X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FHTTP.pm;h=3dd49be30ca7dc1330491b5b875e37384fdf7181;hb=3d41aa23f35501ca92aab8aa42980fa73f7fa74f;hp=00c9a0444bf75e63689d60893d6b3e236c1ca264;hpb=74bbc3da398d00ba12e9294e360ad177ab2061ed;p=public-inbox.git

diff --git a/lib/PublicInbox/HTTP.pm b/lib/PublicInbox/HTTP.pm
index 00c9a044..3dd49be3 100644
--- a/lib/PublicInbox/HTTP.pm
+++ b/lib/PublicInbox/HTTP.pm
@@ -1,22 +1,22 @@
-# Copyright (C) 2016 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2018 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # Generic PSGI server for convenience.  It aims to provide
 # a consistent experience for public-inbox admins so they don't have
 # to learn different ways to admin both NNTP and HTTP components.
-# There's nothing public-inbox-specific, here.
+# There's nothing which depends on public-inbox, here.
 # Each instance of this class represents a HTTP client socket
 
 package PublicInbox::HTTP;
 use strict;
 use warnings;
 use base qw(Danga::Socket);
-use fields qw(httpd env rbuf input_left remote_addr remote_port forward);
+use fields qw(httpd env rbuf input_left remote_addr remote_port forward pull);
 use Fcntl qw(:seek);
 use Plack::HTTPParser qw(parse_http_request); # XS or pure Perl
 use HTTP::Status qw(status_message);
 use HTTP::Date qw(time2str);
-use IO::File;
+use IO::Handle;
 use constant {
 	CHUNK_START => -1,   # [a-f0-9]+\r\n
 	CHUNK_END => -2,     # \r\n
@@ -24,22 +24,16 @@ use constant {
 	CHUNK_MAX_HDR => 256,
 };
 
-# FIXME: duplicated code with NNTP.pm
-my $WEAKEN = {}; # string(inbox) -> inbox
-my $weakt;
-sub weaken_task () {
-	$weakt = undef;
-	$_->weaken_all for values %$WEAKEN;
-	$WEAKEN = {};
-}
-
 my $pipelineq = [];
 my $pipet;
 sub process_pipelineq () {
 	my $q = $pipelineq;
 	$pipet = undef;
 	$pipelineq = [];
-	rbuf_process($_) foreach @$q;
+	foreach (@$q) {
+		next if $_->{closed};
+		rbuf_process($_);
+	}
 }
 
 # Use the same configuration parameter as git since this is primarily
@@ -48,7 +42,7 @@ sub process_pipelineq () {
 our $MAX_REQUEST_BUFFER = $ENV{GIT_HTTP_MAX_REQUEST_BUFFER} ||
 			(10 * 1024 * 1024);
 
-my $null_io = IO::File->new('/dev/null', '<');
+open(my $null_io, '<', '/dev/null') or die "failed to open /dev/null: $!";
 my $http_date;
 my $prev = 0;
 sub http_date () {
@@ -103,7 +97,7 @@ sub rbuf_process {
 	$self->{rbuf} = substr($self->{rbuf}, $r);
 
 	my $len = input_prepare($self, \%env);
-	defined $len or return write_err($self); # EMFILE/ENFILE
+	defined $len or return write_err($self, undef); # EMFILE/ENFILE
 
 	$len ? event_read_input($self) : app_dispatch($self);
 }
@@ -123,7 +117,7 @@ sub event_read_input ($) {
 	while ($len > 0) {
 		if ($$rbuf ne '') {
 			my $w = write_in_full($input, $rbuf, $len);
-			return write_err($self) unless $w;
+			return write_err($self, $len) unless $w;
 			$len -= $w;
 			die "BUG: $len < 0 (w=$w)" if $len < 0;
 			if ($len == 0) { # next request may be pipelined
@@ -219,7 +213,10 @@ sub chunked_wcb ($) {
 		return if $_[0] eq '';
 		more($self, sprintf("%x\r\n", bytes::length($_[0])));
 		more($self, $_[0]);
-		$self->write("\r\n");
+
+		# use $self->write("\n\n") if you care about real-time
+		# streaming responses, public-inbox WWW does not.
+		more($self, "\r\n");
 	}
 }
 
@@ -228,46 +225,83 @@ sub identity_wcb ($) {
 	sub { $self->write(\($_[0])) if $_[0] ne '' }
 }
 
-sub response_write {
-	my ($self, $env, $res) = @_;
-	my $alive = response_header_write($self, $env, $res);
+sub next_request ($) {
+	my ($self) = @_;
+	$self->watch_write(0);
+	if ($self->{rbuf} eq '') { # wait for next request
+		$self->watch_read(1);
+	} else { # avoid recursion for pipelined requests
+		push @$pipelineq, $self;
+		$pipet ||= PublicInbox::EvCleanup::asap(*process_pipelineq);
+	}
+}
 
-	my $write = $alive == 2 ? chunked_wcb($self) : identity_wcb($self);
-	my $close = sub {
+sub response_done_cb ($$) {
+	my ($self, $alive) = @_;
+	sub {
+		my $env = $self->{env};
+		$self->{env} = undef;
 		$self->write("0\r\n\r\n") if $alive == 2;
-		if ($alive) {
-			$self->event_write; # watch for readability if done
-		} else {
-			Danga::Socket::write($self, sub { $self->close });
+		$self->write(sub{$alive ? next_request($self) : $self->close});
+	}
+}
+
+sub getline_cb ($$$) {
+	my ($self, $write, $close) = @_;
+	local $/ = \8192;
+	my $forward = $self->{forward};
+	# limit our own running time for fairness with other
+	# clients and to avoid buffering too much:
+	if ($forward) {
+		my $buf = eval { $forward->getline };
+		if (defined $buf) {
+			$write->($buf); # may close in Danga::Socket::write
+			unless ($self->{closed}) {
+				my $next = $self->{pull};
+				if ($self->{write_buf_size}) {
+					$self->write($next);
+				} else {
+					PublicInbox::EvCleanup::asap($next);
+				}
+				return;
+			}
+		} elsif ($@) {
+			err($self, "response ->getline error: $@");
+			$forward = undef;
+			$self->close;
 		}
-		if (my $obj = $env->{'pi-httpd.inbox'}) {
-			# grace period for reaping resources
-			$WEAKEN->{"$obj"} = $obj;
-			$weakt ||= PublicInbox::EvCleanup::later(*weaken_task);
+	}
+
+	$self->{forward} = $self->{pull} = undef;
+	# avoid recursion
+	if ($forward) {
+		eval { $forward->close };
+		if ($@) {
+			err($self, "response ->close error: $@");
+			$self->close; # idempotent
 		}
-		$self->{env} = undef;
-	};
+	}
+	$close->();
+}
 
+sub getline_response ($$$) {
+	my ($self, $write, $close) = @_;
+	my $pull = $self->{pull} = sub { getline_cb($self, $write, $close) };
+	$pull->();
+}
+
+sub response_write {
+	my ($self, $env, $res) = @_;
+	my $alive = response_header_write($self, $env, $res);
+	my $close = response_done_cb($self, $alive);
+	my $write = $alive == 2 ? chunked_wcb($self) : identity_wcb($self);
 	if (defined(my $body = $res->[2])) {
 		if (ref $body eq 'ARRAY') {
 			$write->($_) foreach @$body;
 			$close->();
 		} else {
-			my $pull;
-			$pull = sub {
-				local $/ = \8192;
-				while (defined(my $buf = $body->getline)) {
-					$write->($buf);
-					if ($self->{write_buf_size}) {
-						$self->write($pull);
-						return;
-					}
-				}
-				$pull = undef;
-				$body->close();
-				$close->();
-			};
-			$pull->();
+			$self->{forward} = $body;
+			getline_response($self, $write, $close);
 		}
 	} else {
 		# this is returned to the calling application:
@@ -278,6 +312,7 @@ sub response_write {
 use constant MSG_MORE => ($^O eq 'linux') ? 0x8000 : 0;
 sub more ($$) {
 	my $self = $_[0];
+	return if $self->{closed};
 	if (MSG_MORE && !$self->{write_buf_size}) {
 		my $n = send($self->{sock}, $_[1], MSG_MORE);
 		if (defined $n) {
@@ -290,33 +325,21 @@ sub more ($$) {
 	$self->write($_[1]);
 }
 
-# overrides existing Danga::Socket method
-sub event_write {
-	my ($self) = @_;
-	# only continue watching for readability when we are done writing:
-	return if $self->write(undef) != 1;
-
-	if ($self->{rbuf} eq '') { # wait for next request
-		$self->watch_read(1);
-	} else { # avoid recursion for pipelined requests
-		push @$pipelineq, $self;
-		$pipet ||= PublicInbox::EvCleanup::asap(*process_pipelineq);
-	}
-}
-
 sub input_prepare {
 	my ($self, $env) = @_;
-	my $input = $null_io;
+	my $input;
 	my $len = $env->{CONTENT_LENGTH};
 	if ($len) {
 		if ($len > $MAX_REQUEST_BUFFER) {
 			quit($self, 413);
 			return;
 		}
-		$input = IO::File->new_tmpfile;
+		open($input, '+>', undef);
 	} elsif (env_chunked($env)) {
 		$len = CHUNK_START;
-		$input = IO::File->new_tmpfile;
+		open($input, '+>', undef);
+	} else {
+		$input = $null_io;
 	}
 
 	# TODO: expire idle clients on ENFILE / EMFILE
@@ -329,11 +352,15 @@ sub input_prepare {
 
 sub env_chunked { ($_[0]->{HTTP_TRANSFER_ENCODING} || '') =~ /\bchunked\b/i }
 
+sub err ($$) {
+	eval { $_[0]->{httpd}->{env}->{'psgi.errors'}->print($_[1]."\n") };
+}
+
 sub write_err {
-	my ($self) = @_;
-	my $err = $self->{httpd}->{env}->{'psgi.errors'};
+	my ($self, $len) = @_;
 	my $msg = $! || '(zero write)';
-	$err->print("error buffering to input: $msg\n");
+	$msg .= " ($len bytes remaining)" if defined $len;
+	err($self, "error buffering to input: $msg");
 	quit($self, 500);
 }
 
@@ -344,8 +371,7 @@ sub recv_err {
 		$self->{input_left} = $len;
 		return;
 	}
-	my $err = $self->{httpd}->{env}->{'psgi.errors'};
-	$err->print("error reading for input: $! ($len bytes remaining)\n");
+	err($self, "error reading for input: $! ($len bytes remaining)");
 	quit($self, 500);
 }
 
@@ -408,7 +434,7 @@ sub event_read_input_chunked { # unlikely...
 		until ($len <= 0) {
 			if ($$rbuf ne '') {
 				my $w = write_in_full($input, $rbuf, $len);
-				return write_err($self) unless $w;
+				return write_err($self, "$len chunk") if !$w;
 				$len -= $w;
 				if ($len == 0) {
 					# we may have leftover data to parse
@@ -445,8 +471,13 @@ sub event_err { $_[0]->close }
 sub close {
 	my $self = shift;
 	my $forward = $self->{forward};
-	$forward->close if $forward;
-	$self->{forward} = $self->{env} = undef;
+	my $env = $self->{env};
+	delete $env->{'psgix.io'} if $env; # prevent circular references
+	$self->{pull} = $self->{forward} = $self->{env} = undef;
+	if ($forward) {
+		eval { $forward->close };
+		err($self, "forward ->close error: $@") if $@;
+	}
 	$self->SUPER::close(@_);
 }