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 1.4 by root, Sun Jul 10 21:04:46 2005 UTC

… …
4SYNOPSIS 4SYNOPSIS
5 use IO::AIO; 5 use IO::AIO;
6 6
7DESCRIPTION 7DESCRIPTION
8 This module implements asynchronous I/O using whatever means your 8 This module implements asynchronous I/O using whatever means your
9 operating system supports. Currently, it falls back to Linux::AIO if 9 operating system supports.
10 that module is available, or uses pthreads to emulato aio functionality.
11 10
12 Currently, in this module a number of threads are started that execute 11 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 12 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 13 or perl, and the threads created by this module will not be visible to
15 will not be visible to the pthreads library. 14 the pthreads library. In the future, this module might make use of the
15 native aio functions available on many operating systems. However, they
16 are often not well-supported (Linux doesn't allow them on normal files
17 currently, for example), and they would only support aio_read and
18 aio_write, so the remaining functionality would have to be implemented
19 using threads anyway.
16 20
17 Although the module will work with in the presence of other threads, it 21 Although the module will work with in the presence of other threads, it
18 is not reentrant, so use appropriate locking yourself. 22 is currently not reentrant, so use appropriate locking yourself.
19 23
20 API NOTES 24FUNCTIONS
25 AIO FUNCTIONS
21 All the "aio_*" calls are more or less thin wrappers around the syscall 26 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 27 with the same name (sans "aio_"). The arguments are similar or
23 identical, and they all accept an additional $callback argument which 28 identical, and they all accept an additional $callback argument which
24 must be a code reference. This code reference will get called with the 29 must be a code reference. This code reference will get called with the
25 syscall return code (e.g. most syscalls return -1 on error, unlike perl, 30 syscall return code (e.g. most syscalls return -1 on error, unlike perl,
… …
32 The filenames you pass to these routines *must* be absolute. The reason 37 The filenames you pass to these routines *must* be absolute. The reason
33 is that at the time the request is being executed, the current working 38 is that at the time the request is being executed, the current working
34 directory could have changed. Alternatively, you can make sure that you 39 directory could have changed. Alternatively, you can make sure that you
35 never change the current working directory. 40 never change the current working directory.
36 41
37 IO::AIO::min_parallel $nthreads
38 Set the minimum number of AIO threads to $nthreads. The default is
39 1, which means a single asynchronous operation can be done at one
40 time (the number of outstanding operations, however, is unlimited).
41
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 42 aio_open $pathname, $flags, $mode, $callback
95 Asynchronously open or create a file and call the callback with the 43 Asynchronously open or create a file and call the callback with a
96 filedescriptor (NOT a perl filehandle, sorry for that, but watch 44 newly created filehandle for the file.
97 out, this might change in the future). 45
46 The pathname passed to "aio_open" must be absolute. See API NOTES,
47 above, for an explanation.
98 48
99 The $mode argument is a bitmask. See the "Fcntl" module for a list. 49 The $mode argument is a bitmask. See the "Fcntl" module for a list.
100 They are the same as used in "sysopen". 50 They are the same as used in "sysopen".
101 51
102 Example: 52 Example:
103 53
104 aio_open "/etc/passwd", O_RDONLY, 0, sub { 54 aio_open "/etc/passwd", O_RDONLY, 0, sub {
105 if ($_[0] >= 0) { 55 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"; 56 print "open successful, fh is $_[0]\n";
109 ... 57 ...
110 } else { 58 } else {
111 die "open failed: $!\n"; 59 die "open failed: $!\n";
112 } 60 }
113 }; 61 };
114 62
115 aio_close $fh, $callback 63 aio_close $fh, $callback
116 Asynchronously close a file and call the callback with the result 64 Asynchronously close a file and call the callback with the result
117 code. 65 code. *WARNING:* although accepted, you should not pass in a perl
66 filehandle here, as perl will likely close the file descriptor
67 itself when the filehandle is destroyed. Normally, you can safely
68 call perls "close" or just let filehandles go out of scope.
118 69
119 aio_read $fh,$offset,$length, $data,$dataoffset,$callback 70 aio_read $fh,$offset,$length, $data,$dataoffset,$callback
120 aio_write $fh,$offset,$length, $data,$dataoffset,$callback 71 aio_write $fh,$offset,$length, $data,$dataoffset,$callback
121 Reads or writes "length" bytes from the specified "fh" and "offset" 72 Reads or writes "length" bytes from the specified "fh" and "offset"
122 into the scalar given by "data" and offset "dataoffset" and calls 73 into the scalar given by "data" and offset "dataoffset" and calls
… …
131 print "read <$buffer>\n"; 82 print "read <$buffer>\n";
132 }; 83 };
133 84
134 aio_readahead $fh,$offset,$length, $callback 85 aio_readahead $fh,$offset,$length, $callback
135 Asynchronously reads the specified byte range into the page cache, 86 Asynchronously reads the specified byte range into the page cache,
136 using the "readahead" syscall. 87 using the "readahead" syscall. If that syscall doesn't exist the
88 status will be -1 and $! is set to ENOSYS.
137 89
138 readahead() populates the page cache with data from a file so that 90 readahead() populates the page cache with data from a file so that
139 subsequent reads from that file will not block on disk I/O. The 91 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 92 $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 93 be read and $length specifies the number of bytes to be read. I/O is
… …
176 128
177 aio_fdatasync $fh, $callback 129 aio_fdatasync $fh, $callback
178 Asynchronously call fdatasync on the given filehandle and call the 130 Asynchronously call fdatasync on the given filehandle and call the
179 callback with the fdatasync result code. 131 callback with the fdatasync result code.
180 132
181BUGS 133 SUPPORT FUNCTIONS
182 This module has been extensively tested in a large and very busy 134 $fileno = IO::AIO::poll_fileno
183 webserver for many years now. 135 Return the *request result pipe filehandle*. This filehandle must be
136 polled for reading by some mechanism outside this module (e.g. Event
137 or select, see below). If the pipe becomes readable you have to call
138 "poll_cb" to check the results.
184 139
185 - aio_open gives a fd, but all other functions expect a perl filehandle. 140 See "poll_cb" for an example.
141
142 IO::AIO::poll_cb
143 Process all outstanding events on the result pipe. You have to call
144 this regularly. Returns the number of events processed. Returns
145 immediately when no events are outstanding.
146
147 You can use Event to multiplex, e.g.:
148
149 Event->io (fd => IO::AIO::poll_fileno,
150 poll => 'r', async => 1,
151 cb => \&IO::AIO::poll_cb);
152
153 IO::AIO::poll_wait
154 Wait till the result filehandle becomes ready for reading (simply
155 does a select on the filehandle. This is useful if you want to
156 synchronously wait for some requests to finish).
157
158 See "nreqs" for an example.
159
160 IO::AIO::nreqs
161 Returns the number of requests currently outstanding.
162
163 Example: wait till there are no outstanding requests anymore:
164
165 IO::AIO::poll_wait, IO::AIO::poll_cb
166 while IO::AIO::nreqs;
167
168 IO::AIO::min_parallel $nthreads
169 Set the minimum number of AIO threads to $nthreads. The default is
170 1, which means a single asynchronous operation can be done at one
171 time (the number of outstanding operations, however, is unlimited).
172
173 It is recommended to keep the number of threads low, as some Linux
174 kernel versions will scale negatively with the number of threads
175 (higher parallelity => MUCH higher latency). With current Linux 2.6
176 versions, 4-32 threads should be fine.
177
178 Under normal circumstances you don't need to call this function, as
179 this module automatically starts some threads (the exact number
180 might change, and is currently 4).
181
182 IO::AIO::max_parallel $nthreads
183 Sets the maximum number of AIO threads to $nthreads. If more than
184 the specified number of threads are currently running, kill them.
185 This function blocks until the limit is reached.
186
187 This module automatically runs "max_parallel 0" at program end, to
188 ensure that all threads are killed and that there are no outstanding
189 requests.
190
191 Under normal circumstances you don't need to call this function.
192
193 $oldnreqs = IO::AIO::max_outstanding $nreqs
194 Sets the maximum number of outstanding requests to $nreqs. If you
195 try to queue up more than this number of requests, the caller will
196 block until some requests have been handled.
197
198 The default is very large, so normally there is no practical limit.
199 If you queue up many requests in a loop it it often improves speed
200 if you set this to a relatively low number, such as 100.
201
202 Under normal circumstances you don't need to call this function.
186 203
187SEE ALSO 204SEE ALSO
188 Coro. 205 Coro, Linux::AIO.
189 206
190AUTHOR 207AUTHOR
191 Marc Lehmann <schmorp@schmorp.de> 208 Marc Lehmann <schmorp@schmorp.de>
192 http://home.schmorp.de/ 209 http://home.schmorp.de/
193 210

Diff Legend

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