--- AnyEvent/lib/AnyEvent/Handle.pm 2009/07/24 22:47:04 1.160 +++ AnyEvent/lib/AnyEvent/Handle.pm 2009/09/03 19:48:27 1.185 @@ -1,20 +1,7 @@ -package AnyEvent::Handle; - -use Scalar::Util (); -use Carp (); -use Errno qw(EAGAIN EINTR); - -use AnyEvent (); BEGIN { AnyEvent::common_sense } -use AnyEvent::Util qw(WSAEWOULDBLOCK); - =head1 NAME AnyEvent::Handle - non-blocking I/O on file handles via AnyEvent -=cut - -our $VERSION = 4.86; - =head1 SYNOPSIS use AnyEvent; @@ -61,6 +48,35 @@ All callbacks will be invoked with the handle object as their first argument. +=cut + +package AnyEvent::Handle; + +use Scalar::Util (); +use List::Util (); +use Carp (); +use Errno qw(EAGAIN EINTR); + +use AnyEvent (); BEGIN { AnyEvent::common_sense } +use AnyEvent::Util qw(WSAEWOULDBLOCK); + +our $VERSION = $AnyEvent::VERSION; + +sub _load_func($) { + my $func = $_[0]; + + unless (defined &$func) { + my $pkg = $func; + do { + $pkg =~ s/::[^:]+$// + or return; + eval "require $pkg"; + } until defined &$func; + } + + \&$func +} + =head1 METHODS =over 4 @@ -103,6 +119,10 @@ (as opposed to settings that can be changed when the connection is already established). +The return value of this callback should be the connect timeout value in +seconds (or C<0>, or C, or the empty list, to indicate the default +timeout is to be used). + =item on_connect => $cb->($handle, $host, $port, $retry->()) This callback is called when a connection has been successfully established. @@ -214,10 +234,21 @@ =item timeout => $fractional_seconds -If non-zero, then this enables an "inactivity" timeout: whenever this many -seconds pass without a successful read or write on the underlying file -handle, the C callback will be invoked (and if that one is -missing, a non-fatal C error will be raised). +=item rtimeout => $fractional_seconds + +=item wtimeout => $fractional_seconds + +If non-zero, then these enables an "inactivity" timeout: whenever this +many seconds pass without a successful read or write on the underlying +file handle (or a call to C), the C callback +will be invoked (and if that one is missing, a non-fatal C +error will be raised). + +There are three variants of the timeouts that work fully independent +of each other, for both read and write, just read, and just write: +C, C and C, with corresponding callbacks +C, C and C, and reset functions +C, C, and C. Note that timeout processing is also active when you currently do not have any outstanding read or write requests: If you plan to keep the connection @@ -271,6 +302,38 @@ The default is your opertaing system's default behaviour (most likely enabled), this option explicitly enables or disables it, if possible. +=item keepalive => + +Enables (default disable) the SO_KEEPALIVE option on the stream socket: +normally, TCP connections have no time-out once established, so TCP +conenctions, once established, can stay alive forever even when the other +side has long gone. TCP keepalives are a cheap way to take down long-lived +TCP connections whent he other side becomes unreachable. While the default +is OS-dependent, TCP keepalives usually kick in after around two hours, +and, if the other side doesn't reply, take down the TCP connection some 10 +to 15 minutes later. + +It is harmless to specify this option for file handles that do not support +keepalives, and enabling it on connections that are potentially long-lived +is usually a good idea. + +=item oobinline => + +BSD majorly fucked up the implementation of TCP urgent data. The result +is that almost no OS implements TCP according to the specs, and every OS +implements it slightly differently. + +If you want to handle TCP urgent data, then setting this flag (the default +is enabled) gives you the most portable way of getting urgent data, by +putting it into the stream. + +Since BSD emulation of OOB data on top of TCP's urgent data can have +security implications, AnyEvent::Handle sets this flag automatically +unless explicitly specified. Note that setting this flag after +establishing a connection I be a bit too late (data loss could +already have occured on BSD systems), but at least it will protect you +from most attacks. + =item read_size => The default read block size (the amount of bytes this module will @@ -436,7 +499,7 @@ $self->{on_connect} and $self->{on_connect}($self, $host, $port, sub { - delete @$self{qw(fh _tw _ww _rw _eof _queue rbuf _wbuf tls _tls_rbuf _tls_wbuf)}; + delete @$self{qw(fh _tw _rtw _wtw _ww _rw _eof _queue rbuf _wbuf tls _tls_rbuf _tls_wbuf)}; $self->{_skip_drain_rbuf} = 1; &$retry; }); @@ -446,15 +509,16 @@ $self->{on_connect_error}($self, "$!"); $self->destroy; } else { - $self->fatal ($!, 1); + $self->_error ($!, 1); } } }, sub { local $self->{fh} = $_[0]; - $self->{on_prepare}->($self) - if $self->{on_prepare}; + $self->{on_prepare} + ? $self->{on_prepare}->($self) + : () } ); } @@ -471,15 +535,23 @@ AnyEvent::Util::fh_nonblocking $self->{fh}, 1; - $self->{_activity} = AnyEvent->now; - $self->_timeout; + $self->{_activity} = + $self->{_ractivity} = + $self->{_wactivity} = AE::now; + + $self->timeout (delete $self->{timeout} ) if $self->{timeout}; + $self->rtimeout (delete $self->{rtimeout} ) if $self->{rtimeout}; + $self->wtimeout (delete $self->{wtimeout} ) if $self->{wtimeout}; - $self->no_delay (delete $self->{no_delay}) if exists $self->{no_delay}; + $self->no_delay (delete $self->{no_delay} ) if exists $self->{no_delay} && $self->{no_delay}; + $self->keepalive (delete $self->{keepalive}) if exists $self->{keepalive} && $self->{keepalive}; - $self->starttls (delete $self->{tls}, delete $self->{tls_ctx}) + $self->oobinline (exists $self->{oobinline} ? delete $self->{oobinline} : 1); + + $self->starttls (delete $self->{tls}, delete $self->{tls_ctx}) if $self->{tls}; - $self->on_drain (delete $self->{on_drain}) if $self->{on_drain}; + $self->on_drain (delete $self->{on_drain}) if $self->{on_drain}; $self->start_read if $self->{on_read} || @{ $self->{_queue} }; @@ -487,15 +559,6 @@ $self->_drain_wbuf; } -#sub _shutdown { -# my ($self) = @_; -# -# delete @$self{qw(_tw _rw _ww fh wbuf on_read _queue)}; -# $self->{_eof} = 1; # tell starttls et. al to stop trying -# -# &_freetls; -#} - sub _error { my ($self, $errno, $fatal, $message) = @_; @@ -541,15 +604,17 @@ =item $handle->on_timeout ($cb) -Replace the current C callback, or disables the callback (but -not the timeout) if C<$cb> = C. See the C constructor -argument and method. +=item $handle->on_rtimeout ($cb) + +=item $handle->on_wtimeout ($cb) + +Replace the current C, C or C +callback, or disables the callback (but not the timeout) if C<$cb> = +C. See the C constructor argument and method. =cut -sub on_timeout { - $_[0]{on_timeout} = $_[1]; -} +# see below =item $handle->autocork ($boolean) @@ -574,7 +639,58 @@ eval { local $SIG{__DIE__}; - setsockopt $_[0]{fh}, &Socket::IPPROTO_TCP, &Socket::TCP_NODELAY, int $_[1] + setsockopt $_[0]{fh}, Socket::IPPROTO_TCP (), Socket::TCP_NODELAY (), int $_[1] + if $_[0]{fh}; + }; +} + +=item $handle->keepalive ($boolean) + +Enables or disables the C setting (see constructor argument of +the same name for details). + +=cut + +sub keepalive { + $_[0]{keepalive} = $_[1]; + + eval { + local $SIG{__DIE__}; + setsockopt $_[0]{fh}, Socket::SOL_SOCKET (), Socket::SO_KEEPALIVE (), int $_[1] + if $_[0]{fh}; + }; +} + +=item $handle->oobinline ($boolean) + +Enables or disables the C setting (see constructor argument of +the same name for details). + +=cut + +sub oobinline { + $_[0]{oobinline} = $_[1]; + + eval { + local $SIG{__DIE__}; + setsockopt $_[0]{fh}, Socket::SOL_SOCKET (), Socket::SO_OOBINLINE (), int $_[1] + if $_[0]{fh}; + }; +} + +=item $handle->keepalive ($boolean) + +Enables or disables the C setting (see constructor argument of +the same name for details). + +=cut + +sub keepalive { + $_[0]{keepalive} = $_[1]; + + eval { + local $SIG{__DIE__}; + setsockopt $_[0]{fh}, Socket::SOL_SOCKET (), Socket::SO_KEEPALIVE (), int $_[1] if $_[0]{fh}; }; } @@ -599,58 +715,99 @@ $_[0]{on_stoptls} = $_[1]; } +=item $handle->rbuf_max ($max_octets) + +Configures the C setting (C disables it). + +=cut + +sub rbuf_max { + $_[0]{rbuf_max} = $_[1]; +} + ############################################################################# =item $handle->timeout ($seconds) +=item $handle->rtimeout ($seconds) + +=item $handle->wtimeout ($seconds) + Configures (or disables) the inactivity timeout. +=item $handle->timeout_reset + +=item $handle->rtimeout_reset + +=item $handle->wtimeout_reset + +Reset the activity timeout, as if data was received or sent. + +These methods are cheap to call. + =cut -sub timeout { - my ($self, $timeout) = @_; +for my $dir ("", "r", "w") { + my $timeout = "${dir}timeout"; + my $tw = "_${dir}tw"; + my $on_timeout = "on_${dir}timeout"; + my $activity = "_${dir}activity"; + my $cb; - $self->{timeout} = $timeout; - $self->_timeout; -} + *$on_timeout = sub { + $_[0]{$on_timeout} = $_[1]; + }; -# reset the timeout watcher, as neccessary -# also check for time-outs -sub _timeout { - my ($self) = @_; + *$timeout = sub { + my ($self, $new_value) = @_; - if ($self->{timeout} && $self->{fh}) { - my $NOW = AnyEvent->now; + $self->{$timeout} = $new_value; + delete $self->{$tw}; &$cb; + }; - # when would the timeout trigger? - my $after = $self->{_activity} + $self->{timeout} - $NOW; + *{"${dir}timeout_reset"} = sub { + $_[0]{$activity} = AE::now; + }; - # now or in the past already? - if ($after <= 0) { - $self->{_activity} = $NOW; + # main workhorse: + # reset the timeout watcher, as neccessary + # also check for time-outs + $cb = sub { + my ($self) = @_; + + if ($self->{$timeout} && $self->{fh}) { + my $NOW = AE::now; + + # when would the timeout trigger? + my $after = $self->{$activity} + $self->{$timeout} - $NOW; + + # now or in the past already? + if ($after <= 0) { + $self->{$activity} = $NOW; - if ($self->{on_timeout}) { - $self->{on_timeout}($self); - } else { - $self->_error (Errno::ETIMEDOUT); - } + if ($self->{$on_timeout}) { + $self->{$on_timeout}($self); + } else { + $self->_error (Errno::ETIMEDOUT); + } - # callback could have changed timeout value, optimise - return unless $self->{timeout}; + # callback could have changed timeout value, optimise + return unless $self->{$timeout}; - # calculate new after - $after = $self->{timeout}; - } + # calculate new after + $after = $self->{$timeout}; + } - Scalar::Util::weaken $self; - return unless $self; # ->error could have destroyed $self + Scalar::Util::weaken $self; + return unless $self; # ->error could have destroyed $self - $self->{_tw} ||= AnyEvent->timer (after => $after, cb => sub { - delete $self->{_tw}; - $self->_timeout; - }); - } else { - delete $self->{_tw}; + $self->{$tw} ||= AE::timer $after, 0, sub { + delete $self->{$tw}; + $cb->($self); + }; + } else { + delete $self->{$tw}; + } } } @@ -708,7 +865,7 @@ if (defined $len) { substr $self->{wbuf}, 0, $len, ""; - $self->{_activity} = AnyEvent->now; + $self->{_activity} = $self->{_wactivity} = AE::now; $self->{on_drain}($self) if $self->{low_water_mark} >= (length $self->{wbuf}) + (length $self->{_tls_wbuf}) @@ -724,13 +881,14 @@ $cb->() unless $self->{autocork}; # if still data left in wbuf, we need to poll - $self->{_ww} = AnyEvent->io (fh => $self->{fh}, poll => "w", cb => $cb) + $self->{_ww} = AE::io $self->{fh}, 1, $cb if length $self->{wbuf}; }; } our %WH; +# deprecated sub register_write_type($$) { $WH{$_[0]} = $_[1]; } @@ -741,7 +899,8 @@ if (@_ > 1) { my $type = shift; - @_ = ($WH{$type} or Carp::croak "unsupported type passed to AnyEvent::Handle::push_write") + @_ = ($WH{$type} ||= _load_func "$type\::anyevent_write_type" + or Carp::croak "unsupported/unloadable type '$type' passed to AnyEvent::Handle::push_write") ->($self, @_); } @@ -756,8 +915,11 @@ =item $handle->push_write (type => @args) -Instead of formatting your data yourself, you can also let this module do -the job by specifying a type and type-specific arguments. +Instead of formatting your data yourself, you can also let this module +do the job by specifying a type and type-specific arguments. You +can also specify the (fully qualified) name of a package, in which +case AnyEvent tries to load the package and then expects to find the +C function inside (see "custom write types", below). Predefined types are (if you have ideas for additional types, feel free to drop by and tell us): @@ -824,13 +986,17 @@ =cut +sub json_coder() { + eval { require JSON::XS; JSON::XS->new->utf8 } + || do { require JSON; JSON->new->utf8 } +} + register_write_type json => sub { my ($self, $ref) = @_; - require JSON; + my $json = $self->{json} ||= json_coder; - $self->{json} ? $self->{json}->encode ($ref) - : JSON::encode_json ($ref) + $json->encode ($ref) }; =item storable => $reference @@ -875,17 +1041,37 @@ $self->on_drain (sub { shutdown $_[0]{fh}, 1 }); } -=item AnyEvent::Handle::register_write_type type => $coderef->($handle, @args) +=item custom write types - Package::anyevent_write_type $handle, @args + +Instead of one of the predefined types, you can also specify the name of +a package. AnyEvent will try to load the package and then expects to find +a function named C inside. If it isn't found, it +progressively tries to load the parent package until it either finds the +function (good) or runs out of packages (bad). + +Whenever the given C is used, C will the function with +the handle object and the remaining arguments. + +The function is supposed to return a single octet string that will be +appended to the write buffer, so you cna mentally treat this function as a +"arguments to on-the-wire-format" converter. + +Example: implement a custom write type C that joins the remaining +arguments using the first one. -This function (not method) lets you add your own types to C. -Whenever the given C is used, C will invoke the code -reference with the handle object and the remaining arguments. + $handle->push_write (My::Type => " ", 1,2,3); -The code reference is supposed to return a single octet string that will -be appended to the write buffer. + # uses the following package, which can be defined in the "My::Type" or in + # the "My" modules to be auto-loaded, or just about anywhere when the + # My::Type::anyevent_write_type is defined before invoking it. -Note that this is a function, and all types registered this way will be -global, so try to use unique names. + package My::Type; + + sub anyevent_write_type { + my ($handle, $delim, @args) = @_; + + join $delim, @args + } =cut @@ -978,29 +1164,23 @@ my ($self) = @_; # avoid recursion - return if exists $self->{_skip_drain_rbuf}; + return if $self->{_skip_drain_rbuf}; local $self->{_skip_drain_rbuf} = 1; - if ( - defined $self->{rbuf_max} - && $self->{rbuf_max} < length $self->{rbuf} - ) { - $self->_error (Errno::ENOSPC, 1), return; - } - while () { # we need to use a separate tls read buffer, as we must not receive data while # we are draining the buffer, and this can only happen with TLS. - $self->{rbuf} .= delete $self->{_tls_rbuf} if exists $self->{_tls_rbuf}; + $self->{rbuf} .= delete $self->{_tls_rbuf} + if exists $self->{_tls_rbuf}; my $len = length $self->{rbuf}; if (my $cb = shift @{ $self->{_queue} }) { unless ($cb->($self)) { - if ($self->{_eof}) { - # no progress can be made (not enough data and no data forthcoming) - $self->_error (Errno::EPIPE, 1), return; - } + # no progress can be made + # (not enough data and no data forthcoming) + $self->_error (Errno::EPIPE, 1), return + if $self->{_eof}; unshift @{ $self->{_queue} }, $cb; last; @@ -1030,11 +1210,18 @@ } if ($self->{_eof}) { - if ($self->{on_eof}) { - $self->{on_eof}($self) - } else { - $self->_error (0, 1, "Unexpected end-of-file"); - } + $self->{on_eof} + ? $self->{on_eof}($self) + : $self->_error (0, 1, "Unexpected end-of-file"); + + return; + } + + if ( + defined $self->{rbuf_max} + && $self->{rbuf_max} < length $self->{rbuf} + ) { + $self->_error (Errno::ENOSPC, 1), return; } # may need to restart read watcher @@ -1113,7 +1300,8 @@ if (@_) { my $type = shift; - $cb = ($RH{$type} or Carp::croak "unsupported type passed to AnyEvent::Handle::push_read") + $cb = ($RH{$type} ||= _load_func "$type\::anyevent_read_type" + or Carp::croak "unsupported/unloadable type '$type' passed to AnyEvent::Handle::push_read") ->($self, $cb, @_); } @@ -1132,7 +1320,6 @@ ->($self, $cb, @_); } - unshift @{ $self->{_queue} }, $cb; $self->_drain_rbuf; } @@ -1143,7 +1330,9 @@ Instead of providing a callback that parses the data itself you can chose between a number of predefined parsing formats, for chunks of data, lines -etc. +etc. You can also specify the (fully qualified) name of a package, in +which case AnyEvent tries to load the package and then expects to find the +C function inside (see "custom read types", below). Predefined types are (if you have ideas for additional types, feel free to drop by and tell us): @@ -1393,9 +1582,7 @@ register_read_type json => sub { my ($self, $cb) = @_; - my $json = $self->{json} ||= - eval { require JSON::XS; JSON::XS->new->utf8 } - || do { require JSON; JSON->new->utf8 }; + my $json = $self->{json} ||= json_coder; my $data; my $rbuf = \$self->{rbuf}; @@ -1474,25 +1661,28 @@ =back -=item AnyEvent::Handle::register_read_type type => $coderef->($handle, $cb, @args) - -This function (not method) lets you add your own types to C. - -Whenever the given C is used, C will invoke the code -reference with the handle object, the callback and the remaining -arguments. - -The code reference is supposed to return a callback (usually a closure) -that works as a plain read callback (see C<< ->push_read ($cb) >>). - -It should invoke the passed callback when it is done reading (remember to -pass C<$handle> as first argument as all other callbacks do that). +=item custom read types - Package::anyevent_read_type $handle, $cb, @args -Note that this is a function, and all types registered this way will be -global, so try to use unique names. +Instead of one of the predefined types, you can also specify the name +of a package. AnyEvent will try to load the package and then expects to +find a function named C inside. If it isn't found, it +progressively tries to load the parent package until it either finds the +function (good) or runs out of packages (bad). + +Whenever this type is used, C will invoke the function with the +handle object, the original callback and the remaining arguments. + +The function is supposed to return a callback (usually a closure) that +works as a plain read callback (see C<< ->push_read ($cb) >>), so you can +mentally treat the function as a "configurable read type to read callback" +converter. + +It should invoke the original callback when it is done reading (remember +to pass C<$handle> as first argument as all other callbacks do that, +although there is no strict requirement on this). -For examples, see the source of this module (F, -search for C)). +For examples, see the source of this module (F, search for C)). =item $handle->stop_read @@ -1525,12 +1715,12 @@ unless ($self->{_rw} || $self->{_eof}) { Scalar::Util::weaken $self; - $self->{_rw} = AnyEvent->io (fh => $self->{fh}, poll => "r", cb => sub { + $self->{_rw} = AE::io $self->{fh}, 0, sub { my $rbuf = \($self->{tls} ? my $buf : $self->{rbuf}); my $len = sysread $self->{fh}, $$rbuf, $self->{read_size} || 8192, length $$rbuf; if ($len > 0) { - $self->{_activity} = AnyEvent->now; + $self->{_activity} = $self->{_ractivity} = AE::now; if ($self->{tls}) { Net::SSLeay::BIO_write ($self->{_rbio}, $$rbuf); @@ -1548,7 +1738,7 @@ } elsif ($! != EAGAIN && $! != EINTR && $! != WSAEWOULDBLOCK) { return $self->_error ($!, 1); } - }); + }; } } @@ -1679,7 +1869,7 @@ $ERROR_SYSCALL = Net::SSLeay::ERROR_SYSCALL (); $ERROR_WANT_READ = Net::SSLeay::ERROR_WANT_READ (); - $tls = $self->{tls}; + $tls = delete $self->{tls}; $ctx = $self->{tls_ctx}; local $Carp::CarpLevel = 1; # skip ourselves when creating a new context or session @@ -1718,6 +1908,8 @@ $self->{_rbio} = Net::SSLeay::BIO_new (Net::SSLeay::BIO_s_mem ()); $self->{_wbio} = Net::SSLeay::BIO_new (Net::SSLeay::BIO_s_mem ()); + Net::SSLeay::BIO_write ($self->{_rbio}, delete $self->{rbuf}); + Net::SSLeay::set_bio ($tls, $self->{_rbio}, $self->{_wbio}); $self->{_on_starttls} = sub { $_[0]{on_starttls}(@_) } @@ -1756,7 +1948,7 @@ return unless $self->{tls}; $self->{tls_ctx}->_put_session (delete $self->{tls}) - if ref $self->{tls}; + if $self->{tls} > 0; delete @$self{qw(_rbio _wbio _tls_wbuf _on_starttls)}; } @@ -1774,7 +1966,7 @@ my @linger; - push @linger, AnyEvent->io (fh => $fh, poll => "w", cb => sub { + push @linger, AE::io $fh, 1, sub { my $len = syswrite $fh, $wbuf, length $wbuf; if ($len > 0) { @@ -1782,10 +1974,10 @@ } else { @linger = (); # end } - }); - push @linger, AnyEvent->timer (after => $linger, cb => sub { + }; + push @linger, AE::timer $linger, 0, sub { @linger = (); - }); + }; } } @@ -1793,7 +1985,9 @@ Shuts down the handle object as much as possible - this call ensures that no further callbacks will be invoked and as many resources as possible -will be freed. You must not call any methods on the object afterwards. +will be freed. Any method you will call on the handle object after +destroying it in this way will be silently ignored (and it will return the +empty list). Normally, you can just "forget" any references to an AnyEvent::Handle object and it will simply shut down. This works in fatal error and EOF @@ -1817,6 +2011,11 @@ $self->DESTROY; %$self = (); + bless $self, "AnyEvent::Handle::destroyed"; +} + +sub AnyEvent::Handle::destroyed::AUTOLOAD { + #nop } =item AnyEvent::Handle::TLS_CTX