… | |
… | |
3 | |
3 | |
4 | SYNOPSIS |
4 | SYNOPSIS |
5 | use Linux::AIO; |
5 | use Linux::AIO; |
6 | |
6 | |
7 | DESCRIPTION |
7 | DESCRIPTION |
8 | This module implements asynchronous i/o using the means available to |
8 | This module implements asynchronous I/O using the means available to |
9 | linux - clone. It does not hook into the POSIX aio_* functions because |
9 | Linux - clone. It does not hook into the POSIX aio_* functions because |
10 | linux does not yet support these in the kernel (and even if, it would |
10 | Linux does not yet support these in the kernel (even as of 2.6.12, only |
11 | only allow aio_read and write, not open and stat). |
11 | O_DIRECT files are supported) and even if, it would only allow aio_read |
|
|
12 | and write, not open, stat and so on. |
12 | |
13 | |
13 | Instead, in this module a number of (non-posix) threads are started that |
14 | Instead, in this module a number of (non-posix) threads are started that |
14 | execute your read/writes and signal their completion. You don't need |
15 | execute your read/writes and signal their completion. You don't need |
15 | thread support in your libc or perl, and the threads created by this |
16 | thread support in your libc or perl, and the threads created by this |
16 | module will not be visible to the pthreads library. |
17 | module will not be visible to the pthreads library. |
17 | |
18 | |
18 | NOTICE: the threads created by this module will automatically be killed |
19 | NOTICE: the threads created by this module will automatically be killed |
19 | when the thread calling min_parallel exits. Make sure you only ever call |
20 | when the thread calling min_parallel exits. Make sure you only ever call |
20 | min_parallel from the same thread that loaded this module. |
21 | min_parallel from the same thread that loaded this module. |
21 | |
22 | |
22 | Although the module will work with threads, it is not reentrant, so use |
23 | Although the module will work with in the presence of other threads, it |
23 | appropriate locking yourself. |
24 | is not reentrant, so use appropriate locking yourself. |
|
|
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 | |
|
|
38 | The filenames you pass to these routines *must* be absolute. The reason |
|
|
39 | is that at the time the request is being executed, the current working |
|
|
40 | directory could have changed. Alternatively, you can make sure that you |
|
|
41 | never change the current working directory. |
24 | |
42 | |
25 | Linux::AIO::min_parallel $nthreads |
43 | Linux::AIO::min_parallel $nthreads |
26 | Set the minimum number of AIO threads to $nthreads. The default is |
44 | Set the minimum number of AIO threads to $nthreads. The default is |
27 | 1, which means a single asynchronous operation can be done at one |
45 | 1, which means a single asynchronous operation can be done at one |
28 | time (the number of outstanding operations, however, is unlimited). |
46 | time (the number of outstanding operations, however, is unlimited). |
29 | |
47 | |
30 | It is recommended to keep the number of threads low, as many linux |
48 | It is recommended to keep the number of threads low, as some linux |
31 | kernel versions will scale negatively with the number of threads |
49 | kernel versions will scale negatively with the number of threads |
32 | (higher parallelity => MUCH higher latency). |
50 | (higher parallelity => MUCH higher latency). |
|
|
51 | |
|
|
52 | Under normal circumstances you don't need to call this function, as |
|
|
53 | this module automatically starts a single async thread. |
|
|
54 | |
|
|
55 | Linux::AIO::max_parallel $nthreads |
|
|
56 | Sets the maximum number of AIO threads to $nthreads. If more than |
|
|
57 | the specified number of threads are currently running, kill them. |
|
|
58 | This function blocks until the limit is reached. |
|
|
59 | |
|
|
60 | This module automatically runs "max_parallel 0" at program end, to |
|
|
61 | ensure that all threads are killed and that there are no outstanding |
|
|
62 | requests. |
|
|
63 | |
|
|
64 | Under normal circumstances you don't need to call this function. |
33 | |
65 | |
34 | $fileno = Linux::AIO::poll_fileno |
66 | $fileno = Linux::AIO::poll_fileno |
35 | Return the *request result pipe filehandle*. This filehandle must be |
67 | Return the *request result pipe filehandle*. This filehandle must be |
36 | polled for reading by some mechanism outside this module (e.g. Event |
68 | polled for reading by some mechanism outside this module (e.g. Event |
37 | or select, see below). If the pipe becomes readable you have to call |
69 | or select, see below). If the pipe becomes readable you have to call |
38 | "poll_cb" to check the results. |
70 | "poll_cb" to check the results. |
39 | |
71 | |
|
|
72 | See "poll_cb" for an example. |
|
|
73 | |
40 | Linux::AIO::poll_cb |
74 | Linux::AIO::poll_cb |
41 | Process all outstanding events on the result pipe. You have to call |
75 | Process all outstanding events on the result pipe. You have to call |
42 | this regularly. Returns the number of events processed. Returns |
76 | this regularly. Returns the number of events processed. Returns |
43 | immediately when no events are outstanding. |
77 | immediately when no events are outstanding. |
44 | |
78 | |
45 | You can use Event to multiplex, e.g.: |
79 | You can use Event to multiplex, e.g.: |
46 | |
80 | |
47 | Event->io (fd => Linux::AIO::poll_fileno, |
81 | Event->io (fd => Linux::AIO::poll_fileno, |
48 | poll => 'r', async => 1, |
82 | poll => 'r', async => 1, |
49 | cb => \&Linux::AIO::poll_cb ); |
83 | cb => \&Linux::AIO::poll_cb); |
|
|
84 | |
|
|
85 | Linux::AIO::poll_wait |
|
|
86 | Wait till the result filehandle becomes ready for reading (simply |
|
|
87 | does a select on the filehandle. This is useful if you want to |
|
|
88 | synchronously wait for some requests to finish). |
|
|
89 | |
|
|
90 | See "nreqs" for an example. |
50 | |
91 | |
51 | Linux::AIO::nreqs |
92 | Linux::AIO::nreqs |
52 | Returns the number of requests currently outstanding. |
93 | Returns the number of requests currently outstanding. |
|
|
94 | |
|
|
95 | Example: wait till there are no outstanding requests anymore: |
|
|
96 | |
|
|
97 | Linux::AIO::poll_wait, Linux::AIO::poll_cb |
|
|
98 | while Linux::AIO::nreqs; |
53 | |
99 | |
54 | aio_open $pathname, $flags, $mode, $callback |
100 | aio_open $pathname, $flags, $mode, $callback |
55 | Asynchronously open or create a file and call the callback with the |
101 | Asynchronously open or create a file and call the callback with the |
56 | filedescriptor (NOT a perl filehandle, sorry for that, but watch |
102 | filedescriptor (NOT a perl filehandle, sorry for that, but watch |
57 | out, this might change in the future). |
103 | out, this might change in the future). |
58 | |
104 | |
|
|
105 | The pathname passed to "aio_open" must be absolute. See API NOTES, |
|
|
106 | above, for an explanation. |
|
|
107 | |
|
|
108 | The $mode argument is a bitmask. See the "Fcntl" module for a list. |
|
|
109 | They are the same as used in "sysopen". |
|
|
110 | |
|
|
111 | Example: |
|
|
112 | |
|
|
113 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
|
|
114 | if ($_[0] >= 0) { |
|
|
115 | open my $fh, "<&=$_[0]"; |
|
|
116 | print "open successful, fh is $fh\n"; |
|
|
117 | ... |
|
|
118 | } else { |
|
|
119 | die "open failed: $!\n"; |
|
|
120 | } |
|
|
121 | }; |
|
|
122 | |
59 | aio_close $fh, $callback |
123 | aio_close $fh, $callback |
60 | Asynchronously close a file and call the callback with the result |
124 | Asynchronously close a file and call the callback with the result |
61 | code. |
125 | code. |
62 | |
126 | |
63 | aio_read $fh,$offset,$length, $data,$dataoffset,$callback |
127 | aio_read $fh,$offset,$length, $data,$dataoffset,$callback |
64 | aio_write $fh,$offset,$length, $data,$dataoffset,$callback |
128 | aio_write $fh,$offset,$length, $data,$dataoffset,$callback |
65 | Reads or writes "length" bytes from the specified "fh" and "offset" |
129 | Reads or writes "length" bytes from the specified "fh" and "offset" |
66 | into the scalar given by "data" and offset "dataoffset" and calls |
130 | into the scalar given by "data" and offset "dataoffset" and calls |
67 | the callback without the actual number of bytes read (or "undef" on |
131 | the callback without the actual number of bytes read (or -1 on |
68 | error). |
132 | error, just like the syscall). |
|
|
133 | |
|
|
134 | Example: Read 15 bytes at offset 7 into scalar $buffer, strating at |
|
|
135 | offset 0 within the scalar: |
|
|
136 | |
|
|
137 | aio_read $fh, 7, 15, $buffer, 0, sub { |
|
|
138 | $_[0] >= 0 or die "read error: $!"; |
|
|
139 | print "read <$buffer>\n"; |
|
|
140 | }; |
|
|
141 | |
|
|
142 | aio_readahead $fh,$offset,$length, $callback |
|
|
143 | Asynchronously reads the specified byte range into the page cache, |
|
|
144 | using the "readahead" syscall. |
|
|
145 | |
|
|
146 | readahead() populates the page cache with data from a file so that |
|
|
147 | subsequent reads from that file will not block on disk I/O. The |
|
|
148 | $offset argument specifies the starting point from which data is to |
|
|
149 | be read and $length specifies the number of bytes to be read. I/O is |
|
|
150 | performed in whole pages, so that offset is effectively rounded down |
|
|
151 | to a page boundary and bytes are read up to the next page boundary |
|
|
152 | greater than or equal to (off-set+length). aio_readahead() does not |
|
|
153 | read beyond the end of the file. The current file offset of the file |
|
|
154 | is left unchanged. |
69 | |
155 | |
70 | aio_stat $fh_or_path, $callback |
156 | aio_stat $fh_or_path, $callback |
71 | aio_lstat $fh, $callback |
157 | aio_lstat $fh, $callback |
72 | Works like perl's "stat" or "lstat" in void context. The callback |
158 | Works like perl's "stat" or "lstat" in void context. The callback |
73 | will be called after the stat and the results will be available |
159 | will be called after the stat and the results will be available |
74 | using "stat _" or "-s _" etc... |
160 | using "stat _" or "-s _" etc... |
75 | |
161 | |
|
|
162 | The pathname passed to "aio_stat" must be absolute. See API NOTES, |
|
|
163 | above, for an explanation. |
|
|
164 | |
76 | Currently, the stats are always 64-bit-stats, i.e. instead of |
165 | Currently, the stats are always 64-bit-stats, i.e. instead of |
77 | returning an error when stat'ing a large file, the results will be |
166 | returning an error when stat'ing a large file, the results will be |
78 | silently truncated unless perl itself is compiled with large file |
167 | silently truncated unless perl itself is compiled with large file |
79 | support. |
168 | support. |
80 | |
169 | |
|
|
170 | Example: Print the length of /etc/passwd: |
|
|
171 | |
|
|
172 | aio_stat "/etc/passwd", sub { |
|
|
173 | $_[0] and die "stat failed: $!"; |
|
|
174 | print "size is ", -s _, "\n"; |
|
|
175 | }; |
|
|
176 | |
81 | aio_unlink $pathname, $callback |
177 | aio_unlink $pathname, $callback |
82 | Asynchronously unlink a file. |
178 | Asynchronously unlink (delete) a file and call the callback with the |
|
|
179 | result code. |
|
|
180 | |
|
|
181 | aio_fsync $fh, $callback |
|
|
182 | Asynchronously call fsync on the given filehandle and call the |
|
|
183 | callback with the fsync result code. |
|
|
184 | |
|
|
185 | aio_fdatasync $fh, $callback |
|
|
186 | Asynchronously call fdatasync on the given filehandle and call the |
|
|
187 | callback with the fdatasync result code. |
83 | |
188 | |
84 | BUGS |
189 | BUGS |
85 | This module has been extensively tested in a large and very busy |
190 | This module has been extensively tested in a large and very busy |
86 | webserver for many years now. |
191 | webserver for many years now. |
87 | |
192 | |
88 | - aio_open gives a fd, but all other functions expect a perl filehandle. |
193 | - aio_open gives a fd, but all other functions expect a perl filehandle. |
89 | |
194 | |
90 | SEE ALSO |
195 | SEE ALSO |
91 | Coro. |
196 | Coro, IO::AIO. |
92 | |
197 | |
93 | AUTHOR |
198 | AUTHOR |
94 | Marc Lehmann <schmorp@schmorp.de> |
199 | Marc Lehmann <schmorp@schmorp.de> |
95 | http://home.schmorp.de/ |
200 | http://home.schmorp.de/ |
96 | |
201 | |