--- libev/ev.pod 2007/12/23 03:50:10 1.105 +++ libev/ev.pod 2010/06/24 19:22:26 1.294 @@ -4,55 +4,83 @@ =head1 SYNOPSIS - #include + #include =head2 EXAMPLE PROGRAM - #include + // a single header file is required + #include - ev_io stdin_watcher; - ev_timer timeout_watcher; + #include // for puts - /* called when data readable on stdin */ - static void - stdin_cb (EV_P_ struct ev_io *w, int revents) - { - /* puts ("stdin ready"); */ - ev_io_stop (EV_A_ w); /* just a syntax example */ - ev_unloop (EV_A_ EVUNLOOP_ALL); /* leave all loop calls */ - } - - static void - timeout_cb (EV_P_ struct ev_timer *w, int revents) - { - /* puts ("timeout"); */ - ev_unloop (EV_A_ EVUNLOOP_ONE); /* leave one loop call */ - } - - int - main (void) - { - struct ev_loop *loop = ev_default_loop (0); - - /* initialise an io watcher, then start it */ - ev_io_init (&stdin_watcher, stdin_cb, /*STDIN_FILENO*/ 0, EV_READ); - ev_io_start (loop, &stdin_watcher); - - /* simple non-repeating 5.5 second timeout */ - ev_timer_init (&timeout_watcher, timeout_cb, 5.5, 0.); - ev_timer_start (loop, &timeout_watcher); - - /* loop till timeout or data ready */ - ev_loop (loop, 0); + // every watcher type has its own typedef'd struct + // with the name ev_TYPE + ev_io stdin_watcher; + ev_timer timeout_watcher; - return 0; - } + // all watcher callbacks have a similar signature + // this callback is called when data is readable on stdin + static void + stdin_cb (EV_P_ ev_io *w, int revents) + { + puts ("stdin ready"); + // for one-shot events, one must manually stop the watcher + // with its corresponding stop function. + ev_io_stop (EV_A_ w); + + // this causes all nested ev_loop's to stop iterating + ev_unloop (EV_A_ EVUNLOOP_ALL); + } + + // another callback, this time for a time-out + static void + timeout_cb (EV_P_ ev_timer *w, int revents) + { + puts ("timeout"); + // this causes the innermost ev_loop to stop iterating + ev_unloop (EV_A_ EVUNLOOP_ONE); + } + + int + main (void) + { + // use the default event loop unless you have special needs + struct ev_loop *loop = ev_default_loop (0); -=head1 DESCRIPTION + // initialise an io watcher, then start it + // this one will watch for stdin to become readable + ev_io_init (&stdin_watcher, stdin_cb, /*STDIN_FILENO*/ 0, EV_READ); + ev_io_start (loop, &stdin_watcher); + + // initialise a timer watcher, then start it + // simple non-repeating 5.5 second timeout + ev_timer_init (&timeout_watcher, timeout_cb, 5.5, 0.); + ev_timer_start (loop, &timeout_watcher); -The newest version of this document is also available as a html-formatted + // now wait for events to arrive + ev_loop (loop, 0); + + // unloop was called, so exit + return 0; + } + +=head1 ABOUT THIS DOCUMENT + +This document documents the libev software package. + +The newest version of this document is also available as an html-formatted web page you might find easier to navigate when reading it for the first -time: L. +time: L. + +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. + +Familarity 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 @@ -72,13 +100,14 @@ Libev supports C which have a high overhead for the actual polling but can deliver many events at once. @@ -637,65 +856,171 @@ time collecting I/O events, so you can handle more events per iteration, at the cost of increasing latency. Timeouts (both C and C) will be not affected. Setting this to a non-null value will -introduce an additional C call into most loop iterations. +introduce an additional C 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 you allow libev to spend more time collecting timeouts, at the expense of increased -latency (the watcher callback will be called later). C watchers -will not be affected. Setting this to a non-null value will not introduce -any overhead in libev. +latency/jitter/inexactness (the watcher callback will be called +later). C watchers will not be affected. Setting this to a non-null +value will not introduce any overhead in libev. -Many (busy) programs can usually benefit by setting the io collect +Many (busy) programs can usually benefit by setting the I/O collect interval to a value near C<0.1> or so, which is often enough for interactive servers (of course not for games), likewise for timeouts. It usually doesn't make much sense to set it to a lower value than C<0.01>, -as this approsaches the timing granularity of most systems. +as this approaches the timing granularity of most systems. Note that if +you do transactions with the outside world and you can't increase the +parallelity, then this setting will limit your transaction rate (if you +need to poll once per transaction and the I/O collect interval is 0.01, +then you can't do more than 100 transations per second). + +Setting the I can improve the opportunity for +saving power, as the program will "bundle" timer callback invocations that +are "near" in time together, by delaying some, thus reducing the number of +times the process sleeps and wakes up again. Another useful technique to +reduce iterations/wake-ups is to use C 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 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 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 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 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 and C, another way is to set these I +and I callbacks on the loop. + +When set, then C will be called just before the thread is +suspended waiting for new events, and C is called just +afterwards. + +Ideally, C will just call your mutex_unlock function, and +C will just call the mutex_lock function again. + +While event loop modifications are allowed between invocations of +C and C (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 watcher to wake up C when you want it +to take note of any changes you made. + +In theory, threads executing C will be async-cancel safe between +invocations of C and C. + +See also the locking example in the C section later in this +document. + +=item ev_set_userdata (loop, void *data) + +=item ev_userdata (loop) + +Set and retrieve a single C associated with a loop. When +C has never been called, then C returns +C<0.> + +These two functions can be used to associate arbitrary data with a loop, +and are intended solely for the C, C and +C 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 support has been +compiled in, which is the default for non-minimal builds. It tries to go +through all internal structures and checks them for validity. If anything +is found to be inconsistent, it will print an error message to standard +error and call C. + +This can be used to catch bugs inside libev itself: under normal +circumstances, this function will never abort as of course libev keeps its +data structures consistent. =back =head1 ANATOMY OF A WATCHER +In the following description, uppercase C in names stands for the +watcher type, e.g. C can mean C for timer +watchers and C 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 watcher for that: - static void my_cb (struct ev_loop *loop, struct ev_io *w, int revents) - { - ev_io_stop (w); - ev_unloop (loop, EVUNLOOP_ALL); - } - - struct ev_loop *loop = ev_default_loop (0); - struct ev_io stdin_watcher; - ev_init (&stdin_watcher, my_cb); - ev_io_set (&stdin_watcher, STDIN_FILENO, EV_READ); - ev_io_start (loop, &stdin_watcher); - ev_loop (loop, 0); + 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); + + 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 a bad idea to do this on the +stack). + +Each watcher has an associated watcher structure (called C +or simply C, as typedefs are provided for all watcher structs). Each watcher structure must be initialised by a call to C, which expects a callback to be provided. This -callback gets invoked each time the event occurs (or, in the case of io +callback gets invoked each time the event occurs (or, in the case of I/O watchers, each time the event loop detects that the file descriptor given is readable and/or writable). -Each watcher type has its own C<< ev__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__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__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__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 macro. +reinitialise it or call its C 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 @@ -714,7 +1039,7 @@ The file descriptor in the C watcher has become readable and/or writable. -=item C +=item C The C watcher has timed out. @@ -759,27 +1084,38 @@ The event loop has been resumed in the child process after fork (see C). +=item C + +The given async watcher has been asynchronously notified (see C). + +=item C + +Not ever sent (or otherwise used) by libev itself, but can be freely used +by libev users to signal watchers (e.g. via C). + =item C -An unspecified error has occured, the watcher has been stopped. This might +An unspecified error has occurred, the watcher has been stopped. This might happen because the watcher could not be properly started because libev ran out of memory, a file descriptor was found to be closed or any other -problem. You best act on it by reporting the problem and somehow coping -with the watcher being stopped. +problem. Libev considers these application bugs. -Libev will usually signal a few "dummy" events together with an error, -for example it might indicate that a fd is readable or writable, and if -your callbacks is well-written it can just attempt the operation and cope -with the error from read() or write(). This will not work in multithreaded -programs, though, so beware. +You best act on it by reporting the problem and somehow coping with the +watcher being stopped. Note that well-written programs should not receive +an error ever, so when your watcher receives it, this usually indicates a +bug in your program. + +Libev will usually signal a few "dummy" events together with an error, for +example it might indicate that a fd is readable or writable, and if your +callbacks is well-written it can just attempt the operation and cope with +the error from read() or write(). This will not work in multi-threaded +programs, though, as the fd could already be closed and reused for another +thing, so beware. =back =head2 GENERIC WATCHER FUNCTIONS -In the following description, C stands for the watcher type, -e.g. C for C watchers and C for C watchers. - =over 4 =item C (ev_TYPE *watcher, callback) @@ -794,10 +1130,16 @@ You can reinitialise a watcher at any time as long as it has been stopped (or never started) and there are no pending events outstanding. -The callback is always of type C. -=item C (ev_TYPE *, [args]) +Example: Initialise an C watcher in two steps. + + ev_io w; + ev_init (&w, my_cb); + ev_io_set (&w, STDIN_FILENO, EV_READ); + +=item C (ev_TYPE *watcher, [args]) This macro initialises the type-specific parts of a watcher. You need to call C at least once before you call this macro, but you can @@ -808,25 +1150,38 @@ Although some watcher types do not have type-specific arguments (e.g. C) you still need to call its C macro. +See C, above, for an example. + =item C (ev_TYPE *watcher, callback, [args]) -This convinience macro rolls both C and C macro -calls into a single call. This is the most convinient method to initialise +This convenience macro rolls both C and C macro +calls into a single call. This is the most convenient method to initialise a watcher. The same limitations apply, of course. -=item C (loop *, ev_TYPE *watcher) +Example: Initialise and set an C watcher in one step. + + ev_io_init (&w, my_cb, STDIN_FILENO, EV_READ); + +=item C (loop, ev_TYPE *watcher) Starts (activates) the given watcher. Only active watchers will receive events. If the watcher is already active nothing will happen. -=item C (loop *, ev_TYPE *watcher) +Example: Start the C watcher that is being abused as example in this +whole section. + + ev_io_start (EV_DEFAULT_UC, &w); + +=item C (loop, ev_TYPE *watcher) -Stops the given watcher again (if active) and clears the pending -status. It is possible that stopped watchers are pending (for example, -non-repeating timers are being stopped when they become pending), but -C 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 function. +Stops the given watcher if active, and clears the pending status (whether +the watcher was active or not). + +It is possible that stopped watchers are pending - for example, +non-repeating timers are being stopped when they become pending - but +calling C 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 function. =item bool ev_is_active (ev_TYPE *watcher) @@ -852,7 +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) @@ -862,96 +1217,222 @@ before watchers with lower priority, but priority will not keep watchers from being executed (except for C watchers). -This means that priorities are I 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 watchers, which provide this functionality. You I change the priority of a watcher as long as it is active or pending. +Setting a priority outside the range of C to C 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 to C 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, below, for a more thorough treatment of +priorities. =item ev_invoke (loop, ev_TYPE *watcher, int revents) Invoke the C with the given C and C. Neither C nor C need to be valid as long as the watcher callback -can deal with that fact. +can deal with that fact, as both are simply passed through to the +callback. =item int ev_clear_pending (loop, ev_TYPE *watcher) -If the watcher is pending, this function returns clears its pending status -and returns its C bitset (as if its callback was invoked). If the +If the watcher is pending, this function clears its pending status and +returns its C bitset (as if its callback was invoked). If the watcher isn't pending it does nothing and returns C<0>. +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 will clear the pending event, even if the watcher was +not started in the first place. + +See also C and C for related +functions that do not need a watcher. + =back =head2 ASSOCIATING CUSTOM DATA WITH A WATCHER Each watcher has, by default, a member C that you can change -and read at any time, libev will completely ignore it. This can be used +and read at any time: libev will completely ignore it. This can be used to associate arbitrary data with your watcher. If you need more data and don't want to allocate memory and store a pointer to it in that data member, you can also "subclass" the watcher type and provide your own data: - struct my_io - { - struct ev_io io; - int otherfd; - void *somedata; - struct whatever *mostinteresting; - } + struct my_io + { + ev_io io; + int otherfd; + void *somedata; + struct whatever *mostinteresting; + }; + + ... + struct my_io w; + ev_io_init (&w.io, my_cb, fd, EV_READ); And since your callback will be called with a pointer to the watcher, you can cast it back to your own type: - static void my_cb (struct ev_loop *loop, struct ev_io *w_, int revents) - { - struct my_io *w = (struct my_io *)w_; - ... - } + static void my_cb (struct ev_loop *loop, ev_io *w_, int revents) + { + struct my_io *w = (struct my_io *)w_; + ... + } More interesting and less C-conformant ways of casting your callback type instead have been omitted. -Another common scenario is having some data structure with multiple -watchers: +Another common scenario is to use some data structure with multiple +embedded watchers: - struct my_biggy - { - int some_data; - ev_timer t1; - ev_timer t2; - } - -In this case getting the pointer to C is a bit more complicated, -you need to use C: - - #include - - static void - t1_cb (EV_P_ struct ev_timer *w, int revents) - { - struct my_biggy big = (struct my_biggy * - (((char *)w) - offsetof (struct my_biggy, t1)); - } - - static void - t2_cb (EV_P_ struct ev_timer *w, int revents) - { - struct my_biggy big = (struct my_biggy * - (((char *)w) - offsetof (struct my_biggy, t2)); - } + struct my_biggy + { + int some_data; + ev_timer t1; + ev_timer t2; + } + +In this case getting the pointer to C is a bit more +complicated: Either you store the address of your C struct +in the C member of the watcher (for woozies), or you need to use +some pointer arithmetic using C inside your watchers (for real +programmers): + + #include + + static void + t1_cb (EV_P_ ev_timer *w, int revents) + { + struct my_biggy big = (struct my_biggy *) + (((char *)w) - offsetof (struct my_biggy, t1)); + } + + static void + t2_cb (EV_P_ ev_timer *w, int revents) + { + struct my_biggy big = (struct my_biggy *) + (((char *)w) - offsetof (struct my_biggy, t2)); + } + +=head2 WATCHER PRIORITY MODELS + +Many event loops support I, 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. 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 watcher to receive data, and an associated C 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 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 +continously 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 ahndle 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 @@ -985,36 +1466,36 @@ descriptors to non-blocking mode is also usually a good idea (but not required if you know what you are doing). -You have to be careful with dup'ed file descriptors, though. Some backends -(the linux epoll backend is a notable example) cannot handle dup'ed file -descriptors correctly if you register interest in two or more fds pointing -to the same underlying file/socket/etc. description (that is, they share -the same underlying "file open"). - -If you must do this, then force the use of a known-to-be-good backend -(at the time of this writing, this includes only C and -C). +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 and C). The same applies to file +descriptors for which non-blocking operation makes no sense (such as +files) - libev doesn't guarentee any specific behaviour in that case. Another thing you have to watch out for is that it is quite easy to -receive "spurious" readyness notifications, that is your callback might +receive "spurious" readiness notifications, that is your callback might be called with C but a subsequent C(2) will actually block because there is no data. Not only are some backends known to create a -lot of those (for example solaris ports), it is very easy to get into +lot of those (for example Solaris ports), it is very easy to get into this situation even with a relatively standard program structure. Thus it is best to always use non-blocking I/O: An extra C(2) returning C is far preferable to a program hanging until some data arrives. -If you cannot run the fd in non-blocking mode (for example you should not -play around with an Xlib connection), then you have to seperately re-test -whether a file descriptor is really ready with a known-to-be good interface -such as poll (fortunately in our Xlib example, Xlib already does this on -its own, so its quite safe to use). +If you cannot run the fd in non-blocking mode (for example you should +not play around with an Xlib connection), then you have to separately +re-test whether a file descriptor is really ready with a known-to-be good +interface such as poll (fortunately in our Xlib example, Xlib already +does this on its own, so its quite safe to use). Some people additionally +use C and an interval timer, just to be sure you won't block +indefinitely. + +But really, best use non-blocking mode. =head3 The special problem of disappearing file descriptors Some backends (e.g. kqueue, epoll) need to be told about closing a file -descriptor (either by calling C explicitly or by any other means, -such as C). The reason is that you register interest in some file +descriptor (either due to calling C explicitly or any other means, +such as C). The reason is that you register interest in some file descriptor, but when it goes away, the operating system will silently drop this interest. If another file descriptor with the same number then is registered with libev, there is no efficient way to see that this is, in @@ -1035,8 +1516,8 @@ Some backends (e.g. epoll), cannot register events for file descriptors, but only events for the underlying file descriptions. That means when you -have C'ed file descriptors and register events for them, only one -file descriptor might actually receive events. +have C'ed file descriptors or weirder constellations, and register +events for them, only one file descriptor might actually receive events. There is no workaround possible except not registering events for potentially C'ed file descriptors, or to resort to @@ -1053,6 +1534,55 @@ enable C, or resort to C or C. +=head3 The special problem of SIGPIPE + +While not really specific to libev, it is easy to forget about C: +when writing to a pipe whose other end has been closed, your program gets +sent a SIGPIPE, which, by default, aborts your program. For most programs +this is sensible behaviour, for daemons, this is usually undesirable. + +So when you encounter spurious, unexplained daemon exits, make sure you +ignore SIGPIPE (and maybe make sure you log the exit status of your daemon +somewhere, as that would have given you a big clue). + +=head3 The special problem of accept()ing when you can't + +Many implementations of the POSIX C 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 to fail with C 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 and C, 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 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), and +when you run into C or C, close it, run C, +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, as +is often done with C failures, but this results in an easy +opportunity for a DoS attack. =head3 Watcher-Specific Functions @@ -1063,8 +1593,8 @@ =item ev_io_set (ev_io *, int fd, int events) Configures an C watcher. The C is the file descriptor to -rceeive events for and events is either C, C or -C to receive the given events. +receive events for and C is either C, C or +C, to express the desire to receive the given events. =item int fd [read-only] @@ -1076,23 +1606,25 @@ =back +=head3 Examples + Example: Call C when STDIN_FILENO has become, well readable, but only once. Since it is likely line-buffered, you could attempt to read a whole line in the callback. - static void - stdin_readable_cb (struct ev_loop *loop, struct ev_io *w, int revents) - { - ev_io_stop (loop, w); - .. read from stdin here (or from w->fd) and haqndle any I/O errors - } - - ... - struct ev_loop *loop = ev_default_init (0); - struct ev_io stdin_readable; - ev_io_init (&stdin_readable, stdin_readable_cb, STDIN_FILENO, EV_READ); - ev_io_start (loop, &stdin_readable); - ev_loop (loop, 0); + static void + stdin_readable_cb (struct ev_loop *loop, ev_io *w, int revents) + { + ev_io_stop (loop, w); + .. read from stdin here (or from w->fd) and handle any I/O errors + } + + ... + struct ev_loop *loop = ev_default_init (0); + ev_io stdin_readable; + ev_io_init (&stdin_readable, stdin_readable_cb, STDIN_FILENO, EV_READ); + ev_io_start (loop, &stdin_readable); + ev_loop (loop, 0); =head2 C - relative and optionally repeating timeouts @@ -1101,22 +1633,242 @@ given time, and optionally repeating in regular intervals after that. The timers are based on real time, that is, if you register an event that -times out after an hour and you reset your system clock to last years -time, it will still time out after (roughly) and hour. "Roughly" because +times out after an hour and you reset your system clock to January last +year, it will still time out after (roughly) one hour. "Roughly" because detecting time jumps is hard, and some inaccuracies are unavoidable (the monotonic clock option helps a lot here). +The callback is guaranteed to be invoked only I its timeout has +passed (not I, 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 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 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 inactivity. + +This is the easiest way, and involves using C instead of +C. + +To implement this, configure an C with a C value +of C<60> and then call C 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 +the timer, and C will automatically restart it if need be. + +That means you can ignore both the C function and the +C argument to C, and only ever use the C +member and C. + +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 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 occured, 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, in fact, time out. Otherwise +the callback was invoked too early (C 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 is used, taking advantage of the +C 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 +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, no libev calls at all: + + last_actiivty = 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 of the list. + +Then use an C to fire when the timeout at the I 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 if it was taken from the beginning of the list. + +This way, one can manage an unlimited number of timeouts in O(1) time for +starting, stopping and updating the timers, at the expense of a major +complication, and having to use a constant timeout. The constant timeout +ensures that the list stays sorted. + +=back + +So which method the best? + +Method #2 is a simple no-brain-required solution that is adequate in most +situations. Method #3 requires a bit more thinking, but handles many cases +better, and isn't very complicated either. In most case, choosing either +one is fine, with #3 being better in typical situations. + +Method #1 is almost always a bad idea, and buys you nothing. Method #4 is +rather complicated, but extremely efficient, something that really pays +off after the first million or so of active timers, i.e. it's usually +overkill :) + +=head3 The special problem of time updates + +Establishing the current time is a costly operation (it usually takes at +least two system calls): EV therefore updates its idea of the current +time only before and after C collects new events, which causes a +growing difference between C and C when handling +lots of events in one iteration. + The relative timeouts are calculated relative to the C time. This is usually the right thing as this timestamp refers to the time of the event triggering whatever timeout you are modifying/starting. If -you suspect event processing to be delayed and you I to base the timeout -on the current time, use something like this to adjust for this: +you suspect event processing to be delayed and you I to base the +timeout on the current time, use something like this to adjust for this: ev_timer_set (&timer, after + ev_now () - ev_time (), 0.); -The callback is guarenteed to be invoked only when its timeout has passed, -but if multiple timers become ready during the same loop iteration then -order of execution is undefined. +If the event loop is suspended for a long time, you can also force an +update of the time returned by C by calling C. + +=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, C) 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 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 Cs 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 +and C in code that handles C, to at least get +deterministic behaviour in this case (you can do nothing against +C). =head3 Watcher-Specific Functions and Data Members @@ -1126,91 +1878,84 @@ =item ev_timer_set (ev_timer *, ev_tstamp after, ev_tstamp repeat) -Configure the timer to trigger after C seconds. If C is -C<0.>, then it will automatically be stopped. If it is positive, then the -timer will automatically be configured to trigger again C seconds -later, again, and again, until stopped manually. - -The timer itself will do a best-effort at avoiding drift, that is, if you -configure a timer to trigger every 10 seconds, then it will trigger at -exactly 10 second intervals. If, however, your program cannot keep up with -the timer (because it takes longer than those 10 seconds to do stuff) the -timer will not fire more than once per event loop iteration. +Configure the timer to trigger after C seconds. If C +is C<0.>, then it will automatically be stopped once the timeout is +reached. If it is positive, then the timer will automatically be +configured to trigger again C seconds later, again, and again, +until stopped manually. + +The timer itself will do a best-effort at avoiding drift, that is, if +you configure a timer to trigger every 10 seconds, then it will normally +trigger at exactly 10 second intervals. If, however, your program cannot +keep up with the timer (because it takes longer than those 10 seconds to +do stuff) the timer will not fire more than once per event loop iteration. -=item ev_timer_again (loop) +=item ev_timer_again (loop, ev_timer *) This will act as if the timer timed out and restart it again if it is repeating. The exact semantics are: If the timer is pending, its pending status is cleared. -If the timer is started but nonrepeating, stop it (as if it timed out). +If the timer is started but non-repeating, stop it (as if it timed out). If the timer is repeating, either start it if necessary (with the C value), or reset the running timer to the C 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 with a C value of C<60> and then call -C 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 the timer, and C will -automatically restart it if need be. +This sounds a bit complicated, see L, above, for a +usage example. -That means you can ignore the C value and C -altogether and only ever use the C value and C: +=item ev_tstamp ev_timer_remaining (loop, ev_timer *) - 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); - -This is more slightly efficient then stopping/starting the timer each time -you want to modify its timeout value. +Returns the remaining time until a timer fires. If the timer is active, +then this time is relative to the current event loop time, otherwise it's +the timeout value currently configured. + +That is, after an C, C returns +C<5>. When the timer is started and one second passes, C +will return C<4>. When the timer expires and is restarted, it will return +roughly C<7> (likely slightly less as callback invocation takes some time, +too), and so on. =item ev_tstamp repeat [read-write] The current C value. Will be used each time the watcher times out -or C is called and determines the next timeout (if any), +or C is called, and determines the next timeout (if any), which is also when any modifications are taken into account. =back +=head3 Examples + Example: Create a timer that fires after 60 seconds. - static void - one_minute_cb (struct ev_loop *loop, struct ev_timer *w, int revents) - { - .. one minute over, w is actually stopped right here - } - - struct ev_timer mytimer; - ev_timer_init (&mytimer, one_minute_cb, 60., 0.); - ev_timer_start (loop, &mytimer); + static void + one_minute_cb (struct ev_loop *loop, ev_timer *w, int revents) + { + .. one minute over, w is actually stopped right here + } + + ev_timer mytimer; + ev_timer_init (&mytimer, one_minute_cb, 60., 0.); + ev_timer_start (loop, &mytimer); Example: Create a timeout timer that times out after 10 seconds of inactivity. - static void - timeout_cb (struct ev_loop *loop, struct ev_timer *w, int revents) - { - .. ten seconds without any activity - } - - struct ev_timer mytimer; - ev_timer_init (&mytimer, timeout_cb, 0., 10.); /* note, only repeat used */ - ev_timer_again (&mytimer); /* start timer */ - ev_loop (loop, 0); - - // and in some piece of code that gets executed on any "activity": - // reset the timeout to start ticking again at 10 seconds - ev_timer_again (&mytimer); + static void + timeout_cb (struct ev_loop *loop, ev_timer *w, int revents) + { + .. ten seconds without any activity + } + + ev_timer mytimer; + ev_timer_init (&mytimer, timeout_cb, 0., 10.); /* note, only repeat used */ + ev_timer_again (&mytimer); /* start timer */ + ev_loop (loop, 0); + + // and in some piece of code that gets executed on any "activity": + // reset the timeout to start ticking again at 10 seconds + ev_timer_again (&mytimer); =head2 C - to cron or not to cron? @@ -1218,82 +1963,104 @@ Periodic watchers are also timers of a kind, but they are very versatile (and unfortunately a bit complex). -Unlike C's, they are not based on real time (or relative time) -but on wallclock time (absolute time). You can tell a periodic watcher -to trigger "at" some specific point in time. For example, if you tell a -periodic watcher to trigger in 10 seconds (by specifiying e.g. C) and then reset your system clock to the last year, then it will -take a year to trigger the event (unlike an C, which would trigger -roughly 10 seconds later). - -They can also be used to implement vastly more complex timers, such as -triggering an event on each midnight, local time or other, complicated, -rules. - -As with timers, the callback is guarenteed to be invoked only when the -time (C) has been passed, but if multiple periodic timers become ready -during the same loop iteration then order of execution is undefined. +Unlike C, 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, 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, which would still trigger roughly 10 seconds after starting +it, as it uses a relative timeout). + +C 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 watchers, as +those cannot react to time jumps. + +As with timers, the callback is guaranteed to be invoked only when the +point in time where it is supposed to trigger has passed. If multiple +timers become ready during the same loop iteration then the ones with +earlier time-out values are invoked before ones with later time-out values +(but this is no longer true when a callback calls C recursively). =head3 Watcher-Specific Functions and Data Members =over 4 -=item ev_periodic_init (ev_periodic *, callback, ev_tstamp at, ev_tstamp interval, reschedule_cb) +=item ev_periodic_init (ev_periodic *, callback, ev_tstamp offset, ev_tstamp interval, reschedule_cb) -=item ev_periodic_set (ev_periodic *, ev_tstamp after, ev_tstamp repeat, reschedule_cb) +=item ev_periodic_set (ev_periodic *, ev_tstamp offset, ev_tstamp interval, reschedule_cb) -Lots of arguments, lets sort it out... There are basically three modes of -operation, and we will explain them from simplest to complex: +Lots of arguments, let's sort it out... There are basically three modes of +operation, and we will explain them from simplest to most complex: =over 4 -=item * absolute timer (at = time, interval = reschedule_cb = 0) +=item * absolute timer (offset = absolute time, interval = 0, reschedule_cb = 0) -In this configuration the watcher triggers an event at the wallclock time -C and doesn't repeat. It will not adjust when a time jump occurs, -that is, if it is to be run at January 1st 2011 then it will run when the -system time reaches or surpasses this time. +In this configuration the watcher triggers an event after the wall clock +time C 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 * non-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 time (for some integer N, which can also be negative) -and then repeat, regardless of any time jumps. - -This can be used to create timers that do not drift with respect to system -time: +C time (for some integer N, which can also be +negative) and then repeat, regardless of any time jumps. The C +argument is merely an offset into the C periods. + +This can be used to create timers that do not drift with respect to the +system clock, for example, here is an C that triggers each +hour, on the hour (with respect to UTC): ev_periodic_set (&periodic, 0., 3600., 0); This doesn't mean there will always be 3600 seconds in between triggers, -but only that the the callback will be called when the system time shows a +but only that the callback will be called when the system time shows a full hour (UTC), or more correctly, when the system time is evenly divisible by 3600. Another way to think about it (for the mathematically inclined) is that C will try to run the callback in this mode at the next possible -time where C