| … | |
… | |
| 511 | This backend maps C<EV_READ> to C<POLLIN | POLLERR | POLLHUP>, and |
511 | This backend maps C<EV_READ> to C<POLLIN | POLLERR | POLLHUP>, and |
| 512 | C<EV_WRITE> to C<POLLOUT | POLLERR | POLLHUP>. |
512 | C<EV_WRITE> to C<POLLOUT | POLLERR | POLLHUP>. |
| 513 | |
513 | |
| 514 | =item C<EVBACKEND_EPOLL> (value 4, Linux) |
514 | =item C<EVBACKEND_EPOLL> (value 4, Linux) |
| 515 | |
515 | |
| 516 | Use the linux-specific epoll(7) interface (for both pre- and post-2.6.9 |
516 | Use the Linux-specific epoll(7) interface (for both pre- and post-2.6.9 |
| 517 | kernels). |
517 | kernels). |
| 518 | |
518 | |
| 519 | For few fds, this backend is a bit little slower than poll and select, but |
519 | For few fds, this backend is a bit little slower than poll and select, but |
| 520 | it scales phenomenally better. While poll and select usually scale like |
520 | it scales phenomenally better. While poll and select usually scale like |
| 521 | O(total_fds) where total_fds is the total number of fds (or the highest |
521 | O(total_fds) where total_fds is the total number of fds (or the highest |
| … | |
… | |
| 574 | This backend maps C<EV_READ> and C<EV_WRITE> in the same way as |
574 | This backend maps C<EV_READ> and C<EV_WRITE> in the same way as |
| 575 | C<EVBACKEND_POLL>. |
575 | C<EVBACKEND_POLL>. |
| 576 | |
576 | |
| 577 | =item C<EVBACKEND_LINUXAIO> (value 64, Linux) |
577 | =item C<EVBACKEND_LINUXAIO> (value 64, Linux) |
| 578 | |
578 | |
| 579 | Use the linux-specific linux aio (I<not> C<< aio(7) >> but C<< |
579 | Use the Linux-specific Linux AIO (I<not> C<< aio(7) >> but C<< |
| 580 | io_submit(2) >>) event interface available in post-4.18 kernels (but libev |
580 | io_submit(2) >>) event interface available in post-4.18 kernels (but libev |
| 581 | only tries to use it in 4.19+). |
581 | only tries to use it in 4.19+). |
| 582 | |
582 | |
| 583 | This is another linux trainwreck of an event interface. |
583 | This is another Linux train wreck of an event interface. |
| 584 | |
584 | |
| 585 | If this backend works for you (as of this writing, it was very |
585 | If this backend works for you (as of this writing, it was very |
| 586 | experimental), it is the best event interface available on linux and might |
586 | experimental), it is the best event interface available on Linux and might |
| 587 | be well worth enabling it - if it isn't available in your kernel this will |
587 | be well worth enabling it - if it isn't available in your kernel this will |
| 588 | be detected and this backend will be skipped. |
588 | be detected and this backend will be skipped. |
| 589 | |
589 | |
| 590 | This backend can batch oneshot requests and supports a user-space ring |
590 | This backend can batch oneshot requests and supports a user-space ring |
| 591 | buffer to receive events. It also doesn't suffer from most of the design |
591 | buffer to receive events. It also doesn't suffer from most of the design |
| 592 | problems of epoll (such as not being able to remove event sources from |
592 | problems of epoll (such as not being able to remove event sources from |
| 593 | the epoll set), and generally sounds too good to be true. Because, this |
593 | the epoll set), and generally sounds too good to be true. Because, this |
| 594 | being the linux kernel, of course it suffers from a whole new set of |
594 | being the Linux kernel, of course it suffers from a whole new set of |
| 595 | limitations, forcing you to fall back to epoll, inheriting all its design |
595 | limitations, forcing you to fall back to epoll, inheriting all its design |
| 596 | issues. |
596 | issues. |
| 597 | |
597 | |
| 598 | For one, it is not easily embeddable (but probably could be done using |
598 | For one, it is not easily embeddable (but probably could be done using |
| 599 | an event fd at some extra overhead). It also is subject to a system wide |
599 | an event fd at some extra overhead). It also is subject to a system wide |
| 600 | limit that can be configured in F</proc/sys/fs/aio-max-nr>. If no aio |
600 | limit that can be configured in F</proc/sys/fs/aio-max-nr>. If no AIO |
| 601 | requests are left, this backend will be skipped during initialisation, and |
601 | requests are left, this backend will be skipped during initialisation, and |
| 602 | will switch to epoll when the loop is active. |
602 | will switch to epoll when the loop is active. |
| 603 | |
603 | |
| 604 | Most problematic in practice, however, is that not all file descriptors |
604 | Most problematic in practice, however, is that not all file descriptors |
| 605 | work with it. For example, in linux 5.1, tcp sockets, pipes, event fds, |
605 | work with it. For example, in Linux 5.1, TCP sockets, pipes, event fds, |
| 606 | files, F</dev/null> and a few others are supported, but ttys do not work |
606 | files, F</dev/null> and many others are supported, but ttys do not work |
| 607 | properly (a known bug that the kernel developers don't care about, see |
607 | properly (a known bug that the kernel developers don't care about, see |
| 608 | L<https://lore.kernel.org/patchwork/patch/1047453/>), so this is not |
608 | L<https://lore.kernel.org/patchwork/patch/1047453/>), so this is not |
| 609 | (yet?) a generic event polling interface. |
609 | (yet?) a generic event polling interface. |
| 610 | |
610 | |
| 611 | Overall, it seems the linux developers just don't want it to have a |
611 | Overall, it seems the Linux developers just don't want it to have a |
| 612 | generic event handling mechanism other than C<select> or C<poll>. |
612 | generic event handling mechanism other than C<select> or C<poll>. |
| 613 | |
613 | |
| 614 | To work around all these problem, the current version of libev uses its |
614 | To work around all these problem, the current version of libev uses its |
| 615 | epoll backend as a fallback for file descriptor types that do not work. Or |
615 | epoll backend as a fallback for file descriptor types that do not work. Or |
| 616 | falls back completely to epoll if the kernel acts up. |
616 | falls back completely to epoll if the kernel acts up. |
| … | |
… | |
| 637 | It scales in the same way as the epoll backend, but the interface to the |
637 | It scales in the same way as the epoll backend, but the interface to the |
| 638 | kernel is more efficient (which says nothing about its actual speed, of |
638 | kernel is more efficient (which says nothing about its actual speed, of |
| 639 | course). While stopping, setting and starting an I/O watcher does never |
639 | course). While stopping, setting and starting an I/O watcher does never |
| 640 | cause an extra system call as with C<EVBACKEND_EPOLL>, it still adds up to |
640 | cause an extra system call as with C<EVBACKEND_EPOLL>, it still adds up to |
| 641 | two event changes per incident. Support for C<fork ()> is very bad (you |
641 | two event changes per incident. Support for C<fork ()> is very bad (you |
| 642 | might have to leak fd's on fork, but it's more sane than epoll) and it |
642 | might have to leak fds on fork, but it's more sane than epoll) and it |
| 643 | drops fds silently in similarly hard-to-detect cases. |
643 | drops fds silently in similarly hard-to-detect cases. |
| 644 | |
644 | |
| 645 | This backend usually performs well under most conditions. |
645 | This backend usually performs well under most conditions. |
| 646 | |
646 | |
| 647 | While nominally embeddable in other event loops, this doesn't work |
647 | While nominally embeddable in other event loops, this doesn't work |
