--- IO-AIO/AIO.pm 2008/09/06 07:14:52 1.133 +++ IO-AIO/AIO.pm 2009/06/14 20:36:59 1.155 @@ -195,12 +195,12 @@ use base 'Exporter'; BEGIN { - our $VERSION = '3.07'; + our $VERSION = '3.23'; our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close - aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir + aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx aio_scandir aio_symlink aio_readlink aio_sync aio_fsync - aio_fdatasync aio_pathsync aio_readahead + aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead aio_rename aio_link aio_move aio_copy aio_group aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown aio_chmod aio_utime aio_truncate); @@ -211,6 +211,8 @@ nreqs nready npending nthreads max_poll_time max_poll_reqs); + push @AIO_REQ, qw(aio_busy); # not exported + @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; require XSLoader; @@ -226,7 +228,7 @@ and they all accept an additional (and optional) C<$callback> argument which must be a code reference. This code reference will get called with the syscall return code (e.g. most syscalls return C<-1> on error, unlike -perl, which usually delivers "false") as it's sole argument when the given +perl, which usually delivers "false") as its sole argument after the given syscall has been executed asynchronously. All functions expecting a filehandle keep a copy of the filehandle @@ -250,7 +252,7 @@ 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 wether it is set or not. +handles correctly whether it is set or not. =over 4 @@ -338,16 +340,20 @@ =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) -Reads or writes C<$length> bytes from the specified C<$fh> and C<$offset> -into the scalar given by C<$data> and offset C<$dataoffset> and calls the -callback without the actual number of bytes read (or -1 on error, just -like the syscall). +Reads or writes C<$length> bytes from or to the specified C<$fh> and +C<$offset> into the scalar given by C<$data> and offset C<$dataoffset> +and calls the callback without the actual number of bytes read (or -1 on +error, just like the syscall). + +C will, like C, shrink or grow the C<$data> scalar to +offset plus the actual number of bytes read. If C<$offset> is undefined, then the current file descriptor offset will be used (and updated), otherwise the file descriptor offset will not be changed by these calls. -If C<$length> is undefined in C, use the remaining length of C<$data>. +If C<$length> is undefined in C, use the remaining length of +C<$data>. If C<$dataoffset> is less than zero, it will be counted from the end of C<$data>. @@ -529,8 +535,74 @@ directory (i.e. opendir + readdir + closedir). The entries will not be sorted, and will B include the C<.> and C<..> entries. -The callback a single argument which is either C or an array-ref -with the filenames. +The callback is passed a single argument which is either C or an +array-ref with the filenames. + + +=item aio_readdirx $pathname, $flags, $callback->($entries, $flags) + +Quite similar to C, but the C<$flags> argument allows to tune +behaviour and output format. In case of an error, C<$entries> will be +C. + +The flags are a combination of the following constants, ORed together (the +flags will also be passed to the callback, possibly modified): + +=over 4 + +=item IO::AIO::READDIR_DENTS + +When this flag is off, then the callback gets an arrayref with of names +only (as with C), otherwise it gets an arrayref with +C<[$name, $type, $inode]> arrayrefs, each describing a single directory +entry in more detail. + +C<$name> is the name of the entry. + +C<$type> is one of the C constants: + +C, C, C, C, +C, C, C, C, +C. + +C means just that: readdir does not know. If you need to +know, you have to run stat yourself. Also, for speed reasons, the C<$type> +scalars are read-only: you can not modify them. + +C<$inode> is the inode number (which might not be exact on systems with 64 +bit inode numbers and 32 bit perls). This field has unspecified content on +systems that do not deliver the inode information. + +=item IO::AIO::READDIR_DIRS_FIRST + +When this flag is set, then the names will be returned in an order where +likely directories come first. This is useful when you need to quickly +find directories, or you want to find all directories while avoiding to +stat() each entry. + +If the system returns type information in readdir, then this is used +to find directories directly. Otherwise, likely directories are files +beginning with ".", or otherwise files with no dots, of which files with +short names are tried first. + +=item IO::AIO::READDIR_STAT_ORDER + +When this flag is set, then the names will be returned in an order +suitable for stat()'ing each one. That is, when you plan to stat() +all files in the given directory, then the returned order will likely +be fastest. + +If both this flag and C are specified, then +the likely dirs come first, resulting in a less optimal stat order. + +=item IO::AIO::READDIR_FOUND_UNKNOWN + +This flag should not be set when calling C. Instead, it +is being set by C, when any of the C<$type>'s found were +C. The absense of this flag therefore indicates that all +C<$type>'s are known, which can be used to speed up some algorithms. + +=back =item aio_load $path, $data, $callback->($status) @@ -567,7 +639,7 @@ destination) from C<$srcpath> to C<$dstpath> and call the callback with the C<0> (error) or C<-1> ok. -This is a composite request that it creates the destination file with +This is a composite request that creates the destination file with mode 0200 and copies the contents of the source file into it using C, followed by restoring atime, mtime, access mode and uid/gid, in that order. @@ -587,7 +659,7 @@ aioreq_pri $pri; add $grp aio_open $src, O_RDONLY, 0, sub { if (my $src_fh = $_[0]) { - my @stat = stat $src_fh; + my @stat = stat $src_fh; # hmm, might bock over nfs? aioreq_pri $pri; add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { @@ -598,13 +670,26 @@ $grp->result (0); close $src_fh; - # those should not normally block. should. should. - utime $stat[8], $stat[9], $dst; - chmod $stat[2] & 07777, $dst_fh; - chown $stat[4], $stat[5], $dst_fh; + my $ch = sub { + aioreq_pri $pri; + add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub { + aioreq_pri $pri; + add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub { + aioreq_pri $pri; + add $grp aio_close $dst_fh; + } + }; + }; aioreq_pri $pri; - add $grp aio_close $dst_fh; + add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub { + if ($_[0] < 0 && $! == ENOSYS) { + aioreq_pri $pri; + add $grp aio_utime $dst, $stat[8], $stat[9], $ch; + } else { + $ch->(); + } + }; } else { $grp->result (-1); close $src_fh; @@ -633,9 +718,9 @@ destination) from C<$srcpath> to C<$dstpath> and call the callback with the C<0> (error) or C<-1> ok. -This is a composite request that tries to rename(2) the file first. If -rename files with C, it copies the file with C and, if -that is successful, unlinking the C<$srcpath>. +This is a composite request that tries to rename(2) the file first; if +rename fails with C, it copies the file with C and, if +that is successful, unlinks the C<$srcpath>. =cut @@ -692,20 +777,24 @@ The C cannot be avoided, but C'ing every entry can. -After reading the directory, the modification time, size etc. of the -directory before and after the readdir is checked, and if they match (and -isn't the current time), the link count will be used to decide how many -entries are directories (if >= 2). Otherwise, no knowledge of the number -of subdirectories will be assumed. - -Then entries will be sorted into likely directories (everything without -a non-initial dot currently) and likely non-directories (everything -else). Then every entry plus an appended C will be C'ed, -likely directories first. If that succeeds, it assumes that the entry -is a directory or a symlink to directory (which will be checked +If readdir returns file type information, then this is used directly to +find directories. + +Otherwise, after reading the directory, the modification time, size etc. +of the directory before and after the readdir is checked, and if they +match (and isn't the current time), the link count will be used to decide +how many entries are directories (if >= 2). Otherwise, no knowledge of the +number of subdirectories will be assumed. + +Then entries will be sorted into likely directories a non-initial dot +currently) and likely non-directories (see C). Then every +entry plus an appended C will be C'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 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). +data (e.g. ext2fs filetype feature), even on systems that cannot return +the filetype information on readdir. If the known number of directories (link count - 2) has been reached, the rest of the entries is assumed to be non-directories. @@ -737,7 +826,7 @@ # read the directory entries aioreq_pri $pri; - add $grp aio_readdir $path, sub { + add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub { my $entries = shift or return $grp->result (); @@ -753,18 +842,11 @@ $ndirs = -1; } else { # if nlink == 2, we are finished - # on non-posix-fs's, we rely on nlink < 2 + # for non-posix-fs's, we rely on nlink < 2 $ndirs = (stat _)[3] - 2 or return $grp->result ([], $entries); } - # sort into likely dirs and likely nondirs - # dirs == files without ".", short entries first - $entries = [map $_->[0], - sort { $b->[1] cmp $a->[1] } - map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], - @$entries]; - my (@dirs, @nondirs); my $statgrp = add $grp aio_group sub { @@ -774,7 +856,7 @@ limit $statgrp $maxreq; feed $statgrp sub { return unless @$entries; - my $entry = pop @$entries; + my $entry = shift @$entries; aioreq_pri $pri; add $statgrp aio_stat "$path/$entry/.", sub { @@ -857,10 +939,22 @@ If this call isn't available because your OS lacks it or it couldn't be detected, it will be emulated by calling C instead. +=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) + +Sync the data portion of the file specified by C<$offset> and C<$length> +to disk (but NOT the metadata), by calling the Linux-specific +sync_file_range call. If sync_file_range is not available or it returns +ENOSYS, then fdatasync or fsync is being substituted. + +C<$flags> can be a combination of C, +C and +C: refer to the sync_file_range +manpage for details. + =item aio_pathsync $path, $callback->($status) This request tries to open, fsync and close the given path. This is a -composite request intended tosync directories after directory operations +composite request intended to sync directories after directory operations (E.g. rename). This might not work on all operating systems or have any specific effect, but usually it makes sure that directory changes get written to disc. It works for anything that can be opened for read-only, @@ -953,8 +1047,9 @@ Cancels the request, if possible. Has the effect of skipping execution when entering the B state and skipping calling the callback when entering the the B state, but will leave the request otherwise -untouched. That means that requests that currently execute will not be -stopped and resources held by the request will not be freed prematurely. +untouched (with the exception of readdir). That means that requests that +currently execute will not be stopped and resources held by the request +will not be freed prematurely. =item cb $req $callback->(...) @@ -1062,9 +1157,9 @@ Sets a feeder/generator on this group: every group can have an attached generator that generates requests if idle. The idea behind this is that, although you could just queue as many requests as you want in a group, -this might starve other requests for a potentially long time. For -example, C might generate hundreds of thousands C -requests, delaying any later requests for a long time. +this might starve other requests for a potentially long time. For example, +C might generate hundreds of thousands C requests, +delaying any later requests for a long time. To avoid this, and allow incremental generation of requests, you can instead a group and set a feeder on it that generates those requests. The @@ -1078,7 +1173,8 @@ If the feed does not queue more requests when called, it will be automatically removed from the group. -If the feed limit is C<0>, it will be set to C<2> automatically. +If the feed limit is C<0> when this method is called, it will be set to +C<2> automatically. Example: @@ -1100,6 +1196,9 @@ Setting the limit to C<0> will pause the feeding process. +The default value for the limit is C<0>, but note that setting a feeder +automatically bumps it up to C<2>. + =back =head2 SUPPORT FUNCTIONS