daemon: warn on missing blobs

[public-inbox.git] / lib / PublicInbox / GzipFilter.pm

diff --git a/lib/PublicInbox/GzipFilter.pm b/lib/PublicInbox/GzipFilter.pm
index 6380f50e91f80ebd5e69d69b791cf36d5296e051..b5ad9eb884cd7a57989b1ec1e9102f35d00bb826 100644 (file)
--- 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
 }
 
@@ -138,18 +147,35 @@ 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 $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
+               warn "E: $smsg->{blob} missing in $self->{-inbox}->{inboxdir}\n";
                return $http->next_step($self->{async_next});
        }
-       $smsg->{blob} eq $oid or die "BUG: $smsg->{blob} != $oid";
-       $self->{async_eml}->($self, PublicInbox::Eml->new($bref));
+       $smsg->{blob} eq $oid or bail($self, "BUG: $smsg->{blob} != $oid");
+       eval { $self->{async_eml}->($self, PublicInbox::Eml->new($bref)) };
+       bail($self, "E: async_eml: $@") if $@;
        $http->next_step($self->{async_next});
 }