_atfork> that resets it. That will
+catch fork calls done by libraries (such as the libc) as well.
+
+In current versions of libev, the signal will not be blocked indefinitely
+unless you use the C<signalfd> API (C<EV_SIGNALFD>). While this reduces
+the window of opportunity for problems, it will not go away, as libev
+I<has> to modify the signal mask, at least temporarily.
+
+So I can't stress this enough: I<If you do not reset your signal mask when
+you expect it to be empty, you have a race condition in your code>. This
+is not a libev-specific thing, this is true for most event libraries.
+
+=head3 The special problem of threads signal handling
+
+POSIX threads has problematic signal handling semantics, specifically,
+a lot of functionality (sigfd, sigwait etc.) only really works if all
+threads in a process block signals, which is hard to achieve.
+
+When you want to use sigwait (or mix libev signal handling with your own
+for the same signals), you can tackle this problem by globally blocking
+all signals before creating any threads (or creating them with a fully set
+sigprocmask) and also specifying the C<EVFLAG_NOSIGMASK> when creating
+loops. Then designate one thread as "signal receiver thread" which handles
+these signals. You can pass on any signals that libev might be interested
+in by calling C<ev_feed_signal>.
 
 =head3 Watcher-Specific Functions and Data Members
 
@@ -1477,35 +2390,42 @@
 
 =head3 Examples
 
-Example: Try to exit cleanly on SIGINT and SIGTERM.
+Example: Try to exit cleanly on SIGINT.
+
+   static void
+   sigint_cb (struct ev_loop *loop, ev_signal *w, int revents)
+   {
+     ev_break (loop, EVBREAK_ALL);
+   }
 
-  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);
+   ev_signal signal_watcher;
+   ev_signal_init (&signal_watcher, sigint_cb, SIGINT);
+   ev_signal_start (loop, &signal_watcher);
 
 
 =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). 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).
+some child status changes (most typically when a child of yours dies or
+exits). 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), i.e.,
+forking and then immediately registering a watcher for the child is fine,
+but forking and registering a watcher a few event loop iterations later or
+in the next callback invocation is not.
 
 Only the default event loop is capable of handling signals, and therefore
-you can only rgeister child watchers in the default event loop.
+you can only register child watchers in the default event loop.
+
+Due to some design glitches inside libev, child watchers will always be
+handled at maximum priority (their priority is set to C<EV_MAXPRI> by
+libev)
 
 =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
+initialised. This is necessary to guarantee proper behaviour even if the
+first child watcher is started after the child exits. The occurrence
 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.
@@ -1520,6 +2440,14 @@
 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 Stopping the Child Watcher
+
+Currently, the child watcher never gets stopped, even when the
+child terminates, so normally one needs to stop the watcher in the
+callback. Future versions of libev might stop the watcher automatically
+when a child exit is detected (calling C<ev_child_stop> twice is not a
+problem).
+
 =head3 Watcher-Specific Functions and Data Members
 
 =over 4
@@ -1557,110 +2485,148 @@
 Example: C<fork()> a new process and install a child handler to wait for
 its completion.
 
-  ev_child cw;
+   ev_child cw;
 
-  static void
-  child_cb (EV_P_ struct ev_child *w, int revents)
-  {
-    ev_child_stop (EV_A_ w);
-    printf ("process %d exited with status %x\n", w->rpid, w->rstatus);
-  }
-
-  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);
-    }
+   static void
+   child_cb (EV_P_ ev_child *w, int revents)
+   {
+     ev_child_stop (EV_A_ w);
+     printf ("process %d exited with status %x\n", w->rpid, w->rstatus);
+   }
+
+   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?
 
-This watches a filesystem path for attribute changes. That is, it calls
-C<stat> regularly (or when the OS says it changed) and sees if it changed
-compared to the last time, invoking the callback if it did.
+This watches a file system path for attribute changes. That is, it calls
+C<stat> on that path in regular intervals (or when the OS says it changed)
+and sees if it changed compared to the last time, invoking the callback if
+it did.
 
 The path does not need to exist: changing from "path exists" to "path does
-not exist" is a status change like any other. The condition "path does
-not exist" is signified by the C<st_nlink> field being zero (which is
-otherwise always forced to be at least one) and all the other fields of
-the stat buffer having unspecified contents.
-
-The path I<should> be absolute and I<must not> end in a slash. If it is
-relative and your working directory changes, the behaviour is undefined.
-
-Since there is no standard to do this, the portable implementation simply
-calls C<stat (2)> regularly on the path to see if it changed somehow. You
-can specify a recommended polling interval for this case. If you specify
-a polling interval of C<0> (highly recommended!) then a I<suitable,
-unspecified default> value will be used (which you can expect to be around
-five seconds, although this might change dynamically). Libev will also
-impose a minimum interval which is currently around C<0.1>, but thats
-usually overkill.
+not exist" is a status change like any other. The condition "path does not
+exist" (or more correctly "path cannot be stat'ed") is signified by the
+C<st_nlink> field being zero (which is otherwise always forced to be at
+least one) and all the other fields of the stat buffer having unspecified
+contents.
+
+The path I<must not> end in a slash or contain special components such as
+C<.> or C<..>. The path I<should> be absolute: If it is relative and
+your working directory changes, then the behaviour is undefined.
+
+Since there is no portable change notification interface available, the
+portable implementation simply calls C<stat(2)> regularly on the path
+to see if it changed somehow. You can specify a recommended polling
+interval for this case. If you specify a polling interval of C<0> (highly
+recommended!) then a I<suitable, unspecified default> value will be used
+(which you can expect to be around five seconds, although this might
+change dynamically). Libev will also impose a minimum interval which is
+currently around C<0.1>, but that's usually overkill.
 
 This watcher type is not meant for massive numbers of stat watchers,
 as even with OS-supported change notifications, this can be
 resource-intensive.
 
-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.
+At the time of this writing, the only OS-specific interface implemented
+is the Linux inotify interface (implementing kqueue support is left as an
+exercise for the reader. Note, however, that the author sees no way of
+implementing C<ev_stat> semantics with kqueue, except as a hint).
 
 =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
+compilation environment, which means that on systems with large file
+support disabled by default, 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
+most noticeably displayed with ev_stat and large file support.
 
-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.
+The solution for this is to lobby your distribution maker to make large
+file interfaces available by default (as e.g. FreeBSD does) and not
+optional. Libev cannot simply switch on large file support because it has
+to exchange stat structures with application programs compiled using the
+default compilation environment.
+
+=head3 Inotify and Kqueue
+
+When C<inotify (7)> support has been compiled into libev 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 are many cases where libev has to resort to regular C<stat> polling,
+but as long as kernel 2.6.25 or newer is used (2.6.24 and older have too
+many bugs), the path exists (i.e. stat succeeds), and the path resides on
+a local filesystem (libev currently assumes only ext2/3, jfs, reiserfs and
+xfs are fully working) libev usually gets away without polling.
 
-(There is no support for kqueue, as apparently it cannot be used to
+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).
+descriptor open on the object at all times, and detecting renames, unlinks
+etc. is difficult.
+
+=head3 C<stat ()> is a synchronous operation
+
+Libev doesn't normally do any kind of I/O itself, and so is not blocking
+the process. The exception are C<ev_stat> watchers - those call C<stat
+()>, which is a synchronous operation.
+
+For local paths, this usually doesn't matter: unless the system is very
+busy or the intervals between stat's are large, a stat call will be fast,
+as the path data is usually in memory already (except when starting the
+watcher).
+
+For networked file systems, calling C<stat ()> can block an indefinite
+time due to network issues, and even under good conditions, a stat call
+often takes multiple milliseconds.
+
+Therefore, it is best to avoid using C<ev_stat> watchers on networked
+paths, although this is fully supported by libev.
 
 =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 might
-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.
-
-The solution to this is to delay acting on a change for a second (or till
-the next second boundary), using a roughly one-second delay C<ev_timer>
-(C<ev_timer_set (w, 0., 1.01); ev_timer_again (loop, w)>). The C<.01>
-is added to work around small timing inconsistencies of some operating
-systems.
+The C<stat ()> system call only supports full-second resolution portably,
+and even on systems where the resolution is higher, most file systems
+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 unless the
+stat data does change in other ways (e.g. file size).
+
+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
 
@@ -1676,28 +2642,32 @@
 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,
+The callback will receive an C<EV_STAT> event 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 (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]
 
@@ -1705,7 +2675,7 @@
 
 =item const char *path [read-only]
 
-The filesystem path that is being watched.
+The file system path that is being watched.
 
 =back
 
@@ -1713,62 +2683,62 @@
 
 Example: Watch C</etc/passwd> for attribute changes.
 
-  static void
-  passwd_cb (struct ev_loop *loop, ev_stat *w, int revents)
-  {
-    /* /etc/passwd changed in some way */
-    if (w->attr.st_nlink)
-      {
-        printf ("passwd current size  %ld\n", (long)w->attr.st_size);
-        printf ("passwd current atime %ld\n", (long)w->attr.st_mtime);
-        printf ("passwd current mtime %ld\n", (long)w->attr.st_mtime);
-      }
-    else
-      /* you shalt not abuse printf for puts */
-      puts ("wow, /etc/passwd is not there, expect problems. "
-            "if this is windows, they already arrived\n");
-  }
+   static void
+   passwd_cb (struct ev_loop *loop, ev_stat *w, int revents)
+   {
+     /* /etc/passwd changed in some way */
+     if (w->attr.st_nlink)
+       {
+         printf ("passwd current size  %ld\n", (long)w->attr.st_size);
+         printf ("passwd current atime %ld\n", (long)w->attr.st_mtime);
+         printf ("passwd current mtime %ld\n", (long)w->attr.st_mtime);
+       }
+     else
+       /* you shalt not abuse printf for puts */
+       puts ("wow, /etc/passwd is not there, expect problems. "
+             "if this is windows, they already arrived\n");
+   }
 
-  ...
-  ev_stat passwd;
+   ...
+   ev_stat passwd;
 
-  ev_stat_init (&passwd, passwd_cb, "/etc/passwd", 0.);
-  ev_stat_start (loop, &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 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., 1.01);
+   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...
 
 Idle watchers trigger events when no other events of the same or higher
-priority are pending (prepare, check and other idle watchers do not
-count).
+priority are pending (prepare, check and other idle watchers do not count
+as receiving "events").
 
 That is, as long as your process is busy handling sockets or timeouts
 (or even signals, imagine) of the same or higher priority it will not be
@@ -1789,7 +2759,7 @@
 
 =over 4
 
-=item ev_idle_init (ev_signal *, callback)
+=item ev_idle_init (ev_idle *, callback)
 
 Initialises and configures the idle watcher - it has no parameters of any
 kind. There is a C<ev_idle_set> macro, but using it is utterly pointless,
@@ -1802,26 +2772,26 @@
 Example: Dynamically allocate an C<ev_idle> watcher, start it, and in the
 callback, free it. Also, use no error checking, as usual.
 
-  static void
-  idle_cb (struct ev_loop *loop, struct ev_idle *w, int revents)
-  {
-    free (w);
-    // now do something you wanted to do when the program has
-    // no longer anything immediate to do.
-  }
-
-  struct ev_idle *idle_watcher = malloc (sizeof (struct ev_idle));
-  ev_idle_init (idle_watcher, idle_cb);
-  ev_idle_start (loop, idle_cb);
+   static void
+   idle_cb (struct ev_loop *loop, ev_idle *w, int revents)
+   {
+     free (w);
+     // now do something you wanted to do when the program has
+     // no longer anything immediate to do.
+   }
+
+   ev_idle *idle_watcher = malloc (sizeof (ev_idle));
+   ev_idle_init (idle_watcher, idle_cb);
+   ev_idle_start (loop, idle_watcher);
 
 
 =head2 C<ev_prepare> and C<ev_check> - customise your event loop!
 
-Prepare and check watchers are usually (but not always) used in tandem:
+Prepare and check watchers are usually (but not always) used in pairs:
 prepare watchers get invoked before the process blocks and check watchers
 afterwards.
 
-You I<must not> call C<ev_loop> or similar functions that enter
+You I<must not> call C<ev_run> or similar functions that enter
 the current event loop from either C<ev_prepare> or C<ev_check>
 watchers. Other loops than the current one are fine, however. The
 rationale behind this is that you do not need to check for recursion in
@@ -1830,21 +2800,21 @@
 called in pairs bracketing the blocking call.
 
 Their main purpose is to integrate other event mechanisms into libev and
-their use is somewhat advanced. This could be used, for example, to track
+their use is somewhat advanced. They could be used, for example, to track
 variable changes, implement your own watchers, integrate net-snmp or a
 coroutine library and lots more. They are also occasionally useful if
 you cache some data and want to flush it before blocking (for example,
 in X programs you might want to do an C<XFlush ()> in an C<ev_prepare>
 watcher).
 
-This is done by examining in each prepare call which file descriptors need
-to be watched by the other library, registering C<ev_io> watchers for
-them and starting an C<ev_timer> watcher for any timeouts (many libraries
-provide just this functionality). Then, in the check watcher you check for
-any events that occured (by checking the pending status of all watchers
-and stopping them) and call back into the library. The I/O and timer
-callbacks will never actually be called (but must be valid nevertheless,
-because you never know, you know?).
+This is done by examining in each prepare call which file descriptors
+need to be watched by the other library, registering C<ev_io> watchers
+for them and starting an C<ev_timer> watcher for any timeouts (many
+libraries provide exactly this functionality). Then, in the check watcher,
+you check for any events that occurred (by checking the pending status
+of all watchers and stopping them) and call back into the library. The
+I/O and timer callbacks will never actually be called (but must be valid
+nevertheless, because you never know, you know?).
 
 As another example, the Perl Coro module uses these hooks to integrate
 coroutines into libev programs, by yielding to other active coroutines
@@ -1857,13 +2827,15 @@
 
 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 will be called 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).
+after the poll (this doesn't matter for C<ev_prepare> watchers).
+
+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
 
@@ -1875,7 +2847,8 @@
 
 Initialises and configures the prepare or check watcher - they have no
 parameters of any kind. There are C<ev_prepare_set> and C<ev_check_set>
-macros, but using them is utterly, utterly and completely pointless.
+macros, but using them is utterly, utterly, utterly and completely
+pointless.
 
 =back
 
@@ -1884,9 +2857,9 @@
 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 for an actually 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).
+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
@@ -1894,119 +2867,120 @@
 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;
+   static ev_io iow [nfd];
+   static ev_timer tw;
+
+   static void
+   io_cb (struct ev_loop *loop, ev_io *w, int revents)
+   {
+   }
+
+   // create io watchers for each fd and a timer before blocking
+   static void
+   adns_prepare_cb (struct ev_loop *loop, ev_prepare *w, int revents)
+   {
+     int timeout = 3600000;
+     struct pollfd fds [nfd];
+     // actual code will need to loop here and realloc etc.
+     adns_beforepoll (ads, fds, &nfd, &timeout, timeval_from (ev_time ()));
+
+     /* the callback is illegal, but won't be called as we stop during check */
+     ev_timer_init (&tw, 0, timeout * 1e-3, 0.);
+     ev_timer_start (loop, &tw);
+
+     // create one ev_io per pollfd
+     for (int i = 0; i < nfd; ++i)
+       {
+         ev_io_init (iow + i, io_cb, fds [i].fd,
+           ((fds [i].events & POLLIN ? EV_READ : 0)
+            | (fds [i].events & POLLOUT ? EV_WRITE : 0)));
+
+         fds [i].revents = 0;
+         ev_io_start (loop, iow + i);
+       }
+   }
+
+   // stop all watchers after blocking
+   static void
+   adns_check_cb (struct ev_loop *loop, ev_check *w, int revents)
+   {
+     ev_timer_stop (loop, &tw);
+
+     for (int i = 0; i < nfd; ++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;
 
-  static void
-  io_cb (ev_loop *loop, ev_io *w, int revents)
-  {
-  }
-
-  // create io watchers for each fd and a timer before blocking
-  static void
-  adns_prepare_cb (ev_loop *loop, ev_prepare *w, int revents)
-  {
-    int timeout = 3600000;
-    struct pollfd fds [nfd];
-    // actual code will need to loop here and realloc etc.
-    adns_beforepoll (ads, fds, &nfd, &timeout, timeval_from (ev_time ()));
-
-    /* the callback is illegal, but won't be called as we stop during check */
-    ev_timer_init (&tw, 0, timeout * 1e-3);
-    ev_timer_start (loop, &tw);
-
-    // create one ev_io per pollfd
-    for (int i = 0; i < nfd; ++i)
-      {
-        ev_io_init (iow + i, io_cb, fds [i].fd,
-          ((fds [i].events & POLLIN ? EV_READ : 0)
-           | (fds [i].events & POLLOUT ? EV_WRITE : 0)));
-
-        fds [i].revents = 0;
-        ev_io_start (loop, iow + i);
-      }
-  }
-
-  // stop all watchers after blocking
-  static void
-  adns_check_cb (ev_loop *loop, ev_check *w, int revents)
-  {
-    ev_timer_stop (loop, &tw);
-
-    for (int i = 0; i < nfd; ++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);
-      }
+         // now stop the watcher
+         ev_io_stop (loop, iow + i);
+       }
 
-    adns_afterpoll (adns, fds, nfd, timeval_from (ev_now (loop));
-  }
+     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
+notification (libadns 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);
-  }
+   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);
 
-  // do not ever call adns_afterpoll
+     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]);
+want to embed is not flexible enough to support it. Instead, you can
+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 uses
+this approach, effectively embedding EV as a client into the horrible
+libglib event loop.
 
-    return got_events;
-  }
+   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_run (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...
@@ -2022,36 +2996,34 @@
 As an example for a bug workaround, the kqueue backend might only support
 sockets on some platform, so it is unusable as generic backend, but you
 still want to make use of it because you have many sockets and it scales
-so nicely. In this case, you would create a kqueue-based loop and embed it
-into your default loop (which might use e.g. poll). Overall operation will
-be a bit slower because first libev has to poll and then call kevent, but
-at least you can use both at what they are best.
-
-As for prioritising I/O: rarely you have the case where some fds have
-to be watched and handled very quickly (with low latency), and even
-priorities and idle watchers might have too much overhead. In this case
-you would put all the high priority stuff in one loop and all the rest in
-a second one, and embed the second one in the first.
-
-As long as the watcher is active, the callback will be invoked every time
-there might be events pending in the embedded loop. The callback must then
-call C<ev_embed_sweep (mainloop, watcher)> to make a single sweep and invoke
-their callbacks (you could also start an idle watcher to give the embedded
-loop strictly lower priority for example). You can also set the callback
-to C<0>, in which case the embed watcher will automatically execute the
-embedded loop sweep.
-
-As long as the watcher is started it will automatically handle events. The
-callback will be invoked whenever some events have been handled. You can
-set the callback to C<0> to avoid having to specify one if you are not
-interested in that.
-
-Also, there have not currently been made special provisions for forking:
-when you fork, you not only have to call C<ev_loop_fork> on both loops,
-but you will also have to stop and restart any C<ev_embed> watchers
-yourself.
+so nicely. In this case, you would create a kqueue-based loop and embed
+it into your default loop (which might use e.g. poll). Overall operation
+will be a bit slower because first libev has to call C<poll> and then
+C<kevent>, but at least you can use both mechanisms for what they are
+best: C<kqueue> for scalable sockets and C<poll> if you want it to work :)
+
+As for prioritising I/O: under rare circumstances you have the case where
+some fds have to be watched and handled very quickly (with low latency),
+and even priorities and idle watchers might have too much overhead. In
+this case you would put all the high priority stuff in one loop and all
+the rest in a second one, and embed the second one in the first.
+
+As long as the watcher is active, the callback will be invoked every
+time there might be events pending in the embedded loop. The callback
+must then call C<ev_embed_sweep (mainloop, watcher)> to make a single
+sweep and invoke their callbacks (the callback doesn't need to invoke the
+C<ev_embed_sweep> function directly, it could also start an idle watcher
+to give the embedded loop strictly lower priority for example).
+
+You can also set the callback to C<0>, in which case the embed watcher
+will automatically execute the embedded loop sweep whenever necessary.
+
+Fork detection will be handled transparently while the C<ev_embed> watcher
+is active, i.e., the embedded loop will automatically be forked when the
+embedding loop forks. In other cases, the user is responsible for calling
+C<ev_loop_fork> on the embedded loop.
 
-Unfortunately, not all backends are embeddable, only the ones returned by
+Unfortunately, not all backends are embeddable: only the ones returned by
 C<ev_embeddable_backends> are, which, unfortunately, does not include any
 portable one.
 
@@ -2060,6 +3032,14 @@
 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.
 
+=head3 C<ev_embed> and fork
+
+While the C<ev_embed> watcher is running, forks in the embedding loop will
+automatically be applied to the embedded loop as well, so no special
+fork handling is required in that case. When the watcher is not running,
+however, it is still the task of the libev user to call C<ev_loop_fork ()>
+as applicable.
+
 =head3 Watcher-Specific Functions and Data Members
 
 =over 4
@@ -2072,13 +3052,13 @@
 embeddable. If the callback is C<0>, then C<ev_embed_sweep> will be
 invoked automatically, otherwise it is the responsibility of the callback
 to invoke it (it will continue to be called until the sweep has been done,
-if you do not want thta, you need to temporarily stop the embed watcher).
+if you do not want that, you need to temporarily stop the embed watcher).
 
 =item ev_embed_sweep (loop, ev_embed *)
 
 Make a single, non-blocking sweep over the embedded loop. This works
-similarly to C<ev_loop (embedded_loop, EVLOOP_NONBLOCK)>, but in the most
-apropriate way for embedded loops.
+similarly to C<ev_run (embedded_loop, EVRUN_NOWAIT)>, but in the most
+appropriate way for embedded loops.
 
 =item struct ev_loop *other [read-only]
 
@@ -2090,49 +3070,49 @@
 
 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
+loop is stored in C<loop_hi>, while the embeddable loop is stored in
+C<loop_lo> (which is C<loop_hi> in the case 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;
+   struct ev_loop *loop_hi = ev_default_init (0);
+   struct ev_loop *loop_lo = 0;
+   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);
-      }
+   struct ev_loop *loop = ev_default_init (0);
+   struct ev_loop *loop_socket = 0;
+   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;
+   if (!loop_socket)
+     loop_socket = loop;
 
-  // now use loop_socket for all sockets, and loop for everything else
+   // 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
@@ -2145,35 +3125,111 @@
 C<ev_default_fork> cheats and calls it in the wrong process, the fork
 handlers will be invoked, too, of course.
 
+=head3 The special problem of life after fork - how is it possible?
+
+Most uses of C<fork()> consist of forking, then some simple calls to set
+up/change the process environment, followed by a call to C<exec()>. This
+sequence should be handled by libev without any problems.
+
+This changes when the application actually wants to do event handling
+in the child, or both parent in child, in effect "continuing" after the
+fork.
+
+The default mode of operation (for libev, with application help to detect
+forks) is to duplicate all the state in the child, as would be expected
+when I<either> the parent I<or> the child process continues.
+
+When both processes want to continue using libev, then this is usually the
+wrong result. In that case, usually one process (typically the parent) is
+supposed to continue with all watchers in place as before, while the other
+process typically wants to start fresh, i.e. without any active watchers.
+
+The cleanest and most efficient way to achieve that with libev is to
+simply create a new event loop, which of course will be "empty", and
+use that for new watchers. This has the advantage of not touching more
+memory than necessary, and thus avoiding the copy-on-write, and the
+disadvantage of having to use multiple event loops (which do not support
+signal watchers).
+
+When this is not possible, or you want to use the default loop for
+other reasons, then in the process that wants to start "fresh", call
+C<ev_loop_destroy (EV_DEFAULT)> followed by C<ev_default_loop (...)>.
+Destroying the default loop will "orphan" (not stop) all registered
+watchers, so you have to be careful not to execute code that modifies
+those watchers. Note also that in that case, you have to re-register any
+signal watchers.
+
 =head3 Watcher-Specific Functions and Data Members
 
 =over 4
 
-=item ev_fork_init (ev_signal *, callback)
+=item ev_fork_init (ev_fork *, callback)
 
 Initialises and configures the fork watcher - it has no parameters of any
 kind. There is a C<ev_fork_set> macro, but using it is utterly pointless,
-believe me.
+really.
 
 =back
 
 
-=head2 C<ev_async> - how to wake up another event loop
+=head2 C<ev_cleanup> - even the best things end
+
+Cleanup watchers are called just before the event loop is being destroyed
+by a call to C<ev_loop_destroy>.
 
-In general, you cannot use an C<ev_loop> from multiple threads or other
+While there is no guarantee that the event loop gets destroyed, cleanup
+watchers provide a convenient method to install cleanup hooks for your
+program, worker threads and so on - you just to make sure to destroy the
+loop when you want them to be invoked.
+
+Cleanup watchers are invoked in the same way as any other watcher. Unlike
+all other watchers, they do not keep a reference to the event loop (which
+makes a lot of sense if you think about it). Like all other watchers, you
+can call libev functions in the callback, except C<ev_cleanup_start>.
+
+=head3 Watcher-Specific Functions and Data Members
+
+=over 4
+
+=item ev_cleanup_init (ev_cleanup *, callback)
+
+Initialises and configures the cleanup watcher - it has no parameters of
+any kind. There is a C<ev_cleanup_set> macro, but using it is utterly
+pointless, I assure you.
+
+=back
+
+Example: Register an atexit handler to destroy the default loop, so any
+cleanup functions are called.
+
+   static void
+   program_exits (void)
+   {
+     ev_loop_destroy (EV_DEFAULT_UC);
+   }
+
+   ...
+   atexit (program_exits);
+
+
+=head2 C<ev_async> - how to wake up an event loop
+
+In general, you cannot use an C<ev_run> 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.
+Sometimes, however, you need to wake up an 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).
+C<ev_async_sent> calls). In fact, you could use signal watchers as a kind
+of "global async watchers" by using a watcher on an otherwise unused
+signal, and C<ev_feed_signal> to signal this watcher from another thread,
+even without knowing which loop owns the signal.
 
 Unlike C<ev_signal> watchers, C<ev_async> works with any event loop, not
 just the default loop.
@@ -2183,10 +3239,11 @@
 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.
+need elaborate support such as pthreads or unportable memory access
+semantics.
 
 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. But at least I can tell you how to implement locking around your
 queue:
 
 =over 4
@@ -2194,8 +3251,8 @@
 =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:
+handler but you block the signal handler in the watcher callback. Here is
+an example that does that for some fictitious SIGUSR1 handler:
 
    static ev_async mysig;
 
@@ -2271,20 +3328,25 @@
 =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.
+kind. There is a C<ev_async_set> macro, but using it is utterly pointless,
+trust 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
+C<ev_feed_event>, this call is safe to do from other threads, signal or
+similar contexts (see the discussion 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>.
+Note that, as with other watchers in libev, multiple events might get
+compressed into a single callback invocation (another way to look at this
+is that C<ev_async> watchers are level-triggered, set on C<ev_async_send>,
+reset when the event loop detects that).
+
+This call incurs the overhead of a system call only once per event loop
+iteration, so while the overhead might be noticeable, it doesn't apply to
+repeated calls to C<ev_async_send> for the same event loop.
 
 =item bool = ev_async_pending (ev_async *)
 
@@ -2295,10 +3357,12 @@
 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.
+quickly check whether 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.
+Not that this does I<not> check whether the watcher itself is pending,
+only whether it has been requested to make this watcher pending: there
+is a time window between the event loop checking and resetting the async
+notification, and the callback being invoked.
 
 =back
 
@@ -2312,50 +3376,97 @@
 =item ev_once (loop, int fd, int events, ev_tstamp timeout, callback)
 
 This function combines a simple timer and an I/O watcher, calls your
-callback on whichever event happens first and automatically stop both
+callback on whichever event happens first and automatically stops both
 watchers. This is useful if you want to wait for a single event on an fd
 or timeout without having to allocate/configure/start/stop/free one or
 more watchers yourself.
 
-If C<fd> is less than 0, then no I/O watcher will be started and events
-is being ignored. Otherwise, an C<ev_io> watcher for the given C<fd> and
-C<events> set will be craeted and started.
+If C<fd> is less than 0, then no I/O watcher will be started and the
+C<events> argument is being ignored. Otherwise, an C<ev_io> watcher for
+the given C<fd> and C<events> set will be created and started.
 
 If C<timeout> is less than 0, then no timeout watcher will be
 started. Otherwise an C<ev_timer> watcher with after = C<timeout> (and
-repeat = 0) will be started. While C<0> is a valid timeout, it is of
-dubious value.
+repeat = 0) will be started. C<0> is a valid timeout.
 
-The callback has the type C<void (*cb)(int revents, void *arg)> and gets
+The callback has the type C<void (*cb)(int revents, void *arg)> and is
 passed an C<revents> set like normal event callbacks (a combination of
-C<EV_ERROR>, C<EV_READ>, C<EV_WRITE> or C<EV_TIMEOUT>) and the C<arg>
-value passed to C<ev_once>:
-
-  static void stdin_ready (int revents, void *arg)
-  {
-    if (revents & EV_TIMEOUT)
-      /* doh, nothing entered */;
-    else if (revents & EV_READ)
-      /* stdin might have data for us, joy! */;
-  }
+C<EV_ERROR>, C<EV_READ>, C<EV_WRITE> or C<EV_TIMER>) and the C<arg>
+value passed to C<ev_once>. Note that it is possible to receive I<both>
+a timeout and an io event at the same time - you probably should give io
+events precedence.
 
-  ev_once (STDIN_FILENO, EV_READ, 10., stdin_ready, 0);
+Example: wait up to ten seconds for data to appear on STDIN_FILENO.
 
-=item ev_feed_event (ev_loop *, watcher *, int revents)
+   static void stdin_ready (int revents, void *arg)
+   {
+     if (revents & EV_READ)
+       /* stdin might have data for us, joy! */;
+     else if (revents & EV_TIMER)
+       /* doh, nothing entered */;
+   }
 
-Feeds the given event set into the event loop, as if the specified event
-had happened for the specified watcher (which must be a pointer to an
-initialised but not necessarily started event watcher).
+   ev_once (STDIN_FILENO, EV_READ, 10., stdin_ready, 0);
 
-=item ev_feed_fd_event (ev_loop *, int fd, int revents)
+=item ev_feed_fd_event (loop, int fd, int revents)
 
 Feed an event on the given fd, as if a file descriptor backend detected
 the given events it.
 
-=item ev_feed_signal_event (ev_loop *loop, int signum)
+=item ev_feed_signal_event (loop, int signum)
+
+Feed an event as if the given signal occurred. See also C<ev_feed_signal>,
+which is async-safe.
+
+=back
+
+
+=head1 COMMON OR USEFUL IDIOMS (OR BOTH)
+
+This section explains some common idioms that are not immediately
+obvious. Note that examples are sprinkled over the whole manual, and this
+section only contains stuff that wouldn't fit anywhere else.
+
+=over 4
+
+=item Model/nested event loop invocations and exit conditions.
+
+Often (especially in GUI toolkits) there are places where you have
+I<modal> interaction, which is most easily implemented by recursively
+invoking C<ev_run>.
+
+This brings the problem of exiting - a callback might want to finish the
+main C<ev_run> call, but not the nested one (e.g. user clicked "Quit", but
+a modal "Are you sure?" dialog is still waiting), or just the nested one
+and not the main one (e.g. user clocked "Ok" in a modal dialog), or some
+other combination: In these cases, C<ev_break> will not work alone.
+
+The solution is to maintain "break this loop" variable for each C<ev_run>
+invocation, and use a loop around C<ev_run> until the condition is
+triggered, using C<EVRUN_ONCE>:
+
+   // main loop
+   int exit_main_loop = 0;
+
+   while (!exit_main_loop)
+     ev_run (EV_DEFAULT_ EVRUN_ONCE);
+
+   // in a model watcher
+   int exit_nested_loop = 0;
+
+   while (!exit_nested_loop)
+     ev_run (EV_A_ EVRUN_ONCE);
+
+To exit from any of these loops, just set the corresponding exit variable:
+
+   // exit modal loop
+   exit_nested_loop = 1;
+
+   // exit main program, after modal loop is finished
+   exit_main_loop = 1;
 
-Feed an event as if the given signal occured (C<loop> must be the default
-loop!).
+   // exit both
+   exit_main_loop = exit_nested_loop = 1;
 
 =back
 
@@ -2367,6 +3478,11 @@
 
 =over 4
 
+=item * Only the libevent-1.4.1-beta API is being emulated.
+
+This was the newest libevent version available when libev was implemented,
+and is still mostly unchanged in 2010.
+
 =item * Use it by including <event.h>, as usual.
 
 =item * The following members are fully supported: ev_base, ev_callback,
@@ -2381,7 +3497,7 @@
 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.
+base that registered the signal gets the signals.
 
 =item * Other members are not supported.
 
@@ -2393,12 +3509,12 @@
 =head1 C++ SUPPORT
 
 Libev comes with some simplistic wrapper classes for C++ that mainly allow
-you to use some convinience methods to start/stop watchers and also change
+you to use some convenience methods to start/stop watchers and also change
 the callback model to a model using method callbacks on objects.
 
 To use it,
    
-  #include <ev++.h>
+   #include <ev++.h>
 
 This automatically includes F<ev.h> and puts all of its definitions (many
 of them macros) into the global namespace. All C++ specific things are
@@ -2410,11 +3526,11 @@
 that the watcher is associated with (or no additional members at all if
 you disable C<EV_MULTIPLICITY> when embedding libev).
 
-Currently, functions, and static and non-static member functions can be
-used as callbacks. Other types should be easy to add as long as they only
-need one additional pointer for context. If you need support for other
-types of functors please contact the author (preferably after implementing
-it).
+Currently, functions, static and non-static member functions and classes
+with C<operator ()> can be used as callbacks. Other types should be easy
+to add as long as they only need one additional pointer for context. If
+you need support for other types of functors please contact the author
+(preferably after implementing it).
 
 Here is a list of things available in the C<ev> namespace:
 
@@ -2442,7 +3558,7 @@
 
 =item ev::TYPE::TYPE ()
 
-=item ev::TYPE::TYPE (struct ev_loop *)
+=item ev::TYPE::TYPE (loop)
 
 =item ev::TYPE::~TYPE
 
@@ -2475,14 +3591,42 @@
 
 Example: simple class declaration and watcher initialisation
 
-  struct myclass
-  {
-    void io_cb (ev::io &w, int revents) { }
-  }
-
-  myclass obj;
-  ev::io iow;
-  iow.set <myclass, &myclass::io_cb> (&obj);
+   struct myclass
+   {
+     void io_cb (ev::io &w, int revents) { }
+   }
+
+   myclass obj;
+   ev::io iow;
+   iow.set <myclass, &myclass::io_cb> (&obj);
+
+=item w->set (object *)
+
+This is a variation of a method callback - leaving out the method to call
+will default the method to C<operator ()>, which makes it possible to use
+functor objects without having to manually specify the C<operator ()> all
+the time. Incidentally, you can then also leave out the template argument
+list.
+
+The C<operator ()> method prototype must be C<void operator ()(watcher &w,
+int revents)>.
+
+See the method-C<set> above for more details.
+
+Example: use a functor object as callback.
+
+   struct myfunctor
+   {
+     void operator() (ev::io &w, int revents)
+     {
+       ...
+     }
+   }
+    
+   myfunctor f;
+
+   ev::io w;
+   w.set (&f);
 
 =item w->set<function> (void *data = 0)
 
@@ -2494,28 +3638,34 @@
 
 See the method-C<set> above for more details.
 
-Example:
+Example: Use a plain function as callback.
 
-  static void io_cb (ev::io &w, int revents) { }
-  iow.set <io_cb> ();
+   static void io_cb (ev::io &w, int revents) { }
+   iow.set <io_cb> ();
 
-=item w->set (struct ev_loop *)
+=item w->set (loop)
 
 Associates a different C<struct ev_loop> with this watcher. You can only
 do this when the watcher is inactive (and not pending either).
 
-=item w->set ([args])
+=item w->set ([arguments])
 
-Basically the same as C<ev_TYPE_set>, with the same args. Must be
-called at least once. Unlike the C counterpart, an active watcher gets
-automatically stopped and restarted when reconfiguring it with this
-method.
+Basically the same as C<ev_TYPE_set>, with the same arguments. Either this
+method or a suitable start method must be called at least once. Unlike the
+C counterpart, an active watcher gets automatically stopped and restarted
+when reconfiguring it with this method.
 
 =item w->start ()
 
 Starts the watcher. Note that there is no C<loop> argument, as the
 constructor already stores the event loop.
 
+=item w->start ([arguments])
+
+Instead of calling C<set> and C<start> methods separately, it is often
+convenient to wrap them in one call. Uses the same type of arguments as
+the configure C<set> method of the watcher.
+
 =item w->stop ()
 
 Stops the watcher if it is active. Again, no C<loop> argument.
@@ -2537,28 +3687,33 @@
 
 =back
 
-Example: Define a class with an IO and idle watcher, start one of them in
-the constructor.
+Example: Define a class with two I/O and idle watchers, start the I/O
+watchers in the constructor.
 
-  class myclass
-  {
-    ev::io   io;  void io_cb   (ev::io   &w, int revents);
-    ev:idle idle  void idle_cb (ev::idle &w, int revents);
-
-    myclass (int fd)
-    {
-      io  .set <myclass, &myclass::io_cb  > (this);
-      idle.set <myclass, &myclass::idle_cb> (this);
-
-      io.start (fd, ev::READ);
-    }
-  };
+   class myclass
+   {
+     ev::io   io  ; void io_cb   (ev::io   &w, int revents);
+     ev::io2  io2 ; void io2_cb  (ev::io   &w, int revents);
+     ev::idle idle; void idle_cb (ev::idle &w, int revents);
+
+     myclass (int fd)
+     {
+       io  .set <myclass, &myclass::io_cb  > (this);
+       io2 .set <myclass, &myclass::io2_cb > (this);
+       idle.set <myclass, &myclass::idle_cb> (this);
+
+       io.set (fd, ev::WRITE); // configure the watcher
+       io.start ();            // start it whenever convenient
+
+       io2.start (fd, ev::READ); // set + start in one call
+     }
+   };
 
 
 =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
+number of 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.
 
@@ -2569,30 +3724,55 @@
 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>).
+to C<libadns> (C<EV::ADNS>, but C<AnyEvent::DNS> is preferred nowadays),
+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
+It can be found and installed via CPAN, its homepage is at
 L<http://software.schmorp.de/pkg/EV>.
 
+=item Python
+
+Python bindings can be found at L<http://code.google.com/p/pyev/>. It
+seems to be quite complete and well-documented.
+
 =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
+of the libev API and adds file handle 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/>.
 
+Roger Pack reports that using the link order C<-lws2_32 -lmsvcrt-ruby-190>
+makes rev work even on mingw.
+
+=item Haskell
+
+A haskell binding to libev is available at
+L<http://hackage.haskell.org/cgi-bin/hackage-scripts/package/hlibev>.
+
 =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>.
+be found at L<http://proj.llucax.com.ar/wiki/evd>.
+
+=item Ocaml
+
+Erkki Seppala has written Ocaml bindings for libev, to be found at
+L<http://modeemi.cs.tut.fi/~flux/software/ocaml-ev/>.
+
+=item Lua
+
+Brian Maher has written a partial interface to libev for lua (at the
+time of this writing, only C<ev_io> and C<ev_timer>), to be found at
+L<http://github.com/brimworks/lua-ev>.
 
 =back
 
 
 =head1 MACRO MAGIC
 
-Libev can be compiled with a variety of options, the most fundamantal
+Libev can be compiled with a variety of options, the most fundamental
 of which is C<EV_MULTIPLICITY>. This option determines whether (most)
 functions and callbacks have an initial C<struct ev_loop *> argument.
 
@@ -2607,9 +3787,9 @@
 loop argument"). The C<EV_A> form is used when this is the sole argument,
 C<EV_A_> is used when other arguments are following. Example:
 
-  ev_unref (EV_A);
-  ev_timer_add (EV_A_ watcher);
-  ev_loop (EV_A_ 0);
+   ev_unref (EV_A);
+   ev_timer_add (EV_A_ watcher);
+   ev_run (EV_A_ 0);
 
 It assumes the variable C<loop> of type C<struct ev_loop *> is in scope,
 which is often provided by the following macro.
@@ -2620,11 +3800,11 @@
 loop parameter"). The C<EV_P> form is used when this is the sole parameter,
 C<EV_P_> is used when other parameters are following. Example:
 
-  // this is how ev_unref is being declared
-  static void ev_unref (EV_P);
+   // this is how ev_unref is being declared
+   static void ev_unref (EV_P);
 
-  // this is how you can declare your typical callback
-  static void cb (EV_P_ ev_timer *w, int revents)
+   // this is how you can declare your typical callback
+   static void cb (EV_P_ ev_timer *w, int revents)
 
 It declares a parameter C<loop> of type C<struct ev_loop *>, quite
 suitable for use with C<EV_A>.
@@ -2650,16 +3830,16 @@
 macros so it will work regardless of whether multiple loops are supported
 or not.
 
-  static void
-  check_cb (EV_P_ ev_timer *w, int revents)
-  {
-    ev_check_stop (EV_A_ w);
-  }
-
-  ev_check check;
-  ev_check_init (&check, check_cb);
-  ev_check_start (EV_DEFAULT_ &check);
-  ev_loop (EV_DEFAULT_ 0);
+   static void
+   check_cb (EV_P_ ev_timer *w, int revents)
+   {
+     ev_check_stop (EV_A_ w);
+   }
+
+   ev_check check;
+   ev_check_init (&check, check_cb);
+   ev_check_start (EV_DEFAULT_ &check);
+   ev_run (EV_DEFAULT_ 0);
 
 =head1 EMBEDDING
 
@@ -2676,15 +3856,15 @@
 =head2 FILESETS
 
 Depending on what features you need you need to include one or more sets of files
-in your app.
+in your application.
 
 =head3 CORE EVENT LOOP
 
 To include only the libev core (all the C<ev_*> functions), with manual
 configuration (no autoconf):
 
-  #define EV_STANDALONE 1
-  #include "ev.c"
+   #define EV_STANDALONE 1
+   #include "ev.c"
 
 This will automatically include F<ev.h>, too, and should be done in a
 single C source file only to provide the function implementations. To use
@@ -2692,28 +3872,28 @@
 done by writing a wrapper around F<ev.h> that you can include instead and
 where you can put other configuration options):
 
-  #define EV_STANDALONE 1
-  #include "ev.h"
+   #define EV_STANDALONE 1
+   #include "ev.h"
 
 Both header files and implementation files can be compiled with a C++
-compiler (at least, thats a stated goal, and breakage will be treated
+compiler (at least, that's a stated goal, and breakage will be treated
 as a bug).
 
 You need the following files in your source tree, or in a directory
 in your include path (e.g. in libev/ when using -Ilibev):
 
-  ev.h
-  ev.c
-  ev_vars.h
-  ev_wrap.h
-
-  ev_win32.c      required on win32 platforms only
-
-  ev_select.c     only when select backend is enabled (which is enabled by default)
-  ev_poll.c       only when poll backend is enabled (disabled by default)
-  ev_epoll.c      only when the epoll backend is enabled (disabled by default)
-  ev_kqueue.c     only when the kqueue backend is enabled (disabled by default)
-  ev_port.c       only when the solaris port backend is enabled (disabled by default)
+   ev.h
+   ev.c
+   ev_vars.h
+   ev_wrap.h
+
+   ev_win32.c      required on win32 platforms only
+
+   ev_select.c     only when select backend is enabled (which is enabled by default)
+   ev_poll.c       only when poll backend is enabled (disabled by default)
+   ev_epoll.c      only when the epoll backend is enabled (disabled by default)
+   ev_kqueue.c     only when the kqueue backend is enabled (disabled by default)
+   ev_port.c       only when the solaris port backend is enabled (disabled by default)
 
 F<ev.c> includes the backend files directly when enabled, so you only need
 to compile this single file.
@@ -2722,39 +3902,62 @@
 
 To include the libevent compatibility API, also include:
 
-  #include "event.c"
+   #include "event.c"
 
 in the file including F<ev.c>, and:
 
-  #include "event.h"
+   #include "event.h"
 
 in the files that want to use the libevent API. This also includes F<ev.h>.
 
 You need the following additional files for this:
 
-  event.h
-  event.c
+   event.h
+   event.c
 
 =head3 AUTOCONF SUPPORT
 
-Instead of using C<EV_STANDALONE=1> and providing your config in
+Instead of using C<EV_STANDALONE=1> and providing your configuration in
 whatever way you want, you can also C<m4_include([libev.m4])> in your
 F<configure.ac> and leave C<EV_STANDALONE> undefined. F<ev.c> will then
 include F<config.h> and configure itself accordingly.
 
 For this of course you need the m4 file:
 
-  libev.m4
+   libev.m4
 
 =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 in the absense of
-autoconf is noted for every option.
+define before including (or compiling) any of its files. The default in
+the absence of autoconf is documented for every option.
+
+Symbols marked with "(h)" do not change the ABI, and can have different
+values when compiling libev vs. including F<ev.h>, so it is permissible
+to redefine them before including F<ev.h> without breaking compatibility
+to a compiled library. All other symbols change the ABI, which means all
+users of libev and the libev code itself must be compiled with compatible
+settings.
 
 =over 4
 
-=item EV_STANDALONE
+=item EV_COMPAT3 (h)
+
+Backwards compatibility is a major concern for libev. This is why this
+release of libev comes with wrappers for the functions and symbols that
+have been renamed between libev version 3 and 4.
+
+You can disable these wrappers (to test compatibility with future
+versions) by defining C<EV_COMPAT3> to C<0> when compiling your
+sources. This has the additional advantage that you can drop the C<struct>
+from C<struct ev_loop> declarations, as libev will provide an C<ev_loop>
+typedef in that case.
+
+In some future version, the default for C<EV_COMPAT3> will become C<0>,
+and in some even more future version the compatibility code will be
+removed completely.
+
+=item EV_STANDALONE (h)
 
 Must always be C<1> if you do not use autoconf configuration, which
 keeps libev from including F<config.h>, and it also defines dummy
@@ -2762,24 +3965,40 @@
 supported). It will also not define any of the structs usually found in
 F<event.h> that are not directly supported by the libev core alone.
 
+In standalone mode, libev will still try to automatically deduce the
+configuration, but has to be more conservative.
+
 =item EV_USE_MONOTONIC
 
 If defined to be C<1>, libev will try to detect the availability of the
-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, although you have
+monotonic clock option at both compile time 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, although you have
 to make sure you link against any libraries where the C<clock_gettime>
-function is hiding in (often F<-lrt>).
+function is hiding in (often F<-lrt>). See also C<EV_USE_CLOCK_SYSCALL>.
 
 =item EV_USE_REALTIME
 
 If defined to be C<1>, libev will try to detect the availability of the
-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 the
-note about libraries in the description of C<EV_USE_MONOTONIC>, though.
+real-time clock option at compile time (and assume its availability
+at runtime if successful). Otherwise no use of the real-time clock
+option will be attempted. This effectively replaces C<gettimeofday>
+by C<clock_get (CLOCK_REALTIME, ...)> and will not normally affect
+correctness. See the note about libraries in the description of
+C<EV_USE_MONOTONIC>, though. Defaults to the opposite value of
+C<EV_USE_CLOCK_SYSCALL>.
+
+=item EV_USE_CLOCK_SYSCALL
+
+If defined to be C<1>, libev will try to use a direct syscall instead
+of calling the system-provided C<clock_gettime> function. This option
+exists because on GNU/Linux, C<clock_gettime> is in C<librt>, but C<librt>
+unconditionally pulls in C<libpthread>, slowing down single-threaded
+programs needlessly. Using a direct syscall is slightly slower (in
+theory), because no optimised vdso implementation can be used, but avoids
+the pthread dependency. Defaults to C<1> on GNU/Linux with glibc 2.x or
+higher, as it simplifies linking (no need for C<-lrt>).
 
 =item EV_USE_NANOSLEEP
 
@@ -2797,7 +4016,7 @@
 =item EV_USE_SELECT
 
 If undefined or defined to be C<1>, libev will compile in support for the
-C<select>(2) backend. No attempt at autodetection will be done: if no
+C<select>(2) backend. No attempt at auto-detection will be done: if no
 other method takes over, select will be it. Otherwise the select backend
 will not be compiled in.
 
@@ -2805,11 +4024,11 @@
 
 If defined to C<1>, then the select backend will use the system C<fd_set>
 structure. This is useful if libev doesn't compile due to a missing
-C<NFDBITS> or C<fd_mask> definition or it misguesses the bitset layout on
-exotic systems. This usually limits the range of file descriptors to some
-low limit such as 1024 or might have other limitations (winsocket only
-allows 64 sockets). The C<FD_SETSIZE> macro, set before compilation, might
-influence the size of the C<fd_set> used.
+C<NFDBITS> or C<fd_mask> definition or it mis-guesses the bitset layout
+on exotic systems. This usually limits the range of file descriptors to
+some low limit such as 1024 or might have other limitations (winsocket
+only allows 64 sockets). The C<FD_SETSIZE> macro, set before compilation,
+configures the maximum size of the C<fd_set>.
 
 =item EV_SELECT_IS_WINSOCKET
 
@@ -2821,7 +4040,7 @@
 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
+=item EV_FD_TO_WIN32_HANDLE(fd)
 
 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
@@ -2829,6 +4048,20 @@
 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_WIN32_HANDLE_TO_FD(handle)
+
+If C<EV_SELECT_IS_WINSOCKET> then libev maps handles to file descriptors
+using the standard C<_open_osfhandle> function. For programs implementing
+their own fd to handle mapping, overwriting this function makes it easier
+to do so. This can be done by defining this macro to an appropriate value.
+
+=item EV_WIN32_CLOSE_FD(fd)
+
+If programs implement their own fd to handle mapping on win32, then this
+macro can be used to override the C<close> function, useful to unregister
+file descriptors again. Note that the replacement function has to close
+the underlying OS handle.
+
 =item EV_USE_POLL
 
 If defined to be C<1>, libev will compile in support for the C<poll>(2)
@@ -2864,7 +4097,7 @@
 
 =item EV_USE_DEVPOLL
 
-reserved for future expansion, works like the USE symbols above.
+Reserved for future expansion, works like the USE symbols above.
 
 =item EV_USE_INOTIFY
 
@@ -2881,27 +4114,27 @@
 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>
+In the absence 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
+=item EV_H (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>, 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
+=item EV_CONFIG_H (h)
 
 If C<EV_STANDALONE> isn't C<1>, this variable can be used to override
 F<ev.c>'s idea of where to find the F<config.h> file, similarly to
 C<EV_H>, above.
 
-=item EV_EVENT_H
+=item EV_EVENT_H (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, the default is C<"event.h">.
 
-=item EV_PROTOTYPES
+=item EV_PROTOTYPES (h)
 
 If defined to be C<0>, then F<ev.h> will not define any function
 prototypes, but still define all the structs and other symbols. This is
@@ -2930,74 +4163,181 @@
 and time, so using the defaults of five priorities (-2 .. +2) is usually
 fine.
 
-If your embedding app does not need any priorities, defining these both to
-C<0> will save some memory and cpu.
+If your embedding application does not need any priorities, defining these
+both to C<0> will save some memory and CPU.
 
-=item EV_PERIODIC_ENABLE
+=item EV_PERIODIC_ENABLE, EV_IDLE_ENABLE, EV_EMBED_ENABLE, EV_STAT_ENABLE,
+EV_PREPARE_ENABLE, EV_CHECK_ENABLE, EV_FORK_ENABLE, EV_SIGNAL_ENABLE,
+EV_ASYNC_ENABLE, EV_CHILD_ENABLE.
+
+If undefined or defined to be C<1> (and the platform supports it), then
+the respective watcher type is supported. If defined to be C<0>, then it
+is not. Disabling watcher types mainly saves code size.
 
-If undefined or defined to be C<1>, then periodic timers are supported. If
-defined to be C<0>, then they are not. Disabling them saves a few kB of
-code.
+=item EV_FEATURES
 
-=item EV_IDLE_ENABLE
+If you need to shave off some kilobytes of code at the expense of some
+speed (but with the full API), you can define this symbol to request
+certain subsets of functionality. The default is to enable all features
+that can be enabled on the platform.
+
+A typical way to use this symbol is to define it to C<0> (or to a bitset
+with some broad features you want) and then selectively re-enable
+additional parts you want, for example if you want everything minimal,
+but multiple event loop support, async and child watchers and the poll
+backend, use this:
+
+   #define EV_FEATURES 0
+   #define EV_MULTIPLICITY 1
+   #define EV_USE_POLL 1
+   #define EV_CHILD_ENABLE 1
+   #define EV_ASYNC_ENABLE 1
 
-If undefined or defined to be C<1>, then idle watchers are supported. If
-defined to be C<0>, then they are not. Disabling them saves a few kB of
-code.
+The actual value is a bitset, it can be a combination of the following
+values:
 
-=item EV_EMBED_ENABLE
+=over 4
 
-If undefined or defined to be C<1>, then embed watchers are supported. If
-defined to be C<0>, then they are not.
+=item C<1> - faster/larger code
 
-=item EV_STAT_ENABLE
+Use larger code to speed up some operations.
 
-If undefined or defined to be C<1>, then stat watchers are supported. If
-defined to be C<0>, then they are not.
+Currently this is used to override some inlining decisions (enlarging the
+code size by roughly 30% on amd64).
 
-=item EV_FORK_ENABLE
+When optimising for size, use of compiler flags such as C<-Os> with
+gcc is recommended, as well as C<-DNDEBUG>, as libev contains a number of
+assertions.
 
-If undefined or defined to be C<1>, then fork watchers are supported. If
-defined to be C<0>, then they are not.
+=item C<2> - faster/larger data structures
 
-=item EV_ASYNC_ENABLE
+Replaces the small 2-heap for timer management by a faster 4-heap, larger
+hash table sizes and so on. This will usually further increase code size
+and can additionally have an effect on the size of data structures at
+runtime.
 
-If undefined or defined to be C<1>, then async watchers are supported. If
-defined to be C<0>, then they are not.
+=item C<4> - full API configuration
 
-=item EV_MINIMAL
+This enables priorities (sets C<EV_MAXPRI>=2 and C<EV_MINPRI>=-2), and
+enables multiplicity (C<EV_MULTIPLICITY>=1).
 
-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.
+=item C<8> - full API
+
+This enables a lot of the "lesser used" API functions. See C<ev.h> for
+details on which parts of the API are still available without this
+feature, and do not complain if this subset changes over time.
+
+=item C<16> - enable all optional watcher types
+
+Enables all optional watcher types.  If you want to selectively enable
+only some watcher types other than I/O and timers (e.g. prepare,
+embed, async, child...) you can enable them manually by defining
+C<EV_watchertype_ENABLE> to C<1> instead.
+
+=item C<32> - enable all backends
+
+This enables all backends - without this feature, you need to enable at
+least one backend manually (C<EV_USE_SELECT> is a good choice).
+
+=item C<64> - enable OS-specific "helper" APIs
+
+Enable inotify, eventfd, signalfd and similar OS-specific helper APIs by
+default.
+
+=back
+
+Compiling with C<gcc -Os -DEV_STANDALONE -DEV_USE_EPOLL=1 -DEV_FEATURES=0>
+reduces the compiled size of libev from 24.7Kb code/2.8Kb data to 6.5Kb
+code/0.3Kb data on my GNU/Linux amd64 system, while still giving you I/O
+watchers, timers and monotonic clock support.
+
+With an intelligent-enough linker (gcc+binutils are intelligent enough
+when you use C<-Wl,--gc-sections -ffunction-sections>) functions unused by
+your program might be left out as well - a binary starting a timer and an
+I/O watcher then might come out at only 5Kb.
+
+=item EV_AVOID_STDIO
+
+If this is set to C<1> at compiletime, then libev will avoid using stdio
+functions (printf, scanf, perror etc.). This will increase the code size
+somewhat, but if your program doesn't otherwise depend on stdio and your
+libc allows it, this avoids linking in the stdio library which is quite
+big.
+
+Note that error messages might become less precise when this option is
+enabled.
+
+=item EV_NSIG
+
+The highest supported signal number, +1 (or, the number of
+signals): Normally, libev tries to deduce the maximum number of signals
+automatically, but sometimes this fails, in which case it can be
+specified. Also, using a lower number than detected (C<32> should be
+good for about any system in existence) can save some memory, as libev
+statically allocates some 12-24 bytes per signal number.
 
 =item EV_PID_HASHSIZE
 
 C<ev_child> watchers use a small hash table to distribute workload by
-pid. The default size is C<16> (or C<1> with C<EV_MINIMAL>), usually more
-than enough. If you need to manage thousands of children you might want to
-increase this value (I<must> be a power of two).
+pid. The default size is C<16> (or C<1> with C<EV_FEATURES> disabled),
+usually more than enough. If you need to manage thousands of children you
+might want to increase this value (I<must> be a power of two).
 
 =item EV_INOTIFY_HASHSIZE
 
 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).
+inotify watch id. The default size is C<16> (or C<1> with C<EV_FEATURES>
+disabled), 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 heaps, libev uses a 4-heap when this symbol is defined
+to C<1>. The 4-heap uses more complicated (longer) code but has noticeably
+faster performance with many (thousands) of watchers.
+
+The default is C<1>, unless C<EV_FEATURES> overrides it, in which case it
+will be C<0>.
+
+=item EV_HEAP_CACHE_AT
+
+Heaps are not very cache-efficient. To improve the cache-efficiency of the
+timer and periodics heaps, 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
+noticeably with many (hundreds) of watchers.
+
+The default is C<1>, unless C<EV_FEATURES> overrides it, in which case it
+will be C<0>.
+
+=item EV_VERIFY
+
+Controls how much internal verification (see C<ev_verify ()>) will
+be done: If set to C<0>, no internal verification code will be compiled
+in. If set to C<1>, then verification code will be compiled in, but not
+called. If set to C<2>, then the internal verification code will be
+called once per loop, which can slow down libev. If set to C<3>, then the
+verification code will be called very frequently, which will slow down
+libev considerably.
+
+The default is C<1>, unless C<EV_FEATURES> overrides it, in which case it
+will be C<0>.
 
 =item EV_COMMON
 
 By default, all watchers have a C<void *data> member. By redefining
-this macro to a something else you can include more and other types of
+this macro to something else you can include more and other types of
 members. You have to define it each time you include one of the files,
 though, and it must be identical each time.
 
 For example, the perl EV module uses something like this:
 
-  #define EV_COMMON                       \
-    SV *self; /* contains this struct */  \
-    SV *cb_sv, *fh /* note no trailing ";" */
+   #define EV_COMMON                       \
+     SV *self; /* contains this struct */  \
+     SV *cb_sv, *fh /* note no trailing ";" */
 
 =item EV_CB_DECLARE (type)
 
@@ -3012,18 +4352,20 @@
 avoid the C<struct ev_loop *> as first argument in all cases, or to use
 method calls instead of plain function calls in C++.
 
+=back
+
 =head2 EXPORTED API SYMBOLS
 
-If you need to re-export the API (e.g. via a dll) and you need a list of
+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
+   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).
+itself, but sometimes it is inconvenient to avoid this).
 
 A sed command like this will create wrapper C<#define>'s that you need to
 include before including F<ev.h>:
@@ -3050,46 +4392,55 @@
 The usage in rxvt-unicode is simpler. It has a F<ev_cpp.h> header file
 that everybody includes and which overrides some configure choices:
 
-  #define EV_MINIMAL 1
-  #define EV_USE_POLL 0
-  #define EV_MULTIPLICITY 0
-  #define EV_PERIODIC_ENABLE 0
-  #define EV_STAT_ENABLE 0
-  #define EV_FORK_ENABLE 0
-  #define EV_CONFIG_H <config.h>
-  #define EV_MINPRI 0
-  #define EV_MAXPRI 0
+   #define EV_FEATURES 8
+   #define EV_USE_SELECT 1
+   #define EV_PREPARE_ENABLE 1
+   #define EV_IDLE_ENABLE 1
+   #define EV_SIGNAL_ENABLE 1
+   #define EV_CHILD_ENABLE 1
+   #define EV_USE_STDEXCEPT 0
+   #define EV_CONFIG_H <config.h>
 
-  #include "ev++.h"
+   #include "ev++.h"
 
 And a F<ev_cpp.C> implementation file that contains libev proper and is compiled:
 
-  #include "ev_cpp.h"
-  #include "ev.c"
-
+   #include "ev_cpp.h"
+   #include "ev.c"
 
-=head1 THREADS AND COROUTINES
+=head1 INTERACTION WITH OTHER PROGRAMS OR LIBRARIES
 
-=head2 THREADS
+=head2 THREADS AND COROUTINES
 
-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.
+=head3 THREADS
 
-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:
+All libev functions are reentrant and thread-safe unless explicitly
+documented otherwise, but libev implements no locking itself. This means
+that you can use as many loops as you want in parallel, as long as there
+are no concurrent calls into any libev function with the same loop
+parameter (C<ev_default_*> calls have an implicit default loop parameter,
+of course): libev guarantees that different event loops share no data
+structures that need any locking.
+
+Or to put it differently: calls with different loop parameters can be done
+concurrently 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).
+
+Specifically to support threads (and signal handlers), libev implements
+so-called C<ev_async> watchers, which allow some limited form of
+concurrency on the same event loop, namely waking it up "from the
+outside".
+
+If you want to know which design (one loop, locking, or multiple loops
+without or something else still) is best for your problem, then I cannot
+help you, but here is 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.
+in that thread, or create a separate 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.
@@ -3100,54 +4451,509 @@
 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.
+loop is handed through multiple threads in a kind of round-robin fashion.
 
-Chosing a model is hard - look around, learn, know that usually you cna do
+Choosing a model is hard - look around, learn, know that usually you can 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...).
+event loop.
+
+C<ev_async> watchers can be used to wake them up from other threads safely
+(or from signal contexts...).
+
+An example use would be to communicate signals or other events that only
+work in the default loop by registering the signal watcher with the
+default loop and triggering an C<ev_async> watcher from the default loop
+watcher callback into the event loop interested in the signal.
 
 =back
 
-=head2 COROUTINES
+=head4 THREAD LOCKING EXAMPLE
+
+Here is a fictitious example of how to run an event loop in a different
+thread than where callbacks are being invoked and watchers are
+created/added/removed.
+
+For a real-world example, see the C<EV::Loop::Async> perl module,
+which uses exactly this technique (which is suited for many high-level
+languages).
+
+The example uses a pthread mutex to protect the loop data, a condition
+variable to wait for callback invocations, an async watcher to notify the
+event loop thread and an unspecified mechanism to wake up the main thread.
+
+First, you need to associate some data with the event loop:
+
+   typedef struct {
+     mutex_t lock; /* global loop lock */
+     ev_async async_w;
+     thread_t tid;
+     cond_t invoke_cv;
+   } userdata;
+
+   void prepare_loop (EV_P)
+   {
+      // for simplicity, we use a static userdata struct.
+      static userdata u;
+
+      ev_async_init (&u->async_w, async_cb);
+      ev_async_start (EV_A_ &u->async_w);
+
+      pthread_mutex_init (&u->lock, 0);
+      pthread_cond_init (&u->invoke_cv, 0);
+
+      // now associate this with the loop
+      ev_set_userdata (EV_A_ u);
+      ev_set_invoke_pending_cb (EV_A_ l_invoke);
+      ev_set_loop_release_cb (EV_A_ l_release, l_acquire);
+
+      // then create the thread running ev_loop
+      pthread_create (&u->tid, 0, l_run, EV_A);
+   }
+
+The callback for the C<ev_async> watcher does nothing: the watcher is used
+solely to wake up the event loop so it takes notice of any new watchers
+that might have been added:
+
+   static void
+   async_cb (EV_P_ ev_async *w, int revents)
+   {
+      // just used for the side effects
+   }
+
+The C<l_release> and C<l_acquire> callbacks simply unlock/lock the mutex
+protecting the loop data, respectively.
+
+   static void
+   l_release (EV_P)
+   {
+     userdata *u = ev_userdata (EV_A);
+     pthread_mutex_unlock (&u->lock);
+   }
+
+   static void
+   l_acquire (EV_P)
+   {
+     userdata *u = ev_userdata (EV_A);
+     pthread_mutex_lock (&u->lock);
+   }
+
+The event loop thread first acquires the mutex, and then jumps straight
+into C<ev_run>:
+
+   void *
+   l_run (void *thr_arg)
+   {
+     struct ev_loop *loop = (struct ev_loop *)thr_arg;
+
+     l_acquire (EV_A);
+     pthread_setcanceltype (PTHREAD_CANCEL_ASYNCHRONOUS, 0);
+     ev_run (EV_A_ 0);
+     l_release (EV_A);
+
+     return 0;
+   }
+
+Instead of invoking all pending watchers, the C<l_invoke> callback will
+signal the main thread via some unspecified mechanism (signals? pipe
+writes? C<Async::Interrupt>?) and then waits until all pending watchers
+have been called (in a while loop because a) spurious wakeups are possible
+and b) skipping inter-thread-communication when there are no pending
+watchers is very beneficial):
+
+   static void
+   l_invoke (EV_P)
+   {
+     userdata *u = ev_userdata (EV_A);
+
+     while (ev_pending_count (EV_A))
+       {
+         wake_up_other_thread_in_some_magic_or_not_so_magic_way ();
+         pthread_cond_wait (&u->invoke_cv, &u->lock);
+       }
+   }
+
+Now, whenever the main thread gets told to invoke pending watchers, it
+will grab the lock, call C<ev_invoke_pending> and then signal the loop
+thread to continue:
+
+   static void
+   real_invoke_pending (EV_P)
+   {
+     userdata *u = ev_userdata (EV_A);
+
+     pthread_mutex_lock (&u->lock);
+     ev_invoke_pending (EV_A);
+     pthread_cond_signal (&u->invoke_cv);
+     pthread_mutex_unlock (&u->lock);
+   }
+
+Whenever you want to start/stop a watcher or do other modifications to an
+event loop, you will now have to lock:
 
-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.
+   ev_timer timeout_watcher;
+   userdata *u = ev_userdata (EV_A);
 
-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.
+   ev_timer_init (&timeout_watcher, timeout_cb, 5.5, 0.);
 
+   pthread_mutex_lock (&u->lock);
+   ev_timer_start (EV_A_ &timeout_watcher);
+   ev_async_send (EV_A_ &u->async_w);
+   pthread_mutex_unlock (&u->lock);
 
-=head1 COMPLEXITIES
+Note that sending the C<ev_async> watcher is required because otherwise
+an event loop currently blocking in the kernel will have no knowledge
+about the newly added timer. By waking up the loop it will pick up any new
+watchers in the next event loop iteration.
+
+=head3 COROUTINES
+
+Libev is very accommodating to coroutines ("cooperative threads"):
+libev fully supports nesting calls to its functions from different
+coroutines (e.g. you can call C<ev_run> 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 taken to ensure that libev does not keep local state inside
+C<ev_run>, and other calls do not usually allow for coroutine switches as
+they do not call any callbacks.
+
+=head2 COMPILER WARNINGS
+
+Depending on your compiler and compiler settings, you might get no or a
+lot of warnings when compiling libev code. Some people are apparently
+scared by this.
+
+However, these are unavoidable for many reasons. For one, each compiler
+has different warnings, and each user has different tastes regarding
+warning options. "Warn-free" code therefore cannot be a goal except when
+targeting a specific compiler and compiler-version.
+
+Another reason is that some compiler warnings require elaborate
+workarounds, or other changes to the code that make it less clear and less
+maintainable.
+
+And of course, some compiler warnings are just plain stupid, or simply
+wrong (because they don't actually warn about the condition their message
+seems to warn about). For example, certain older gcc versions had some
+warnings that resulted in an extreme number of false positives. These have
+been fixed, but some people still insist on making code warn-free with
+such buggy versions.
+
+While libev is written to generate as few warnings as possible,
+"warn-free" code is not a goal, and it is recommended not to build libev
+with any compiler warnings enabled unless you are prepared to cope with
+them (e.g. by ignoring them). Remember that warnings are just that:
+warnings, not errors, or proof of bugs.
+
+
+=head2 VALGRIND
+
+Valgrind has a special section here because it is a popular tool that is
+highly useful. Unfortunately, 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, just as memory accounted to global variables
+is not a memleak - the memory is still being referenced, and didn't leak.
+
+Similarly, under some circumstances, valgrind might report kernel bugs
+as if it were a bug in libev (e.g. in realloc or in the poll backend,
+although an acceptable workaround has been found here), or it might be
+confused.
+
+Keep in mind that valgrind is a very good tool, but only a tool. Don't
+make it into some kind of religion.
+
+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 (best check the archives, too :). 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 PORTABILITY NOTES
+
+=head2 GNU/LINUX 32 BIT LIMITATIONS
+
+GNU/Linux is the only common platform that supports 64 bit file/large file
+interfaces but I<disables> them by default.
+
+That means that libev compiled in the default environment doesn't support
+files larger than 2GiB or so, which mainly affects C<ev_stat> watchers.
+
+Unfortunately, many programs try to work around this GNU/Linux issue
+by enabling the large file API, which makes them incompatible with the
+standard libev compiled for their system.
+
+Likewise, libev cannot enable the large file API itself as this would
+suddenly make it incompatible to the default compile time environment,
+i.e. all programs not using special compile switches.
+
+=head2 OS/X AND DARWIN BUGS
+
+The whole thing is a bug if you ask me - basically any system interface
+you touch is broken, whether it is locales, poll, kqueue or even the
+OpenGL drivers.
+
+=head3 C<kqueue> is buggy
+
+The kqueue syscall is broken in all known versions - most versions support
+only sockets, many support pipes.
+
+Libev tries to work around this by not using C<kqueue> by default on this
+rotten platform, but of course you can still ask for it when creating a
+loop - embedding a socket-only kqueue loop into a select-based one is
+probably going to work well.
+
+=head3 C<poll> is buggy
+
+Instead of fixing C<kqueue>, Apple replaced their (working) C<poll>
+implementation by something calling C<kqueue> internally around the 10.5.6
+release, so now C<kqueue> I<and> C<poll> are broken.
+
+Libev tries to work around this by not using C<poll> by default on
+this rotten platform, but of course you can still ask for it when creating
+a loop.
+
+=head3 C<select> is buggy
+
+All that's left is C<select>, and of course Apple found a way to fuck this
+one up as well: On OS/X, C<select> actively limits the number of file
+descriptors you can pass in to 1024 - your program suddenly crashes when
+you use more.
+
+There is an undocumented "workaround" for this - defining
+C<_DARWIN_UNLIMITED_SELECT>, which libev tries to use, so select I<should>
+work on OS/X.
+
+=head2 SOLARIS PROBLEMS AND WORKAROUNDS
+
+=head3 C<errno> reentrancy
+
+The default compile environment on Solaris is unfortunately so
+thread-unsafe that you can't even use components/libraries compiled
+without C<-D_REENTRANT> in a threaded program, which, of course, isn't
+defined by default. A valid, if stupid, implementation choice.
+
+If you want to use libev in threaded environments you have to make sure
+it's compiled with C<_REENTRANT> defined.
+
+=head3 Event port backend
+
+The scalable event interface for Solaris is called "event
+ports". Unfortunately, this mechanism is very buggy in all major
+releases. If you run into high CPU usage, your program freezes or you get
+a large number of spurious wakeups, make sure you have all the relevant
+and latest kernel patches applied. No, I don't know which ones, but there
+are multiple ones to apply, and afterwards, event ports actually work
+great.
+
+If you can't get it to work, you can try running the program by setting
+the environment variable C<LIBEV_FLAGS=3> to only allow C<poll> and
+C<select> backends.
+
+=head2 AIX POLL BUG
+
+AIX unfortunately has a broken C<poll.h> header. Libev works around
+this by trying to avoid the poll backend altogether (i.e. it's not even
+compiled in), which normally isn't a big problem as C<select> works fine
+with large bitsets on AIX, and AIX is dead anyway.
+
+=head2 WIN32 PLATFORM LIMITATIONS AND WORKAROUNDS
+
+=head3 General issues
+
+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. Actually, it only applies to the microsofts own compilers,
+as every compielr comes with a slightly differently broken/incompatible
+environment.
+
+Lifting these limitations would basically require the full
+re-implementation of the I/O system. If you are into this kind of thing,
+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.
+
+Sensible signal handling is officially unsupported by Microsoft - libev
+tries its best, but under most conditions, signals will simply not work.
+
+Not a libev limitation but worth mentioning: windows apparently doesn't
+accept large writes: instead of resulting in a partial write, windows will
+either accept everything or return C<ENOBUFS> if the buffer is too large,
+so make sure you only write small amounts into your sockets (less than a
+megabyte seems safe, but this apparently depends on the amount of memory
+available).
+
+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
+(due to Microsoft monopoly games).
+
+A typical way to use libev under windows is to embed it (see the embedding
+section for details) and use the following F<evwrap.h> header file instead
+of F<ev.h>:
+
+   #define EV_STANDALONE              /* keeps ev from requiring config.h */
+   #define EV_SELECT_IS_WINSOCKET 1   /* configure libev for windows select */
+
+   #include "ev.h"
+
+And compile the following F<evwrap.c> file into your project (make sure
+you do I<not> compile the F<ev.c> or any other embedded source files!):
+
+   #include "evwrap.h"
+   #include "ev.c"
+
+=head3 The winsocket C<select> function
+
+The winsocket C<select> function doesn't follow POSIX in that it
+requires socket I<handles> and not socket I<file descriptors> (it is
+also extremely buggy). This makes select very inefficient, and also
+requires a mapping from file descriptors to socket handles (the Microsoft
+C runtime provides the function C<_open_osfhandle> for this). 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.
+
+=head3 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. Sounds 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 and many
+other interpreters do their 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.
+
+=head2 PORTABILITY REQUIREMENTS
+
+In addition to a working ISO-C implementation and of course the
+backend-specific APIs, libev relies on a few additional extensions:
+
+=over 4
+
+=item C<void (*)(ev_watcher_type *, int revents)> must have compatible
+calling conventions regardless of C<ev_watcher_type *>.
+
+Libev assumes not only that all watcher pointers have the same internal
+structure (guaranteed by POSIX but not by ISO C for example), but it also
+assumes that the same (machine) code can be used to call any watcher
+callback: The watcher callbacks have different type signatures, but libev
+calls them using an C<ev_watcher *> internally.
+
+=item pointer accesses must be thread-atomic
+
+Accessing a pointer value must be atomic, it must both be readable and
+writable in one piece - this is the case on all current architectures.
+
+=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 with respect to 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 its API, 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 with millisecond accuracy
+(the design goal for libev). This requirement is overfulfilled by
+implementations using IEEE 754, which is basically all existing ones. With
+IEEE 754 doubles, you get microsecond accuracy until at least 2200.
+
+=back
+
+If you know of other additional requirements drop me a note.
+
+
+=head1 ALGORITHMIC COMPLEXITIES
 
 In this section the complexities of (many of) the algorithms used inside
-libev will be explained. For complexity discussions about backends see the
-documentation for C<ev_default_init>.
+libev will be documented. For complexity discussions about backends see
+the documentation for C<ev_default_init>.
 
 All of the following are about amortised time: If an array needs to be
 extended, libev needs to realloc and move the whole array, but this
-happens asymptotically never with higher number of elements, so O(1) might
-mean it might do a lengthy realloc operation in rare cases, but on average
-it is much faster and asymptotically approaches constant time.
+happens asymptotically rarer with higher number of elements, so O(1) might
+mean that libev does a lengthy realloc operation in rare cases, but on
+average it is much faster and asymptotically approaches constant time.
 
 =over 4
 
 =item Starting and stopping timer/periodic watchers: O(log skipped_other_timers)
 
 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
+there are 100 watchers that would trigger before that, then inserting will
 have to skip roughly seven (C<ld 100>) of these watchers.
 
 =item Changing timer/periodic watchers (by autorepeat or calling again): O(log skipped_other_timers)
 
-That means that 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/fork/async watchers: O(1)
@@ -3158,20 +4964,21 @@
 
 =item Stopping an io/signal/child watcher: O(number_of_watchers_for_this_(fd/signal/pid % EV_PID_HASHSIZE))
 
-These watchers are stored in lists then need to be walked to find the
+These watchers are stored in lists, so they need to be walked to find the
 correct watcher to remove. The lists are usually short (you don't usually
-have many watchers waiting for the same fd or signal).
+have many watchers waiting for the same fd or signal: one is typical, two
+is rare).
 
 =item Finding the next timer in each loop iteration: O(1)
 
-By virtue of using a binary heap, the next timer is always found at the
-beginning of the storage array.
+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, depending
-on backend and wether C<ev_io_set> was used).
+on backend and whether C<ev_io_set> was used).
 
 =item Activating one watcher (putting it into the pending state): O(1)
 
@@ -3180,7 +4987,7 @@
 Priorities are implemented by allocating some space for each
 priority. When doing priority-based operations, libev usually has to
 linearly search all the priorities, but starting/stopping and activating
-watchers becomes O(1) w.r.t. priority handling.
+watchers becomes O(1) with respect to priority handling.
 
 =item Sending an ev_async: O(1)
 
@@ -3188,113 +4995,147 @@
 
 =item Processing signals: O(max_signal_number)
 
-Sending involves a syscall I<iff> there were no other C<ev_async_send>
+Sending involves a system call 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.
+=head1 PORTING FROM LIBEV 3.X TO 4.X
 
-There is no supported compilation method available on windows except
-embedding it into other applications.
+The major version 4 introduced some incompatible changes to the API.
 
-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 model, which cannot
-be implemented efficiently on windows (microsoft monopoly games).
+At the moment, the C<ev.h> header file provides compatibility definitions
+for all changes, so most programs should still compile. The compatibility
+layer might be removed in later versions of libev, so better update to the
+new API early than late.
 
 =over 4
 
-=item The winsocket select function
+=item C<EV_COMPAT3> backwards compatibility mechanism
 
-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 backward compatibility mechanism can be controlled by
+C<EV_COMPAT3>. See L<PREPROCESSOR SYMBOLS/MACROS> in the L<EMBEDDING>
+section.
 
-The configuration for a "naked" win32 using the microsoft runtime
-libraries and raw winsocket select is:
+=item C<ev_default_destroy> and C<ev_default_fork> have been removed
 
-  #define EV_USE_SELECT 1
-  #define EV_SELECT_IS_WINSOCKET 1   /* forces EV_SELECT_USE_FD_SET, too */
+These calls can be replaced easily by their C<ev_loop_xxx> counterparts:
 
-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.
+   ev_loop_destroy (EV_DEFAULT_UC);
+   ev_loop_fork (EV_DEFAULT);
 
-=item Limited number of file descriptors
+=item function/symbol renames
 
-Windows has numerous arbitrary (and low) limits on things. Early versions
-of winsocket's select only supported waiting for a max. 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).
+A number of functions and symbols have been renamed:
 
-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).
+  ev_loop         => ev_run
+  EVLOOP_NONBLOCK => EVRUN_NOWAIT
+  EVLOOP_ONESHOT  => EVRUN_ONCE
 
-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.
+  ev_unloop       => ev_break
+  EVUNLOOP_CANCEL => EVBREAK_CANCEL
+  EVUNLOOP_ONE    => EVBREAK_ONE
+  EVUNLOOP_ALL    => EVBREAK_ALL
 
-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.
+  EV_TIMEOUT      => EV_TIMER
 
-=back
+  ev_loop_count   => ev_iteration
+  ev_loop_depth   => ev_depth
+  ev_loop_verify  => ev_verify
 
+Most functions working on C<struct ev_loop> objects don't have an
+C<ev_loop_> prefix, so it was removed; C<ev_loop>, C<ev_unloop> and
+associated constants have been renamed to not collide with the C<struct
+ev_loop> anymore and C<EV_TIMER> now follows the same naming scheme
+as all other watcher types. Note that C<ev_loop_fork> is still called
+C<ev_loop_fork> because it would otherwise clash with the C<ev_fork>
+typedef.
 
-=head1 PORTABILITY REQUIREMENTS
+=item C<EV_MINIMAL> mechanism replaced by C<EV_FEATURES>
 
-In addition to a working ISO-C implementation, libev relies on a few
-additional extensions:
+The preprocessor symbol C<EV_MINIMAL> has been replaced by a different
+mechanism, C<EV_FEATURES>. Programs using C<EV_MINIMAL> usually compile
+and work, but the library code will of course be larger.
+
+=back
+
+
+=head1 GLOSSARY
 
 =over 4
 
-=item C<sig_atomic_t volatile> must be thread-atomic as well
+=item active
 
-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.
+A watcher is active as long as it has been started and not yet stopped.
+See L<WATCHER STATES> for details.
 
-=item C<sigprocmask> must work in a threaded environment
+=item application
 
-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.
+In this document, an application is whatever is using libev.
 
-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 backend
 
-=back
+The part of the code dealing with the operating system interfaces.
 
-If you know of other additional requirements drop me a note.
+=item callback
+
+The address of a function that is called when some event has been
+detected. Callbacks are being passed the event loop, the watcher that
+received the event, and the actual event bitset.
 
+=item callback/watcher invocation
+
+The act of calling the callback associated with a watcher.
+
+=item event
+
+A change of state of some external event, such as data now being available
+for reading on a file descriptor, time having passed or simply not having
+any other events happening anymore.
+
+In libev, events are represented as single bits (such as C<EV_READ> or
+C<EV_TIMER>).
+
+=item event library
+
+A software package implementing an event model and loop.
+
+=item event loop
+
+An entity that handles and processes external events and converts them
+into callback invocations.
+
+=item event model
+
+The model used to describe how an event loop handles and processes
+watchers and events.
+
+=item pending
+
+A watcher is pending as soon as the corresponding event has been
+detected. See L<WATCHER STATES> for details.
+
+=item real time
+
+The physical time that is observed. It is apparently strictly monotonic :)
+
+=item wall-clock time
+
+The time and date as shown on clocks. Unlike real time, it can actually
+be wrong and jump forwards and backwards, e.g. when the you adjust your
+clock.
+
+=item watcher
+
+A data structure that describes interest in certain events. Watchers need
+to be started (attached to an event loop) before they can receive events.
+
+=back
 
 =head1 AUTHOR
 
-Marc Lehmann <libev@schmorp.de>.
+Marc Lehmann <libev@schmorp.de>, with repeated corrections by Mikael
+Magnusson and Emanuele Giaquinta.