… | |
… | |
204 | IO::AIO::max_poll_reqs $nreqs |
204 | IO::AIO::max_poll_reqs $nreqs |
205 | IO::AIO::max_poll_time $seconds |
205 | IO::AIO::max_poll_time $seconds |
206 | IO::AIO::min_parallel $nthreads |
206 | IO::AIO::min_parallel $nthreads |
207 | IO::AIO::max_parallel $nthreads |
207 | IO::AIO::max_parallel $nthreads |
208 | IO::AIO::max_idle $nthreads |
208 | IO::AIO::max_idle $nthreads |
|
|
209 | IO::AIO::idle_timeout $seconds |
209 | IO::AIO::max_outstanding $maxreqs |
210 | IO::AIO::max_outstanding $maxreqs |
210 | IO::AIO::nreqs |
211 | IO::AIO::nreqs |
211 | IO::AIO::nready |
212 | IO::AIO::nready |
212 | IO::AIO::npending |
213 | IO::AIO::npending |
213 | |
214 | |
… | |
… | |
305 | } else { |
306 | } else { |
306 | die "open failed: $!\n"; |
307 | die "open failed: $!\n"; |
307 | } |
308 | } |
308 | }; |
309 | }; |
309 | |
310 | |
|
|
311 | In addition to all the common open modes/flags ("O_RDONLY", |
|
|
312 | "O_WRONLY", "O_RDWR", "O_CREAT", "O_TRUNC", "O_EXCL" and |
|
|
313 | "O_APPEND"), the following POSIX and non-POSIX constants are |
|
|
314 | available (missing ones on your system are, as usual, 0): |
|
|
315 | |
|
|
316 | "O_ASYNC", "O_DIRECT", "O_NOATIME", "O_CLOEXEC", "O_NOCTTY", |
|
|
317 | "O_NOFOLLOW", "O_NONBLOCK", "O_EXEC", "O_SEARCH", "O_DIRECTORY", |
|
|
318 | "O_DSYNC", "O_RSYNC", "O_SYNC" and "O_TTY_INIT". |
|
|
319 | |
310 | aio_close $fh, $callback->($status) |
320 | aio_close $fh, $callback->($status) |
311 | Asynchronously close a file and call the callback with the result |
321 | Asynchronously close a file and call the callback with the result |
312 | code. |
322 | code. |
313 | |
323 | |
314 | Unfortunately, you can't do this to perl. Perl *insists* very |
324 | Unfortunately, you can't do this to perl. Perl *insists* very |
… | |
… | |
357 | aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
367 | aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
358 | Tries to copy $length bytes from $in_fh to $out_fh. It starts |
368 | Tries to copy $length bytes from $in_fh to $out_fh. It starts |
359 | reading at byte offset $in_offset, and starts writing at the current |
369 | reading at byte offset $in_offset, and starts writing at the current |
360 | file offset of $out_fh. Because of that, it is not safe to issue |
370 | file offset of $out_fh. Because of that, it is not safe to issue |
361 | more than one "aio_sendfile" per $out_fh, as they will interfere |
371 | more than one "aio_sendfile" per $out_fh, as they will interfere |
362 | with each other. |
372 | with each other. The same $in_fh works fine though, as this function |
|
|
373 | does not move or use the file offset of $in_fh. |
363 | |
374 | |
364 | Please note that "aio_sendfile" can read more bytes from $in_fh than |
375 | Please note that "aio_sendfile" can read more bytes from $in_fh than |
365 | are written, and there is no way to find out how many bytes have |
376 | are written, and there is no way to find out how many more bytes |
366 | been read from "aio_sendfile" alone, as "aio_sendfile" only provides |
377 | have been read from "aio_sendfile" alone, as "aio_sendfile" only |
367 | the number of bytes written to $out_fh. Only if the result value |
378 | provides the number of bytes written to $out_fh. Only if the result |
368 | equals $length one can assume that $length bytes have been read. |
379 | value equals $length one can assume that $length bytes have been |
|
|
380 | read. |
369 | |
381 | |
370 | Unlike with other "aio_" functions, it makes a lot of sense to use |
382 | Unlike with other "aio_" functions, it makes a lot of sense to use |
371 | "aio_sendfile" on non-blocking sockets, as long as one end |
383 | "aio_sendfile" on non-blocking sockets, as long as one end |
372 | (typically the $in_fh) is a file - the file I/O will then be |
384 | (typically the $in_fh) is a file - the file I/O will then be |
373 | asynchronous, while the socket I/O will be non-blocking. Note, |
385 | asynchronous, while the socket I/O will be non-blocking. Note, |
374 | however, that you can run into a trap where "aio_sendfile" reads |
386 | however, that you can run into a trap where "aio_sendfile" reads |
375 | some data with readahead, then fails to write all data, and when the |
387 | some data with readahead, then fails to write all data, and when the |
376 | socket is ready the next time, the data in the cache is already |
388 | socket is ready the next time, the data in the cache is already |
377 | lost, forcing "aio_sendfile" to again hit the disk. Explicit |
389 | lost, forcing "aio_sendfile" to again hit the disk. Explicit |
378 | "aio_read" + "aio_write" let's you control resource usage much |
390 | "aio_read" + "aio_write" let's you better control resource usage. |
379 | better. |
|
|
380 | |
391 | |
381 | This call tries to make use of a native "sendfile" syscall to |
392 | This call tries to make use of a native "sendfile"-like syscall to |
382 | provide zero-copy operation. For this to work, $out_fh should refer |
393 | provide zero-copy operation. For this to work, $out_fh should refer |
383 | to a socket, and $in_fh should refer to an mmap'able file. |
394 | to a socket, and $in_fh should refer to an mmap'able file. |
384 | |
395 | |
385 | If a native sendfile cannot be found or it fails with "ENOSYS", |
396 | If a native sendfile cannot be found or it fails with "ENOSYS", |
386 | "ENOTSUP", "EOPNOTSUPP", "EAFNOSUPPORT", "EPROTOTYPE" or "ENOTSOCK", |
397 | "EINVAL", "ENOTSUP", "EOPNOTSUPP", "EAFNOSUPPORT", "EPROTOTYPE" or |
387 | it will be emulated, so you can call "aio_sendfile" on any type of |
398 | "ENOTSOCK", it will be emulated, so you can call "aio_sendfile" on |
388 | filehandle regardless of the limitations of the operating system. |
399 | any type of filehandle regardless of the limitations of the |
|
|
400 | operating system. |
|
|
401 | |
|
|
402 | As native sendfile syscalls (as practically any non-POSIX interface |
|
|
403 | hacked together in a hurry to improve benchmark numbers) tend to be |
|
|
404 | rather buggy on many systems, this implementation tries to work |
|
|
405 | around some known bugs in Linux and FreeBSD kernels (probably |
|
|
406 | others, too), but that might fail, so you really really should check |
|
|
407 | the return value of "aio_sendfile" - fewre bytes than expected might |
|
|
408 | have been transferred. |
389 | |
409 | |
390 | aio_readahead $fh,$offset,$length, $callback->($retval) |
410 | aio_readahead $fh,$offset,$length, $callback->($retval) |
391 | "aio_readahead" populates the page cache with data from a file so |
411 | "aio_readahead" populates the page cache with data from a file so |
392 | that subsequent reads from that file will not block on disk I/O. The |
412 | that subsequent reads from that file will not block on disk I/O. The |
393 | $offset argument specifies the starting point from which data is to |
413 | $offset argument specifies the starting point from which data is to |
… | |
… | |
413 | |
433 | |
414 | Currently, the stats are always 64-bit-stats, i.e. instead of |
434 | Currently, the stats are always 64-bit-stats, i.e. instead of |
415 | returning an error when stat'ing a large file, the results will be |
435 | returning an error when stat'ing a large file, the results will be |
416 | silently truncated unless perl itself is compiled with large file |
436 | silently truncated unless perl itself is compiled with large file |
417 | support. |
437 | support. |
|
|
438 | |
|
|
439 | To help interpret the mode and dev/rdev stat values, IO::AIO offers |
|
|
440 | the following constants and functions (if not implemented, the |
|
|
441 | constants will be 0 and the functions will either "croak" or fall |
|
|
442 | back on traditional behaviour). |
|
|
443 | |
|
|
444 | "S_IFMT", "S_IFIFO", "S_IFCHR", "S_IFBLK", "S_IFLNK", "S_IFREG", |
|
|
445 | "S_IFDIR", "S_IFWHT", "S_IFSOCK", "IO::AIO::major $dev_t", |
|
|
446 | "IO::AIO::minor $dev_t", "IO::AIO::makedev $major, $minor". |
418 | |
447 | |
419 | Example: Print the length of /etc/passwd: |
448 | Example: Print the length of /etc/passwd: |
420 | |
449 | |
421 | aio_stat "/etc/passwd", sub { |
450 | aio_stat "/etc/passwd", sub { |
422 | $_[0] and die "stat failed: $!"; |
451 | $_[0] and die "stat failed: $!"; |
… | |
… | |
511 | |
540 | |
512 | The only (POSIX-) portable way of calling this function is: |
541 | The only (POSIX-) portable way of calling this function is: |
513 | |
542 | |
514 | aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
543 | aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
515 | |
544 | |
|
|
545 | See "aio_stat" for info about some potentially helpful extra |
|
|
546 | constants and functions. |
|
|
547 | |
516 | aio_link $srcpath, $dstpath, $callback->($status) |
548 | aio_link $srcpath, $dstpath, $callback->($status) |
517 | Asynchronously create a new link to the existing object at $srcpath |
549 | Asynchronously create a new link to the existing object at $srcpath |
518 | at the path $dstpath and call the callback with the result code. |
550 | at the path $dstpath and call the callback with the result code. |
519 | |
551 | |
520 | aio_symlink $srcpath, $dstpath, $callback->($status) |
552 | aio_symlink $srcpath, $dstpath, $callback->($status) |
… | |
… | |
556 | The flags are a combination of the following constants, ORed |
588 | The flags are a combination of the following constants, ORed |
557 | together (the flags will also be passed to the callback, possibly |
589 | together (the flags will also be passed to the callback, possibly |
558 | modified): |
590 | modified): |
559 | |
591 | |
560 | IO::AIO::READDIR_DENTS |
592 | IO::AIO::READDIR_DENTS |
561 | When this flag is off, then the callback gets an arrayref with |
593 | When this flag is off, then the callback gets an arrayref |
562 | of names only (as with "aio_readdir"), otherwise it gets an |
594 | consisting of names only (as with "aio_readdir"), otherwise it |
563 | arrayref with "[$name, $type, $inode]" arrayrefs, each |
595 | gets an arrayref with "[$name, $type, $inode]" arrayrefs, each |
564 | describing a single directory entry in more detail. |
596 | describing a single directory entry in more detail. |
565 | |
597 | |
566 | $name is the name of the entry. |
598 | $name is the name of the entry. |
567 | |
599 | |
568 | $type is one of the "IO::AIO::DT_xxx" constants: |
600 | $type is one of the "IO::AIO::DT_xxx" constants: |
… | |
… | |
581 | unspecified content on systems that do not deliver the inode |
613 | unspecified content on systems that do not deliver the inode |
582 | information. |
614 | information. |
583 | |
615 | |
584 | IO::AIO::READDIR_DIRS_FIRST |
616 | IO::AIO::READDIR_DIRS_FIRST |
585 | When this flag is set, then the names will be returned in an |
617 | When this flag is set, then the names will be returned in an |
586 | order where likely directories come first. This is useful when |
618 | order where likely directories come first, in optimal stat |
587 | you need to quickly find directories, or you want to find all |
619 | order. This is useful when you need to quickly find directories, |
588 | directories while avoiding to stat() each entry. |
620 | or you want to find all directories while avoiding to stat() |
|
|
621 | each entry. |
589 | |
622 | |
590 | If the system returns type information in readdir, then this is |
623 | If the system returns type information in readdir, then this is |
591 | used to find directories directly. Otherwise, likely directories |
624 | used to find directories directly. Otherwise, likely directories |
592 | are files beginning with ".", or otherwise files with no dots, |
625 | are names beginning with ".", or otherwise names with no dots, |
593 | of which files with short names are tried first. |
626 | of which names with short names are tried first. |
594 | |
627 | |
595 | IO::AIO::READDIR_STAT_ORDER |
628 | IO::AIO::READDIR_STAT_ORDER |
596 | When this flag is set, then the names will be returned in an |
629 | When this flag is set, then the names will be returned in an |
597 | order suitable for stat()'ing each one. That is, when you plan |
630 | order suitable for stat()'ing each one. That is, when you plan |
598 | to stat() all files in the given directory, then the returned |
631 | to stat() all files in the given directory, then the returned |
… | |
… | |
1009 | |
1042 | |
1010 | See "poll_cb" for an example. |
1043 | See "poll_cb" for an example. |
1011 | |
1044 | |
1012 | IO::AIO::poll_cb |
1045 | IO::AIO::poll_cb |
1013 | Process some outstanding events on the result pipe. You have to call |
1046 | Process some outstanding events on the result pipe. You have to call |
1014 | this regularly. Returns 0 if all events could be processed, or -1 if |
1047 | this regularly. Returns 0 if all events could be processed (or there |
1015 | it returned earlier for whatever reason. Returns immediately when no |
1048 | were no events to process), or -1 if it returned earlier for |
1016 | events are outstanding. The amount of events processed depends on |
1049 | whatever reason. Returns immediately when no events are outstanding. |
1017 | the settings of "IO::AIO::max_poll_req" and |
1050 | The amount of events processed depends on the settings of |
1018 | "IO::AIO::max_poll_time". |
1051 | "IO::AIO::max_poll_req" and "IO::AIO::max_poll_time". |
1019 | |
1052 | |
1020 | If not all requests were processed for whatever reason, the |
1053 | If not all requests were processed for whatever reason, the |
1021 | filehandle will still be ready when "poll_cb" returns, so normally |
1054 | filehandle will still be ready when "poll_cb" returns, so normally |
1022 | you don't have to do anything special to have it called later. |
1055 | you don't have to do anything special to have it called later. |
|
|
1056 | |
|
|
1057 | Apart from calling "IO::AIO::poll_cb" when the event filehandle |
|
|
1058 | becomes ready, it can be beneficial to call this function from loops |
|
|
1059 | which submit a lot of requests, to make sure the results get |
|
|
1060 | processed when they become available and not just when the loop is |
|
|
1061 | finished and the event loop takes over again. This function returns |
|
|
1062 | very fast when there are no outstanding requests. |
1023 | |
1063 | |
1024 | Example: Install an Event watcher that automatically calls |
1064 | Example: Install an Event watcher that automatically calls |
1025 | IO::AIO::poll_cb with high priority (more examples can be found in |
1065 | IO::AIO::poll_cb with high priority (more examples can be found in |
1026 | the SYNOPSIS section, at the top of this document): |
1066 | the SYNOPSIS section, at the top of this document): |
1027 | |
1067 | |
… | |
… | |
1121 | |
1161 | |
1122 | Under normal circumstances you don't need to call this function. |
1162 | Under normal circumstances you don't need to call this function. |
1123 | |
1163 | |
1124 | IO::AIO::max_idle $nthreads |
1164 | IO::AIO::max_idle $nthreads |
1125 | Limit the number of threads (default: 4) that are allowed to idle |
1165 | Limit the number of threads (default: 4) that are allowed to idle |
1126 | (i.e., threads that did not get a request to process within 10 |
1166 | (i.e., threads that did not get a request to process within the idle |
1127 | seconds). That means if a thread becomes idle while $nthreads other |
1167 | timeout (default: 10 seconds). That means if a thread becomes idle |
1128 | threads are also idle, it will free its resources and exit. |
1168 | while $nthreads other threads are also idle, it will free its |
|
|
1169 | resources and exit. |
1129 | |
1170 | |
1130 | This is useful when you allow a large number of threads (e.g. 100 or |
1171 | This is useful when you allow a large number of threads (e.g. 100 or |
1131 | 1000) to allow for extremely high load situations, but want to free |
1172 | 1000) to allow for extremely high load situations, but want to free |
1132 | resources under normal circumstances (1000 threads can easily |
1173 | resources under normal circumstances (1000 threads can easily |
1133 | consume 30MB of RAM). |
1174 | consume 30MB of RAM). |
1134 | |
1175 | |
1135 | The default is probably ok in most situations, especially if thread |
1176 | The default is probably ok in most situations, especially if thread |
1136 | creation is fast. If thread creation is very slow on your system you |
1177 | creation is fast. If thread creation is very slow on your system you |
1137 | might want to use larger values. |
1178 | might want to use larger values. |
1138 | |
1179 | |
|
|
1180 | IO::AIO::idle_timeout $seconds |
|
|
1181 | Sets the minimum idle timeout (default 10) after which worker |
|
|
1182 | threads are allowed to exit. SEe "IO::AIO::max_idle". |
|
|
1183 | |
1139 | IO::AIO::max_outstanding $maxreqs |
1184 | IO::AIO::max_outstanding $maxreqs |
|
|
1185 | Sets the maximum number of outstanding requests to $nreqs. If you do |
|
|
1186 | queue up more than this number of requests, the next call to |
|
|
1187 | "IO::AIO::poll_cb" (and other functions calling "poll_cb", such as |
|
|
1188 | "IO::AIO::flush" or "IO::AIO::poll") will block until the limit is |
|
|
1189 | no longer exceeded. |
|
|
1190 | |
|
|
1191 | In other words, this setting does not enforce a queue limit, but can |
|
|
1192 | be used to make poll functions block if the limit is exceeded. |
|
|
1193 | |
1140 | This is a very bad function to use in interactive programs because |
1194 | This is a very bad function to use in interactive programs because |
1141 | it blocks, and a bad way to reduce concurrency because it is |
1195 | it blocks, and a bad way to reduce concurrency because it is |
1142 | inexact: Better use an "aio_group" together with a feed callback. |
1196 | inexact: Better use an "aio_group" together with a feed callback. |
1143 | |
1197 | |
1144 | Sets the maximum number of outstanding requests to $nreqs. If you do |
1198 | It's main use is in scripts without an event loop - when you want to |
1145 | queue up more than this number of requests, the next call to the |
1199 | stat a lot of files, you can write somehting like this: |
1146 | "poll_cb" (and "poll_some" and other functions calling "poll_cb") |
|
|
1147 | function will block until the limit is no longer exceeded. |
|
|
1148 | |
1200 | |
1149 | The default value is very large, so there is no practical limit on |
1201 | IO::AIO::max_outstanding 32; |
|
|
1202 | |
|
|
1203 | for my $path (...) { |
|
|
1204 | aio_stat $path , ...; |
|
|
1205 | IO::AIO::poll_cb; |
|
|
1206 | } |
|
|
1207 | |
|
|
1208 | IO::AIO::flush; |
|
|
1209 | |
|
|
1210 | The call to "poll_cb" inside the loop will normally return |
|
|
1211 | instantly, but as soon as more thna 32 reqeusts are in-flight, it |
|
|
1212 | will block until some requests have been handled. This keeps the |
|
|
1213 | loop from pushing a large number of "aio_stat" requests onto the |
|
|
1214 | queue. |
|
|
1215 | |
|
|
1216 | The default value for "max_outstanding" is very large, so there is |
1150 | the number of outstanding requests. |
1217 | no practical limit on the number of outstanding requests. |
1151 | |
|
|
1152 | You can still queue as many requests as you want. Therefore, |
|
|
1153 | "max_outstanding" is mainly useful in simple scripts (with low |
|
|
1154 | values) or as a stop gap to shield against fatal memory overflow |
|
|
1155 | (with large values). |
|
|
1156 | |
1218 | |
1157 | STATISTICAL INFORMATION |
1219 | STATISTICAL INFORMATION |
1158 | IO::AIO::nreqs |
1220 | IO::AIO::nreqs |
1159 | Returns the number of requests currently in the ready, execute or |
1221 | Returns the number of requests currently in the ready, execute or |
1160 | pending states (i.e. for which their callback has not been invoked |
1222 | pending states (i.e. for which their callback has not been invoked |
… | |
… | |
1306 | # Danga::Socket integration |
1368 | # Danga::Socket integration |
1307 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
1369 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
1308 | \&IO::AIO::poll_cb); |
1370 | \&IO::AIO::poll_cb); |
1309 | |
1371 | |
1310 | FORK BEHAVIOUR |
1372 | FORK BEHAVIOUR |
1311 | This module should do "the right thing" when the process using it forks: |
1373 | Usage of pthreads in a program changes the semantics of fork |
|
|
1374 | considerably. Specifically, only async-safe functions can be called |
|
|
1375 | after fork. Perl doesn't know about this, so in general, you cannot call |
|
|
1376 | fork with defined behaviour in perl. IO::AIO uses pthreads, so this |
|
|
1377 | applies, but many other extensions and (for inexplicable reasons) perl |
|
|
1378 | itself often is linked against pthreads, so this limitation applies. |
1312 | |
1379 | |
1313 | Before the fork, IO::AIO enters a quiescent state where no requests can |
1380 | Some operating systems have extensions that allow safe use of fork, and |
1314 | be added in other threads and no results will be processed. After the |
1381 | this module should do "the right thing" on those, and tries on others. |
1315 | fork the parent simply leaves the quiescent state and continues |
1382 | At the time of this writing (2011) only GNU/Linux supports these |
1316 | request/result processing, while the child frees the request/result |
1383 | extensions to POSIX. |
1317 | queue (so that the requests started before the fork will only be handled |
|
|
1318 | in the parent). Threads will be started on demand until the limit set in |
|
|
1319 | the parent process has been reached again. |
|
|
1320 | |
|
|
1321 | In short: the parent will, after a short pause, continue as if fork had |
|
|
1322 | not been called, while the child will act as if IO::AIO has not been |
|
|
1323 | used yet. |
|
|
1324 | |
1384 | |
1325 | MEMORY USAGE |
1385 | MEMORY USAGE |
1326 | Per-request usage: |
1386 | Per-request usage: |
1327 | |
1387 | |
1328 | Each aio request uses - depending on your architecture - around 100-200 |
1388 | Each aio request uses - depending on your architecture - around 100-200 |