--- IO-AIO/AIO.pm 2005/07/10 22:19:54 1.7 +++ IO-AIO/AIO.pm 2006/10/23 00:50:10 1.64 @@ -14,22 +14,39 @@ aio_unlink "/tmp/file", sub { }; aio_read $fh, 30000, 1024, $buffer, 0, sub { - $_[0] >= 0 or die "read error: $!"; + $_[0] > 0 or die "read error: $!"; }; - # Event + # version 2+ has request and group objects + use IO::AIO 2; + + my $req = aio_unlink "/tmp/file", sub { }; + $req->cancel; # cancel request if still in queue + + my $grp = aio_group sub { print "all stats done\n" }; + add $grp aio_stat "..." for ...; + + # AnyEvent integration + open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; + my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb }); + + # Event integration Event->io (fd => IO::AIO::poll_fileno, poll => 'r', cb => \&IO::AIO::poll_cb); - # Glib/Gtk2 + # Glib/Gtk2 integration add_watch Glib::IO IO::AIO::poll_fileno, - \&IO::AIO::poll_cb; + in => sub { IO::AIO::poll_cb; 1 }; - # Tk + # Tk integration Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", readable => \&IO::AIO::poll_cb); + # Danga::Socket integration + Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => + \&IO::AIO::poll_cb); + =head1 DESCRIPTION This module implements asynchronous I/O using whatever means your @@ -45,25 +62,32 @@ remaining functionality would have to be implemented using threads anyway. Although the module will work with in the presence of other threads, it is -currently not reentrant, so use appropriate locking yourself. +currently not reentrant, so use appropriate locking yourself, always call +C from within the same thread, or never call C (or other +C functions) recursively. =cut package IO::AIO; -use base 'Exporter'; +no warnings; +use strict 'vars'; -use Fcntl (); +use base 'Exporter'; BEGIN { - $VERSION = 0.2; + our $VERSION = '2.0'; + + our @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat + aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink + aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move + aio_group aio_nop); + our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); - @EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink - aio_fsync aio_fdatasync aio_readahead); - @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); + @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; require XSLoader; - XSLoader::load IO::AIO, $VERSION; + XSLoader::load ("IO::AIO", $VERSION); } =head1 FUNCTIONS @@ -72,22 +96,34 @@ All the C calls are more or less thin wrappers around the syscall with the same name (sans C). The arguments are similar or identical, -and they all accept an additional C<$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 syscall has -been executed asynchronously. - -All functions that expect a filehandle will also accept a file descriptor. - -The filenames you pass to these routines I be absolute. The reason -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. +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 +syscall has been executed asynchronously. + +All functions expecting a filehandle keep a copy of the filehandle +internally until the request has finished. + +All requests return 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 in byte form. 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. + +To encode pathnames to byte form, either make sure you either: a) +always pass in filenames you got from outside (command line, readdir +etc.), 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. =over 4 -=item aio_open $pathname, $flags, $mode, $callback +=item 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. @@ -95,8 +131,13 @@ The pathname passed to C must be absolute. See API NOTES, above, for an explanation. -The C<$mode> argument is a bitmask. See the C module for a -list. They are the same as used in C. +The C<$flags> argument is a bitmask. See the C module for a +list. They are the same as used by C. + +Likewise, C<$mode> specifies the mode of the newly created file, if it +didn't exist and C has been given, just like perl's C, +except that it is mandatory (i.e. use C<0> if you don't create new files, +and C<0666> or C<0777> if you do). Example: @@ -109,49 +150,148 @@ } }; -=item aio_close $fh, $callback +=item aio_close $fh, $callback->($status) Asynchronously close a file and call the callback with the result code. I although accepted, you should not pass in a perl -filehandle here, as perl will likely close the file descriptor itself when -the filehandle is destroyed. Normally, you can safely call perls C -or just let filehandles go out of scope. +filehandle here, as perl will likely close the file descriptor another +time when the filehandle is destroyed. Normally, you can safely call perls +C or just let filehandles go out of scope. + +This is supposed to be a bug in the API, so that might change. It's +therefore best to avoid this function. -=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback +=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) -=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback +=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) Reads or writes C bytes from the specified C and C into the scalar given by C and offset C and calls the callback without the actual number of bytes read (or -1 on error, just like the syscall). -Example: Read 15 bytes at offset 7 into scalar C<$buffer>, strating at +The C<$data> scalar I be modified in any way while the request +is outstanding. Modifying it can result in segfaults or WW3 (if the +necessary/optional hardware is installed). + +Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at offset C<0> within the scalar: aio_read $fh, 7, 15, $buffer, 0, sub { - $_[0] >= 0 or die "read error: $!"; - print "read <$buffer>\n"; + $_[0] > 0 or die "read error: $!"; + print "read $_[0] bytes: <$buffer>\n"; }; -=item aio_readahead $fh,$offset,$length, $callback +=item aio_move $srcpath, $dstpath, $callback->($status) + +[EXPERIMENTAL due to internal aio_group use] + +Try to move the I (directories not supported as either source or +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 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, and unlinking the C<$srcpath>. + +If an error occurs, the partial destination file will be unlinked, if +possible, except when setting atime, mtime, access mode and uid/gid, where +errors are being ignored. + +=cut -Asynchronously reads the specified byte range into the page cache, using -the C syscall. If that syscall doesn't exist the status will be -C<-1> and C<$!> is set to ENOSYS. +sub aio_move($$$) { + my ($src, $dst, $cb) = @_; -readahead() populates the page cache with data from a file so that + my $grp = aio_group $cb; + + add $grp aio_rename $src, $dst, sub { + if ($_[0] && $! == EXDEV) { + add $grp aio_open $src, O_RDONLY, 0, sub { + if (my $src_fh = $_[0]) { + my @stat = stat $src_fh; + + add $grp aio_open $dst, O_WRONLY, 0200, sub { + if (my $dst_fh = $_[0]) { + add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { + close $src_fh; + + if ($_[0] == $stat[7]) { + utime $stat[8], $stat[9], $dst; + chmod $stat[2] & 07777, $dst_fh; + chown $stat[4], $stat[5], $dst_fh; + close $dst_fh; + + add $grp aio_unlink $src, sub { + $grp->result ($_[0]); + }; + } else { + my $errno = $!; + add $grp aio_unlink $dst, sub { + $! = $errno; + $grp->result (-1); + }; + } + }; + } else { + $grp->result (-1); + } + }, + + } else { + $grp->result (-1); + } + }; + } else { + $grp->result ($_[0]); + } + }; + + $grp +} + +=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) + +Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts +reading at byte offset C<$in_offset>, and starts writing at the current +file offset of C<$out_fh>. Because of that, it is not safe to issue more +than one C per C<$out_fh>, as they will interfere with each +other. + +This call tries to make use of a native C syscall to provide +zero-copy operation. For this to work, C<$out_fh> should refer to a +socket, and C<$in_fh> should refer to mmap'able file. + +If the native sendfile call fails or is not implemented, it will be +emulated, so you can call C on any type of filehandle +regardless of the limitations of the operating system. + +Please note, however, that C can read more bytes from +C<$in_fh> than are written, and there is no way to find out how many +bytes have been read from C alone, as C only +provides the number of bytes written to C<$out_fh>. Only if the result +value equals C<$length> one can assume that C<$length> bytes have been +read. + +=item aio_readahead $fh,$offset,$length, $callback->($retval) + +C populates the page cache with data from a file so that subsequent reads from that file will not block on disk I/O. The C<$offset> argument specifies the starting point from which data is to be read and C<$length> specifies the number of bytes to be read. I/O is performed in whole pages, so that offset is effectively rounded down to a page boundary and bytes are read up to the next page boundary greater than or equal to -(off-set+length). aio_readahead() does not read beyond the end of the +(off-set+length). C does not read beyond the end of the file. The current file offset of the file is left unchanged. -=item aio_stat $fh_or_path, $callback +If that syscall doesn't exist (likely if your OS isn't Linux) it will be +emulated by simply reading the data, which would have a similar effect. + +=item aio_stat $fh_or_path, $callback->($status) -=item aio_lstat $fh, $callback +=item aio_lstat $fh, $callback->($status) Works like perl's C or C in void context. The callback will be called after the stat and the results will be available using C @@ -171,21 +311,404 @@ print "size is ", -s _, "\n"; }; -=item aio_unlink $pathname, $callback +=item aio_unlink $pathname, $callback->($status) Asynchronously unlink (delete) a file and call the callback with the result code. -=item aio_fsync $fh, $callback +=item aio_link $srcpath, $dstpath, $callback->($status) + +Asynchronously create a new link to the existing object at C<$srcpath> at +the path C<$dstpath> and call the callback with the result code. + +=item aio_symlink $srcpath, $dstpath, $callback->($status) + +Asynchronously create a new symbolic link to the existing object at C<$srcpath> at +the path C<$dstpath> and call the callback with the result code. + +=item aio_rename $srcpath, $dstpath, $callback->($status) + +Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as +rename(2) and call the callback with the result code. + +=item aio_rmdir $pathname, $callback->($status) + +Asynchronously rmdir (delete) a directory and call the callback with the +result code. + +=item aio_readdir $pathname, $callback->($entries) + +Unlike the POSIX call of the same name, C reads an entire +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. + +=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) + +[EXPERIMENTAL due to internal aio_group use] + +Scans a directory (similar to C) but additionally tries to +separate the entries of directory C<$path> into two sets of names, ones +you can recurse into (directories or links to them), and ones you cannot +recurse into (everything else). + +C is a composite request that creates of many sub requests_ +C<$maxreq> specifies the maximum number of outstanding aio requests that +this function generates. If it is C<< <= 0 >>, then a suitable default +will be chosen (currently 6). + +On error, the callback is called without arguments, otherwise it receives +two array-refs with path-relative entry names. + +Example: + + aio_scandir $dir, 0, sub { + my ($dirs, $nondirs) = @_; + print "real directories: @$dirs\n"; + print "everything else: @$nondirs\n"; + }; + +Implementation notes. + +The 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 +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). + +If the known number of directories (link count - 2) has been reached, the +rest of the entries is assumed to be non-directories. + +This only works with certainty on POSIX (= UNIX) filesystems, which +fortunately are the vast majority of filesystems around. + +It will also likely work on non-POSIX filesystems with reduced efficiency +as those tend to return 0 or 1 as link counts, which disables the +directory counting heuristic. + +=cut + +sub aio_scandir($$$) { + my ($path, $maxreq, $cb) = @_; + + my $grp = aio_group $cb; + + $maxreq = 6 if $maxreq <= 0; + + # stat once + add $grp aio_stat $path, sub { + return $grp->result () if $_[0]; + my $now = time; + my $hash1 = join ":", (stat _)[0,1,3,7,9]; + + # read the directory entries + add $grp aio_readdir $path, sub { + my $entries = shift + or return $grp->result (); + + # stat the dir another time + add $grp aio_stat $path, sub { + my $hash2 = join ":", (stat _)[0,1,3,7,9]; + + my $ndirs; + + # take the slow route if anything looks fishy + if ($hash1 ne $hash2 or (stat _)[9] == $now) { + $ndirs = -1; + } else { + # if nlink == 2, we are finished + # on 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], + @$entries]; + + my (@dirs, @nondirs); + + my ($statcb, $schedcb); + my $nreq = 0; + + my $statgrp = add $grp aio_group; + + $schedcb = sub { + if (@$entries) { + if ($nreq < $maxreq) { + my $ent = pop @$entries; + $nreq++; + add $statgrp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) }; + } + } elsif (!$nreq) { + # finished + $statgrp->cancel; + undef $statcb; + undef $schedcb; + $grp->result (\@dirs, \@nondirs); + } + }; + $statcb = sub { + my ($status, $entry) = @_; + + if ($status < 0) { + $nreq--; + push @nondirs, $entry; + &$schedcb; + } else { + # need to check for real directory + add $grp aio_lstat "$path/$entry", sub { + $nreq--; + + if (-d _) { + push @dirs, $entry; + + if (!--$ndirs) { + push @nondirs, @$entries; + $entries = []; + } + } else { + push @nondirs, $entry; + } + + &$schedcb; + } + } + }; + + &$schedcb while @$entries && $nreq < $maxreq; + }; + }; + }; + + $grp +} + +=item aio_fsync $fh, $callback->($status) Asynchronously call fsync on the given filehandle and call the callback with the fsync result code. -=item aio_fdatasync $fh, $callback +=item aio_fdatasync $fh, $callback->($status) Asynchronously call fdatasync on the given filehandle and call the callback with the fdatasync result code. +If this call isn't available because your OS lacks it or it couldn't be +detected, it will be emulated by calling C instead. + +=item aio_group $callback->(...) + +[EXPERIMENTAL] + +This is a very special aio request: Instead of doing something, it is a +container for other aio requests, which is useful if you want to bundle +many requests into a single, composite, request. + +Returns an object of class L. See its documentation below +for more info. + +Example: + + my $grp = aio_group sub { + print "all stats done\n"; + }; + + add $grp + (aio_stat ...), + (aio_stat ...), + ...; + +=item aio_nop $callback->() + +This is a special request - it does nothing in itself and is only used for +side effects, such as when you want to add a dummy request to a group so +that finishing the requests in the group depends on executing the given +code. + +While this request does nothing, it still goes through the execution +phase and still requires a worker thread. Thus, the callback will not +be executed immediately but only after other requests in the queue have +entered their execution phase. This can be used to measure request +latency. + +=item IO::AIO::aio_sleep $fractional_seconds, $callback->() *NOT EXPORTED* + +Mainly used for debugging and benchmarking, this aio request puts one of +the request workers to sleep for the given time. + +While it is theoretically handy to have simple I/O scheduling requests +like sleep and file handle readable/writable, the overhead this creates +is immense, so do not use this function except to put your application +under artificial I/O pressure. + +=back + +=head2 IO::AIO::REQ CLASS + +All non-aggregate C functions return an object of this class when +called in non-void context. + +A request always moves through the following five states in its lifetime, +in order: B (request has been created, but has not been executed +yet), B (request is currently being executed), B +(request has been executed but callback has not been called yet), +B (results are being processed synchronously, includes calling the +callback) and B (request has reached the end of its lifetime and +holds no resources anymore). + +=over 4 + +=item $req->cancel + +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. + +=back + +=head2 IO::AIO::GRP CLASS + +This class is a subclass of L, so all its methods apply to +objects of this class, too. + +A IO::AIO::GRP object is a special request that can contain multiple other +aio requests. + +You create one by calling the C constructing function with a +callback that will be called when all contained requests have entered the +C state: + + my $grp = aio_group sub { + print "all requests are done\n"; + }; + +You add requests by calling the C method with one or more +C objects: + + $grp->add (aio_unlink "..."); + + add $grp aio_stat "...", sub { + $_[0] or return $grp->result ("error"); + + # add another request dynamically, if first succeeded + add $grp aio_open "...", sub { + $grp->result ("ok"); + }; + }; + +This makes it very easy to create composite requests (see the source of +C for an application) that work and feel like simple requests. + +=over 4 + +=item * The IO::AIO::GRP objects will be cleaned up during calls to +C, just like any other request. + +=item * They can be canceled like any other request. Canceling will cancel not +only the request itself, but also all requests it contains. + +=item * They can also can also be added to other IO::AIO::GRP objects. + +=item * You must not add requests to a group from within the group callback (or +any later time). + +=item * This does not harmonise well with C, so best do +not combine C with it. Groups and feeders are recommended for +this kind of concurrency-limiting. + +=back + +Their lifetime, simplified, looks like this: when they are empty, they +will finish very quickly. If they contain only requests that are in the +C state, they will also finish. Otherwise they will continue to +exist. + +That means after creating a group you have some time to add requests. And +in the callbacks of those requests, you can add further requests to the +group. And only when all those requests have finished will the the group +itself finish. + +=over 4 + +=item $grp->add (...) + +=item add $grp ... + +Add one or more requests to the group. Any type of L can +be added, including other groups, as long as you do not create circular +dependencies. + +Returns all its arguments. + +=item $grp->result (...) + +Set the result value(s) that will be passed to the group callback when all +subrequests have finished. By default, no argument will be passed. + +=item $grp->set_feeder ($callback->($grp)) + +[VERY EXPERIMENTAL] + +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. + +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 +feeder will be called whenever there are few enough (see C, +below) requests active in the group itself and is expected to queue more +requests. + +The feeder can queue as many requests as it likes (i.e. C does not +impose any limits). + +If the feeder does not queue more requests when called, it will be +automatically removed from the group. + +If the feeder limit is C<0>, it will be set to C<2> automatically. + +Example: + + # stat all files in @files, but only ever use four aio requests concurrently: + + my $grp = aio_group sub { print "finished\n" }; + $grp->feeder_limit (4); + $grp->set_feeder (sub { + my $file = pop @files + or return; + + add $grp aio_stat $file, sub { ... }; + }); + +=item $grp->feeder_limit ($num) + +Sets the feeder limit for the group: The feeder will be called whenever +the group contains less than this many requests. + +Setting the limit to C<0> will pause the feeding process. + =back =head2 SUPPORT FUNCTIONS @@ -194,10 +717,10 @@ =item $fileno = IO::AIO::poll_fileno -Return the I. This filehandle must be -polled for reading by some mechanism outside this module (e.g. Event -or select, see below). If the pipe becomes readable you have to call -C to check the results. +Return the I. This filehandle must be +polled for reading by some mechanism outside this module (e.g. Event or +select, see below or the SYNOPSIS). If the pipe becomes readable you have +to call C to check the results. See C for an example. @@ -207,7 +730,8 @@ regularly. Returns the number of events processed. Returns immediately when no events are outstanding. -You can use Event to multiplex, e.g.: +Example: Install an Event watcher that automatically calls +IO::AIO::poll_cb with high priority: Event->io (fd => IO::AIO::poll_fileno, poll => 'r', async => 1, @@ -216,40 +740,65 @@ =item IO::AIO::poll_wait 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 +C