--- IO-AIO/AIO.pm 2006/10/27 20:10:06 1.82 +++ IO-AIO/AIO.pm 2007/01/07 21:36:58 1.100 @@ -7,7 +7,8 @@ use IO::AIO; aio_open "/etc/passwd", O_RDONLY, 0, sub { - my ($fh) = @_; + my $fh = shift + or die "/etc/passwd: $!"; ... }; @@ -53,12 +54,29 @@ This module implements asynchronous I/O using whatever means your operating system supports. +Asynchronous means that operations that can normally block your program +(e.g. reading from disk) will be done asynchronously: the operation +will still block, but you can do something else in the meantime. This +is extremely useful for programs that need to stay interactive even +when doing heavy I/O (GUI programs, high performance network servers +etc.), but can also be used to easily do operations in parallel that are +normally done sequentially, e.g. stat'ing many files, which is much faster +on a RAID volume or over NFS when you do a number of stat operations +concurrently. + +While most of this works on all types of file descriptors (for example +sockets), using these functions on file descriptors that support +nonblocking operation (again, sockets, pipes etc.) is very inefficient or +might not work (aio_read fails on sockets/pipes/fifos). Use an event loop +for that (such as the L module): IO::AIO will naturally fit +into such an event loop itself. + In this version, a number of threads are started that execute your requests and signal their completion. You don't need thread support in perl, and the threads created by this module will not be visible to perl. In the future, this module might make use of the native aio functions available on many operating systems. However, they are often -not well-supported or restricted (Linux doesn't allow them on normal +not well-supported or restricted (GNU/Linux doesn't allow them on normal files currently, for example), and they would only support aio_read and aio_write, so the remaining functionality would have to be implemented using threads anyway. @@ -68,6 +86,50 @@ locking yourself, always call C from within the same thread, or never call C (or other C functions) recursively. +=head2 EXAMPLE + +This is a simple example that uses the Event module and loads +F asynchronously: + + use Fcntl; + use Event; + use IO::AIO; + + # register the IO::AIO callback with Event + Event->io (fd => IO::AIO::poll_fileno, + poll => 'r', + cb => \&IO::AIO::poll_cb); + + # queue the request to open /etc/passwd + aio_open "/etc/passwd", O_RDONLY, 0, sub { + my $fh = shift + or die "error while opening: $!"; + + # stat'ing filehandles is generally non-blocking + my $size = -s $fh; + + # queue a request to read the file + my $contents; + aio_read $fh, 0, $size, $contents, 0, sub { + $_[0] == $size + or die "short read: $!"; + + close $fh; + + # file contents now in $contents + print $contents; + + # exit event loop and program + Event::unloop; + }; + }; + + # possibly queue up other requests, or open GUI windows, + # check for sockets etc. etc. + + # process events as long as there are some: + Event::loop; + =head1 REQUEST ANATOMY AND LIFETIME Every C function creates a request. which is a C data structure not @@ -118,6 +180,8 @@ aio request is severed and calling its methods will either do nothing or result in a runtime error). +=back + =cut package IO::AIO; @@ -128,15 +192,17 @@ use base 'Exporter'; BEGIN { - our $VERSION = '2.0'; + our $VERSION = '2.32'; 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_scandir aio_symlink - aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move - aio_copy aio_group aio_nop aio_mknod); - our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); + aio_readlink aio_fsync aio_fdatasync aio_readahead aio_rename aio_link + aio_move aio_copy aio_group aio_nop aio_mknod aio_load aio_rmtree); + our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice aio_block)); our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush - min_parallel max_parallel nreqs nready npending); + min_parallel max_parallel max_idle + nreqs nready npending nthreads + max_poll_time max_poll_reqs); @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; @@ -146,7 +212,7 @@ =head1 FUNCTIONS -=head2 AIO FUNCTIONS +=head2 AIO REQUEST FUNCTIONS 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, @@ -159,21 +225,25 @@ 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. +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 in byte form. The reason for the former is that at the time the +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. +current working directory anywhere in the program and then use relative +paths. -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 +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. +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. =over 4 @@ -206,7 +276,7 @@ =item aioreq_nice $pri_adjust Similar to C, but subtracts the given value from the current -priority, so effects are cumulative. +priority, so the effect is cumulative. =item aio_open $pathname, $flags, $mode, $callback->($fh) @@ -333,9 +403,13 @@ =item aio_mknod $path, $mode, $dev, $callback->($status) -Asynchronously create a device node (or fifo). See mknod(2): the only -portable value for C<$mode> is C ored with permissions, and C<0> -for C<$dev>. +[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 { ... =item aio_link $srcpath, $dstpath, $callback->($status) @@ -347,6 +421,12 @@ 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_readlink $path, $callback->($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_rename $srcpath, $dstpath, $callback->($status) Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as @@ -366,6 +446,36 @@ The callback a single argument which is either C or an array-ref with the filenames. +=item aio_load $path, $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. + +=cut + +sub aio_load($$;$) { + aio_block { + my ($path, undef, $cb) = @_; + my $data = \$_[1]; + + my $pri = aioreq_pri; + my $grp = aio_group $cb; + + aioreq_pri $pri; + add $grp aio_open $path, O_RDONLY, 0, sub { + my ($fh) = @_ + or return $grp->result (-1); + + aioreq_pri $pri; + add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub { + $grp->result ($_[0]); + }; + }; + + $grp + } +} + =item aio_copy $srcpath, $dstpath, $callback->($status) Try to copy the I (directories not supported as either source or @@ -384,50 +494,52 @@ =cut sub aio_copy($$;$) { - my ($src, $dst, $cb) = @_; - - my $pri = aioreq_pri; - my $grp = aio_group $cb; + aio_block { + my ($src, $dst, $cb) = @_; - aioreq_pri $pri; - add $grp aio_open $src, O_RDONLY, 0, sub { - if (my $src_fh = $_[0]) { - my @stat = stat $src_fh; + my $pri = aioreq_pri; + my $grp = aio_group $cb; - aioreq_pri $pri; - add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { - if (my $dst_fh = $_[0]) { - aioreq_pri $pri; - add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { - if ($_[0] == $stat[7]) { - $grp->result (0); - close $src_fh; - - # those should not normally block. should. should. - utime $stat[8], $stat[9], $dst; - chmod $stat[2] & 07777, $dst_fh; - chown $stat[4], $stat[5], $dst_fh; - close $dst_fh; - } else { - $grp->result (-1); - close $src_fh; - close $dst_fh; - - aioreq $pri; - add $grp aio_unlink $dst; - } - }; - } else { - $grp->result (-1); - } - }, + aioreq_pri $pri; + add $grp aio_open $src, O_RDONLY, 0, sub { + if (my $src_fh = $_[0]) { + my @stat = stat $src_fh; + + aioreq_pri $pri; + add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { + if (my $dst_fh = $_[0]) { + aioreq_pri $pri; + add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { + if ($_[0] == $stat[7]) { + $grp->result (0); + close $src_fh; + + # those should not normally block. should. should. + utime $stat[8], $stat[9], $dst; + chmod $stat[2] & 07777, $dst_fh; + chown $stat[4], $stat[5], $dst_fh; + close $dst_fh; + } else { + $grp->result (-1); + close $src_fh; + close $dst_fh; - } else { - $grp->result (-1); - } - }; + aioreq $pri; + add $grp aio_unlink $dst; + } + }; + } else { + $grp->result (-1); + } + }, + + } else { + $grp->result (-1); + } + }; - $grp + $grp + } } =item aio_move $srcpath, $dstpath, $callback->($status) @@ -443,29 +555,31 @@ =cut sub aio_move($$;$) { - my ($src, $dst, $cb) = @_; + aio_block { + my ($src, $dst, $cb) = @_; - my $pri = aioreq_pri; - my $grp = aio_group $cb; + my $pri = aioreq_pri; + my $grp = aio_group $cb; - aioreq_pri $pri; - add $grp aio_rename $src, $dst, sub { - if ($_[0] && $! == EXDEV) { - aioreq_pri $pri; - add $grp aio_copy $src, $dst, sub { + aioreq_pri $pri; + add $grp aio_rename $src, $dst, sub { + if ($_[0] && $! == EXDEV) { + aioreq_pri $pri; + add $grp aio_copy $src, $dst, sub { + $grp->result ($_[0]); + + if (!$_[0]) { + aioreq_pri $pri; + add $grp aio_unlink $src; + } + }; + } else { $grp->result ($_[0]); + } + }; - if (!$_[0]) { - aioreq_pri $pri; - add $grp aio_unlink $src; - } - }; - } else { - $grp->result ($_[0]); - } - }; - - $grp + $grp + } } =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) @@ -522,90 +636,129 @@ =cut -sub aio_scandir($$$) { - my ($path, $maxreq, $cb) = @_; - - my $pri = aioreq_pri; +sub aio_scandir($$;$) { + aio_block { + my ($path, $maxreq, $cb) = @_; - my $grp = aio_group $cb; + my $pri = aioreq_pri; - $maxreq = 4 if $maxreq <= 0; + my $grp = aio_group $cb; - # stat once - 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]; + $maxreq = 4 if $maxreq <= 0; - # read the directory entries + # stat once aioreq_pri $pri; - add $grp aio_readdir $path, sub { - my $entries = shift - or return $grp->result (); + add $grp aio_stat $path, 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]; - - 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]; + add $grp aio_readdir $path, sub { + my $entries = shift + or return $grp->result (); + + # stat the dir another time + aioreq_pri $pri; + 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 (@dirs, @nondirs); - my $statgrp = add $grp aio_group sub { - $grp->result (\@dirs, \@nondirs); - }; + my $statgrp = add $grp aio_group sub { + $grp->result (\@dirs, \@nondirs); + }; - limit $statgrp $maxreq; - feed $statgrp sub { - return unless @$entries; - my $entry = pop @$entries; - - 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 $entry = pop @$entries; + + 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; + } + } else { + push @nondirs, $entry; } - } else { - push @nondirs, $entry; } } - } + }; }; }; }; }; - }; - $grp + $grp + } +} + +=item aio_rmtree $path, $callback->($status) + +Delete a directory tree starting (and including) C<$path>, return the +status of the final C only. This is a composite request that +uses C to recurse into and rmdir directories, and unlink +everything else. + +=cut + +sub aio_rmtree; +sub aio_rmtree($;$) { + aio_block { + my ($path, $cb) = @_; + + my $pri = aioreq_pri; + my $grp = aio_group $cb; + + aioreq_pri $pri; + add $grp aio_scandir $path, 0, sub { + my ($dirs, $nondirs) = @_; + + my $dirgrp = aio_group sub { + add $grp aio_rmdir $path, sub { + $grp->result ($_[0]); + }; + }; + + (aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs; + (aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs; + + add $grp $dirgrp; + }; + + $grp + } } =item aio_fsync $fh, $callback->($status) @@ -829,6 +982,8 @@ =head2 SUPPORT FUNCTIONS +=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION + =over 4 =item $fileno = IO::AIO::poll_fileno @@ -842,9 +997,10 @@ =item IO::AIO::poll_cb -Process all outstanding events on the result pipe. You have to call this +Process some outstanding events on the result pipe. You have to call this regularly. Returns the number of events processed. Returns immediately -when no events are outstanding. +when no events are outstanding. The amount of events processed depends on +the settings of C and C. If not all requests were processed for whatever reason, the filehandle will still be ready when C returns. @@ -856,49 +1012,56 @@ poll => 'r', async => 1, cb => \&IO::AIO::poll_cb); -=item IO::AIO::poll_some $max_requests +=item IO::AIO::max_poll_reqs $nreqs + +=item IO::AIO::max_poll_time $seconds -Similar to C, but only processes up to C<$max_requests> requests -at a time. +These set the maximum number of requests (default C<0>, meaning infinity) +that are being processed by C in one call, respectively +the maximum amount of time (default C<0>, meaning infinity) spent in +C to process requests (more correctly the mininum amount +of time C is allowed to use). + +Setting C to a non-zero value creates an overhead of one +syscall per request processed, which is not normally a problem unless your +callbacks are really really fast or your OS is really really slow (I am +not mentioning Solaris here). Using C incurs no overhead. + +Setting these is useful if you want to ensure some level of +interactiveness when perl is not fast enough to process all requests in +time. -Useful if you want to ensure some level of interactiveness when perl is -not fast enough to process all requests in time. +For interactive programs, values such as C<0.01> to C<0.1> should be fine. Example: Install an Event watcher that automatically calls -IO::AIO::poll_some with low priority, to ensure that other parts of the +IO::AIO::poll_cb with low priority, to ensure that other parts of the program get the CPU sometimes even under high AIO load. + # try not to spend much more than 0.1s in poll_cb + IO::AIO::max_poll_time 0.1; + + # use a low priority so other tasks have priority Event->io (fd => IO::AIO::poll_fileno, poll => 'r', nice => 1, - cb => sub { IO::AIO::poll_some 256 }); + cb => &IO::AIO::poll_cb); =item IO::AIO::poll_wait -Wait till the result filehandle becomes ready for reading (simply does a -C on the filehandle. This is useful if you want to +synchronously wait for some requests to finish). See C for an example. -=item IO::AIO::nreqs +=item IO::AIO::poll -Returns the number of requests currently in the ready, execute or pending -states (i.e. for which their callback has not been invoked yet). +Waits until some requests have been handled. -Example: wait till there are no outstanding requests anymore: +Returns the number of requests processed, but is otherwise strictly +equivalent to: IO::AIO::poll_wait, IO::AIO::poll_cb - while IO::AIO::nreqs; - -=item IO::AIO::nready - -Returns the number of requests currently in the ready state (not yet -executed). - -=item IO::AIO::npending - -Returns the number of requests currently in the pending state (executed, -but not yet processed by poll_cb). =item IO::AIO::flush @@ -909,14 +1072,7 @@ IO::AIO::poll_wait, IO::AIO::poll_cb while IO::AIO::nreqs; -=item IO::AIO::poll - -Waits until some requests have been handled. - -Strictly equivalent to: - - IO::AIO::poll_wait, IO::AIO::poll_cb - if IO::AIO::nreqs; +=head3 CONTROLLING THE NUMBER OF THREADS =item IO::AIO::min_parallel $nthreads @@ -926,7 +1082,9 @@ however, is unlimited). IO::AIO starts threads only on demand, when an AIO request is queued and -no free thread exists. +no free thread exists. Please note that queueing up a hundred requests can +create demand for a hundred threads, even if it turns out that everything +is in the cache and could have been processed faster by a single thread. It is recommended to keep the number of threads relatively low, as some Linux kernel versions will scale negatively with the number of threads @@ -950,6 +1108,21 @@ Under normal circumstances you don't need to call this function. +=item IO::AIO::max_idle $nthreads + +Limit the number of threads (default: 4) that are allowed to idle (i.e., +threads that did not get a request to process within 10 seconds). That +means if a thread becomes idle while C<$nthreads> other threads are also +idle, it will free its resources and exit. + +This is useful when you allow a large number of threads (e.g. 100 or 1000) +to allow for extremely high load situations, but want to free resources +under normal circumstances (1000 threads can easily consume 30MB of RAM). + +The default is probably ok in most situations, especially if thread +creation is fast. If thread creation is very slow on your system you might +want to use larger values. + =item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs This is a very bad function to use in interactive programs because it @@ -968,6 +1141,28 @@ C is mainly useful in simple scripts (with low values) or as a stop gap to shield against fatal memory overflow (with large values). +=head3 STATISTICAL INFORMATION + +=item IO::AIO::nreqs + +Returns the number of requests currently in the ready, execute or pending +states (i.e. for which their callback has not been invoked yet). + +Example: wait till there are no outstanding requests anymore: + + IO::AIO::poll_wait, IO::AIO::poll_cb + while IO::AIO::nreqs; + +=item IO::AIO::nready + +Returns the number of requests currently in the ready state (not yet +executed). + +=item IO::AIO::npending + +Returns the number of requests currently in the pending state (executed, +but not yet processed by poll_cb). + =back =cut @@ -990,9 +1185,7 @@ min_parallel 8; -END { - flush; -}; +END { flush } 1;