IO-AIO/AIO.pm

=head1 NAME

IO::AIO - Asynchronous Input/Output

=head1 SYNOPSIS

 use IO::AIO;

 aio_open "/etc/passwd", O_RDONLY, 0, sub {
    my ($fh) = @_;
    ...
 };

 aio_unlink "/tmp/file", sub { };

 aio_read $fh, 30000, 1024, $buffer, 0, sub {
    $_[0] > 0 or die "read error: $!";
 };

 # Event
 Event->io (fd => IO::AIO::poll_fileno,
            poll => 'r',
            cb => \&IO::AIO::poll_cb);

 # Glib/Gtk2
 add_watch Glib::IO IO::AIO::poll_fileno,
           in => sub { IO::AIO::poll_cb; 1 };

 # Tk
 Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
                           readable => \&IO::AIO::poll_cb);

 # Danga::Socket
 Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
                             \&IO::AIO::poll_cb);


=head1 DESCRIPTION

This module implements asynchronous I/O using whatever means your
operating system supports.

Currently, a number of threads are started that execute your read/writes
and signal their completion. You don't need thread support in your libc or
perl, and the threads created by this module will not be visible to the
pthreads library. 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 (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 threads, it is
currently not reentrant, so use appropriate locking yourself, always call
C<poll_cb> from within the same thread, or never call C<poll_cb> (or other
C<aio_> functions) recursively.

=cut

package IO::AIO;

no warnings;

use base 'Exporter';

use Fcntl ();

BEGIN {
   $VERSION = 1.5;

   @EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink
                aio_rmdir aio_symlink aio_fsync aio_fdatasync aio_readahead);
   @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);

   require XSLoader;
   XSLoader::load IO::AIO, $VERSION;
}

=head1 FUNCTIONS

=head2 AIO FUNCTIONS

All the C<aio_*> calls are more or less thin wrappers around the syscall
with the same name (sans C<aio_>). 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
syscall has been executed asynchronously.

All functions expecting a filehandle keep a copy of the filehandle
internally until the request has finished.

The pathnames you pass to these routines I<must> 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

Asynchronously open or create a file and call the callback with a newly
created filehandle for the file.

The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
for an explanation.

The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
list. They are the same as used by C<sysopen>.

Likewise, C<$mode> specifies the mode of the newly created file, if it
didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
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:

   aio_open "/etc/passwd", O_RDONLY, 0, sub {
      if ($_[0]) {
         print "open successful, fh is $_[0]\n";
         ...
      } else {
         die "open failed: $!\n";
      }
   };

=item aio_close $fh, $callback

Asynchronously close a file and call the callback with the result
code. I<WARNING:> 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<close> 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_write $fh,$offset,$length, $data,$dataoffset,$callback

Reads or writes C<length> bytes from 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).

The C<$data> scalar I<MUST NOT> 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 $_[0] bytes: <$buffer>\n";
   };

=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback

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<$out_fh>. Because of that, it is not safe to issue more
than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
other.

This call tries to make use of a native C<sendfile> 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<aio_sendfile> on any filehandles regardless of
the limitations of the OS.

Please note, however, that C<aio_sendfile> can read more bytes from
C<$in_fh> than are written, and there is no way to find out how many
bytes have been read form C<aio_sendfile> alone, as C<aio_sendfile> only
provides the number of bytes written to C<$out_fh>. Only if the return
value (the value provided to the callback) equals C<$length> one can
assume that C<$length> bytes have been read.

=item aio_readahead $fh,$offset,$length, $callback

C<aio_readahead> 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). C<aio_readahead> does not read beyond the end of the
file. The current file offset of the file is left unchanged.

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

=item aio_lstat $fh, $callback

Works like perl's C<stat> or C<lstat> in void context. The callback will
be called after the stat and the results will be available using C<stat _>
or C<-s _> etc...

The pathname passed to C<aio_stat> must be absolute. See API NOTES, above,
for an explanation.

Currently, the stats are always 64-bit-stats, i.e. instead of returning an
error when stat'ing a large file, the results will be silently truncated
unless perl itself is compiled with large file support.

Example: Print the length of F</etc/passwd>:

   aio_stat "/etc/passwd", sub {
      $_[0] and die "stat failed: $!";
      print "size is ", -s _, "\n";
   };

=item aio_unlink $pathname, $callback

Asynchronously unlink (delete) a file and call the callback with the
result code.

=item aio_rmdir $pathname, $callback

Asynchronously rmdir (delete) a directory and call the callback with the
result code.

=item aio_fsync $fh, $callback

Asynchronously call fsync on the given filehandle and call the callback
with the fsync result code.

=item aio_fdatasync $fh, $callback

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<fsync> instead.

=back

=head2 SUPPORT FUNCTIONS

=over 4

=item $fileno = IO::AIO::poll_fileno

Return the I<request result pipe file descriptor>. 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<poll_cb> to check the results.

See C<poll_cb> for an example.

=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.

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,
              cb => \&IO::AIO::poll_cb);

=item IO::AIO::poll_wait

Wait till the result filehandle becomes ready for reading (simply does a
C<select> on the filehandle. This is useful if you want to synchronously wait
for some requests to finish).

See C<nreqs> for an example.

=item IO::AIO::nreqs

Returns the number of requests currently outstanding (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::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;

=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;

=item IO::AIO::min_parallel $nthreads

Set the minimum number of AIO threads to C<$nthreads>. The current default
is C<4>, which means four asynchronous operations can be done at one time
(the number of outstanding operations, however, is unlimited).

IO::AIO starts threads only on demand, when an AIO request is queued and
no free thread exists.

It is recommended to keep the number of threads low, as some Linux
kernel versions will scale negatively with the number of threads (higher
parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32
threads should be fine.

Under most circumstances you don't need to call this function, as the
module selects a default that is suitable for low to moderate load.

=item IO::AIO::max_parallel $nthreads

Sets the maximum number of AIO threads to C<$nthreads>. If more than the
specified number of threads are currently running, this function kills
them. This function blocks until the limit is reached.

While C<$nthreads> are zero, aio requests get queued but not executed
until the number of threads has been increased again.

This module automatically runs C<max_parallel 0> at program end, to ensure
that all threads are killed and that there are no outstanding requests.

Under normal circumstances you don't need to call this function.

=item $oldnreqs = IO::AIO::max_outstanding $nreqs

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.

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>.

Under normal circumstances you don't need to call this function.

=back

=cut

# 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;

   *$sym
}

min_parallel 4;

END {
   max_parallel 0;
}

1;

=head2 FORK BEHAVIOUR

Before the fork, IO::AIO enters a quiescent state where no requests
can be added in other threads and no results will be processed. After
the fork the parent simply leaves the quiescent state and continues
request/result processing, while the child clears the request/result
queue (so the requests started before the fork will only be handled in
the parent). Threats will be started on demand until the limit ste in the
parent process has been reached again.

=head1 SEE ALSO

L<Coro>, L<Linux::AIO>.

=head1 AUTHOR

 Marc Lehmann <schmorp@schmorp.de>
 http://home.schmorp.de/

=cut

Revision:	1.35
Committed:	Mon Aug 22 23:20:37 2005 UTC (18 years, 9 months ago) by root
Branch:	MAIN
Changes since 1.34:	+23 -0 lines
Log Message:	* empty log message *
#	User	Rev	Content
1	root	1.1	=head1 NAME
2
3			IO::AIO - Asynchronous Input/Output
4
5			=head1 SYNOPSIS
6
7			use IO::AIO;
8
9	root	1.6	aio_open "/etc/passwd", O_RDONLY, 0, sub {
10			my ($fh) = @_;
11			...
12			};
13
14			aio_unlink "/tmp/file", sub { };
15
16			aio_read $fh, 30000, 1024, $buffer, 0, sub {
17	root	1.8	$_[0] > 0 or die "read error: $!";
18	root	1.6	};
19
20			# Event
21			Event->io (fd => IO::AIO::poll_fileno,
22	root	1.7	poll => 'r',
23	root	1.6	cb => \&IO::AIO::poll_cb);
24
25			# Glib/Gtk2
26			add_watch Glib::IO IO::AIO::poll_fileno,
27	root	1.22	in => sub { IO::AIO::poll_cb; 1 };
28	root	1.6
29			# Tk
30			Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
31			readable => \&IO::AIO::poll_cb);
32
33	root	1.11	# Danga::Socket
34			Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
35			\&IO::AIO::poll_cb);
36
37
38	root	1.1	=head1 DESCRIPTION
39
40			This module implements asynchronous I/O using whatever means your
41	root	1.2	operating system supports.
42	root	1.1
43	root	1.2	Currently, a number of threads are started that execute your read/writes
44			and signal their completion. You don't need thread support in your libc or
45			perl, and the threads created by this module will not be visible to the
46			pthreads library. In the future, this module might make use of the native
47			aio functions available on many operating systems. However, they are often
48			not well-supported (Linux doesn't allow them on normal files currently,
49			for example), and they would only support aio_read and aio_write, so the
50			remaining functionality would have to be implemented using threads anyway.
51	root	1.1
52			Although the module will work with in the presence of other threads, it is
53	root	1.22	currently not reentrant, so use appropriate locking yourself, always call
54			C<poll_cb> from within the same thread, or never call C<poll_cb> (or other
55			C<aio_> functions) recursively.
56	root	1.1
57			=cut
58
59			package IO::AIO;
60
61	root	1.23	no warnings;
62
63	root	1.1	use base 'Exporter';
64
65	root	1.2	use Fcntl ();
66
67	root	1.1	BEGIN {
68	root	1.34	$VERSION = 1.5;
69	root	1.1
70			@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink
71	root	1.27	aio_rmdir aio_symlink aio_fsync aio_fdatasync aio_readahead);
72	root	1.4	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);
73	root	1.1
74			require XSLoader;
75			XSLoader::load IO::AIO, $VERSION;
76			}
77
78	root	1.5	=head1 FUNCTIONS
79	root	1.1
80	root	1.5	=head2 AIO FUNCTIONS
81	root	1.1
82	root	1.5	All the C<aio_*> calls are more or less thin wrappers around the syscall
83			with the same name (sans C<aio_>). The arguments are similar or identical,
84	root	1.14	and they all accept an additional (and optional) C<$callback> argument
85			which must be a code reference. This code reference will get called with
86			the syscall return code (e.g. most syscalls return C<-1> on error, unlike
87			perl, which usually delivers "false") as it's sole argument when the given
88			syscall has been executed asynchronously.
89	root	1.1
90	root	1.23	All functions expecting a filehandle keep a copy of the filehandle
91			internally until the request has finished.
92	root	1.1
93	root	1.28	The pathnames you pass to these routines I<must> be absolute and
94			encoded in byte form. The reason for the former is that at the time the
95			request is being executed, the current working directory could have
96			changed. Alternatively, you can make sure that you never change the
97			current working directory.
98
99			To encode pathnames to byte form, either make sure you either: a)
100			always pass in filenames you got from outside (command line, readdir
101			etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode
102			your pathnames to the locale (or other) encoding in effect in the user
103			environment, d) use Glib::filename_from_unicode on unicode filenames or e)
104			use something else.
105	root	1.1
106	root	1.5	=over 4
107	root	1.1
108			=item aio_open $pathname, $flags, $mode, $callback
109
110	root	1.2	Asynchronously open or create a file and call the callback with a newly
111			created filehandle for the file.
112	root	1.1
113			The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
114			for an explanation.
115
116	root	1.20	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
117			list. They are the same as used by C<sysopen>.
118
119			Likewise, C<$mode> specifies the mode of the newly created file, if it
120			didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
121			except that it is mandatory (i.e. use C<0> if you don't create new files,
122			and C<0666> or C<0777> if you do).
123	root	1.1
124			Example:
125
126			aio_open "/etc/passwd", O_RDONLY, 0, sub {
127	root	1.2	if ($_[0]) {
128			print "open successful, fh is $_[0]\n";
129	root	1.1	...
130			} else {
131			die "open failed: $!\n";
132			}
133			};
134
135			=item aio_close $fh, $callback
136
137	root	1.2	Asynchronously close a file and call the callback with the result
138			code. I<WARNING:> although accepted, you should not pass in a perl
139	root	1.20	filehandle here, as perl will likely close the file descriptor another
140			time when the filehandle is destroyed. Normally, you can safely call perls
141			C<close> or just let filehandles go out of scope.
142
143			This is supposed to be a bug in the API, so that might change. It's
144			therefore best to avoid this function.
145	root	1.1
146			=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback
147
148			=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback
149
150			Reads or writes C<length> bytes from the specified C<fh> and C<offset>
151			into the scalar given by C<data> and offset C<dataoffset> and calls the
152			callback without the actual number of bytes read (or -1 on error, just
153			like the syscall).
154
155	root	1.31	The C<$data> scalar I<MUST NOT> be modified in any way while the request
156			is outstanding. Modifying it can result in segfaults or WW3 (if the
157			necessary/optional hardware is installed).
158
159	root	1.17	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
160	root	1.1	offset C<0> within the scalar:
161
162			aio_read $fh, 7, 15, $buffer, 0, sub {
163	root	1.9	$_[0] > 0 or die "read error: $!";
164			print "read $_[0] bytes: <$buffer>\n";
165	root	1.1	};
166
167	root	1.35	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback
168
169			Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
170			reading at byte offset C<$in_offset>, and starts writing at the current
171			file offset of C<$out_fh>. Because of that, it is not safe to issue more
172			than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
173			other.
174
175			This call tries to make use of a native C<sendfile> syscall to provide
176			zero-copy operation. For this to work, C<$out_fh> should refer to a
177			socket, and C<$in_fh> should refer to mmap'able file.
178
179			If the native sendfile call fails or is not implemented, it will be
180			emulated, so you can call C<aio_sendfile> on any filehandles regardless of
181			the limitations of the OS.
182
183			Please note, however, that C<aio_sendfile> can read more bytes from
184			C<$in_fh> than are written, and there is no way to find out how many
185			bytes have been read form C<aio_sendfile> alone, as C<aio_sendfile> only
186			provides the number of bytes written to C<$out_fh>. Only if the return
187			value (the value provided to the callback) equals C<$length> one can
188			assume that C<$length> bytes have been read.
189
190	root	1.1	=item aio_readahead $fh,$offset,$length, $callback
191
192	root	1.20	C<aio_readahead> populates the page cache with data from a file so that
193	root	1.1	subsequent reads from that file will not block on disk I/O. The C<$offset>
194			argument specifies the starting point from which data is to be read and
195			C<$length> specifies the number of bytes to be read. I/O is performed in
196			whole pages, so that offset is effectively rounded down to a page boundary
197			and bytes are read up to the next page boundary greater than or equal to
198	root	1.20	(off-set+length). C<aio_readahead> does not read beyond the end of the
199	root	1.1	file. The current file offset of the file is left unchanged.
200
201	root	1.26	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
202			emulated by simply reading the data, which would have a similar effect.
203
204	root	1.1	=item aio_stat $fh_or_path, $callback
205
206			=item aio_lstat $fh, $callback
207
208			Works like perl's C<stat> or C<lstat> in void context. The callback will
209			be called after the stat and the results will be available using C<stat _>
210			or C<-s _> etc...
211
212			The pathname passed to C<aio_stat> must be absolute. See API NOTES, above,
213			for an explanation.
214
215			Currently, the stats are always 64-bit-stats, i.e. instead of returning an
216			error when stat'ing a large file, the results will be silently truncated
217			unless perl itself is compiled with large file support.
218
219			Example: Print the length of F</etc/passwd>:
220
221			aio_stat "/etc/passwd", sub {
222			$_[0] and die "stat failed: $!";
223			print "size is ", -s _, "\n";
224			};
225
226			=item aio_unlink $pathname, $callback
227
228			Asynchronously unlink (delete) a file and call the callback with the
229			result code.
230
231	root	1.27	=item aio_rmdir $pathname, $callback
232
233			Asynchronously rmdir (delete) a directory and call the callback with the
234			result code.
235
236	root	1.1	=item aio_fsync $fh, $callback
237
238			Asynchronously call fsync on the given filehandle and call the callback
239			with the fsync result code.
240
241			=item aio_fdatasync $fh, $callback
242
243			Asynchronously call fdatasync on the given filehandle and call the
244	root	1.26	callback with the fdatasync result code.
245
246			If this call isn't available because your OS lacks it or it couldn't be
247			detected, it will be emulated by calling C<fsync> instead.
248	root	1.1
249	root	1.5	=back
250
251			=head2 SUPPORT FUNCTIONS
252
253			=over 4
254
255			=item $fileno = IO::AIO::poll_fileno
256
257	root	1.20	Return the I<request result pipe file descriptor>. This filehandle must be
258			polled for reading by some mechanism outside this module (e.g. Event or
259			select, see below or the SYNOPSIS). If the pipe becomes readable you have
260			to call C<poll_cb> to check the results.
261	root	1.5
262			See C<poll_cb> for an example.
263
264			=item IO::AIO::poll_cb
265
266			Process all outstanding events on the result pipe. You have to call this
267			regularly. Returns the number of events processed. Returns immediately
268			when no events are outstanding.
269
270	root	1.20	Example: Install an Event watcher that automatically calls
271			IO::AIO::poll_cb with high priority:
272	root	1.5
273			Event->io (fd => IO::AIO::poll_fileno,
274			poll => 'r', async => 1,
275			cb => \&IO::AIO::poll_cb);
276
277			=item IO::AIO::poll_wait
278
279			Wait till the result filehandle becomes ready for reading (simply does a
280	root	1.20	C<select> on the filehandle. This is useful if you want to synchronously wait
281	root	1.5	for some requests to finish).
282
283			See C<nreqs> for an example.
284
285			=item IO::AIO::nreqs
286
287	root	1.20	Returns the number of requests currently outstanding (i.e. for which their
288			callback has not been invoked yet).
289	root	1.5
290			Example: wait till there are no outstanding requests anymore:
291
292			IO::AIO::poll_wait, IO::AIO::poll_cb
293			while IO::AIO::nreqs;
294
295	root	1.12	=item IO::AIO::flush
296
297			Wait till all outstanding AIO requests have been handled.
298
299	root	1.13	Strictly equivalent to:
300
301			IO::AIO::poll_wait, IO::AIO::poll_cb
302			while IO::AIO::nreqs;
303
304			=item IO::AIO::poll
305
306			Waits until some requests have been handled.
307
308			Strictly equivalent to:
309
310			IO::AIO::poll_wait, IO::AIO::poll_cb
311			if IO::AIO::nreqs;
312
313	root	1.5	=item IO::AIO::min_parallel $nthreads
314
315	root	1.34	Set the minimum number of AIO threads to C<$nthreads>. The current default
316			is C<4>, which means four asynchronous operations can be done at one time
317	root	1.5	(the number of outstanding operations, however, is unlimited).
318
319	root	1.34	IO::AIO starts threads only on demand, when an AIO request is queued and
320			no free thread exists.
321
322	root	1.5	It is recommended to keep the number of threads low, as some Linux
323			kernel versions will scale negatively with the number of threads (higher
324			parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32
325			threads should be fine.
326
327	root	1.34	Under most circumstances you don't need to call this function, as the
328			module selects a default that is suitable for low to moderate load.
329	root	1.5
330			=item IO::AIO::max_parallel $nthreads
331
332	root	1.34	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
333			specified number of threads are currently running, this function kills
334			them. This function blocks until the limit is reached.
335
336			While C<$nthreads> are zero, aio requests get queued but not executed
337			until the number of threads has been increased again.
338	root	1.5
339			This module automatically runs C<max_parallel 0> at program end, to ensure
340			that all threads are killed and that there are no outstanding requests.
341
342			Under normal circumstances you don't need to call this function.
343
344			=item $oldnreqs = IO::AIO::max_outstanding $nreqs
345
346			Sets the maximum number of outstanding requests to C<$nreqs>. If you
347			try to queue up more than this number of requests, the caller will block until
348			some requests have been handled.
349
350			The default is very large, so normally there is no practical limit. If you
351	root	1.34	queue up many requests in a loop it often improves speed if you set
352	root	1.5	this to a relatively low number, such as C<100>.
353
354			Under normal circumstances you don't need to call this function.
355
356			=back
357
358	root	1.1	=cut
359
360	root	1.2	# support function to convert a fd into a perl filehandle
361			sub _fd2fh {
362			return undef if $_[0] < 0;
363
364	root	1.23	# try to generate nice filehandles
365			my $sym = "IO::AIO::fd#$_[0]";
366			local *$sym;
367	root	1.25
368	root	1.27	open *$sym, "+<&=$_[0]" # usually works under any unix
369			or open *$sym, "<&=$_[0]" # cygwin needs this
370			or open *$sym, ">&=$_[0]" # or this
371	root	1.2	or return undef;
372
373	root	1.23	*$sym
374	root	1.2	}
375
376	root	1.1	min_parallel 4;
377
378			END {
379			max_parallel 0;
380			}
381
382			1;
383
384	root	1.27	=head2 FORK BEHAVIOUR
385
386	root	1.34	Before the fork, IO::AIO enters a quiescent state where no requests
387			can be added in other threads and no results will be processed. After
388			the fork the parent simply leaves the quiescent state and continues
389			request/result processing, while the child clears the request/result
390			queue (so the requests started before the fork will only be handled in
391			the parent). Threats will be started on demand until the limit ste in the
392			parent process has been reached again.
393	root	1.27
394	root	1.1	=head1 SEE ALSO
395
396			L<Coro>, L<Linux::AIO>.
397
398			=head1 AUTHOR
399
400			Marc Lehmann <schmorp@schmorp.de>
401			http://home.schmorp.de/
402
403			=cut
404