--- IO-AIO/AIO.pm 2006/10/24 14:25:53 1.72 +++ IO-AIO/AIO.pm 2009/06/12 00:43:16 1.151 @@ -7,7 +7,8 @@ use IO::AIO; aio_open "/etc/passwd", O_RDONLY, 0, sub { - my ($fh) = @_; + my $fh = shift + or die "/etc/passwd: $!"; ... }; @@ -27,9 +28,11 @@ 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 }); + # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) + use AnyEvent::AIO; + + # EV integration + my $w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; # Event integration Event->io (fd => IO::AIO::poll_fileno, @@ -53,20 +56,80 @@ 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. 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. -Although the module will work with in the presence of other (Perl-) -threads, it is currently not reentrant in any way, so use appropriate -locking yourself, always call C from within the same thread, or -never call C (or other C functions) recursively. +Although the module will work in the presence of other (Perl-) threads, +it is currently not reentrant in any way, so use appropriate 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 @@ -118,25 +181,37 @@ aio request is severed and calling its methods will either do nothing or result in a runtime error). +=back + =cut package IO::AIO; +use Carp (); + no warnings; use strict 'vars'; use base 'Exporter'; BEGIN { - our $VERSION = '2.0'; + our $VERSION = '3.2'; + + our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close + aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx + aio_scandir aio_symlink aio_readlink aio_sync aio_fsync + aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead + aio_rename aio_link aio_move aio_copy aio_group + aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown + aio_chmod aio_utime aio_truncate); - our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat - aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink - aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move - aio_group aio_nop); our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush - min_parallel max_parallel max_outstanding nreqs); + min_parallel max_parallel max_idle + nreqs nready npending nthreads + max_poll_time max_poll_reqs); + + push @AIO_REQ, qw(aio_busy); # not exported @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; @@ -146,44 +221,51 @@ =head1 FUNCTIONS -=head2 AIO FUNCTIONS +=head2 AIO REQUEST FUNCTIONS All the C calls are more or less thin wrappers around the syscall with the same name (sans C). The arguments are similar or identical, and they all accept an additional (and optional) C<$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 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 whether it is set or not. =over 4 -=item aioreq_pri $pri +=item $prev_pri = aioreq_pri [$pri] -Sets the priority for the next aio request. The default priority -is C<0>, the minimum and maximum priorities are C<-4> and C<4>, -respectively. Requests with higher priority will be serviced first. +Returns the priority value that would be used for the next request and, if +C<$pri> is given, sets the priority for the next aio request. -The priority will be reset to C<0> after each call to one of the C +The default priority is C<0>, the minimum and maximum priorities are C<-4> +and C<4>, respectively. Requests with higher priority will be serviced +first. + +The priority will be reset to C<0> after each call to one of the C functions. Example: open a file with low priority, then read something from it with @@ -200,10 +282,12 @@ }; }; + =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) @@ -219,7 +303,9 @@ Likewise, C<$mode> specifies the mode of the newly created file, if it didn't exist and C has been given, just like perl's C, except that it is mandatory (i.e. use C<0> if you don't create new files, -and C<0666> or C<0777> if you do). +and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified +by the umask in effect then the request is being executed, so better never +change the umask. Example: @@ -232,29 +318,49 @@ } }; + =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 another -time when the filehandle is destroyed. Normally, you can safely call perls -C or just let filehandles go out of scope. +code. -This is supposed to be a bug in the API, so that might change. It's -therefore best to avoid this function. +Unfortunately, you can't do this to perl. Perl I very strongly on +closing the file descriptor associated with the filehandle itself. + +Therefore, C will not close the filehandle - instead it will +use dup2 to overwrite the file descriptor with the write-end of a pipe +(the pipe fd will be created on demand and will be cached). + +Or in other words: the file descriptor will be closed, but it will not be +free for reuse until the perl filehandle is closed. + +=cut =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) =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). +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<$data>. + +If C<$dataoffset> is less than zero, it will be counted from the end of +C<$data>. The C<$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). +is outstanding. Modifying it can result in segfaults or World War III (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: @@ -264,73 +370,6 @@ print "read $_[0] bytes: <$buffer>\n"; }; -=item aio_move $srcpath, $dstpath, $callback->($status) - -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 - -sub aio_move($$$) { - my ($src, $dst, $cb) = @_; - - 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) @@ -355,6 +394,7 @@ 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 @@ -369,6 +409,7 @@ 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->($status) @@ -391,51 +432,335 @@ print "size is ", -s _, "\n"; }; + +=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status) + +Works like perl's C function (including the special case of $atime +and $mtime being undef). Fractional times are supported if the underlying +syscalls support them. + +When called with a pathname, uses utimes(2) if available, otherwise +utime(2). If called on a file descriptor, uses futimes(2) if available, +otherwise returns ENOSYS, so this is not portable. + +Examples: + + # set atime and mtime to current time (basically touch(1)): + aio_utime "path", undef, undef; + # set atime to current time and mtime to beginning of the epoch: + aio_utime "path", time, undef; # undef==0 + + +=item aio_chown $fh_or_path, $uid, $gid, $callback->($status) + +Works like perl's C function, except that C for either $uid +or $gid is being interpreted as "do not change" (but -1 can also be used). + +Examples: + + # same as "chown root path" in the shell: + aio_chown "path", 0, -1; + # same as above: + aio_chown "path", 0, undef; + + +=item aio_truncate $fh_or_path, $offset, $callback->($status) + +Works like truncate(2) or ftruncate(2). + + +=item aio_chmod $fh_or_path, $mode, $callback->($status) + +Works like perl's C function. + + =item aio_unlink $pathname, $callback->($status) Asynchronously unlink (delete) a file and call the callback with the result code. + +=item aio_mknod $path, $mode, $dev, $callback->($status) + +[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) 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_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 rename(2) and call the callback with the result code. + +=item aio_mkdir $pathname, $mode, $callback->($status) + +Asynchronously mkdir (create) a directory and call the callback with +the result code. C<$mode> will be modified by the umask at the time the +request is executed, so do not change your umask. + + =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. +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). On systems that do not deliver the +inode information, this will always be zero. + +=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) + +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($$;$) { + my ($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 = shift + or return $grp->result (-1); + + aioreq_pri $pri; + add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub { + $grp->result ($_[0]); + }; + }; + + $grp +} + +=item aio_copy $srcpath, $dstpath, $callback->($status) + +Try to copy the I (directories not supported as either source or +destination) from C<$srcpath> to C<$dstpath> and call the callback with +the C<0> (error) or C<-1> ok. + +This is a composite request that creates the destination file with +mode 0200 and copies the contents of the source file into it using +C, followed by restoring atime, mtime, access mode and +uid/gid, in that order. + +If an error occurs, the partial destination file will be unlinked, if +possible, except when setting atime, mtime, access mode and uid/gid, where +errors are being ignored. + +=cut + +sub aio_copy($$;$) { + my ($src, $dst, $cb) = @_; + + my $pri = aioreq_pri; + my $grp = aio_group $cb; + + aioreq_pri $pri; + add $grp aio_open $src, O_RDONLY, 0, sub { + if (my $src_fh = $_[0]) { + 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 { + 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; + + 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_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; + close $dst_fh; + + aioreq $pri; + add $grp aio_unlink $dst; + } + }; + } else { + $grp->result (-1); + } + }, + + } else { + $grp->result (-1); + } + }; + + $grp +} + +=item aio_move $srcpath, $dstpath, $callback->($status) + +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 fails with C, it copies the file with C and, if +that is successful, unlinks the C<$srcpath>. + +=cut + +sub aio_move($$;$) { + my ($src, $dst, $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 { + $grp->result ($_[0]); + + if (!$_[0]) { + aioreq_pri $pri; + add $grp aio_unlink $src; + } + }; + } else { + $grp->result ($_[0]); + } + }; + + $grp +} =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) 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). +efficiently separate the entries of directory C<$path> into two sets of +names, directories you can recurse into (directories), and ones you cannot +recurse into (everything else, including symlinks to directories). 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). +will be chosen (currently 4). On error, the callback is called without arguments, otherwise it receives two array-refs with path-relative entry names. @@ -452,20 +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. @@ -479,25 +808,30 @@ =cut -sub aio_scandir($$$) { +sub aio_scandir($$;$) { my ($path, $maxreq, $cb) = @_; + my $pri = aioreq_pri; + my $grp = aio_group $cb; - $maxreq = 6 if $maxreq <= 0; + $maxreq = 4 if $maxreq <= 0; # 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]; # read the directory entries - add $grp aio_readdir $path, sub { + aioreq_pri $pri; + add $grp aio_readdirx $path, READDIR_DIRS_FIRST, 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]; @@ -508,76 +842,90 @@ $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], - @$entries]; - my (@dirs, @nondirs); - my ($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); - } + my $statgrp = add $grp aio_group sub { + $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 = []; + limit $statgrp $maxreq; + feed $statgrp sub { + return unless @$entries; + my $entry = shift @$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, $entry; } - - &$schedcb; } - } + }; }; + }; + }; + }; - &$schedcb while @$entries && $nreq < $maxreq; + $grp +} + +=item aio_rmtree $path, $callback->($status) + +Delete a directory tree starting (and including) C<$path>, return the +status of the final C only. This is a composite request that +uses C to recurse into and rmdir directories, and unlink +everything else. + +=cut + +sub aio_rmtree; +sub aio_rmtree($;$) { + my ($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_sync $callback->($status) + +Asynchronously call sync and call the callback when finished. + =item aio_fsync $fh, $callback->($status) Asynchronously call fsync on the given filehandle and call the callback @@ -591,9 +939,57 @@ 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->(...) +=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) -[EXPERIMENTAL] +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 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, +not just directories. + +Passes C<0> when everything went ok, and C<-1> on error. + +=cut + +sub aio_pathsync($;$) { + my ($path, $cb) = @_; + + my $pri = aioreq_pri; + my $grp = aio_group $cb; + + aioreq_pri $pri; + add $grp aio_open $path, O_RDONLY, 0, sub { + my ($fh) = @_; + if ($fh) { + aioreq_pri $pri; + add $grp aio_fsync $fh, sub { + $grp->result ($_[0]); + + aioreq_pri $pri; + add $grp aio_close $fh; + }; + } else { + $grp->result (-1); + } + }; + + $grp +} + +=item aio_group $callback->(...) 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 @@ -651,8 +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->(...) @@ -706,10 +1103,6 @@ =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 @@ -717,10 +1110,11 @@ 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. +That means after creating a group you have some time to add requests +(precisely before the callback has been invoked, which is only done within +the C). 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 @@ -734,21 +1128,38 @@ Returns all its arguments. +=item $grp->cancel_subs + +Cancel all subrequests and clears any feeder, but not the group request +itself. Useful when you queued a lot of events but got a result early. + =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. +subrequests have finished and set the groups errno to the current value +of errno (just like calling C without an error number). By default, +no argument will be passed and errno is zero. -=item feed $grp $callback->($grp) +=item $grp->errno ([$errno]) + +Sets the group errno value to C<$errno>, or the current value of errno +when the argument is missing. + +Every aio request has an associated errno value that is restored when +the callback is invoked. This method lets you change this value from its +default (0). -[VERY EXPERIMENTAL] +Calling C will also set errno, so make sure you either set C<$!> +before the call to C, or call c after it. + +=item feed $grp $callback->($grp) 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 @@ -762,7 +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: @@ -784,10 +1196,15 @@ 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 +=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION + =over 4 =item $fileno = IO::AIO::poll_fileno @@ -801,9 +1218,15 @@ =item IO::AIO::poll_cb -Process all 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. +Process some outstanding events on the result pipe. You have to call this +regularly. Returns C<0> if all events could be processed, or C<-1> if it +returned earlier for whatever reason. Returns immediately 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, so normally you don't have to +do anything special to have it called later. Example: Install an Event watcher that automatically calls IO::AIO::poll_cb with high priority: @@ -812,23 +1235,56 @@ poll => 'r', async => 1, cb => \&IO::AIO::poll_cb); +=item IO::AIO::max_poll_reqs $nreqs + +=item IO::AIO::max_poll_time $seconds + +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. + +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_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 => &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 outstanding (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::flush @@ -839,14 +1295,11 @@ IO::AIO::poll_wait, IO::AIO::poll_cb while IO::AIO::nreqs; -=item IO::AIO::poll - -Waits until some requests have been handled. +=back -Strictly equivalent to: +=head3 CONTROLLING THE NUMBER OF THREADS - IO::AIO::poll_wait, IO::AIO::poll_cb - if IO::AIO::nreqs; +=over =item IO::AIO::min_parallel $nthreads @@ -856,7 +1309,9 @@ 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 @@ -880,49 +1335,72 @@ Under normal circumstances you don't need to call this function. -=item $oldnreqs = IO::AIO::max_outstanding $nreqs +=item IO::AIO::max_idle $nthreads -[DEPRECATED] +Limit the number of threads (default: 4) that are allowed to idle (i.e., +threads that did not get a request to process within 10 seconds). That +means if a thread becomes idle while C<$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 IO::AIO::max_outstanding $maxreqs + +This is a very bad function to use in interactive programs because it +blocks, and a bad way to reduce concurrency because it is inexact: Better +use an C together with a feed callback. Sets the maximum number of outstanding requests to C<$nreqs>. If you -try to queue up more than this number of requests, the caller will block until -some requests have been handled. +do queue up more than this number of requests, the next call to the +C (and C and other functions calling C) +function will block until the limit is no longer exceeded. + +The default value is very large, so there is no practical limit on the +number of outstanding requests. + +You can still queue as many requests as you want. Therefore, +C is mainly useful in simple scripts (with low values) or +as a stop gap to shield against fatal memory overflow (with large values). + +=back -The default is very large, so normally there is no practical limit. If you -queue up many requests in a loop it often improves speed if you set -this to a relatively low number, such as C<100>. - -This function does not work well together with C's, and their -feeder interface is better suited to limiting concurrency, so do not use -this function. +=head3 STATISTICAL INFORMATION -Under normal circumstances you don't need to call this function. +=over -=back +=item IO::AIO::nreqs -=cut +Returns the number of requests currently in the ready, execute or pending +states (i.e. for which their callback has not been invoked yet). -# support function to convert a fd into a perl filehandle -sub _fd2fh { - return undef if $_[0] < 0; - - # try to generate nice filehandles - my $sym = "IO::AIO::fd#$_[0]"; - local *$sym; - - open *$sym, "+<&=$_[0]" # usually works under any unix - or open *$sym, "<&=$_[0]" # cygwin needs this - or open *$sym, ">&=$_[0]" # or this - or return undef; +Example: wait till there are no outstanding requests anymore: - *$sym -} + 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 min_parallel 8; -END { - max_parallel 0; -} +END { flush } 1; @@ -938,12 +1416,6 @@ parent). Threads will be started on demand until the limit set in the parent process has been reached again. -Temporary memory that was allocated for request processing is not -reclaimed in the child, however. While this is possible in some cases, it -is almost impossible in others (threads are evil you know), so you will -have to live with it. This is around 64k buffer (for sendfile, readahead -emulation) + the size of the directory being scanned (readdir). - In short: the parent will, after a short pause, continue as if fork had not been called, while the child will act as if IO::AIO has not been used yet. @@ -958,7 +1430,7 @@ scalars and other data passed into aio requests will also be locked and will consume memory till the request has entered the done state. -This is now awfully much, so queuing lots of requests is not usually a +This is not awfully much, so queuing lots of requests is not usually a problem. Per-thread usage: @@ -969,11 +1441,12 @@ =head1 KNOWN BUGS -See FORK BEHAVIOUR, above. +Known bugs will be fixed in the next release. =head1 SEE ALSO -L. +L for easy integration into event loops, L for a +more natural syntax. =head1 AUTHOR