NAME IO::AIO - Asynchronous/Advanced Input/Output SYNOPSIS use IO::AIO; aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub { my $fh = shift or die "/etc/passwd: $!"; ... }; aio_unlink "/tmp/file", sub { }; aio_read $fh, 30000, 1024, $buffer, 0, sub { $_[0] > 0 or die "read error: $!"; }; # version 2+ has request and group objects use IO::AIO 2; aioreq_pri 4; # give next request a very high priority my $req = aio_unlink "/tmp/file", sub { }; $req->cancel; # cancel request if still in queue my $grp = aio_group sub { print "all stats done\n" }; add $grp aio_stat "..." for ...; DESCRIPTION This module implements asynchronous I/O using whatever means your operating system supports. It is implemented as an interface to "libeio" (). Asynchronous means that operations that can normally block your program (e.g. reading from disk) will be done asynchronously: the operation will still block, but you can do something else in the meantime. This is extremely useful for programs that need to stay interactive even when doing heavy I/O (GUI programs, high performance network servers etc.), but can also be used to easily do operations in parallel that are normally done sequentially, e.g. stat'ing many files, which is much faster on a RAID volume or over NFS when you do a number of stat operations concurrently. While most of this works on all types of file descriptors (for example sockets), using these functions on file descriptors that support nonblocking operation (again, sockets, pipes etc.) is very inefficient. Use an event loop for that (such as the EV module): IO::AIO will naturally fit into such an event loop itself. In this version, a number of threads are started that execute your requests and signal their completion. You don't need thread support in perl, and the threads created by this module will not be visible to perl. In the future, this module might make use of the native aio functions available on many operating systems. However, they are often not well-supported or restricted (GNU/Linux doesn't allow them on normal files currently, for example), and they would only support aio_read and aio_write, so the remaining functionality would have to be implemented using threads anyway. In addition to asynchronous I/O, this module also exports some rather arcane interfaces, such as "madvise" or linux's "splice" system call, which is why the "A" in "AIO" can also mean *advanced*. Although the module will work in the presence of other (Perl-) threads, it is currently not reentrant in any way, so use appropriate locking yourself, always call "poll_cb" from within the same thread, or never call "poll_cb" (or other "aio_" functions) recursively. EXAMPLE This is a simple example that uses the EV module and loads /etc/passwd asynchronously: use EV; use IO::AIO; # register the IO::AIO callback with EV my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; # queue the request to open /etc/passwd aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub { my $fh = shift or die "error while opening: $!"; # stat'ing filehandles is generally non-blocking my $size = -s $fh; # queue a request to read the file my $contents; aio_read $fh, 0, $size, $contents, 0, sub { $_[0] == $size or die "short read: $!"; close $fh; # file contents now in $contents print $contents; # exit event loop and program EV::break; }; }; # possibly queue up other requests, or open GUI windows, # check for sockets etc. etc. # process events as long as there are some: EV::run; REQUEST ANATOMY AND LIFETIME Every "aio_*" function creates a request. which is a C data structure not directly visible to Perl. If called in non-void context, every request function returns a Perl object representing the request. In void context, nothing is returned, which saves a bit of memory. The perl object is a fairly standard ref-to-hash object. The hash contents are not used by IO::AIO so you are free to store anything you like in it. During their existance, aio requests travel through the following states, in order: ready Immediately after a request is created it is put into the ready state, waiting for a thread to execute it. execute A thread has accepted the request for processing and is currently executing it (e.g. blocking in read). pending The request has been executed and is waiting for result processing. While request submission and execution is fully asynchronous, result processing is not and relies on the perl interpreter calling "poll_cb" (or another function with the same effect). result The request results are processed synchronously by "poll_cb". The "poll_cb" function will process all outstanding aio requests by calling their callbacks, freeing memory associated with them and managing any groups they are contained in. done Request has reached the end of its lifetime and holds no resources anymore (except possibly for the Perl object, but its connection to the actual aio request is severed and calling its methods will either do nothing or result in a runtime error). FUNCTIONS QUICK OVERVIEW This section simply lists the prototypes most of the functions 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_seek $fh,$offset,$whence, $callback->($offs) aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) aio_readahead $fh,$offset,$length, $callback->($retval) aio_stat $fh_or_path, $callback->($status) aio_lstat $fh, $callback->($status) aio_statvfs $fh_or_path, $callback->($statvfs) aio_utime $fh_or_path, $atime, $mtime, $callback->($status) aio_chown $fh_or_path, $uid, $gid, $callback->($status) aio_chmod $fh_or_path, $mode, $callback->($status) aio_truncate $fh_or_path, $offset, $callback->($status) aio_allocate $fh, $mode, $offset, $len, $callback->($status) aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents) aio_unlink $pathname, $callback->($status) aio_mknod $pathname, $mode, $dev, $callback->($status) aio_link $srcpath, $dstpath, $callback->($status) aio_symlink $srcpath, $dstpath, $callback->($status) aio_readlink $pathname, $callback->($link) aio_realpath $pathname, $callback->($path) aio_rename $srcpath, $dstpath, $callback->($status) aio_rename2 $srcpath, $dstpath, $flags, $callback->($status) aio_mkdir $pathname, $mode, $callback->($status) aio_rmdir $pathname, $callback->($status) aio_readdir $pathname, $callback->($entries) 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_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_rmtree $pathname, $callback->($status) aio_fcntl $fh, $cmd, $arg, $callback->($status) aio_ioctl $fh, $request, $buf, $callback->($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 $pathname, $callback->($status) aio_msync $scalar, $offset = 0, $length = undef, flags = MS_SYNC, $callback->($status) aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status) aio_mlockall $flags, $callback->($status) aio_group $callback->(...) aio_nop $callback->() $prev_pri = aioreq_pri [$pri] aioreq_nice $pri_adjust IO::AIO::poll_wait IO::AIO::poll_cb IO::AIO::poll IO::AIO::flush IO::AIO::max_poll_reqs $nreqs IO::AIO::max_poll_time $seconds 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 IO::AIO::npending $nfd = IO::AIO::get_fdlimit [EXPERIMENTAL] IO::AIO::min_fdlimit $nfd [EXPERIMENTAL] IO::AIO::sendfile $ofh, $ifh, $offset, $count IO::AIO::fadvise $fh, $offset, $len, $advice IO::AIO::mmap $scalar, $length, $prot, $flags[, $fh[, $offset]] IO::AIO::munmap $scalar IO::AIO::mremap $scalar, $new_length, $flags[, $new_address] IO::AIO::madvise $scalar, $offset, $length, $advice IO::AIO::mprotect $scalar, $offset, $length, $protect IO::AIO::munlock $scalar, $offset = 0, $length = undef IO::AIO::munlockall API NOTES 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 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. 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 *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 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. AIO REQUEST FUNCTIONS $prev_pri = aioreq_pri [$pri] Returns the priority value that would be used for the next request and, if $pri is given, sets the priority for the next aio request. The default priority is 0, the minimum and maximum priorities are -4 and 4, respectively. Requests with higher priority will be serviced first. The priority will be reset to 0 after each call to one of the "aio_*" functions. Example: open a file with low priority, then read something from it with higher priority so the read request is serviced before other low priority open requests (potentially spamming the cache): aioreq_pri -3; aio_open ..., sub { return unless $_[0]; aioreq_pri -2; aio_read $_[0], ..., sub { ... }; }; aioreq_nice $pri_adjust Similar to "aioreq_pri", but subtracts the given value from the current priority, so the effect is cumulative. aio_open $pathname, $flags, $mode, $callback->($fh) Asynchronously open or create a file and call the callback with a newly created filehandle for the file (or "undef" in case of an error). The pathname passed to "aio_open" must be absolute. See API NOTES, above, for an explanation. The $flags argument is a bitmask. See the "Fcntl" module for a list. They are the same as used by "sysopen". Likewise, $mode specifies the mode of the newly created file, if it didn't exist and "O_CREAT" has been given, just like perl's "sysopen", except that it is mandatory (i.e. use 0 if you don't create new files, and 0666 or 0777 if you do). Note that the $mode will be modified by the umask in effect then the request is being executed, so better never change the umask. Example: aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub { if ($_[0]) { print "open successful, fh is $_[0]\n"; ... } else { die "open failed: $!\n"; } }; 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", "O_PATH", "O_TMPFILE", "O_TTY_INIT" and "O_ACCMODE". aio_close $fh, $callback->($status) Asynchronously close a file and call the callback with the result code. Unfortunately, you can't do this to perl. Perl *insists* very strongly on closing the file descriptor associated with the filehandle itself. Therefore, "aio_close" will not close the filehandle - instead it will use dup2 to overwrite the file descriptor with the write-end of a pipe (the pipe fd will be created on demand and will be cached). Or in other words: the file descriptor will be closed, but it will not be free for reuse until the perl filehandle is closed. aio_seek $fh, $offset, $whence, $callback->($offs) Seeks the filehandle to the new $offset, similarly to perl's "sysseek". The $whence can use the traditional values (0 for "IO::AIO::SEEK_SET", 1 for "IO::AIO::SEEK_CUR" or 2 for "IO::AIO::SEEK_END"). The resulting absolute offset will be passed to the callback, or -1 in case of an error. In theory, the $whence constants could be different than the corresponding values from Fcntl, but perl guarantees they are the same, so don't panic. As a GNU/Linux (and maybe Solaris) extension, also the constants "IO::AIO::SEEK_DATA" and "IO::AIO::SEEK_HOLE" are available, if they could be found. No guarantees about suitability for use in "aio_seek" or Perl's "sysseek" can be made though, although I would naively assume they "just work". aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) Reads or writes $length bytes from or to the specified $fh and $offset into the scalar given by $data and offset $dataoffset and calls the callback with the actual number of bytes transferred (or -1 on error, just like the syscall). "aio_read" will, like "sysread", shrink or grow the $data scalar to offset plus the actual number of bytes read. If $offset is undefined, then the current file descriptor offset will be used (and updated), otherwise the file descriptor offset will not be changed by these calls. If $length is undefined in "aio_write", use the remaining length of $data. If $dataoffset is less than zero, it will be counted from the end of $data. The $data scalar *MUST NOT* be modified in any way while the request is outstanding. Modifying it can result in segfaults or World War III (if the necessary/optional hardware is installed). Example: Read 15 bytes at offset 7 into scalar $buffer, starting at offset 0 within the scalar: aio_read $fh, 7, 15, $buffer, 0, sub { $_[0] > 0 or die "read error: $!"; print "read $_[0] bytes: <$buffer>\n"; }; aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) Tries to copy $length bytes from $in_fh to $out_fh. It starts 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. 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 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 (typically the $in_fh) is a file - the file I/O will then be asynchronous, while the socket I/O will be non-blocking. Note, however, that you can run into a trap where "aio_sendfile" reads 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 better control resource usage. 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", "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" - fewer 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 that subsequent reads from that file will not block on disk I/O. The $offset argument specifies the starting point from which data is to be read and $length specifies the number of bytes to be read. I/O is performed in whole pages, so that offset is effectively rounded down to a page boundary and bytes are read up to the next page boundary greater than or equal to (off-set+length). "aio_readahead" does not read beyond the end of the file. The current file offset of the file is left unchanged. If that syscall doesn't exist (likely if your kernel isn't Linux) it will be emulated by simply reading the data, which would have a similar effect. aio_stat $fh_or_path, $callback->($status) aio_lstat $fh, $callback->($status) Works like perl's "stat" or "lstat" in void context. The callback will be called after the stat and the results will be available using "stat _" or "-s _" etc... The pathname passed to "aio_stat" must be absolute. See API NOTES, above, for an explanation. Currently, the stats are always 64-bit-stats, i.e. instead of returning an error when stat'ing a large file, the results will be 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". To access higher resolution stat timestamps, see "SUBSECOND STAT TIME ACCESS". Example: Print the length of /etc/passwd: aio_stat "/etc/passwd", sub { $_[0] and die "stat failed: $!"; print "size is ", -s _, "\n"; }; aio_statvfs $fh_or_path, $callback->($statvfs) Works like the POSIX "statvfs" or "fstatvfs" syscalls, depending on whether a file handle or path was passed. On success, the callback is passed a hash reference with the following members: "bsize", "frsize", "blocks", "bfree", "bavail", "files", "ffree", "favail", "fsid", "flag" and "namemax". On failure, "undef" is passed. The following POSIX IO::AIO::ST_* constants are defined: "ST_RDONLY" and "ST_NOSUID". The following non-POSIX IO::AIO::ST_* flag masks are defined to their correct value when available, or to 0 on systems that do not support them: "ST_NODEV", "ST_NOEXEC", "ST_SYNCHRONOUS", "ST_MANDLOCK", "ST_WRITE", "ST_APPEND", "ST_IMMUTABLE", "ST_NOATIME", "ST_NODIRATIME" and "ST_RELATIME". Example: stat "/wd" and dump out the data if successful. aio_statvfs "/wd", sub { my $f = $_[0] or die "statvfs: $!"; use Data::Dumper; say Dumper $f; }; # result: { bsize => 1024, bfree => 4333064312, blocks => 10253828096, files => 2050765568, flag => 4096, favail => 2042092649, bavail => 4333064312, ffree => 2042092649, namemax => 255, frsize => 1024, fsid => 1810 } aio_utime $fh_or_path, $atime, $mtime, $callback->($status) Works like perl's "utime" function (including the special case of $atime and $mtime being undef). Fractional times are supported if the underlying syscalls support them. When called with a pathname, uses utimes(2) if available, otherwise utime(2). If called on a file descriptor, uses futimes(2) if available, otherwise returns ENOSYS, so this is not portable. Examples: # set atime and mtime to current time (basically touch(1)): aio_utime "path", undef, undef; # set atime to current time and mtime to beginning of the epoch: aio_utime "path", time, undef; # undef==0 aio_chown $fh_or_path, $uid, $gid, $callback->($status) Works like perl's "chown" function, except that "undef" for either $uid or $gid is being interpreted as "do not change" (but -1 can also be used). Examples: # same as "chown root path" in the shell: aio_chown "path", 0, -1; # same as above: aio_chown "path", 0, undef; aio_truncate $fh_or_path, $offset, $callback->($status) Works like truncate(2) or ftruncate(2). aio_allocate $fh, $mode, $offset, $len, $callback->($status) Allocates or frees disk space according to the $mode argument. See the linux "fallocate" documentation for details. $mode is usually 0 or "IO::AIO::FALLOC_FL_KEEP_SIZE" to allocate space, or "IO::AIO::FALLOC_FL_PUNCH_HOLE | IO::AIO::FALLOC_FL_KEEP_SIZE", to deallocate a file range. IO::AIO also supports "FALLOC_FL_COLLAPSE_RANGE", to remove a range (without leaving a hole), "FALLOC_FL_ZERO_RANGE", to zero a range, "FALLOC_FL_INSERT_RANGE" to insert a range and "FALLOC_FL_UNSHARE_RANGE" to unshare shared blocks (see your fallocate(2) manpage). The file system block size used by "fallocate" is presumably the "f_bsize" returned by "statvfs", but different filesystems and filetypes can dictate other limitations. If "fallocate" isn't available or cannot be emulated (currently no emulation will be attempted), passes -1 and sets $! to "ENOSYS". aio_chmod $fh_or_path, $mode, $callback->($status) Works like perl's "chmod" function. aio_unlink $pathname, $callback->($status) Asynchronously unlink (delete) a file and call the callback with the result code. 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 $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 at the path $dstpath and call the callback with the result code. aio_symlink $srcpath, $dstpath, $callback->($status) Asynchronously create a new symbolic link to the existing object at $srcpath at the path $dstpath and call the callback with the result code. 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 $dstpath, just as rename(2) and call the callback with the result code. On systems that support the AIO::WD working directory abstraction natively, the case "[$wd, "."]" as $srcpath is specialcased - instead of failing, "rename" is called on the absolute path of $wd. aio_rename2 $srcpath, $dstpath, $flags, $callback->($status) Basically a version of "aio_rename" with an additional $flags argument. Calling this with "$flags=0" is the same as calling "aio_rename". Non-zero flags are currently only supported on GNU/Linux systems that support renameat2. Other systems fail with "ENOSYS" in this case. The following constants are available (missing ones are, as usual 0), see renameat2(2) for details: "IO::AIO::RENAME_NOREPLACE", "IO::AIO::RENAME_EXCHANGE" and "IO::AIO::RENAME_WHITEOUT". aio_mkdir $pathname, $mode, $callback->($status) Asynchronously mkdir (create) a directory and call the callback with the result code. $mode will be modified by the umask at the time the request is executed, so do not change your umask. aio_rmdir $pathname, $callback->($status) Asynchronously rmdir (delete) a directory and call the callback with the result code. On systems that support the AIO::WD working directory abstraction natively, the case "[$wd, "."]" is specialcased - instead of failing, "rmdir" is called on the absolute path of $wd. aio_readdir $pathname, $callback->($entries) Unlike the POSIX call of the same name, "aio_readdir" reads an entire directory (i.e. opendir + readdir + closedir). The entries will not be sorted, and will NOT include the "." and ".." entries. The callback is passed a single argument which is either "undef" or an array-ref with the filenames. aio_readdirx $pathname, $flags, $callback->($entries, $flags) Quite similar to "aio_readdir", but the $flags argument allows one to tune behaviour and output format. In case of an error, $entries will be "undef". The flags are a combination of the following constants, ORed together (the flags will also be passed to the callback, possibly modified): IO::AIO::READDIR_DENTS Normally the callback gets an arrayref consisting of names only (as with "aio_readdir"). If this flag is set, then the callback gets an arrayref with "[$name, $type, $inode]" arrayrefs, each describing a single directory entry in more detail: $name is the name of the entry. $type is one of the "IO::AIO::DT_xxx" constants: "IO::AIO::DT_UNKNOWN", "IO::AIO::DT_FIFO", "IO::AIO::DT_CHR", "IO::AIO::DT_DIR", "IO::AIO::DT_BLK", "IO::AIO::DT_REG", "IO::AIO::DT_LNK", "IO::AIO::DT_SOCK", "IO::AIO::DT_WHT". "IO::AIO::DT_UNKNOWN" means just that: readdir does not know. If you need to know, you have to run stat yourself. Also, for speed/memory reasons, the $type scalars are read-only: you must not modify them. $inode is the inode number (which might not be exact on systems with 64 bit inode numbers and 32 bit perls). This field has unspecified content on systems that do not deliver the inode information. IO::AIO::READDIR_DIRS_FIRST When this flag is set, then the names will be returned in an 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 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 order suitable for stat()'ing each one. That is, when you plan to stat() most or all files in the given directory, then the returned order will likely be faster. If both this flag and "IO::AIO::READDIR_DIRS_FIRST" are specified, then the likely dirs come first, resulting in a less optimal stat order for stat'ing all entries, but likely a more optimal order for finding subdirectories. 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 absence of this flag therefore indicates that all $type's are known, which can be used to speed up some algorithms. aio_slurp $pathname, $offset, $length, $data, $callback->($status) Opens, reads and closes the given file. The data is put into $data, which is resized as required. If $offset is negative, then it is counted from the end of the file. If $length is zero, then the remaining length of the file is used. Also, in this case, the same limitations to modifying $data apply as when IO::AIO::mmap is used, i.e. it must only be modified in-place with "substr". If the size of the file is known, specifying a non-zero $length results in a performance advantage. This request is similar to the older "aio_load" request, but since it is a single request, it might be more efficient to use. Example: load /etc/passwd into $passwd. my $passwd; aio_slurp "/etc/passwd", 0, 0, $passwd, sub { $_[0] >= 0 or die "/etc/passwd: $!\n"; printf "/etc/passwd is %d bytes long, and contains:\n", length $passwd; print $passwd; }; IO::AIO::flush; 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. Using "aio_slurp" might be more efficient, as it is a single request. aio_copy $srcpath, $dstpath, $callback->($status) Try to copy the *file* (directories not supported as either source or destination) from $srcpath to $dstpath and call the callback with a status of 0 (ok) or -1 (error, see $!). Existing destination files will be truncated. This is a composite request that creates the destination file with mode 0200 and copies the contents of the source file into it using "aio_sendfile", followed by restoring atime, mtime, access mode and uid/gid, in that order. If an error occurs, the partial destination file will be unlinked, if possible, except when setting atime, mtime, access mode and uid/gid, where errors are being ignored. aio_move $srcpath, $dstpath, $callback->($status) Try to move the *file* (directories not supported as either source or destination) from $srcpath to $dstpath and call the callback with a status of 0 (ok) or -1 (error, see $!). This is a composite request that tries to rename(2) the file first; if rename fails with "EXDEV", it copies the file with "aio_copy" and, if that is successful, unlinks the $srcpath. 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 you cannot recurse into (everything else, including symlinks to directories). "aio_scandir" is a composite request that generates many sub requests. $maxreq specifies the maximum number of outstanding aio requests that this function generates. If it is "<= 0", then a suitable default will be chosen (currently 4). On error, the callback is called without arguments, otherwise it receives two array-refs with path-relative entry names. Example: aio_scandir $dir, 0, sub { my ($dirs, $nondirs) = @_; print "real directories: @$dirs\n"; print "everything else: @$nondirs\n"; }; Implementation notes. The "aio_readdir" cannot be avoided, but "stat()"'ing every entry can. If readdir returns file type information, then this is used directly to find directories. Otherwise, after reading the directory, the modification time, size etc. of the directory before and after the readdir is checked, and if they match (and isn't the current time), the link count will be used to decide how many entries are directories (if >= 2). Otherwise, no knowledge of the number of subdirectories will be assumed. Then entries will be sorted into likely directories a non-initial dot currently) and likely non-directories (see "aio_readdirx"). Then 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 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 information on readdir. If the known number of directories (link count - 2) has been reached, the rest of the entries is assumed to be non-directories. This only works with certainty on POSIX (= UNIX) filesystems, which fortunately are the vast majority of filesystems around. It will also likely work on non-POSIX filesystems with reduced efficiency as those tend to return 0 or 1 as link counts, which disables the directory counting heuristic. 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 everything else. aio_fcntl $fh, $cmd, $arg, $callback->($status) aio_ioctl $fh, $request, $buf, $callback->($status) These work just like the "fcntl" and "ioctl" built-in functions, except they execute asynchronously and pass the return value to the callback. Both calls can be used for a lot of things, some of which make more sense to run asynchronously in their own thread, while some others make less sense. For example, calls that block waiting for external events, such as locking, will also lock down an I/O thread while it is waiting, which can deadlock the whole I/O system. At the same time, there might be no alternative to using a thread to wait. So in general, you should only use these calls for things that do (filesystem) I/O, not for things that wait for other events (network, other processes), although if you are careful and know what you are doing, you still can. The following constants are available (missing ones are, as usual 0): "F_DUPFD_CLOEXEC", "F_OFD_GETLK", "F_OFD_SETLK", "F_OFD_GETLKW", "FIFREEZE", "FITHAW", "FITRIM", "FICLONE", "FICLONERANGE", "FIDEDUPERANGE". "FS_IOC_GETFLAGS", "FS_IOC_SETFLAGS", "FS_IOC_GETVERSION", "FS_IOC_SETVERSION", "FS_IOC_FIEMAP". "FS_IOC_FSGETXATTR", "FS_IOC_FSSETXATTR", "FS_IOC_SET_ENCRYPTION_POLICY", "FS_IOC_GET_ENCRYPTION_PWSALT", "FS_IOC_GET_ENCRYPTION_POLICY", "FS_KEY_DESCRIPTOR_SIZE". "FS_SECRM_FL", "FS_UNRM_FL", "FS_COMPR_FL", "FS_SYNC_FL", "FS_IMMUTABLE_FL", "FS_APPEND_FL", "FS_NODUMP_FL", "FS_NOATIME_FL", "FS_DIRTY_FL", "FS_COMPRBLK_FL", "FS_NOCOMP_FL", "FS_ENCRYPT_FL", "FS_BTREE_FL", "FS_INDEX_FL", "FS_JOURNAL_DATA_FL", "FS_NOTAIL_FL", "FS_DIRSYNC_FL", "FS_TOPDIR_FL", "FS_FL_USER_MODIFIABLE". "FS_XFLAG_REALTIME", "FS_XFLAG_PREALLOC", "FS_XFLAG_IMMUTABLE", "FS_XFLAG_APPEND", "FS_XFLAG_SYNC", "FS_XFLAG_NOATIME", "FS_XFLAG_NODUMP", "FS_XFLAG_RTINHERIT", "FS_XFLAG_PROJINHERIT", "FS_XFLAG_NOSYMLINKS", "FS_XFLAG_EXTSIZE", "FS_XFLAG_EXTSZINHERIT", "FS_XFLAG_NODEFRAG", "FS_XFLAG_FILESTREAM", "FS_XFLAG_DAX", "FS_XFLAG_HASATTR", aio_sync $callback->($status) Asynchronously call sync and call the callback when finished. aio_fsync $fh, $callback->($status) Asynchronously call fsync on the given filehandle and call the callback with the fsync result code. aio_fdatasync $fh, $callback->($status) Asynchronously call fdatasync on the given filehandle and call the callback with the fdatasync result code. 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 sync_file_range call. If sync_file_range is not available or it returns ENOSYS, then fdatasync or fsync is being substituted. $flags can be a combination of "IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE", "IO::AIO::SYNC_FILE_RANGE_WRITE" and "IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER": refer to the sync_file_range manpage for details. 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 systems or have any specific effect, but usually it makes sure that directory changes get written to disc. It works for anything that can be opened for read-only, not just directories. Future versions of this function might fall back to other methods when "fsync" on the directory fails (such as calling "sync"). Passes 0 when everything went ok, and -1 on error. aio_msync $scalar, $offset = 0, $length = undef, flags = MS_SYNC, $callback->($status) This is a rather advanced IO::AIO call, which only works on mmap(2)ed scalars (see the "IO::AIO::mmap" function, although it also works on data scalars managed by the Sys::Mmap or Mmap modules, note that the scalar must only be modified in-place while an aio operation is pending on it). It calls the "msync" function of your OS, if available, with the memory area starting at $offset in the string and ending $length bytes later. If $length is negative, counts from the end, and if $length is "undef", then it goes till the end of the string. The flags can be either "IO::AIO::MS_ASYNC" or "IO::AIO::MS_SYNC", plus an optional "IO::AIO::MS_INVALIDATE". aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) This is a rather advanced IO::AIO call, which works best on mmap(2)ed scalars. It touches (reads or writes) all memory pages in the specified range inside the scalar. All caveats and parameters are the same as for "aio_msync", above, except for flags, which must be either 0 (which reads all pages and ensures they are instantiated) or "IO::AIO::MT_MODIFY", which modifies the memory pages (by reading and writing an octet from it, which dirties the page). aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status) This is a rather advanced IO::AIO call, which works best on mmap(2)ed scalars. It reads in all the pages of the underlying storage into memory (if any) and locks them, so they are not getting swapped/paged out or removed. If $length is undefined, then the scalar will be locked till the end. On systems that do not implement "mlock", this function returns -1 and sets errno to "ENOSYS". Note that the corresponding "munlock" is synchronous and is documented under "MISCELLANEOUS FUNCTIONS". Example: open a file, mmap and mlock it - both will be undone when $data gets destroyed. open my $fh, "<", $path or die "$path: $!"; my $data; IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh; aio_mlock $data; # mlock in background aio_mlockall $flags, $callback->($status) Calls the "mlockall" function with the given $flags (a combination of "IO::AIO::MCL_CURRENT" and "IO::AIO::MCL_FUTURE"). On systems that do not implement "mlockall", this function returns -1 and sets errno to "ENOSYS". Note that the corresponding "munlockall" is synchronous and is documented under "MISCELLANEOUS FUNCTIONS". Example: asynchronously lock all current and future pages into memory. aio_mlockall IO::AIO::MCL_FUTURE; aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents) Queries the extents of the given file (by calling the Linux "FIEMAP" ioctl, see for details). If the ioctl is not available on your OS, then this request will fail with "ENOSYS". $start is the starting offset to query extents for, $length is the size of the range to query - if it is "undef", then the whole file will be queried. $flags is a combination of flags ("IO::AIO::FIEMAP_FLAG_SYNC" or "IO::AIO::FIEMAP_FLAG_XATTR" - "IO::AIO::FIEMAP_FLAGS_COMPAT" is also exported), and is normally 0 or "IO::AIO::FIEMAP_FLAG_SYNC" to query the data portion. $count is the maximum number of extent records to return. If it is "undef", then IO::AIO queries all extents of the range. As a very special case, if it is 0, then the callback receives the number of extents instead of the extents themselves (which is unreliable, see below). If an error occurs, the callback receives no arguments. The special "errno" value "IO::AIO::EBADR" is available to test for flag errors. Otherwise, the callback receives an array reference with extent structures. Each extent structure is an array reference itself, with the following members: [$logical, $physical, $length, $flags] Flags is any combination of the following flag values (typically either 0 or "IO::AIO::FIEMAP_EXTENT_LAST" (1)): "IO::AIO::FIEMAP_EXTENT_LAST", "IO::AIO::FIEMAP_EXTENT_UNKNOWN", "IO::AIO::FIEMAP_EXTENT_DELALLOC", "IO::AIO::FIEMAP_EXTENT_ENCODED", "IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED", "IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED", "IO::AIO::FIEMAP_EXTENT_DATA_INLINE", "IO::AIO::FIEMAP_EXTENT_DATA_TAIL", "IO::AIO::FIEMAP_EXTENT_UNWRITTEN", "IO::AIO::FIEMAP_EXTENT_MERGED" or "IO::AIO::FIEMAP_EXTENT_SHARED". At the time of this writing (Linux 3.2), this request is unreliable unless $count is "undef", as the kernel has all sorts of bugs preventing it to return all extents of a range for files with a large number of extents. The code (only) works around all these issues if $count is "undef". aio_group $callback->(...) This is a very special aio request: Instead of doing something, it is a container for other aio requests, which is useful if you want to bundle many requests into a single, composite, request with a definite callback and the ability to cancel the whole request with its subrequests. Returns an object of class IO::AIO::GRP. See its documentation below for more info. Example: my $grp = aio_group sub { print "all stats done\n"; }; add $grp (aio_stat ...), (aio_stat ...), ...; aio_nop $callback->() This is a special request - it does nothing in itself and is only used for side effects, such as when you want to add a dummy request to a group so that finishing the requests in the group depends on executing the given code. While this request does nothing, it still goes through the execution phase and still requires a worker thread. Thus, the callback will not be executed immediately but only after other requests in the queue have entered their execution phase. This can be used to measure request latency. IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED* Mainly used for debugging and benchmarking, this aio request puts one of the request workers to sleep for the given time. While it is theoretically handy to have simple I/O scheduling requests like sleep and file handle readable/writable, the overhead this creates is immense (it blocks a thread for a long time) so do not use this function except to put your application under artificial I/O pressure. IO::AIO::WD - multiple working directories Your process only has one current working directory, which is used by all threads. This makes it hard to use relative paths (some other component could call "chdir" at any time, and it is hard to control when the path will be used by IO::AIO). One solution for this is to always use absolute paths. This usually works, but can be quite slow (the kernel has to walk the whole path on every access), and can also be a hassle to implement. Newer POSIX systems have a number of functions (openat, fdopendir, futimensat and so on) that make it possible to specify working directories per operation. For portability, and because the clowns who "designed", or shall I write, perpetrated this new interface were obviously half-drunk, this abstraction cannot be perfect, though. IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD object. This object stores the canonicalised, absolute version of the path, and on systems that allow it, also a directory file descriptor. Everywhere where a pathname is accepted by IO::AIO (e.g. in "aio_stat" or "aio_unlink"), one can specify an array reference with an IO::AIO::WD object and a pathname instead (or the IO::AIO::WD object alone, which gets interpreted as "[$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 }; }; The fact 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 "aio_realpath") will always rely on the string form of the pathname. So this functionality 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. 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. For example, these calls are functionally identical: aio_stat "somefile", sub { ... }; aio_stat [IO::AIO::CWD, "somefile"], sub { ... }; To recover the path associated with an IO::AIO::WD object, you can use "aio_realpath": aio_realpath $wd, sub { warn "path is $_[0]\n"; }; Currently, "aio_statvfs" always, and "aio_rename" and "aio_rmdir" sometimes, fall back to using an absolue path. IO::AIO::REQ CLASS All non-aggregate "aio_*" functions return an object of this class when called in non-void context. cancel $req Cancels the request, if possible. Has the effect of skipping execution when entering the execute state and skipping calling the callback when entering the the result state, but will leave the request otherwise untouched (with the exception of readdir). That means that requests that currently execute will not be stopped and resources held by the request will not be freed prematurely. cb $req $callback->(...) Replace (or simply set) the callback registered to the request. IO::AIO::GRP CLASS This class is a subclass of IO::AIO::REQ, so all its methods apply to objects of this class, too. A IO::AIO::GRP object is a special request that can contain multiple other aio requests. You create one by calling the "aio_group" constructing function with a callback that will be called when all contained requests have entered the "done" state: my $grp = aio_group sub { print "all requests are done\n"; }; You add requests by calling the "add" method with one or more "IO::AIO::REQ" objects: $grp->add (aio_unlink "..."); add $grp aio_stat "...", sub { $_[0] or return $grp->result ("error"); # add another request dynamically, if first succeeded add $grp aio_open "...", sub { $grp->result ("ok"); }; }; This makes it very easy to create composite requests (see the source of "aio_move" for an application) that work and feel like simple requests. * The IO::AIO::GRP objects will be cleaned up during calls to "IO::AIO::poll_cb", just like any other request. * They can be canceled like any other request. Canceling will cancel not only the request itself, but also all requests it contains. * They can also can also be added to other IO::AIO::GRP objects. * You must not add requests to a group from within the group callback (or any later time). Their lifetime, simplified, looks like this: when they are empty, they will finish very quickly. If they contain only requests that are in the "done" state, they will also finish. Otherwise they will continue to exist. That means after creating a group you have some time to add requests (precisely before the callback has been invoked, which is only done within the "poll_cb"). And in the callbacks of those requests, you can add further requests to the group. And only when all those requests have finished will the the group itself finish. add $grp ... $grp->add (...) Add one or more requests to the group. Any type of IO::AIO::REQ can be added, including other groups, as long as you do not create circular dependencies. Returns all its arguments. $grp->cancel_subs Cancel all subrequests and clears any feeder, but not the group request itself. Useful when you queued a lot of events but got a result early. The group request will finish normally (you cannot add requests to the group). $grp->result (...) Set the result value(s) that will be passed to the group callback when all subrequests have finished and set the groups errno to the current value of errno (just like calling "errno" without an error number). By default, no argument will be passed and errno is zero. $grp->errno ([$errno]) Sets the group errno value to $errno, or the current value of errno when the argument is missing. Every aio request has an associated errno value that is restored when the callback is invoked. This method lets you change this value from its default (0). Calling "result" will also set errno, so make sure you either set $! before the call to "result", or call c after it. feed $grp $callback->($grp) Sets a feeder/generator on this group: every group can have an attached generator that generates requests if idle. The idea behind 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 of "aio_stat" requests, delaying any later requests for a long time. To avoid this, and allow incremental generation of requests, you can instead a group and set a feeder on it that generates those requests. The feed callback will be called whenever there are few enough (see "limit", below) requests active in the group itself and is expected to queue more requests. The feed callback can queue as many requests as it likes (i.e. "add" does not impose any limits). If the feed does not queue more requests when called, it will be automatically removed from the group. If the feed limit is 0 when this method is called, it will be set to 2 automatically. Example: # stat all files in @files, but only ever use four aio requests concurrently: my $grp = aio_group sub { print "finished\n" }; limit $grp 4; feed $grp sub { my $file = pop @files or return; add $grp aio_stat $file, sub { ... }; }; limit $grp $num Sets the feeder limit for the group: The feeder will be called whenever the group contains less than this many requests. Setting the limit to 0 will pause the feeding process. The default value for the limit is 0, but note that setting a feeder automatically bumps it up to 2. SUPPORT FUNCTIONS EVENT PROCESSING AND EVENT LOOP INTEGRATION $fileno = IO::AIO::poll_fileno Return the *request result pipe file descriptor*. This filehandle must be polled for reading by some mechanism outside this module (e.g. EV, Glib, select and so on, see below or the SYNOPSIS). If the pipe becomes readable you have to call "poll_cb" to check the results. See "poll_cb" for an example. IO::AIO::poll_cb Process some requests that have reached the result phase (i.e. they have been executed but the results are not yet reported). You have to call this "regularly" to finish outstanding requests. 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", "IO::AIO::max_poll_time" and "IO::AIO::max_outstanding". If not all requests were processed for whatever reason, the poll file descriptor 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): Event->io (fd => IO::AIO::poll_fileno, poll => 'r', async => 1, cb => \&IO::AIO::poll_cb); IO::AIO::poll_wait Wait until either at least one request is in the result phase or no requests are outstanding anymore. This is useful if you want to synchronously wait for some requests to become ready, without actually handling them. See "nreqs" for an example. IO::AIO::poll Waits until some requests have been handled. Returns the number of requests processed, but is otherwise strictly equivalent to: IO::AIO::poll_wait, IO::AIO::poll_cb IO::AIO::flush Wait till all outstanding AIO requests have been handled. Strictly equivalent to: IO::AIO::poll_wait, IO::AIO::poll_cb while IO::AIO::nreqs; IO::AIO::max_poll_reqs $nreqs IO::AIO::max_poll_time $seconds These set the maximum number of requests (default 0, meaning infinity) that are being processed by "IO::AIO::poll_cb" in one call, respectively the maximum amount of time (default 0, meaning infinity) spent in "IO::AIO::poll_cb" to process requests (more correctly the mininum amount of time "poll_cb" is allowed to use). Setting "max_poll_time" to a non-zero value creates an overhead of one syscall per request processed, which is not normally a problem unless your callbacks are really really fast or your OS is really really slow (I am not mentioning Solaris here). Using "max_poll_reqs" incurs no overhead. Setting these is useful if you want to ensure some level of interactiveness when perl is not fast enough to process all requests in time. For interactive programs, values such as 0.01 to 0.1 should be fine. Example: Install an Event watcher that automatically calls IO::AIO::poll_cb with low priority, to ensure that other parts of the program get the CPU sometimes even under high AIO load. # try not to spend much more than 0.1s in poll_cb IO::AIO::max_poll_time 0.1; # use a low priority so other tasks have priority Event->io (fd => IO::AIO::poll_fileno, poll => 'r', nice => 1, cb => &IO::AIO::poll_cb); CONTROLLING THE NUMBER OF THREADS IO::AIO::min_parallel $nthreads Set the minimum number of AIO threads to $nthreads. The current default is 8, which means eight asynchronous operations can execute concurrently at any one time (the number of outstanding requests, however, is unlimited). IO::AIO starts threads only on demand, when an AIO request is queued and no free thread exists. Please note that queueing up a hundred requests can create demand for a hundred threads, even if it turns out that everything is in the cache and could have been processed faster by a single thread. It is recommended to keep the number of threads relatively low, as some Linux kernel versions will scale negatively with the number of threads (higher parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 threads should be fine. Under most circumstances you don't need to call this function, as the module selects a default that is suitable for low to moderate load. IO::AIO::max_parallel $nthreads Sets the maximum number of AIO threads to $nthreads. If more than the specified number of threads are currently running, this function kills them. This function blocks until the limit is reached. While $nthreads are zero, aio requests get queued but not executed until the number of threads has been increased again. This module automatically runs "max_parallel 0" at program end, to ensure that all threads are killed and that there are no outstanding requests. Under normal circumstances you don't need to call this function. 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 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 resources under normal circumstances (1000 threads can easily consume 30MB of RAM). The default is probably ok in most situations, especially if thread 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. Its main use is in scripts without an event loop - when you want to stat a lot of files, you can write something 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 Returns the number of requests currently in the ready, execute or pending states (i.e. for which their callback has not been invoked yet). Example: wait till there are no outstanding requests anymore: IO::AIO::poll_wait, IO::AIO::poll_cb while IO::AIO::nreqs; IO::AIO::nready Returns the number of requests currently in the ready state (not yet executed). IO::AIO::npending Returns the number of requests currently in the pending state (executed, but not yet processed by poll_cb). SUBSECOND STAT TIME ACCESS Both "aio_stat"/"aio_lstat" and perl's "stat"/"lstat" functions can generally find access/modification and change times with subsecond time accuracy of the system supports it, but perl's built-in functions only return the integer part. The following functions return the timestamps of the most recent stat with subsecond precision on most systems and work both after "aio_stat"/"aio_lstat" and perl's "stat"/"lstat" calls. Their return value is only meaningful after a successful "stat"/"lstat" call, or during/after a successful "aio_stat"/"aio_lstat" callback. This is similar to the Time::HiRes "stat" functions, but can return full resolution without rounding and work with standard perl "stat", alleviating the need to call the special "Time::HiRes" functions, which do not act like their perl counterparts. On operating systems or file systems where subsecond time resolution is not supported or could not be detected, a fractional part of 0 is returned, so it is always safe to call these functions. $seconds = IO::AIO::st_atime, IO::AIO::st_mtime, IO::AIO::st_ctime Return the access, modication or change time, respectively, including fractional part. Due to the limited precision of floating point, the accuracy on most platforms is only a bit better than milliseconds for times around now - see the *nsec* function family, below, for full accuracy. ($atime, $mtime, $ctime, ...) = IO::AIO::st_xtime Returns access, modification and change time all in one go, and maybe more times in the future version. $nanoseconds = IO::AIO::st_atimensec, IO::AIO::st_mtimensec, IO::AIO::st_ctimensec Return the fractional access, modifcation or change time, in nanoseconds, as an integer in the range 0 to 999999999. ($atime, $mtime, $ctime, ...) = IO::AIO::st_xtimensec Like the functions above, but returns all three times in one go (and maybe more in future versions). Example: print the high resolution modification time of /etc, using "stat", and "IO::AIO::aio_stat". if (stat "/etc") { printf "stat(/etc) mtime: %f\n", IO::AIO::st_mtime; } IO::AIO::aio_stat "/etc", sub { $_[0] and return; printf "aio_stat(/etc) mtime: %d.%09d\n", (stat _)[9], IO::AIO::st_mtimensec; }; IO::AIO::flush; Output of the awbove on my system, showing reduced and full accuracy: stat(/etc) mtime: 1534043702.020808 aio_stat(/etc) mtime: 1534043702.020807792 MISCELLANEOUS FUNCTIONS IO::AIO implements some functions that are useful when you want to use some "Advanced I/O" function not available to in Perl, without going the "Asynchronous I/O" route. Many of these have an asynchronous "aio_*" counterpart. $numfd = IO::AIO::get_fdlimit This function is *EXPERIMENTAL* and subject to change. Tries to find the current file descriptor limit and returns it, or "undef" and sets $! in case of an error. The limit is one larger than the highest valid file descriptor number. IO::AIO::min_fdlimit [$numfd] This function is *EXPERIMENTAL* and subject to change. Try to increase the current file descriptor limit(s) to at least $numfd by changing the soft or hard file descriptor resource limit. If $numfd is missing, it will try to set a very high limit, although this is not recommended when you know the actual minimum that you require. If the limit cannot be raised enough, the function makes a best-effort attempt to increase the limit as much as possible, using various tricks, while still failing. You can query the resulting limit using "IO::AIO::get_fdlimit". If an error occurs, returns "undef" and sets $!, otherwise returns true. IO::AIO::sendfile $ofh, $ifh, $offset, $count Calls the "eio_sendfile_sync" function, which is like "aio_sendfile", but is blocking (this makes most sense if you know the input data is likely cached already and the output filehandle is set to non-blocking operations). Returns the number of bytes copied, or -1 on error. IO::AIO::fadvise $fh, $offset, $len, $advice Simply calls the "posix_fadvise" function (see its manpage for 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". On systems that do not implement "posix_fadvise", this function returns ENOSYS, otherwise the return value of "posix_fadvise". IO::AIO::madvise $scalar, $offset, $len, $advice Simply calls the "posix_madvise" function (see its manpage for 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". If $offset is negative, counts from the end. If $length is negative, the remaining length of the $scalar is used. If possible, $length will be reduced to fit into the $scalar. On systems that do not implement "posix_madvise", this function returns ENOSYS, otherwise the return value of "posix_madvise". 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 available: "IO::AIO::PROT_NONE", "IO::AIO::PROT_READ", "IO::AIO::PROT_WRITE", "IO::AIO::PROT_EXEC". If $offset is negative, counts from the end. If $length is negative, the remaining length of the $scalar is used. If possible, $length will be reduced to fit into the $scalar. On systems that do not implement "mprotect", this function returns ENOSYS, otherwise the return value of "mprotect". IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset] Memory-maps a file (or anonymous memory range) and attaches it to the given $scalar, which will act like a string scalar. Returns true on success, and false otherwise. The scalar must exist, but its contents do not matter - this means you cannot use a nonexistant array or hash element. When in doubt, "undef" the scalar first. The only operations allowed on the mmapped scalar are "substr"/"vec", which don't change the string length, and most read-only operations such as copying it or searching it with regexes and so on. Anything else is unsafe and will, at best, result in memory leaks. The memory map associated with the $scalar is automatically removed when the $scalar is undef'd or destroyed, or when the "IO::AIO::mmap" or "IO::AIO::munmap" functions are called on it. This calls the "mmap"(2) function internally. See your system's manual page for details on the $length, $prot and $flags parameters. The $length must be larger than zero and smaller than the actual filesize. $prot is a combination of "IO::AIO::PROT_NONE", "IO::AIO::PROT_EXEC", "IO::AIO::PROT_READ" and/or "IO::AIO::PROT_WRITE", $flags can be a combination of "IO::AIO::MAP_SHARED" or "IO::AIO::MAP_PRIVATE", or a number of system-specific flags (when not available, the are 0): "IO::AIO::MAP_ANONYMOUS" (which is set to "MAP_ANON" if your system only provides this constant), "IO::AIO::MAP_LOCKED", "IO::AIO::MAP_NORESERVE", "IO::AIO::MAP_POPULATE", "IO::AIO::MAP_NONBLOCK", "IO::AIO::MAP_FIXED", "IO::AIO::MAP_GROWSDOWN", "IO::AIO::MAP_32BIT", "IO::AIO::MAP_HUGETLB" or "IO::AIO::MAP_STACK". If $fh is "undef", then a file descriptor of -1 is passed. $offset is the offset from the start of the file - it generally must be a multiple of "IO::AIO::PAGESIZE" and defaults to 0. Example: use Digest::MD5; use IO::AIO; open my $fh, "io (fd => IO::AIO::poll_fileno, poll => 'r', cb => \&IO::AIO::poll_cb); # Glib/Gtk2 integration add_watch Glib::IO IO::AIO::poll_fileno, in => sub { IO::AIO::poll_cb; 1 }; # Tk integration Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", readable => \&IO::AIO::poll_cb); # Danga::Socket integration Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => \&IO::AIO::poll_cb); FORK BEHAVIOUR 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. LINUX-SPECIFIC CALLS When a call is documented as "linux-specific" then this means it originated on GNU/Linux. "IO::AIO" will usually try to autodetect the availability and compatibility of such calls regardless of the platform it is compiled on, so platforms such as FreeBSD which often implement these calls will work. When in doubt, call them and see if they fail wth "ENOSYS". MEMORY USAGE Per-request usage: Each aio request uses - depending on your architecture - around 100-200 bytes of memory. In addition, stat requests need a stat buffer (possibly a few hundred bytes), readdir requires a result buffer and so on. Perl scalars and other data passed into aio requests will also be locked and will consume memory till the request has entered the done state. This is not awfully much, so queuing lots of requests is not usually a problem. Per-thread usage: In the execution phase, some aio requests require more memory for temporary buffers, and each thread requires a stack and other data structures (usually around 16k-128k, depending on the OS). KNOWN BUGS Known bugs will be fixed in the next release :) KNOWN ISSUES Calls that try to "import" foreign memory areas (such as "IO::AIO::mmap" or "IO::AIO::aio_slurp") do not work with generic lvalues, such as non-created hash slots or other scalars I didn't think of. It's best to avoid such and either use scalar variables or making sure that the scalar exists (e.g. by storing "undef") and isn't "funny" (e.g. tied). I am not sure anything can be done about this, so this is considered a known issue, rather than a bug. SEE ALSO AnyEvent::AIO for easy integration into event loops, Coro::AIO for a more natural syntax. AUTHOR Marc Lehmann http://home.schmorp.de/