… | |
… | |
4 | |
4 | |
5 | =head1 SYNOPSIS |
5 | =head1 SYNOPSIS |
6 | |
6 | |
7 | use IO::AIO; |
7 | use IO::AIO; |
8 | |
8 | |
|
|
9 | 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 | $_[0] > 0 or die "read error: $!"; |
|
|
18 | }; |
|
|
19 | |
|
|
20 | # Event |
|
|
21 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
22 | poll => 'r', |
|
|
23 | cb => \&IO::AIO::poll_cb); |
|
|
24 | |
|
|
25 | # Glib/Gtk2 |
|
|
26 | add_watch Glib::IO IO::AIO::poll_fileno, |
|
|
27 | in => sub { IO::AIO::poll_cb; 1 }; |
|
|
28 | |
|
|
29 | # Tk |
|
|
30 | Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
|
|
31 | readable => \&IO::AIO::poll_cb); |
|
|
32 | |
|
|
33 | # Danga::Socket |
|
|
34 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
|
|
35 | \&IO::AIO::poll_cb); |
|
|
36 | |
|
|
37 | |
9 | =head1 DESCRIPTION |
38 | =head1 DESCRIPTION |
10 | |
39 | |
11 | This module implements asynchronous I/O using whatever means your |
40 | This module implements asynchronous I/O using whatever means your |
12 | operating system supports. Currently, it falls back to Linux::AIO if that |
41 | operating system supports. |
13 | module is available, or uses pthreads to emulato aio functionality. |
|
|
14 | |
42 | |
15 | Currently, in this module a number of threads are started that execute |
43 | Currently, a number of threads are started that execute your read/writes |
16 | your read/writes and signal their completion. You don't need thread |
44 | and signal their completion. You don't need thread support in your libc or |
17 | support in your libc or perl, and the threads created by this module will |
45 | perl, and the threads created by this module will not be visible to the |
18 | not be visible to the pthreads library. |
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. |
19 | |
51 | |
20 | Although the module will work with in the presence of other threads, it is |
52 | Although the module will work with in the presence of other threads, it is |
21 | not reentrant, so use appropriate locking yourself. |
53 | currently not reentrant, so use appropriate locking yourself, always call |
22 | |
54 | C<poll_cb> from within the same thread, or never call C<poll_cb> (or other |
23 | =head2 API NOTES |
55 | C<aio_> functions) recursively. |
24 | |
|
|
25 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
|
|
26 | with the same name (sans C<aio_>). The arguments are similar or identical, |
|
|
27 | and they all accept an additional C<$callback> argument which must be |
|
|
28 | a code reference. This code reference will get called with the syscall |
|
|
29 | return code (e.g. most syscalls return C<-1> on error, unlike perl, which |
|
|
30 | usually delivers "false") as it's sole argument when the given syscall has |
|
|
31 | been executed asynchronously. |
|
|
32 | |
|
|
33 | All functions that expect a filehandle will also accept a file descriptor. |
|
|
34 | |
|
|
35 | The filenames you pass to these routines I<must> be absolute. The reason |
|
|
36 | is that at the time the request is being executed, the current working |
|
|
37 | directory could have changed. Alternatively, you can make sure that you |
|
|
38 | never change the current working directory. |
|
|
39 | |
|
|
40 | =over 4 |
|
|
41 | |
56 | |
42 | =cut |
57 | =cut |
43 | |
58 | |
44 | package IO::AIO; |
59 | package IO::AIO; |
45 | |
60 | |
|
|
61 | no warnings; |
|
|
62 | |
46 | use base 'Exporter'; |
63 | use base 'Exporter'; |
47 | |
64 | |
|
|
65 | use Fcntl (); |
|
|
66 | |
48 | BEGIN { |
67 | BEGIN { |
49 | $VERSION = 0.1; |
68 | $VERSION = 1.6; |
50 | |
69 | |
51 | @EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink |
70 | @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
|
|
71 | aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink |
52 | aio_fsync aio_fdatasync aio_readahead); |
72 | aio_fsync aio_fdatasync aio_readahead); |
53 | @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel nreqs); |
73 | @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel |
|
|
74 | max_outstanding nreqs); |
54 | |
75 | |
55 | require XSLoader; |
76 | require XSLoader; |
56 | XSLoader::load IO::AIO, $VERSION; |
77 | XSLoader::load IO::AIO, $VERSION; |
57 | } |
78 | } |
58 | |
79 | |
59 | =item IO::AIO::min_parallel $nthreads |
80 | =head1 FUNCTIONS |
60 | |
81 | |
61 | Set the minimum number of AIO threads to C<$nthreads>. The default is |
82 | =head2 AIO FUNCTIONS |
62 | C<1>, which means a single asynchronous operation can be done at one time |
|
|
63 | (the number of outstanding operations, however, is unlimited). |
|
|
64 | |
83 | |
65 | It is recommended to keep the number of threads low, as some linux |
84 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
66 | kernel versions will scale negatively with the number of threads (higher |
85 | with the same name (sans C<aio_>). The arguments are similar or identical, |
67 | parallelity => MUCH higher latency). |
86 | and they all accept an additional (and optional) C<$callback> argument |
|
|
87 | which must be a code reference. This code reference will get called with |
|
|
88 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
|
|
89 | perl, which usually delivers "false") as it's sole argument when the given |
|
|
90 | syscall has been executed asynchronously. |
68 | |
91 | |
69 | Under normal circumstances you don't need to call this function, as this |
92 | All functions expecting a filehandle keep a copy of the filehandle |
70 | module automatically starts a single async thread. |
93 | internally until the request has finished. |
71 | |
94 | |
72 | =item IO::AIO::max_parallel $nthreads |
95 | The pathnames you pass to these routines I<must> be absolute and |
|
|
96 | encoded in byte form. The reason for the former is that at the time the |
|
|
97 | request is being executed, the current working directory could have |
|
|
98 | changed. Alternatively, you can make sure that you never change the |
|
|
99 | current working directory. |
73 | |
100 | |
74 | Sets the maximum number of AIO threads to C<$nthreads>. If more than |
101 | To encode pathnames to byte form, either make sure you either: a) |
75 | the specified number of threads are currently running, kill them. This |
102 | always pass in filenames you got from outside (command line, readdir |
76 | function blocks until the limit is reached. |
103 | etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
|
|
104 | your pathnames to the locale (or other) encoding in effect in the user |
|
|
105 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
|
|
106 | use something else. |
77 | |
107 | |
78 | This module automatically runs C<max_parallel 0> at program end, to ensure |
108 | =over 4 |
79 | that all threads are killed and that there are no outstanding requests. |
|
|
80 | |
109 | |
81 | Under normal circumstances you don't need to call this function. |
|
|
82 | |
|
|
83 | =item $fileno = IO::AIO::poll_fileno |
|
|
84 | |
|
|
85 | Return the I<request result pipe filehandle>. This filehandle must be |
|
|
86 | polled for reading by some mechanism outside this module (e.g. Event |
|
|
87 | or select, see below). If the pipe becomes readable you have to call |
|
|
88 | C<poll_cb> to check the results. |
|
|
89 | |
|
|
90 | See C<poll_cb> for an example. |
|
|
91 | |
|
|
92 | =item IO::AIO::poll_cb |
|
|
93 | |
|
|
94 | Process all outstanding events on the result pipe. You have to call this |
|
|
95 | regularly. Returns the number of events processed. Returns immediately |
|
|
96 | when no events are outstanding. |
|
|
97 | |
|
|
98 | You can use Event to multiplex, e.g.: |
|
|
99 | |
|
|
100 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
101 | poll => 'r', async => 1, |
|
|
102 | cb => \&IO::AIO::poll_cb); |
|
|
103 | |
|
|
104 | =item IO::AIO::poll_wait |
|
|
105 | |
|
|
106 | Wait till the result filehandle becomes ready for reading (simply does a |
|
|
107 | select on the filehandle. This is useful if you want to synchronously wait |
|
|
108 | for some requests to finish). |
|
|
109 | |
|
|
110 | See C<nreqs> for an example. |
|
|
111 | |
|
|
112 | =item IO::AIO::nreqs |
|
|
113 | |
|
|
114 | Returns the number of requests currently outstanding. |
|
|
115 | |
|
|
116 | Example: wait till there are no outstanding requests anymore: |
|
|
117 | |
|
|
118 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
119 | while IO::AIO::nreqs; |
|
|
120 | |
|
|
121 | =item aio_open $pathname, $flags, $mode, $callback |
110 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
122 | |
111 | |
123 | Asynchronously open or create a file and call the callback with the |
112 | Asynchronously open or create a file and call the callback with a newly |
124 | filedescriptor (NOT a perl filehandle, sorry for that, but watch out, this |
113 | created filehandle for the file. |
125 | might change in the future). |
|
|
126 | |
114 | |
127 | The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
115 | The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
128 | for an explanation. |
116 | for an explanation. |
129 | |
117 | |
130 | The C<$mode> argument is a bitmask. See the C<Fcntl> module for a |
118 | The C<$flags> argument is a bitmask. See the C<Fcntl> module for a |
131 | list. They are the same as used in C<sysopen>. |
119 | list. They are the same as used by C<sysopen>. |
|
|
120 | |
|
|
121 | Likewise, C<$mode> specifies the mode of the newly created file, if it |
|
|
122 | didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>, |
|
|
123 | except that it is mandatory (i.e. use C<0> if you don't create new files, |
|
|
124 | and C<0666> or C<0777> if you do). |
132 | |
125 | |
133 | Example: |
126 | Example: |
134 | |
127 | |
135 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
128 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
136 | if ($_[0] >= 0) { |
129 | if ($_[0]) { |
137 | open my $fh, "<&$_[0]"; # create a copy for perl |
|
|
138 | aio_close $_[0], sub { }; # close the aio handle |
|
|
139 | print "open successful, fh is $fh\n"; |
130 | print "open successful, fh is $_[0]\n"; |
140 | ... |
131 | ... |
141 | } else { |
132 | } else { |
142 | die "open failed: $!\n"; |
133 | die "open failed: $!\n"; |
143 | } |
134 | } |
144 | }; |
135 | }; |
145 | |
136 | |
146 | =item aio_close $fh, $callback |
137 | =item aio_close $fh, $callback->($status) |
147 | |
138 | |
148 | Asynchronously close a file and call the callback with the result code. |
139 | Asynchronously close a file and call the callback with the result |
|
|
140 | code. I<WARNING:> although accepted, you should not pass in a perl |
|
|
141 | filehandle here, as perl will likely close the file descriptor another |
|
|
142 | time when the filehandle is destroyed. Normally, you can safely call perls |
|
|
143 | C<close> or just let filehandles go out of scope. |
149 | |
144 | |
|
|
145 | This is supposed to be a bug in the API, so that might change. It's |
|
|
146 | therefore best to avoid this function. |
|
|
147 | |
150 | =item aio_read $fh,$offset,$length, $data,$dataoffset,$callback |
148 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
151 | |
149 | |
152 | =item aio_write $fh,$offset,$length, $data,$dataoffset,$callback |
150 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
153 | |
151 | |
154 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
152 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
155 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
153 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
156 | callback without the actual number of bytes read (or -1 on error, just |
154 | callback without the actual number of bytes read (or -1 on error, just |
157 | like the syscall). |
155 | like the syscall). |
158 | |
156 | |
|
|
157 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
|
|
158 | is outstanding. Modifying it can result in segfaults or WW3 (if the |
|
|
159 | necessary/optional hardware is installed). |
|
|
160 | |
159 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, strating at |
161 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
160 | offset C<0> within the scalar: |
162 | offset C<0> within the scalar: |
161 | |
163 | |
162 | aio_read $fh, 7, 15, $buffer, 0, sub { |
164 | aio_read $fh, 7, 15, $buffer, 0, sub { |
163 | $_[0] >= 0 or die "read error: $!"; |
165 | $_[0] > 0 or die "read error: $!"; |
164 | print "read <$buffer>\n"; |
166 | print "read $_[0] bytes: <$buffer>\n"; |
165 | }; |
167 | }; |
166 | |
168 | |
|
|
169 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
|
|
170 | |
|
|
171 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
|
|
172 | reading at byte offset C<$in_offset>, and starts writing at the current |
|
|
173 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
|
|
174 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
|
|
175 | other. |
|
|
176 | |
|
|
177 | This call tries to make use of a native C<sendfile> syscall to provide |
|
|
178 | zero-copy operation. For this to work, C<$out_fh> should refer to a |
|
|
179 | socket, and C<$in_fh> should refer to mmap'able file. |
|
|
180 | |
|
|
181 | If the native sendfile call fails or is not implemented, it will be |
|
|
182 | emulated, so you can call C<aio_sendfile> on any type of filehandle |
|
|
183 | regardless of the limitations of the operating system. |
|
|
184 | |
|
|
185 | Please note, however, that C<aio_sendfile> can read more bytes from |
|
|
186 | C<$in_fh> than are written, and there is no way to find out how many |
|
|
187 | bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
|
|
188 | provides the number of bytes written to C<$out_fh>. Only if the result |
|
|
189 | value equals C<$length> one can assume that C<$length> bytes have been |
|
|
190 | read. |
|
|
191 | |
167 | =item aio_readahead $fh,$offset,$length, $callback |
192 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
168 | |
193 | |
169 | Asynchronously reads the specified byte range into the page cache, using |
|
|
170 | the C<readahead> syscall. If that syscall doesn't exist the status will be |
|
|
171 | C<-1> and C<$!> is set to ENOSYS. |
|
|
172 | |
|
|
173 | readahead() populates the page cache with data from a file so that |
194 | C<aio_readahead> populates the page cache with data from a file so that |
174 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
195 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
175 | argument specifies the starting point from which data is to be read and |
196 | argument specifies the starting point from which data is to be read and |
176 | C<$length> specifies the number of bytes to be read. I/O is performed in |
197 | C<$length> specifies the number of bytes to be read. I/O is performed in |
177 | whole pages, so that offset is effectively rounded down to a page boundary |
198 | whole pages, so that offset is effectively rounded down to a page boundary |
178 | and bytes are read up to the next page boundary greater than or equal to |
199 | and bytes are read up to the next page boundary greater than or equal to |
179 | (off-set+length). aio_readahead() does not read beyond the end of the |
200 | (off-set+length). C<aio_readahead> does not read beyond the end of the |
180 | file. The current file offset of the file is left unchanged. |
201 | file. The current file offset of the file is left unchanged. |
181 | |
202 | |
|
|
203 | If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
|
|
204 | emulated by simply reading the data, which would have a similar effect. |
|
|
205 | |
182 | =item aio_stat $fh_or_path, $callback |
206 | =item aio_stat $fh_or_path, $callback->($status) |
183 | |
207 | |
184 | =item aio_lstat $fh, $callback |
208 | =item aio_lstat $fh, $callback->($status) |
185 | |
209 | |
186 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
210 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
187 | be called after the stat and the results will be available using C<stat _> |
211 | be called after the stat and the results will be available using C<stat _> |
188 | or C<-s _> etc... |
212 | or C<-s _> etc... |
189 | |
213 | |
… | |
… | |
199 | aio_stat "/etc/passwd", sub { |
223 | aio_stat "/etc/passwd", sub { |
200 | $_[0] and die "stat failed: $!"; |
224 | $_[0] and die "stat failed: $!"; |
201 | print "size is ", -s _, "\n"; |
225 | print "size is ", -s _, "\n"; |
202 | }; |
226 | }; |
203 | |
227 | |
204 | =item aio_unlink $pathname, $callback |
228 | =item aio_unlink $pathname, $callback->($status) |
205 | |
229 | |
206 | Asynchronously unlink (delete) a file and call the callback with the |
230 | Asynchronously unlink (delete) a file and call the callback with the |
207 | result code. |
231 | result code. |
208 | |
232 | |
|
|
233 | =item aio_rmdir $pathname, $callback->($status) |
|
|
234 | |
|
|
235 | Asynchronously rmdir (delete) a directory and call the callback with the |
|
|
236 | result code. |
|
|
237 | |
|
|
238 | =item aio_readdir $pathname $callback->($entries) |
|
|
239 | |
|
|
240 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
|
|
241 | directory (i.e. opendir + readdir + closedir). The entries will not be |
|
|
242 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
|
|
243 | |
|
|
244 | The callback a single argument which is either C<undef> or an array-ref |
|
|
245 | with the filenames. |
|
|
246 | |
|
|
247 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
|
|
248 | |
|
|
249 | Scans a directory (similar to C<aio_readdir>) and tries to separate the |
|
|
250 | entries of directory C<$path> into two sets of names, ones you can recurse |
|
|
251 | into (directories), and ones you cannot recurse into (everything else). |
|
|
252 | |
|
|
253 | C<aio_scandir> is a composite request that consists of many |
|
|
254 | aio-primitives. C<$maxreq> specifies the maximum number of outstanding |
|
|
255 | aio requests that this function generates. If it is C<< <= 0 >>, then a |
|
|
256 | suitable default will be chosen (currently 8). |
|
|
257 | |
|
|
258 | On error, the callback is called without arguments, otherwise it receives |
|
|
259 | two array-refs with path-relative entry names. |
|
|
260 | |
|
|
261 | Example: |
|
|
262 | |
|
|
263 | aio_scandir $dir, 0, sub { |
|
|
264 | my ($dirs, $nondirs) = @_; |
|
|
265 | print "real directories: @$dirs\n"; |
|
|
266 | print "everything else: @$nondirs\n"; |
|
|
267 | }; |
|
|
268 | |
|
|
269 | Implementation notes. |
|
|
270 | |
|
|
271 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
|
|
272 | |
|
|
273 | After reading the directory, the modification time, size etc. of the |
|
|
274 | directory before and after the readdir is checked, and if they match, the |
|
|
275 | link count will be used to decide how many entries are directories (if |
|
|
276 | >= 2). Otherwise, no knowledge of the number of subdirectories will be |
|
|
277 | assumed. |
|
|
278 | |
|
|
279 | Then entires will be sorted into likely directories (everything without a |
|
|
280 | non-initial dot) and likely non-directories (everything else). Then every |
|
|
281 | entry + C</.> will be C<stat>'ed, likely directories first. This is often |
|
|
282 | faster because filesystems might detect the type of the entry without |
|
|
283 | reading the inode data (e.g. ext2s filetype feature). If that succeeds, |
|
|
284 | it assumes that the entry is a directory or a symlink to directory (which |
|
|
285 | will be checked seperately). |
|
|
286 | |
|
|
287 | If the known number of directories has been reached, the rest of the |
|
|
288 | entries is assumed to be non-directories. |
|
|
289 | |
|
|
290 | =cut |
|
|
291 | |
|
|
292 | sub aio_scandir($$$) { |
|
|
293 | my ($path, $maxreq, $cb) = @_; |
|
|
294 | |
|
|
295 | $maxreq = 8 if $maxreq <= 0; |
|
|
296 | |
|
|
297 | # stat once |
|
|
298 | aio_stat $path, sub { |
|
|
299 | $cb->() if $_[0]; |
|
|
300 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
|
|
301 | |
|
|
302 | # read the directory entries |
|
|
303 | aio_readdir $path, sub { |
|
|
304 | my $entries = shift |
|
|
305 | or return $cb->(); |
|
|
306 | |
|
|
307 | # stat the dir another time |
|
|
308 | aio_stat $path, sub { |
|
|
309 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
|
|
310 | |
|
|
311 | my $ndirs; |
|
|
312 | |
|
|
313 | # take the slow route if anything looks fishy |
|
|
314 | if ($hash1 ne $hash2) { |
|
|
315 | $ndirs = -1; |
|
|
316 | } else { |
|
|
317 | # if nlink == 2, we are finished |
|
|
318 | # on non-posix-fs's, we rely on nlink < 2 |
|
|
319 | $ndirs = (stat _)[3] - 2 |
|
|
320 | or $cb->([], $entries); |
|
|
321 | } |
|
|
322 | |
|
|
323 | # sort into likely dirs and likely nondirs |
|
|
324 | # dirs == files without ".", short entries first |
|
|
325 | $entries = [map $_->[0], |
|
|
326 | sort { $b->[1] cmp $a->[1] } |
|
|
327 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
|
|
328 | @$entries]; |
|
|
329 | |
|
|
330 | my (@dirs, @nondirs); |
|
|
331 | |
|
|
332 | my ($statcb, $schedcb); |
|
|
333 | my $nreq = 0; |
|
|
334 | |
|
|
335 | $schedcb = sub { |
|
|
336 | if (@$entries) { |
|
|
337 | if ($nreq < $maxreq) { |
|
|
338 | my $ent = pop @$entries; |
|
|
339 | $nreq++; |
|
|
340 | aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) }; |
|
|
341 | } |
|
|
342 | } elsif (!$nreq) { |
|
|
343 | # finished |
|
|
344 | undef $statcb; |
|
|
345 | undef $schedcb; |
|
|
346 | $cb->(\@dirs, \@nondirs); |
|
|
347 | undef $cb; |
|
|
348 | } |
|
|
349 | }; |
|
|
350 | $statcb = sub { |
|
|
351 | my ($status, $entry) = @_; |
|
|
352 | |
|
|
353 | if ($status < 0) { |
|
|
354 | $nreq--; |
|
|
355 | push @nondirs, $entry; |
|
|
356 | &$schedcb; |
|
|
357 | } else { |
|
|
358 | # need to check for real directory |
|
|
359 | aio_lstat "$path/$entry", sub { |
|
|
360 | $nreq--; |
|
|
361 | |
|
|
362 | if (-d _) { |
|
|
363 | push @dirs, $entry; |
|
|
364 | |
|
|
365 | if (!--$ndirs) { |
|
|
366 | push @nondirs, @$entries; |
|
|
367 | $entries = []; |
|
|
368 | } |
|
|
369 | } else { |
|
|
370 | push @nondirs, $entry; |
|
|
371 | } |
|
|
372 | |
|
|
373 | &$schedcb; |
|
|
374 | } |
|
|
375 | } |
|
|
376 | }; |
|
|
377 | |
|
|
378 | &$schedcb while @$entries && $nreq < $maxreq; |
|
|
379 | }; |
|
|
380 | }; |
|
|
381 | }; |
|
|
382 | } |
|
|
383 | |
209 | =item aio_fsync $fh, $callback |
384 | =item aio_fsync $fh, $callback->($status) |
210 | |
385 | |
211 | Asynchronously call fsync on the given filehandle and call the callback |
386 | Asynchronously call fsync on the given filehandle and call the callback |
212 | with the fsync result code. |
387 | with the fsync result code. |
213 | |
388 | |
214 | =item aio_fdatasync $fh, $callback |
389 | =item aio_fdatasync $fh, $callback->($status) |
215 | |
390 | |
216 | Asynchronously call fdatasync on the given filehandle and call the |
391 | Asynchronously call fdatasync on the given filehandle and call the |
217 | callback with the fdatasync result code. |
392 | callback with the fdatasync result code. |
218 | |
393 | |
|
|
394 | If this call isn't available because your OS lacks it or it couldn't be |
|
|
395 | detected, it will be emulated by calling C<fsync> instead. |
|
|
396 | |
|
|
397 | =back |
|
|
398 | |
|
|
399 | =head2 SUPPORT FUNCTIONS |
|
|
400 | |
|
|
401 | =over 4 |
|
|
402 | |
|
|
403 | =item $fileno = IO::AIO::poll_fileno |
|
|
404 | |
|
|
405 | Return the I<request result pipe file descriptor>. This filehandle must be |
|
|
406 | polled for reading by some mechanism outside this module (e.g. Event or |
|
|
407 | select, see below or the SYNOPSIS). If the pipe becomes readable you have |
|
|
408 | to call C<poll_cb> to check the results. |
|
|
409 | |
|
|
410 | See C<poll_cb> for an example. |
|
|
411 | |
|
|
412 | =item IO::AIO::poll_cb |
|
|
413 | |
|
|
414 | Process all outstanding events on the result pipe. You have to call this |
|
|
415 | regularly. Returns the number of events processed. Returns immediately |
|
|
416 | when no events are outstanding. |
|
|
417 | |
|
|
418 | Example: Install an Event watcher that automatically calls |
|
|
419 | IO::AIO::poll_cb with high priority: |
|
|
420 | |
|
|
421 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
422 | poll => 'r', async => 1, |
|
|
423 | cb => \&IO::AIO::poll_cb); |
|
|
424 | |
|
|
425 | =item IO::AIO::poll_wait |
|
|
426 | |
|
|
427 | Wait till the result filehandle becomes ready for reading (simply does a |
|
|
428 | C<select> on the filehandle. This is useful if you want to synchronously wait |
|
|
429 | for some requests to finish). |
|
|
430 | |
|
|
431 | See C<nreqs> for an example. |
|
|
432 | |
|
|
433 | =item IO::AIO::nreqs |
|
|
434 | |
|
|
435 | Returns the number of requests currently outstanding (i.e. for which their |
|
|
436 | callback has not been invoked yet). |
|
|
437 | |
|
|
438 | Example: wait till there are no outstanding requests anymore: |
|
|
439 | |
|
|
440 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
441 | while IO::AIO::nreqs; |
|
|
442 | |
|
|
443 | =item IO::AIO::flush |
|
|
444 | |
|
|
445 | Wait till all outstanding AIO requests have been handled. |
|
|
446 | |
|
|
447 | Strictly equivalent to: |
|
|
448 | |
|
|
449 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
450 | while IO::AIO::nreqs; |
|
|
451 | |
|
|
452 | =item IO::AIO::poll |
|
|
453 | |
|
|
454 | Waits until some requests have been handled. |
|
|
455 | |
|
|
456 | Strictly equivalent to: |
|
|
457 | |
|
|
458 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
459 | if IO::AIO::nreqs; |
|
|
460 | |
|
|
461 | =item IO::AIO::min_parallel $nthreads |
|
|
462 | |
|
|
463 | Set the minimum number of AIO threads to C<$nthreads>. The current default |
|
|
464 | is C<4>, which means four asynchronous operations can be done at one time |
|
|
465 | (the number of outstanding operations, however, is unlimited). |
|
|
466 | |
|
|
467 | IO::AIO starts threads only on demand, when an AIO request is queued and |
|
|
468 | no free thread exists. |
|
|
469 | |
|
|
470 | It is recommended to keep the number of threads low, as some Linux |
|
|
471 | kernel versions will scale negatively with the number of threads (higher |
|
|
472 | parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
|
|
473 | threads should be fine. |
|
|
474 | |
|
|
475 | Under most circumstances you don't need to call this function, as the |
|
|
476 | module selects a default that is suitable for low to moderate load. |
|
|
477 | |
|
|
478 | =item IO::AIO::max_parallel $nthreads |
|
|
479 | |
|
|
480 | Sets the maximum number of AIO threads to C<$nthreads>. If more than the |
|
|
481 | specified number of threads are currently running, this function kills |
|
|
482 | them. This function blocks until the limit is reached. |
|
|
483 | |
|
|
484 | While C<$nthreads> are zero, aio requests get queued but not executed |
|
|
485 | until the number of threads has been increased again. |
|
|
486 | |
|
|
487 | This module automatically runs C<max_parallel 0> at program end, to ensure |
|
|
488 | that all threads are killed and that there are no outstanding requests. |
|
|
489 | |
|
|
490 | Under normal circumstances you don't need to call this function. |
|
|
491 | |
|
|
492 | =item $oldnreqs = IO::AIO::max_outstanding $nreqs |
|
|
493 | |
|
|
494 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
|
|
495 | try to queue up more than this number of requests, the caller will block until |
|
|
496 | some requests have been handled. |
|
|
497 | |
|
|
498 | The default is very large, so normally there is no practical limit. If you |
|
|
499 | queue up many requests in a loop it often improves speed if you set |
|
|
500 | this to a relatively low number, such as C<100>. |
|
|
501 | |
|
|
502 | Under normal circumstances you don't need to call this function. |
|
|
503 | |
|
|
504 | =back |
|
|
505 | |
219 | =cut |
506 | =cut |
|
|
507 | |
|
|
508 | # support function to convert a fd into a perl filehandle |
|
|
509 | sub _fd2fh { |
|
|
510 | return undef if $_[0] < 0; |
|
|
511 | |
|
|
512 | # try to generate nice filehandles |
|
|
513 | my $sym = "IO::AIO::fd#$_[0]"; |
|
|
514 | local *$sym; |
|
|
515 | |
|
|
516 | open *$sym, "+<&=$_[0]" # usually works under any unix |
|
|
517 | or open *$sym, "<&=$_[0]" # cygwin needs this |
|
|
518 | or open *$sym, ">&=$_[0]" # or this |
|
|
519 | or return undef; |
|
|
520 | |
|
|
521 | *$sym |
|
|
522 | } |
220 | |
523 | |
221 | min_parallel 4; |
524 | min_parallel 4; |
222 | |
525 | |
223 | END { |
526 | END { |
224 | max_parallel 0; |
527 | max_parallel 0; |
225 | } |
528 | } |
226 | |
529 | |
227 | 1; |
530 | 1; |
228 | |
531 | |
229 | =back |
532 | =head2 FORK BEHAVIOUR |
230 | |
533 | |
231 | =head1 BUGS |
534 | Before the fork, IO::AIO enters a quiescent state where no requests |
232 | |
535 | can be added in other threads and no results will be processed. After |
233 | - aio_open gives a fd, but all other functions expect a perl filehandle. |
536 | the fork the parent simply leaves the quiescent state and continues |
|
|
537 | request/result processing, while the child clears the request/result |
|
|
538 | queue (so the requests started before the fork will only be handled in |
|
|
539 | the parent). Threats will be started on demand until the limit ste in the |
|
|
540 | parent process has been reached again. |
234 | |
541 | |
235 | =head1 SEE ALSO |
542 | =head1 SEE ALSO |
236 | |
543 | |
237 | L<Coro>, L<Linux::AIO>. |
544 | L<Coro>, L<Linux::AIO>. |
238 | |
545 | |