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

Comparing Linux-AIO/README (file contents):
Revision 1.3 by root, Sat Jul 9 04:11:30 2005 UTC vs.
Revision 1.4 by root, Sun Jul 10 01:02:51 2005 UTC

… …
21 min_parallel from the same thread that loaded this module. 21 min_parallel from the same thread that loaded this module.
22 22
23 Although the module will work with in the presence of other threads, it 23 Although the module will work with in the presence of other threads, it
24 is not reentrant, so use appropriate locking yourself. 24 is not reentrant, so use appropriate locking yourself.
25 25
26 API NOTES
27 All the "aio_*" calls are more or less thin wrappers around the syscall
28 with the same name (sans "aio_"). The arguments are similar or
29 identical, and they all accept an additional $callback argument which
30 must be a code reference. This code reference will get called with the
31 syscall return code (e.g. most syscalls return -1 on error, unlike perl,
32 which usually delivers "false") as it's sole argument when the given
33 syscall has been executed asynchronously.
34
35 All functions that expect a filehandle will also accept a file
36 descriptor.
37
26 Linux::AIO::min_parallel $nthreads 38 Linux::AIO::min_parallel $nthreads
27 Set the minimum number of AIO threads to $nthreads. The default is 39 Set the minimum number of AIO threads to $nthreads. The default is
28 1, which means a single asynchronous operation can be done at one 40 1, which means a single asynchronous operation can be done at one
29 time (the number of outstanding operations, however, is unlimited). 41 time (the number of outstanding operations, however, is unlimited).
30 42
31 It is recommended to keep the number of threads low, as some linux 43 It is recommended to keep the number of threads low, as some linux
32 kernel versions will scale negatively with the number of threads 44 kernel versions will scale negatively with the number of threads
33 (higher parallelity => MUCH higher latency). 45 (higher parallelity => MUCH higher latency).
46
47 Under normal circumstances you don't need to call this function, as
48 this module automatically starts a single async thread.
34 49
35 Linux::AIO::max_parallel $nthreads 50 Linux::AIO::max_parallel $nthreads
36 Sets the maximum number of AIO threads to $nthreads. If more than 51 Sets the maximum number of AIO threads to $nthreads. If more than
37 the specified number of threads are currently running, kill them. 52 the specified number of threads are currently running, kill them.
38 This function blocks until the limit is reached. 53 This function blocks until the limit is reached.
39 54
40 This module automatically runs "max_parallel 0" at program end, to 55 This module automatically runs "max_parallel 0" at program end, to
41 ensure that all threads are killed and that there are no outstanding 56 ensure that all threads are killed and that there are no outstanding
42 requests. 57 requests.
43 58
59 Under normal circumstances you don't need to call this function.
60
44 $fileno = Linux::AIO::poll_fileno 61 $fileno = Linux::AIO::poll_fileno
45 Return the *request result pipe filehandle*. This filehandle must be 62 Return the *request result pipe filehandle*. This filehandle must be
46 polled for reading by some mechanism outside this module (e.g. Event 63 polled for reading by some mechanism outside this module (e.g. Event
47 or select, see below). If the pipe becomes readable you have to call 64 or select, see below). If the pipe becomes readable you have to call
48 "poll_cb" to check the results. 65 "poll_cb" to check the results.
66
67 See "poll_cb" for an example.
49 68
50 Linux::AIO::poll_cb 69 Linux::AIO::poll_cb
51 Process all outstanding events on the result pipe. You have to call 70 Process all outstanding events on the result pipe. You have to call
52 this regularly. Returns the number of events processed. Returns 71 this regularly. Returns the number of events processed. Returns
53 immediately when no events are outstanding. 72 immediately when no events are outstanding.
54 73
55 You can use Event to multiplex, e.g.: 74 You can use Event to multiplex, e.g.:
56 75
57 Event->io (fd => Linux::AIO::poll_fileno, 76 Event->io (fd => Linux::AIO::poll_fileno,
58 poll => 'r', async => 1, 77 poll => 'r', async => 1,
59 cb => \&Linux::AIO::poll_cb ); 78 cb => \&Linux::AIO::poll_cb);
60 79
61 Linux::AIO::poll_wait 80 Linux::AIO::poll_wait
62 Wait till the result filehandle becomes ready for reading (simply 81 Wait till the result filehandle becomes ready for reading (simply
63 does a select on the filehandle. This is useful if you want to 82 does a select on the filehandle. This is useful if you want to
64 synchronously wait for some requests to finish). 83 synchronously wait for some requests to finish).
65 84
85 See "nreqs" for an example.
86
66 Linux::AIO::nreqs 87 Linux::AIO::nreqs
67 Returns the number of requests currently outstanding. 88 Returns the number of requests currently outstanding.
89
90 Example: wait till there are no outstanding requests anymore:
91
92 Linux::AIO::poll_wait while Linux::AIO::nreqs;
68 93
69 aio_open $pathname, $flags, $mode, $callback 94 aio_open $pathname, $flags, $mode, $callback
70 Asynchronously open or create a file and call the callback with the 95 Asynchronously open or create a file and call the callback with the
71 filedescriptor (NOT a perl filehandle, sorry for that, but watch 96 filedescriptor (NOT a perl filehandle, sorry for that, but watch
72 out, this might change in the future). 97 out, this might change in the future).
98
99 The $mode argument is a bitmask. See the "Fcntl" module for a list.
100 They are the same as used in "sysopen".
101
102 Example:
103
104 aio_open "/etc/passwd", O_RDONLY, 0, sub {
105 if ($_[0] >= 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";
109 ...
110 } else {
111 die "open failed: $!\n";
112 }
113 };
73 114
74 aio_close $fh, $callback 115 aio_close $fh, $callback
75 Asynchronously close a file and call the callback with the result 116 Asynchronously close a file and call the callback with the result
76 code. 117 code.
77 118
78 aio_read $fh,$offset,$length, $data,$dataoffset,$callback 119 aio_read $fh,$offset,$length, $data,$dataoffset,$callback
79 aio_write $fh,$offset,$length, $data,$dataoffset,$callback 120 aio_write $fh,$offset,$length, $data,$dataoffset,$callback
80 Reads or writes "length" bytes from the specified "fh" and "offset" 121 Reads or writes "length" bytes from the specified "fh" and "offset"
81 into the scalar given by "data" and offset "dataoffset" and calls 122 into the scalar given by "data" and offset "dataoffset" and calls
82 the callback without the actual number of bytes read (or "undef" on 123 the callback without the actual number of bytes read (or -1 on
83 error). 124 error, just like the syscall).
125
126 Example: Read 15 bytes at offset 7 into scalar $buffer, strating at
127 offset 0 within the scalar:
128
129 aio_read $fh, 7, 15, $buffer, 0, sub {
130 $_[0] >= 0 or die "read error: $!";
131 print "read <$buffer>\n";
132 };
133
134 aio_readahead $fh,$offset,$length, $callback
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
139 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
141 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
143 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
145 read beyond the end of the file. The current file offset of the file
146 is left unchanged.
84 147
85 aio_stat $fh_or_path, $callback 148 aio_stat $fh_or_path, $callback
86 aio_lstat $fh, $callback 149 aio_lstat $fh, $callback
87 Works like perl's "stat" or "lstat" in void context. The callback 150 Works like perl's "stat" or "lstat" in void context. The callback
88 will be called after the stat and the results will be available 151 will be called after the stat and the results will be available
… …
91 Currently, the stats are always 64-bit-stats, i.e. instead of 154 Currently, the stats are always 64-bit-stats, i.e. instead of
92 returning an error when stat'ing a large file, the results will be 155 returning an error when stat'ing a large file, the results will be
93 silently truncated unless perl itself is compiled with large file 156 silently truncated unless perl itself is compiled with large file
94 support. 157 support.
95 158
159 Example: Print the length of /etc/passwd:
160
161 aio_stat "/etc/passwd", sub {
162 $_[0] and die "stat failed: $!";
163 print "size is ", -s _, "\n";
164 };
165
96 aio_unlink $pathname, $callback 166 aio_unlink $pathname, $callback
97 Asynchronously unlink a file. 167 Asynchronously unlink (delete) a file and call the callback with the
168 result code.
169
170 aio_fsync $fh, $callback
171 Asynchronously call fsync on the given filehandle and call the
172 callback with the fsync result code.
173
174 aio_fdatasync $fh, $callback
175 Asynchronously call fdatasync on the given filehandle and call the
176 callback with the fdatasync result code.
98 177
99BUGS 178BUGS
100 This module has been extensively tested in a large and very busy 179 This module has been extensively tested in a large and very busy
101 webserver for many years now. 180 webserver for many years now.
102 181

Diff Legend

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