--- IO-AIO/README 2010/12/30 07:19:31 1.45 +++ IO-AIO/README 2011/10/09 08:24:49 1.50 @@ -152,6 +152,7 @@ for quick reference. See the following sections for function-by-function documentation. + aio_wd $pathname, $callback->($wd) aio_open $pathname, $flags, $mode, $callback->($fh) aio_close $fh, $callback->($status) aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) @@ -166,10 +167,11 @@ aio_truncate $fh_or_path, $offset, $callback->($status) aio_chmod $fh_or_path, $mode, $callback->($status) aio_unlink $pathname, $callback->($status) - aio_mknod $path, $mode, $dev, $callback->($status) + aio_mknod $pathname, $mode, $dev, $callback->($status) aio_link $srcpath, $dstpath, $callback->($status) aio_symlink $srcpath, $dstpath, $callback->($status) - aio_readlink $path, $callback->($link) + aio_readlink $pathname, $callback->($link) + aio_realpath $pathname, $callback->($link) aio_rename $srcpath, $dstpath, $callback->($status) aio_mkdir $pathname, $mode, $callback->($status) aio_rmdir $pathname, $callback->($status) @@ -177,16 +179,17 @@ aio_readdirx $pathname, $flags, $callback->($entries, $flags) IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN - aio_load $path, $data, $callback->($status) + aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs) + aio_load $pathname, $data, $callback->($status) aio_copy $srcpath, $dstpath, $callback->($status) aio_move $srcpath, $dstpath, $callback->($status) - aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) - aio_rmtree $path, $callback->($status) + aio_rmtree $pathname, $callback->($status) aio_sync $callback->($status) + aio_syncfs $fh, $callback->($status) aio_fsync $fh, $callback->($status) aio_fdatasync $fh, $callback->($status) aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) - aio_pathsync $path, $callback->($status) + aio_pathsync $pathname, $callback->($status) aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status) @@ -206,6 +209,7 @@ IO::AIO::min_parallel $nthreads IO::AIO::max_parallel $nthreads IO::AIO::max_idle $nthreads + IO::AIO::idle_timeout $seconds IO::AIO::max_outstanding $maxreqs IO::AIO::nreqs IO::AIO::nready @@ -222,10 +226,15 @@ All the "aio_*" calls are more or less thin wrappers around the syscall with the same name (sans "aio_"). The arguments are similar or identical, and they all accept an additional (and optional) $callback - argument which must be a code reference. This code reference will get - called with the syscall return code (e.g. most syscalls return -1 on - error, unlike perl, which usually delivers "false") as its sole argument - after the given syscall has been executed asynchronously. + argument which must be a code reference. This code reference will be + called after the syscall has been executed in an asynchronous fashion. + The results of the request will be passed as arguments to the callback + (and, if an error occured, in $!) - for most requests the syscall return + code (e.g. most syscalls return -1 on error, unlike perl, which usually + delivers "false"). + + Some requests (such as "aio_readdir") pass the actual results and + communicate failures by passing "undef". All functions expecting a filehandle keep a copy of the filehandle internally until the request has finished. @@ -233,19 +242,22 @@ All functions return request objects of type IO::AIO::REQ that allow further manipulation of those requests while they are in-flight. - The pathnames you pass to these routines *must* be absolute and encoded - as octets. The reason for the former is that at the time the request is - being executed, the current working directory could have changed. - Alternatively, you can make sure that you never change the current - working directory anywhere in the program and then use relative paths. + The pathnames you pass to these routines *should* be absolute. The + reason for this is that at the time the request is being executed, the + current working directory could have changed. Alternatively, you can + make sure that you never change the current working directory anywhere + in the program and then use relative paths. You can also take advantage + of IO::AIOs working directory abstraction, that lets you specify paths + relative to some previously-opened "working directory object" - see the + description of the "IO::AIO::WD" class later in this document. To encode pathnames as octets, either make sure you either: a) always pass in filenames you got from outside (command line, readdir etc.) - without tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module - and encode your pathnames to the locale (or other) encoding in effect in - the user environment, d) use Glib::filename_from_unicode on unicode - filenames or e) use something else to ensure your scalar has the correct - contents. + without tinkering, b) are in your native filesystem encoding, c) use the + Encode module and encode your pathnames to the locale (or other) + encoding in effect in the user environment, d) use + Glib::filename_from_unicode on unicode filenames or e) use something + else to ensure your scalar has the correct contents. This works, btw. independent of the internal UTF-8 bit, which IO::AIO handles correctly whether it is set or not. @@ -307,6 +319,15 @@ } }; + In addition to all the common open modes/flags ("O_RDONLY", + "O_WRONLY", "O_RDWR", "O_CREAT", "O_TRUNC", "O_EXCL" and + "O_APPEND"), the following POSIX and non-POSIX constants are + available (missing ones on your system are, as usual, 0): + + "O_ASYNC", "O_DIRECT", "O_NOATIME", "O_CLOEXEC", "O_NOCTTY", + "O_NOFOLLOW", "O_NONBLOCK", "O_EXEC", "O_SEARCH", "O_DIRECTORY", + "O_DSYNC", "O_RSYNC", "O_SYNC" and "O_TTY_INIT". + aio_close $fh, $callback->($status) Asynchronously close a file and call the callback with the result code. @@ -359,13 +380,15 @@ reading at byte offset $in_offset, and starts writing at the current file offset of $out_fh. Because of that, it is not safe to issue more than one "aio_sendfile" per $out_fh, as they will interfere - with each other. + with each other. The same $in_fh works fine though, as this function + does not move or use the file offset of $in_fh. Please note that "aio_sendfile" can read more bytes from $in_fh than - are written, and there is no way to find out how many bytes have - been read from "aio_sendfile" alone, as "aio_sendfile" only provides - the number of bytes written to $out_fh. Only if the result value - equals $length one can assume that $length bytes have been read. + are written, and there is no way to find out how many more bytes + have been read from "aio_sendfile" alone, as "aio_sendfile" only + provides the number of bytes written to $out_fh. Only if the result + value equals $length one can assume that $length bytes have been + read. Unlike with other "aio_" functions, it makes a lot of sense to use "aio_sendfile" on non-blocking sockets, as long as one end @@ -375,17 +398,25 @@ some data with readahead, then fails to write all data, and when the socket is ready the next time, the data in the cache is already lost, forcing "aio_sendfile" to again hit the disk. Explicit - "aio_read" + "aio_write" let's you control resource usage much - better. + "aio_read" + "aio_write" let's you better control resource usage. - This call tries to make use of a native "sendfile" syscall to + This call tries to make use of a native "sendfile"-like syscall to provide zero-copy operation. For this to work, $out_fh should refer to a socket, and $in_fh should refer to an mmap'able file. If a native sendfile cannot be found or it fails with "ENOSYS", - "ENOTSUP", "EOPNOTSUPP", "EAFNOSUPPORT", "EPROTOTYPE" or "ENOTSOCK", - it will be emulated, so you can call "aio_sendfile" on any type of - filehandle regardless of the limitations of the operating system. + "EINVAL", "ENOTSUP", "EOPNOTSUPP", "EAFNOSUPPORT", "EPROTOTYPE" or + "ENOTSOCK", it will be emulated, so you can call "aio_sendfile" on + any type of filehandle regardless of the limitations of the + operating system. + + As native sendfile syscalls (as practically any non-POSIX interface + hacked together in a hurry to improve benchmark numbers) tend to be + rather buggy on many systems, this implementation tries to work + around some known bugs in Linux and FreeBSD kernels (probably + others, too), but that might fail, so you really really should check + the return value of "aio_sendfile" - fewre bytes than expected might + have been transferred. aio_readahead $fh,$offset,$length, $callback->($retval) "aio_readahead" populates the page cache with data from a file so @@ -416,6 +447,15 @@ silently truncated unless perl itself is compiled with large file support. + To help interpret the mode and dev/rdev stat values, IO::AIO offers + the following constants and functions (if not implemented, the + constants will be 0 and the functions will either "croak" or fall + back on traditional behaviour). + + "S_IFMT", "S_IFIFO", "S_IFCHR", "S_IFBLK", "S_IFLNK", "S_IFREG", + "S_IFDIR", "S_IFWHT", "S_IFSOCK", "IO::AIO::major $dev_t", + "IO::AIO::minor $dev_t", "IO::AIO::makedev $major, $minor". + Example: Print the length of /etc/passwd: aio_stat "/etc/passwd", sub { @@ -504,14 +544,17 @@ Asynchronously unlink (delete) a file and call the callback with the result code. - aio_mknod $path, $mode, $dev, $callback->($status) + aio_mknod $pathname, $mode, $dev, $callback->($status) [EXPERIMENTAL] Asynchronously create a device node (or fifo). See mknod(2). The only (POSIX-) portable way of calling this function is: - aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... + aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ... + + See "aio_stat" for info about some potentially helpful extra + constants and functions. aio_link $srcpath, $dstpath, $callback->($status) Asynchronously create a new link to the existing object at $srcpath @@ -522,11 +565,19 @@ $srcpath at the path $dstpath and call the callback with the result code. - aio_readlink $path, $callback->($link) + aio_readlink $pathname, $callback->($link) Asynchronously read the symlink specified by $path and pass it to the callback. If an error occurs, nothing or undef gets passed to the callback. + aio_realpath $pathname, $callback->($path) + Asynchronously make the path absolute and resolve any symlinks in + $path. The resulting path only consists of directories (Same as + Cwd::realpath). + + This request can be used to get the absolute path of the current + working directory by passing it a path of . (a single dot). + aio_rename $srcpath, $dstpath, $callback->($status) Asynchronously rename the object at $srcpath to $dstpath, just as rename(2) and call the callback with the result code. @@ -549,18 +600,18 @@ an array-ref with the filenames. aio_readdirx $pathname, $flags, $callback->($entries, $flags) - Quite similar to "aio_readdir", but the $flags argument allows to - tune behaviour and output format. In case of an error, $entries will - be "undef". + Quite similar to "aio_readdir", but the $flags argument allows one + to tune behaviour and output format. In case of an error, $entries + will be "undef". The flags are a combination of the following constants, ORed together (the flags will also be passed to the callback, possibly modified): IO::AIO::READDIR_DENTS - When this flag is off, then the callback gets an arrayref with - of names only (as with "aio_readdir"), otherwise it gets an - arrayref with "[$name, $type, $inode]" arrayrefs, each + When this flag is off, then the callback gets an arrayref + consisting of names only (as with "aio_readdir"), otherwise it + gets an arrayref with "[$name, $type, $inode]" arrayrefs, each describing a single directory entry in more detail. $name is the name of the entry. @@ -583,14 +634,15 @@ IO::AIO::READDIR_DIRS_FIRST When this flag is set, then the names will be returned in an - order where likely directories come first. This is useful when - you need to quickly find directories, or you want to find all - directories while avoiding to stat() each entry. + order where likely directories come first, in optimal stat + order. This is useful when you need to quickly find directories, + or you want to find all directories while avoiding to stat() + each entry. If the system returns type information in readdir, then this is used to find directories directly. Otherwise, likely directories - are files beginning with ".", or otherwise files with no dots, - of which files with short names are tried first. + are names beginning with ".", or otherwise names with no dots, + of which names with short names are tried first. IO::AIO::READDIR_STAT_ORDER When this flag is set, then the names will be returned in an @@ -605,11 +657,11 @@ IO::AIO::READDIR_FOUND_UNKNOWN This flag should not be set when calling "aio_readdirx". Instead, it is being set by "aio_readdirx", when any of the - $type's found were "IO::AIO::DT_UNKNOWN". The absense of this + $type's found were "IO::AIO::DT_UNKNOWN". The absence of this flag therefore indicates that all $type's are known, which can be used to speed up some algorithms. - aio_load $path, $data, $callback->($status) + aio_load $pathname, $data, $callback->($status) This is a composite request that tries to fully load the given file into memory. Status is the same as with aio_read. @@ -636,7 +688,7 @@ if rename fails with "EXDEV", it copies the file with "aio_copy" and, if that is successful, unlinks the $srcpath. - aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) + aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs) Scans a directory (similar to "aio_readdir") but additionally tries to efficiently separate the entries of directory $path into two sets of names, directories you can recurse into (directories), and ones @@ -679,7 +731,7 @@ every entry plus an appended "/." will be "stat"'ed, likely directories first, in order of their inode numbers. If that succeeds, it assumes that the entry is a directory or a symlink to - directory (which will be checked seperately). This is often faster + directory (which will be checked separately). This is often faster than stat'ing the entry itself because filesystems might detect the type of the entry without reading the inode data (e.g. ext2fs filetype feature), even on systems that cannot return the filetype @@ -695,7 +747,7 @@ efficiency as those tend to return 0 or 1 as link counts, which disables the directory counting heuristic. - aio_rmtree $path, $callback->($status) + aio_rmtree $pathname, $callback->($status) Delete a directory tree starting (and including) $path, return the status of the final "rmdir" only. This is a composite request that uses "aio_scandir" to recurse into and rmdir directories, and unlink @@ -715,6 +767,12 @@ If this call isn't available because your OS lacks it or it couldn't be detected, it will be emulated by calling "fsync" instead. + aio_syncfs $fh, $callback->($status) + Asynchronously call the syncfs syscall to sync the filesystem + associated to the given filehandle and call the callback with the + syncfs result code. If syncfs is not available, calls sync(), but + returns -1 and sets errno to "ENOSYS" nevertheless. + aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) Sync the data portion of the file specified by $offset and $length to disk (but NOT the metadata), by calling the Linux-specific @@ -727,7 +785,7 @@ "IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER": refer to the sync_file_range manpage for details. - aio_pathsync $path, $callback->($status) + aio_pathsync $pathname, $callback->($status) This request tries to open, fsync and close the given path. This is a composite request intended to sync directories after directory operations (E.g. rename). This might not work on all operating @@ -850,6 +908,117 @@ not use this function except to put your application under artificial I/O pressure. + IO::AIO::WD - multiple working directories + Your process only has one current working directory, which is used by + all threads. This makes it hard to use relative paths (some other + component could call "chdir" at any time, and it is hard to control when + the path will be used by IO::AIO). + + One solution for this is to always use absolute paths. This usually + works, but can be quite slow (the kernel has to walk the whole path on + every access), and can also be a hassle to implement. + + Newer POSIX systems have a number of functions (openat, fdopendir, + futimensat and so on) that make it possible to specify working + directories per operation. + + For portability, and because the clowns who "designed", or shall I + write, perpetrated this new interface were obviously half-drunk, this + abstraction cannot be perfect, though. + + IO::AIO allows you to convert directory paths into a so-called + IO::AIO::WD object. This object stores the canonicalised, absolute + version of the path, and on systems that allow it, also a directory file + descriptor. + + Everywhere where a pathname is accepted by IO::AIO (e.g. in "aio_stat" + or "aio_unlink"), one can specify an array reference with an IO::AIO::WD + object and a pathname instead (or the IO::AIO::WD object alone, which + gets interpreted as "[$wd, "."]"). If the pathname is absolute, the + IO::AIO::WD object is ignored, otherwise the pathname is resolved + relative to that IO::AIO::WD object. + + For example, to get a wd object for /etc and then stat passwd inside, + you would write: + + aio_wd "/etc", sub { + my $etcdir = shift; + + # although $etcdir can be undef on error, there is generally no reason + # to check for errors here, as aio_stat will fail with ENOENT + # when $etcdir is undef. + + aio_stat [$etcdir, "passwd"], sub { + # yay + }; + }; + + That "aio_wd" is a request and not a normal function shows that creating + an IO::AIO::WD object is itself a potentially blocking operation, which + is why it is done asynchronously. + + To stat the directory obtained with "aio_wd" above, one could write + either of the following three request calls: + + aio_lstat "/etc" , sub { ... # pathname as normal string + aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself) + aio_lstat $wd , sub { ... # shorthand for the previous + + As with normal pathnames, IO::AIO keeps a copy of the working directory + object and the pathname string, so you could write the following without + causing any issues due to $path getting reused: + + my $path = [$wd, undef]; + + for my $name (qw(abc def ghi)) { + $path->[1] = $name; + aio_stat $path, sub { + # ... + }; + } + + There are some caveats: when directories get renamed (or deleted), the + pathname string doesn't change, so will point to the new directory (or + nowhere at all), while the directory fd, if available on the system, + will still point to the original directory. Most functions accepting a + pathname will use the directory fd on newer systems, and the string on + older systems. Some functions (such as realpath) will always rely on the + string form of the pathname. + + So this fucntionality is mainly useful to get some protection against + "chdir", to easily get an absolute path out of a relative path for + future reference, and to speed up doing many operations in the same + directory (e.g. when stat'ing all files in a directory). + + The following functions implement this working directory abstraction: + + aio_wd $pathname, $callback->($wd) + Asynchonously canonicalise the given pathname and convert it to an + IO::AIO::WD object representing it. If possible and supported on the + system, also open a directory fd to speed up pathname resolution + relative to this working directory. + + If something goes wrong, then "undef" is passwd to the callback + instead of a working directory object and $! is set appropriately. + Since passing "undef" as working directory component of a pathname + fails the request with "ENOENT", there is often no need for error + checking in the "aio_wd" callback, as future requests using the + value will fail in the expected way. + + If this call isn't available because your OS lacks it or it couldn't + be detected, it will be emulated by calling "fsync" instead. + + IO::AIO::CWD + This is a compiletime constant (object) that represents the process + current working directory. + + Specifying this object as working directory object for a pathname is + as if the pathname would be specified directly, without a directory + object, e.g., these calls are functionally identical: + + aio_stat "somefile", sub { ... }; + aio_stat [IO::AIO::CWD, "somefile"], sub { ... }; + IO::AIO::REQ CLASS All non-aggregate "aio_*" functions return an object of this class when called in non-void context. @@ -958,7 +1127,7 @@ this is that, although you could just queue as many requests as you want in a group, this might starve other requests for a potentially long time. For example, "aio_scandir" might generate hundreds of - thousands "aio_stat" requests, delaying any later requests for a + thousands of "aio_stat" requests, delaying any later requests for a long time. To avoid this, and allow incremental generation of requests, you can @@ -1011,16 +1180,23 @@ IO::AIO::poll_cb Process some outstanding events on the result pipe. You have to call - this regularly. Returns 0 if all events could be processed, or -1 if - it returned earlier for whatever reason. Returns immediately when no - events are outstanding. The amount of events processed depends on - the settings of "IO::AIO::max_poll_req" and - "IO::AIO::max_poll_time". + this regularly. Returns 0 if all events could be processed (or there + were no events to process), or -1 if it returned earlier for + whatever reason. Returns immediately when no events are outstanding. + The amount of events processed depends on the settings of + "IO::AIO::max_poll_req" and "IO::AIO::max_poll_time". If not all requests were processed for whatever reason, the filehandle will still be ready when "poll_cb" returns, so normally you don't have to do anything special to have it called later. + Apart from calling "IO::AIO::poll_cb" when the event filehandle + becomes ready, it can be beneficial to call this function from loops + which submit a lot of requests, to make sure the results get + processed when they become available and not just when the loop is + finished and the event loop takes over again. This function returns + very fast when there are no outstanding requests. + Example: Install an Event watcher that automatically calls IO::AIO::poll_cb with high priority (more examples can be found in the SYNOPSIS section, at the top of this document): @@ -1123,9 +1299,10 @@ IO::AIO::max_idle $nthreads Limit the number of threads (default: 4) that are allowed to idle - (i.e., threads that did not get a request to process within 10 - seconds). That means if a thread becomes idle while $nthreads other - threads are also idle, it will free its resources and exit. + (i.e., threads that did not get a request to process within the idle + timeout (default: 10 seconds). That means if a thread becomes idle + while $nthreads other threads are also idle, it will free its + resources and exit. This is useful when you allow a large number of threads (e.g. 100 or 1000) to allow for extremely high load situations, but want to free @@ -1136,23 +1313,44 @@ creation is fast. If thread creation is very slow on your system you might want to use larger values. + IO::AIO::idle_timeout $seconds + Sets the minimum idle timeout (default 10) after which worker + threads are allowed to exit. SEe "IO::AIO::max_idle". + IO::AIO::max_outstanding $maxreqs + Sets the maximum number of outstanding requests to $nreqs. If you do + queue up more than this number of requests, the next call to + "IO::AIO::poll_cb" (and other functions calling "poll_cb", such as + "IO::AIO::flush" or "IO::AIO::poll") will block until the limit is + no longer exceeded. + + In other words, this setting does not enforce a queue limit, but can + be used to make poll functions block if the limit is exceeded. + This is a very bad function to use in interactive programs because it blocks, and a bad way to reduce concurrency because it is inexact: Better use an "aio_group" together with a feed callback. - Sets the maximum number of outstanding requests to $nreqs. If you do - queue up more than this number of requests, the next call to the - "poll_cb" (and "poll_some" and other functions calling "poll_cb") - function will block until the limit is no longer exceeded. - - The default value is very large, so there is no practical limit on - the number of outstanding requests. - - You can still queue as many requests as you want. Therefore, - "max_outstanding" is mainly useful in simple scripts (with low - values) or as a stop gap to shield against fatal memory overflow - (with large values). + It's main use is in scripts without an event loop - when you want to + stat a lot of files, you can write somehting like this: + + IO::AIO::max_outstanding 32; + + for my $path (...) { + aio_stat $path , ...; + IO::AIO::poll_cb; + } + + IO::AIO::flush; + + The call to "poll_cb" inside the loop will normally return + instantly, but as soon as more thna 32 reqeusts are in-flight, it + will block until some requests have been handled. This keeps the + loop from pushing a large number of "aio_stat" requests onto the + queue. + + The default value for "max_outstanding" is very large, so there is + no practical limit on the number of outstanding requests. STATISTICAL INFORMATION IO::AIO::nreqs @@ -1187,7 +1385,7 @@ IO::AIO::fadvise $fh, $offset, $len, $advice Simply calls the "posix_fadvise" function (see its manpage for - details). The following advice constants are avaiable: + details). The following advice constants are available: "IO::AIO::FADV_NORMAL", "IO::AIO::FADV_SEQUENTIAL", "IO::AIO::FADV_RANDOM", "IO::AIO::FADV_NOREUSE", "IO::AIO::FADV_WILLNEED", "IO::AIO::FADV_DONTNEED". @@ -1197,7 +1395,7 @@ IO::AIO::madvise $scalar, $offset, $len, $advice Simply calls the "posix_madvise" function (see its manpage for - details). The following advice constants are avaiable: + details). The following advice constants are available: "IO::AIO::MADV_NORMAL", "IO::AIO::MADV_SEQUENTIAL", "IO::AIO::MADV_RANDOM", "IO::AIO::MADV_WILLNEED", "IO::AIO::MADV_DONTNEED". @@ -1208,7 +1406,7 @@ IO::AIO::mprotect $scalar, $offset, $len, $protect Simply calls the "mprotect" function on the preferably AIO::mmap'ed $scalar (see its manpage for details). The following protect - constants are avaiable: "IO::AIO::PROT_NONE", "IO::AIO::PROT_READ", + constants are available: "IO::AIO::PROT_NONE", "IO::AIO::PROT_READ", "IO::AIO::PROT_WRITE", "IO::AIO::PROT_EXEC". On systems that do not implement "mprotect", this function returns @@ -1308,19 +1506,32 @@ \&IO::AIO::poll_cb); FORK BEHAVIOUR - This module should do "the right thing" when the process using it forks: - - Before the fork, IO::AIO enters a quiescent state where no requests can - be added in other threads and no results will be processed. After the - fork the parent simply leaves the quiescent state and continues - request/result processing, while the child frees the request/result - queue (so that the requests started before the fork will only be handled - in the parent). Threads will be started on demand until the limit set in - the parent process has been reached again. - - In short: the parent will, after a short pause, continue as if fork had - not been called, while the child will act as if IO::AIO has not been - used yet. + Usage of pthreads in a program changes the semantics of fork + considerably. Specifically, only async-safe functions can be called + after fork. Perl doesn't know about this, so in general, you cannot call + fork with defined behaviour in perl if pthreads are involved. IO::AIO + uses pthreads, so this applies, but many other extensions and (for + inexplicable reasons) perl itself often is linked against pthreads, so + this limitation applies to quite a lot of perls. + + This module no longer tries to fight your OS, or POSIX. That means + IO::AIO only works in the process that loaded it. Forking is fully + supported, but using IO::AIO in the child is not. + + You might get around by not *using* IO::AIO before (or after) forking. + You could also try to call the IO::AIO::reinit function in the child: + + IO::AIO::reinit + Abandons all current requests and I/O threads and simply + reinitialises all data structures. This is not an operation + supported by any standards, but happens to work on GNU/Linux and + some newer BSD systems. + + The only reasonable use for this function is to call it after + forking, if "IO::AIO" was used in the parent. Calling it while + IO::AIO is active in the process will result in undefined behaviour. + Calling it at any time will also result in any undefined (by POSIX) + behaviour. MEMORY USAGE Per-request usage: