--- IO-AIO/README 2005/07/10 23:45:16 1.5 +++ IO-AIO/README 2008/10/12 22:40:52 1.33 @@ -5,7 +5,8 @@ use IO::AIO; aio_open "/etc/passwd", O_RDONLY, 0, sub { - my ($fh) = @_; + my $fh = shift + or die "/etc/passwd: $!"; ... }; @@ -15,63 +16,238 @@ $_[0] > 0 or die "read error: $!"; }; - # Event + # version 2+ has request and group objects + use IO::AIO 2; + + aioreq_pri 4; # give next request a very high priority + my $req = aio_unlink "/tmp/file", sub { }; + $req->cancel; # cancel request if still in queue + + my $grp = aio_group sub { print "all stats done\n" }; + add $grp aio_stat "..." for ...; + + # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) + use AnyEvent::AIO; + + # EV integration + my $w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; + + # Event integration Event->io (fd => IO::AIO::poll_fileno, poll => 'r', cb => \&IO::AIO::poll_cb); - # Glib/Gtk2 + # Glib/Gtk2 integration add_watch Glib::IO IO::AIO::poll_fileno, - \&IO::AIO::poll_cb; + in => sub { IO::AIO::poll_cb; 1 }; - # Tk + # Tk integration Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", readable => \&IO::AIO::poll_cb); + # Danga::Socket integration + Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => + \&IO::AIO::poll_cb); + DESCRIPTION This module implements asynchronous I/O using whatever means your operating system supports. - Currently, a number of threads are started that execute your read/writes - and signal their completion. You don't need thread support in your libc - or perl, and the threads created by this module will not be visible to - the pthreads library. In the future, this module might make use of the - native aio functions available on many operating systems. However, they - are often not well-supported (Linux doesn't allow them on normal files - currently, for example), and they would only support aio_read and + Asynchronous means that operations that can normally block your program + (e.g. reading from disk) will be done asynchronously: the operation will + still block, but you can do something else in the meantime. This is + extremely useful for programs that need to stay interactive even when + doing heavy I/O (GUI programs, high performance network servers etc.), + but can also be used to easily do operations in parallel that are + normally done sequentially, e.g. stat'ing many files, which is much + faster on a RAID volume or over NFS when you do a number of stat + operations concurrently. + + While most of this works on all types of file descriptors (for example + sockets), using these functions on file descriptors that support + nonblocking operation (again, sockets, pipes etc.) is very inefficient. + Use an event loop for that (such as the Event module): IO::AIO will + naturally fit into such an event loop itself. + + In this version, a number of threads are started that execute your + requests and signal their completion. You don't need thread support in + perl, and the threads created by this module will not be visible to + perl. In the future, this module might make use of the native aio + functions available on many operating systems. However, they are often + not well-supported or restricted (GNU/Linux doesn't allow them on normal + files currently, for example), and they would only support aio_read and aio_write, so the remaining functionality would have to be implemented using threads anyway. - Although the module will work with in the presence of other threads, it - is currently not reentrant, so use appropriate locking yourself. + Although the module will work in the presence of other (Perl-) threads, + it is currently not reentrant in any way, so use appropriate locking + yourself, always call "poll_cb" from within the same thread, or never + call "poll_cb" (or other "aio_" functions) recursively. + + EXAMPLE + This is a simple example that uses the Event module and loads + /etc/passwd asynchronously: + + use Fcntl; + use Event; + use IO::AIO; + + # register the IO::AIO callback with Event + Event->io (fd => IO::AIO::poll_fileno, + poll => 'r', + cb => \&IO::AIO::poll_cb); + + # queue the request to open /etc/passwd + aio_open "/etc/passwd", O_RDONLY, 0, sub { + my $fh = shift + or die "error while opening: $!"; + + # stat'ing filehandles is generally non-blocking + my $size = -s $fh; + + # queue a request to read the file + my $contents; + aio_read $fh, 0, $size, $contents, 0, sub { + $_[0] == $size + or die "short read: $!"; + + close $fh; + + # file contents now in $contents + print $contents; + + # exit event loop and program + Event::unloop; + }; + }; + + # possibly queue up other requests, or open GUI windows, + # check for sockets etc. etc. + + # process events as long as there are some: + Event::loop; + +REQUEST ANATOMY AND LIFETIME + Every "aio_*" function creates a request. which is a C data structure + not directly visible to Perl. + + If called in non-void context, every request function returns a Perl + object representing the request. In void context, nothing is returned, + which saves a bit of memory. + + The perl object is a fairly standard ref-to-hash object. The hash + contents are not used by IO::AIO so you are free to store anything you + like in it. + + During their existance, aio requests travel through the following + states, in order: + + ready + Immediately after a request is created it is put into the ready + state, waiting for a thread to execute it. + + execute + A thread has accepted the request for processing and is currently + executing it (e.g. blocking in read). + + pending + The request has been executed and is waiting for result processing. + + While request submission and execution is fully asynchronous, result + processing is not and relies on the perl interpreter calling + "poll_cb" (or another function with the same effect). + + result + The request results are processed synchronously by "poll_cb". + + The "poll_cb" function will process all outstanding aio requests by + calling their callbacks, freeing memory associated with them and + managing any groups they are contained in. + + done + Request has reached the end of its lifetime and holds no resources + anymore (except possibly for the Perl object, but its connection to + the actual aio request is severed and calling its methods will + either do nothing or result in a runtime error). FUNCTIONS - AIO FUNCTIONS + AIO REQUEST FUNCTIONS All the "aio_*" calls are more or less thin wrappers around the syscall with the same name (sans "aio_"). The arguments are similar or - identical, and they all accept an additional $callback argument which - must be a code reference. This code reference will get called with the - syscall return code (e.g. most syscalls return -1 on error, unlike perl, - which usually delivers "false") as it's sole argument when the given - syscall has been executed asynchronously. - - All functions that expect a filehandle will also accept a file - descriptor. - - The filenames you pass to these routines *must* be absolute. The reason - is that at the time the request is being executed, the current working - directory could have changed. Alternatively, you can make sure that you - never change the current working directory. + identical, and they all accept an additional (and optional) $callback + argument which must be a code reference. This code reference will get + called with the syscall return code (e.g. most syscalls return -1 on + error, unlike perl, which usually delivers "false") as its sole argument + after the given syscall has been executed asynchronously. + + All functions expecting a filehandle keep a copy of the filehandle + internally until the request has finished. + + All functions return request objects of type IO::AIO::REQ that allow + further manipulation of those requests while they are in-flight. + + The pathnames you pass to these routines *must* be absolute and encoded + as octets. The reason for the former is that at the time the request is + being executed, the current working directory could have changed. + Alternatively, you can make sure that you never change the current + working directory anywhere in the program and then use relative paths. + + To encode pathnames as octets, either make sure you either: a) always + pass in filenames you got from outside (command line, readdir etc.) + without tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module + and encode your pathnames to the locale (or other) encoding in effect in + the user environment, d) use Glib::filename_from_unicode on unicode + filenames or e) use something else to ensure your scalar has the correct + contents. + + This works, btw. independent of the internal UTF-8 bit, which IO::AIO + handles correctly whether it is set or not. + + $prev_pri = aioreq_pri [$pri] + Returns the priority value that would be used for the next request + and, if $pri is given, sets the priority for the next aio request. + + The default priority is 0, the minimum and maximum priorities are -4 + and 4, respectively. Requests with higher priority will be serviced + first. + + The priority will be reset to 0 after each call to one of the + "aio_*" functions. + + Example: open a file with low priority, then read something from it + with higher priority so the read request is serviced before other + low priority open requests (potentially spamming the cache): + + aioreq_pri -3; + aio_open ..., sub { + return unless $_[0]; - aio_open $pathname, $flags, $mode, $callback + aioreq_pri -2; + aio_read $_[0], ..., sub { + ... + }; + }; + + aioreq_nice $pri_adjust + Similar to "aioreq_pri", but subtracts the given value from the + current priority, so the effect is cumulative. + + aio_open $pathname, $flags, $mode, $callback->($fh) Asynchronously open or create a file and call the callback with a newly created filehandle for the file. The pathname passed to "aio_open" must be absolute. See API NOTES, above, for an explanation. - The $mode argument is a bitmask. See the "Fcntl" module for a list. - They are the same as used in "sysopen". + The $flags argument is a bitmask. See the "Fcntl" module for a list. + They are the same as used by "sysopen". + + Likewise, $mode specifies the mode of the newly created file, if it + didn't exist and "O_CREAT" has been given, just like perl's + "sysopen", except that it is mandatory (i.e. use 0 if you don't + create new files, and 0666 or 0777 if you do). Note that the $mode + will be modified by the umask in effect then the request is being + executed, so better never change the umask. Example: @@ -84,21 +260,43 @@ } }; - aio_close $fh, $callback + aio_close $fh, $callback->($status) Asynchronously close a file and call the callback with the result - code. *WARNING:* although accepted, you should not pass in a perl - filehandle here, as perl will likely close the file descriptor - itself when the filehandle is destroyed. Normally, you can safely - call perls "close" or just let filehandles go out of scope. - - aio_read $fh,$offset,$length, $data,$dataoffset,$callback - aio_write $fh,$offset,$length, $data,$dataoffset,$callback - Reads or writes "length" bytes from the specified "fh" and "offset" - into the scalar given by "data" and offset "dataoffset" and calls - the callback without the actual number of bytes read (or -1 on - error, just like the syscall). + code. - Example: Read 15 bytes at offset 7 into scalar $buffer, strating at + Unfortunately, you can't do this to perl. Perl *insists* very + strongly on closing the file descriptor associated with the + filehandle itself. + + Therefore, "aio_close" will not close the filehandle - instead it + will use dup2 to overwrite the file descriptor with the write-end of + a pipe (the pipe fd will be created on demand and will be cached). + + Or in other words: the file descriptor will be closed, but it will + not be free for reuse until the perl filehandle is closed. + + aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) + aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) + Reads or writes $length bytes from the specified $fh and $offset + into the scalar given by $data and offset $dataoffset and calls the + callback without the actual number of bytes read (or -1 on error, + just like the syscall). + + If $offset is undefined, then the current file descriptor offset + will be used (and updated), otherwise the file descriptor offset + will not be changed by these calls. + + If $length is undefined in "aio_write", use the remaining length of + $data. + + If $dataoffset is less than zero, it will be counted from the end of + $data. + + The $data scalar *MUST NOT* be modified in any way while the request + is outstanding. Modifying it can result in segfaults or World War + III (if the necessary/optional hardware is installed). + + Example: Read 15 bytes at offset 7 into scalar $buffer, starting at offset 0 within the scalar: aio_read $fh, 7, 15, $buffer, 0, sub { @@ -106,23 +304,45 @@ print "read $_[0] bytes: <$buffer>\n"; }; - aio_readahead $fh,$offset,$length, $callback - Asynchronously reads the specified byte range into the page cache, - using the "readahead" syscall. If that syscall doesn't exist the - status will be -1 and $! is set to ENOSYS. - - readahead() populates the page cache with data from a file so that - subsequent reads from that file will not block on disk I/O. The + aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) + Tries to copy $length bytes from $in_fh to $out_fh. It starts + reading at byte offset $in_offset, and starts writing at the current + file offset of $out_fh. Because of that, it is not safe to issue + more than one "aio_sendfile" per $out_fh, as they will interfere + with each other. + + This call tries to make use of a native "sendfile" syscall to + provide zero-copy operation. For this to work, $out_fh should refer + to a socket, and $in_fh should refer to mmap'able file. + + If the native sendfile call fails or is not implemented, it will be + emulated, so you can call "aio_sendfile" on any type of filehandle + regardless of the limitations of the operating system. + + Please note, however, that "aio_sendfile" can read more bytes from + $in_fh than are written, and there is no way to find out how many + bytes have been read from "aio_sendfile" alone, as "aio_sendfile" + only provides the number of bytes written to $out_fh. Only if the + result value equals $length one can assume that $length bytes have + been read. + + aio_readahead $fh,$offset,$length, $callback->($retval) + "aio_readahead" populates the page cache with data from a file so + that subsequent reads from that file will not block on disk I/O. The $offset argument specifies the starting point from which data is to be read and $length specifies the number of bytes to be read. I/O is performed in whole pages, so that offset is effectively rounded down to a page boundary and bytes are read up to the next page boundary - greater than or equal to (off-set+length). aio_readahead() does not + greater than or equal to (off-set+length). "aio_readahead" does not read beyond the end of the file. The current file offset of the file is left unchanged. - aio_stat $fh_or_path, $callback - aio_lstat $fh, $callback + If that syscall doesn't exist (likely if your OS isn't Linux) it + will be emulated by simply reading the data, which would have a + similar effect. + + aio_stat $fh_or_path, $callback->($status) + aio_lstat $fh, $callback->($status) Works like perl's "stat" or "lstat" in void context. The callback will be called after the stat and the results will be available using "stat _" or "-s _" etc... @@ -142,71 +362,500 @@ print "size is ", -s _, "\n"; }; - aio_unlink $pathname, $callback + aio_utime $fh_or_path, $atime, $mtime, $callback->($status) + Works like perl's "utime" function (including the special case of + $atime and $mtime being undef). Fractional times are supported if + the underlying syscalls support them. + + When called with a pathname, uses utimes(2) if available, otherwise + utime(2). If called on a file descriptor, uses futimes(2) if + available, otherwise returns ENOSYS, so this is not portable. + + Examples: + + # set atime and mtime to current time (basically touch(1)): + aio_utime "path", undef, undef; + # set atime to current time and mtime to beginning of the epoch: + aio_utime "path", time, undef; # undef==0 + + aio_chown $fh_or_path, $uid, $gid, $callback->($status) + Works like perl's "chown" function, except that "undef" for either + $uid or $gid is being interpreted as "do not change" (but -1 can + also be used). + + Examples: + + # same as "chown root path" in the shell: + aio_chown "path", 0, -1; + # same as above: + aio_chown "path", 0, undef; + + aio_truncate $fh_or_path, $offset, $callback->($status) + Works like truncate(2) or ftruncate(2). + + aio_chmod $fh_or_path, $mode, $callback->($status) + Works like perl's "chmod" function. + + aio_unlink $pathname, $callback->($status) Asynchronously unlink (delete) a file and call the callback with the result code. - aio_fsync $fh, $callback + aio_mknod $path, $mode, $dev, $callback->($status) + [EXPERIMENTAL] + + Asynchronously create a device node (or fifo). See mknod(2). + + The only (POSIX-) portable way of calling this function is: + + aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... + + aio_link $srcpath, $dstpath, $callback->($status) + Asynchronously create a new link to the existing object at $srcpath + at the path $dstpath and call the callback with the result code. + + aio_symlink $srcpath, $dstpath, $callback->($status) + Asynchronously create a new symbolic link to the existing object at + $srcpath at the path $dstpath and call the callback with the result + code. + + aio_readlink $path, $callback->($link) + Asynchronously read the symlink specified by $path and pass it to + the callback. If an error occurs, nothing or undef gets passed to + the callback. + + aio_rename $srcpath, $dstpath, $callback->($status) + Asynchronously rename the object at $srcpath to $dstpath, just as + rename(2) and call the callback with the result code. + + aio_mkdir $pathname, $mode, $callback->($status) + Asynchronously mkdir (create) a directory and call the callback with + the result code. $mode will be modified by the umask at the time the + request is executed, so do not change your umask. + + aio_rmdir $pathname, $callback->($status) + Asynchronously rmdir (delete) a directory and call the callback with + the result code. + + aio_readdir $pathname, $callback->($entries) + Unlike the POSIX call of the same name, "aio_readdir" reads an + entire directory (i.e. opendir + readdir + closedir). The entries + will not be sorted, and will NOT include the "." and ".." entries. + + The callback a single argument which is either "undef" or an + array-ref with the filenames. + + aio_load $path, $data, $callback->($status) + This is a composite request that tries to fully load the given file + into memory. Status is the same as with aio_read. + + aio_copy $srcpath, $dstpath, $callback->($status) + Try to copy the *file* (directories not supported as either source + or destination) from $srcpath to $dstpath and call the callback with + the 0 (error) or -1 ok. + + This is a composite request that creates the destination file with + mode 0200 and copies the contents of the source file into it using + "aio_sendfile", followed by restoring atime, mtime, access mode and + uid/gid, in that order. + + If an error occurs, the partial destination file will be unlinked, + if possible, except when setting atime, mtime, access mode and + uid/gid, where errors are being ignored. + + aio_move $srcpath, $dstpath, $callback->($status) + Try to move the *file* (directories not supported as either source + or destination) from $srcpath to $dstpath and call the callback with + the 0 (error) or -1 ok. + + This is a composite request that tries to rename(2) the file first; + if rename fails with "EXDEV", it copies the file with "aio_copy" + and, if that is successful, unlinks the $srcpath. + + aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) + Scans a directory (similar to "aio_readdir") but additionally tries + to efficiently separate the entries of directory $path into two sets + of names, directories you can recurse into (directories), and ones + you cannot recurse into (everything else, including symlinks to + directories). + + "aio_scandir" is a composite request that creates of many sub + requests_ $maxreq specifies the maximum number of outstanding aio + requests that this function generates. If it is "<= 0", then a + suitable default will be chosen (currently 4). + + On error, the callback is called without arguments, otherwise it + receives two array-refs with path-relative entry names. + + Example: + + aio_scandir $dir, 0, sub { + my ($dirs, $nondirs) = @_; + print "real directories: @$dirs\n"; + print "everything else: @$nondirs\n"; + }; + + Implementation notes. + + The "aio_readdir" cannot be avoided, but "stat()"'ing every entry + can. + + After reading the directory, the modification time, size etc. of the + directory before and after the readdir is checked, and if they match + (and isn't the current time), the link count will be used to decide + how many entries are directories (if >= 2). Otherwise, no knowledge + of the number of subdirectories will be assumed. + + Then entries will be sorted into likely directories (everything + without a non-initial dot currently) and likely non-directories + (everything else). Then every entry plus an appended "/." will be + "stat"'ed, likely directories first. If that succeeds, it assumes + that the entry is a directory or a symlink to directory (which will + be checked seperately). This is often faster than stat'ing the entry + itself because filesystems might detect the type of the entry + without reading the inode data (e.g. ext2fs filetype feature). + + If the known number of directories (link count - 2) has been + reached, the rest of the entries is assumed to be non-directories. + + This only works with certainty on POSIX (= UNIX) filesystems, which + fortunately are the vast majority of filesystems around. + + It will also likely work on non-POSIX filesystems with reduced + efficiency as those tend to return 0 or 1 as link counts, which + disables the directory counting heuristic. + + aio_rmtree $path, $callback->($status) + Delete a directory tree starting (and including) $path, return the + status of the final "rmdir" only. This is a composite request that + uses "aio_scandir" to recurse into and rmdir directories, and unlink + everything else. + + aio_sync $callback->($status) + Asynchronously call sync and call the callback when finished. + + aio_fsync $fh, $callback->($status) Asynchronously call fsync on the given filehandle and call the callback with the fsync result code. - aio_fdatasync $fh, $callback + aio_fdatasync $fh, $callback->($status) Asynchronously call fdatasync on the given filehandle and call the callback with the fdatasync result code. + If this call isn't available because your OS lacks it or it couldn't + be detected, it will be emulated by calling "fsync" instead. + + aio_pathsync $path, $callback->($status) + This request tries to open, fsync and close the given path. This is + a composite request intended to sync directories after directory + operations (E.g. rename). This might not work on all operating + systems or have any specific effect, but usually it makes sure that + directory changes get written to disc. It works for anything that + can be opened for read-only, not just directories. + + Passes 0 when everything went ok, and -1 on error. + + aio_group $callback->(...) + This is a very special aio request: Instead of doing something, it + is a container for other aio requests, which is useful if you want + to bundle many requests into a single, composite, request with a + definite callback and the ability to cancel the whole request with + its subrequests. + + Returns an object of class IO::AIO::GRP. See its documentation below + for more info. + + Example: + + my $grp = aio_group sub { + print "all stats done\n"; + }; + + add $grp + (aio_stat ...), + (aio_stat ...), + ...; + + aio_nop $callback->() + This is a special request - it does nothing in itself and is only + used for side effects, such as when you want to add a dummy request + to a group so that finishing the requests in the group depends on + executing the given code. + + While this request does nothing, it still goes through the execution + phase and still requires a worker thread. Thus, the callback will + not be executed immediately but only after other requests in the + queue have entered their execution phase. This can be used to + measure request latency. + + IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED* + Mainly used for debugging and benchmarking, this aio request puts + one of the request workers to sleep for the given time. + + While it is theoretically handy to have simple I/O scheduling + requests like sleep and file handle readable/writable, the overhead + this creates is immense (it blocks a thread for a long time) so do + not use this function except to put your application under + artificial I/O pressure. + + IO::AIO::REQ CLASS + All non-aggregate "aio_*" functions return an object of this class when + called in non-void context. + + cancel $req + Cancels the request, if possible. Has the effect of skipping + execution when entering the execute state and skipping calling the + callback when entering the the result state, but will leave the + request otherwise untouched. That means that requests that currently + execute will not be stopped and resources held by the request will + not be freed prematurely. + + cb $req $callback->(...) + Replace (or simply set) the callback registered to the request. + + IO::AIO::GRP CLASS + This class is a subclass of IO::AIO::REQ, so all its methods apply to + objects of this class, too. + + A IO::AIO::GRP object is a special request that can contain multiple + other aio requests. + + You create one by calling the "aio_group" constructing function with a + callback that will be called when all contained requests have entered + the "done" state: + + my $grp = aio_group sub { + print "all requests are done\n"; + }; + + You add requests by calling the "add" method with one or more + "IO::AIO::REQ" objects: + + $grp->add (aio_unlink "..."); + + add $grp aio_stat "...", sub { + $_[0] or return $grp->result ("error"); + + # add another request dynamically, if first succeeded + add $grp aio_open "...", sub { + $grp->result ("ok"); + }; + }; + + This makes it very easy to create composite requests (see the source of + "aio_move" for an application) that work and feel like simple requests. + + * The IO::AIO::GRP objects will be cleaned up during calls to + "IO::AIO::poll_cb", just like any other request. + + * They can be canceled like any other request. Canceling will cancel + not only the request itself, but also all requests it contains. + + * They can also can also be added to other IO::AIO::GRP objects. + + * You must not add requests to a group from within the group callback + (or any later time). + + Their lifetime, simplified, looks like this: when they are empty, they + will finish very quickly. If they contain only requests that are in the + "done" state, they will also finish. Otherwise they will continue to + exist. + + That means after creating a group you have some time to add requests + (precisely before the callback has been invoked, which is only done + within the "poll_cb"). And in the callbacks of those requests, you can + add further requests to the group. And only when all those requests have + finished will the the group itself finish. + + add $grp ... + $grp->add (...) + Add one or more requests to the group. Any type of IO::AIO::REQ can + be added, including other groups, as long as you do not create + circular dependencies. + + Returns all its arguments. + + $grp->cancel_subs + Cancel all subrequests and clears any feeder, but not the group + request itself. Useful when you queued a lot of events but got a + result early. + + $grp->result (...) + Set the result value(s) that will be passed to the group callback + when all subrequests have finished and set the groups errno to the + current value of errno (just like calling "errno" without an error + number). By default, no argument will be passed and errno is zero. + + $grp->errno ([$errno]) + Sets the group errno value to $errno, or the current value of errno + when the argument is missing. + + Every aio request has an associated errno value that is restored + when the callback is invoked. This method lets you change this value + from its default (0). + + Calling "result" will also set errno, so make sure you either set $! + before the call to "result", or call c after it. + + feed $grp $callback->($grp) + Sets a feeder/generator on this group: every group can have an + attached generator that generates requests if idle. The idea behind + this is that, although you could just queue as many requests as you + want in a group, this might starve other requests for a potentially + long time. For example, "aio_scandir" might generate hundreds of + thousands "aio_stat" requests, delaying any later requests for a + long time. + + To avoid this, and allow incremental generation of requests, you can + instead a group and set a feeder on it that generates those + requests. The feed callback will be called whenever there are few + enough (see "limit", below) requests active in the group itself and + is expected to queue more requests. + + The feed callback can queue as many requests as it likes (i.e. "add" + does not impose any limits). + + If the feed does not queue more requests when called, it will be + automatically removed from the group. + + If the feed limit is 0 when this method is called, it will be set to + 2 automatically. + + Example: + + # stat all files in @files, but only ever use four aio requests concurrently: + + my $grp = aio_group sub { print "finished\n" }; + limit $grp 4; + feed $grp sub { + my $file = pop @files + or return; + + add $grp aio_stat $file, sub { ... }; + }; + + limit $grp $num + Sets the feeder limit for the group: The feeder will be called + whenever the group contains less than this many requests. + + Setting the limit to 0 will pause the feeding process. + + The default value for the limit is 0, but note that setting a feeder + automatically bumps it up to 2. + SUPPORT FUNCTIONS + EVENT PROCESSING AND EVENT LOOP INTEGRATION $fileno = IO::AIO::poll_fileno - Return the *request result pipe filehandle*. This filehandle must be - polled for reading by some mechanism outside this module (e.g. Event - or select, see below). If the pipe becomes readable you have to call - "poll_cb" to check the results. + Return the *request result pipe file descriptor*. This filehandle + must be polled for reading by some mechanism outside this module + (e.g. Event or select, see below or the SYNOPSIS). If the pipe + becomes readable you have to call "poll_cb" to check the results. See "poll_cb" for an example. IO::AIO::poll_cb - Process all outstanding events on the result pipe. You have to call - this regularly. Returns the number of events processed. Returns - immediately when no events are outstanding. + Process some outstanding events on the result pipe. You have to call + this regularly. Returns 0 if all events could be processed, or -1 if + it returned earlier for whatever reason. Returns immediately when no + events are outstanding. The amount of events processed depends on + the settings of "IO::AIO::max_poll_req" and + "IO::AIO::max_poll_time". + + If not all requests were processed for whatever reason, the + filehandle will still be ready when "poll_cb" returns, so normally + you don't have to do anything special to have it called later. - You can use Event to multiplex, e.g.: + Example: Install an Event watcher that automatically calls + IO::AIO::poll_cb with high priority: Event->io (fd => IO::AIO::poll_fileno, poll => 'r', async => 1, cb => \&IO::AIO::poll_cb); + IO::AIO::max_poll_reqs $nreqs + IO::AIO::max_poll_time $seconds + These set the maximum number of requests (default 0, meaning + infinity) that are being processed by "IO::AIO::poll_cb" in one + call, respectively the maximum amount of time (default 0, meaning + infinity) spent in "IO::AIO::poll_cb" to process requests (more + correctly the mininum amount of time "poll_cb" is allowed to use). + + Setting "max_poll_time" to a non-zero value creates an overhead of + one syscall per request processed, which is not normally a problem + unless your callbacks are really really fast or your OS is really + really slow (I am not mentioning Solaris here). Using + "max_poll_reqs" incurs no overhead. + + Setting these is useful if you want to ensure some level of + interactiveness when perl is not fast enough to process all requests + in time. + + For interactive programs, values such as 0.01 to 0.1 should be fine. + + Example: Install an Event watcher that automatically calls + IO::AIO::poll_cb with low priority, to ensure that other parts of + the program get the CPU sometimes even under high AIO load. + + # try not to spend much more than 0.1s in poll_cb + IO::AIO::max_poll_time 0.1; + + # use a low priority so other tasks have priority + Event->io (fd => IO::AIO::poll_fileno, + poll => 'r', nice => 1, + cb => &IO::AIO::poll_cb); + IO::AIO::poll_wait - Wait till the result filehandle becomes ready for reading (simply - does a select on the filehandle. This is useful if you want to - synchronously wait for some requests to finish). + If there are any outstanding requests and none of them in the result + phase, wait till the result filehandle becomes ready for reading + (simply does a "select" on the filehandle. This is useful if you + want to synchronously wait for some requests to finish). See "nreqs" for an example. - IO::AIO::nreqs - Returns the number of requests currently outstanding. + IO::AIO::poll + Waits until some requests have been handled. - Example: wait till there are no outstanding requests anymore: + Returns the number of requests processed, but is otherwise strictly + equivalent to: + + IO::AIO::poll_wait, IO::AIO::poll_cb + + IO::AIO::flush + Wait till all outstanding AIO requests have been handled. + + Strictly equivalent to: IO::AIO::poll_wait, IO::AIO::poll_cb while IO::AIO::nreqs; + CONTROLLING THE NUMBER OF THREADS IO::AIO::min_parallel $nthreads - Set the minimum number of AIO threads to $nthreads. The default is - 1, which means a single asynchronous operation can be done at one - time (the number of outstanding operations, however, is unlimited). - - It is recommended to keep the number of threads low, as some Linux - kernel versions will scale negatively with the number of threads - (higher parallelity => MUCH higher latency). With current Linux 2.6 - versions, 4-32 threads should be fine. - - Under normal circumstances you don't need to call this function, as - this module automatically starts some threads (the exact number - might change, and is currently 4). + Set the minimum number of AIO threads to $nthreads. The current + default is 8, which means eight asynchronous operations can execute + concurrently at any one time (the number of outstanding requests, + however, is unlimited). + + IO::AIO starts threads only on demand, when an AIO request is queued + and no free thread exists. Please note that queueing up a hundred + requests can create demand for a hundred threads, even if it turns + out that everything is in the cache and could have been processed + faster by a single thread. + + It is recommended to keep the number of threads relatively low, as + some Linux kernel versions will scale negatively with the number of + threads (higher parallelity => MUCH higher latency). With current + Linux 2.6 versions, 4-32 threads should be fine. + + Under most circumstances you don't need to call this function, as + the module selects a default that is suitable for low to moderate + load. IO::AIO::max_parallel $nthreads Sets the maximum number of AIO threads to $nthreads. If more than - the specified number of threads are currently running, kill them. - This function blocks until the limit is reached. + the specified number of threads are currently running, this function + kills them. This function blocks until the limit is reached. + + While $nthreads are zero, aio requests get queued but not executed + until the number of threads has been increased again. This module automatically runs "max_parallel 0" at program end, to ensure that all threads are killed and that there are no outstanding @@ -214,19 +863,97 @@ Under normal circumstances you don't need to call this function. - $oldnreqs = IO::AIO::max_outstanding $nreqs - Sets the maximum number of outstanding requests to $nreqs. If you - try to queue up more than this number of requests, the caller will - block until some requests have been handled. - - The default is very large, so normally there is no practical limit. - If you queue up many requests in a loop it it often improves speed - if you set this to a relatively low number, such as 100. + IO::AIO::max_idle $nthreads + Limit the number of threads (default: 4) that are allowed to idle + (i.e., threads that did not get a request to process within 10 + seconds). That means if a thread becomes idle while $nthreads other + threads are also idle, it will free its resources and exit. + + This is useful when you allow a large number of threads (e.g. 100 or + 1000) to allow for extremely high load situations, but want to free + resources under normal circumstances (1000 threads can easily + consume 30MB of RAM). + + The default is probably ok in most situations, especially if thread + creation is fast. If thread creation is very slow on your system you + might want to use larger values. + + IO::AIO::max_outstanding $maxreqs + This is a very bad function to use in interactive programs because + it blocks, and a bad way to reduce concurrency because it is + inexact: Better use an "aio_group" together with a feed callback. + + Sets the maximum number of outstanding requests to $nreqs. If you do + queue up more than this number of requests, the next call to the + "poll_cb" (and "poll_some" and other functions calling "poll_cb") + function will block until the limit is no longer exceeded. + + The default value is very large, so there is no practical limit on + the number of outstanding requests. + + You can still queue as many requests as you want. Therefore, + "max_outstanding" is mainly useful in simple scripts (with low + values) or as a stop gap to shield against fatal memory overflow + (with large values). - Under normal circumstances you don't need to call this function. + STATISTICAL INFORMATION + IO::AIO::nreqs + Returns the number of requests currently in the ready, execute or + pending states (i.e. for which their callback has not been invoked + yet). + + Example: wait till there are no outstanding requests anymore: + + IO::AIO::poll_wait, IO::AIO::poll_cb + while IO::AIO::nreqs; + + IO::AIO::nready + Returns the number of requests currently in the ready state (not yet + executed). + + IO::AIO::npending + Returns the number of requests currently in the pending state + (executed, but not yet processed by poll_cb). + + FORK BEHAVIOUR + This module should do "the right thing" when the process using it forks: + + Before the fork, IO::AIO enters a quiescent state where no requests can + be added in other threads and no results will be processed. After the + fork the parent simply leaves the quiescent state and continues + request/result processing, while the child frees the request/result + queue (so that the requests started before the fork will only be handled + in the parent). Threads will be started on demand until the limit set in + the parent process has been reached again. + + In short: the parent will, after a short pause, continue as if fork had + not been called, while the child will act as if IO::AIO has not been + used yet. + + MEMORY USAGE + Per-request usage: + + Each aio request uses - depending on your architecture - around 100-200 + bytes of memory. In addition, stat requests need a stat buffer (possibly + a few hundred bytes), readdir requires a result buffer and so on. Perl + scalars and other data passed into aio requests will also be locked and + will consume memory till the request has entered the done state. + + This is not awfully much, so queuing lots of requests is not usually a + problem. + + Per-thread usage: + + In the execution phase, some aio requests require more memory for + temporary buffers, and each thread requires a stack and other data + structures (usually around 16k-128k, depending on the OS). + +KNOWN BUGS + Known bugs will be fixed in the next release. SEE ALSO - Coro, Linux::AIO. + AnyEvent::AIO for easy integration into event loops, Coro::AIO for a + more natural syntax. AUTHOR Marc Lehmann