--- IO-AIO/README 2007/01/06 02:47:11 1.22 +++ IO-AIO/README 2009/08/05 11:53:16 1.39 @@ -26,9 +26,11 @@ my $grp = aio_group sub { print "all stats done\n" }; add $grp aio_stat "..." for ...; - # AnyEvent integration - open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; - my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb }); + # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) + use AnyEvent::AIO; + + # EV integration + my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; # Event integration Event->io (fd => IO::AIO::poll_fileno, @@ -49,7 +51,8 @@ DESCRIPTION This module implements asynchronous I/O using whatever means your - operating system supports. + operating system supports. It is implemented as an interface to "libeio" + (). Asynchronous means that operations that can normally block your program (e.g. reading from disk) will be done asynchronously: the operation will @@ -63,10 +66,9 @@ 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 - or might not work (aio_read fails on sockets/pipes/fifos). Use an event - loop for that (such as the Event module): IO::AIO will naturally fit - into such an event loop itself. + nonblocking operation (again, sockets, pipes etc.) is very inefficient. + Use an event loop for that (such as the EV 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 @@ -78,23 +80,21 @@ 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 (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. + 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: + This is a simple example that uses the EV module and loads /etc/passwd + asynchronously: use Fcntl; - use Event; + use EV; use IO::AIO; - # register the IO::AIO callback with Event - Event->io (fd => IO::AIO::poll_fileno, - poll => 'r', - cb => \&IO::AIO::poll_cb); + # register the IO::AIO callback with EV + my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; # queue the request to open /etc/passwd aio_open "/etc/passwd", O_RDONLY, 0, sub { @@ -116,7 +116,7 @@ print $contents; # exit event loop and program - Event::unloop; + EV::unloop; }; }; @@ -124,7 +124,7 @@ # check for sockets etc. etc. # process events as long as there are some: - Event::loop; + EV::loop; REQUEST ANATOMY AND LIFETIME Every "aio_*" function creates a request. which is a C data structure @@ -176,8 +176,8 @@ 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 it's sole - argument when the given syscall has been executed asynchronously. + 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. @@ -200,7 +200,7 @@ contents. This works, btw. independent of the internal UTF-8 bit, which IO::AIO - handles correctly wether it is set or not. + 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 @@ -244,7 +244,9 @@ 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). + 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: @@ -259,24 +261,42 @@ 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 - another time when the filehandle is destroyed. Normally, you can - safely call perls "close" or just let filehandles go out of scope. + code. + + 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). - This is supposed to be a bug in the API, so that might change. It's - therefore best to avoid this function. + 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 + Reads or writes $length bytes from or to 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). + "aio_read" will, like "sysread", shrink or grow the $data scalar to + offset plus the actual number of bytes read. + + 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 WW3 (if the - necessary/optional hardware is installed). + 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: @@ -344,6 +364,40 @@ print "size is ", -s _, "\n"; }; + 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. @@ -375,6 +429,11 @@ 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. @@ -384,8 +443,69 @@ 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. + The callback is passed a single argument which is either "undef" or + an array-ref with the filenames. + + aio_readdirx $pathname, $flags, $callback->($entries, $flags) + Quite similar to "aio_readdir", but the $flags argument allows to + tune behaviour and output format. In case of an error, $entries will + be "undef". + + The flags are a combination of the following constants, ORed + together (the flags will also be passed to the callback, possibly + modified): + + IO::AIO::READDIR_DENTS + When this flag is off, then the callback gets an arrayref with + of names only (as with "aio_readdir"), otherwise it gets an + arrayref with "[$name, $type, $inode]" arrayrefs, each + describing a single directory entry in more detail. + + $name is the name of the entry. + + $type is one of the "IO::AIO::DT_xxx" constants: + + "IO::AIO::DT_UNKNOWN", "IO::AIO::DT_FIFO", "IO::AIO::DT_CHR", + "IO::AIO::DT_DIR", "IO::AIO::DT_BLK", "IO::AIO::DT_REG", + "IO::AIO::DT_LNK", "IO::AIO::DT_SOCK", "IO::AIO::DT_WHT". + + "IO::AIO::DT_UNKNOWN" means just that: readdir does not know. If + you need to know, you have to run stat yourself. Also, for speed + reasons, the $type scalars are read-only: you can not modify + them. + + $inode is the inode number (which might not be exact on systems + with 64 bit inode numbers and 32 bit perls). This field has + unspecified content on systems that do not deliver the inode + information. + + IO::AIO::READDIR_DIRS_FIRST + When this flag is set, then the names will be returned in an + order where likely directories come first. This is useful when + you need to quickly find directories, or you want to find all + directories while avoiding to stat() each entry. + + If the system returns type information in readdir, then this is + used to find directories directly. Otherwise, likely directories + are files beginning with ".", or otherwise files with no dots, + of which files with short names are tried first. + + IO::AIO::READDIR_STAT_ORDER + When this flag is set, then the names will be returned in an + order suitable for stat()'ing each one. That is, when you plan + to stat() all files in the given directory, then the returned + order will likely be fastest. + + If both this flag and "IO::AIO::READDIR_DIRS_FIRST" are + specified, then the likely dirs come first, resulting in a less + optimal stat order. + + IO::AIO::READDIR_FOUND_UNKNOWN + This flag should not be set when calling "aio_readdirx". + Instead, it is being set by "aio_readdirx", when any of the + $type's found were "IO::AIO::DT_UNKNOWN". The absense of this + flag therefore indicates that all $type's are known, which can + be used to speed up some algorithms. aio_load $path, $data, $callback->($status) This is a composite request that tries to fully load the given file @@ -396,10 +516,10 @@ or destination) from $srcpath to $dstpath and call the callback with the 0 (error) or -1 ok. - This is a composite request that it 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. + 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 @@ -410,9 +530,9 @@ 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 files with "EXDEV", it copies the file with "aio_copy" - and, if that is successful, unlinking the $srcpath. + 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 @@ -442,20 +562,26 @@ 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 readdir returns file type information, then this is used directly + to find directories. + + Otherwise, 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 a non-initial + dot currently) and likely non-directories (see "aio_readdirx"). Then + every entry plus an appended "/." will be "stat"'ed, likely + directories first, in order of their inode numbers. 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), even on systems that cannot return the filetype + information on readdir. If the known number of directories (link count - 2) has been reached, the rest of the entries is assumed to be non-directories. @@ -467,6 +593,15 @@ 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. @@ -478,6 +613,31 @@ 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_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) + Sync the data portion of the file specified by $offset and $length + to disk (but NOT the metadata), by calling the Linux-specific + sync_file_range call. If sync_file_range is not available or it + returns ENOSYS, then fdatasync or fsync is being substituted. + + $flags can be a combination of + "IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE", + "IO::AIO::SYNC_FILE_RANGE_WRITE" and + "IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER": refer to the sync_file_range + manpage for details. + + 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. + + Future versions of this function might fall back to other methods + when "fsync" on the directory fails (such as calling "sync"). + + 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 @@ -529,9 +689,9 @@ 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. + request otherwise untouched (with the exception of readdir). 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. @@ -568,23 +728,27 @@ 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). + * 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. - 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. + 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 (...) @@ -601,7 +765,7 @@ $grp->result (...) Set the result value(s) that will be passed to the group callback - when all subrequests have finished and set thre groups errno to the + 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. @@ -637,7 +801,8 @@ If the feed does not queue more requests when called, it will be automatically removed from the group. - If the feed limit is 0, it will be set to 2 automatically. + If the feed limit is 0 when this method is called, it will be set to + 2 automatically. Example: @@ -658,28 +823,35 @@ 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 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. + (e.g. EV, Glib, select and so on, 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 some 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. The amount of events - processed depends on the settings of "IO::AIO::max_poll_req" and + 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. + filehandle will still be ready when "poll_cb" returns, so normally + you don't have to do anything special to have it called later. Example: Install an Event watcher that automatically calls - IO::AIO::poll_cb with high priority: + IO::AIO::poll_cb with high priority (more examples can be found in + the SYNOPSIS section, at the top of this document): Event->io (fd => IO::AIO::poll_fileno, poll => 'r', async => 1, @@ -792,12 +964,12 @@ creation is fast. If thread creation is very slow on your system you might want to use larger values. - $oldmaxreqs = IO::AIO::max_outstanding $maxreqs + 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 to + 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. @@ -806,7 +978,7 @@ the number of outstanding requests. You can still queue as many requests as you want. Therefore, - "max_oustsanding" is mainly useful in simple scripts (with low + "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). @@ -829,6 +1001,28 @@ Returns the number of requests currently in the pending state (executed, but not yet processed by poll_cb). + MISCELLANEOUS FUNCTIONS + IO::AIO implements some functions that might be useful, but are not + asynchronous. + + IO::AIO::sendfile $ofh, $ifh, $offset, $count + Calls the "eio_sendfile_sync" function, which is like + "aio_sendfile", but is blocking (this makes most sense if you know + the input data is likely cached already and the output filehandle is + set to non-blocking operations). + + Returns the number of bytes copied, or -1 on error. + + IO::AIO::fadvise $fh, $offset, $len, $advice + Simply calls the "posix_fadvise" function (see it's manpage for + details). The following advice constants are avaiable: + "IO::AIO::FADV_NORMAL", "IO::AIO::FADV_SEQUENTIAL", + "IO::AIO::FADV_RANDOM", "IO::AIO::FADV_NOREUSE", + "IO::AIO::FADV_WILLNEED", "IO::AIO::FADV_DONTNEED". + + On systems that do not implement "posix_fadvise", this function + returns ENOSYS, otherwise the return value of "posix_fadvise". + FORK BEHAVIOUR This module should do "the right thing" when the process using it forks: @@ -853,7 +1047,7 @@ 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 now awfully much, so queuing lots of requests is not usually a + This is not awfully much, so queuing lots of requests is not usually a problem. Per-thread usage: @@ -866,7 +1060,8 @@ Known bugs will be fixed in the next release. SEE ALSO - Coro::AIO. + AnyEvent::AIO for easy integration into event loops, Coro::AIO for a + more natural syntax. AUTHOR Marc Lehmann