1 |
=head1 NAME |
2 |
|
3 |
libeio - truly asynchronous POSIX I/O |
4 |
|
5 |
=head1 SYNOPSIS |
6 |
|
7 |
#include <eio.h> |
8 |
|
9 |
=head1 DESCRIPTION |
10 |
|
11 |
The newest version of this document is also available as an html-formatted |
12 |
web page you might find easier to navigate when reading it for the first |
13 |
time: L<http://pod.tst.eu/http://cvs.schmorp.de/libeio/eio.pod>. |
14 |
|
15 |
Note that this library is a by-product of the C<IO::AIO> perl |
16 |
module, and many of the subtler points regarding requests lifetime |
17 |
and so on are only documented in its documentation at the |
18 |
moment: L<http://pod.tst.eu/http://cvs.schmorp.de/IO-AIO/AIO.pm>. |
19 |
|
20 |
=head2 FEATURES |
21 |
|
22 |
This library provides fully asynchronous versions of most POSIX functions |
23 |
dealing with I/O. Unlike most asynchronous libraries, this not only |
24 |
includes C<read> and C<write>, but also C<open>, C<stat>, C<unlink> and |
25 |
similar functions, as well as less rarely ones such as C<mknod>, C<futime> |
26 |
or C<readlink>. |
27 |
|
28 |
It also offers wrappers around C<sendfile> (Solaris, Linux, HP-UX and |
29 |
FreeBSD, with emulation on other platforms) and C<readahead> (Linux, with |
30 |
emulation elsewhere>). |
31 |
|
32 |
The goal is to enable you to write fully non-blocking programs. For |
33 |
example, in a game server, you would not want to freeze for a few seconds |
34 |
just because the server is running a backup and you happen to call |
35 |
C<readdir>. |
36 |
|
37 |
=head2 TIME REPRESENTATION |
38 |
|
39 |
Libeio represents time as a single floating point number, representing the |
40 |
(fractional) number of seconds since the (POSIX) epoch (somewhere near |
41 |
the beginning of 1970, details are complicated, don't ask). This type is |
42 |
called C<eio_tstamp>, but it is guaranteed to be of type C<double> (or |
43 |
better), so you can freely use C<double> yourself. |
44 |
|
45 |
Unlike the name component C<stamp> might indicate, it is also used for |
46 |
time differences throughout libeio. |
47 |
|
48 |
=head2 FORK SUPPORT |
49 |
|
50 |
Usage of pthreads in a program changes the semantics of fork |
51 |
considerably. Specifically, only async-safe functions can be called after |
52 |
fork. Libeio uses pthreads, so this applies, and makes using fork hard for |
53 |
anything but relatively fork + exec uses. |
54 |
|
55 |
This library only works in the process that initialised it: Forking is |
56 |
fully supported, but using libeio in any other process than the one that |
57 |
called C<eio_init> is not. |
58 |
|
59 |
You might get around by not I<using> libeio before (or after) forking in |
60 |
the parent, and using it in the child afterwards. You could also try to |
61 |
call the L<eio_init> function again in the child, which will brutally |
62 |
reinitialise all data structures, which isn't POSIX conformant, but |
63 |
typically works. |
64 |
|
65 |
Otherwise, the only recommendation you should follow is: treat fork code |
66 |
the same way you treat signal handlers, and only ever call C<eio_init> in |
67 |
the process that uses it, and only once ever. |
68 |
|
69 |
=head1 INITIALISATION/INTEGRATION |
70 |
|
71 |
Before you can call any eio functions you first have to initialise the |
72 |
library. The library integrates into any event loop, but can also be used |
73 |
without one, including in polling mode. |
74 |
|
75 |
You have to provide the necessary glue yourself, however. |
76 |
|
77 |
=over 4 |
78 |
|
79 |
=item int eio_init (void (*want_poll)(void), void (*done_poll)(void)) |
80 |
|
81 |
This function initialises the library. On success it returns C<0>, on |
82 |
failure it returns C<-1> and sets C<errno> appropriately. |
83 |
|
84 |
It accepts two function pointers specifying callbacks as argument, both of |
85 |
which can be C<0>, in which case the callback isn't called. |
86 |
|
87 |
There is currently no way to change these callbacks later, or to |
88 |
"uninitialise" the library again. |
89 |
|
90 |
=item want_poll callback |
91 |
|
92 |
The C<want_poll> callback is invoked whenever libeio wants attention (i.e. |
93 |
it wants to be polled by calling C<eio_poll>). It is "edge-triggered", |
94 |
that is, it will only be called once when eio wants attention, until all |
95 |
pending requests have been handled. |
96 |
|
97 |
This callback is called while locks are being held, so I<you must |
98 |
not call any libeio functions inside this callback>. That includes |
99 |
C<eio_poll>. What you should do is notify some other thread, or wake up |
100 |
your event loop, and then call C<eio_poll>. |
101 |
|
102 |
=item done_poll callback |
103 |
|
104 |
This callback is invoked when libeio detects that all pending requests |
105 |
have been handled. It is "edge-triggered", that is, it will only be |
106 |
called once after C<want_poll>. To put it differently, C<want_poll> and |
107 |
C<done_poll> are invoked in pairs: after C<want_poll> you have to call |
108 |
C<eio_poll ()> until either C<eio_poll> indicates that everything has been |
109 |
handled or C<done_poll> has been called, which signals the same. |
110 |
|
111 |
Note that C<eio_poll> might return after C<done_poll> and C<want_poll> |
112 |
have been called again, so watch out for races in your code. |
113 |
|
114 |
As with C<want_poll>, this callback is called while locks are being held, |
115 |
so you I<must not call any libeio functions form within this callback>. |
116 |
|
117 |
=item int eio_poll () |
118 |
|
119 |
This function has to be called whenever there are pending requests that |
120 |
need finishing. You usually call this after C<want_poll> has indicated |
121 |
that you should do so, but you can also call this function regularly to |
122 |
poll for new results. |
123 |
|
124 |
If any request invocation returns a non-zero value, then C<eio_poll ()> |
125 |
immediately returns with that value as return value. |
126 |
|
127 |
Otherwise, if all requests could be handled, it returns C<0>. If for some |
128 |
reason not all requests have been handled, i.e. some are still pending, it |
129 |
returns C<-1>. |
130 |
|
131 |
=back |
132 |
|
133 |
For libev, you would typically use an C<ev_async> watcher: the |
134 |
C<want_poll> callback would invoke C<ev_async_send> to wake up the event |
135 |
loop. Inside the callback set for the watcher, one would call C<eio_poll |
136 |
()>. |
137 |
|
138 |
If C<eio_poll ()> is configured to not handle all results in one go |
139 |
(i.e. it returns C<-1>) then you should start an idle watcher that calls |
140 |
C<eio_poll> until it returns something C<!= -1>. |
141 |
|
142 |
A full-featured connector between libeio and libev would look as follows |
143 |
(if C<eio_poll> is handling all requests, it can of course be simplified a |
144 |
lot by removing the idle watcher logic): |
145 |
|
146 |
static struct ev_loop *loop; |
147 |
static ev_idle repeat_watcher; |
148 |
static ev_async ready_watcher; |
149 |
|
150 |
/* idle watcher callback, only used when eio_poll */ |
151 |
/* didn't handle all results in one call */ |
152 |
static void |
153 |
repeat (EV_P_ ev_idle *w, int revents) |
154 |
{ |
155 |
if (eio_poll () != -1) |
156 |
ev_idle_stop (EV_A_ w); |
157 |
} |
158 |
|
159 |
/* eio has some results, process them */ |
160 |
static void |
161 |
ready (EV_P_ ev_async *w, int revents) |
162 |
{ |
163 |
if (eio_poll () == -1) |
164 |
ev_idle_start (EV_A_ &repeat_watcher); |
165 |
} |
166 |
|
167 |
/* wake up the event loop */ |
168 |
static void |
169 |
want_poll (void) |
170 |
{ |
171 |
ev_async_send (loop, &ready_watcher) |
172 |
} |
173 |
|
174 |
void |
175 |
my_init_eio () |
176 |
{ |
177 |
loop = EV_DEFAULT; |
178 |
|
179 |
ev_idle_init (&repeat_watcher, repeat); |
180 |
ev_async_init (&ready_watcher, ready); |
181 |
ev_async_start (loop &watcher); |
182 |
|
183 |
eio_init (want_poll, 0); |
184 |
} |
185 |
|
186 |
For most other event loops, you would typically use a pipe - the event |
187 |
loop should be told to wait for read readiness on the read end. In |
188 |
C<want_poll> you would write a single byte, in C<done_poll> you would try |
189 |
to read that byte, and in the callback for the read end, you would call |
190 |
C<eio_poll>. |
191 |
|
192 |
You don't have to take special care in the case C<eio_poll> doesn't handle |
193 |
all requests, as the done callback will not be invoked, so the event loop |
194 |
will still signal readiness for the pipe until I<all> results have been |
195 |
processed. |
196 |
|
197 |
|
198 |
=head1 HIGH LEVEL REQUEST API |
199 |
|
200 |
Libeio has both a high-level API, which consists of calling a request |
201 |
function with a callback to be called on completion, and a low-level API |
202 |
where you fill out request structures and submit them. |
203 |
|
204 |
This section describes the high-level API. |
205 |
|
206 |
=head2 REQUEST SUBMISSION AND RESULT PROCESSING |
207 |
|
208 |
You submit a request by calling the relevant C<eio_TYPE> function with the |
209 |
required parameters, a callback of type C<int (*eio_cb)(eio_req *req)> |
210 |
(called C<eio_cb> below) and a freely usable C<void *data> argument. |
211 |
|
212 |
The return value will either be 0, in case something went really wrong |
213 |
(which can basically only happen on very fatal errors, such as C<malloc> |
214 |
returning 0, which is rather unlikely), or a pointer to the newly-created |
215 |
and submitted C<eio_req *>. |
216 |
|
217 |
The callback will be called with an C<eio_req *> which contains the |
218 |
results of the request. The members you can access inside that structure |
219 |
vary from request to request, except for: |
220 |
|
221 |
=over 4 |
222 |
|
223 |
=item C<ssize_t result> |
224 |
|
225 |
This contains the result value from the call (usually the same as the |
226 |
syscall of the same name). |
227 |
|
228 |
=item C<int errorno> |
229 |
|
230 |
This contains the value of C<errno> after the call. |
231 |
|
232 |
=item C<void *data> |
233 |
|
234 |
The C<void *data> member simply stores the value of the C<data> argument. |
235 |
|
236 |
=back |
237 |
|
238 |
The return value of the callback is normally C<0>, which tells libeio to |
239 |
continue normally. If a callback returns a nonzero value, libeio will |
240 |
stop processing results (in C<eio_poll>) and will return the value to its |
241 |
caller. |
242 |
|
243 |
Memory areas passed to libeio must stay valid as long as a request |
244 |
executes, with the exception of paths, which are being copied |
245 |
internally. Any memory libeio itself allocates will be freed after the |
246 |
finish callback has been called. If you want to manage all memory passed |
247 |
to libeio yourself you can use the low-level API. |
248 |
|
249 |
For example, to open a file, you could do this: |
250 |
|
251 |
static int |
252 |
file_open_done (eio_req *req) |
253 |
{ |
254 |
if (req->result < 0) |
255 |
{ |
256 |
/* open() returned -1 */ |
257 |
errno = req->errorno; |
258 |
perror ("open"); |
259 |
} |
260 |
else |
261 |
{ |
262 |
int fd = req->result; |
263 |
/* now we have the new fd in fd */ |
264 |
} |
265 |
|
266 |
return 0; |
267 |
} |
268 |
|
269 |
/* the first three arguments are passed to open(2) */ |
270 |
/* the remaining are priority, callback and data */ |
271 |
if (!eio_open ("/etc/passwd", O_RDONLY, 0, 0, file_open_done, 0)) |
272 |
abort (); /* something went wrong, we will all die!!! */ |
273 |
|
274 |
Note that you additionally need to call C<eio_poll> when the C<want_cb> |
275 |
indicates that requests are ready to be processed. |
276 |
|
277 |
=head2 CANCELLING REQUESTS |
278 |
|
279 |
Sometimes the need for a request goes away before the request is |
280 |
finished. In that case, one can cancel the request by a call to |
281 |
C<eio_cancel>: |
282 |
|
283 |
=over 4 |
284 |
|
285 |
=item eio_cancel (eio_req *req) |
286 |
|
287 |
Cancel the request (and all its subrequests). If the request is currently |
288 |
executing it might still continue to execute, and in other cases it might |
289 |
still take a while till the request is cancelled. |
290 |
|
291 |
Even if cancelled, the finish callback will still be invoked - the |
292 |
callbacks of all cancellable requests need to check whether the request |
293 |
has been cancelled by calling C<EIO_CANCELLED (req)>: |
294 |
|
295 |
static int |
296 |
my_eio_cb (eio_req *req) |
297 |
{ |
298 |
if (EIO_CANCELLED (req)) |
299 |
return 0; |
300 |
} |
301 |
|
302 |
In addition, cancelled requests will I<either> have C<< req->result >> |
303 |
set to C<-1> and C<errno> to C<ECANCELED>, or I<otherwise> they were |
304 |
successfully executed, despite being cancelled (e.g. when they have |
305 |
already been executed at the time they were cancelled). |
306 |
|
307 |
C<EIO_CANCELLED> is still true for requests that have successfully |
308 |
executed, as long as C<eio_cancel> was called on them at some point. |
309 |
|
310 |
=back |
311 |
|
312 |
=head2 AVAILABLE REQUESTS |
313 |
|
314 |
The following request functions are available. I<All> of them return the |
315 |
C<eio_req *> on success and C<0> on failure, and I<all> of them have the |
316 |
same three trailing arguments: C<pri>, C<cb> and C<data>. The C<cb> is |
317 |
mandatory, but in most cases, you pass in C<0> as C<pri> and C<0> or some |
318 |
custom data value as C<data>. |
319 |
|
320 |
=head3 POSIX API WRAPPERS |
321 |
|
322 |
These requests simply wrap the POSIX call of the same name, with the same |
323 |
arguments. If a function is not implemented by the OS and cannot be emulated |
324 |
in some way, then all of these return C<-1> and set C<errorno> to C<ENOSYS>. |
325 |
|
326 |
=over 4 |
327 |
|
328 |
=item eio_open (const char *path, int flags, mode_t mode, int pri, eio_cb cb, void *data) |
329 |
|
330 |
=item eio_truncate (const char *path, off_t offset, int pri, eio_cb cb, void *data) |
331 |
|
332 |
=item eio_chown (const char *path, uid_t uid, gid_t gid, int pri, eio_cb cb, void *data) |
333 |
|
334 |
=item eio_chmod (const char *path, mode_t mode, int pri, eio_cb cb, void *data) |
335 |
|
336 |
=item eio_mkdir (const char *path, mode_t mode, int pri, eio_cb cb, void *data) |
337 |
|
338 |
=item eio_rmdir (const char *path, int pri, eio_cb cb, void *data) |
339 |
|
340 |
=item eio_unlink (const char *path, int pri, eio_cb cb, void *data) |
341 |
|
342 |
=item eio_utime (const char *path, eio_tstamp atime, eio_tstamp mtime, int pri, eio_cb cb, void *data) |
343 |
|
344 |
=item eio_mknod (const char *path, mode_t mode, dev_t dev, int pri, eio_cb cb, void *data) |
345 |
|
346 |
=item eio_link (const char *path, const char *new_path, int pri, eio_cb cb, void *data) |
347 |
|
348 |
=item eio_symlink (const char *path, const char *new_path, int pri, eio_cb cb, void *data) |
349 |
|
350 |
=item eio_rename (const char *path, const char *new_path, int pri, eio_cb cb, void *data) |
351 |
|
352 |
=item eio_mlock (void *addr, size_t length, int pri, eio_cb cb, void *data) |
353 |
|
354 |
=item eio_close (int fd, int pri, eio_cb cb, void *data) |
355 |
|
356 |
=item eio_sync (int pri, eio_cb cb, void *data) |
357 |
|
358 |
=item eio_fsync (int fd, int pri, eio_cb cb, void *data) |
359 |
|
360 |
=item eio_fdatasync (int fd, int pri, eio_cb cb, void *data) |
361 |
|
362 |
=item eio_futime (int fd, eio_tstamp atime, eio_tstamp mtime, int pri, eio_cb cb, void *data) |
363 |
|
364 |
=item eio_ftruncate (int fd, off_t offset, int pri, eio_cb cb, void *data) |
365 |
|
366 |
=item eio_fchmod (int fd, mode_t mode, int pri, eio_cb cb, void *data) |
367 |
|
368 |
=item eio_fchown (int fd, uid_t uid, gid_t gid, int pri, eio_cb cb, void *data) |
369 |
|
370 |
=item eio_dup2 (int fd, int fd2, int pri, eio_cb cb, void *data) |
371 |
|
372 |
These have the same semantics as the syscall of the same name, their |
373 |
return value is available as C<< req->result >> later. |
374 |
|
375 |
=item eio_read (int fd, void *buf, size_t length, off_t offset, int pri, eio_cb cb, void *data) |
376 |
|
377 |
=item eio_write (int fd, void *buf, size_t length, off_t offset, int pri, eio_cb cb, void *data) |
378 |
|
379 |
These two requests are called C<read> and C<write>, but actually wrap |
380 |
C<pread> and C<pwrite>. On systems that lack these calls (such as cygwin), |
381 |
libeio uses lseek/read_or_write/lseek and a mutex to serialise the |
382 |
requests, so all these requests run serially and do not disturb each |
383 |
other. However, they still disturb the file offset while they run, so it's |
384 |
not safe to call these functions concurrently with non-libeio functions on |
385 |
the same fd on these systems. |
386 |
|
387 |
Not surprisingly, pread and pwrite are not thread-safe on Darwin (OS/X), |
388 |
so it is advised not to submit multiple requests on the same fd on this |
389 |
horrible pile of garbage. |
390 |
|
391 |
=item eio_mlockall (int flags, int pri, eio_cb cb, void *data) |
392 |
|
393 |
Like C<mlockall>, but the flag value constants are called |
394 |
C<EIO_MCL_CURRENT> and C<EIO_MCL_FUTURE>. |
395 |
|
396 |
=item eio_msync (void *addr, size_t length, int flags, int pri, eio_cb cb, void *data) |
397 |
|
398 |
Just like msync, except that the flag values are called C<EIO_MS_ASYNC>, |
399 |
C<EIO_MS_INVALIDATE> and C<EIO_MS_SYNC>. |
400 |
|
401 |
=item eio_readlink (const char *path, int pri, eio_cb cb, void *data) |
402 |
|
403 |
If successful, the path read by C<readlink(2)> can be accessed via C<< |
404 |
req->ptr2 >> and is I<NOT> null-terminated, with the length specified as |
405 |
C<< req->result >>. |
406 |
|
407 |
if (req->result >= 0) |
408 |
{ |
409 |
char *target = strndup ((char *)req->ptr2, req->result); |
410 |
|
411 |
free (target); |
412 |
} |
413 |
|
414 |
=item eio_realpath (const char *path, int pri, eio_cb cb, void *data) |
415 |
|
416 |
Similar to the realpath libc function, but unlike that one, C<< |
417 |
req->result >> is C<-1> on failure. On success, the result is the length |
418 |
of the returned path in C<ptr2> (which is I<NOT> 0-terminated) - this is |
419 |
similar to readlink. |
420 |
|
421 |
=item eio_stat (const char *path, int pri, eio_cb cb, void *data) |
422 |
|
423 |
=item eio_lstat (const char *path, int pri, eio_cb cb, void *data) |
424 |
|
425 |
=item eio_fstat (int fd, int pri, eio_cb cb, void *data) |
426 |
|
427 |
Stats a file - if C<< req->result >> indicates success, then you can |
428 |
access the C<struct stat>-like structure via C<< req->ptr2 >>: |
429 |
|
430 |
EIO_STRUCT_STAT *statdata = (EIO_STRUCT_STAT *)req->ptr2; |
431 |
|
432 |
=item eio_statvfs (const char *path, int pri, eio_cb cb, void *data) |
433 |
|
434 |
=item eio_fstatvfs (int fd, int pri, eio_cb cb, void *data) |
435 |
|
436 |
Stats a filesystem - if C<< req->result >> indicates success, then you can |
437 |
access the C<struct statvfs>-like structure via C<< req->ptr2 >>: |
438 |
|
439 |
EIO_STRUCT_STATVFS *statdata = (EIO_STRUCT_STATVFS *)req->ptr2; |
440 |
|
441 |
=back |
442 |
|
443 |
=head3 READING DIRECTORIES |
444 |
|
445 |
Reading directories sounds simple, but can be rather demanding, especially |
446 |
if you want to do stuff such as traversing a directory hierarchy or |
447 |
processing all files in a directory. Libeio can assist these complex tasks |
448 |
with it's C<eio_readdir> call. |
449 |
|
450 |
=over 4 |
451 |
|
452 |
=item eio_readdir (const char *path, int flags, int pri, eio_cb cb, void *data) |
453 |
|
454 |
This is a very complex call. It basically reads through a whole directory |
455 |
(via the C<opendir>, C<readdir> and C<closedir> calls) and returns either |
456 |
the names or an array of C<struct eio_dirent>, depending on the C<flags> |
457 |
argument. |
458 |
|
459 |
The C<< req->result >> indicates either the number of files found, or |
460 |
C<-1> on error. On success, null-terminated names can be found as C<< req->ptr2 >>, |
461 |
and C<struct eio_dirents>, if requested by C<flags>, can be found via C<< |
462 |
req->ptr1 >>. |
463 |
|
464 |
Here is an example that prints all the names: |
465 |
|
466 |
int i; |
467 |
char *names = (char *)req->ptr2; |
468 |
|
469 |
for (i = 0; i < req->result; ++i) |
470 |
{ |
471 |
printf ("name #%d: %s\n", i, names); |
472 |
|
473 |
/* move to next name */ |
474 |
names += strlen (names) + 1; |
475 |
} |
476 |
|
477 |
Pseudo-entries such as F<.> and F<..> are never returned by C<eio_readdir>. |
478 |
|
479 |
C<flags> can be any combination of: |
480 |
|
481 |
=over 4 |
482 |
|
483 |
=item EIO_READDIR_DENTS |
484 |
|
485 |
If this flag is specified, then, in addition to the names in C<ptr2>, |
486 |
also an array of C<struct eio_dirent> is returned, in C<ptr1>. A C<struct |
487 |
eio_dirent> looks like this: |
488 |
|
489 |
struct eio_dirent |
490 |
{ |
491 |
int nameofs; /* offset of null-terminated name string in (char *)req->ptr2 */ |
492 |
unsigned short namelen; /* size of filename without trailing 0 */ |
493 |
unsigned char type; /* one of EIO_DT_* */ |
494 |
signed char score; /* internal use */ |
495 |
ino_t inode; /* the inode number, if available, otherwise unspecified */ |
496 |
}; |
497 |
|
498 |
The only members you normally would access are C<nameofs>, which is the |
499 |
byte-offset from C<ptr2> to the start of the name, C<namelen> and C<type>. |
500 |
|
501 |
C<type> can be one of: |
502 |
|
503 |
C<EIO_DT_UNKNOWN> - if the type is not known (very common) and you have to C<stat> |
504 |
the name yourself if you need to know, |
505 |
one of the "standard" POSIX file types (C<EIO_DT_REG>, C<EIO_DT_DIR>, C<EIO_DT_LNK>, |
506 |
C<EIO_DT_FIFO>, C<EIO_DT_SOCK>, C<EIO_DT_CHR>, C<EIO_DT_BLK>) |
507 |
or some OS-specific type (currently |
508 |
C<EIO_DT_MPC> - multiplexed char device (v7+coherent), |
509 |
C<EIO_DT_NAM> - xenix special named file, |
510 |
C<EIO_DT_MPB> - multiplexed block device (v7+coherent), |
511 |
C<EIO_DT_NWK> - HP-UX network special, |
512 |
C<EIO_DT_CMP> - VxFS compressed, |
513 |
C<EIO_DT_DOOR> - solaris door, or |
514 |
C<EIO_DT_WHT>). |
515 |
|
516 |
This example prints all names and their type: |
517 |
|
518 |
int i; |
519 |
struct eio_dirent *ents = (struct eio_dirent *)req->ptr1; |
520 |
char *names = (char *)req->ptr2; |
521 |
|
522 |
for (i = 0; i < req->result; ++i) |
523 |
{ |
524 |
struct eio_dirent *ent = ents + i; |
525 |
char *name = names + ent->nameofs; |
526 |
|
527 |
printf ("name #%d: %s (type %d)\n", i, name, ent->type); |
528 |
} |
529 |
|
530 |
=item EIO_READDIR_DIRS_FIRST |
531 |
|
532 |
When this flag is specified, then the names will be returned in an order |
533 |
where likely directories come first, in optimal C<stat> order. This is |
534 |
useful when you need to quickly find directories, or you want to find all |
535 |
directories while avoiding to stat() each entry. |
536 |
|
537 |
If the system returns type information in readdir, then this is used |
538 |
to find directories directly. Otherwise, likely directories are names |
539 |
beginning with ".", or otherwise names with no dots, of which names with |
540 |
short names are tried first. |
541 |
|
542 |
=item EIO_READDIR_STAT_ORDER |
543 |
|
544 |
When this flag is specified, then the names will be returned in an order |
545 |
suitable for stat()'ing each one. That is, when you plan to stat() |
546 |
all files in the given directory, then the returned order will likely |
547 |
be fastest. |
548 |
|
549 |
If both this flag and C<EIO_READDIR_DIRS_FIRST> are specified, then the |
550 |
likely directories come first, resulting in a less optimal stat order. |
551 |
|
552 |
=item EIO_READDIR_FOUND_UNKNOWN |
553 |
|
554 |
This flag should not be specified when calling C<eio_readdir>. Instead, |
555 |
it is being set by C<eio_readdir> (you can access the C<flags> via C<< |
556 |
req->int1 >>, when any of the C<type>'s found were C<EIO_DT_UNKNOWN>. The |
557 |
absence of this flag therefore indicates that all C<type>'s are known, |
558 |
which can be used to speed up some algorithms. |
559 |
|
560 |
A typical use case would be to identify all subdirectories within a |
561 |
directory - you would ask C<eio_readdir> for C<EIO_READDIR_DIRS_FIRST>. If |
562 |
then this flag is I<NOT> set, then all the entries at the beginning of the |
563 |
returned array of type C<EIO_DT_DIR> are the directories. Otherwise, you |
564 |
should start C<stat()>'ing the entries starting at the beginning of the |
565 |
array, stopping as soon as you found all directories (the count can be |
566 |
deduced by the link count of the directory). |
567 |
|
568 |
=back |
569 |
|
570 |
=back |
571 |
|
572 |
=head3 OS-SPECIFIC CALL WRAPPERS |
573 |
|
574 |
These wrap OS-specific calls (usually Linux ones), and might or might not |
575 |
be emulated on other operating systems. Calls that are not emulated will |
576 |
return C<-1> and set C<errno> to C<ENOSYS>. |
577 |
|
578 |
=over 4 |
579 |
|
580 |
=item eio_sendfile (int out_fd, int in_fd, off_t in_offset, size_t length, int pri, eio_cb cb, void *data) |
581 |
|
582 |
Wraps the C<sendfile> syscall. The arguments follow the Linux version, but |
583 |
libeio supports and will use similar calls on FreeBSD, HP/UX, Solaris and |
584 |
Darwin. |
585 |
|
586 |
If the OS doesn't support some sendfile-like call, or the call fails, |
587 |
indicating support for the given file descriptor type (for example, |
588 |
Linux's sendfile might not support file to file copies), then libeio will |
589 |
emulate the call in userspace, so there are almost no limitations on its |
590 |
use. |
591 |
|
592 |
=item eio_readahead (int fd, off_t offset, size_t length, int pri, eio_cb cb, void *data) |
593 |
|
594 |
Calls C<readahead(2)>. If the syscall is missing, then the call is |
595 |
emulated by simply reading the data (currently in 64kiB chunks). |
596 |
|
597 |
=item eio_sync_file_range (int fd, off_t offset, size_t nbytes, unsigned int flags, int pri, eio_cb cb, void *data) |
598 |
|
599 |
Calls C<sync_file_range>. If the syscall is missing, then this is the same |
600 |
as calling C<fdatasync>. |
601 |
|
602 |
Flags can be any combination of C<EIO_SYNC_FILE_RANGE_WAIT_BEFORE>, |
603 |
C<EIO_SYNC_FILE_RANGE_WRITE> and C<EIO_SYNC_FILE_RANGE_WAIT_AFTER>. |
604 |
|
605 |
=item eio_fallocate (int fd, int mode, off_t offset, off_t len, int pri, eio_cb cb, void *data) |
606 |
|
607 |
Calls C<fallocate> (note: I<NOT> C<posix_fallocate>!). If the syscall is |
608 |
missing, then it returns failure and sets C<errno> to C<ENOSYS>. |
609 |
|
610 |
The C<mode> argument can be C<0> (for behaviour similar to |
611 |
C<posix_fallocate>), or C<EIO_FALLOC_FL_KEEP_SIZE>, which keeps the size |
612 |
of the file unchanged (but still preallocates space beyond end of file). |
613 |
|
614 |
=back |
615 |
|
616 |
=head3 LIBEIO-SPECIFIC REQUESTS |
617 |
|
618 |
These requests are specific to libeio and do not correspond to any OS call. |
619 |
|
620 |
=over 4 |
621 |
|
622 |
=item eio_mtouch (void *addr, size_t length, int flags, int pri, eio_cb cb, void *data) |
623 |
|
624 |
Reads (C<flags == 0>) or modifies (C<flags == EIO_MT_MODIFY) the given |
625 |
memory area, page-wise, that is, it reads (or reads and writes back) the |
626 |
first octet of every page that spans the memory area. |
627 |
|
628 |
This can be used to page in some mmapped file, or dirty some pages. Note |
629 |
that dirtying is an unlocked read-write access, so races can ensue when |
630 |
the some other thread modifies the data stored in that memory area. |
631 |
|
632 |
=item eio_custom (void (*)(eio_req *) execute, int pri, eio_cb cb, void *data) |
633 |
|
634 |
Executes a custom request, i.e., a user-specified callback. |
635 |
|
636 |
The callback gets the C<eio_req *> as parameter and is expected to read |
637 |
and modify any request-specific members. Specifically, it should set C<< |
638 |
req->result >> to the result value, just like other requests. |
639 |
|
640 |
Here is an example that simply calls C<open>, like C<eio_open>, but it |
641 |
uses the C<data> member as filename and uses a hardcoded C<O_RDONLY>. If |
642 |
you want to pass more/other parameters, you either need to pass some |
643 |
struct or so via C<data> or provide your own wrapper using the low-level |
644 |
API. |
645 |
|
646 |
static int |
647 |
my_open_done (eio_req *req) |
648 |
{ |
649 |
int fd = req->result; |
650 |
|
651 |
return 0; |
652 |
} |
653 |
|
654 |
static void |
655 |
my_open (eio_req *req) |
656 |
{ |
657 |
req->result = open (req->data, O_RDONLY); |
658 |
} |
659 |
|
660 |
eio_custom (my_open, 0, my_open_done, "/etc/passwd"); |
661 |
|
662 |
=item eio_busy (eio_tstamp delay, int pri, eio_cb cb, void *data) |
663 |
|
664 |
This is a request that takes C<delay> seconds to execute, but otherwise |
665 |
does nothing - it simply puts one of the worker threads to sleep for this |
666 |
long. |
667 |
|
668 |
This request can be used to artificially increase load, e.g. for debugging |
669 |
or benchmarking reasons. |
670 |
|
671 |
=item eio_nop (int pri, eio_cb cb, void *data) |
672 |
|
673 |
This request does nothing, except go through the whole request cycle. This |
674 |
can be used to measure latency or in some cases to simplify code, but is |
675 |
not really of much use. |
676 |
|
677 |
=back |
678 |
|
679 |
=head3 GROUPING AND LIMITING REQUESTS |
680 |
|
681 |
There is one more rather special request, C<eio_grp>. It is a very special |
682 |
aio request: Instead of doing something, it is a container for other eio |
683 |
requests. |
684 |
|
685 |
There are two primary use cases for this: a) bundle many requests into a |
686 |
single, composite, request with a definite callback and the ability to |
687 |
cancel the whole request with its subrequests and b) limiting the number |
688 |
of "active" requests. |
689 |
|
690 |
Further below you will find more discussion of these topics - first |
691 |
follows the reference section detailing the request generator and other |
692 |
methods. |
693 |
|
694 |
=over 4 |
695 |
|
696 |
=item eio_req *grp = eio_grp (eio_cb cb, void *data) |
697 |
|
698 |
Creates, submits and returns a group request. Note that it doesn't have a |
699 |
priority, unlike all other requests. |
700 |
|
701 |
=item eio_grp_add (eio_req *grp, eio_req *req) |
702 |
|
703 |
Adds a request to the request group. |
704 |
|
705 |
=item eio_grp_cancel (eio_req *grp) |
706 |
|
707 |
Cancels all requests I<in> the group, but I<not> the group request |
708 |
itself. You can cancel the group request I<and> all subrequests via a |
709 |
normal C<eio_cancel> call. |
710 |
|
711 |
=back |
712 |
|
713 |
=head4 GROUP REQUEST LIFETIME |
714 |
|
715 |
Left alone, a group request will instantly move to the pending state and |
716 |
will be finished at the next call of C<eio_poll>. |
717 |
|
718 |
The usefulness stems from the fact that, if a subrequest is added to a |
719 |
group I<before> a call to C<eio_poll>, via C<eio_grp_add>, then the group |
720 |
will not finish until all the subrequests have finished. |
721 |
|
722 |
So the usage cycle of a group request is like this: after it is created, |
723 |
you normally instantly add a subrequest. If none is added, the group |
724 |
request will finish on it's own. As long as subrequests are added before |
725 |
the group request is finished it will be kept from finishing, that is the |
726 |
callbacks of any subrequests can, in turn, add more requests to the group, |
727 |
and as long as any requests are active, the group request itself will not |
728 |
finish. |
729 |
|
730 |
=head4 CREATING COMPOSITE REQUESTS |
731 |
|
732 |
Imagine you wanted to create an C<eio_load> request that opens a file, |
733 |
reads it and closes it. This means it has to execute at least three eio |
734 |
requests, but for various reasons it might be nice if that request looked |
735 |
like any other eio request. |
736 |
|
737 |
This can be done with groups: |
738 |
|
739 |
=over 4 |
740 |
|
741 |
=item 1) create the request object |
742 |
|
743 |
Create a group that contains all further requests. This is the request you |
744 |
can return as "the load request". |
745 |
|
746 |
=item 2) open the file, maybe |
747 |
|
748 |
Next, open the file with C<eio_open> and add the request to the group |
749 |
request and you are finished setting up the request. |
750 |
|
751 |
If, for some reason, you cannot C<eio_open> (path is a null ptr?) you |
752 |
can set C<< grp->result >> to C<-1> to signal an error and let the group |
753 |
request finish on its own. |
754 |
|
755 |
=item 3) open callback adds more requests |
756 |
|
757 |
In the open callback, if the open was not successful, copy C<< |
758 |
req->errorno >> to C<< grp->errorno >> and set C<< grp->errorno >> to |
759 |
C<-1> to signal an error. |
760 |
|
761 |
Otherwise, malloc some memory or so and issue a read request, adding the |
762 |
read request to the group. |
763 |
|
764 |
=item 4) continue issuing requests till finished |
765 |
|
766 |
In the real callback, check for errors and possibly continue with |
767 |
C<eio_close> or any other eio request in the same way. |
768 |
|
769 |
As soon as no new requests are added the group request will finish. Make |
770 |
sure you I<always> set C<< grp->result >> to some sensible value. |
771 |
|
772 |
=back |
773 |
|
774 |
=head4 REQUEST LIMITING |
775 |
|
776 |
|
777 |
#TODO |
778 |
|
779 |
void eio_grp_limit (eio_req *grp, int limit); |
780 |
|
781 |
|
782 |
=back |
783 |
|
784 |
|
785 |
=head1 LOW LEVEL REQUEST API |
786 |
|
787 |
#TODO |
788 |
|
789 |
|
790 |
=head1 ANATOMY AND LIFETIME OF AN EIO REQUEST |
791 |
|
792 |
A request is represented by a structure of type C<eio_req>. To initialise |
793 |
it, clear it to all zero bytes: |
794 |
|
795 |
eio_req req; |
796 |
|
797 |
memset (&req, 0, sizeof (req)); |
798 |
|
799 |
A more common way to initialise a new C<eio_req> is to use C<calloc>: |
800 |
|
801 |
eio_req *req = calloc (1, sizeof (*req)); |
802 |
|
803 |
In either case, libeio neither allocates, initialises or frees the |
804 |
C<eio_req> structure for you - it merely uses it. |
805 |
|
806 |
zero |
807 |
|
808 |
#TODO |
809 |
|
810 |
=head2 CONFIGURATION |
811 |
|
812 |
The functions in this section can sometimes be useful, but the default |
813 |
configuration will do in most case, so you should skip this section on |
814 |
first reading. |
815 |
|
816 |
=over 4 |
817 |
|
818 |
=item eio_set_max_poll_time (eio_tstamp nseconds) |
819 |
|
820 |
This causes C<eio_poll ()> to return after it has detected that it was |
821 |
running for C<nsecond> seconds or longer (this number can be fractional). |
822 |
|
823 |
This can be used to limit the amount of time spent handling eio requests, |
824 |
for example, in interactive programs, you might want to limit this time to |
825 |
C<0.01> seconds or so. |
826 |
|
827 |
Note that: |
828 |
|
829 |
=over 4 |
830 |
|
831 |
=item a) libeio doesn't know how long your request callbacks take, so the |
832 |
time spent in C<eio_poll> is up to one callback invocation longer then |
833 |
this interval. |
834 |
|
835 |
=item b) this is implemented by calling C<gettimeofday> after each |
836 |
request, which can be costly. |
837 |
|
838 |
=item c) at least one request will be handled. |
839 |
|
840 |
=back |
841 |
|
842 |
=item eio_set_max_poll_reqs (unsigned int nreqs) |
843 |
|
844 |
When C<nreqs> is non-zero, then C<eio_poll> will not handle more than |
845 |
C<nreqs> requests per invocation. This is a less costly way to limit the |
846 |
amount of work done by C<eio_poll> then setting a time limit. |
847 |
|
848 |
If you know your callbacks are generally fast, you could use this to |
849 |
encourage interactiveness in your programs by setting it to C<10>, C<100> |
850 |
or even C<1000>. |
851 |
|
852 |
=item eio_set_min_parallel (unsigned int nthreads) |
853 |
|
854 |
Make sure libeio can handle at least this many requests in parallel. It |
855 |
might be able handle more. |
856 |
|
857 |
=item eio_set_max_parallel (unsigned int nthreads) |
858 |
|
859 |
Set the maximum number of threads that libeio will spawn. |
860 |
|
861 |
=item eio_set_max_idle (unsigned int nthreads) |
862 |
|
863 |
Libeio uses threads internally to handle most requests, and will start and stop threads on demand. |
864 |
|
865 |
This call can be used to limit the number of idle threads (threads without |
866 |
work to do): libeio will keep some threads idle in preparation for more |
867 |
requests, but never longer than C<nthreads> threads. |
868 |
|
869 |
In addition to this, libeio will also stop threads when they are idle for |
870 |
a few seconds, regardless of this setting. |
871 |
|
872 |
=item unsigned int eio_nthreads () |
873 |
|
874 |
Return the number of worker threads currently running. |
875 |
|
876 |
=item unsigned int eio_nreqs () |
877 |
|
878 |
Return the number of requests currently handled by libeio. This is the |
879 |
total number of requests that have been submitted to libeio, but not yet |
880 |
destroyed. |
881 |
|
882 |
=item unsigned int eio_nready () |
883 |
|
884 |
Returns the number of ready requests, i.e. requests that have been |
885 |
submitted but have not yet entered the execution phase. |
886 |
|
887 |
=item unsigned int eio_npending () |
888 |
|
889 |
Returns the number of pending requests, i.e. requests that have been |
890 |
executed and have results, but have not been finished yet by a call to |
891 |
C<eio_poll>). |
892 |
|
893 |
=back |
894 |
|
895 |
=head1 EMBEDDING |
896 |
|
897 |
Libeio can be embedded directly into programs. This functionality is not |
898 |
documented and not (yet) officially supported. |
899 |
|
900 |
Note that, when including C<libeio.m4>, you are responsible for defining |
901 |
the compilation environment (C<_LARGEFILE_SOURCE>, C<_GNU_SOURCE> etc.). |
902 |
|
903 |
If you need to know how, check the C<IO::AIO> perl module, which does |
904 |
exactly that. |
905 |
|
906 |
|
907 |
=head1 COMPILETIME CONFIGURATION |
908 |
|
909 |
These symbols, if used, must be defined when compiling F<eio.c>. |
910 |
|
911 |
=over 4 |
912 |
|
913 |
=item EIO_STACKSIZE |
914 |
|
915 |
This symbol governs the stack size for each eio thread. Libeio itself |
916 |
was written to use very little stackspace, but when using C<EIO_CUSTOM> |
917 |
requests, you might want to increase this. |
918 |
|
919 |
If this symbol is undefined (the default) then libeio will use its default |
920 |
stack size (C<sizeof (void *) * 4096> currently). If it is defined, but |
921 |
C<0>, then the default operating system stack size will be used. In all |
922 |
other cases, the value must be an expression that evaluates to the desired |
923 |
stack size. |
924 |
|
925 |
=back |
926 |
|
927 |
|
928 |
=head1 PORTABILITY REQUIREMENTS |
929 |
|
930 |
In addition to a working ISO-C implementation, libeio relies on a few |
931 |
additional extensions: |
932 |
|
933 |
=over 4 |
934 |
|
935 |
=item POSIX threads |
936 |
|
937 |
To be portable, this module uses threads, specifically, the POSIX threads |
938 |
library must be available (and working, which partially excludes many xBSD |
939 |
systems, where C<fork ()> is buggy). |
940 |
|
941 |
=item POSIX-compatible filesystem API |
942 |
|
943 |
This is actually a harder portability requirement: The libeio API is quite |
944 |
demanding regarding POSIX API calls (symlinks, user/group management |
945 |
etc.). |
946 |
|
947 |
=item C<double> must hold a time value in seconds with enough accuracy |
948 |
|
949 |
The type C<double> is used to represent timestamps. It is required to |
950 |
have at least 51 bits of mantissa (and 9 bits of exponent), which is good |
951 |
enough for at least into the year 4000. This requirement is fulfilled by |
952 |
implementations implementing IEEE 754 (basically all existing ones). |
953 |
|
954 |
=back |
955 |
|
956 |
If you know of other additional requirements drop me a note. |
957 |
|
958 |
|
959 |
=head1 AUTHOR |
960 |
|
961 |
Marc Lehmann <libeio@schmorp.de>. |
962 |
|