ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/IO-AIO/README
(Generate patch)

Comparing IO-AIO/README (file contents):
Revision 1.1 by root, Sun Jul 10 17:07:44 2005 UTC vs.
Revision 1.13 by root, Tue Aug 30 15:45:10 2005 UTC

… …
2 IO::AIO - Asynchronous Input/Output 2 IO::AIO - Asynchronous Input/Output
3 3
4SYNOPSIS 4SYNOPSIS
5 use IO::AIO; 5 use IO::AIO;
6 6
7 aio_open "/etc/passwd", O_RDONLY, 0, sub {
8 my ($fh) = @_;
9 ...
10 };
11
12 aio_unlink "/tmp/file", sub { };
13
14 aio_read $fh, 30000, 1024, $buffer, 0, sub {
15 $_[0] > 0 or die "read error: $!";
16 };
17
18 # Event
19 Event->io (fd => IO::AIO::poll_fileno,
20 poll => 'r',
21 cb => \&IO::AIO::poll_cb);
22
23 # Glib/Gtk2
24 add_watch Glib::IO IO::AIO::poll_fileno,
25 in => sub { IO::AIO::poll_cb; 1 };
26
27 # Tk
28 Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
29 readable => \&IO::AIO::poll_cb);
30
31 # Danga::Socket
32 Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
33 \&IO::AIO::poll_cb);
34
7DESCRIPTION 35DESCRIPTION
8 This module implements asynchronous I/O using whatever means your 36 This module implements asynchronous I/O using whatever means your
9 operating system supports. Currently, it falls back to Linux::AIO if 37 operating system supports.
10 that module is available, or uses pthreads to emulato aio functionality.
11 38
12 Currently, in this module a number of threads are started that execute 39 Currently, a number of threads are started that execute your read/writes
13 your read/writes and signal their completion. You don't need thread 40 and signal their completion. You don't need thread support in your libc
14 support in your libc or perl, and the threads created by this module 41 or perl, and the threads created by this module will not be visible to
15 will not be visible to the pthreads library. 42 the pthreads library. In the future, this module might make use of the
43 native aio functions available on many operating systems. However, they
44 are often not well-supported (Linux doesn't allow them on normal files
45 currently, for example), and they would only support aio_read and
46 aio_write, so the remaining functionality would have to be implemented
47 using threads anyway.
16 48
17 Although the module will work with in the presence of other threads, it 49 Although the module will work with in the presence of other threads, it
18 is not reentrant, so use appropriate locking yourself. 50 is currently not reentrant, so use appropriate locking yourself, always
51 call "poll_cb" from within the same thread, or never call "poll_cb" (or
52 other "aio_" functions) recursively.
19 53
20 API NOTES 54FUNCTIONS
55 AIO FUNCTIONS
21 All the "aio_*" calls are more or less thin wrappers around the syscall 56 All the "aio_*" calls are more or less thin wrappers around the syscall
22 with the same name (sans "aio_"). The arguments are similar or 57 with the same name (sans "aio_"). The arguments are similar or
23 identical, and they all accept an additional $callback argument which 58 identical, and they all accept an additional (and optional) $callback
24 must be a code reference. This code reference will get called with the 59 argument which must be a code reference. This code reference will get
25 syscall return code (e.g. most syscalls return -1 on error, unlike perl, 60 called with the syscall return code (e.g. most syscalls return -1 on
26 which usually delivers "false") as it's sole argument when the given 61 error, unlike perl, which usually delivers "false") as it's sole
27 syscall has been executed asynchronously. 62 argument when the given syscall has been executed asynchronously.
28 63
29 All functions that expect a filehandle will also accept a file 64 All functions expecting a filehandle keep a copy of the filehandle
30 descriptor. 65 internally until the request has finished.
31 66
32 The filenames you pass to these routines *must* be absolute. The reason 67 The pathnames you pass to these routines *must* be absolute and encoded
33 is that at the time the request is being executed, the current working 68 in byte form. The reason for the former is that at the time the request
34 directory could have changed. Alternatively, you can make sure that you 69 is being executed, the current working directory could have changed.
35 never change the current working directory. 70 Alternatively, you can make sure that you never change the current
71 working directory.
36 72
37 IO::AIO::min_parallel $nthreads 73 To encode pathnames to byte form, either make sure you either: a) always
38 Set the minimum number of AIO threads to $nthreads. The default is 74 pass in filenames you got from outside (command line, readdir etc.), b)
39 1, which means a single asynchronous operation can be done at one 75 are ASCII or ISO 8859-1, c) use the Encode module and encode your
40 time (the number of outstanding operations, however, is unlimited). 76 pathnames to the locale (or other) encoding in effect in the user
77 environment, d) use Glib::filename_from_unicode on unicode filenames or
78 e) use something else.
41 79
42 It is recommended to keep the number of threads low, as some linux
43 kernel versions will scale negatively with the number of threads
44 (higher parallelity => MUCH higher latency).
45
46 Under normal circumstances you don't need to call this function, as
47 this module automatically starts a single async thread.
48
49 IO::AIO::max_parallel $nthreads
50 Sets the maximum number of AIO threads to $nthreads. If more than
51 the specified number of threads are currently running, kill them.
52 This function blocks until the limit is reached.
53
54 This module automatically runs "max_parallel 0" at program end, to
55 ensure that all threads are killed and that there are no outstanding
56 requests.
57
58 Under normal circumstances you don't need to call this function.
59
60 $fileno = IO::AIO::poll_fileno
61 Return the *request result pipe filehandle*. This filehandle must be
62 polled for reading by some mechanism outside this module (e.g. Event
63 or select, see below). If the pipe becomes readable you have to call
64 "poll_cb" to check the results.
65
66 See "poll_cb" for an example.
67
68 IO::AIO::poll_cb
69 Process all outstanding events on the result pipe. You have to call
70 this regularly. Returns the number of events processed. Returns
71 immediately when no events are outstanding.
72
73 You can use Event to multiplex, e.g.:
74
75 Event->io (fd => IO::AIO::poll_fileno,
76 poll => 'r', async => 1,
77 cb => \&IO::AIO::poll_cb);
78
79 IO::AIO::poll_wait
80 Wait till the result filehandle becomes ready for reading (simply
81 does a select on the filehandle. This is useful if you want to
82 synchronously wait for some requests to finish).
83
84 See "nreqs" for an example.
85
86 IO::AIO::nreqs
87 Returns the number of requests currently outstanding.
88
89 Example: wait till there are no outstanding requests anymore:
90
91 IO::AIO::poll_wait, IO::AIO::poll_cb
92 while IO::AIO::nreqs;
93
94 aio_open $pathname, $flags, $mode, $callback 80 aio_open $pathname, $flags, $mode, $callback->($fh)
95 Asynchronously open or create a file and call the callback with the 81 Asynchronously open or create a file and call the callback with a
96 filedescriptor (NOT a perl filehandle, sorry for that, but watch 82 newly created filehandle for the file.
97 out, this might change in the future).
98 83
84 The pathname passed to "aio_open" must be absolute. See API NOTES,
85 above, for an explanation.
86
99 The $mode argument is a bitmask. See the "Fcntl" module for a list. 87 The $flags argument is a bitmask. See the "Fcntl" module for a list.
100 They are the same as used in "sysopen". 88 They are the same as used by "sysopen".
89
90 Likewise, $mode specifies the mode of the newly created file, if it
91 didn't exist and "O_CREAT" has been given, just like perl's
92 "sysopen", except that it is mandatory (i.e. use 0 if you don't
93 create new files, and 0666 or 0777 if you do).
101 94
102 Example: 95 Example:
103 96
104 aio_open "/etc/passwd", O_RDONLY, 0, sub { 97 aio_open "/etc/passwd", O_RDONLY, 0, sub {
105 if ($_[0] >= 0) { 98 if ($_[0]) {
106 open my $fh, "<&$_[0]"; # create a copy for perl
107 aio_close $_[0], sub { }; # close the aio handle
108 print "open successful, fh is $fh\n"; 99 print "open successful, fh is $_[0]\n";
109 ... 100 ...
110 } else { 101 } else {
111 die "open failed: $!\n"; 102 die "open failed: $!\n";
112 } 103 }
113 }; 104 };
114 105
115 aio_close $fh, $callback 106 aio_close $fh, $callback->($status)
116 Asynchronously close a file and call the callback with the result 107 Asynchronously close a file and call the callback with the result
117 code. 108 code. *WARNING:* although accepted, you should not pass in a perl
109 filehandle here, as perl will likely close the file descriptor
110 another time when the filehandle is destroyed. Normally, you can
111 safely call perls "close" or just let filehandles go out of scope.
118 112
113 This is supposed to be a bug in the API, so that might change. It's
114 therefore best to avoid this function.
115
119 aio_read $fh,$offset,$length, $data,$dataoffset,$callback 116 aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
120 aio_write $fh,$offset,$length, $data,$dataoffset,$callback 117 aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
121 Reads or writes "length" bytes from the specified "fh" and "offset" 118 Reads or writes "length" bytes from the specified "fh" and "offset"
122 into the scalar given by "data" and offset "dataoffset" and calls 119 into the scalar given by "data" and offset "dataoffset" and calls
123 the callback without the actual number of bytes read (or -1 on 120 the callback without the actual number of bytes read (or -1 on
124 error, just like the syscall). 121 error, just like the syscall).
125 122
123 The $data scalar *MUST NOT* be modified in any way while the request
124 is outstanding. Modifying it can result in segfaults or WW3 (if the
125 necessary/optional hardware is installed).
126
126 Example: Read 15 bytes at offset 7 into scalar $buffer, strating at 127 Example: Read 15 bytes at offset 7 into scalar $buffer, starting at
127 offset 0 within the scalar: 128 offset 0 within the scalar:
128 129
129 aio_read $fh, 7, 15, $buffer, 0, sub { 130 aio_read $fh, 7, 15, $buffer, 0, sub {
130 $_[0] >= 0 or die "read error: $!"; 131 $_[0] > 0 or die "read error: $!";
131 print "read <$buffer>\n"; 132 print "read $_[0] bytes: <$buffer>\n";
132 }; 133 };
133 134
135 aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
136 Tries to copy $length bytes from $in_fh to $out_fh. It starts
137 reading at byte offset $in_offset, and starts writing at the current
138 file offset of $out_fh. Because of that, it is not safe to issue
139 more than one "aio_sendfile" per $out_fh, as they will interfere
140 with each other.
141
142 This call tries to make use of a native "sendfile" syscall to
143 provide zero-copy operation. For this to work, $out_fh should refer
144 to a socket, and $in_fh should refer to mmap'able file.
145
146 If the native sendfile call fails or is not implemented, it will be
147 emulated, so you can call "aio_sendfile" on any type of filehandle
148 regardless of the limitations of the operating system.
149
150 Please note, however, that "aio_sendfile" can read more bytes from
151 $in_fh than are written, and there is no way to find out how many
152 bytes have been read from "aio_sendfile" alone, as "aio_sendfile"
153 only provides the number of bytes written to $out_fh. Only if the
154 result value equals $length one can assume that $length bytes have
155 been read.
156
134 aio_readahead $fh,$offset,$length, $callback 157 aio_readahead $fh,$offset,$length, $callback->($retval)
135 Asynchronously reads the specified byte range into the page cache,
136 using the "readahead" syscall.
137
138 readahead() populates the page cache with data from a file so that 158 "aio_readahead" populates the page cache with data from a file so
139 subsequent reads from that file will not block on disk I/O. The 159 that subsequent reads from that file will not block on disk I/O. The
140 $offset argument specifies the starting point from which data is to 160 $offset argument specifies the starting point from which data is to
141 be read and $length specifies the number of bytes to be read. I/O is 161 be read and $length specifies the number of bytes to be read. I/O is
142 performed in whole pages, so that offset is effectively rounded down 162 performed in whole pages, so that offset is effectively rounded down
143 to a page boundary and bytes are read up to the next page boundary 163 to a page boundary and bytes are read up to the next page boundary
144 greater than or equal to (off-set+length). aio_readahead() does not 164 greater than or equal to (off-set+length). "aio_readahead" does not
145 read beyond the end of the file. The current file offset of the file 165 read beyond the end of the file. The current file offset of the file
146 is left unchanged. 166 is left unchanged.
147 167
168 If that syscall doesn't exist (likely if your OS isn't Linux) it
169 will be emulated by simply reading the data, which would have a
170 similar effect.
171
148 aio_stat $fh_or_path, $callback 172 aio_stat $fh_or_path, $callback->($status)
149 aio_lstat $fh, $callback 173 aio_lstat $fh, $callback->($status)
150 Works like perl's "stat" or "lstat" in void context. The callback 174 Works like perl's "stat" or "lstat" in void context. The callback
151 will be called after the stat and the results will be available 175 will be called after the stat and the results will be available
152 using "stat _" or "-s _" etc... 176 using "stat _" or "-s _" etc...
153 177
154 The pathname passed to "aio_stat" must be absolute. See API NOTES, 178 The pathname passed to "aio_stat" must be absolute. See API NOTES,
… …
164 aio_stat "/etc/passwd", sub { 188 aio_stat "/etc/passwd", sub {
165 $_[0] and die "stat failed: $!"; 189 $_[0] and die "stat failed: $!";
166 print "size is ", -s _, "\n"; 190 print "size is ", -s _, "\n";
167 }; 191 };
168 192
169 aio_unlink $pathname, $callback 193 aio_unlink $pathname, $callback->($status)
170 Asynchronously unlink (delete) a file and call the callback with the 194 Asynchronously unlink (delete) a file and call the callback with the
171 result code. 195 result code.
172 196
197 aio_rmdir $pathname, $callback->($status)
198 Asynchronously rmdir (delete) a directory and call the callback with
199 the result code.
200
201 aio_readdir $pathname $callback->($entries)
202 Unlike the POSIX call of the same name, "aio_readdir" reads an
203 entire directory (i.e. opendir + readdir + closedir). The entries
204 will not be sorted, and will NOT include the "." and ".." entries.
205
206 The callback a single argument which is either "undef" or an
207 array-ref with the filenames.
208
209 aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
210 Scans a directory (similar to "aio_readdir") and tries to separate
211 the entries of directory $path into two sets of names, ones you can
212 recurse into (directories), and ones you cannot recurse into
213 (everything else).
214
215 "aio_scandir" is a composite request that consists of many
216 aio-primitives. $maxreq specifies the maximum number of outstanding
217 aio requests that this function generates. If it is "<= 0", then a
218 suitable default will be chosen (currently 8).
219
220 On error, the callback is called without arguments, otherwise it
221 receives two array-refs with path-relative entry names.
222
223 Example:
224
225 aio_scandir $dir, 0, sub {
226 my ($dirs, $nondirs) = @_;
227 print "real directories: @$dirs\n";
228 print "everything else: @$nondirs\n";
229 };
230
231 Implementation notes.
232
233 The "aio_readdir" cannot be avoided, but "stat()"'ing every entry
234 can.
235
236 After reading the directory, the modification time, size etc. of the
237 directory before and after the readdir is checked, and if they
238 match, the link count will be used to decide how many entries are
239 directories (if >= 2). Otherwise, no knowledge of the number of
240 subdirectories will be assumed.
241
242 Then entires will be sorted into likely directories (everything
243 without a non-initial dot) and likely non-directories (everything
244 else). Then every entry + "/." will be "stat"'ed, likely directories
245 first. This is often faster because filesystems might detect the
246 type of the entry without reading the inode data (e.g. ext2s
247 filetype feature). If that succeeds, it assumes that the entry is a
248 directory or a symlink to directory (which will be checked
249 seperately).
250
251 If the known number of directories has been reached, the rest of the
252 entries is assumed to be non-directories.
253
173 aio_fsync $fh, $callback 254 aio_fsync $fh, $callback->($status)
174 Asynchronously call fsync on the given filehandle and call the 255 Asynchronously call fsync on the given filehandle and call the
175 callback with the fsync result code. 256 callback with the fsync result code.
176 257
177 aio_fdatasync $fh, $callback 258 aio_fdatasync $fh, $callback->($status)
178 Asynchronously call fdatasync on the given filehandle and call the 259 Asynchronously call fdatasync on the given filehandle and call the
179 callback with the fdatasync result code. 260 callback with the fdatasync result code.
180 261
181BUGS 262 If this call isn't available because your OS lacks it or it couldn't
182 This module has been extensively tested in a large and very busy 263 be detected, it will be emulated by calling "fsync" instead.
183 webserver for many years now.
184 264
185 - aio_open gives a fd, but all other functions expect a perl filehandle. 265 SUPPORT FUNCTIONS
266 $fileno = IO::AIO::poll_fileno
267 Return the *request result pipe file descriptor*. This filehandle
268 must be polled for reading by some mechanism outside this module
269 (e.g. Event or select, see below or the SYNOPSIS). If the pipe
270 becomes readable you have to call "poll_cb" to check the results.
271
272 See "poll_cb" for an example.
273
274 IO::AIO::poll_cb
275 Process all outstanding events on the result pipe. You have to call
276 this regularly. Returns the number of events processed. Returns
277 immediately when no events are outstanding.
278
279 Example: Install an Event watcher that automatically calls
280 IO::AIO::poll_cb with high priority:
281
282 Event->io (fd => IO::AIO::poll_fileno,
283 poll => 'r', async => 1,
284 cb => \&IO::AIO::poll_cb);
285
286 IO::AIO::poll_wait
287 Wait till the result filehandle becomes ready for reading (simply
288 does a "select" on the filehandle. This is useful if you want to
289 synchronously wait for some requests to finish).
290
291 See "nreqs" for an example.
292
293 IO::AIO::nreqs
294 Returns the number of requests currently outstanding (i.e. for which
295 their callback has not been invoked yet).
296
297 Example: wait till there are no outstanding requests anymore:
298
299 IO::AIO::poll_wait, IO::AIO::poll_cb
300 while IO::AIO::nreqs;
301
302 IO::AIO::flush
303 Wait till all outstanding AIO requests have been handled.
304
305 Strictly equivalent to:
306
307 IO::AIO::poll_wait, IO::AIO::poll_cb
308 while IO::AIO::nreqs;
309
310 IO::AIO::poll
311 Waits until some requests have been handled.
312
313 Strictly equivalent to:
314
315 IO::AIO::poll_wait, IO::AIO::poll_cb
316 if IO::AIO::nreqs;
317
318 IO::AIO::min_parallel $nthreads
319 Set the minimum number of AIO threads to $nthreads. The current
320 default is 4, which means four asynchronous operations can be done
321 at one time (the number of outstanding operations, however, is
322 unlimited).
323
324 IO::AIO starts threads only on demand, when an AIO request is queued
325 and no free thread exists.
326
327 It is recommended to keep the number of threads low, as some Linux
328 kernel versions will scale negatively with the number of threads
329 (higher parallelity => MUCH higher latency). With current Linux 2.6
330 versions, 4-32 threads should be fine.
331
332 Under most circumstances you don't need to call this function, as
333 the module selects a default that is suitable for low to moderate
334 load.
335
336 IO::AIO::max_parallel $nthreads
337 Sets the maximum number of AIO threads to $nthreads. If more than
338 the specified number of threads are currently running, this function
339 kills them. This function blocks until the limit is reached.
340
341 While $nthreads are zero, aio requests get queued but not executed
342 until the number of threads has been increased again.
343
344 This module automatically runs "max_parallel 0" at program end, to
345 ensure that all threads are killed and that there are no outstanding
346 requests.
347
348 Under normal circumstances you don't need to call this function.
349
350 $oldnreqs = IO::AIO::max_outstanding $nreqs
351 Sets the maximum number of outstanding requests to $nreqs. If you
352 try to queue up more than this number of requests, the caller will
353 block until some requests have been handled.
354
355 The default is very large, so normally there is no practical limit.
356 If you queue up many requests in a loop it often improves speed if
357 you set this to a relatively low number, such as 100.
358
359 Under normal circumstances you don't need to call this function.
360
361 FORK BEHAVIOUR
362 Before the fork, IO::AIO enters a quiescent state where no requests can
363 be added in other threads and no results will be processed. After the
364 fork the parent simply leaves the quiescent state and continues
365 request/result processing, while the child clears the request/result
366 queue (so the requests started before the fork will only be handled in
367 the parent). Threats will be started on demand until the limit ste in
368 the parent process has been reached again.
186 369
187SEE ALSO 370SEE ALSO
188 Coro. 371 Coro, Linux::AIO.
189 372
190AUTHOR 373AUTHOR
191 Marc Lehmann <schmorp@schmorp.de> 374 Marc Lehmann <schmorp@schmorp.de>
192 http://home.schmorp.de/ 375 http://home.schmorp.de/
193 376

Diff Legend

– Removed lines
+ Added lines
< Changed lines
> Changed lines