--- IO-AIO/README 2011/07/18 03:09:06 1.49 +++ IO-AIO/README 2016/01/18 11:53:09 1.57 @@ -66,7 +66,6 @@ This is a simple example that uses the EV module and loads /etc/passwd asynchronously: - use Fcntl; use EV; use IO::AIO; @@ -93,7 +92,7 @@ print $contents; # exit event loop and program - EV::unloop; + EV::break; }; }; @@ -101,7 +100,7 @@ # check for sockets etc. etc. # process events as long as there are some: - EV::loop; + EV::run; REQUEST ANATOMY AND LIFETIME Every "aio_*" function creates a request. which is a C data structure @@ -148,12 +147,14 @@ FUNCTIONS QUICK OVERVIEW - This section simply lists the prototypes of the most important functions - for quick reference. See the following sections for function-by-function + 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) @@ -163,14 +164,16 @@ 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_truncate $fh_or_path, $offset, $callback->($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 $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_realpath $path, $callback->($link) + aio_readlink $pathname, $callback->($link) + aio_realpath $pathname, $callback->($path) aio_rename $srcpath, $dstpath, $callback->($status) aio_mkdir $pathname, $mode, $callback->($status) aio_rmdir $pathname, $callback->($status) @@ -178,16 +181,17 @@ 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) @@ -215,19 +219,26 @@ 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::madvise $scalar, $offset, $length, $advice IO::AIO::mprotect $scalar, $offset, $length, $protect IO::AIO::munlock $scalar, $offset = 0, $length = undef IO::AIO::munlockall - AIO REQUEST FUNCTIONS + 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 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. @@ -235,23 +246,27 @@ 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. + 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. @@ -283,7 +298,8 @@ 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. + 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. @@ -316,7 +332,8 @@ "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". + "O_DSYNC", "O_RSYNC", "O_SYNC", "O_PATH", "O_TMPFILE", and + "O_TTY_INIT". aio_close $fh, $callback->($status) Asynchronously close a file and call the callback with the result @@ -333,6 +350,25 @@ 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 @@ -496,6 +532,91 @@ fsid => 1810 } + Here is a (likely partial - send me updates!) list of fsid values + used by Linux - it is safe to hardcode these when $^O is "linux": + + 0x0000adf5 adfs + 0x0000adff affs + 0x5346414f afs + 0x09041934 anon-inode filesystem + 0x00000187 autofs + 0x42465331 befs + 0x1badface bfs + 0x42494e4d binfmt_misc + 0x9123683e btrfs + 0x0027e0eb cgroupfs + 0xff534d42 cifs + 0x73757245 coda + 0x012ff7b7 coh + 0x28cd3d45 cramfs + 0x453dcd28 cramfs-wend (wrong endianness) + 0x64626720 debugfs + 0x00001373 devfs + 0x00001cd1 devpts + 0x0000f15f ecryptfs + 0x00414a53 efs + 0x0000137d ext + 0x0000ef53 ext2/ext3/ext4 + 0x0000ef51 ext2 + 0xf2f52010 f2fs + 0x00004006 fat + 0x65735546 fuseblk + 0x65735543 fusectl + 0x0bad1dea futexfs + 0x01161970 gfs2 + 0x47504653 gpfs + 0x00004244 hfs + 0xf995e849 hpfs + 0x00c0ffee hostfs + 0x958458f6 hugetlbfs + 0x2bad1dea inotifyfs + 0x00009660 isofs + 0x000072b6 jffs2 + 0x3153464a jfs + 0x6b414653 k-afs + 0x0bd00bd0 lustre + 0x0000137f minix + 0x0000138f minix 30 char names + 0x00002468 minix v2 + 0x00002478 minix v2 30 char names + 0x00004d5a minix v3 + 0x19800202 mqueue + 0x00004d44 msdos + 0x0000564c novell + 0x00006969 nfs + 0x6e667364 nfsd + 0x00003434 nilfs + 0x5346544e ntfs + 0x00009fa1 openprom + 0x7461636F ocfs2 + 0x00009fa0 proc + 0x6165676c pstorefs + 0x0000002f qnx4 + 0x68191122 qnx6 + 0x858458f6 ramfs + 0x52654973 reiserfs + 0x00007275 romfs + 0x67596969 rpc_pipefs + 0x73636673 securityfs + 0xf97cff8c selinux + 0x0000517b smb + 0x534f434b sockfs + 0x73717368 squashfs + 0x62656572 sysfs + 0x012ff7b6 sysv2 + 0x012ff7b5 sysv4 + 0x01021994 tmpfs + 0x15013346 udf + 0x00011954 ufs + 0x54190100 ufs byteswapped + 0x00009fa2 usbdevfs + 0x01021997 v9fs + 0xa501fcf5 vxfs + 0xabba1974 xenfs + 0x012ff7b4 xenix + 0x58465342 xfs + 0x012fd16d xia + 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 @@ -527,6 +648,24 @@ 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) and "FALLOC_FL_ZERO_RANGE", to zero a range + (see your fallocate(2) manpage). + + The file system block size used by "fallocate" is presumably the + "f_bsize" returned by "statvfs". + + 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. @@ -534,14 +673,14 @@ 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. @@ -555,14 +694,14 @@ $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 $path, $callback->($path) + 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 + $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 @@ -572,6 +711,10 @@ 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_mkdir $pathname, $mode, $callback->($status) Asynchronously mkdir (create) a directory and call the callback with the result code. $mode will be modified by the umask at the time the @@ -581,6 +724,10 @@ Asynchronously rmdir (delete) a directory and call the callback with the result code. + On systems that support the AIO::WD working directory abstraction + natively, the case "[$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 @@ -590,9 +737,9 @@ 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 @@ -647,11 +794,11 @@ 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. @@ -678,7 +825,7 @@ 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 @@ -721,7 +868,7 @@ 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 @@ -737,7 +884,7 @@ 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 @@ -757,6 +904,12 @@ 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 @@ -769,7 +922,7 @@ "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 @@ -806,7 +959,7 @@ 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 page s(by reading + "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) @@ -849,6 +1002,54 @@ 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 requets 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 large + number of extents. The code works around all these issues if $count + is undef. + aio_group $callback->(...) This is a very special aio request: Instead of doing something, it is a container for other aio requests, which is useful if you want @@ -892,6 +1093,124 @@ not use this function except to put your application under artificial I/O pressure. + IO::AIO::WD - multiple working directories + Your process only has one current working directory, which is used by + all threads. This makes it hard to use relative paths (some other + component could call "chdir" at any time, and it is hard to control when + the path will be used by IO::AIO). + + One solution for this is to always use absolute paths. This usually + works, but can be quite slow (the kernel has to walk the whole path on + every access), and can also be a hassle to implement. + + Newer POSIX systems have a number of functions (openat, fdopendir, + futimensat and so on) that make it possible to specify working + directories per operation. + + For portability, and because the clowns who "designed", or shall I + write, perpetrated this new interface were obviously half-drunk, this + abstraction cannot be perfect, though. + + IO::AIO allows you to convert directory paths into a so-called + IO::AIO::WD object. This object stores the canonicalised, absolute + version of the path, and on systems that allow it, also a directory file + descriptor. + + Everywhere where a pathname is accepted by IO::AIO (e.g. in "aio_stat" + or "aio_unlink"), one can specify an array reference with an IO::AIO::WD + object and a pathname instead (or the IO::AIO::WD object alone, which + gets interpreted as "[$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 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. @@ -1000,7 +1319,7 @@ 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 @@ -1052,16 +1371,20 @@ See "poll_cb" for an example. 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 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. + 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 @@ -1079,10 +1402,11 @@ cb => \&IO::AIO::poll_cb); IO::AIO::poll_wait - If there are any outstanding requests and none of them in the result - phase, wait till the result filehandle becomes ready for reading - (simply does a "select" on the filehandle. This is useful if you - want to synchronously wait for some requests to finish). + 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. @@ -1204,7 +1528,7 @@ it blocks, and a bad way to reduce concurrency because it is inexact: Better use an "aio_group" together with a feed callback. - It's main use is in scripts without an event loop - when you want to + Its 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; @@ -1245,8 +1569,10 @@ (executed, but not yet processed by poll_cb). MISCELLANEOUS FUNCTIONS - IO::AIO implements some functions that might be useful, but are not - asynchronous. + 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. IO::AIO::sendfile $ofh, $ifh, $offset, $count Calls the "eio_sendfile_sync" function, which is like @@ -1258,7 +1584,7 @@ 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". @@ -1268,7 +1594,7 @@ 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". @@ -1279,7 +1605,7 @@ 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 @@ -1287,7 +1613,8 @@ 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. + the given $scalar, which will act like a string scalar. Returns true + on success, and false otherwise. The only operations allowed on the scalar are "substr"/"vec" that don't change the string length, and most read-only operations such @@ -1311,11 +1638,13 @@ $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 defined as 0): "IO::AIO::MAP_ANONYMOUS" - (which is set to "MAP_ANON" if your system only provides this - constant), "IO::AIO::MAP_HUGETLB", "IO::AIO::MAP_LOCKED", - "IO::AIO::MAP_NORESERVE", "IO::AIO::MAP_POPULATE" or - "IO::AIO::MAP_NONBLOCK" + 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_HUGETLB", "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. @@ -1348,6 +1677,50 @@ On systems that do not implement "munlockall", this function returns ENOSYS, otherwise the return value of "munlockall". + IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags + Calls the GNU/Linux splice(2) syscall, if available. If $r_off or + $w_off are "undef", then "NULL" is passed for these, otherwise they + should be the file offset. + + $r_fh and $w_fh should not refer to the same file, as splice might + silently corrupt the data in this case. + + The following symbol flag values are available: + "IO::AIO::SPLICE_F_MOVE", "IO::AIO::SPLICE_F_NONBLOCK", + "IO::AIO::SPLICE_F_MORE" and "IO::AIO::SPLICE_F_GIFT". + + See the splice(2) manpage for details. + + IO::AIO::tee $r_fh, $w_fh, $length, $flags + Calls the GNU/Linux tee(2) syscall, see its manpage and the + description for "IO::AIO::splice" above for details. + + $actual_size = IO::AIO::pipesize $r_fh[, $new_size] + Attempts to query or change the pipe buffer size. Obviously works + only on pipes, and currently works only on GNU/Linux systems, and + fails with -1/"ENOSYS" everywhere else. If anybody knows how to + influence pipe buffer size on other systems, drop me a note. + + ($rfh, $wfh) = IO::AIO::pipe2 [$flags] + This is a direct interface to the Linux pipe2(2) system call. If + $flags is missing or 0, then this should be the same as a call to + perl's built-in "pipe" function and create a new pipe, and works on + systems that lack the pipe2 syscall. On win32, this case invokes + "_pipe (..., 4096, O_BINARY)". + + If $flags is non-zero, it tries to invoke the pipe2 system call with + the given flags (Linux 2.6.27, glibc 2.9). + + On success, the read and write file handles are returned. + + On error, nothing will be returned. If the pipe2 syscall is missing + and $flags is non-zero, fails with "ENOSYS". + + Please refer to pipe2(2) for more info on the $flags, but at the + time of this writing, "IO::AIO::O_CLOEXEC", "IO::AIO::O_NONBLOCK" + and "IO::AIO::O_DIRECT" (Linux 3.4, for packet-based pipes) were + supported. + EVENT LOOP INTEGRATION It is recommended to use AnyEvent::AIO to integrate IO::AIO automatically into many event loops: @@ -1395,9 +1768,9 @@ You could also try to call the IO::AIO::reinit function in the child: IO::AIO::reinit - Abondons all current requests and I/O threads and simply + Abandons all current requests and I/O threads and simply reinitialises all data structures. This is not an operation - suppported by any standards, but happens to work on GNU/Linux and + 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