X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FGzipFilter.pm;h=5f7016730810ea649374ca05140ffa9ba2890478;hb=e3b57fe9f68e80fc85cff46ccec9246b670f1312;hp=6380f50e91f80ebd5e69d69b791cf36d5296e051;hpb=9f9290893bc241c5363d03b2d3c4acd15deb6d71;p=public-inbox.git

diff --git a/lib/PublicInbox/GzipFilter.pm b/lib/PublicInbox/GzipFilter.pm
index 6380f50e..5f701673 100644
--- a/lib/PublicInbox/GzipFilter.pm
+++ b/lib/PublicInbox/GzipFilter.pm
@@ -1,7 +1,16 @@
 # Copyright (C) 2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
-
-# Qspawn filter
+#
+# In public-inbox <=1.5.0, public-inbox-httpd favored "getline"
+# response bodies to take a "pull"-based approach to feeding
+# slow clients (as opposed to a more common "push" model).
+#
+# In newer versions, public-inbox-httpd supports a backpressure-aware
+# pull/push model which also accounts for slow git blob storage.
+# async_next callbacks only run when the DS {wbuf} is drained
+# async_eml callbacks only run when a blob arrives from git.
+#
+# We continue to support getline+close for generic PSGI servers.
 package PublicInbox::GzipFilter;
 use strict;
 use parent qw(Exporter);
@@ -14,12 +23,12 @@ our @EXPORT_OK = qw(gzf_maybe);
 my %OPT = (-WindowBits => 15 + 16, -AppendOutput => 1);
 my @GZIP_HDRS = qw(Vary Accept-Encoding Content-Encoding gzip);
 
-sub new { bless {}, shift }
+sub new { bless {}, shift } # qspawn filter
 
 # for Qspawn if using $env->{'pi-httpd.async'}
 sub attach {
 	my ($self, $http_out) = @_;
-	$self->{http_out} = $http_out;
+	$self->{http_out} = $http_out; # PublicInbox::HTTP::{Chunked,Identity}
 	$self
 }
 
@@ -37,18 +46,16 @@ sub gz_or_noop {
 sub gzf_maybe ($$) { bless { gz => gz_or_noop(@_) }, __PACKAGE__ }
 
 sub psgi_response {
-	my ($self, $code, $res_hdr, $next_cb, $eml_cb) = @_;
+	my ($self, $code, $res_hdr) = @_;
 	my $env = $self->{env};
 	$self->{gz} //= gz_or_noop($res_hdr, $env);
 	if ($env->{'pi-httpd.async'}) {
-		$self->{async_next} = $next_cb;
-		$self->{async_eml} = $eml_cb;
 		my $http = $env->{'psgix.io'}; # PublicInbox::HTTP
 		$http->{forward} = $self;
 		sub {
 			my ($wcb) = @_; # -httpd provided write callback
 			$self->{http_out} = $wcb->([$code, $res_hdr]);
-			$next_cb->($http); # start stepping
+			$self->can('async_next')->($http); # start stepping
 		};
 	} else { # generic PSGI code path
 		[ $code, $res_hdr, $self ];
@@ -138,24 +145,42 @@ sub close {
 	}
 }
 
+sub bail  {
+	my $self = shift;
+	if (my $env = $self->{env}) {
+		eval { $env->{'psgi.errors'}->print(@_, "\n") };
+		warn("E: error printing to psgi.errors: $@", @_) if $@;
+		my $http = $env->{'psgix.io'} or return; # client abort
+		eval { $http->close }; # should hit our close
+		warn "E: error in http->close: $@" if $@;
+		eval { $self->close }; # just in case...
+		warn "E: error in self->close: $@" if $@;
+	} else {
+		warn @_, "\n";
+	}
+}
+
 # this is public-inbox-httpd-specific
 sub async_blob_cb { # git->cat_async callback
 	my ($bref, $oid, $type, $size, $self) = @_;
-	my $http = $self->{env}->{'psgix.io'} or return; # client abort
-	my $smsg = $self->{smsg} or die 'BUG: no smsg';
+	my $http = $self->{env}->{'psgix.io'};
+	$http->{forward} or return; # client aborted
+	my $smsg = $self->{smsg} or bail($self, 'BUG: no smsg');
 	if (!defined($oid)) {
 		# it's possible to have TOCTOU if an admin runs
 		# public-inbox-(edit|purge), just move onto the next message
-		return $http->next_step($self->{async_next});
+		warn "E: $smsg->{blob} missing in $self->{ibx}->{inboxdir}\n";
+		return $http->next_step($self->can('async_next'));
 	}
-	$smsg->{blob} eq $oid or die "BUG: $smsg->{blob} != $oid";
-	$self->{async_eml}->($self, PublicInbox::Eml->new($bref));
-	$http->next_step($self->{async_next});
+	$smsg->{blob} eq $oid or bail($self, "BUG: $smsg->{blob} != $oid");
+	eval { $self->async_eml(PublicInbox::Eml->new($bref)) };
+	bail($self, "E: async_eml: $@") if $@;
+	$http->next_step($self->can('async_next'));
 }
 
 sub smsg_blob {
 	my ($self, $smsg) = @_;
-	git_async_cat($self->{-inbox}->git, $smsg->{blob},
+	git_async_cat($self->{ibx}->git, $smsg->{blob},
 			\&async_blob_cb, $self);
 }