--- Coro/Coro.pm	2003/05/27 01:15:26	1.53
+++ Coro/Coro.pm	2007/01/12 01:15:03	1.109
@@ -10,7 +10,7 @@
     # some asynchronous thread of execution
  };
 
- # alternatively create an async process like this:
+ # alternatively create an async coroutine like this:
 
  sub some_func : Coro {
     # some more async code
@@ -20,31 +20,45 @@
 
 =head1 DESCRIPTION
 
-This module collection manages coroutines. Coroutines are similar to
-threads but don't run in parallel.
-
-In this module, coroutines are defined as "callchain + lexical variables
-+ @_ + $_ + $@ + $^W + C stack), that is, a coroutine has it's own
-callchain, it's own set of lexicals and it's own set of perl's most
-important global variables.
+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
+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.
+
+(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).
+
+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.
 
 =cut
 
 package Coro;
 
-no warnings qw(uninitialized);
+use strict;
+no warnings "uninitialized";
 
 use Coro::State;
 
-use base Exporter;
+use base qw(Coro::State Exporter);
+
+our $idle;    # idle handler
+our $main;    # main coroutine
+our $current; # current coroutine
 
-$VERSION = 0.7;
+our $VERSION = '3.3';
 
-@EXPORT = qw(async cede schedule terminate current);
-%EXPORT_TAGS = (
+our @EXPORT = qw(async async_pool cede schedule terminate current unblock_sub);
+our %EXPORT_TAGS = (
       prio => [qw(PRIO_MAX PRIO_HIGH PRIO_NORMAL PRIO_LOW PRIO_IDLE PRIO_MIN)],
 );
-@EXPORT_OK = @{$EXPORT_TAGS{prio}};
+our @EXPORT_OK = (@{$EXPORT_TAGS{prio}}, qw(nready));
 
 {
    my @async;
@@ -52,7 +66,10 @@
 
    # this way of handling attributes simply is NOT scalable ;()
    sub import {
-      Coro->export_to_level(1, @_);
+      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);
@@ -85,191 +102,320 @@
 
 =cut
 
-our $main = new Coro;
+$main = new Coro;
 
 =item $current (or as function: current)
 
-The current coroutine (the last coroutine switched to). The initial value is C<$main> (of course).
+The current coroutine (the last coroutine switched to). The initial value
+is C<$main> (of course).
+
+This variable is B<strictly> I<read-only>. It is provided for performance
+reasons. If performance is not essentiel you are encouraged to use the
+C<Coro::current> function instead.
 
 =cut
 
 # maybe some other module used Coro::Specific before...
-if ($current) {
-   $main->{specific} = $current->{specific};
-}
+$main->{specific} = $current->{specific}
+   if $current;
 
-our $current = $main;
+_set_current $main;
 
 sub current() { $current }
 
 =item $idle
 
-The coroutine to switch to when no other coroutine is running. The default
-implementation prints "FATAL: deadlock detected" and exits.
+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<Coro::Timer> and
+C<Coro::Event> to wait on an external event that hopefully wake up a
+coroutine so the scheduler can run it.
+
+Please note that if your callback recursively invokes perl (e.g. for event
+handlers), then it must be prepared to be called recursively.
 
 =cut
 
-# should be done using priorities :(
-our $idle = new Coro sub {
-   print STDERR "FATAL: deadlock detected\n";
-   exit(51);
+$idle = sub {
+   require Carp;
+   Carp::croak ("FATAL: deadlock detected");
 };
 
+sub _cancel {
+   my ($self) = @_;
+
+   # free coroutine data and mark as destructed
+   $self->_destroy
+      or return;
+
+   # call all destruction callbacks
+   $_->(@{$self->{status}})
+      for @{(delete $self->{destroy_cb}) || []};
+}
+
 # this coroutine is necessary because a coroutine
 # cannot destroy itself.
 my @destroy;
 my $manager;
+
 $manager = new Coro sub {
-   while() {
-      # by overwriting the state object with the manager we destroy it
-      # while still being able to schedule this coroutine (in case it has
-      # been readied multiple times. this is harmless since the manager
-      # can be called as many times as neccessary and will always
-      # remove itself from the runqueue
-      while (@destroy) {
-         my $coro = pop @destroy;
-         $coro->{status} ||= [];
-         $_->ready for @{delete $coro->{join} || []};
-         $coro->{_coro_state} = $manager->{_coro_state};
-      }
+   while () {
+      (shift @destroy)->_cancel
+         while @destroy;
+
       &schedule;
    }
 };
 
+$manager->prio (PRIO_MAX);
+
 # static methods. not really.
 
 =back
 
 =head2 STATIC METHODS
 
-Static methods are actually functions that operate on the current process only.
+Static methods are actually functions that operate on the current coroutine only.
 
 =over 4
 
 =item async { ... } [@args...]
 
-Create a new asynchronous process and return it's process object
-(usually unused). When the sub returns the new process is automatically
+Create a new asynchronous coroutine and return it's coroutine object
+(usually unused). When the sub returns the new coroutine is automatically
 terminated.
 
+Calling C<exit> in a coroutine will not work correctly, so do not do that.
+
+When the coroutine dies, the program will exit, just as in the main
+program.
+
    # create a new coroutine that just prints its arguments
    async {
       print "@_\n";
    } 1,2,3,4;
 
-The coderef you submit MUST NOT be a closure that refers to variables
-in an outer scope. This does NOT work. Pass arguments into it instead.
-
 =cut
 
 sub async(&@) {
-   my $pid = new Coro @_;
-   $manager->ready; # this ensures that the stack is cloned from the manager
-   $pid->ready;
-   $pid;
+   my $coro = new Coro @_;
+   $coro->ready;
+   $coro
+}
+
+=item async_pool { ... } [@args...]
+
+Similar to C<async>, 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 :).
+
+Also, the block is executed in an C<eval> context and a warning will be
+issued in case of an exception instead of terminating the program, as
+C<async> does. As the coroutine is being reused, stuff like C<on_destroy>
+will not work in the expected way, unless you call terminate or cancel,
+which somehow defeats the purpose of pooling.
+
+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.
+
+If you are concerned about pooled coroutines growing a lot because a
+single C<async_pool> used a lot of stackspace you can e.g. C<async_pool {
+terminate }> once per second or so to slowly replenish the pool.
+
+=cut
+
+our $POOL_SIZE = 8;
+our @pool;
+
+sub pool_handler {
+   while () {
+      eval {
+         my ($cb, @arg) = @{ delete $current->{_invoke} };
+         $cb->(@arg);
+      };
+      warn $@ if $@;
+
+      last if @pool >= $POOL_SIZE;
+      push @pool, $current;
+
+      $current->prio (0);
+      schedule;
+   }
+}
+
+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
 }
 
 =item schedule
 
-Calls the scheduler. Please note that the current process will not be put
+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.
+never be called again unless something else (e.g. an event handler) calls
+ready.
 
-=cut
+The canonical way to wait on external events is this:
+
+   {
+      # remember current coroutine
+      my $current = $Coro::current;
+
+      # register a hypothetical event handler
+      on_event_invoke sub {
+         # wake up sleeping coroutine
+         $current->ready;
+         undef $current;
+      };
+
+      # call schedule until event occured.
+      # in case we are woken up for other reasons
+      # (current still defined), loop.
+      Coro::schedule while $current;
+   }
 
 =item cede
 
-"Cede" to other processes. This function puts the current process into the
+"Cede" to other coroutines. This function puts the current coroutine into the
 ready queue and calls C<schedule>, which has the effect of giving up the
 current "timeslice" to other coroutines of the same or higher priority.
 
-=cut
+Returns true if at least one coroutine switch has happened.
 
-=item terminate [arg...]
+=item Coro::cede_notself
 
-Terminates the current process.
+Works like cede, but is not exported by default and will cede to any
+coroutine, regardless of priority, once.
 
-Future versions of this function will allow result arguments.
+Returns true if at least one coroutine switch has happened.
+
+=item terminate [arg...]
+
+Terminates the current coroutine with the given status values (see L<cancel>).
 
 =cut
 
 sub terminate {
-   $current->{status} = [@_];
-   $current->cancel;
-   &schedule;
-   die; # NORETURN
+   $current->cancel (@_);
 }
 
 =back
 
 # dynamic methods
 
-=head2 PROCESS METHODS
+=head2 COROUTINE METHODS
 
-These are the methods you can call on process objects.
+These are the methods you can call on coroutine objects.
 
 =over 4
 
 =item new Coro \&sub [, @args...]
 
-Create a new process and return it. When the sub returns the process
+Create a new coroutine and return it. When the sub returns the coroutine
 automatically terminates as if C<terminate> with the returned values were
-called. To make the process run you must first put it into the ready queue
+called. To make the coroutine run you must first put it into the ready queue
 by calling the ready method.
 
+Calling C<exit> in a coroutine will not work correctly, so do not do that.
+
 =cut
 
-sub _newcoro {
+sub _run_coro {
    terminate &{+shift};
 }
 
 sub new {
    my $class = shift;
-   bless {
-      _coro_state => (new Coro::State $_[0] && \&_newcoro, @_),
-   }, $class;
+
+   $class->SUPER::new (\&_run_coro, @_)
 }
 
-=item $process->ready
+=item $success = $coroutine->ready
 
-Put the given process into the ready queue.
+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.
 
-=cut
+=item $is_ready = $coroutine->is_ready
+
+Return wether the coroutine is currently the ready queue or not,
 
-=item $process->cancel
+=item $coroutine->cancel (arg...)
 
-Like C<terminate>, but terminates the specified process instead.
+Terminates the given coroutine and makes it return the given arguments as
+status (default: the empty list). Never returns if the coroutine is the
+current coroutine.
 
 =cut
 
 sub cancel {
-   push @destroy, $_[0];
-   $manager->ready;
-   &schedule if $current == $_[0];
+   my $self = shift;
+   $self->{status} = [@_];
+
+   if ($current == $self) {
+      push @destroy, $self;
+      $manager->ready;
+      &schedule while 1;
+   } else {
+      $self->_cancel;
+   }
 }
 
-=item $process->join
+=item $coroutine->join
 
 Wait until the coroutine terminates and return any values given to the
-C<terminate> function. C<join> can be called multiple times from multiple
-processes.
+C<terminate> or C<cancel> functions. C<join> can be called multiple times
+from multiple coroutine.
 
 =cut
 
 sub join {
    my $self = shift;
+
    unless ($self->{status}) {
-      push @{$self->{join}}, $current;
-      &schedule;
+      my $current = $current;
+
+      push @{$self->{destroy_cb}}, sub {
+         $current->ready;
+         undef $current;
+      };
+
+      &schedule while $current;
    }
+
    wantarray ? @{$self->{status}} : $self->{status}[0];
 }
 
-=item $oldprio = $process->prio($newprio)
+=item $coroutine->on_destroy (\&cb)
+
+Registers a callback that is called when this coroutine gets destroyed,
+but before it is joined. The callback gets passed the terminate arguments,
+if any.
+
+=cut
+
+sub on_destroy {
+   my ($self, $cb) = @_;
+
+   push @{ $self->{destroy_cb} }, $cb;
+}
+
+=item $oldprio = $coroutine->prio ($newprio)
 
 Sets (or gets, if the argument is missing) the priority of the
-process. Higher priority processes get run before lower priority
-processes. Priorities are small signed integers (currently -4 .. +3),
+coroutine. Higher priority coroutines get run before lower priority
+coroutines. Priorities are small signed integers (currently -4 .. +3),
 that you can refer to using PRIO_xxx constants (use the import tag :prio
 to get then):
 
@@ -282,41 +428,126 @@
 The idle coroutine ($Coro::idle) always has a lower priority than any
 existing coroutine.
 
-Changing the priority of the current process will take effect immediately,
-but changing the priority of processes in the ready queue (but not
+Changing the priority of the current coroutine will take effect immediately,
+but changing the priority of coroutines in the ready queue (but not
 running) will only take effect after the next schedule (of that
-process). This is a bug that will be fixed in some future version.
+coroutine). This is a bug that will be fixed in some future version.
+
+=item $newprio = $coroutine->nice ($change)
+
+Similar to C<prio>, but subtract the given value from the priority (i.e.
+higher values mean lower priority, just as in unix).
+
+=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.
 
 =cut
 
-sub prio {
-   my $old = $_[0]{prio};
-   $_[0]{prio} = $_[1] if @_ > 1;
+sub desc {
+   my $old = $_[0]{desc};
+   $_[0]{desc} = $_[1] if @_ > 1;
    $old;
 }
 
-=item $newprio = $process->nice($change)
+=back
 
-Similar to C<prio>, but subtract the given value from the priority (i.e.
-higher values mean lower priority, just as in unix).
+=head2 GLOBAL FUNCTIONS
+
+=over 4
+
+=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<cede> would have no effect,
+and C<schedule> 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
+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
+guard block will be executed. The guard object supports only one method,
+C<< ->cancel >>, which will keep the codeblock from being executed.
+
+Example: set some flag and clear it again when the coroutine gets canceled
+or the function returns:
+
+   sub do_something {
+      my $guard = Coro::guard { $busy = 0 };
+      $busy = 1;
+
+      # do something that requires $busy to be true
+   }
 
 =cut
 
-sub nice {
-   $_[0]{prio} -= $_[1];
+sub guard(&) {
+   bless \(my $cb = $_[0]), "Coro::guard"
 }
 
-=item $olddesc = $process->desc($newdesc)
+sub Coro::guard::cancel {
+   ${$_[0]} = sub { };
+}
+
+sub Coro::guard::DESTROY {
+   ${$_[0]}->();
+}
 
-Sets (or gets in case the argument is missing) the description for this
-process. This is just a free-form string you can associate with a process.
+
+=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.
+
+The reason this fucntion exists is that many event libraries (such as the
+venerable L<Event|Event> 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.
+
+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<Coro::AIO|Coro::AIO> functions to save results to
+disk.
+
+In short: simply use C<unblock_sub { ... }> instead of C<sub { ... }> when
+creating event callbacks that want to block.
 
 =cut
 
-sub desc {
-   my $old = $_[0]{desc};
-   $_[0]{desc} = $_[1] if @_ > 1;
-   $old;
+our @unblock_queue;
+
+# we create a special coro because we want to cede,
+# 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 {
+   while () {
+      while (my $cb = pop @unblock_queue) {
+         # this is an inlined copy of async_pool
+         my $coro = (pop @pool or new Coro \&pool_handler);
+
+         $coro->{_invoke} = $cb;
+         $coro->ready;
+         cede; # for short-lived callbacks, this reduces pressure on the coro pool
+      }
+      schedule; # sleep well
+   }
+};
+
+sub unblock_sub(&) {
+   my $cb = shift;
+
+   sub {
+      unshift @unblock_queue, [$cb, @_];
+      $unblock_scheduler->ready;
+   }
 }
 
 =back
@@ -337,14 +568,18 @@
 
 =head1 SEE ALSO
 
-L<Coro::Channel>, L<Coro::Cont>, L<Coro::Specific>, L<Coro::Semaphore>,
-L<Coro::Signal>, L<Coro::State>, L<Coro::Event>, L<Coro::RWLock>,
-L<Coro::Handle>, L<Coro::Socket>.
+Support/Utility: L<Coro::Cont>, L<Coro::Specific>, L<Coro::State>, L<Coro::Util>.
+
+Locking/IPC: L<Coro::Signal>, L<Coro::Channel>, L<Coro::Semaphore>, L<Coro::SemaphoreSet>, L<Coro::RWLock>.
+
+Event/IO: L<Coro::Timer>, L<Coro::Event>, L<Coro::Handle>, L<Coro::Socket>, L<Coro::Select>.
+
+Embedding: L<Coro:MakeMaker>
 
 =head1 AUTHOR
 
- Marc Lehmann <pcg@goof.com>
- http://www.goof.com/pcg/marc/
+ Marc Lehmann <schmorp@schmorp.de>
+ http://home.schmorp.de/
 
 =cut