--- IO-AIO/AIO.pm 2011/09/26 20:19:08 1.208 +++ IO-AIO/AIO.pm 2011/09/27 12:10:29 1.211 @@ -223,11 +223,11 @@ aio_truncate $fh_or_path, $offset, $callback->($status) aio_chmod $fh_or_path, $mode, $callback->($status) aio_unlink $pathname, $callback->($status) - aio_mknod $path, $mode, $dev, $callback->($status) + aio_mknod $pathname, $mode, $dev, $callback->($status) aio_link $srcpath, $dstpath, $callback->($status) aio_symlink $srcpath, $dstpath, $callback->($status) - aio_readlink $path, $callback->($link) - aio_realpath $path, $callback->($link) + aio_readlink $pathname, $callback->($link) + aio_realpath $pathname, $callback->($link) aio_rename $srcpath, $dstpath, $callback->($status) aio_mkdir $pathname, $mode, $callback->($status) aio_rmdir $pathname, $callback->($status) @@ -235,17 +235,17 @@ 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_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_scandir $pathname, $maxreq, $callback->($dirs, $nondirs) + 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) @@ -294,12 +294,13 @@ All functions return request objects of type L that allow further manipulation of those requests while they are in-flight. -The pathnames you pass to these routines I 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 I 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. Lastly, you can take advantage +of IO::AIOs working directory abstraction - see the description of the +C 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 @@ -618,7 +619,7 @@ result code. -=item aio_mknod $path, $mode, $dev, $callback->($status) +=item aio_mknod $pathname, $mode, $dev, $callback->($status) [EXPERIMENTAL] @@ -626,7 +627,7 @@ 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 | $mode, 0, sub { ... See C for info about some potentially helpful extra constants and functions. @@ -643,14 +644,14 @@ the path C<$dstpath> and call the callback with the result code. -=item aio_readlink $path, $callback->($link) +=item aio_readlink $pathname, $callback->($link) Asynchronously read the symlink specified by C<$path> and pass it to the callback. If an error occurs, nothing or undef gets passed to the callback. -=item aio_realpath $path, $callback->($path) +=item aio_realpath $pathname, $callback->($path) Asynchronously make the path absolute and resolve any symlinks in C<$path>. The resulting path only consists of directories (Same as @@ -755,7 +756,7 @@ =back -=item aio_load $path, $data, $callback->($status) +=item 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. @@ -900,7 +901,7 @@ $grp } -=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) +=item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs) Scans a directory (similar to C) but additionally tries to efficiently separate the entries of directory C<$path> into two sets of @@ -967,67 +968,76 @@ $maxreq = 4 if $maxreq <= 0; - # stat once + # get a wd object + aioreq_pri $pri; - add $grp aio_stat $path, sub { - return $grp->result () if $_[0]; - my $now = time; - my $hash1 = join ":", (stat _)[0,1,3,7,9]; + add $grp aio_wd $path, sub { + my $wd = [shift, "."]; - # read the directory entries + # stat once aioreq_pri $pri; - add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub { - my $entries = shift - or return $grp->result (); + add $grp aio_stat $wd, sub { + return $grp->result () if $_[0]; + my $now = time; + my $hash1 = join ":", (stat _)[0,1,3,7,9]; - # stat the dir another time + # read the directory entries aioreq_pri $pri; - add $grp aio_stat $path, sub { - my $hash2 = join ":", (stat _)[0,1,3,7,9]; + add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub { + my $entries = shift + or return $grp->result (); - my $ndirs; + # stat the dir another time + aioreq_pri $pri; + add $grp aio_stat $wd, sub { + my $hash2 = join ":", (stat _)[0,1,3,7,9]; - # take the slow route if anything looks fishy - if ($hash1 ne $hash2 or (stat _)[9] == $now) { - $ndirs = -1; - } else { - # if nlink == 2, we are finished - # for non-posix-fs's, we rely on nlink < 2 - $ndirs = (stat _)[3] - 2 - or return $grp->result ([], $entries); - } + my $ndirs; - my (@dirs, @nondirs); + # take the slow route if anything looks fishy + if ($hash1 ne $hash2 or (stat _)[9] == $now) { + $ndirs = -1; + } else { + # if nlink == 2, we are finished + # for non-posix-fs's, we rely on nlink < 2 + $ndirs = (stat _)[3] - 2 + or return $grp->result ([], $entries); + } - my $statgrp = add $grp aio_group sub { - $grp->result (\@dirs, \@nondirs); - }; + my (@dirs, @nondirs); - limit $statgrp $maxreq; - feed $statgrp sub { - return unless @$entries; - my $entry = shift @$entries; + my $statgrp = add $grp aio_group sub { + $grp->result (\@dirs, \@nondirs); + }; - aioreq_pri $pri; - add $statgrp aio_stat "$path/$entry/.", sub { - if ($_[0] < 0) { - push @nondirs, $entry; - } else { - # need to check for real directory - aioreq_pri $pri; - add $statgrp aio_lstat "$path/$entry", sub { - if (-d _) { - push @dirs, $entry; - - unless (--$ndirs) { - push @nondirs, @$entries; - feed $statgrp; + limit $statgrp $maxreq; + feed $statgrp sub { + return unless @$entries; + my $entry = shift @$entries; + + aioreq_pri $pri; + $wd->[1] = "$entry/."; + add $statgrp aio_stat $wd, sub { + if ($_[0] < 0) { + push @nondirs, $entry; + } else { + # need to check for real directory + aioreq_pri $pri; + $wd->[1] = $entry; + add $statgrp aio_lstat $wd, sub { + if (-d _) { + push @dirs, $entry; + + unless (--$ndirs) { + push @nondirs, @$entries; + feed $statgrp; + } + } else { + push @nondirs, $entry; } - } else { - push @nondirs, $entry; } } - } + }; }; }; }; @@ -1037,7 +1047,7 @@ $grp } -=item aio_rmtree $path, $callback->($status) +=item aio_rmtree $pathname, $callback->($status) Delete a directory tree starting (and including) C<$path>, return the status of the final C only. This is a composite request that @@ -1108,7 +1118,7 @@ C: refer to the sync_file_range manpage for details. -=item aio_pathsync $path, $callback->($status) +=item 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 @@ -1261,6 +1271,116 @@ =back + +=head2 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 C 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 C +or C), one can specify an array reference with an IO::AIO::WD +object and a pathname instead. If the pathname is absolute, the +IO::AIO::WD objetc is ignored, otherwise the pathname is resolved relative +to that IO::AIO::WD object. + +For example, to get a wd object for F and then stat F +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 + }; + }; + +This shows that creating an IO::AIO::WD object is itself a potentially +blocking operation, which is why it is done asynchronously. + +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 C<$path> getting reused: + + my $path = [$wd, undef]; + + for my $name (qw(abc def ghi)) { + $path->[1] = $name; + aio_stat $path, sub { + # ... + }; + } + +There are some caveats: when directories get renamed (or deleted), the +pathname string doesn't change, so will point to the new directory (or +nowhere at all), while the directory fd, if available on the system, +will still point to the original directory. Most functions accepting a +pathname will use the directory fd on newer systems, and the string on +older systems. Some functions (such as realpath) will always rely on the +string form of the pathname. + +So this fucntionality is mainly useful to get some protection against +C, 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: + +=over 4 + +=item 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 C is passwd to the callback instead +of a working directory object and C<$!> is set appropriately. Since +passing C as working directory component of a pathname fails the +request with C, there is often no need for error checking in the +C callback, as future requests using the value will fail in the +expected way. + +If this call isn't available because your OS lacks it or it couldn't be +detected, it will be emulated by calling C instead. + +=item IO::AIO::CWD + +This is a compiletime constant (object) that represents the process +current working directory. + +Specifying this object as working directory object for a pathname is as +if the pathname would be specified directly, without a directory object, +e.g., these calls are functionally identical: + + aio_stat "somefile", sub { ... }; + aio_stat [IO::AIO::CWD, "somefile"], sub { ... }; + +=back + + =head2 IO::AIO::REQ CLASS All non-aggregate C functions return an object of this class when @@ -1387,8 +1507,8 @@ 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. +C might generate hundreds of thousands of 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