--- IO-AIO/README 2011/03/27 10:26:08 1.46 +++ IO-AIO/README 2019/03/04 10:28:38 1.63 @@ -1,5 +1,5 @@ NAME - IO::AIO - Asynchronous Input/Output + IO::AIO - Asynchronous/Advanced Input/Output SYNOPSIS use IO::AIO; @@ -57,6 +57,10 @@ 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 @@ -66,7 +70,6 @@ This is a simple example that uses the EV module and loads /etc/passwd asynchronously: - use Fcntl; use EV; use IO::AIO; @@ -93,7 +96,7 @@ print $contents; # exit event loop and program - EV::unloop; + EV::break; }; }; @@ -101,7 +104,7 @@ # 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 +151,14 @@ 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) @@ -163,31 +168,38 @@ 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_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_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_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 $path, $callback->($status) - aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($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) @@ -211,22 +223,32 @@ 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 - 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. @@ -234,23 +256,27 @@ 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. @@ -282,7 +308,8 @@ 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. @@ -308,6 +335,16 @@ } }; + 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. @@ -323,12 +360,31 @@ 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 without the actual number of bytes read (or -1 on - error, just like the syscall). + 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. @@ -360,13 +416,15 @@ reading at byte offset $in_offset, and starts writing at the current file offset of $out_fh. Because of that, it is not safe to issue more than one "aio_sendfile" per $out_fh, as they will interfere - with each other. + with each other. The same $in_fh works fine though, as this function + does not move or use the file offset of $in_fh. Please note that "aio_sendfile" can read more bytes from $in_fh than - are written, and there is no way to find out how many bytes have - been read from "aio_sendfile" alone, as "aio_sendfile" only provides - the number of bytes written to $out_fh. Only if the result value - equals $length one can assume that $length bytes have been read. + are written, and there is no way to find out how many more bytes + have been read from "aio_sendfile" alone, as "aio_sendfile" only + provides the number of bytes written to $out_fh. Only if the result + value equals $length one can assume that $length bytes have been + read. Unlike with other "aio_" functions, it makes a lot of sense to use "aio_sendfile" on non-blocking sockets, as long as one end @@ -376,17 +434,25 @@ some data with readahead, then fails to write all data, and when the socket is ready the next time, the data in the cache is already lost, forcing "aio_sendfile" to again hit the disk. Explicit - "aio_read" + "aio_write" let's you control resource usage much - better. + "aio_read" + "aio_write" let's you better control resource usage. - This call tries to make use of a native "sendfile" syscall to + This call tries to make use of a native "sendfile"-like syscall to provide zero-copy operation. For this to work, $out_fh should refer to a socket, and $in_fh should refer to an mmap'able file. If a native sendfile cannot be found or it fails with "ENOSYS", - "ENOTSUP", "EOPNOTSUPP", "EAFNOSUPPORT", "EPROTOTYPE" or "ENOTSOCK", - it will be emulated, so you can call "aio_sendfile" on any type of - filehandle regardless of the limitations of the operating system. + "EINVAL", "ENOTSUP", "EOPNOTSUPP", "EAFNOSUPPORT", "EPROTOTYPE" or + "ENOTSOCK", it will be emulated, so you can call "aio_sendfile" on + any type of filehandle regardless of the limitations of the + operating system. + + As native sendfile syscalls (as practically any non-POSIX interface + hacked together in a hurry to improve benchmark numbers) tend to be + rather buggy on many systems, this implementation tries to work + around some known bugs in Linux and FreeBSD kernels (probably + others, too), but that might fail, so you really really should check + the return value of "aio_sendfile" - 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 @@ -399,15 +465,16 @@ 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 OS isn't Linux) it + 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... + Works almost exactly 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 _" and other tests (with the + exception of "-B" and "-T"). The pathname passed to "aio_stat" must be absolute. See API NOTES, above, for an explanation. @@ -426,6 +493,9 @@ "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 { @@ -481,9 +551,10 @@ $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. + When called with a pathname, uses utimensat(2) or utimes(2) if + available, otherwise utime(2). If called on a file descriptor, uses + futimens(2) or futimes(2) if available, otherwise returns ENOSYS, so + this is not portable. Examples: @@ -507,6 +578,27 @@ 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. @@ -514,14 +606,14 @@ 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. @@ -535,15 +627,42 @@ $srcpath at the path $dstpath and call the callback with the result code. - aio_readlink $path, $callback->($link) + aio_readlink $pathname, $callback->($link) Asynchronously read the symlink specified by $path and pass it to the callback. If an error occurs, nothing or undef gets passed to the callback. + aio_realpath $pathname, $callback->($path) + Asynchronously make the path absolute and resolve any symlinks in + $path. The resulting path only consists of directories (same as + Cwd::realpath). + + This request can be used to get the absolute path of the current + working directory by passing it a path of . (a single dot). + aio_rename $srcpath, $dstpath, $callback->($status) Asynchronously rename the object at $srcpath to $dstpath, just as rename(2) and call the callback with the result code. + On systems that support the AIO::WD working directory abstraction + natively, the case "[$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. $mode will be modified by the umask at the time the @@ -553,6 +672,10 @@ Asynchronously rmdir (delete) a directory and call the callback with the result code. + On systems that support the AIO::WD working directory abstraction + natively, the case "[$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 @@ -562,19 +685,19 @@ an array-ref with the filenames. aio_readdirx $pathname, $flags, $callback->($entries, $flags) - Quite similar to "aio_readdir", but the $flags argument allows to - tune behaviour and output format. In case of an error, $entries will - be "undef". + Quite similar to "aio_readdir", but the $flags argument allows one + to tune behaviour and output format. In case of an error, $entries + will be "undef". The flags are a combination of the following constants, ORed together (the flags will also be passed to the callback, possibly modified): IO::AIO::READDIR_DENTS - When this flag is off, then the callback gets an arrayref with - of names only (as with "aio_readdir"), otherwise it gets an - arrayref with "[$name, $type, $inode]" arrayrefs, each - describing a single directory entry in more detail. + Normally the callback gets an arrayref consisting of names only + (as with "aio_readdir"). If this flag is set, then the callback + gets an arrayref with "[$name, $type, $inode]" arrayrefs, each + describing a single directory entry in more detail: $name is the name of the entry. @@ -585,9 +708,9 @@ "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 - reasons, the $type scalars are read-only: you can not modify - them. + 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 @@ -596,41 +719,75 @@ IO::AIO::READDIR_DIRS_FIRST When this flag is set, then the names will be returned in an - order where likely directories come first. This is useful when - you need to quickly find directories, or you want to find all - directories while avoiding to stat() each entry. + order where likely directories come first, in optimal stat + order. This is useful when you need to quickly find directories, + or you want to find all directories while avoiding to stat() + each entry. If the system returns type information in readdir, then this is used to find directories directly. Otherwise, likely directories - are files beginning with ".", or otherwise files with no dots, - of which files with short names are tried first. + are names beginning with ".", or otherwise names with no dots, + of which names with short names are tried first. IO::AIO::READDIR_STAT_ORDER When this flag is set, then the names will be returned in an order suitable for stat()'ing each one. That is, when you plan - to stat() all files in the given directory, then the returned - order will likely be fastest. + 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. + 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 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_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 @@ -649,15 +806,15 @@ 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 you cannot recurse into (everything else, including symlinks to directories). - "aio_scandir" is a composite request that creates of many sub - requests_ $maxreq specifies the maximum number of outstanding aio + "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). @@ -692,7 +849,7 @@ 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 @@ -708,12 +865,60 @@ 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 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. @@ -728,6 +933,12 @@ 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 @@ -740,7 +951,7 @@ "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 @@ -753,7 +964,7 @@ Passes 0 when everything went ok, and -1 on error. - aio_msync $scalar, $offset = 0, $length = undef, flags = 0, + 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 @@ -765,8 +976,8 @@ 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 a combination of "IO::AIO::MS_ASYNC", - "IO::AIO::MS_INVALIDATE" and "IO::AIO::MS_SYNC". + 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) @@ -777,7 +988,7 @@ 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) @@ -807,10 +1018,13 @@ 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"). + of "IO::AIO::MCL_CURRENT", "IO::AIO::MCL_FUTURE" and + "IO::AIO::MCL_ONFAULT"). On systems that do not implement "mlockall", this function returns - -1 and sets errno to "ENOSYS". + -1 and sets errno to "ENOSYS". Similarly, flag combinations not + supported by the system result in a return value of -1 with errno + being set to "EINVAL". Note that the corresponding "munlockall" is synchronous and is documented under "MISCELLANEOUS FUNCTIONS". @@ -820,6 +1034,54 @@ 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 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 $callback->(...) This is a very special aio request: Instead of doing something, it is a container for other aio requests, which is useful if you want @@ -863,6 +1125,124 @@ not use this function except to put your application under artificial I/O pressure. + IO::AIO::WD - multiple working directories + Your process only has one current working directory, which is used by + all threads. This makes it hard to use relative paths (some other + component could call "chdir" at any time, and it is hard to control when + the path will be used by IO::AIO). + + One solution for this is to always use absolute paths. This usually + works, but can be quite slow (the kernel has to walk the whole path on + every access), and can also be a hassle to implement. + + Newer POSIX systems have a number of functions (openat, fdopendir, + futimensat and so on) that make it possible to specify working + directories per operation. + + For portability, and because the clowns who "designed", or shall I + write, perpetrated this new interface were obviously half-drunk, this + abstraction cannot be perfect, though. + + IO::AIO allows you to convert directory paths into a so-called + IO::AIO::WD object. This object stores the canonicalised, absolute + version of the path, and on systems that allow it, also a directory file + descriptor. + + Everywhere where a pathname is accepted by IO::AIO (e.g. in "aio_stat" + or "aio_unlink"), one can specify an array reference with an IO::AIO::WD + object and a pathname instead (or the IO::AIO::WD object alone, which + gets interpreted as "[$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 "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. @@ -971,7 +1351,7 @@ 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 @@ -1023,16 +1403,27 @@ 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 -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 + 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 @@ -1043,10 +1434,11 @@ 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. @@ -1066,6 +1458,17 @@ IO::AIO::poll_wait, IO::AIO::poll_cb while IO::AIO::nreqs; + This function can be useful at program aborts, to make sure + outstanding I/O has been done ("IO::AIO" uses an "END" block which + already calls this function on normal exits), or when you are merely + using "IO::AIO" for its more advanced functions, rather than for + async I/O, e.g.: + + my ($dirs, $nondirs); + IO::AIO::aio_scandir "/tmp", 0, sub { ($dirs, $nondirs) = @_ }; + IO::AIO::flush; + # $dirs, $nondirs are now set + IO::AIO::max_poll_reqs $nreqs IO::AIO::max_poll_time $seconds These set the maximum number of requests (default 0, meaning @@ -1155,22 +1558,39 @@ threads are allowed to exit. SEe "IO::AIO::max_idle". IO::AIO::max_outstanding $maxreqs + Sets the maximum number of outstanding requests to $nreqs. If you do + queue up more than this number of requests, the next call to + "IO::AIO::poll_cb" (and other functions calling "poll_cb", such as + "IO::AIO::flush" or "IO::AIO::poll") will block until the limit is + no longer exceeded. + + In other words, this setting does not enforce a queue limit, but can + be used to make poll functions block if the limit is exceeded. + This is a very bad function to use in interactive programs because it blocks, and a bad way to reduce concurrency because it is inexact: Better use an "aio_group" together with a feed callback. - Sets the maximum number of outstanding requests to $nreqs. If you do - queue up more than this number of requests, the next call to the - "poll_cb" (and "poll_some" and other functions calling "poll_cb") - function will block until the limit is no longer exceeded. - - The default value is very large, so there is no practical limit on - the number of outstanding requests. - - You can still queue as many requests as you want. Therefore, - "max_outstanding" is mainly useful in simple scripts (with low - values) or as a stop gap to shield against fatal memory overflow - (with large values). + 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 @@ -1191,9 +1611,120 @@ 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. + + $seconds = IO::AIO::st_atime, IO::AIO::st_mtime, IO::AIO::st_ctime, + IO::AIO::st_btime + Return the access, modication, change or birth time, respectively, + including fractional part. Due to the limited precision of floating + point, the accuracy on most platforms is only a bit better than + milliseconds for times around now - see the *nsec* function family, + below, for full accuracy. + + File birth time is only available when the OS and perl support it + (on FreeBSD and NetBSD at the time of this writing, although support + is adaptive, so if your OS/perl gains support, IO::AIO can take + avdantage of it). On systems where it isn't available, 0 is + currently returned, but this might change to "undef" in a future + version. + + ($atime, $mtime, $ctime, $btime, ...) = IO::AIO::st_xtime + Returns access, modification, change and birth 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, IO::AIO::st_btimensec + Return the fractional access, modifcation, change or birth time, in + nanoseconds, as an integer in the range 0 to 999999999. + + Note that no accessors are provided for access, modification and + change times - you need to get those from "stat _" if required ("int + IO::AIO::st_atime" and so on will *not* generally give you the + correct value). + + $seconds = IO::AIO::st_btimesec + The (integral) seconds part of the file birth time, if available. + + ($atime, $mtime, $ctime, $btime, ...) = IO::AIO::st_xtimensec + Like the functions above, but returns all four times in one go (and + maybe more in future versions). + + $counter = IO::AIO::st_gen + Returns the generation counter (in practice this is just a random + number) of the file. This is only available on platforms which have + this member in their "struct stat" (most BSDs at the time of this + writing) and generally only to the root usert. If unsupported, 0 is + returned, but this might change to "undef" in a future version. + + 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 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. + + $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 @@ -1205,7 +1736,7 @@ 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". @@ -1215,36 +1746,50 @@ 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". + 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 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". + 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. + 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 - as copying it or searching it with regexes and so on. + 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 destroyed, or when the "IO::AIO::mmap" or - "IO::AIO::munmap" functions are called. + 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. @@ -1258,11 +1803,13 @@ $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_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. @@ -1285,6 +1832,34 @@ IO::AIO::munmap $scalar Removes a previous mmap and undefines the $scalar. + IO::AIO::mremap $scalar, $new_length, $flags = MREMAP_MAYMOVE[, + $new_address = 0] + Calls the Linux-specific mremap(2) system call. The $scalar must + have been mapped by "IO::AIO::mmap", and $flags must currently + either be 0 or "IO::AIO::MREMAP_MAYMOVE". + + Returns true if successful, and false otherwise. If the underlying + mmapped region has changed address, then the true value has the + numerical value 1, otherwise it has the numerical value 0: + + my $success = IO::AIO::mremap $mmapped, 8192, IO::AIO::MREMAP_MAYMOVE + or die "mremap: $!"; + + if ($success*1) { + warn "scalar has chanegd address in memory\n"; + } + + "IO::AIO::MREMAP_FIXED" and the $new_address argument are currently + implemented, but not supported and might go away in a future + version. + + On systems where this call is not supported or is not emulated, this + call returns falls and sets $! to "ENOSYS". + + IO::AIO::mlockall $flags + Calls the "eio_mlockall_sync" function, which is like + "aio_mlockall", but is blocking. + IO::AIO::munlock $scalar, $offset = 0, $length = undef Calls the "munlock" function, undoing the effects of a previous "aio_mlock" call (see its description for details). @@ -1295,6 +1870,134 @@ 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 $flags, but at the + time of this writing, "IO::AIO::O_CLOEXEC", "IO::AIO::O_NONBLOCK" + and "IO::AIO::O_DIRECT" (Linux 3.4, for packet-based pipes) were + supported. + + Example: create a pipe race-free w.r.t. threads and fork: + + my ($rfh, $wfh) = IO::AIO::pipe2 IO::AIO::O_CLOEXEC + or die "pipe2: $!\n"; + + $fh = IO::AIO::eventfd [$initval, [$flags]] + This is a direct interface to the Linux eventfd(2) system call. The + (unhelpful) defaults for $initval and $flags are 0 for both. + + On success, the new eventfd filehandle is returned, otherwise + returns "undef". If the eventfd syscall is missing, fails with + "ENOSYS". + + Please refer to eventfd(2) for more info on this call. + + The following symbol flag values are available: + "IO::AIO::EFD_CLOEXEC", "IO::AIO::EFD_NONBLOCK" and + "IO::AIO::EFD_SEMAPHORE" (Linux 2.6.30). + + Example: create a new eventfd filehandle: + + $fh = IO::AIO::eventfd 0, IO::AIO::O_CLOEXEC + or die "eventfd: $!\n"; + + $fh = IO::AIO::timerfd_create $clockid[, $flags] + This is a direct interface to the Linux timerfd_create(2) system + call. The (unhelpful) default for $flags is 0. + + On success, the new timerfd filehandle is returned, otherwise + returns "undef". If the eventfd syscall is missing, fails with + "ENOSYS". + + Please refer to timerfd_create(2) for more info on this call. + + The following $clockid values are available: + "IO::AIO::CLOCK_REALTIME", "IO::AIO::CLOCK_MONOTONIC" + "IO::AIO::CLOCK_CLOCK_BOOTTIME" (Linux 3.15) + "IO::AIO::CLOCK_CLOCK_REALTIME_ALARM" (Linux 3.11) and + "IO::AIO::CLOCK_CLOCK_BOOTTIME_ALARM" (Linux 3.11). + + The following $flags values are available (Linux 2.6.27): + "IO::AIO::TFD_NONBLOCK" and "IO::AIO::TFD_CLOEXEC". + + Example: create a new timerfd and set it to one-second repeated + alarms, then wait for two alarms: + + my $fh = IO::AIO::timerfd_create IO::AIO::CLOCK_BOOTTIME, IO::AIO::TFD_CLOEXEC + or die "timerfd_create: $!\n"; + + defined IO::AIO::timerfd_settime $fh, 0, 1, 1 + or die "timerfd_settime: $!\n"; + + for (1..2) { + 8 == sysread $fh, my $buf, 8 + or die "timerfd read failure\n"; + + printf "number of expirations (likely 1): %d\n", + unpack "Q", $buf; + } + + ($cur_interval, $cur_value) = IO::AIO::timerfd_settime $fh, $flags, + $new_interval, $nbw_value + This is a direct interface to the Linux timerfd_settime(2) system + call. Please refer to its manpage for more info on this call. + + The new itimerspec is specified using two (possibly fractional) + second values, $new_interval and $new_value). + + On success, the current interval and value are returned (as per + "timerfd_gettime"). On failure, the empty list is returned. + + The following $flags values are available: + "IO::AIO::TFD_TIMER_ABSTIME" and "IO::AIO::TFD_TIMER_CANCEL_ON_SET". + + See "IO::AIO::timerfd_create" for a full example. + + ($cur_interval, $cur_value) = IO::AIO::timerfd_gettime $fh + This is a direct interface to the Linux timerfd_gettime(2) system + call. Please refer to its manpage for more info on this call. + + On success, returns the current values of interval and value for the + given timerfd (as potentially fractional second values). On failure, + the empty list is returned. + EVENT LOOP INTEGRATION It is recommended to use AnyEvent::AIO to integrate IO::AIO automatically into many event loops: @@ -1326,19 +2029,40 @@ \&IO::AIO::poll_cb); FORK BEHAVIOUR - This module should do "the right thing" when the process using it forks: - - Before the fork, IO::AIO enters a quiescent state where no requests can - be added in other threads and no results will be processed. After the - fork the parent simply leaves the quiescent state and continues - request/result processing, while the child frees the request/result - queue (so that the requests started before the fork will only be handled - in the parent). Threads will be started on demand until the limit set in - the parent process has been reached again. - - In short: the parent will, after a short pause, continue as if fork had - not been called, while the child will act as if IO::AIO has not been - used yet. + Usage of pthreads in a program changes the semantics of fork + considerably. Specifically, only async-safe functions can be called + after fork. Perl doesn't know about this, so in general, you cannot call + fork with defined behaviour in perl if pthreads are involved. IO::AIO + uses pthreads, so this applies, but many other extensions and (for + inexplicable reasons) perl itself often is linked against pthreads, so + this limitation applies to quite a lot of perls. + + This module no longer tries to fight your OS, or POSIX. That means + IO::AIO only works in the process that loaded it. Forking is fully + supported, but using IO::AIO in the child is not. + + You might get around by not *using* IO::AIO before (or after) forking. + You could also try to call the IO::AIO::reinit function in the child: + + IO::AIO::reinit + Abandons all current requests and I/O threads and simply + reinitialises all data structures. This is not an operation + supported by any standards, but happens to work on GNU/Linux and + some newer BSD systems. + + The only reasonable use for this function is to call it after + forking, if "IO::AIO" was used in the parent. Calling it while + IO::AIO is active in the process will result in undefined behaviour. + Calling it at any time will also result in any undefined (by POSIX) + behaviour. + + 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: @@ -1359,7 +2083,17 @@ structures (usually around 16k-128k, depending on the OS). KNOWN BUGS - Known bugs will be fixed in the next release. + 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