From da0bddd3a5c573cd4623d1c95ebf4ee6dd87ed27 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@yhbt.net>
Date: Fri, 24 Jan 2020 09:43:52 +0000
Subject: wwwstatic: wire up buffer bypass for -httpd

This prevents public-inbox-httpd from buffering ->getline
results from a static file into another temporary file when
writing to slow clients.  Instead we inject the static file
ref with offsets and length directly into the {wbuf} queue.

It took me a while to decide to go this route, some
rejected ideas:

1. Using Plack::Util::set_io_path and having PublicInbox::HTTP
   serve the result directly.  This is compatible with what
   some other PSGI servers do using sendfile.  However, neither
   Starman or Twiggy currently use sendfile for partial responses.

2. Parsing the Content-Range response header for offsets and
   lengths to use with set_io_path for partial responses.

These rejected ideas required increasing the complexity of HTTP
response writing in PublicInbox::HTTP in the common, non-static
file cases.  Instead, we made minor changes to the colder write
buffering path of PublicInbox::DS and leave the hot paths
untouched.

We still support generic PSGI servers via ->getline.  However,
since we don't know the characteristics of other PSGI servers,
we no longer do a 64K initial read in an attempt to negotiate a
larger TCP window.
---
 lib/PublicInbox/WwwStatic.pm | 48 +++++++++++++++++++++++++++++---------------
 1 file changed, 32 insertions(+), 16 deletions(-)

(limited to 'lib/PublicInbox/WwwStatic.pm')

diff --git a/lib/PublicInbox/WwwStatic.pm b/lib/PublicInbox/WwwStatic.pm
index e1f536f3..60a71d8d 100644
--- a/lib/PublicInbox/WwwStatic.pm
+++ b/lib/PublicInbox/WwwStatic.pm
@@ -51,7 +51,19 @@ sub r ($;$) {
 	  [ $msg ] ]
 }
 
-sub prepare_range {
+sub getline_response ($$$$$) {
+	my ($env, $in, $off, $len, $path) = @_;
+	my $r = bless {}, __PACKAGE__;
+	if ($env->{'pi-httpd.async'}) { # public-inbox-httpd-only mode
+		$env->{'psgix.no-compress'} = 1; # do not chunk response
+		%$r = ( bypass => [$in, $off, $len, $env->{'psgix.io'}] );
+	} else {
+		%$r = ( in => $in, off => $off, len => $len, path => $path );
+	}
+	$r;
+}
+
+sub setup_range {
 	my ($env, $in, $h, $beg, $end, $size) = @_;
 	my $code = 200;
 	my $len = $size;
@@ -81,9 +93,6 @@ sub prepare_range {
 		if ($len <= 0) {
 			$code = 416;
 		} else {
-			if ($in) {
-				sysseek($in, $beg, SEEK_SET) or return r(500);
-			}
 			push @$h, qw(Accept-Ranges bytes Content-Range);
 			push @$h, "bytes $beg-$end/$size";
 
@@ -95,7 +104,7 @@ sub prepare_range {
 		push @$h, 'Content-Range', "bytes */$size";
 		return [ 416, $h, [] ];
 	}
-	($code, $len);
+	($code, $beg, $len);
 }
 
 # returns a PSGI arrayref response iff .gz and non-.gz mtimes match
@@ -142,30 +151,37 @@ sub response ($$$;$) {
 	my $len = $size;
 	my $code = 200;
 	push @$h, 'Content-Type', $type;
+	my $off = 0;
 	if (($env->{HTTP_RANGE} || '') =~ /\bbytes=([0-9]*)-([0-9]*)\z/) {
-		($code, $len) = prepare_range($env, $in, $h, $1, $2, $size);
+		($code, $off, $len) = setup_range($env, $in, $h, $1, $2, $size);
 		return $code if ref($code);
 	}
 	push @$h, 'Content-Length', $len, 'Last-Modified', $mtime;
-	my $body = $in ? bless {
-		initial_rd => 65536,
-		len => $len,
-		in => $in,
-		path => $path,
-		env => $env,
-	}, __PACKAGE__ : [];
-	[ $code, $h, $body ];
+	[ $code, $h, $in ? getline_response($env, $in, $off, $len, $path) : [] ]
 }
 
 # called by PSGI servers on each response chunk:
 sub getline {
 	my ($self) = @_;
+
+	# avoid buffering, by becoming the buffer! (public-inbox-httpd)
+	if (my $tmpio = delete $self->{bypass}) {
+		my $http = pop @$tmpio; # PublicInbox::HTTP
+		push @{$http->{wbuf}}, $tmpio; # [ $in, $off, $len ]
+		$http->flush_write;
+		return; # undef, EOF
+	}
+
+	# generic PSGI runs this:
 	my $len = $self->{len} or return; # undef, tells server we're done
-	my $n = delete($self->{initial_rd}) // 8192;
+	my $n = 8192;
 	$n = $len if $len < $n;
-	my $r = sysread($self->{in}, my $buf, $n);
+	seek($self->{in}, $self->{off}, SEEK_SET) or
+			die "seek ($self->{path}): $!";
+	my $r = read($self->{in}, my $buf, $n);
 	if (defined $r && $r > 0) { # success!
 		$self->{len} = $len - $r;
+		$self->{off} += $r;
 		return $buf;
 	}
 	my $m = defined $r ? "EOF with $len bytes left" : "read error: $!";
-- 
cgit v1.2.3-24-ge0c7