… | |
… | |
24 | $req->cancel; # cancel request if still in queue |
24 | $req->cancel; # cancel request if still in queue |
25 | |
25 | |
26 | my $grp = aio_group sub { print "all stats done\n" }; |
26 | my $grp = aio_group sub { print "all stats done\n" }; |
27 | add $grp aio_stat "..." for ...; |
27 | add $grp aio_stat "..." for ...; |
28 | |
28 | |
|
|
29 | # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) |
|
|
30 | use AnyEvent::AIO; |
|
|
31 | |
29 | # AnyEvent integration |
32 | # EV integration |
30 | open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; |
33 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
31 | my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb }); |
|
|
32 | |
34 | |
33 | # Event integration |
35 | # Event integration |
34 | Event->io (fd => IO::AIO::poll_fileno, |
36 | Event->io (fd => IO::AIO::poll_fileno, |
35 | poll => 'r', |
37 | poll => 'r', |
36 | cb => \&IO::AIO::poll_cb); |
38 | cb => \&IO::AIO::poll_cb); |
… | |
… | |
47 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
49 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
48 | \&IO::AIO::poll_cb); |
50 | \&IO::AIO::poll_cb); |
49 | |
51 | |
50 | DESCRIPTION |
52 | DESCRIPTION |
51 | This module implements asynchronous I/O using whatever means your |
53 | This module implements asynchronous I/O using whatever means your |
52 | operating system supports. |
54 | operating system supports. It is implemented as an interface to "libeio" |
|
|
55 | (<http://software.schmorp.de/pkg/libeio.html>). |
53 | |
56 | |
54 | Asynchronous means that operations that can normally block your program |
57 | Asynchronous means that operations that can normally block your program |
55 | (e.g. reading from disk) will be done asynchronously: the operation will |
58 | (e.g. reading from disk) will be done asynchronously: the operation will |
56 | still block, but you can do something else in the meantime. This is |
59 | still block, but you can do something else in the meantime. This is |
57 | extremely useful for programs that need to stay interactive even when |
60 | extremely useful for programs that need to stay interactive even when |
… | |
… | |
61 | faster on a RAID volume or over NFS when you do a number of stat |
64 | faster on a RAID volume or over NFS when you do a number of stat |
62 | operations concurrently. |
65 | operations concurrently. |
63 | |
66 | |
64 | While most of this works on all types of file descriptors (for example |
67 | While most of this works on all types of file descriptors (for example |
65 | sockets), using these functions on file descriptors that support |
68 | sockets), using these functions on file descriptors that support |
66 | nonblocking operation (again, sockets, pipes etc.) is very inefficient |
69 | nonblocking operation (again, sockets, pipes etc.) is very inefficient. |
67 | or might not work (aio_read fails on sockets/pipes/fifos). Use an event |
|
|
68 | loop for that (such as the Event module): IO::AIO will naturally fit |
70 | Use an event loop for that (such as the EV module): IO::AIO will |
69 | into such an event loop itself. |
71 | naturally fit into such an event loop itself. |
70 | |
72 | |
71 | In this version, a number of threads are started that execute your |
73 | In this version, a number of threads are started that execute your |
72 | requests and signal their completion. You don't need thread support in |
74 | requests and signal their completion. You don't need thread support in |
73 | perl, and the threads created by this module will not be visible to |
75 | perl, and the threads created by this module will not be visible to |
74 | perl. In the future, this module might make use of the native aio |
76 | perl. In the future, this module might make use of the native aio |
… | |
… | |
76 | not well-supported or restricted (GNU/Linux doesn't allow them on normal |
78 | not well-supported or restricted (GNU/Linux doesn't allow them on normal |
77 | files currently, for example), and they would only support aio_read and |
79 | files currently, for example), and they would only support aio_read and |
78 | aio_write, so the remaining functionality would have to be implemented |
80 | aio_write, so the remaining functionality would have to be implemented |
79 | using threads anyway. |
81 | using threads anyway. |
80 | |
82 | |
81 | Although the module will work with in the presence of other (Perl-) |
83 | Although the module will work in the presence of other (Perl-) threads, |
82 | threads, it is currently not reentrant in any way, so use appropriate |
84 | it is currently not reentrant in any way, so use appropriate locking |
83 | locking yourself, always call "poll_cb" from within the same thread, or |
85 | yourself, always call "poll_cb" from within the same thread, or never |
84 | never call "poll_cb" (or other "aio_" functions) recursively. |
86 | call "poll_cb" (or other "aio_" functions) recursively. |
85 | |
87 | |
86 | EXAMPLE |
88 | EXAMPLE |
87 | This is a simple example that uses the Event module and loads |
89 | This is a simple example that uses the EV module and loads /etc/passwd |
88 | /etc/passwd asynchronously: |
90 | asynchronously: |
89 | |
91 | |
90 | use Fcntl; |
92 | use Fcntl; |
91 | use Event; |
93 | use EV; |
92 | use IO::AIO; |
94 | use IO::AIO; |
93 | |
95 | |
94 | # register the IO::AIO callback with Event |
96 | # register the IO::AIO callback with EV |
95 | Event->io (fd => IO::AIO::poll_fileno, |
97 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
96 | poll => 'r', |
|
|
97 | cb => \&IO::AIO::poll_cb); |
|
|
98 | |
98 | |
99 | # queue the request to open /etc/passwd |
99 | # queue the request to open /etc/passwd |
100 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
100 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
101 | my $fh = shift |
101 | my $fh = shift |
102 | or die "error while opening: $!"; |
102 | or die "error while opening: $!"; |
… | |
… | |
114 | |
114 | |
115 | # file contents now in $contents |
115 | # file contents now in $contents |
116 | print $contents; |
116 | print $contents; |
117 | |
117 | |
118 | # exit event loop and program |
118 | # exit event loop and program |
119 | Event::unloop; |
119 | EV::unloop; |
120 | }; |
120 | }; |
121 | }; |
121 | }; |
122 | |
122 | |
123 | # possibly queue up other requests, or open GUI windows, |
123 | # possibly queue up other requests, or open GUI windows, |
124 | # check for sockets etc. etc. |
124 | # check for sockets etc. etc. |
125 | |
125 | |
126 | # process events as long as there are some: |
126 | # process events as long as there are some: |
127 | Event::loop; |
127 | EV::loop; |
128 | |
128 | |
129 | REQUEST ANATOMY AND LIFETIME |
129 | REQUEST ANATOMY AND LIFETIME |
130 | Every "aio_*" function creates a request. which is a C data structure |
130 | Every "aio_*" function creates a request. which is a C data structure |
131 | not directly visible to Perl. |
131 | not directly visible to Perl. |
132 | |
132 | |
… | |
… | |
174 | All the "aio_*" calls are more or less thin wrappers around the syscall |
174 | All the "aio_*" calls are more or less thin wrappers around the syscall |
175 | with the same name (sans "aio_"). The arguments are similar or |
175 | with the same name (sans "aio_"). The arguments are similar or |
176 | identical, and they all accept an additional (and optional) $callback |
176 | identical, and they all accept an additional (and optional) $callback |
177 | argument which must be a code reference. This code reference will get |
177 | argument which must be a code reference. This code reference will get |
178 | called with the syscall return code (e.g. most syscalls return -1 on |
178 | called with the syscall return code (e.g. most syscalls return -1 on |
179 | error, unlike perl, which usually delivers "false") as it's sole |
179 | error, unlike perl, which usually delivers "false") as its sole argument |
180 | argument when the given syscall has been executed asynchronously. |
180 | after the given syscall has been executed asynchronously. |
181 | |
181 | |
182 | All functions expecting a filehandle keep a copy of the filehandle |
182 | All functions expecting a filehandle keep a copy of the filehandle |
183 | internally until the request has finished. |
183 | internally until the request has finished. |
184 | |
184 | |
185 | All functions return request objects of type IO::AIO::REQ that allow |
185 | All functions return request objects of type IO::AIO::REQ that allow |
… | |
… | |
198 | the user environment, d) use Glib::filename_from_unicode on unicode |
198 | the user environment, d) use Glib::filename_from_unicode on unicode |
199 | filenames or e) use something else to ensure your scalar has the correct |
199 | filenames or e) use something else to ensure your scalar has the correct |
200 | contents. |
200 | contents. |
201 | |
201 | |
202 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
202 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
203 | handles correctly wether it is set or not. |
203 | handles correctly whether it is set or not. |
204 | |
204 | |
205 | $prev_pri = aioreq_pri [$pri] |
205 | $prev_pri = aioreq_pri [$pri] |
206 | Returns the priority value that would be used for the next request |
206 | Returns the priority value that would be used for the next request |
207 | and, if $pri is given, sets the priority for the next aio request. |
207 | and, if $pri is given, sets the priority for the next aio request. |
208 | |
208 | |
… | |
… | |
259 | } |
259 | } |
260 | }; |
260 | }; |
261 | |
261 | |
262 | aio_close $fh, $callback->($status) |
262 | aio_close $fh, $callback->($status) |
263 | Asynchronously close a file and call the callback with the result |
263 | Asynchronously close a file and call the callback with the result |
264 | code. *WARNING:* although accepted, you should not pass in a perl |
264 | code. |
265 | filehandle here, as perl will likely close the file descriptor |
|
|
266 | another time when the filehandle is destroyed. Normally, you can |
|
|
267 | safely call perls "close" or just let filehandles go out of scope. |
|
|
268 | |
265 | |
269 | This is supposed to be a bug in the API, so that might change. It's |
266 | Unfortunately, you can't do this to perl. Perl *insists* very |
270 | therefore best to avoid this function. |
267 | strongly on closing the file descriptor associated with the |
|
|
268 | filehandle itself. |
|
|
269 | |
|
|
270 | Therefore, "aio_close" will not close the filehandle - instead it |
|
|
271 | will use dup2 to overwrite the file descriptor with the write-end of |
|
|
272 | a pipe (the pipe fd will be created on demand and will be cached). |
|
|
273 | |
|
|
274 | Or in other words: the file descriptor will be closed, but it will |
|
|
275 | not be free for reuse until the perl filehandle is closed. |
271 | |
276 | |
272 | aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
277 | aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
273 | aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
278 | aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
274 | Reads or writes "length" bytes from the specified "fh" and "offset" |
279 | Reads or writes $length bytes from or to the specified $fh and |
275 | into the scalar given by "data" and offset "dataoffset" and calls |
280 | $offset into the scalar given by $data and offset $dataoffset and |
276 | the callback without the actual number of bytes read (or -1 on |
281 | calls the callback without the actual number of bytes read (or -1 on |
277 | error, just like the syscall). |
282 | error, just like the syscall). |
278 | |
283 | |
|
|
284 | "aio_read" will, like "sysread", shrink or grow the $data scalar to |
|
|
285 | offset plus the actual number of bytes read. |
|
|
286 | |
|
|
287 | If $offset is undefined, then the current file descriptor offset |
|
|
288 | will be used (and updated), otherwise the file descriptor offset |
|
|
289 | will not be changed by these calls. |
|
|
290 | |
|
|
291 | If $length is undefined in "aio_write", use the remaining length of |
|
|
292 | $data. |
|
|
293 | |
|
|
294 | If $dataoffset is less than zero, it will be counted from the end of |
|
|
295 | $data. |
|
|
296 | |
279 | The $data scalar *MUST NOT* be modified in any way while the request |
297 | The $data scalar *MUST NOT* be modified in any way while the request |
280 | is outstanding. Modifying it can result in segfaults or WW3 (if the |
298 | is outstanding. Modifying it can result in segfaults or World War |
281 | necessary/optional hardware is installed). |
299 | III (if the necessary/optional hardware is installed). |
282 | |
300 | |
283 | Example: Read 15 bytes at offset 7 into scalar $buffer, starting at |
301 | Example: Read 15 bytes at offset 7 into scalar $buffer, starting at |
284 | offset 0 within the scalar: |
302 | offset 0 within the scalar: |
285 | |
303 | |
286 | aio_read $fh, 7, 15, $buffer, 0, sub { |
304 | aio_read $fh, 7, 15, $buffer, 0, sub { |
… | |
… | |
297 | |
315 | |
298 | This call tries to make use of a native "sendfile" syscall to |
316 | This call tries to make use of a native "sendfile" syscall to |
299 | provide zero-copy operation. For this to work, $out_fh should refer |
317 | provide zero-copy operation. For this to work, $out_fh should refer |
300 | to a socket, and $in_fh should refer to mmap'able file. |
318 | to a socket, and $in_fh should refer to mmap'able file. |
301 | |
319 | |
302 | If the native sendfile call fails or is not implemented, it will be |
320 | If a native sendfile cannot be found or it fails with "ENOSYS", |
|
|
321 | "ENOTSUP", "EOPNOTSUPP", "EAFNOSUPPORT", "EPROTOTYPE" or "ENOTSOCK", |
303 | emulated, so you can call "aio_sendfile" on any type of filehandle |
322 | it will be emulated, so you can call "aio_sendfile" on any type of |
304 | regardless of the limitations of the operating system. |
323 | filehandle regardless of the limitations of the operating system. |
305 | |
324 | |
306 | Please note, however, that "aio_sendfile" can read more bytes from |
325 | Please note, however, that "aio_sendfile" can read more bytes from |
307 | $in_fh than are written, and there is no way to find out how many |
326 | $in_fh than are written, and there is no way to find out how many |
308 | bytes have been read from "aio_sendfile" alone, as "aio_sendfile" |
327 | bytes have been read from "aio_sendfile" alone, as "aio_sendfile" |
309 | only provides the number of bytes written to $out_fh. Only if the |
328 | only provides the number of bytes written to $out_fh. Only if the |
… | |
… | |
344 | aio_stat "/etc/passwd", sub { |
363 | aio_stat "/etc/passwd", sub { |
345 | $_[0] and die "stat failed: $!"; |
364 | $_[0] and die "stat failed: $!"; |
346 | print "size is ", -s _, "\n"; |
365 | print "size is ", -s _, "\n"; |
347 | }; |
366 | }; |
348 | |
367 | |
|
|
368 | aio_utime $fh_or_path, $atime, $mtime, $callback->($status) |
|
|
369 | Works like perl's "utime" function (including the special case of |
|
|
370 | $atime and $mtime being undef). Fractional times are supported if |
|
|
371 | the underlying syscalls support them. |
|
|
372 | |
|
|
373 | When called with a pathname, uses utimes(2) if available, otherwise |
|
|
374 | utime(2). If called on a file descriptor, uses futimes(2) if |
|
|
375 | available, otherwise returns ENOSYS, so this is not portable. |
|
|
376 | |
|
|
377 | Examples: |
|
|
378 | |
|
|
379 | # set atime and mtime to current time (basically touch(1)): |
|
|
380 | aio_utime "path", undef, undef; |
|
|
381 | # set atime to current time and mtime to beginning of the epoch: |
|
|
382 | aio_utime "path", time, undef; # undef==0 |
|
|
383 | |
|
|
384 | aio_chown $fh_or_path, $uid, $gid, $callback->($status) |
|
|
385 | Works like perl's "chown" function, except that "undef" for either |
|
|
386 | $uid or $gid is being interpreted as "do not change" (but -1 can |
|
|
387 | also be used). |
|
|
388 | |
|
|
389 | Examples: |
|
|
390 | |
|
|
391 | # same as "chown root path" in the shell: |
|
|
392 | aio_chown "path", 0, -1; |
|
|
393 | # same as above: |
|
|
394 | aio_chown "path", 0, undef; |
|
|
395 | |
|
|
396 | aio_truncate $fh_or_path, $offset, $callback->($status) |
|
|
397 | Works like truncate(2) or ftruncate(2). |
|
|
398 | |
|
|
399 | aio_chmod $fh_or_path, $mode, $callback->($status) |
|
|
400 | Works like perl's "chmod" function. |
|
|
401 | |
349 | aio_unlink $pathname, $callback->($status) |
402 | aio_unlink $pathname, $callback->($status) |
350 | Asynchronously unlink (delete) a file and call the callback with the |
403 | Asynchronously unlink (delete) a file and call the callback with the |
351 | result code. |
404 | result code. |
352 | |
405 | |
353 | aio_mknod $path, $mode, $dev, $callback->($status) |
406 | aio_mknod $path, $mode, $dev, $callback->($status) |
… | |
… | |
389 | aio_readdir $pathname, $callback->($entries) |
442 | aio_readdir $pathname, $callback->($entries) |
390 | Unlike the POSIX call of the same name, "aio_readdir" reads an |
443 | Unlike the POSIX call of the same name, "aio_readdir" reads an |
391 | entire directory (i.e. opendir + readdir + closedir). The entries |
444 | entire directory (i.e. opendir + readdir + closedir). The entries |
392 | will not be sorted, and will NOT include the "." and ".." entries. |
445 | will not be sorted, and will NOT include the "." and ".." entries. |
393 | |
446 | |
394 | The callback a single argument which is either "undef" or an |
447 | The callback is passed a single argument which is either "undef" or |
395 | array-ref with the filenames. |
448 | an array-ref with the filenames. |
|
|
449 | |
|
|
450 | aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
|
|
451 | Quite similar to "aio_readdir", but the $flags argument allows to |
|
|
452 | tune behaviour and output format. In case of an error, $entries will |
|
|
453 | be "undef". |
|
|
454 | |
|
|
455 | The flags are a combination of the following constants, ORed |
|
|
456 | together (the flags will also be passed to the callback, possibly |
|
|
457 | modified): |
|
|
458 | |
|
|
459 | IO::AIO::READDIR_DENTS |
|
|
460 | When this flag is off, then the callback gets an arrayref with |
|
|
461 | of names only (as with "aio_readdir"), otherwise it gets an |
|
|
462 | arrayref with "[$name, $type, $inode]" arrayrefs, each |
|
|
463 | describing a single directory entry in more detail. |
|
|
464 | |
|
|
465 | $name is the name of the entry. |
|
|
466 | |
|
|
467 | $type is one of the "IO::AIO::DT_xxx" constants: |
|
|
468 | |
|
|
469 | "IO::AIO::DT_UNKNOWN", "IO::AIO::DT_FIFO", "IO::AIO::DT_CHR", |
|
|
470 | "IO::AIO::DT_DIR", "IO::AIO::DT_BLK", "IO::AIO::DT_REG", |
|
|
471 | "IO::AIO::DT_LNK", "IO::AIO::DT_SOCK", "IO::AIO::DT_WHT". |
|
|
472 | |
|
|
473 | "IO::AIO::DT_UNKNOWN" means just that: readdir does not know. If |
|
|
474 | you need to know, you have to run stat yourself. Also, for speed |
|
|
475 | reasons, the $type scalars are read-only: you can not modify |
|
|
476 | them. |
|
|
477 | |
|
|
478 | $inode is the inode number (which might not be exact on systems |
|
|
479 | with 64 bit inode numbers and 32 bit perls). This field has |
|
|
480 | unspecified content on systems that do not deliver the inode |
|
|
481 | information. |
|
|
482 | |
|
|
483 | IO::AIO::READDIR_DIRS_FIRST |
|
|
484 | When this flag is set, then the names will be returned in an |
|
|
485 | order where likely directories come first. This is useful when |
|
|
486 | you need to quickly find directories, or you want to find all |
|
|
487 | directories while avoiding to stat() each entry. |
|
|
488 | |
|
|
489 | If the system returns type information in readdir, then this is |
|
|
490 | used to find directories directly. Otherwise, likely directories |
|
|
491 | are files beginning with ".", or otherwise files with no dots, |
|
|
492 | of which files with short names are tried first. |
|
|
493 | |
|
|
494 | IO::AIO::READDIR_STAT_ORDER |
|
|
495 | When this flag is set, then the names will be returned in an |
|
|
496 | order suitable for stat()'ing each one. That is, when you plan |
|
|
497 | to stat() all files in the given directory, then the returned |
|
|
498 | order will likely be fastest. |
|
|
499 | |
|
|
500 | If both this flag and "IO::AIO::READDIR_DIRS_FIRST" are |
|
|
501 | specified, then the likely dirs come first, resulting in a less |
|
|
502 | optimal stat order. |
|
|
503 | |
|
|
504 | IO::AIO::READDIR_FOUND_UNKNOWN |
|
|
505 | This flag should not be set when calling "aio_readdirx". |
|
|
506 | Instead, it is being set by "aio_readdirx", when any of the |
|
|
507 | $type's found were "IO::AIO::DT_UNKNOWN". The absense of this |
|
|
508 | flag therefore indicates that all $type's are known, which can |
|
|
509 | be used to speed up some algorithms. |
396 | |
510 | |
397 | aio_load $path, $data, $callback->($status) |
511 | aio_load $path, $data, $callback->($status) |
398 | This is a composite request that tries to fully load the given file |
512 | This is a composite request that tries to fully load the given file |
399 | into memory. Status is the same as with aio_read. |
513 | into memory. Status is the same as with aio_read. |
400 | |
514 | |
401 | aio_copy $srcpath, $dstpath, $callback->($status) |
515 | aio_copy $srcpath, $dstpath, $callback->($status) |
402 | Try to copy the *file* (directories not supported as either source |
516 | Try to copy the *file* (directories not supported as either source |
403 | or destination) from $srcpath to $dstpath and call the callback with |
517 | or destination) from $srcpath to $dstpath and call the callback with |
404 | the 0 (error) or -1 ok. |
518 | a status of 0 (ok) or -1 (error, see $!). |
405 | |
519 | |
406 | This is a composite request that it creates the destination file |
520 | This is a composite request that creates the destination file with |
407 | with mode 0200 and copies the contents of the source file into it |
521 | mode 0200 and copies the contents of the source file into it using |
408 | using "aio_sendfile", followed by restoring atime, mtime, access |
522 | "aio_sendfile", followed by restoring atime, mtime, access mode and |
409 | mode and uid/gid, in that order. |
523 | uid/gid, in that order. |
410 | |
524 | |
411 | If an error occurs, the partial destination file will be unlinked, |
525 | If an error occurs, the partial destination file will be unlinked, |
412 | if possible, except when setting atime, mtime, access mode and |
526 | if possible, except when setting atime, mtime, access mode and |
413 | uid/gid, where errors are being ignored. |
527 | uid/gid, where errors are being ignored. |
414 | |
528 | |
415 | aio_move $srcpath, $dstpath, $callback->($status) |
529 | aio_move $srcpath, $dstpath, $callback->($status) |
416 | Try to move the *file* (directories not supported as either source |
530 | Try to move the *file* (directories not supported as either source |
417 | or destination) from $srcpath to $dstpath and call the callback with |
531 | or destination) from $srcpath to $dstpath and call the callback with |
418 | the 0 (error) or -1 ok. |
532 | a status of 0 (ok) or -1 (error, see $!). |
419 | |
533 | |
420 | This is a composite request that tries to rename(2) the file first. |
534 | This is a composite request that tries to rename(2) the file first; |
421 | If rename files with "EXDEV", it copies the file with "aio_copy" |
535 | if rename fails with "EXDEV", it copies the file with "aio_copy" |
422 | and, if that is successful, unlinking the $srcpath. |
536 | and, if that is successful, unlinks the $srcpath. |
423 | |
537 | |
424 | aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
538 | aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
425 | Scans a directory (similar to "aio_readdir") but additionally tries |
539 | Scans a directory (similar to "aio_readdir") but additionally tries |
426 | to efficiently separate the entries of directory $path into two sets |
540 | to efficiently separate the entries of directory $path into two sets |
427 | of names, directories you can recurse into (directories), and ones |
541 | of names, directories you can recurse into (directories), and ones |
… | |
… | |
447 | Implementation notes. |
561 | Implementation notes. |
448 | |
562 | |
449 | The "aio_readdir" cannot be avoided, but "stat()"'ing every entry |
563 | The "aio_readdir" cannot be avoided, but "stat()"'ing every entry |
450 | can. |
564 | can. |
451 | |
565 | |
|
|
566 | If readdir returns file type information, then this is used directly |
|
|
567 | to find directories. |
|
|
568 | |
452 | After reading the directory, the modification time, size etc. of the |
569 | Otherwise, after reading the directory, the modification time, size |
453 | directory before and after the readdir is checked, and if they match |
570 | etc. of the directory before and after the readdir is checked, and |
454 | (and isn't the current time), the link count will be used to decide |
571 | if they match (and isn't the current time), the link count will be |
455 | how many entries are directories (if >= 2). Otherwise, no knowledge |
572 | used to decide how many entries are directories (if >= 2). |
456 | of the number of subdirectories will be assumed. |
573 | Otherwise, no knowledge of the number of subdirectories will be |
|
|
574 | assumed. |
457 | |
575 | |
458 | Then entries will be sorted into likely directories (everything |
576 | Then entries will be sorted into likely directories a non-initial |
459 | without a non-initial dot currently) and likely non-directories |
577 | dot currently) and likely non-directories (see "aio_readdirx"). Then |
460 | (everything else). Then every entry plus an appended "/." will be |
578 | every entry plus an appended "/." will be "stat"'ed, likely |
461 | "stat"'ed, likely directories first. If that succeeds, it assumes |
579 | directories first, in order of their inode numbers. If that |
462 | that the entry is a directory or a symlink to directory (which will |
580 | succeeds, it assumes that the entry is a directory or a symlink to |
463 | be checked seperately). This is often faster than stat'ing the entry |
581 | directory (which will be checked seperately). This is often faster |
464 | itself because filesystems might detect the type of the entry |
582 | than stat'ing the entry itself because filesystems might detect the |
465 | without reading the inode data (e.g. ext2fs filetype feature). |
583 | type of the entry without reading the inode data (e.g. ext2fs |
|
|
584 | filetype feature), even on systems that cannot return the filetype |
|
|
585 | information on readdir. |
466 | |
586 | |
467 | If the known number of directories (link count - 2) has been |
587 | If the known number of directories (link count - 2) has been |
468 | reached, the rest of the entries is assumed to be non-directories. |
588 | reached, the rest of the entries is assumed to be non-directories. |
469 | |
589 | |
470 | This only works with certainty on POSIX (= UNIX) filesystems, which |
590 | This only works with certainty on POSIX (= UNIX) filesystems, which |
… | |
… | |
478 | Delete a directory tree starting (and including) $path, return the |
598 | Delete a directory tree starting (and including) $path, return the |
479 | status of the final "rmdir" only. This is a composite request that |
599 | status of the final "rmdir" only. This is a composite request that |
480 | uses "aio_scandir" to recurse into and rmdir directories, and unlink |
600 | uses "aio_scandir" to recurse into and rmdir directories, and unlink |
481 | everything else. |
601 | everything else. |
482 | |
602 | |
|
|
603 | aio_sync $callback->($status) |
|
|
604 | Asynchronously call sync and call the callback when finished. |
|
|
605 | |
483 | aio_fsync $fh, $callback->($status) |
606 | aio_fsync $fh, $callback->($status) |
484 | Asynchronously call fsync on the given filehandle and call the |
607 | Asynchronously call fsync on the given filehandle and call the |
485 | callback with the fsync result code. |
608 | callback with the fsync result code. |
486 | |
609 | |
487 | aio_fdatasync $fh, $callback->($status) |
610 | aio_fdatasync $fh, $callback->($status) |
488 | Asynchronously call fdatasync on the given filehandle and call the |
611 | Asynchronously call fdatasync on the given filehandle and call the |
489 | callback with the fdatasync result code. |
612 | callback with the fdatasync result code. |
490 | |
613 | |
491 | If this call isn't available because your OS lacks it or it couldn't |
614 | If this call isn't available because your OS lacks it or it couldn't |
492 | be detected, it will be emulated by calling "fsync" instead. |
615 | be detected, it will be emulated by calling "fsync" instead. |
|
|
616 | |
|
|
617 | aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
|
|
618 | Sync the data portion of the file specified by $offset and $length |
|
|
619 | to disk (but NOT the metadata), by calling the Linux-specific |
|
|
620 | sync_file_range call. If sync_file_range is not available or it |
|
|
621 | returns ENOSYS, then fdatasync or fsync is being substituted. |
|
|
622 | |
|
|
623 | $flags can be a combination of |
|
|
624 | "IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE", |
|
|
625 | "IO::AIO::SYNC_FILE_RANGE_WRITE" and |
|
|
626 | "IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER": refer to the sync_file_range |
|
|
627 | manpage for details. |
|
|
628 | |
|
|
629 | aio_pathsync $path, $callback->($status) |
|
|
630 | This request tries to open, fsync and close the given path. This is |
|
|
631 | a composite request intended to sync directories after directory |
|
|
632 | operations (E.g. rename). This might not work on all operating |
|
|
633 | systems or have any specific effect, but usually it makes sure that |
|
|
634 | directory changes get written to disc. It works for anything that |
|
|
635 | can be opened for read-only, not just directories. |
|
|
636 | |
|
|
637 | Future versions of this function might fall back to other methods |
|
|
638 | when "fsync" on the directory fails (such as calling "sync"). |
|
|
639 | |
|
|
640 | Passes 0 when everything went ok, and -1 on error. |
|
|
641 | |
|
|
642 | aio_msync $scalar, $offset = 0, $length = undef, flags = 0, |
|
|
643 | $callback->($status) |
|
|
644 | This is a rather advanced IO::AIO call, which only works on |
|
|
645 | mmap(2)ed scalars (see the Sys::Mmap or Mmap modules for details on |
|
|
646 | this, note that the scalar must only be modified in-place while an |
|
|
647 | aio operation is pending on it). |
|
|
648 | |
|
|
649 | It calls the "msync" function of your OS, if available, with the |
|
|
650 | memory area starting at $offset in the string and ending $length |
|
|
651 | bytes later. If $length is negative, counts from the end, and if |
|
|
652 | $length is "undef", then it goes till the end of the string. The |
|
|
653 | flags can be a combination of "IO::AIO::MS_ASYNC", |
|
|
654 | "IO::AIO::MS_INVALIDATE" and "IO::AIO::MS_SYNC". |
|
|
655 | |
|
|
656 | aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, |
|
|
657 | $callback->($status) |
|
|
658 | This is a rather advanced IO::AIO call, which works best on |
|
|
659 | mmap(2)ed scalars. |
|
|
660 | |
|
|
661 | It touches (reads or writes) all memory pages in the specified range |
|
|
662 | inside the scalar. All caveats and parameters are the same as for |
|
|
663 | "aio_msync", above, except for flags, which must be either 0 (which |
|
|
664 | reads all pages and ensures they are instantiated) or |
|
|
665 | "IO::AIO::MT_MODIFY", which modifies the memory page s(by reading |
|
|
666 | and writing an octet from it, which dirties the page). |
493 | |
667 | |
494 | aio_group $callback->(...) |
668 | aio_group $callback->(...) |
495 | This is a very special aio request: Instead of doing something, it |
669 | This is a very special aio request: Instead of doing something, it |
496 | is a container for other aio requests, which is useful if you want |
670 | is a container for other aio requests, which is useful if you want |
497 | to bundle many requests into a single, composite, request with a |
671 | to bundle many requests into a single, composite, request with a |
… | |
… | |
540 | |
714 | |
541 | cancel $req |
715 | cancel $req |
542 | Cancels the request, if possible. Has the effect of skipping |
716 | Cancels the request, if possible. Has the effect of skipping |
543 | execution when entering the execute state and skipping calling the |
717 | execution when entering the execute state and skipping calling the |
544 | callback when entering the the result state, but will leave the |
718 | callback when entering the the result state, but will leave the |
545 | request otherwise untouched. That means that requests that currently |
719 | request otherwise untouched (with the exception of readdir). That |
546 | execute will not be stopped and resources held by the request will |
720 | means that requests that currently execute will not be stopped and |
547 | not be freed prematurely. |
721 | resources held by the request will not be freed prematurely. |
548 | |
722 | |
549 | cb $req $callback->(...) |
723 | cb $req $callback->(...) |
550 | Replace (or simply set) the callback registered to the request. |
724 | Replace (or simply set) the callback registered to the request. |
551 | |
725 | |
552 | IO::AIO::GRP CLASS |
726 | IO::AIO::GRP CLASS |
… | |
… | |
579 | }; |
753 | }; |
580 | |
754 | |
581 | This makes it very easy to create composite requests (see the source of |
755 | This makes it very easy to create composite requests (see the source of |
582 | "aio_move" for an application) that work and feel like simple requests. |
756 | "aio_move" for an application) that work and feel like simple requests. |
583 | |
757 | |
584 | * The IO::AIO::GRP objects will be cleaned up during calls to |
758 | * The IO::AIO::GRP objects will be cleaned up during calls to |
585 | "IO::AIO::poll_cb", just like any other request. |
759 | "IO::AIO::poll_cb", just like any other request. |
|
|
760 | |
586 | * They can be canceled like any other request. Canceling will cancel not |
761 | * They can be canceled like any other request. Canceling will cancel |
587 | only the request itself, but also all requests it contains. |
762 | not only the request itself, but also all requests it contains. |
|
|
763 | |
588 | * They can also can also be added to other IO::AIO::GRP objects. |
764 | * They can also can also be added to other IO::AIO::GRP objects. |
|
|
765 | |
589 | * You must not add requests to a group from within the group callback |
766 | * You must not add requests to a group from within the group callback |
590 | (or any later time). |
767 | (or any later time). |
591 | |
768 | |
592 | Their lifetime, simplified, looks like this: when they are empty, they |
769 | Their lifetime, simplified, looks like this: when they are empty, they |
593 | will finish very quickly. If they contain only requests that are in the |
770 | will finish very quickly. If they contain only requests that are in the |
594 | "done" state, they will also finish. Otherwise they will continue to |
771 | "done" state, they will also finish. Otherwise they will continue to |
595 | exist. |
772 | exist. |
596 | |
773 | |
597 | That means after creating a group you have some time to add requests. |
774 | That means after creating a group you have some time to add requests |
598 | And in the callbacks of those requests, you can add further requests to |
775 | (precisely before the callback has been invoked, which is only done |
599 | the group. And only when all those requests have finished will the the |
776 | within the "poll_cb"). And in the callbacks of those requests, you can |
600 | group itself finish. |
777 | add further requests to the group. And only when all those requests have |
|
|
778 | finished will the the group itself finish. |
601 | |
779 | |
602 | add $grp ... |
780 | add $grp ... |
603 | $grp->add (...) |
781 | $grp->add (...) |
604 | Add one or more requests to the group. Any type of IO::AIO::REQ can |
782 | Add one or more requests to the group. Any type of IO::AIO::REQ can |
605 | be added, including other groups, as long as you do not create |
783 | be added, including other groups, as long as you do not create |
… | |
… | |
610 | $grp->cancel_subs |
788 | $grp->cancel_subs |
611 | Cancel all subrequests and clears any feeder, but not the group |
789 | Cancel all subrequests and clears any feeder, but not the group |
612 | request itself. Useful when you queued a lot of events but got a |
790 | request itself. Useful when you queued a lot of events but got a |
613 | result early. |
791 | result early. |
614 | |
792 | |
|
|
793 | The group request will finish normally (you cannot add requests to |
|
|
794 | the group). |
|
|
795 | |
615 | $grp->result (...) |
796 | $grp->result (...) |
616 | Set the result value(s) that will be passed to the group callback |
797 | Set the result value(s) that will be passed to the group callback |
617 | when all subrequests have finished and set thre groups errno to the |
798 | when all subrequests have finished and set the groups errno to the |
618 | current value of errno (just like calling "errno" without an error |
799 | current value of errno (just like calling "errno" without an error |
619 | number). By default, no argument will be passed and errno is zero. |
800 | number). By default, no argument will be passed and errno is zero. |
620 | |
801 | |
621 | $grp->errno ([$errno]) |
802 | $grp->errno ([$errno]) |
622 | Sets the group errno value to $errno, or the current value of errno |
803 | Sets the group errno value to $errno, or the current value of errno |
… | |
… | |
648 | does not impose any limits). |
829 | does not impose any limits). |
649 | |
830 | |
650 | If the feed does not queue more requests when called, it will be |
831 | If the feed does not queue more requests when called, it will be |
651 | automatically removed from the group. |
832 | automatically removed from the group. |
652 | |
833 | |
653 | If the feed limit is 0, it will be set to 2 automatically. |
834 | If the feed limit is 0 when this method is called, it will be set to |
|
|
835 | 2 automatically. |
654 | |
836 | |
655 | Example: |
837 | Example: |
656 | |
838 | |
657 | # stat all files in @files, but only ever use four aio requests concurrently: |
839 | # stat all files in @files, but only ever use four aio requests concurrently: |
658 | |
840 | |
… | |
… | |
669 | Sets the feeder limit for the group: The feeder will be called |
851 | Sets the feeder limit for the group: The feeder will be called |
670 | whenever the group contains less than this many requests. |
852 | whenever the group contains less than this many requests. |
671 | |
853 | |
672 | Setting the limit to 0 will pause the feeding process. |
854 | Setting the limit to 0 will pause the feeding process. |
673 | |
855 | |
|
|
856 | The default value for the limit is 0, but note that setting a feeder |
|
|
857 | automatically bumps it up to 2. |
|
|
858 | |
674 | SUPPORT FUNCTIONS |
859 | SUPPORT FUNCTIONS |
675 | EVENT PROCESSING AND EVENT LOOP INTEGRATION |
860 | EVENT PROCESSING AND EVENT LOOP INTEGRATION |
676 | $fileno = IO::AIO::poll_fileno |
861 | $fileno = IO::AIO::poll_fileno |
677 | Return the *request result pipe file descriptor*. This filehandle |
862 | Return the *request result pipe file descriptor*. This filehandle |
678 | must be polled for reading by some mechanism outside this module |
863 | must be polled for reading by some mechanism outside this module |
679 | (e.g. Event or select, see below or the SYNOPSIS). If the pipe |
864 | (e.g. EV, Glib, select and so on, see below or the SYNOPSIS). If the |
680 | becomes readable you have to call "poll_cb" to check the results. |
865 | pipe becomes readable you have to call "poll_cb" to check the |
|
|
866 | results. |
681 | |
867 | |
682 | See "poll_cb" for an example. |
868 | See "poll_cb" for an example. |
683 | |
869 | |
684 | IO::AIO::poll_cb |
870 | IO::AIO::poll_cb |
685 | Process some outstanding events on the result pipe. You have to call |
871 | Process some outstanding events on the result pipe. You have to call |
686 | this regularly. Returns the number of events processed. Returns |
872 | this regularly. Returns 0 if all events could be processed, or -1 if |
687 | immediately when no events are outstanding. The amount of events |
873 | it returned earlier for whatever reason. Returns immediately when no |
|
|
874 | events are outstanding. The amount of events processed depends on |
688 | processed depends on the settings of "IO::AIO::max_poll_req" and |
875 | the settings of "IO::AIO::max_poll_req" and |
689 | "IO::AIO::max_poll_time". |
876 | "IO::AIO::max_poll_time". |
690 | |
877 | |
691 | If not all requests were processed for whatever reason, the |
878 | If not all requests were processed for whatever reason, the |
692 | filehandle will still be ready when "poll_cb" returns. |
879 | filehandle will still be ready when "poll_cb" returns, so normally |
|
|
880 | you don't have to do anything special to have it called later. |
693 | |
881 | |
694 | Example: Install an Event watcher that automatically calls |
882 | Example: Install an Event watcher that automatically calls |
695 | IO::AIO::poll_cb with high priority: |
883 | IO::AIO::poll_cb with high priority (more examples can be found in |
|
|
884 | the SYNOPSIS section, at the top of this document): |
696 | |
885 | |
697 | Event->io (fd => IO::AIO::poll_fileno, |
886 | Event->io (fd => IO::AIO::poll_fileno, |
698 | poll => 'r', async => 1, |
887 | poll => 'r', async => 1, |
699 | cb => \&IO::AIO::poll_cb); |
888 | cb => \&IO::AIO::poll_cb); |
700 | |
889 | |
… | |
… | |
803 | |
992 | |
804 | The default is probably ok in most situations, especially if thread |
993 | The default is probably ok in most situations, especially if thread |
805 | creation is fast. If thread creation is very slow on your system you |
994 | creation is fast. If thread creation is very slow on your system you |
806 | might want to use larger values. |
995 | might want to use larger values. |
807 | |
996 | |
808 | $oldmaxreqs = IO::AIO::max_outstanding $maxreqs |
997 | IO::AIO::max_outstanding $maxreqs |
809 | This is a very bad function to use in interactive programs because |
998 | This is a very bad function to use in interactive programs because |
810 | it blocks, and a bad way to reduce concurrency because it is |
999 | it blocks, and a bad way to reduce concurrency because it is |
811 | inexact: Better use an "aio_group" together with a feed callback. |
1000 | inexact: Better use an "aio_group" together with a feed callback. |
812 | |
1001 | |
813 | Sets the maximum number of outstanding requests to $nreqs. If you to |
1002 | Sets the maximum number of outstanding requests to $nreqs. If you do |
814 | queue up more than this number of requests, the next call to the |
1003 | queue up more than this number of requests, the next call to the |
815 | "poll_cb" (and "poll_some" and other functions calling "poll_cb") |
1004 | "poll_cb" (and "poll_some" and other functions calling "poll_cb") |
816 | function will block until the limit is no longer exceeded. |
1005 | function will block until the limit is no longer exceeded. |
817 | |
1006 | |
818 | The default value is very large, so there is no practical limit on |
1007 | The default value is very large, so there is no practical limit on |
819 | the number of outstanding requests. |
1008 | the number of outstanding requests. |
820 | |
1009 | |
821 | You can still queue as many requests as you want. Therefore, |
1010 | You can still queue as many requests as you want. Therefore, |
822 | "max_oustsanding" is mainly useful in simple scripts (with low |
1011 | "max_outstanding" is mainly useful in simple scripts (with low |
823 | values) or as a stop gap to shield against fatal memory overflow |
1012 | values) or as a stop gap to shield against fatal memory overflow |
824 | (with large values). |
1013 | (with large values). |
825 | |
1014 | |
826 | STATISTICAL INFORMATION |
1015 | STATISTICAL INFORMATION |
827 | IO::AIO::nreqs |
1016 | IO::AIO::nreqs |
… | |
… | |
839 | executed). |
1028 | executed). |
840 | |
1029 | |
841 | IO::AIO::npending |
1030 | IO::AIO::npending |
842 | Returns the number of requests currently in the pending state |
1031 | Returns the number of requests currently in the pending state |
843 | (executed, but not yet processed by poll_cb). |
1032 | (executed, but not yet processed by poll_cb). |
|
|
1033 | |
|
|
1034 | MISCELLANEOUS FUNCTIONS |
|
|
1035 | IO::AIO implements some functions that might be useful, but are not |
|
|
1036 | asynchronous. |
|
|
1037 | |
|
|
1038 | IO::AIO::sendfile $ofh, $ifh, $offset, $count |
|
|
1039 | Calls the "eio_sendfile_sync" function, which is like |
|
|
1040 | "aio_sendfile", but is blocking (this makes most sense if you know |
|
|
1041 | the input data is likely cached already and the output filehandle is |
|
|
1042 | set to non-blocking operations). |
|
|
1043 | |
|
|
1044 | Returns the number of bytes copied, or -1 on error. |
|
|
1045 | |
|
|
1046 | IO::AIO::fadvise $fh, $offset, $len, $advice |
|
|
1047 | Simply calls the "posix_fadvise" function (see it's manpage for |
|
|
1048 | details). The following advice constants are avaiable: |
|
|
1049 | "IO::AIO::FADV_NORMAL", "IO::AIO::FADV_SEQUENTIAL", |
|
|
1050 | "IO::AIO::FADV_RANDOM", "IO::AIO::FADV_NOREUSE", |
|
|
1051 | "IO::AIO::FADV_WILLNEED", "IO::AIO::FADV_DONTNEED". |
|
|
1052 | |
|
|
1053 | On systems that do not implement "posix_fadvise", this function |
|
|
1054 | returns ENOSYS, otherwise the return value of "posix_fadvise". |
844 | |
1055 | |
845 | FORK BEHAVIOUR |
1056 | FORK BEHAVIOUR |
846 | This module should do "the right thing" when the process using it forks: |
1057 | This module should do "the right thing" when the process using it forks: |
847 | |
1058 | |
848 | Before the fork, IO::AIO enters a quiescent state where no requests can |
1059 | Before the fork, IO::AIO enters a quiescent state where no requests can |
… | |
… | |
864 | bytes of memory. In addition, stat requests need a stat buffer (possibly |
1075 | bytes of memory. In addition, stat requests need a stat buffer (possibly |
865 | a few hundred bytes), readdir requires a result buffer and so on. Perl |
1076 | a few hundred bytes), readdir requires a result buffer and so on. Perl |
866 | scalars and other data passed into aio requests will also be locked and |
1077 | scalars and other data passed into aio requests will also be locked and |
867 | will consume memory till the request has entered the done state. |
1078 | will consume memory till the request has entered the done state. |
868 | |
1079 | |
869 | This is now awfully much, so queuing lots of requests is not usually a |
1080 | This is not awfully much, so queuing lots of requests is not usually a |
870 | problem. |
1081 | problem. |
871 | |
1082 | |
872 | Per-thread usage: |
1083 | Per-thread usage: |
873 | |
1084 | |
874 | In the execution phase, some aio requests require more memory for |
1085 | In the execution phase, some aio requests require more memory for |
… | |
… | |
877 | |
1088 | |
878 | KNOWN BUGS |
1089 | KNOWN BUGS |
879 | Known bugs will be fixed in the next release. |
1090 | Known bugs will be fixed in the next release. |
880 | |
1091 | |
881 | SEE ALSO |
1092 | SEE ALSO |
882 | Coro::AIO. |
1093 | AnyEvent::AIO for easy integration into event loops, Coro::AIO for a |
|
|
1094 | more natural syntax. |
883 | |
1095 | |
884 | AUTHOR |
1096 | AUTHOR |
885 | Marc Lehmann <schmorp@schmorp.de> |
1097 | Marc Lehmann <schmorp@schmorp.de> |
886 | http://home.schmorp.de/ |
1098 | http://home.schmorp.de/ |
887 | |
1099 | |