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

Comparing IO-AIO/README (file contents):
Revision 1.5 by root, Sun Jul 10 23:45:16 2005 UTC vs.
Revision 1.16 by root, Wed Mar 1 23:56:55 2006 UTC

… …
13 13
14 aio_read $fh, 30000, 1024, $buffer, 0, sub { 14 aio_read $fh, 30000, 1024, $buffer, 0, sub {
15 $_[0] > 0 or die "read error: $!"; 15 $_[0] > 0 or die "read error: $!";
16 }; 16 };
17 17
18 # AnyEvent
19 open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";
20 my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
21
18 # Event 22 # Event
19 Event->io (fd => IO::AIO::poll_fileno, 23 Event->io (fd => IO::AIO::poll_fileno,
20 poll => 'r', 24 poll => 'r',
21 cb => \&IO::AIO::poll_cb); 25 cb => \&IO::AIO::poll_cb);
22 26
23 # Glib/Gtk2 27 # Glib/Gtk2
24 add_watch Glib::IO IO::AIO::poll_fileno, 28 add_watch Glib::IO IO::AIO::poll_fileno,
25 \&IO::AIO::poll_cb; 29 in => sub { IO::AIO::poll_cb; 1 };
26 30
27 # Tk 31 # Tk
28 Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", 32 Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
29 readable => \&IO::AIO::poll_cb); 33 readable => \&IO::AIO::poll_cb);
34
35 # Danga::Socket
36 Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
37 \&IO::AIO::poll_cb);
30 38
31DESCRIPTION 39DESCRIPTION
32 This module implements asynchronous I/O using whatever means your 40 This module implements asynchronous I/O using whatever means your
33 operating system supports. 41 operating system supports.
34 42
… …
41 currently, for example), and they would only support aio_read and 49 currently, for example), and they would only support aio_read and
42 aio_write, so the remaining functionality would have to be implemented 50 aio_write, so the remaining functionality would have to be implemented
43 using threads anyway. 51 using threads anyway.
44 52
45 Although the module will work with in the presence of other threads, it 53 Although the module will work with in the presence of other threads, it
46 is currently not reentrant, so use appropriate locking yourself. 54 is currently not reentrant, so use appropriate locking yourself, always
55 call "poll_cb" from within the same thread, or never call "poll_cb" (or
56 other "aio_" functions) recursively.
47 57
48FUNCTIONS 58FUNCTIONS
49 AIO FUNCTIONS 59 AIO FUNCTIONS
50 All the "aio_*" calls are more or less thin wrappers around the syscall 60 All the "aio_*" calls are more or less thin wrappers around the syscall
51 with the same name (sans "aio_"). The arguments are similar or 61 with the same name (sans "aio_"). The arguments are similar or
52 identical, and they all accept an additional $callback argument which 62 identical, and they all accept an additional (and optional) $callback
53 must be a code reference. This code reference will get called with the 63 argument which must be a code reference. This code reference will get
54 syscall return code (e.g. most syscalls return -1 on error, unlike perl, 64 called with the syscall return code (e.g. most syscalls return -1 on
55 which usually delivers "false") as it's sole argument when the given 65 error, unlike perl, which usually delivers "false") as it's sole
56 syscall has been executed asynchronously. 66 argument when the given syscall has been executed asynchronously.
57 67
58 All functions that expect a filehandle will also accept a file 68 All functions expecting a filehandle keep a copy of the filehandle
59 descriptor. 69 internally until the request has finished.
60 70
61 The filenames you pass to these routines *must* be absolute. The reason 71 The pathnames you pass to these routines *must* be absolute and encoded
62 is that at the time the request is being executed, the current working 72 in byte form. The reason for the former is that at the time the request
63 directory could have changed. Alternatively, you can make sure that you 73 is being executed, the current working directory could have changed.
64 never change the current working directory. 74 Alternatively, you can make sure that you never change the current
75 working directory.
65 76
77 To encode pathnames to byte form, either make sure you either: a) always
78 pass in filenames you got from outside (command line, readdir etc.), b)
79 are ASCII or ISO 8859-1, c) use the Encode module and encode your
80 pathnames to the locale (or other) encoding in effect in the user
81 environment, d) use Glib::filename_from_unicode on unicode filenames or
82 e) use something else.
83
66 aio_open $pathname, $flags, $mode, $callback 84 aio_open $pathname, $flags, $mode, $callback->($fh)
67 Asynchronously open or create a file and call the callback with a 85 Asynchronously open or create a file and call the callback with a
68 newly created filehandle for the file. 86 newly created filehandle for the file.
69 87
70 The pathname passed to "aio_open" must be absolute. See API NOTES, 88 The pathname passed to "aio_open" must be absolute. See API NOTES,
71 above, for an explanation. 89 above, for an explanation.
72 90
73 The $mode argument is a bitmask. See the "Fcntl" module for a list. 91 The $flags argument is a bitmask. See the "Fcntl" module for a list.
74 They are the same as used in "sysopen". 92 They are the same as used by "sysopen".
93
94 Likewise, $mode specifies the mode of the newly created file, if it
95 didn't exist and "O_CREAT" has been given, just like perl's
96 "sysopen", except that it is mandatory (i.e. use 0 if you don't
97 create new files, and 0666 or 0777 if you do).
75 98
76 Example: 99 Example:
77 100
78 aio_open "/etc/passwd", O_RDONLY, 0, sub { 101 aio_open "/etc/passwd", O_RDONLY, 0, sub {
79 if ($_[0]) { 102 if ($_[0]) {
… …
82 } else { 105 } else {
83 die "open failed: $!\n"; 106 die "open failed: $!\n";
84 } 107 }
85 }; 108 };
86 109
87 aio_close $fh, $callback 110 aio_close $fh, $callback->($status)
88 Asynchronously close a file and call the callback with the result 111 Asynchronously close a file and call the callback with the result
89 code. *WARNING:* although accepted, you should not pass in a perl 112 code. *WARNING:* although accepted, you should not pass in a perl
90 filehandle here, as perl will likely close the file descriptor 113 filehandle here, as perl will likely close the file descriptor
91 itself when the filehandle is destroyed. Normally, you can safely 114 another time when the filehandle is destroyed. Normally, you can
92 call perls "close" or just let filehandles go out of scope. 115 safely call perls "close" or just let filehandles go out of scope.
93 116
117 This is supposed to be a bug in the API, so that might change. It's
118 therefore best to avoid this function.
119
94 aio_read $fh,$offset,$length, $data,$dataoffset,$callback 120 aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
95 aio_write $fh,$offset,$length, $data,$dataoffset,$callback 121 aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
96 Reads or writes "length" bytes from the specified "fh" and "offset" 122 Reads or writes "length" bytes from the specified "fh" and "offset"
97 into the scalar given by "data" and offset "dataoffset" and calls 123 into the scalar given by "data" and offset "dataoffset" and calls
98 the callback without the actual number of bytes read (or -1 on 124 the callback without the actual number of bytes read (or -1 on
99 error, just like the syscall). 125 error, just like the syscall).
100 126
127 The $data scalar *MUST NOT* be modified in any way while the request
128 is outstanding. Modifying it can result in segfaults or WW3 (if the
129 necessary/optional hardware is installed).
130
101 Example: Read 15 bytes at offset 7 into scalar $buffer, strating at 131 Example: Read 15 bytes at offset 7 into scalar $buffer, starting at
102 offset 0 within the scalar: 132 offset 0 within the scalar:
103 133
104 aio_read $fh, 7, 15, $buffer, 0, sub { 134 aio_read $fh, 7, 15, $buffer, 0, sub {
105 $_[0] > 0 or die "read error: $!"; 135 $_[0] > 0 or die "read error: $!";
106 print "read $_[0] bytes: <$buffer>\n"; 136 print "read $_[0] bytes: <$buffer>\n";
107 }; 137 };
108 138
139 aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
140 Tries to copy $length bytes from $in_fh to $out_fh. It starts
141 reading at byte offset $in_offset, and starts writing at the current
142 file offset of $out_fh. Because of that, it is not safe to issue
143 more than one "aio_sendfile" per $out_fh, as they will interfere
144 with each other.
145
146 This call tries to make use of a native "sendfile" syscall to
147 provide zero-copy operation. For this to work, $out_fh should refer
148 to a socket, and $in_fh should refer to mmap'able file.
149
150 If the native sendfile call fails or is not implemented, it will be
151 emulated, so you can call "aio_sendfile" on any type of filehandle
152 regardless of the limitations of the operating system.
153
154 Please note, however, that "aio_sendfile" can read more bytes from
155 $in_fh than are written, and there is no way to find out how many
156 bytes have been read from "aio_sendfile" alone, as "aio_sendfile"
157 only provides the number of bytes written to $out_fh. Only if the
158 result value equals $length one can assume that $length bytes have
159 been read.
160
109 aio_readahead $fh,$offset,$length, $callback 161 aio_readahead $fh,$offset,$length, $callback->($retval)
110 Asynchronously reads the specified byte range into the page cache,
111 using the "readahead" syscall. If that syscall doesn't exist the
112 status will be -1 and $! is set to ENOSYS.
113
114 readahead() populates the page cache with data from a file so that 162 "aio_readahead" populates the page cache with data from a file so
115 subsequent reads from that file will not block on disk I/O. The 163 that subsequent reads from that file will not block on disk I/O. The
116 $offset argument specifies the starting point from which data is to 164 $offset argument specifies the starting point from which data is to
117 be read and $length specifies the number of bytes to be read. I/O is 165 be read and $length specifies the number of bytes to be read. I/O is
118 performed in whole pages, so that offset is effectively rounded down 166 performed in whole pages, so that offset is effectively rounded down
119 to a page boundary and bytes are read up to the next page boundary 167 to a page boundary and bytes are read up to the next page boundary
120 greater than or equal to (off-set+length). aio_readahead() does not 168 greater than or equal to (off-set+length). "aio_readahead" does not
121 read beyond the end of the file. The current file offset of the file 169 read beyond the end of the file. The current file offset of the file
122 is left unchanged. 170 is left unchanged.
123 171
172 If that syscall doesn't exist (likely if your OS isn't Linux) it
173 will be emulated by simply reading the data, which would have a
174 similar effect.
175
124 aio_stat $fh_or_path, $callback 176 aio_stat $fh_or_path, $callback->($status)
125 aio_lstat $fh, $callback 177 aio_lstat $fh, $callback->($status)
126 Works like perl's "stat" or "lstat" in void context. The callback 178 Works like perl's "stat" or "lstat" in void context. The callback
127 will be called after the stat and the results will be available 179 will be called after the stat and the results will be available
128 using "stat _" or "-s _" etc... 180 using "stat _" or "-s _" etc...
129 181
130 The pathname passed to "aio_stat" must be absolute. See API NOTES, 182 The pathname passed to "aio_stat" must be absolute. See API NOTES,
… …
140 aio_stat "/etc/passwd", sub { 192 aio_stat "/etc/passwd", sub {
141 $_[0] and die "stat failed: $!"; 193 $_[0] and die "stat failed: $!";
142 print "size is ", -s _, "\n"; 194 print "size is ", -s _, "\n";
143 }; 195 };
144 196
145 aio_unlink $pathname, $callback 197 aio_unlink $pathname, $callback->($status)
146 Asynchronously unlink (delete) a file and call the callback with the 198 Asynchronously unlink (delete) a file and call the callback with the
147 result code. 199 result code.
148 200
201 aio_rmdir $pathname, $callback->($status)
202 Asynchronously rmdir (delete) a directory and call the callback with
203 the result code.
204
205 aio_readdir $pathname, $callback->($entries)
206 Unlike the POSIX call of the same name, "aio_readdir" reads an
207 entire directory (i.e. opendir + readdir + closedir). The entries
208 will not be sorted, and will NOT include the "." and ".." entries.
209
210 The callback a single argument which is either "undef" or an
211 array-ref with the filenames.
212
213 aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
214 Scans a directory (similar to "aio_readdir") and tries to separate
215 the entries of directory $path into two sets of names, ones you can
216 recurse into (directories), and ones you cannot recurse into
217 (everything else).
218
219 "aio_scandir" is a composite request that consists of many
220 aio-primitives. $maxreq specifies the maximum number of outstanding
221 aio requests that this function generates. If it is "<= 0", then a
222 suitable default will be chosen (currently 8).
223
224 On error, the callback is called without arguments, otherwise it
225 receives two array-refs with path-relative entry names.
226
227 Example:
228
229 aio_scandir $dir, 0, sub {
230 my ($dirs, $nondirs) = @_;
231 print "real directories: @$dirs\n";
232 print "everything else: @$nondirs\n";
233 };
234
235 Implementation notes.
236
237 The "aio_readdir" cannot be avoided, but "stat()"'ing every entry
238 can.
239
240 After reading the directory, the modification time, size etc. of the
241 directory before and after the readdir is checked, and if they
242 match, the link count will be used to decide how many entries are
243 directories (if >= 2). Otherwise, no knowledge of the number of
244 subdirectories will be assumed.
245
246 Then entires will be sorted into likely directories (everything
247 without a non-initial dot) and likely non-directories (everything
248 else). Then every entry + "/." will be "stat"'ed, likely directories
249 first. This is often faster because filesystems might detect the
250 type of the entry without reading the inode data (e.g. ext2fs
251 filetype feature). If that succeeds, it assumes that the entry is a
252 directory or a symlink to directory (which will be checked
253 seperately).
254
255 If the known number of directories has been reached, the rest of the
256 entries is assumed to be non-directories.
257
149 aio_fsync $fh, $callback 258 aio_fsync $fh, $callback->($status)
150 Asynchronously call fsync on the given filehandle and call the 259 Asynchronously call fsync on the given filehandle and call the
151 callback with the fsync result code. 260 callback with the fsync result code.
152 261
153 aio_fdatasync $fh, $callback 262 aio_fdatasync $fh, $callback->($status)
154 Asynchronously call fdatasync on the given filehandle and call the 263 Asynchronously call fdatasync on the given filehandle and call the
155 callback with the fdatasync result code. 264 callback with the fdatasync result code.
156 265
266 If this call isn't available because your OS lacks it or it couldn't
267 be detected, it will be emulated by calling "fsync" instead.
268
157 SUPPORT FUNCTIONS 269 SUPPORT FUNCTIONS
158 $fileno = IO::AIO::poll_fileno 270 $fileno = IO::AIO::poll_fileno
159 Return the *request result pipe filehandle*. This filehandle must be 271 Return the *request result pipe file descriptor*. This filehandle
160 polled for reading by some mechanism outside this module (e.g. Event 272 must be polled for reading by some mechanism outside this module
161 or select, see below). If the pipe becomes readable you have to call 273 (e.g. Event or select, see below or the SYNOPSIS). If the pipe
162 "poll_cb" to check the results. 274 becomes readable you have to call "poll_cb" to check the results.
163 275
164 See "poll_cb" for an example. 276 See "poll_cb" for an example.
165 277
166 IO::AIO::poll_cb 278 IO::AIO::poll_cb
167 Process all outstanding events on the result pipe. You have to call 279 Process all outstanding events on the result pipe. You have to call
168 this regularly. Returns the number of events processed. Returns 280 this regularly. Returns the number of events processed. Returns
169 immediately when no events are outstanding. 281 immediately when no events are outstanding.
170 282
171 You can use Event to multiplex, e.g.: 283 Example: Install an Event watcher that automatically calls
284 IO::AIO::poll_cb with high priority:
172 285
173 Event->io (fd => IO::AIO::poll_fileno, 286 Event->io (fd => IO::AIO::poll_fileno,
174 poll => 'r', async => 1, 287 poll => 'r', async => 1,
175 cb => \&IO::AIO::poll_cb); 288 cb => \&IO::AIO::poll_cb);
176 289
177 IO::AIO::poll_wait 290 IO::AIO::poll_wait
178 Wait till the result filehandle becomes ready for reading (simply 291 Wait till the result filehandle becomes ready for reading (simply
179 does a select on the filehandle. This is useful if you want to 292 does a "select" on the filehandle. This is useful if you want to
180 synchronously wait for some requests to finish). 293 synchronously wait for some requests to finish).
181 294
182 See "nreqs" for an example. 295 See "nreqs" for an example.
183 296
184 IO::AIO::nreqs 297 IO::AIO::nreqs
185 Returns the number of requests currently outstanding. 298 Returns the number of requests currently outstanding (i.e. for which
299 their callback has not been invoked yet).
186 300
187 Example: wait till there are no outstanding requests anymore: 301 Example: wait till there are no outstanding requests anymore:
188 302
189 IO::AIO::poll_wait, IO::AIO::poll_cb 303 IO::AIO::poll_wait, IO::AIO::poll_cb
190 while IO::AIO::nreqs; 304 while IO::AIO::nreqs;
191 305
306 IO::AIO::flush
307 Wait till all outstanding AIO requests have been handled.
308
309 Strictly equivalent to:
310
311 IO::AIO::poll_wait, IO::AIO::poll_cb
312 while IO::AIO::nreqs;
313
314 IO::AIO::poll
315 Waits until some requests have been handled.
316
317 Strictly equivalent to:
318
319 IO::AIO::poll_wait, IO::AIO::poll_cb
320 if IO::AIO::nreqs;
321
192 IO::AIO::min_parallel $nthreads 322 IO::AIO::min_parallel $nthreads
193 Set the minimum number of AIO threads to $nthreads. The default is 323 Set the minimum number of AIO threads to $nthreads. The current
194 1, which means a single asynchronous operation can be done at one 324 default is 4, which means four asynchronous operations can be done
195 time (the number of outstanding operations, however, is unlimited). 325 at one time (the number of outstanding operations, however, is
326 unlimited).
327
328 IO::AIO starts threads only on demand, when an AIO request is queued
329 and no free thread exists.
196 330
197 It is recommended to keep the number of threads low, as some Linux 331 It is recommended to keep the number of threads low, as some Linux
198 kernel versions will scale negatively with the number of threads 332 kernel versions will scale negatively with the number of threads
199 (higher parallelity => MUCH higher latency). With current Linux 2.6 333 (higher parallelity => MUCH higher latency). With current Linux 2.6
200 versions, 4-32 threads should be fine. 334 versions, 4-32 threads should be fine.
201 335
202 Under normal circumstances you don't need to call this function, as 336 Under most circumstances you don't need to call this function, as
203 this module automatically starts some threads (the exact number 337 the module selects a default that is suitable for low to moderate
204 might change, and is currently 4). 338 load.
205 339
206 IO::AIO::max_parallel $nthreads 340 IO::AIO::max_parallel $nthreads
207 Sets the maximum number of AIO threads to $nthreads. If more than 341 Sets the maximum number of AIO threads to $nthreads. If more than
208 the specified number of threads are currently running, kill them. 342 the specified number of threads are currently running, this function
209 This function blocks until the limit is reached. 343 kills them. This function blocks until the limit is reached.
344
345 While $nthreads are zero, aio requests get queued but not executed
346 until the number of threads has been increased again.
210 347
211 This module automatically runs "max_parallel 0" at program end, to 348 This module automatically runs "max_parallel 0" at program end, to
212 ensure that all threads are killed and that there are no outstanding 349 ensure that all threads are killed and that there are no outstanding
213 requests. 350 requests.
214 351
… …
218 Sets the maximum number of outstanding requests to $nreqs. If you 355 Sets the maximum number of outstanding requests to $nreqs. If you
219 try to queue up more than this number of requests, the caller will 356 try to queue up more than this number of requests, the caller will
220 block until some requests have been handled. 357 block until some requests have been handled.
221 358
222 The default is very large, so normally there is no practical limit. 359 The default is very large, so normally there is no practical limit.
223 If you queue up many requests in a loop it it often improves speed 360 If you queue up many requests in a loop it often improves speed if
224 if you set this to a relatively low number, such as 100. 361 you set this to a relatively low number, such as 100.
225 362
226 Under normal circumstances you don't need to call this function. 363 Under normal circumstances you don't need to call this function.
364
365 FORK BEHAVIOUR
366 Before the fork, IO::AIO enters a quiescent state where no requests can
367 be added in other threads and no results will be processed. After the
368 fork the parent simply leaves the quiescent state and continues
369 request/result processing, while the child clears the request/result
370 queue (so the requests started before the fork will only be handled in
371 the parent). Threats will be started on demand until the limit ste in
372 the parent process has been reached again.
227 373
228SEE ALSO 374SEE ALSO
229 Coro, Linux::AIO. 375 Coro, Linux::AIO.
230 376
231AUTHOR 377AUTHOR

Diff Legend

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