-# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2020-2021 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);
-use Compress::Raw::Zlib qw(Z_FINISH Z_OK);
+use Compress::Raw::Zlib qw(Z_OK);
use PublicInbox::CompressNoop;
use PublicInbox::Eml;
use PublicInbox::GitAsyncCat;
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
}
sub gzf_maybe ($$) { bless { gz => gz_or_noop(@_) }, __PACKAGE__ }
sub psgi_response {
- my ($self, $code, $res_hdr, $next_cb, $eml_cb) = @_;
+ my ($self, $code, $res_hdr) = @_;
my $env = $self->{env};
$self->{gz} //= gz_or_noop($res_hdr, $env);
if ($env->{'pi-httpd.async'}) {
- $self->{async_next} = $next_cb;
- $self->{async_eml} = $eml_cb;
my $http = $env->{'psgix.io'}; # PublicInbox::HTTP
$http->{forward} = $self;
sub {
my ($wcb) = @_; # -httpd provided write callback
- $self->{http_out} = $wcb->([$code, $res_hdr]);
- $next_cb->($http); # start stepping
+ $self->{wcb_args} = [ $code, $res_hdr, $wcb ];
+ $self->can('async_next')->($http); # start stepping
};
} else { # generic PSGI code path
[ $code, $res_hdr, $self ];
$gz;
}
+sub gone { # what: search/over/mm
+ my ($ctx, $what) = @_;
+ warn "W: `$ctx->{ibx}->{name}' $what went away unexpectedly\n";
+ undef;
+}
+
# for GetlineBody (via Qspawn) when NOT using $env->{'pi-httpd.async'}
# Also used for ->getline callbacks
sub translate ($$) {
$self->{zbuf} = $zbuf;
'';
} else { # undef == EOF
- my $err = $gz->flush($zbuf, Z_FINISH);
+ my $err = $gz->flush($zbuf);
die "gzip->flush: $err" if $err != Z_OK;
$zbuf;
}
}
+sub http_out ($) {
+ my ($self) = @_;
+ $self->{http_out} //= do {
+ my $args = delete $self->{wcb_args} // return undef;
+ pop(@$args)->($args); # $wcb->([$code, $hdr_ary])
+ };
+}
+
sub write {
# my $ret = bytes::length($_[1]); # XXX does anybody care?
- $_[0]->{http_out}->write(translate($_[0], $_[1]));
+ http_out($_[0])->write(translate($_[0], $_[1]));
}
# similar to ->translate; use this when we're sure we know we have
$err = $gz->deflate($_[1], $zbuf);
die "gzip->deflate: $err" if $err != Z_OK;
}
- $err = $gz->flush($zbuf, Z_FINISH);
+ $err = $gz->flush($zbuf);
die "gzip->flush: $err" if $err != Z_OK;
$zbuf;
}
sub close {
my ($self) = @_;
- if (my $http_out = delete $self->{http_out}) {
- $http_out->write(zflush($self));
- $http_out->close;
+ my $http_out = http_out($self) // return;
+ $http_out->write(zflush($self));
+ delete($self->{http_out})->close;
+}
+
+sub bail {
+ my $self = shift;
+ if (my $env = $self->{env}) {
+ warn @_, "\n";
+ 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 $oid or bail($self, "BUG: $smsg->{blob} != $oid");
+ eval { $self->async_eml(PublicInbox::Eml->new($bref)) };
+ bail($self, "E: async_eml: $@") if $@;
+ if ($self->{-low_prio}) {
+ push(@{$self->{www}->{-low_prio_q}}, $self) == 1 and
+ PublicInbox::DS::requeue($self->{www});
+ } else {
+ $http->next_step($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});
}
sub smsg_blob {
my ($self, $smsg) = @_;
- git_async_cat($self->{-inbox}->git, $smsg->{blob},
- \&async_blob_cb, $self);
+ ibx_async_cat($self->{ibx}, $smsg->{blob}, \&async_blob_cb, $self);
}
1;