--- libev/ev.pod	2008/10/20 16:08:36	1.194
+++ libev/ev.pod	2010/08/28 21:42:12	1.299
@@ -11,15 +11,17 @@
    // a single header file is required
    #include <ev.h>
 
+   #include <stdio.h> // for puts
+
    // every watcher type has its own typedef'd struct
-   // with the name ev_<type>
+   // 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)
+   stdin_cb (EV_P_ ev_io *w, int revents)
    {
      puts ("stdin ready");
      // for one-shot events, one must manually stop the watcher
@@ -32,7 +34,7 @@
 
    // another callback, this time for a time-out
    static void
-   timeout_cb (EV_P_ struct ev_timer *w, int revents)
+   timeout_cb (EV_P_ ev_timer *w, int revents)
    {
      puts ("timeout");
      // this causes the innermost ev_loop to stop iterating
@@ -62,12 +64,24 @@
      return 0;
    }
 
-=head1 DESCRIPTION
+=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://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 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
 these event sources and provide your program with events.
@@ -86,13 +100,14 @@
 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 +125,15 @@
 
 =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 floating point 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 practise
+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
 
@@ -178,7 +194,7 @@
 not a problem.
 
 Example: Make sure we haven't accidentally been linked against the wrong
-version.
+version (note, however, that this will not detect ABI mismatches :).
 
    assert (("libev version mismatch",
             ev_version_major () == EV_VERSION_MAJOR
@@ -278,9 +294,13 @@
 
 =head1 FUNCTIONS CONTROLLING THE EVENT LOOP
 
-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, as there is also an C<ev_loop>
+I<function>).
+
+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.
 
 =over 4
 
@@ -296,7 +316,7 @@
 
 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).
+as loops cannot be shared easily between threads anyway).
 
 The default loop is the only loop that can handle C<ev_signal> and
 C<ev_child> watchers, and to do this, it always registers a handler
@@ -328,9 +348,8 @@
 
 =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
@@ -346,6 +365,26 @@
 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 it's 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 it's 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<EVBACKEND_SELECT>  (value 1, portable select backend)
 
 This is your standard select(2) backend. Not I<completely> standard, as
@@ -379,29 +418,49 @@
 
 =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 system call 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 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.
 
 While stopping, setting and starting an I/O watcher in the same iteration
-will result in some caching, there is still a system call 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. Stopping and
 starting a watcher (without re-setting it) also usually doesn't cause
-extra overhead.
+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 embeddable in other event loops, this feature is broken in
 all kernel versions tested so far.
@@ -411,12 +470,15 @@
 
 =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 "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.
+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). 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.
 
 You still can embed kqueue into a normal poll or select backend and use it
 only for sockets (after having made sure that sockets work with kqueue on
@@ -426,8 +488,9 @@
 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 system call 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.
+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.
 
@@ -435,8 +498,8 @@
 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, did I mention it,
-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
@@ -466,7 +529,7 @@
 On the positive side, with the exception of the spurious readiness
 notifications, this backend actually performed fully to specification
 in all tests and is fully embeddable, which is a rare feat among the
-OS-specific backends.
+OS-specific backends (I vastly prefer correctness over speed hacks).
 
 This backend maps C<EV_READ> and C<EV_WRITE> in the same way as
 C<EVBACKEND_POLL>.
@@ -481,9 +544,10 @@
 
 =back
 
-If one or more of these 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.
+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.
 
 Example: This is the most typical usage.
 
@@ -505,11 +569,9 @@
 =item struct ev_loop *ev_loop_new (unsigned int flags)
 
 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).
+always distinct from the default loop.
 
-Note that this function I<is> thread-safe, and the recommended way to use
+Note that this function I<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.
 
@@ -521,22 +583,21 @@
 
 =item ev_default_destroy ()
 
-Destroys the default loop again (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 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.
+Destroys the default loop (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 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 (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.
 
 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>).
+C<ev_loop_new> and C<ev_loop_destroy>.
 
 =item ev_loop_destroy (loop)
 
@@ -552,9 +613,15 @@
 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.
 
+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.
 
 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
@@ -566,23 +633,37 @@
 
 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 that you want to re-use in the child, and how you do this is
-entirely your own problem.
+after fork that you want to re-use in the child, and how you keep track of 
+them is entirely your own problem.
 
 =item int ev_is_default_loop (loop)
 
 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
+Returns the current iteration count 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.
 
 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_loop> was entered minus the number of
+times C<ev_loop> was exited, in other words, the recursion depth.
+
+Outside C<ev_loop>, this number is zero. In a callback, this number is
+C<1>, unless C<ev_loop> was invoked recursively (or from another thread),
+in which case it is higher.
+
+Leaving C<ev_loop> abnormally (setjmp/longjmp, cancelling the thread
+etc.), doesn't count as "exit" - consider this as a hint to avoid such
+ungentleman behaviour unless it's really convenient.
 
 =item unsigned int ev_backend (loop)
 
@@ -607,13 +688,39 @@
 very long time without entering the event loop, updating libev's idea of
 the current time is a good idea.
 
-See also "The special problem of time updates" in the C<ev_timer> section.
+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 a 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_loop (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.
 
 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.
@@ -633,7 +740,7 @@
 A flags value of C<EVLOOP_ONESHOT> 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 guarentee that a
+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.
 
@@ -687,7 +794,7 @@
 
 This "unloop state" will be cleared when entering C<ev_loop> again.
 
-It is safe to call C<ev_unloop> from otuside any C<ev_loop> calls.
+It is safe to call C<ev_unloop> from outside any C<ev_loop> calls.
 
 =item ev_ref (loop)
 
@@ -697,22 +804,25 @@
 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, call ev_unref() after starting, and 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_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).
+This is useful when you have a watcher that you never intend to
+unregister, but that nevertheless should not keep C<ev_loop> 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_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. 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>
 running when nothing else is active.
 
-   struct ev_signal exitsig;
+   ev_signal exitsig;
    ev_signal_init (&exitsig, sig_cb, SIGINT);
    ev_signal_start (loop, &exitsig);
    evf_unref (loop);
@@ -746,7 +856,9 @@
 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
@@ -758,7 +870,11 @@
 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 approaches 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
@@ -767,10 +883,81 @@
 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_loop> does this automatically when required,
+but when overriding the invoke callback this call comes handy.
+
+=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_loop> 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_loop> 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 loop via
+C<ev_unloop> 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_loop> when you want it
+to take note of any changes you made.
+
+In theory, threads executing C<ev_loop> 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 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_loop_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
+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 ()>.
@@ -784,26 +971,36 @@
 
 =head1 ANATOMY OF A WATCHER
 
+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 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)
+   static void my_cb (struct ev_loop *loop, 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_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);
 
 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 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
@@ -811,19 +1008,19 @@
 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 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
@@ -842,7 +1039,7 @@
 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.
 
@@ -891,13 +1088,22 @@
 
 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 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.
+
+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
@@ -910,9 +1116,6 @@
 
 =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)
@@ -927,7 +1130,7 @@
 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)>.
 
 Example: Initialise an C<ev_io> watcher in two steps.
@@ -936,7 +1139,7 @@
    ev_init (&w, my_cb);
    ev_io_set (&w, STDIN_FILENO, EV_READ);
 
-=item C<ev_TYPE_set> (ev_TYPE *, [args])
+=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
@@ -959,7 +1162,7 @@
 
    ev_io_init (&w, my_cb, STDIN_FILENO, EV_READ);
 
-=item C<ev_TYPE_start> (loop *, ev_TYPE *watcher)
+=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.
@@ -969,14 +1172,16 @@
 
    ev_io_start (EV_DEFAULT_UC, &w);
 
-=item C<ev_TYPE_stop> (loop *, ev_TYPE *watcher)
+=item C<ev_TYPE_stop> (loop, ev_TYPE *watcher)
+
+Stops the given watcher if active, and clears the pending status (whether
+the watcher was active or not).
 
-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.
+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)
 
@@ -1002,7 +1207,7 @@
 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)
 
@@ -1012,23 +1217,21 @@
 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)
 
@@ -1046,6 +1249,20 @@
 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
 
 
@@ -1060,7 +1277,7 @@
 
    struct my_io
    {
-     struct ev_io io;
+     ev_io io;
      int otherfd;
      void *somedata;
      struct whatever *mostinteresting;
@@ -1073,7 +1290,7 @@
 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)
+   static void my_cb (struct ev_loop *loop, ev_io *w_, int revents)
    {
      struct my_io *w = (struct my_io *)w_;
      ...
@@ -1101,19 +1318,122 @@
    #include <stddef.h>
 
    static void
-   t1_cb (EV_P_ struct ev_timer *w, int revents)
+   t1_cb (EV_P_ ev_timer *w, int revents)
    {
-     struct my_biggy big = (struct my_biggy *
+     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)
+   t2_cb (EV_P_ ev_timer *w, int revents)
    {
-     struct my_biggy big = (struct my_biggy *
+     struct my_biggy big = (struct my_biggy *)
        (((char *)w) - offsetof (struct my_biggy, t2));
    }
 
+=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);
+   }
+
+   // 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
 
@@ -1148,7 +1468,9 @@
 
 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>).
+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" readiness notifications, that is your callback might
@@ -1223,6 +1545,44 @@
 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
 
@@ -1253,7 +1613,7 @@
 attempt to read a whole line in the callback.
 
    static void
-   stdin_readable_cb (struct ev_loop *loop, struct ev_io *w, int revents)
+   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
@@ -1261,7 +1621,7 @@
 
    ...
    struct ev_loop *loop = ev_default_init (0);
-   struct ev_io stdin_readable;
+   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);
@@ -1279,8 +1639,186 @@
 monotonic clock option helps a lot here).
 
 The callback is guaranteed to be invoked only I<after> its timeout has
-passed, but if multiple timers become ready during the same loop iteration
-then order of execution is undefined.
+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_loop> 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
 
@@ -1302,6 +1840,36 @@
 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
 
 =over 4
@@ -1334,36 +1902,20 @@
 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.
-
-Note, however, that it is often even more efficient to remember the
-time of the last activity and let the timer time-out naturally. In the
-callback, you then check whether the time-out is real, or, if there was
-some activity, you reschedule the watcher to time-out in "last_activity +
-timeout - ev_now ()" seconds.
+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]
 
@@ -1378,12 +1930,12 @@
 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_cb (struct ev_loop *loop, ev_timer *w, int revents)
    {
      .. one minute over, w is actually stopped right here
    }
 
-   struct ev_timer mytimer;
+   ev_timer mytimer;
    ev_timer_init (&mytimer, one_minute_cb, 60., 0.);
    ev_timer_start (loop, &mytimer);
 
@@ -1391,12 +1943,12 @@
 inactivity.
 
    static void
-   timeout_cb (struct ev_loop *loop, struct ev_timer *w, int revents)
+   timeout_cb (struct ev_loop *loop, ev_timer *w, int revents)
    {
      .. ten seconds without any activity
    }
 
-   struct ev_timer mytimer;
+   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);
@@ -1411,52 +1963,63 @@
 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 wall clock time (absolute time). 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 more than year
-to trigger the event (unlike an C<ev_timer>, which would still trigger
-roughly 10 seconds later as it uses a relative timeout).
-
-C<ev_periodic>s can also be used to implement vastly more complex timers,
-such as triggering an event on each "midnight, local time", or other
-complicated rules.
+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
-time (C<at>) has passed, but if multiple periodic timers become ready
-during the same loop iteration, then order of execution is undefined.
+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_loop> 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
+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 after the wall clock
-time C<at> 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
-only run when the system clock reaches or surpasses this time.
+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.
+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 a C<ev_periodic> that triggers each
-hour, on the hour:
+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);
 
@@ -1467,9 +2030,9 @@
 
 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, and in fact is often specified as zero.
 
@@ -1478,24 +2041,26 @@
 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 whatsoever>.
+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).
 
-The callback prototype is C<ev_tstamp (*reschedule_cb)(struct ev_periodic
+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.;
    }
@@ -1525,13 +2090,16 @@
 
 =item ev_tstamp ev_periodic_at (ev_periodic *)
 
-When active, returns the absolute time that the watcher is supposed to
-trigger next.
+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.
@@ -1542,7 +2110,7 @@
 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
@@ -1557,12 +2125,12 @@
 potentially a lot of jitter, but good long-term stability.
 
    static void
-   clock_cb (struct ev_loop *loop, struct ev_io *w, int revents)
+   clock_cb (struct ev_loop *loop, 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 hourly_tick;
    ev_periodic_init (&hourly_tick, clock_cb, 0., 3600., 0);
    ev_periodic_start (loop, &hourly_tick);
 
@@ -1571,7 +2139,7 @@
    #include <math.h>
 
    static ev_tstamp
-   my_scheduler_cb (struct ev_periodic *w, ev_tstamp now)
+   my_scheduler_cb (ev_periodic *w, ev_tstamp now)
    {
      return now + (3600. - fmod (now, 3600.));
    }
@@ -1580,7 +2148,7 @@
 
 Example: Call a callback every hour, starting now:
 
-   struct ev_periodic 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);
@@ -1593,22 +2161,55 @@
 will try it's best to deliver signals synchronously, i.e. as part of the
 normal event processing, like any other event.
 
-If you want signals 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.
+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.
 
-You can configure as many watchers as you like per signal. Only when the
-first watcher gets started will libev actually register a signal handler
+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). 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).
+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 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.
+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 Watcher-Specific Functions and Data Members
 
@@ -1632,12 +2233,12 @@
 Example: Try to exit cleanly on SIGINT.
 
    static void
-   sigint_cb (struct ev_loop *loop, struct ev_signal *w, int revents)
+   sigint_cb (struct ev_loop *loop, ev_signal *w, int revents)
    {
      ev_unloop (loop, EVUNLOOP_ALL);
    }
 
-   struct ev_signal signal_watcher;
+   ev_signal signal_watcher;
    ev_signal_init (&signal_watcher, sigint_cb, SIGINT);
    ev_signal_start (loop, &signal_watcher);
 
@@ -1650,17 +2251,21 @@
 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 is
-not.
+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 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 occurrence
+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.
@@ -1680,7 +2285,8 @@
 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.
+when a child exit is detected (calling C<ev_child_stop> twice is not a
+problem).
 
 =head3 Watcher-Specific Functions and Data Members
 
@@ -1722,7 +2328,7 @@
    ev_child cw;
 
    static void
-   child_cb (EV_P_ struct ev_child *w, int revents)
+   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);
@@ -1747,35 +2353,38 @@
 =head2 C<ev_stat> - did the file attributes just change?
 
 This watches a file system 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.
+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 kernel interface 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, 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).
+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)
 
@@ -1786,7 +2395,7 @@
 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 noticeably disabled with ev_stat and large file support.
+most noticeably displayed with ev_stat and large file support.
 
 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
@@ -1796,27 +2405,48 @@
 
 =head3 Inotify and Kqueue
 
-When C<inotify (7)> support has been compiled into libev (generally only
-available with 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.
+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,
-but as long as the path exists, libev usually gets away without 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
 implement this functionality, due to the requirement of having a file
 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 ()> 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.
+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
@@ -1969,7 +2599,7 @@
 
 =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,
@@ -1983,16 +2613,16 @@
 callback, free it. Also, use no error checking, as usual.
 
    static void
-   idle_cb (struct ev_loop *loop, struct ev_idle *w, int revents)
+   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.
    }
 
-   struct ev_idle *idle_watcher = malloc (sizeof (struct ev_idle));
+   ev_idle *idle_watcher = malloc (sizeof (ev_idle));
    ev_idle_init (idle_watcher, idle_cb);
-   ev_idle_start (loop, idle_cb);
+   ev_idle_start (loop, idle_watcher);
 
 
 =head2 C<ev_prepare> and C<ev_check> - customise your event loop!
@@ -2081,13 +2711,13 @@
    static ev_timer tw;
 
    static void
-   io_cb (ev_loop *loop, ev_io *w, int revents)
+   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 (ev_loop *loop, ev_prepare *w, int revents)
+   adns_prepare_cb (struct ev_loop *loop, ev_prepare *w, int revents)
    {
      int timeout = 3600000;
      struct pollfd fds [nfd];
@@ -2095,7 +2725,7 @@
      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_init (&tw, 0, timeout * 1e-3, 0.);
      ev_timer_start (loop, &tw);
 
      // create one ev_io per pollfd
@@ -2112,7 +2742,7 @@
 
    // stop all watchers after blocking
    static void
-   adns_check_cb (ev_loop *loop, ev_check *w, int revents)
+   adns_check_cb (struct ev_loop *loop, ev_check *w, int revents)
    {
      ev_timer_stop (loop, &tw);
 
@@ -2218,24 +2848,20 @@
 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 - but you can use a fork watcher to handle this automatically,
-and future versions of libev might do just that.
+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
 C<ev_embeddable_backends> are, which, unfortunately, does not include any
@@ -2290,7 +2916,7 @@
 
    struct ev_loop *loop_hi = ev_default_init (0);
    struct ev_loop *loop_lo = 0;
-   struct ev_embed embed;
+   ev_embed embed;
    
    // see if there is a chance of getting one that works
    // (remember that a flags value of 0 means autodetection)
@@ -2314,7 +2940,7 @@
 
    struct ev_loop *loop = ev_default_init (0);
    struct ev_loop *loop_socket = 0;
-   struct ev_embed embed;
+   ev_embed embed;
    
    if (ev_supported_backends () & ~ev_recommended_backends () & EVBACKEND_KQUEUE)
      if ((loop_socket = ev_loop_new (EVBACKEND_KQUEUE))
@@ -2339,6 +2965,39 @@
 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 ste
+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_default_destroy ()> 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
@@ -2377,7 +3036,8 @@
 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 how to implement locking around your
@@ -2465,7 +3125,7 @@
 =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,
+kind. There is a C<ev_async_set> macro, but using it is utterly pointless,
 trust me.
 
 =item ev_async_send (loop, ev_async *)
@@ -2476,9 +3136,14 @@
 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 system call only once per loop iteration,
-so while the overhead might be noticeable, 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 *)
 
@@ -2491,8 +3156,10 @@
 it will reset the flag again. C<ev_async_pending> can be used to very
 quickly check whether invoking the loop might be a good idea.
 
-Not that this does I<not> check whether the watcher itself is pending, only
-whether 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
 
@@ -2519,9 +3186,9 @@
 started. Otherwise an C<ev_timer> watcher with after = C<timeout> (and
 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>
+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.
@@ -2532,24 +3199,18 @@
    {
      if (revents & EV_READ)
        /* stdin might have data for us, joy! */;
-     else if (revents & EV_TIMEOUT)
+     else if (revents & EV_TIMER)
        /* doh, nothing entered */;
    }
 
    ev_once (STDIN_FILENO, EV_READ, 10., stdin_ready, 0);
 
-=item ev_feed_event (ev_loop *, 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).
-
-=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 (C<loop> must be the default
 loop!).
@@ -2639,7 +3300,7 @@
 
 =item ev::TYPE::TYPE ()
 
-=item ev::TYPE::TYPE (struct ev_loop *)
+=item ev::TYPE::TYPE (loop)
 
 =item ev::TYPE::~TYPE
 
@@ -2681,6 +3342,34 @@
    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)
 
 Also sets a callback, but uses a static method or plain function as
@@ -2696,7 +3385,7 @@
    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).
@@ -2776,11 +3465,7 @@
 =item Python
 
 Python bindings can be found at L<http://code.google.com/p/pyev/>. It
-seems to be quite complete and well-documented. Note, however, that the
-patch they require for libev is outright dangerous as it breaks the ABI
-for everybody else, and therefore, should never be applied in an installed
-libev (if python requires an incompatible ABI then it needs to embed
-libev).
+seems to be quite complete and well-documented.
 
 =item Ruby
 
@@ -2789,11 +3474,30 @@
 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://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
 
 
@@ -2903,7 +3607,7 @@
    #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
@@ -2956,12 +3660,19 @@
 =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 absence of
-autoconf is documented 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_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
@@ -2969,24 +3680,40 @@
 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 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
+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
-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.
+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
 
@@ -3012,11 +3739,11 @@
 
 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 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, 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
 
@@ -3028,7 +3755,7 @@
 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
@@ -3036,6 +3763,20 @@
 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)
@@ -3091,24 +3832,24 @@
 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
@@ -3140,60 +3881,130 @@
 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. Embed watchers rely on most other
-watcher types, which therefore must not be disabled.
+=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 this is used to override some
-inlining decisions, saves roughly 30% code size on amd64. It also selects a
-much smaller 2-heap for timer management over the default 4-heap.
+=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
 
@@ -3202,8 +4013,8 @@
 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_MINIMAL> is set in which case it is C<0>
-(disabled).
+The default is C<1>, unless C<EV_FEATURES> overrides it, in which case it
+will be C<0>.
 
 =item EV_HEAP_CACHE_AT
 
@@ -3214,8 +4025,8 @@
 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_MINIMAL> is set in which case it is C<0>
-(disabled).
+The default is C<1>, unless C<EV_FEATURES> overrides it, in which case it
+will be C<0>.
 
 =item EV_VERIFY
 
@@ -3227,8 +4038,8 @@
 verification code will be called very frequently, which will slow down
 libev considerably.
 
-The default is C<1>, unless C<EV_MINIMAL> is set, in which case it will be
-C<0>.
+The default is C<1>, unless C<EV_FEATURES> overrides it, in which case it
+will be C<0>.
 
 =item EV_COMMON
 
@@ -3296,15 +4107,14 @@
 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_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>
-   #define EV_MINPRI 0
-   #define EV_MAXPRI 0
 
    #include "ev++.h"
 
@@ -3374,18 +4184,156 @@
 
 =back
 
+=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_loop>:
+
+   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_loop (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:
+
+   ev_timer timeout_watcher;
+   userdata *u = ev_userdata (EV_A);
+
+   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);
+
+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_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.
+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_loop>, and other calls do not usually allow for coroutine switches as
-they do not clal any callbacks.
+they do not call any callbacks.
 
 =head2 COMPILER WARNINGS
 
@@ -3429,7 +4377,7 @@
    ==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 refernced, and didn't leak.
+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,
@@ -3468,6 +4416,9 @@
 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,
@@ -3481,7 +4432,7 @@
 more than a hundred or so sockets, then likely it needs to use a totally
 different implementation for windows, as libev offers the POSIX readiness
 notification model, which cannot be implemented efficiently on windows
-(Microsoft monopoly games).
+(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
@@ -3527,24 +4478,22 @@
 of C<64> handles (probably owning to the fact that all windows kernels
 can only wait for C<64> things at the same time internally; Microsoft
 recommends spawning a chain of threads and wait for 63 handles and the
-previous thread in each. Great).
+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 does its own
-select emulation on windows).
+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.
+libraries, which by default is C<64> (there must be a hidden I<64>
+fetish or something like this inside Microsoft). You can increase this
+by calling C<_setmaxstdio>, which can increase this limit to C<2048>
+(another arbitrary limit), but is broken in many versions of the Microsoft
+runtime libraries. This might get you to about C<512> or C<2048> sockets
+(depending on windows version and/or the phase of the moon). To get more,
+you need to wrap all I/O functions and provide your own fd management, but
+the cost of calling select (O(n²)) will likely make this unworkable.
 
 =back
 
@@ -3597,7 +4546,9 @@
 The type C<double> is used to represent timestamps. It is required to
 have at least 51 bits of mantissa (and 9 bits of exponent), which is good
 enough for at least into the year 4000. This requirement is fulfilled by
-implementations implementing IEEE 754 (basically all existing ones).
+implementations implementing IEEE 754, which is basically all existing
+ones. With IEEE 754 doubles, you get microsecond accuracy until at least
+2200.
 
 =back
 
@@ -3675,7 +4626,122 @@
 =back
 
 
+=head1 PORTING FROM LIBEV 3.X TO 4.X
+
+The major version 4 introduced some minor incompatible changes to the API.
+
+At the moment, the C<ev.h> header file tries to implement superficial
+compatibility, so most programs should still compile. Those might be
+removed in later versions of libev, so better update early than late.
+
+=over 4
+
+=item C<ev_loop_count> renamed to C<ev_iteration>
+
+=item C<ev_loop_depth> renamed to C<ev_depth>
+
+=item C<ev_loop_verify> renamed to C<ev_verify>
+
+Most functions working on C<struct ev_loop> objects don't have an
+C<ev_loop_> prefix, so it was removed. Note that C<ev_loop_fork> is
+still called C<ev_loop_fork> because it would otherwise clash with the
+C<ev_fork> typedef.
+
+=item C<EV_TIMEOUT> renamed to C<EV_TIMER> in C<revents>
+
+This is a simple rename - all other watcher types use their name
+as revents flag, and now C<ev_timer> does, too.
+
+Both C<EV_TIMER> and C<EV_TIMEOUT> symbols were present in 3.x versions
+and continue to be present for the foreseeable future, so this is mostly a
+documentation change.
+
+=item C<EV_MINIMAL> mechanism replaced by C<EV_FEATURES>
+
+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 active
+
+A watcher is active as long as it has been started (has been attached to
+an event loop) but not yet stopped (disassociated from the event loop).
+
+=item application
+
+In this document, an application is whatever is using libev.
+
+=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 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,
+and stops being pending as soon as the watcher will be invoked or its
+pending status is explicitly cleared by the application.
+
+A watcher can be pending, but not active. Stopping a watcher also clears
+its pending status.
+
+=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.
+
+=item watcher invocation
+
+The act of calling the callback associated with a watcher.
+
+=back
+
 =head1 AUTHOR
 
-Marc Lehmann <libev@schmorp.de>.
+Marc Lehmann <libev@schmorp.de>, with repeated corrections by Mikael Magnusson.