--- Coro/Coro.pm 2007/01/12 01:15:03 1.109 +++ Coro/Coro.pm 2008/11/20 06:32:55 1.229 @@ -4,44 +4,61 @@ =head1 SYNOPSIS - use Coro; - - async { - # some asynchronous thread of execution - }; - - # alternatively create an async coroutine like this: - - sub some_func : Coro { - # some more async code - } - - cede; + use Coro; + + async { + # some asynchronous thread of execution + print "2\n"; + cede; # yield back to main + print "4\n"; + }; + print "1\n"; + cede; # yield to coroutine + print "3\n"; + cede; # and again + + # use locking + use Coro::Semaphore; + my $lock = new Coro::Semaphore; + my $locked; + + $lock->down; + $locked = 1; + $lock->up; =head1 DESCRIPTION -This module collection manages coroutines. Coroutines are similar -to threads but don't run in parallel at the same time even on SMP -machines. The specific flavor of coroutine use din this module also -guarentees you that it will not switch between coroutines unless +This module collection manages coroutines. Coroutines are similar to +threads but don't (in general) run in parallel at the same time even +on SMP machines. The specific flavor of coroutine used in this module +also guarantees you that it will not switch between coroutines unless necessary, at easily-identified points in your program, so locking and parallel access are rarely an issue, making coroutine programming much -safer than threads programming. +safer and easier than threads programming. -(Perl, however, does not natively support real threads but instead does a -very slow and memory-intensive emulation of processes using threads. This -is a performance win on Windows machines, and a loss everywhere else). +Unlike a normal perl program, however, coroutines allow you to have +multiple running interpreters that share data, which is especially useful +to code pseudo-parallel processes and for event-based programming, such as +multiple HTTP-GET requests running concurrently. See L to +learn more. + +Coroutines are also useful because Perl has no support for threads (the so +called "threads" that perl offers are nothing more than the (bad) process +emulation coming from the Windows platform: On standard operating systems +they serve no purpose whatsoever, except by making your programs slow and +making them use a lot of memory. Best disable them when building perl, or +aks your software vendor/distributor to do it for you). In this module, coroutines are defined as "callchain + lexical variables + @_ + $_ + $@ + $/ + C stack), that is, a coroutine has its own callchain, its own set of lexicals and its own set of perls most important global -variables. +variables (see L for more configuration). =cut package Coro; -use strict; +use strict qw(vars subs); no warnings "uninitialized"; use Coro::State; @@ -52,7 +69,7 @@ our $main; # main coroutine our $current; # current coroutine -our $VERSION = '3.3'; +our $VERSION = 5.0; our @EXPORT = qw(async async_pool cede schedule terminate current unblock_sub); our %EXPORT_TAGS = ( @@ -60,81 +77,58 @@ ); our @EXPORT_OK = (@{$EXPORT_TAGS{prio}}, qw(nready)); -{ - my @async; - my $init; - - # this way of handling attributes simply is NOT scalable ;() - sub import { - no strict 'refs'; - - Coro->export_to_level (1, @_); - - my $old = *{(caller)[0]."::MODIFY_CODE_ATTRIBUTES"}{CODE}; - *{(caller)[0]."::MODIFY_CODE_ATTRIBUTES"} = sub { - my ($package, $ref) = (shift, shift); - my @attrs; - for (@_) { - if ($_ eq "Coro") { - push @async, $ref; - unless ($init++) { - eval q{ - sub INIT { - &async(pop @async) while @async; - } - }; - } - } else { - push @attrs, $_; - } - } - return $old ? $old->($package, $ref, @attrs) : @attrs; - }; - } - -} - =over 4 -=item $main +=item $Coro::main -This coroutine represents the main program. +This variable stores the coroutine object that represents the main +program. While you cna C it and do most other things you can do to +coroutines, it is mainly useful to compare again C<$Coro::current>, to see +whether you are running in the main program or not. =cut -$main = new Coro; +# $main is now being initialised by Coro::State -=item $current (or as function: current) +=item $Coro::current -The current coroutine (the last coroutine switched to). The initial value -is C<$main> (of course). +The coroutine object representing the current coroutine (the last +coroutine that the Coro scheduler switched to). The initial value is +C<$Coro::main> (of course). -This variable is B I. It is provided for performance -reasons. If performance is not essentiel you are encouraged to use the -C function instead. +This variable is B I. You can take copies of the +value stored in it and use it as any other coroutine object, but you must +not otherwise modify the variable itself. =cut -# maybe some other module used Coro::Specific before... -$main->{specific} = $current->{specific} - if $current; +sub current() { $current } # [DEPRECATED] -_set_current $main; +=item $Coro::idle -sub current() { $current } +This variable is mainly useful to integrate Coro into event loops. It is +usually better to rely on L or LC, as this is +pretty low-level functionality. -=item $idle - -A callback that is called whenever the scheduler finds no ready coroutines -to run. The default implementation prints "FATAL: deadlock detected" and -exits, because the program has no other way to continue. +This variable stores a callback that is called whenever the scheduler +finds no ready coroutines to run. The default implementation prints +"FATAL: deadlock detected" and exits, because the program has no other way +to continue. This hook is overwritten by modules such as C and -C to wait on an external event that hopefully wake up a +C to wait on an external event that hopefully wake up a coroutine so the scheduler can run it. +Note that the callback I, under any circumstances, block +the current coroutine. Normally, this is achieved by having an "idle +coroutine" that calls the event loop and then blocks again, and then +readying that coroutine in the idle handler. + +See L or L for examples of using this +technique. + Please note that if your callback recursively invokes perl (e.g. for event -handlers), then it must be prepared to be called recursively. +handlers), then it must be prepared to be called recursively itself. =cut @@ -151,14 +145,14 @@ or return; # call all destruction callbacks - $_->(@{$self->{status}}) - for @{(delete $self->{destroy_cb}) || []}; + $_->(@{$self->{_status}}) + for @{ delete $self->{_on_destroy} || [] }; } # this coroutine is necessary because a coroutine # cannot destroy itself. -my @destroy; -my $manager; +our @destroy; +our $manager; $manager = new Coro sub { while () { @@ -168,31 +162,39 @@ &schedule; } }; - +$manager->{desc} = "[coro manager]"; $manager->prio (PRIO_MAX); -# static methods. not really. - =back -=head2 STATIC METHODS - -Static methods are actually functions that operate on the current coroutine only. +=head2 SIMPLE COROUTINE CREATION =over 4 =item async { ... } [@args...] -Create a new asynchronous coroutine and return it's coroutine object -(usually unused). When the sub returns the new coroutine is automatically +Create a new coroutine and return it's coroutine object (usually +unused). The coroutine will be put into the ready queue, so +it will start running automatically on the next scheduler run. + +The first argument is a codeblock/closure that should be executed in the +coroutine. When it returns argument returns the coroutine is automatically terminated. -Calling C in a coroutine will not work correctly, so do not do that. +The remaining arguments are passed as arguments to the closure. -When the coroutine dies, the program will exit, just as in the main -program. +See the C constructor for info about the coroutine +environment in which coroutines are executed. + +Calling C in a coroutine will do the same as calling exit outside +the coroutine. Likewise, when the coroutine dies, the program will exit, +just as it would in the main program. + +If you do not want that, you can provide a default C handler, or +simply avoid dieing (by use of C). + +Example: Create a new coroutine that just prints its arguments. - # create a new coroutine that just prints its arguments async { print "@_\n"; } 1,2,3,4; @@ -208,148 +210,169 @@ =item async_pool { ... } [@args...] Similar to C, but uses a coroutine pool, so you should not call -terminate or join (although you are allowed to), and you get a coroutine -that might have executed other code already (which can be good or bad :). +terminate or join on it (although you are allowed to), and you get a +coroutine that might have executed other code already (which can be good +or bad :). + +On the plus side, this function is about twice as fast as creating (and +destroying) a completely new coroutine, so if you need a lot of generic +coroutines in quick successsion, use C, not C. -Also, the block is executed in an C context and a warning will be +The code block is executed in an C context and a warning will be issued in case of an exception instead of terminating the program, as C does. As the coroutine is being reused, stuff like C will not work in the expected way, unless you call terminate or cancel, -which somehow defeats the purpose of pooling. +which somehow defeats the purpose of pooling (but is fine in the +exceptional case). -The priority will be reset to C<0> after each job, otherwise the coroutine -will be re-used "as-is". - -The pool size is limited to 8 idle coroutines (this can be adjusted by -changing $Coro::POOL_SIZE), and there can be as many non-idle coros as -required. +The priority will be reset to C<0> after each run, tracing will be +disabled, the description will be reset and the default output filehandle +gets restored, so you can change all these. Otherwise the coroutine will +be re-used "as-is": most notably if you change other per-coroutine global +stuff such as C<$/> you I revert that change, which is most +simply done by using local as in: C<< local $/ >>. + +The idle pool size is limited to C<8> idle coroutines (this can be +adjusted by changing $Coro::POOL_SIZE), but there can be as many non-idle +coros as required. If you are concerned about pooled coroutines growing a lot because a -single C used a lot of stackspace you can e.g. C once per second or so to slowly replenish the pool. +single C used a lot of stackspace you can e.g. C once per second or so to slowly replenish the pool. In +addition to that, when the stacks used by a handler grows larger than 16kb +(adjustable via $Coro::POOL_RSS) it will also be destroyed. =cut our $POOL_SIZE = 8; -our @pool; +our $POOL_RSS = 16 * 1024; +our @async_pool; sub pool_handler { while () { eval { - my ($cb, @arg) = @{ delete $current->{_invoke} }; - $cb->(@arg); + &{&_pool_handler} while 1; }; - warn $@ if $@; - - last if @pool >= $POOL_SIZE; - push @pool, $current; - $current->prio (0); - schedule; + warn $@ if $@; } } -sub async_pool(&@) { - # this is also inlined into the unlock_scheduler - my $coro = (pop @pool or new Coro \&pool_handler); - - $coro->{_invoke} = [@_]; - $coro->ready; - - $coro -} +=back -=item schedule +=head2 STATIC METHODS -Calls the scheduler. Please note that the current coroutine will not be put -into the ready queue, so calling this function usually means you will -never be called again unless something else (e.g. an event handler) calls -ready. +Static methods are actually functions that operate on the current coroutine. -The canonical way to wait on external events is this: +=over 4 - { - # remember current coroutine - my $current = $Coro::current; +=item schedule - # register a hypothetical event handler - on_event_invoke sub { - # wake up sleeping coroutine - $current->ready; - undef $current; - }; +Calls the scheduler. The scheduler will find the next coroutine that is +to be run from the ready queue and switches to it. The next coroutine +to be run is simply the one with the highest priority that is longest +in its ready queue. If there is no coroutine ready, it will clal the +C<$Coro::idle> hook. + +Please note that the current coroutine will I be put into the ready +queue, so calling this function usually means you will never be called +again unless something else (e.g. an event handler) calls C<< ->ready >>, +thus waking you up. + +This makes C I generic method to use to block the current +coroutine and wait for events: first you remember the current coroutine in +a variable, then arrange for some callback of yours to call C<< ->ready +>> on that once some event happens, and last you call C to put +yourself to sleep. Note that a lot of things can wake your coroutine up, +so you need to check whether the event indeed happened, e.g. by storing the +status in a variable. - # call schedule until event occured. - # in case we are woken up for other reasons - # (current still defined), loop. - Coro::schedule while $current; - } +See B, below, for some ways to wait for callbacks. =item cede -"Cede" to other coroutines. This function puts the current coroutine into the -ready queue and calls C, which has the effect of giving up the -current "timeslice" to other coroutines of the same or higher priority. +"Cede" to other coroutines. This function puts the current coroutine into +the ready queue and calls C, which has the effect of giving +up the current "timeslice" to other coroutines of the same or higher +priority. Once your coroutine gets its turn again it will automatically be +resumed. -Returns true if at least one coroutine switch has happened. +This function is often called C in other languages. =item Coro::cede_notself -Works like cede, but is not exported by default and will cede to any -coroutine, regardless of priority, once. - -Returns true if at least one coroutine switch has happened. +Works like cede, but is not exported by default and will cede to I +coroutine, regardless of priority. This is useful sometimes to ensure +progress is made. =item terminate [arg...] Terminates the current coroutine with the given status values (see L). +=item killall + +Kills/terminates/cancels all coroutines except the currently running +one. This is useful after a fork, either in the child or the parent, as +usually only one of them should inherit the running coroutines. + +Note that while this will try to free some of the main programs resources, +you cannot free all of them, so if a coroutine that is not the main +program calls this function, there will be some one-time resource leak. + =cut sub terminate { - $current->cancel (@_); + $current->{_status} = [@_]; + push @destroy, $current; + $manager->ready; + do { &schedule } while 1; } -=back +sub killall { + for (Coro::State::list) { + $_->cancel + if $_ != $current && UNIVERSAL::isa $_, "Coro"; + } +} -# dynamic methods +=back =head2 COROUTINE METHODS -These are the methods you can call on coroutine objects. +These are the methods you can call on coroutine objects (or to create +them). =over 4 =item new Coro \&sub [, @args...] -Create a new coroutine and return it. When the sub returns the coroutine +Create a new coroutine and return it. When the sub returns, the coroutine automatically terminates as if C with the returned values were -called. To make the coroutine run you must first put it into the ready queue -by calling the ready method. +called. To make the coroutine run you must first put it into the ready +queue by calling the ready method. -Calling C in a coroutine will not work correctly, so do not do that. +See C and C for additional info about the +coroutine environment. =cut -sub _run_coro { +sub _terminate { terminate &{+shift}; } -sub new { - my $class = shift; - - $class->SUPER::new (\&_run_coro, @_) -} - =item $success = $coroutine->ready -Put the given coroutine into the ready queue (according to it's priority) -and return true. If the coroutine is already in the ready queue, do nothing -and return false. +Put the given coroutine into the end of its ready queue (there is one +queue for each priority) and return true. If the coroutine is already in +the ready queue, do nothing and return false. + +This ensures that the scheduler will resume this coroutine automatically +once all the coroutines of higher priority and all coroutines of the same +priority that were put into the ready queue earlier have been resumed. =item $is_ready = $coroutine->is_ready -Return wether the coroutine is currently the ready queue or not, +Return whether the coroutine is currently the ready queue or not, =item $coroutine->cancel (arg...) @@ -361,32 +384,73 @@ sub cancel { my $self = shift; - $self->{status} = [@_]; if ($current == $self) { - push @destroy, $self; - $manager->ready; - &schedule while 1; + terminate @_; } else { + $self->{_status} = [@_]; $self->_cancel; } } +=item $coroutine->schedule_to + +Puts the current coroutine to sleep (like C), but instead +of continuing with the next coro from the ready queue, always switch to +the given coroutine object (regardless of priority etc.). The readyness +state of that coroutine isn't changed. + +This is an advanced method for special cases - I'd love to hear about any +uses for this one. + +=item $coroutine->cede_to + +Like C, but puts the current coroutine into the ready +queue. This has the effect of temporarily switching to the given +coroutine, and continuing some time later. + +This is an advanced method for special cases - I'd love to hear about any +uses for this one. + +=item $coroutine->throw ([$scalar]) + +If C<$throw> is specified and defined, it will be thrown as an exception +inside the coroutine at the next convenient point in time. Otherwise +clears the exception object. + +Coro will check for the exception each time a schedule-like-function +returns, i.e. after each C, C, C<< Coro::Semaphore->down +>>, C<< Coro::Handle->readable >> and so on. Most of these functions +detect this case and return early in case an exception is pending. + +The exception object will be thrown "as is" with the specified scalar in +C<$@>, i.e. if it is a string, no line number or newline will be appended +(unlike with C). + +This can be used as a softer means than C to ask a coroutine to +end itself, although there is no guarantee that the exception will lead to +termination, and if the exception isn't caught it might well end the whole +program. + +You might also think of C as being the moral equivalent of +Cing a coroutine with a signal (in this case, a scalar). + =item $coroutine->join Wait until the coroutine terminates and return any values given to the -C or C functions. C can be called multiple times -from multiple coroutine. +C or C functions. C can be called concurrently +from multiple coroutines, and all will be resumed and given the status +return once the C<$coroutine> terminates. =cut sub join { my $self = shift; - unless ($self->{status}) { + unless ($self->{_status}) { my $current = $current; - push @{$self->{destroy_cb}}, sub { + push @{$self->{_on_destroy}}, sub { $current->ready; undef $current; }; @@ -394,21 +458,21 @@ &schedule while $current; } - wantarray ? @{$self->{status}} : $self->{status}[0]; + wantarray ? @{$self->{_status}} : $self->{_status}[0]; } =item $coroutine->on_destroy (\&cb) Registers a callback that is called when this coroutine gets destroyed, but before it is joined. The callback gets passed the terminate arguments, -if any. +if any, and I die, under any circumstances. =cut sub on_destroy { my ($self, $cb) = @_; - push @{ $self->{destroy_cb} }, $cb; + push @{ $self->{_on_destroy} }, $cb; } =item $oldprio = $coroutine->prio ($newprio) @@ -441,7 +505,11 @@ =item $olddesc = $coroutine->desc ($newdesc) Sets (or gets in case the argument is missing) the description for this -coroutine. This is just a free-form string you can associate with a coroutine. +coroutine. This is just a free-form string you can associate with a +coroutine. + +This method simply sets the C<< $coroutine->{desc} >> member to the given +string. You can modify this member directly if you wish. =cut @@ -460,14 +528,15 @@ =item Coro::nready Returns the number of coroutines that are currently in the ready state, -i.e. that can be swicthed to. The value C<0> means that the only runnable -coroutine is the currently running one, so C would have no effect, -and C would cause a deadlock unless there is an idle handler -that wakes up some coroutines. +i.e. that can be switched to by calling C directory or +indirectly. The value C<0> means that the only runnable coroutine is the +currently running one, so C would have no effect, and C +would cause a deadlock unless there is an idle handler that wakes up some +coroutines. =item my $guard = Coro::guard { ... } -This creates and returns a guard object. Nothing happens until the objetc +This creates and returns a guard object. Nothing happens until the object gets destroyed, in which case the codeblock given as argument will be executed. This is useful to free locks or other resources in case of a runtime error or when the coroutine gets canceled, as in both cases the @@ -502,23 +571,35 @@ =item unblock_sub { ... } This utility function takes a BLOCK or code reference and "unblocks" it, -returning the new coderef. This means that the new coderef will return -immediately without blocking, returning nothing, while the original code -ref will be called (with parameters) from within its own coroutine. +returning a new coderef. Unblocking means that calling the new coderef +will return immediately without blocking, returning nothing, while the +original code ref will be called (with parameters) from within another +coroutine. -The reason this fucntion exists is that many event libraries (such as the +The reason this function exists is that many event libraries (such as the venerable L module) are not coroutine-safe (a weaker form of thread-safety). This means you must not block within event callbacks, -otherwise you might suffer from crashes or worse. +otherwise you might suffer from crashes or worse. The only event library +currently known that is safe to use without C is L. This function allows your callbacks to block by executing them in another coroutine where it is safe to block. One example where blocking is handy is when you use the L functions to save results to -disk. +disk, for example. In short: simply use C instead of C when creating event callbacks that want to block. +If your handler does not plan to block (e.g. simply sends a message to +another coroutine, or puts some other coroutine into the ready queue), +there is no reason to use C. + +Note that you also need to use C for any other callbacks that +are indirectly executed by any C-based event loop. For example, when you +use a module that uses L (and you use L) and it +provides callbacks that are the result of some event callback, then you +must not block either, or use C. + =cut our @unblock_queue; @@ -527,19 +608,20 @@ # to reduce pressure on the coro pool (because most callbacks # return immediately and can be reused) and because we cannot cede # inside an event callback. -our $unblock_scheduler = async { +our $unblock_scheduler = new Coro sub { while () { while (my $cb = pop @unblock_queue) { - # this is an inlined copy of async_pool - my $coro = (pop @pool or new Coro \&pool_handler); + &async_pool (@$cb); - $coro->{_invoke} = $cb; - $coro->ready; - cede; # for short-lived callbacks, this reduces pressure on the coro pool + # for short-lived callbacks, this reduces pressure on the coro pool + # as the chance is very high that the async_poll coro will be back + # in the idle state when cede returns + cede; } schedule; # sleep well } }; +$unblock_scheduler->{desc} = "[unblock_sub scheduler]"; sub unblock_sub(&) { my $cb = shift; @@ -550,31 +632,147 @@ } } +=item $cb = Coro::rouse_cb + +Create and return a "rouse callback". That's a code reference that, when +called, will save its arguments and notify the owner coroutine of the +callback. + +See the next function. + +=item @args = Coro::rouse_wait [$cb] + +Wait for the specified rouse callback (or the last one tht was created in +this coroutine). + +As soon as the callback is invoked (or when the calback was invoked before +C), it will return a copy of the arguments originally passed +to the rouse callback. + +See the section B for an actual usage example. + =back =cut 1; +=head1 HOW TO WAIT FOR A CALLBACK + +It is very common for a coroutine to wait for some callback to be +called. This occurs naturally when you use coroutines in an otherwise +event-based program, or when you use event-based libraries. + +These typically register a callback for some event, and call that callback +when the event occured. In a coroutine, however, you typically want to +just wait for the event, simplyifying things. + +For example C<< AnyEvent->child >> registers a callback to be called when +a specific child has exited: + + my $child_watcher = AnyEvent->child (pid => $pid, cb => sub { ... }); + +But from withina coroutine, you often just want to write this: + + my $status = wait_for_child $pid; + +Coro offers two functions specifically designed to make this easy, +C and C. + +The first function, C, generates and returns a callback that, +when invoked, will save it's arguments and notify the coroutine that +created the callback. + +The second function, C, waits for the callback to be called +(by calling C to go to sleep) and returns the arguments +originally passed to the callback. + +Using these functions, it becomes easy to write the C +function mentioned above: + + sub wait_for_child($) { + my ($pid) = @_; + + my $watcher = AnyEvent->child (pid => $pid, cb => Coro::rouse_cb); + + my ($rpid, $rstatus) = Coro::rouse_wait; + $rstatus + } + +In the case where C and C are not flexible enough, +you can roll your own, using C: + + sub wait_for_child($) { + my ($pid) = @_; + + # store the current coroutine in $current, + # and provide result variables for the closure passed to ->child + my $current = $Coro::current; + my ($done, $rstatus); + + # pass a closure to ->child + my $watcher = AnyEvent->child (pid => $pid, cb => sub { + $rstatus = $_[1]; # remember rstatus + $done = 1; # mark $rstatus as valud + }); + + # wait until the closure has been called + schedule while !$done; + + $rstatus + } + + =head1 BUGS/LIMITATIONS - - you must make very sure that no coro is still active on global - destruction. very bad things might happen otherwise (usually segfaults). +=over 4 + +=item fork with pthread backend + +When Coro is compiled using the pthread backend (which isn't recommended +but required on many BSDs as their libcs are completely broken), then +coroutines will not survive a fork. There is no known workaround except to +fix your libc and use a saner backend. + +=item perl process emulation ("threads") + +This module is not perl-pseudo-thread-safe. You should only ever use this +module from the same thread (this requirement might be removed in the +future to allow per-thread schedulers, but Coro::State does not yet allow +this). I recommend disabling thread support and using processes, as having +the windows process emulation enabled under unix roughly halves perl +performance, even when not used. + +=item coroutine switching not signal safe + +You must not switch to another coroutine from within a signal handler +(only relevant with %SIG - most event libraries provide safe signals). + +That means you I call any function that might "block" the +current coroutine - C, C C<< Coro::Semaphore->down >> or +anything that calls those. Everything else, including calling C, +works. + +=back - - this module is not thread-safe. You should only ever use this module - from the same thread (this requirement might be losened in the future - to allow per-thread schedulers, but Coro::State does not yet allow - this). =head1 SEE ALSO -Support/Utility: L, L, L, L. +Event-Loop integration: L, L, L. + +Debugging: L. + +Support/Utility: L, L. Locking/IPC: L, L, L, L, L. -Event/IO: L, L, L, L, L. +IO/Timers: L, L, L, L. + +Compatibility: L, L, L, L. + +XS API: L. -Embedding: L +Low level Configuration, Coroutine Environment: L. =head1 AUTHOR