--- IO-AIO/AIO.pm 2009/11/30 22:22:13 1.168 +++ IO-AIO/AIO.pm 2010/12/11 19:06:07 1.185 @@ -6,7 +6,7 @@ use IO::AIO; - aio_open "/etc/passwd", O_RDONLY, 0, sub { + aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub { my $fh = shift or die "/etc/passwd: $!"; ... @@ -28,29 +28,6 @@ my $grp = aio_group sub { print "all stats done\n" }; add $grp aio_stat "..." for ...; - # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) - use AnyEvent::AIO; - - # EV integration - my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; - - # Event integration - Event->io (fd => IO::AIO::poll_fileno, - poll => 'r', - cb => \&IO::AIO::poll_cb); - - # Glib/Gtk2 integration - add_watch Glib::IO IO::AIO::poll_fileno, - in => sub { IO::AIO::poll_cb; 1 }; - - # 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 @@ -101,7 +78,7 @@ my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; # queue the request to open /etc/passwd - aio_open "/etc/passwd", O_RDONLY, 0, sub { + aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub { my $fh = shift or die "error while opening: $!"; @@ -193,7 +170,7 @@ use base 'Exporter'; BEGIN { - our $VERSION = '3.31'; + our $VERSION = '3.7'; 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_readdirx @@ -201,14 +178,17 @@ 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); + aio_chmod aio_utime aio_truncate + aio_msync aio_mtouch aio_mlock aio_mlockall + aio_statvfs); our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush min_parallel max_parallel max_idle nreqs nready npending nthreads max_poll_time max_poll_reqs - sendfile fadvise); + sendfile fadvise madvise + mmap munmap munlock munlockall); push @AIO_REQ, qw(aio_busy); # not exported @@ -220,6 +200,78 @@ =head1 FUNCTIONS +=head2 QUICK OVERVIEW + +This section simply lists the prototypes of the most important functions +for quick reference. See the following sections for function-by-function +documentation. + + aio_open $pathname, $flags, $mode, $callback->($fh) + aio_close $fh, $callback->($status) + 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) + aio_readahead $fh,$offset,$length, $callback->($retval) + aio_stat $fh_or_path, $callback->($status) + aio_lstat $fh, $callback->($status) + 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_unlink $pathname, $callback->($status) + aio_mknod $path, $mode, $dev, $callback->($status) + aio_link $srcpath, $dstpath, $callback->($status) + aio_symlink $srcpath, $dstpath, $callback->($status) + aio_readlink $path, $callback->($link) + aio_rename $srcpath, $dstpath, $callback->($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_copy $srcpath, $dstpath, $callback->($status) + aio_move $srcpath, $dstpath, $callback->($status) + aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) + aio_rmtree $path, $callback->($status) + aio_sync $callback->($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_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) + aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status) + aio_mlockall $flags, $callback->($status) + aio_group $callback->(...) + aio_nop $callback->() + + $prev_pri = aioreq_pri [$pri] + aioreq_nice $pri_adjust + + IO::AIO::poll_wait + IO::AIO::poll_cb + IO::AIO::poll + IO::AIO::flush + IO::AIO::max_poll_reqs $nreqs + IO::AIO::max_poll_time $seconds + IO::AIO::min_parallel $nthreads + IO::AIO::max_parallel $nthreads + IO::AIO::max_idle $nthreads + IO::AIO::max_outstanding $maxreqs + IO::AIO::nreqs + IO::AIO::nready + IO::AIO::npending + + IO::AIO::sendfile $ofh, $ifh, $offset, $count + IO::AIO::fadvise $fh, $offset, $len, $advice + IO::AIO::madvise $scalar, $offset, $length, $advice + IO::AIO::mprotect $scalar, $offset, $length, $protect + IO::AIO::munlock $scalar, $offset = 0, $length = undef + IO::AIO::munlockall + =head2 AIO REQUEST FUNCTIONS All the C calls are more or less thin wrappers around the syscall @@ -308,7 +360,7 @@ Example: - aio_open "/etc/passwd", O_RDONLY, 0, sub { + aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub { if ($_[0]) { print "open successful, fh is $_[0]\n"; ... @@ -378,20 +430,30 @@ than one C per C<$out_fh>, as they will interfere with each other. +Please note 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. + +Unlike with other C functions, it makes a lot of sense to use +C on non-blocking sockets, as long as one end (typically +the C<$in_fh>) is a file - the file I/O will then be asynchronous, while +the socket I/O will be non-blocking. Note, however, that you can run into +a trap where C reads some data with readahead, then fails +to write all data, and when the socket is ready the next time, the data +in the cache is already lost, forcing C to again hit the +disk. Explicit C + C let's you control resource usage +much better. + This call tries to make use of a native C syscall to provide zero-copy operation. For this to work, C<$out_fh> should refer to a -socket, and C<$in_fh> should refer to mmap'able file. +socket, and C<$in_fh> should refer to an 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. +If a native sendfile cannot be found or it fails with C, +C, C, C, C or C, +it will be emulated, so you can call C on any type of +filehandle regardless of the limitations of the operating system. =item aio_readahead $fh,$offset,$length, $callback->($retval) @@ -432,6 +494,51 @@ }; +=item aio_statvfs $fh_or_path, $callback->($statvfs) + +Works like the POSIX C or C syscalls, depending on +whether a file handle or path was passed. + +On success, the callback is passed a hash reference with the following +members: C, C, C, C, C, C, +C, C, C, C and C. On failure, C +is passed. + +The following POSIX IO::AIO::ST_* constants are defined: C and +C. + +The following non-POSIX IO::AIO::ST_* flag masks are defined to +their correct value when available, or to C<0> on systems that do +not support them: C, C, C, +C, C, C, C, C, +C and C. + +Example: stat C and dump out the data if successful. + + aio_statvfs "/wd", sub { + my $f = $_[0] + or die "statvfs: $!"; + + use Data::Dumper; + say Dumper $f; + }; + + # result: + { + bsize => 1024, + bfree => 4333064312, + blocks => 10253828096, + files => 2050765568, + flag => 4096, + favail => 2042092649, + bavail => 4333064312, + ffree => 2042092649, + namemax => 255, + frsize => 1024, + fsid => 1810 + } + + =item aio_utime $fh_or_path, $atime, $mtime, $callback->($status) Works like perl's C function (including the special case of $atime @@ -991,6 +1098,72 @@ $grp } +=item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) + +This is a rather advanced IO::AIO call, which only works on mmap(2)ed +scalars (see the C function, although it also works on data +scalars managed by the L or L modules, note that the +scalar must only be modified in-place while an aio operation is pending on +it). + +It calls the C function of your OS, if available, with the memory +area starting at C<$offset> in the string and ending C<$length> bytes +later. If C<$length> is negative, counts from the end, and if C<$length> +is C, then it goes till the end of the string. The flags can be +a combination of C, C and +C. + +=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) + +This is a rather advanced IO::AIO call, which works best on mmap(2)ed +scalars. + +It touches (reads or writes) all memory pages in the specified +range inside the scalar. All caveats and parameters are the same +as for C, above, except for flags, which must be either +C<0> (which reads all pages and ensures they are instantiated) or +C, which modifies the memory page s(by reading and +writing an octet from it, which dirties the page). + +=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status) + +This is a rather advanced IO::AIO call, which works best on mmap(2)ed +scalars. + +It reads in all the pages of the underlying storage into memory (if any) +and locks them, so they are not getting swapped/paged out or removed. + +If C<$length> is undefined, then the scalar will be locked till the end. + +On systems that do not implement C, this function returns C<-1> +and sets errno to C. + +Note that the corresponding C is synchronous and is +documented under L. + +Example: open a file, mmap and mlock it - both will be undone when +C<$data> gets destroyed. + + open my $fh, "<", $path or die "$path: $!"; + my $data; + IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh; + aio_mlock $data; # mlock in background + +=item aio_mlockall $flags, $callback->($status) + +Calls the C function with the given C<$flags> (a combination of +C and C). + +On systems that do not implement C, this function returns C<-1> +and sets errno to C. + +Note that the corresponding C is synchronous and is +documented under L. + +Example: asynchronously lock all current and future pages into memory. + + aio_mlockall IO::AIO::MCL_FUTURE; + =item aio_group $callback->(...) This is a very special aio request: Instead of doing something, it is a @@ -1241,6 +1414,33 @@ poll => 'r', async => 1, cb => \&IO::AIO::poll_cb); +=item 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 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::poll - -Waits until some requests have been handled. - -Returns the number of requests processed, but is otherwise strictly -equivalent to: - - IO::AIO::poll_wait, IO::AIO::poll_cb - -=item IO::AIO::flush - -Wait till all outstanding AIO requests have been handled. - -Strictly equivalent to: - - IO::AIO::poll_wait, IO::AIO::poll_cb - while IO::AIO::nreqs; - =back =head3 CONTROLLING THE NUMBER OF THREADS @@ -1420,7 +1593,7 @@ =item IO::AIO::fadvise $fh, $offset, $len, $advice -Simply calls the C function (see it's +Simply calls the C function (see its manpage for details). The following advice constants are avaiable: C, C, C, C, @@ -1429,6 +1602,92 @@ On systems that do not implement C, this function returns ENOSYS, otherwise the return value of C. +=item IO::AIO::madvise $scalar, $offset, $len, $advice + +Simply calls the C function (see its +manpage for details). The following advice constants are +avaiable: C, C, +C, C, C. + +On systems that do not implement C, this function returns +ENOSYS, otherwise the return value of C. + +=item IO::AIO::mprotect $scalar, $offset, $len, $protect + +Simply calls the C function on the preferably AIO::mmap'ed +$scalar (see its manpage for details). The following protect +constants are avaiable: C, C, +C, C. + +On systems that do not implement C, this function returns +ENOSYS, otherwise the return value of C. + +=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset] + +Memory-maps a file (or anonymous memory range) and attaches it to the +given C<$scalar>, which will act like a string scalar. + +The only operations allowed on the scalar are C/C that 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 C<$scalar> is automatically removed +when the C<$scalar> is destroyed, or when the C or +C functions are called. + +This calls the C(2) function internally. See your system's manual +page for details on the C<$length>, C<$prot> and C<$flags> parameters. + +The C<$length> must be larger than zero and smaller than the actual +filesize. + +C<$prot> is a combination of C, C, +C and/or C, + +C<$flags> can be a combination of C or +C, or a number of system-specific flags (when +not available, the are defined as 0): C +(which is set to C if your system only provides this +constant), C, C, +C, C or +C + +If C<$fh> is C, then a file descriptor of C<-1> is passed. + +C<$offset> is the offset from the start of the file - it generally must be +a multiple of C and defaults to C<0>. + +Example: + + use Digest::MD5; + use IO::AIO; + + open my $fh, ". + +=item IO::AIO::munlock $scalar, $offset = 0, $length = undef + +Calls the C function, undoing the effects of a previous +C call (see its description for details). + +=item IO::AIO::munlockall + +Calls the C function. + +On systems that do not implement C, this function returns +ENOSYS, otherwise the return value of C. + =back =cut @@ -1439,6 +1698,37 @@ 1; +=head1 EVENT LOOP INTEGRATION + +It is recommended to use L to integrate IO::AIO +automatically into many event loops: + + # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) + use AnyEvent::AIO; + +You can also integrate IO::AIO manually into many event loops, here are +some examples of how to do this: + + # EV integration + my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; + + # Event integration + Event->io (fd => IO::AIO::poll_fileno, + poll => 'r', + cb => \&IO::AIO::poll_cb); + + # Glib/Gtk2 integration + add_watch Glib::IO IO::AIO::poll_fileno, + in => sub { IO::AIO::poll_cb; 1 }; + + # 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); + =head2 FORK BEHAVIOUR This module should do "the right thing" when the process using it forks: