… | |
… | |
30 | |
30 | |
31 | # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) |
31 | # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) |
32 | use AnyEvent::AIO; |
32 | use AnyEvent::AIO; |
33 | |
33 | |
34 | # EV integration |
34 | # EV integration |
35 | my $w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
35 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
36 | |
36 | |
37 | # Event integration |
37 | # Event integration |
38 | Event->io (fd => IO::AIO::poll_fileno, |
38 | Event->io (fd => IO::AIO::poll_fileno, |
39 | poll => 'r', |
39 | poll => 'r', |
40 | cb => \&IO::AIO::poll_cb); |
40 | cb => \&IO::AIO::poll_cb); |
… | |
… | |
52 | \&IO::AIO::poll_cb); |
52 | \&IO::AIO::poll_cb); |
53 | |
53 | |
54 | =head1 DESCRIPTION |
54 | =head1 DESCRIPTION |
55 | |
55 | |
56 | This module implements asynchronous I/O using whatever means your |
56 | This module implements asynchronous I/O using whatever means your |
57 | operating system supports. |
57 | operating system supports. It is implemented as an interface to C<libeio> |
|
|
58 | (L<http://software.schmorp.de/pkg/libeio.html>). |
58 | |
59 | |
59 | Asynchronous means that operations that can normally block your program |
60 | Asynchronous means that operations that can normally block your program |
60 | (e.g. reading from disk) will be done asynchronously: the operation |
61 | (e.g. reading from disk) will be done asynchronously: the operation |
61 | will still block, but you can do something else in the meantime. This |
62 | will still block, but you can do something else in the meantime. This |
62 | is extremely useful for programs that need to stay interactive even |
63 | is extremely useful for programs that need to stay interactive even |
… | |
… | |
66 | on a RAID volume or over NFS when you do a number of stat operations |
67 | on a RAID volume or over NFS when you do a number of stat operations |
67 | concurrently. |
68 | concurrently. |
68 | |
69 | |
69 | While most of this works on all types of file descriptors (for |
70 | While most of this works on all types of file descriptors (for |
70 | example sockets), using these functions on file descriptors that |
71 | example sockets), using these functions on file descriptors that |
71 | support nonblocking operation (again, sockets, pipes etc.) is very |
72 | support nonblocking operation (again, sockets, pipes etc.) is |
72 | inefficient. Use an event loop for that (such as the L<Event|Event> |
73 | very inefficient. Use an event loop for that (such as the L<EV> |
73 | module): IO::AIO will naturally fit into such an event loop itself. |
74 | module): IO::AIO will naturally fit into such an event loop itself. |
74 | |
75 | |
75 | In this version, a number of threads are started that execute your |
76 | In this version, a number of threads are started that execute your |
76 | requests and signal their completion. You don't need thread support |
77 | requests and signal their completion. You don't need thread support |
77 | in perl, and the threads created by this module will not be visible |
78 | in perl, and the threads created by this module will not be visible |
… | |
… | |
87 | yourself, always call C<poll_cb> from within the same thread, or never |
88 | yourself, always call C<poll_cb> from within the same thread, or never |
88 | call C<poll_cb> (or other C<aio_> functions) recursively. |
89 | call C<poll_cb> (or other C<aio_> functions) recursively. |
89 | |
90 | |
90 | =head2 EXAMPLE |
91 | =head2 EXAMPLE |
91 | |
92 | |
92 | This is a simple example that uses the Event module and loads |
93 | This is a simple example that uses the EV module and loads |
93 | F</etc/passwd> asynchronously: |
94 | F</etc/passwd> asynchronously: |
94 | |
95 | |
95 | use Fcntl; |
96 | use Fcntl; |
96 | use Event; |
97 | use EV; |
97 | use IO::AIO; |
98 | use IO::AIO; |
98 | |
99 | |
99 | # register the IO::AIO callback with Event |
100 | # register the IO::AIO callback with EV |
100 | Event->io (fd => IO::AIO::poll_fileno, |
101 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
101 | poll => 'r', |
|
|
102 | cb => \&IO::AIO::poll_cb); |
|
|
103 | |
102 | |
104 | # queue the request to open /etc/passwd |
103 | # queue the request to open /etc/passwd |
105 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
104 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
106 | my $fh = shift |
105 | my $fh = shift |
107 | or die "error while opening: $!"; |
106 | or die "error while opening: $!"; |
… | |
… | |
119 | |
118 | |
120 | # file contents now in $contents |
119 | # file contents now in $contents |
121 | print $contents; |
120 | print $contents; |
122 | |
121 | |
123 | # exit event loop and program |
122 | # exit event loop and program |
124 | Event::unloop; |
123 | EV::unloop; |
125 | }; |
124 | }; |
126 | }; |
125 | }; |
127 | |
126 | |
128 | # possibly queue up other requests, or open GUI windows, |
127 | # possibly queue up other requests, or open GUI windows, |
129 | # check for sockets etc. etc. |
128 | # check for sockets etc. etc. |
130 | |
129 | |
131 | # process events as long as there are some: |
130 | # process events as long as there are some: |
132 | Event::loop; |
131 | EV::loop; |
133 | |
132 | |
134 | =head1 REQUEST ANATOMY AND LIFETIME |
133 | =head1 REQUEST ANATOMY AND LIFETIME |
135 | |
134 | |
136 | Every C<aio_*> function creates a request. which is a C data structure not |
135 | Every C<aio_*> function creates a request. which is a C data structure not |
137 | directly visible to Perl. |
136 | directly visible to Perl. |
… | |
… | |
193 | use strict 'vars'; |
192 | use strict 'vars'; |
194 | |
193 | |
195 | use base 'Exporter'; |
194 | use base 'Exporter'; |
196 | |
195 | |
197 | BEGIN { |
196 | BEGIN { |
198 | our $VERSION = '3.19'; |
197 | our $VERSION = '3.23'; |
199 | |
198 | |
200 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close |
199 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close |
201 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
200 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
202 | aio_scandir aio_symlink aio_readlink aio_sync aio_fsync |
201 | aio_scandir aio_symlink aio_readlink aio_sync aio_fsync |
203 | aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead |
202 | aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead |
… | |
… | |
207 | |
206 | |
208 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
207 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
209 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
208 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
210 | min_parallel max_parallel max_idle |
209 | min_parallel max_parallel max_idle |
211 | nreqs nready npending nthreads |
210 | nreqs nready npending nthreads |
212 | max_poll_time max_poll_reqs); |
211 | max_poll_time max_poll_reqs |
|
|
212 | sendfile fadvise); |
213 | |
213 | |
214 | push @AIO_REQ, qw(aio_busy); # not exported |
214 | push @AIO_REQ, qw(aio_busy); # not exported |
215 | |
215 | |
216 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
216 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
217 | |
217 | |
… | |
… | |
548 | The flags are a combination of the following constants, ORed together (the |
548 | The flags are a combination of the following constants, ORed together (the |
549 | flags will also be passed to the callback, possibly modified): |
549 | flags will also be passed to the callback, possibly modified): |
550 | |
550 | |
551 | =over 4 |
551 | =over 4 |
552 | |
552 | |
553 | =item AIO::READDIR_DENTS |
553 | =item IO::AIO::READDIR_DENTS |
554 | |
554 | |
555 | When this flag is off, then the callback gets an arrayref with of names |
555 | When this flag is off, then the callback gets an arrayref with of names |
556 | only (as with C<aio_readdir>), otherwise it gets an arrayref with |
556 | only (as with C<aio_readdir>), otherwise it gets an arrayref with |
557 | C<[$name, $inode, $type]> arrayrefs, each describing a single directory |
557 | C<[$name, $type, $inode]> arrayrefs, each describing a single directory |
558 | entry in more detail. |
558 | entry in more detail. |
559 | |
559 | |
560 | C<$name> is the name of the entry. |
560 | C<$name> is the name of the entry. |
561 | |
561 | |
562 | C<$inode> is the inode number (which might not be exact on systems with 64 |
|
|
563 | bit inode numbers and 32 bit perls). On systems that do not deliver the |
|
|
564 | inode information, this will always be zero. |
|
|
565 | |
|
|
566 | C<$type> is one of the C<AIO::DT_xxx> constants: |
562 | C<$type> is one of the C<IO::AIO::DT_xxx> constants: |
567 | |
563 | |
568 | C<AIO::DT_UNKNOWN>, C<AIO::DT_FIFO>, C<AIO::DT_CHR>, C<AIO::DT_DIR>, |
564 | C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>, |
569 | C<AIO::DT_BLK>, C<AIO::DT_REG>, C<AIO::DT_LNK>, C<AIO::DT_SOCK>, |
565 | C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>, |
570 | C<AIO::DT_WHT>. |
566 | C<IO::AIO::DT_WHT>. |
571 | |
567 | |
572 | C<AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to |
568 | C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to |
573 | know, you have to run stat yourself. Also, for speed reasons, the C<$type> |
569 | know, you have to run stat yourself. Also, for speed reasons, the C<$type> |
574 | scalars are read-only: you can not modify them. |
570 | scalars are read-only: you can not modify them. |
575 | |
571 | |
|
|
572 | C<$inode> is the inode number (which might not be exact on systems with 64 |
|
|
573 | bit inode numbers and 32 bit perls). This field has unspecified content on |
|
|
574 | systems that do not deliver the inode information. |
|
|
575 | |
576 | =item AIO::READDIR_DIRS_FIRST |
576 | =item IO::AIO::READDIR_DIRS_FIRST |
577 | |
577 | |
578 | When this flag is set, then the names will be returned in an order where |
578 | When this flag is set, then the names will be returned in an order where |
579 | likely directories come first. This is useful when you need to quickly |
579 | likely directories come first. This is useful when you need to quickly |
580 | find directories, or you want to find all directories while avoiding to |
580 | find directories, or you want to find all directories while avoiding to |
581 | stat() each entry. |
581 | stat() each entry. |
582 | |
582 | |
|
|
583 | If the system returns type information in readdir, then this is used |
|
|
584 | to find directories directly. Otherwise, likely directories are files |
|
|
585 | beginning with ".", or otherwise files with no dots, of which files with |
|
|
586 | short names are tried first. |
|
|
587 | |
583 | =item AIO::READDIR_STAT_ORDER |
588 | =item IO::AIO::READDIR_STAT_ORDER |
584 | |
589 | |
585 | When this flag is set, then the names will be returned in an order |
590 | When this flag is set, then the names will be returned in an order |
586 | suitable for stat()'ing each one. That is, when you plan to stat() |
591 | suitable for stat()'ing each one. That is, when you plan to stat() |
587 | all files in the given directory, then the returned order will likely |
592 | all files in the given directory, then the returned order will likely |
588 | be fastest. |
593 | be fastest. |
589 | |
594 | |
590 | If both this flag and IO::READDIR_DIRS_FIRST are specified, then the |
595 | If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then |
591 | likely dirs come first, resulting in a less optimal stat order. |
596 | the likely dirs come first, resulting in a less optimal stat order. |
592 | |
597 | |
593 | =item AIO::READDIR_FOUND_UNKNOWN |
598 | =item IO::AIO::READDIR_FOUND_UNKNOWN |
594 | |
599 | |
595 | This flag should not be set when calling C<aio_readdirx>. Instead, it |
600 | This flag should not be set when calling C<aio_readdirx>. Instead, it |
596 | is being set by C<aio_readdirx>, when any of the C<$type>'s found were |
601 | is being set by C<aio_readdirx>, when any of the C<$type>'s found were |
597 | C<AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all |
602 | C<IO::AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all |
598 | C<$type>'s are known, which can be used to speed up some algorithms. |
603 | C<$type>'s are known, which can be used to speed up some algorithms. |
599 | |
604 | |
600 | =back |
605 | =back |
601 | |
606 | |
602 | |
607 | |
… | |
… | |
770 | |
775 | |
771 | Implementation notes. |
776 | Implementation notes. |
772 | |
777 | |
773 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
778 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
774 | |
779 | |
|
|
780 | If readdir returns file type information, then this is used directly to |
|
|
781 | find directories. |
|
|
782 | |
775 | After reading the directory, the modification time, size etc. of the |
783 | Otherwise, after reading the directory, the modification time, size etc. |
776 | directory before and after the readdir is checked, and if they match (and |
784 | of the directory before and after the readdir is checked, and if they |
777 | isn't the current time), the link count will be used to decide how many |
785 | match (and isn't the current time), the link count will be used to decide |
778 | entries are directories (if >= 2). Otherwise, no knowledge of the number |
786 | how many entries are directories (if >= 2). Otherwise, no knowledge of the |
779 | of subdirectories will be assumed. |
787 | number of subdirectories will be assumed. |
780 | |
788 | |
781 | Then entries will be sorted into likely directories (everything without |
789 | Then entries will be sorted into likely directories a non-initial dot |
782 | a non-initial dot currently) and likely non-directories (everything |
790 | currently) and likely non-directories (see C<aio_readdirx>). Then every |
783 | else). Then every entry plus an appended C</.> will be C<stat>'ed, |
791 | entry plus an appended C</.> will be C<stat>'ed, likely directories first, |
784 | likely directories first. If that succeeds, it assumes that the entry |
792 | in order of their inode numbers. If that succeeds, it assumes that the |
785 | is a directory or a symlink to directory (which will be checked |
793 | entry is a directory or a symlink to directory (which will be checked |
786 | seperately). This is often faster than stat'ing the entry itself because |
794 | seperately). This is often faster than stat'ing the entry itself because |
787 | filesystems might detect the type of the entry without reading the inode |
795 | filesystems might detect the type of the entry without reading the inode |
788 | data (e.g. ext2fs filetype feature). |
796 | data (e.g. ext2fs filetype feature), even on systems that cannot return |
|
|
797 | the filetype information on readdir. |
789 | |
798 | |
790 | If the known number of directories (link count - 2) has been reached, the |
799 | If the known number of directories (link count - 2) has been reached, the |
791 | rest of the entries is assumed to be non-directories. |
800 | rest of the entries is assumed to be non-directories. |
792 | |
801 | |
793 | This only works with certainty on POSIX (= UNIX) filesystems, which |
802 | This only works with certainty on POSIX (= UNIX) filesystems, which |
… | |
… | |
831 | # take the slow route if anything looks fishy |
840 | # take the slow route if anything looks fishy |
832 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
841 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
833 | $ndirs = -1; |
842 | $ndirs = -1; |
834 | } else { |
843 | } else { |
835 | # if nlink == 2, we are finished |
844 | # if nlink == 2, we are finished |
836 | # on non-posix-fs's, we rely on nlink < 2 |
845 | # for non-posix-fs's, we rely on nlink < 2 |
837 | $ndirs = (stat _)[3] - 2 |
846 | $ndirs = (stat _)[3] - 2 |
838 | or return $grp->result ([], $entries); |
847 | or return $grp->result ([], $entries); |
839 | } |
848 | } |
840 | |
849 | |
841 | # sort into likely dirs and likely nondirs |
|
|
842 | # dirs == files without ".", short entries first |
|
|
843 | $entries = [map $_->[0], |
|
|
844 | sort { $b->[1] cmp $a->[1] } |
|
|
845 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
|
|
846 | @$entries]; |
|
|
847 | |
|
|
848 | my (@dirs, @nondirs); |
850 | my (@dirs, @nondirs); |
849 | |
851 | |
850 | my $statgrp = add $grp aio_group sub { |
852 | my $statgrp = add $grp aio_group sub { |
851 | $grp->result (\@dirs, \@nondirs); |
853 | $grp->result (\@dirs, \@nondirs); |
852 | }; |
854 | }; |
853 | |
855 | |
854 | limit $statgrp $maxreq; |
856 | limit $statgrp $maxreq; |
855 | feed $statgrp sub { |
857 | feed $statgrp sub { |
856 | return unless @$entries; |
858 | return unless @$entries; |
857 | my $entry = pop @$entries; |
859 | my $entry = shift @$entries; |
858 | |
860 | |
859 | aioreq_pri $pri; |
861 | aioreq_pri $pri; |
860 | add $statgrp aio_stat "$path/$entry/.", sub { |
862 | add $statgrp aio_stat "$path/$entry/.", sub { |
861 | if ($_[0] < 0) { |
863 | if ($_[0] < 0) { |
862 | push @nondirs, $entry; |
864 | push @nondirs, $entry; |
… | |
… | |
1043 | =item cancel $req |
1045 | =item cancel $req |
1044 | |
1046 | |
1045 | Cancels the request, if possible. Has the effect of skipping execution |
1047 | Cancels the request, if possible. Has the effect of skipping execution |
1046 | when entering the B<execute> state and skipping calling the callback when |
1048 | when entering the B<execute> state and skipping calling the callback when |
1047 | entering the the B<result> state, but will leave the request otherwise |
1049 | entering the the B<result> state, but will leave the request otherwise |
1048 | untouched. That means that requests that currently execute will not be |
1050 | untouched (with the exception of readdir). That means that requests that |
1049 | stopped and resources held by the request will not be freed prematurely. |
1051 | currently execute will not be stopped and resources held by the request |
|
|
1052 | will not be freed prematurely. |
1050 | |
1053 | |
1051 | =item cb $req $callback->(...) |
1054 | =item cb $req $callback->(...) |
1052 | |
1055 | |
1053 | Replace (or simply set) the callback registered to the request. |
1056 | Replace (or simply set) the callback registered to the request. |
1054 | |
1057 | |
… | |
… | |
1205 | =over 4 |
1208 | =over 4 |
1206 | |
1209 | |
1207 | =item $fileno = IO::AIO::poll_fileno |
1210 | =item $fileno = IO::AIO::poll_fileno |
1208 | |
1211 | |
1209 | Return the I<request result pipe file descriptor>. This filehandle must be |
1212 | Return the I<request result pipe file descriptor>. This filehandle must be |
1210 | polled for reading by some mechanism outside this module (e.g. Event or |
1213 | polled for reading by some mechanism outside this module (e.g. EV, Glib, |
1211 | select, see below or the SYNOPSIS). If the pipe becomes readable you have |
1214 | select and so on, see below or the SYNOPSIS). If the pipe becomes readable |
1212 | to call C<poll_cb> to check the results. |
1215 | you have to call C<poll_cb> to check the results. |
1213 | |
1216 | |
1214 | See C<poll_cb> for an example. |
1217 | See C<poll_cb> for an example. |
1215 | |
1218 | |
1216 | =item IO::AIO::poll_cb |
1219 | =item IO::AIO::poll_cb |
1217 | |
1220 | |
… | |
… | |
1224 | If not all requests were processed for whatever reason, the filehandle |
1227 | If not all requests were processed for whatever reason, the filehandle |
1225 | will still be ready when C<poll_cb> returns, so normally you don't have to |
1228 | will still be ready when C<poll_cb> returns, so normally you don't have to |
1226 | do anything special to have it called later. |
1229 | do anything special to have it called later. |
1227 | |
1230 | |
1228 | Example: Install an Event watcher that automatically calls |
1231 | Example: Install an Event watcher that automatically calls |
1229 | IO::AIO::poll_cb with high priority: |
1232 | IO::AIO::poll_cb with high priority (more examples can be found in the |
|
|
1233 | SYNOPSIS section, at the top of this document): |
1230 | |
1234 | |
1231 | Event->io (fd => IO::AIO::poll_fileno, |
1235 | Event->io (fd => IO::AIO::poll_fileno, |
1232 | poll => 'r', async => 1, |
1236 | poll => 'r', async => 1, |
1233 | cb => \&IO::AIO::poll_cb); |
1237 | cb => \&IO::AIO::poll_cb); |
1234 | |
1238 | |
… | |
… | |
1388 | |
1392 | |
1389 | =item IO::AIO::npending |
1393 | =item IO::AIO::npending |
1390 | |
1394 | |
1391 | Returns the number of requests currently in the pending state (executed, |
1395 | Returns the number of requests currently in the pending state (executed, |
1392 | but not yet processed by poll_cb). |
1396 | but not yet processed by poll_cb). |
|
|
1397 | |
|
|
1398 | =back |
|
|
1399 | |
|
|
1400 | =head3 MISCELLANEOUS FUNCTIONS |
|
|
1401 | |
|
|
1402 | IO::AIO implements some functions that might be useful, but are not |
|
|
1403 | asynchronous. |
|
|
1404 | |
|
|
1405 | =over 4 |
|
|
1406 | |
|
|
1407 | =item IO::AIO::sendfile $ofh, $ifh, $offset, $count |
|
|
1408 | |
|
|
1409 | Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>, |
|
|
1410 | but is blocking (this makes most sense if you know the input data is |
|
|
1411 | likely cached already and the output filehandle is set to non-blocking |
|
|
1412 | operations). |
|
|
1413 | |
|
|
1414 | Returns the number of bytes copied, or C<-1> on error. |
|
|
1415 | |
|
|
1416 | =item IO::AIO::fadvise $fh, $offset, $len, $advice |
|
|
1417 | |
|
|
1418 | Simply calls the C<posix_fadvise> function (see it's |
|
|
1419 | manpage for details). The following advice constants are |
|
|
1420 | avaiable: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>, |
|
|
1421 | C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>, |
|
|
1422 | C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>. |
|
|
1423 | |
|
|
1424 | On systems that do not implement C<posix_fadvise>, this function returns |
|
|
1425 | ENOSYS, otherwise the return value of C<posix_fadvise>. |
1393 | |
1426 | |
1394 | =back |
1427 | =back |
1395 | |
1428 | |
1396 | =cut |
1429 | =cut |
1397 | |
1430 | |