… | |
… | |
178 | you actually want to know. Also interesting is the combination of |
178 | you actually want to know. Also interesting is the combination of |
179 | C<ev_update_now> and C<ev_now>. |
179 | C<ev_update_now> and C<ev_now>. |
180 | |
180 | |
181 | =item ev_sleep (ev_tstamp interval) |
181 | =item ev_sleep (ev_tstamp interval) |
182 | |
182 | |
183 | Sleep for the given interval: The current thread will be blocked until |
183 | Sleep for the given interval: The current thread will be blocked |
184 | either it is interrupted or the given time interval has passed. Basically |
184 | until either it is interrupted or the given time interval has |
|
|
185 | passed (approximately - it might return a bit earlier even if not |
|
|
186 | interrupted). Returns immediately if C<< interval <= 0 >>. |
|
|
187 | |
185 | this is a sub-second-resolution C<sleep ()>. |
188 | Basically this is a sub-second-resolution C<sleep ()>. |
|
|
189 | |
|
|
190 | The range of the C<interval> is limited - libev only guarantees to work |
|
|
191 | with sleep times of up to one day (C<< interval <= 86400 >>). |
186 | |
192 | |
187 | =item int ev_version_major () |
193 | =item int ev_version_major () |
188 | |
194 | |
189 | =item int ev_version_minor () |
195 | =item int ev_version_minor () |
190 | |
196 | |
… | |
… | |
435 | example) that can't properly initialise their signal masks. |
441 | example) that can't properly initialise their signal masks. |
436 | |
442 | |
437 | =item C<EVFLAG_NOSIGMASK> |
443 | =item C<EVFLAG_NOSIGMASK> |
438 | |
444 | |
439 | When this flag is specified, then libev will avoid to modify the signal |
445 | When this flag is specified, then libev will avoid to modify the signal |
440 | mask. Specifically, this means you ahve to make sure signals are unblocked |
446 | mask. Specifically, this means you have to make sure signals are unblocked |
441 | when you want to receive them. |
447 | when you want to receive them. |
442 | |
448 | |
443 | This behaviour is useful when you want to do your own signal handling, or |
449 | This behaviour is useful when you want to do your own signal handling, or |
444 | want to handle signals only in specific threads and want to avoid libev |
450 | want to handle signals only in specific threads and want to avoid libev |
445 | unblocking the signals. |
451 | unblocking the signals. |
… | |
… | |
483 | =item C<EVBACKEND_EPOLL> (value 4, Linux) |
489 | =item C<EVBACKEND_EPOLL> (value 4, Linux) |
484 | |
490 | |
485 | Use the linux-specific epoll(7) interface (for both pre- and post-2.6.9 |
491 | Use the linux-specific epoll(7) interface (for both pre- and post-2.6.9 |
486 | kernels). |
492 | kernels). |
487 | |
493 | |
488 | For few fds, this backend is a bit little slower than poll and select, |
494 | For few fds, this backend is a bit little slower than poll and select, but |
489 | but it scales phenomenally better. While poll and select usually scale |
495 | it scales phenomenally better. While poll and select usually scale like |
490 | like O(total_fds) where n is the total number of fds (or the highest fd), |
496 | O(total_fds) where total_fds is the total number of fds (or the highest |
491 | epoll scales either O(1) or O(active_fds). |
497 | fd), epoll scales either O(1) or O(active_fds). |
492 | |
498 | |
493 | The epoll mechanism deserves honorable mention as the most misdesigned |
499 | The epoll mechanism deserves honorable mention as the most misdesigned |
494 | of the more advanced event mechanisms: mere annoyances include silently |
500 | of the more advanced event mechanisms: mere annoyances include silently |
495 | dropping file descriptors, requiring a system call per change per file |
501 | dropping file descriptors, requiring a system call per change per file |
496 | descriptor (and unnecessary guessing of parameters), problems with dup, |
502 | descriptor (and unnecessary guessing of parameters), problems with dup, |
… | |
… | |
499 | 0.1ms) and so on. The biggest issue is fork races, however - if a program |
505 | 0.1ms) and so on. The biggest issue is fork races, however - if a program |
500 | forks then I<both> parent and child process have to recreate the epoll |
506 | forks then I<both> parent and child process have to recreate the epoll |
501 | set, which can take considerable time (one syscall per file descriptor) |
507 | set, which can take considerable time (one syscall per file descriptor) |
502 | and is of course hard to detect. |
508 | and is of course hard to detect. |
503 | |
509 | |
504 | Epoll is also notoriously buggy - embedding epoll fds I<should> work, but |
510 | Epoll is also notoriously buggy - embedding epoll fds I<should> work, |
505 | of course I<doesn't>, and epoll just loves to report events for totally |
511 | but of course I<doesn't>, and epoll just loves to report events for |
506 | I<different> file descriptors (even already closed ones, so one cannot |
512 | totally I<different> file descriptors (even already closed ones, so |
507 | even remove them from the set) than registered in the set (especially |
513 | one cannot even remove them from the set) than registered in the set |
508 | on SMP systems). Libev tries to counter these spurious notifications by |
514 | (especially on SMP systems). Libev tries to counter these spurious |
509 | employing an additional generation counter and comparing that against the |
515 | notifications by employing an additional generation counter and comparing |
510 | events to filter out spurious ones, recreating the set when required. Last |
516 | that against the events to filter out spurious ones, recreating the set |
|
|
517 | when required. Epoll also erroneously rounds down timeouts, but gives you |
|
|
518 | no way to know when and by how much, so sometimes you have to busy-wait |
|
|
519 | because epoll returns immediately despite a nonzero timeout. And last |
511 | not least, it also refuses to work with some file descriptors which work |
520 | not least, it also refuses to work with some file descriptors which work |
512 | perfectly fine with C<select> (files, many character devices...). |
521 | perfectly fine with C<select> (files, many character devices...). |
513 | |
522 | |
514 | Epoll is truly the train wreck analog among event poll mechanisms, |
523 | Epoll is truly the train wreck among event poll mechanisms, a frankenpoll, |
515 | a frankenpoll, cobbled together in a hurry, no thought to design or |
524 | cobbled together in a hurry, no thought to design or interaction with |
516 | interaction with others. |
525 | others. Oh, the pain, will it ever stop... |
517 | |
526 | |
518 | While stopping, setting and starting an I/O watcher in the same iteration |
527 | While stopping, setting and starting an I/O watcher in the same iteration |
519 | will result in some caching, there is still a system call per such |
528 | will result in some caching, there is still a system call per such |
520 | incident (because the same I<file descriptor> could point to a different |
529 | incident (because the same I<file descriptor> could point to a different |
521 | I<file description> now), so its best to avoid that. Also, C<dup ()>'ed |
530 | I<file description> now), so its best to avoid that. Also, C<dup ()>'ed |
… | |
… | |
599 | among the OS-specific backends (I vastly prefer correctness over speed |
608 | among the OS-specific backends (I vastly prefer correctness over speed |
600 | hacks). |
609 | hacks). |
601 | |
610 | |
602 | On the negative side, the interface is I<bizarre> - so bizarre that |
611 | On the negative side, the interface is I<bizarre> - so bizarre that |
603 | even sun itself gets it wrong in their code examples: The event polling |
612 | even sun itself gets it wrong in their code examples: The event polling |
604 | function sometimes returning events to the caller even though an error |
613 | function sometimes returns events to the caller even though an error |
605 | occurred, but with no indication whether it has done so or not (yes, it's |
614 | occurred, but with no indication whether it has done so or not (yes, it's |
606 | even documented that way) - deadly for edge-triggered interfaces where |
615 | even documented that way) - deadly for edge-triggered interfaces where you |
607 | you absolutely have to know whether an event occurred or not because you |
616 | absolutely have to know whether an event occurred or not because you have |
608 | have to re-arm the watcher. |
617 | to re-arm the watcher. |
609 | |
618 | |
610 | Fortunately libev seems to be able to work around these idiocies. |
619 | Fortunately libev seems to be able to work around these idiocies. |
611 | |
620 | |
612 | This backend maps C<EV_READ> and C<EV_WRITE> in the same way as |
621 | This backend maps C<EV_READ> and C<EV_WRITE> in the same way as |
613 | C<EVBACKEND_POLL>. |
622 | C<EVBACKEND_POLL>. |
… | |
… | |
825 | This is useful if you are waiting for some external event in conjunction |
834 | This is useful if you are waiting for some external event in conjunction |
826 | with something not expressible using other libev watchers (i.e. "roll your |
835 | with something not expressible using other libev watchers (i.e. "roll your |
827 | own C<ev_run>"). However, a pair of C<ev_prepare>/C<ev_check> watchers is |
836 | own C<ev_run>"). However, a pair of C<ev_prepare>/C<ev_check> watchers is |
828 | usually a better approach for this kind of thing. |
837 | usually a better approach for this kind of thing. |
829 | |
838 | |
830 | Here are the gory details of what C<ev_run> does: |
839 | Here are the gory details of what C<ev_run> does (this is for your |
|
|
840 | understanding, not a guarantee that things will work exactly like this in |
|
|
841 | future versions): |
831 | |
842 | |
832 | - Increment loop depth. |
843 | - Increment loop depth. |
833 | - Reset the ev_break status. |
844 | - Reset the ev_break status. |
834 | - Before the first iteration, call any pending watchers. |
845 | - Before the first iteration, call any pending watchers. |
835 | LOOP: |
846 | LOOP: |
… | |
… | |
941 | overhead for the actual polling but can deliver many events at once. |
952 | overhead for the actual polling but can deliver many events at once. |
942 | |
953 | |
943 | By setting a higher I<io collect interval> you allow libev to spend more |
954 | By setting a higher I<io collect interval> you allow libev to spend more |
944 | time collecting I/O events, so you can handle more events per iteration, |
955 | time collecting I/O events, so you can handle more events per iteration, |
945 | at the cost of increasing latency. Timeouts (both C<ev_periodic> and |
956 | at the cost of increasing latency. Timeouts (both C<ev_periodic> and |
946 | C<ev_timer>) will be not affected. Setting this to a non-null value will |
957 | C<ev_timer>) will not be affected. Setting this to a non-null value will |
947 | introduce an additional C<ev_sleep ()> call into most loop iterations. The |
958 | introduce an additional C<ev_sleep ()> call into most loop iterations. The |
948 | sleep time ensures that libev will not poll for I/O events more often then |
959 | sleep time ensures that libev will not poll for I/O events more often then |
949 | once per this interval, on average. |
960 | once per this interval, on average (as long as the host time resolution is |
|
|
961 | good enough). |
950 | |
962 | |
951 | Likewise, by setting a higher I<timeout collect interval> you allow libev |
963 | Likewise, by setting a higher I<timeout collect interval> you allow libev |
952 | to spend more time collecting timeouts, at the expense of increased |
964 | to spend more time collecting timeouts, at the expense of increased |
953 | latency/jitter/inexactness (the watcher callback will be called |
965 | latency/jitter/inexactness (the watcher callback will be called |
954 | later). C<ev_io> watchers will not be affected. Setting this to a non-null |
966 | later). C<ev_io> watchers will not be affected. Setting this to a non-null |
… | |
… | |
1374 | |
1386 | |
1375 | =over 4 |
1387 | =over 4 |
1376 | |
1388 | |
1377 | =item initialiased |
1389 | =item initialiased |
1378 | |
1390 | |
1379 | Before a watcher can be registered with the event looop it has to be |
1391 | Before a watcher can be registered with the event loop it has to be |
1380 | initialised. This can be done with a call to C<ev_TYPE_init>, or calls to |
1392 | initialised. This can be done with a call to C<ev_TYPE_init>, or calls to |
1381 | C<ev_init> followed by the watcher-specific C<ev_TYPE_set> function. |
1393 | C<ev_init> followed by the watcher-specific C<ev_TYPE_set> function. |
1382 | |
1394 | |
1383 | In this state it is simply some block of memory that is suitable for |
1395 | In this state it is simply some block of memory that is suitable for |
1384 | use in an event loop. It can be moved around, freed, reused etc. at |
1396 | use in an event loop. It can be moved around, freed, reused etc. at |
… | |
… | |
2011 | keep up with the timer (because it takes longer than those 10 seconds to |
2023 | keep up with the timer (because it takes longer than those 10 seconds to |
2012 | do stuff) the timer will not fire more than once per event loop iteration. |
2024 | do stuff) the timer will not fire more than once per event loop iteration. |
2013 | |
2025 | |
2014 | =item ev_timer_again (loop, ev_timer *) |
2026 | =item ev_timer_again (loop, ev_timer *) |
2015 | |
2027 | |
2016 | This will act as if the timer timed out and restart it again if it is |
2028 | This will act as if the timer timed out and restarts it again if it is |
2017 | repeating. The exact semantics are: |
2029 | repeating. The exact semantics are: |
2018 | |
2030 | |
2019 | If the timer is pending, its pending status is cleared. |
2031 | If the timer is pending, its pending status is cleared. |
2020 | |
2032 | |
2021 | If the timer is started but non-repeating, stop it (as if it timed out). |
2033 | If the timer is started but non-repeating, stop it (as if it timed out). |
… | |
… | |
2151 | |
2163 | |
2152 | Another way to think about it (for the mathematically inclined) is that |
2164 | Another way to think about it (for the mathematically inclined) is that |
2153 | C<ev_periodic> will try to run the callback in this mode at the next possible |
2165 | C<ev_periodic> will try to run the callback in this mode at the next possible |
2154 | time where C<time = offset (mod interval)>, regardless of any time jumps. |
2166 | time where C<time = offset (mod interval)>, regardless of any time jumps. |
2155 | |
2167 | |
2156 | For numerical stability it is preferable that the C<offset> value is near |
2168 | The C<interval> I<MUST> be positive, and for numerical stability, the |
2157 | C<ev_now ()> (the current time), but there is no range requirement for |
2169 | interval value should be higher than C<1/8192> (which is around 100 |
2158 | this value, and in fact is often specified as zero. |
2170 | microseconds) and C<offset> should be higher than C<0> and should have |
|
|
2171 | at most a similar magnitude as the current time (say, within a factor of |
|
|
2172 | ten). Typical values for offset are, in fact, C<0> or something between |
|
|
2173 | C<0> and C<interval>, which is also the recommended range. |
2159 | |
2174 | |
2160 | Note also that there is an upper limit to how often a timer can fire (CPU |
2175 | Note also that there is an upper limit to how often a timer can fire (CPU |
2161 | speed for example), so if C<interval> is very small then timing stability |
2176 | speed for example), so if C<interval> is very small then timing stability |
2162 | will of course deteriorate. Libev itself tries to be exact to be about one |
2177 | will of course deteriorate. Libev itself tries to be exact to be about one |
2163 | millisecond (if the OS supports it and the machine is fast enough). |
2178 | millisecond (if the OS supports it and the machine is fast enough). |
… | |
… | |
3205 | C<ev_async_sent> calls). In fact, you could use signal watchers as a kind |
3220 | C<ev_async_sent> calls). In fact, you could use signal watchers as a kind |
3206 | of "global async watchers" by using a watcher on an otherwise unused |
3221 | of "global async watchers" by using a watcher on an otherwise unused |
3207 | signal, and C<ev_feed_signal> to signal this watcher from another thread, |
3222 | signal, and C<ev_feed_signal> to signal this watcher from another thread, |
3208 | even without knowing which loop owns the signal. |
3223 | even without knowing which loop owns the signal. |
3209 | |
3224 | |
3210 | Unlike C<ev_signal> watchers, C<ev_async> works with any event loop, not |
|
|
3211 | just the default loop. |
|
|
3212 | |
|
|
3213 | =head3 Queueing |
3225 | =head3 Queueing |
3214 | |
3226 | |
3215 | C<ev_async> does not support queueing of data in any way. The reason |
3227 | C<ev_async> does not support queueing of data in any way. The reason |
3216 | is that the author does not know of a simple (or any) algorithm for a |
3228 | is that the author does not know of a simple (or any) algorithm for a |
3217 | multiple-writer-single-reader queue that works in all cases and doesn't |
3229 | multiple-writer-single-reader queue that works in all cases and doesn't |
… | |
… | |
3316 | Unlike C<ev_feed_event>, this call is safe to do from other threads, |
3328 | Unlike C<ev_feed_event>, this call is safe to do from other threads, |
3317 | signal or similar contexts (see the discussion of C<EV_ATOMIC_T> in the |
3329 | signal or similar contexts (see the discussion of C<EV_ATOMIC_T> in the |
3318 | embedding section below on what exactly this means). |
3330 | embedding section below on what exactly this means). |
3319 | |
3331 | |
3320 | Note that, as with other watchers in libev, multiple events might get |
3332 | Note that, as with other watchers in libev, multiple events might get |
3321 | compressed into a single callback invocation (another way to look at this |
3333 | compressed into a single callback invocation (another way to look at |
3322 | is that C<ev_async> watchers are level-triggered, set on C<ev_async_send>, |
3334 | this is that C<ev_async> watchers are level-triggered: they are set on |
3323 | reset when the event loop detects that). |
3335 | C<ev_async_send>, reset when the event loop detects that). |
3324 | |
3336 | |
3325 | This call incurs the overhead of a system call only once per event loop |
3337 | This call incurs the overhead of at most one extra system call per event |
3326 | iteration, so while the overhead might be noticeable, it doesn't apply to |
3338 | loop iteration, if the event loop is blocked, and no syscall at all if |
3327 | repeated calls to C<ev_async_send> for the same event loop. |
3339 | the event loop (or your program) is processing events. That means that |
|
|
3340 | repeated calls are basically free (there is no need to avoid calls for |
|
|
3341 | performance reasons) and that the overhead becomes smaller (typically |
|
|
3342 | zero) under load. |
3328 | |
3343 | |
3329 | =item bool = ev_async_pending (ev_async *) |
3344 | =item bool = ev_async_pending (ev_async *) |
3330 | |
3345 | |
3331 | Returns a non-zero value when C<ev_async_send> has been called on the |
3346 | Returns a non-zero value when C<ev_async_send> has been called on the |
3332 | watcher but the event has not yet been processed (or even noted) by the |
3347 | watcher but the event has not yet been processed (or even noted) by the |
… | |
… | |
4204 | F<event.h> that are not directly supported by the libev core alone. |
4219 | F<event.h> that are not directly supported by the libev core alone. |
4205 | |
4220 | |
4206 | In standalone mode, libev will still try to automatically deduce the |
4221 | In standalone mode, libev will still try to automatically deduce the |
4207 | configuration, but has to be more conservative. |
4222 | configuration, but has to be more conservative. |
4208 | |
4223 | |
|
|
4224 | =item EV_USE_FLOOR |
|
|
4225 | |
|
|
4226 | If defined to be C<1>, libev will use the C<floor ()> function for its |
|
|
4227 | periodic reschedule calculations, otherwise libev will fall back on a |
|
|
4228 | portable (slower) implementation. If you enable this, you usually have to |
|
|
4229 | link against libm or something equivalent. Enabling this when the C<floor> |
|
|
4230 | function is not available will fail, so the safe default is to not enable |
|
|
4231 | this. |
|
|
4232 | |
4209 | =item EV_USE_MONOTONIC |
4233 | =item EV_USE_MONOTONIC |
4210 | |
4234 | |
4211 | If defined to be C<1>, libev will try to detect the availability of the |
4235 | If defined to be C<1>, libev will try to detect the availability of the |
4212 | monotonic clock option at both compile time and runtime. Otherwise no |
4236 | monotonic clock option at both compile time and runtime. Otherwise no |
4213 | use of the monotonic clock option will be attempted. If you enable this, |
4237 | use of the monotonic clock option will be attempted. If you enable this, |
… | |
… | |
4345 | indicate GNU/Linux + Glibc 2.4 or newer, otherwise disabled. |
4369 | indicate GNU/Linux + Glibc 2.4 or newer, otherwise disabled. |
4346 | |
4370 | |
4347 | =item EV_ATOMIC_T |
4371 | =item EV_ATOMIC_T |
4348 | |
4372 | |
4349 | Libev requires an integer type (suitable for storing C<0> or C<1>) whose |
4373 | Libev requires an integer type (suitable for storing C<0> or C<1>) whose |
4350 | access is atomic with respect to other threads or signal contexts. No such |
4374 | access is atomic and serialised with respect to other threads or signal |
4351 | type is easily found in the C language, so you can provide your own type |
4375 | contexts. No such type is easily found in the C language, so you can |
4352 | that you know is safe for your purposes. It is used both for signal handler "locking" |
4376 | provide your own type that you know is safe for your purposes. It is used |
4353 | as well as for signal and thread safety in C<ev_async> watchers. |
4377 | both for signal handler "locking" as well as for signal and thread safety |
|
|
4378 | in C<ev_async> watchers. |
4354 | |
4379 | |
4355 | In the absence of this define, libev will use C<sig_atomic_t volatile> |
4380 | In the absence of this define, libev will use C<sig_atomic_t volatile> |
4356 | (from F<signal.h>), which is usually good enough on most platforms. |
4381 | (from F<signal.h>), which is usually good enough on most platforms. |
4357 | |
4382 | |
4358 | =item EV_H (h) |
4383 | =item EV_H (h) |
… | |
… | |
4880 | requires, and its I/O model is fundamentally incompatible with the POSIX |
4905 | requires, and its I/O model is fundamentally incompatible with the POSIX |
4881 | model. Libev still offers limited functionality on this platform in |
4906 | model. Libev still offers limited functionality on this platform in |
4882 | the form of the C<EVBACKEND_SELECT> backend, and only supports socket |
4907 | the form of the C<EVBACKEND_SELECT> backend, and only supports socket |
4883 | descriptors. This only applies when using Win32 natively, not when using |
4908 | descriptors. This only applies when using Win32 natively, not when using |
4884 | e.g. cygwin. Actually, it only applies to the microsofts own compilers, |
4909 | e.g. cygwin. Actually, it only applies to the microsofts own compilers, |
4885 | as every compielr comes with a slightly differently broken/incompatible |
4910 | as every compiler comes with a slightly differently broken/incompatible |
4886 | environment. |
4911 | environment. |
4887 | |
4912 | |
4888 | Lifting these limitations would basically require the full |
4913 | Lifting these limitations would basically require the full |
4889 | re-implementation of the I/O system. If you are into this kind of thing, |
4914 | re-implementation of the I/O system. If you are into this kind of thing, |
4890 | then note that glib does exactly that for you in a very portable way (note |
4915 | then note that glib does exactly that for you in a very portable way (note |
… | |
… | |
5023 | |
5048 | |
5024 | The type C<double> is used to represent timestamps. It is required to |
5049 | The type C<double> is used to represent timestamps. It is required to |
5025 | have at least 51 bits of mantissa (and 9 bits of exponent), which is |
5050 | have at least 51 bits of mantissa (and 9 bits of exponent), which is |
5026 | good enough for at least into the year 4000 with millisecond accuracy |
5051 | good enough for at least into the year 4000 with millisecond accuracy |
5027 | (the design goal for libev). This requirement is overfulfilled by |
5052 | (the design goal for libev). This requirement is overfulfilled by |
5028 | implementations using IEEE 754, which is basically all existing ones. With |
5053 | implementations using IEEE 754, which is basically all existing ones. |
|
|
5054 | |
5029 | IEEE 754 doubles, you get microsecond accuracy until at least 2200. |
5055 | With IEEE 754 doubles, you get microsecond accuracy until at least the |
|
|
5056 | year 2255 (and millisecond accuray till the year 287396 - by then, libev |
|
|
5057 | is either obsolete or somebody patched it to use C<long double> or |
|
|
5058 | something like that, just kidding). |
5030 | |
5059 | |
5031 | =back |
5060 | =back |
5032 | |
5061 | |
5033 | If you know of other additional requirements drop me a note. |
5062 | If you know of other additional requirements drop me a note. |
5034 | |
5063 | |
… | |
… | |
5096 | =item Processing ev_async_send: O(number_of_async_watchers) |
5125 | =item Processing ev_async_send: O(number_of_async_watchers) |
5097 | |
5126 | |
5098 | =item Processing signals: O(max_signal_number) |
5127 | =item Processing signals: O(max_signal_number) |
5099 | |
5128 | |
5100 | Sending involves a system call I<iff> there were no other C<ev_async_send> |
5129 | Sending involves a system call I<iff> there were no other C<ev_async_send> |
5101 | calls in the current loop iteration. Checking for async and signal events |
5130 | calls in the current loop iteration and the loop is currently |
|
|
5131 | blocked. Checking for async and signal events involves iterating over all |
5102 | involves iterating over all running async watchers or all signal numbers. |
5132 | running async watchers or all signal numbers. |
5103 | |
5133 | |
5104 | =back |
5134 | =back |
5105 | |
5135 | |
5106 | |
5136 | |
5107 | =head1 PORTING FROM LIBEV 3.X TO 4.X |
5137 | =head1 PORTING FROM LIBEV 3.X TO 4.X |