X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FGzipFilter.pm;h=c4858a971495449ce7e4fd35b3a0c123153ed07b;hb=ead71b8c387f0748338a4add37eeb437a14b02d8;hp=d2eb4e6643e500f7a77cdf27aecb75380be8377c;hpb=f26183401e3abfb64ad82537151f2718ac889074;p=public-inbox.git diff --git a/lib/PublicInbox/GzipFilter.pm b/lib/PublicInbox/GzipFilter.pm index d2eb4e66..c4858a97 100644 --- a/lib/PublicInbox/GzipFilter.pm +++ b/lib/PublicInbox/GzipFilter.pm @@ -1,35 +1,81 @@ -# Copyright (C) 2020 all contributors +# Copyright (C) 2020-2021 all contributors # License: AGPL-3.0+ - -# 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; + 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, $fh) = @_; - $self->{fh} = $fh; + my ($self, $http_out) = @_; + $self->{http_out} = $http_out; # PublicInbox::HTTP::{Chunked,Identity} $self } -# returns `0' and not `undef' on failure (see Www*Stream) -sub gzf_maybe ($$) { +sub gz_or_noop { my ($res_hdr, $env) = @_; - return 0 if (($env->{HTTP_ACCEPT_ENCODING}) // '') !~ /\bgzip\b/; - my ($gz, $err) = Compress::Raw::Zlib::Deflate->new(%OPT); - return 0 if $err != Z_OK; + if (($env->{HTTP_ACCEPT_ENCODING} // '') =~ /\bgzip\b/) { + $env->{'plack.skip-deflater'} = 1; + push @$res_hdr, @GZIP_HDRS; + gzip_or_die(); + } else { + PublicInbox::CompressNoop::new(); + } +} + +sub gzf_maybe ($$) { bless { gz => gz_or_noop(@_) }, __PACKAGE__ } +sub psgi_response { + my ($self, $code, $res_hdr) = @_; + my $env = $self->{env}; + $self->{gz} //= gz_or_noop($res_hdr, $env); + if ($env->{'pi-httpd.async'}) { + my $http = $env->{'psgix.io'}; # PublicInbox::HTTP + $http->{forward} = $self; + sub { + my ($wcb) = @_; # -httpd provided write callback + $self->{wcb_args} = [ $code, $res_hdr, $wcb ]; + $self->can('async_next')->($http); # start stepping + }; + } else { # generic PSGI code path + [ $code, $res_hdr, $self ]; + } +} + +sub qsp_maybe ($$) { + my ($res_hdr, $env) = @_; + return if ($env->{HTTP_ACCEPT_ENCODING} // '') !~ /\bgzip\b/; + my $hdr = join("\n", @$res_hdr); + return if $hdr !~ m!^Content-Type\n + (?:(?:text/(?:html|plain))| + application/atom\+xml)\b!ixsm; + return if $hdr =~ m!^Content-Encoding\ngzip\n!smi; + return if $hdr =~ m!^Content-Length\n[0-9]+\n!smi; + return if $hdr =~ m!^Transfer-Encoding\n!smi; # in case Plack::Middleware::Deflater is loaded: - $env->{'plack.skip-deflater'} = 1; + return if $env->{'plack.skip-deflater'}++; push @$res_hdr, @GZIP_HDRS; - bless { gz => $gz }, __PACKAGE__; + bless {}, __PACKAGE__; } sub gzip_or_die () { @@ -38,6 +84,12 @@ sub gzip_or_die () { $gz; } +sub gone { # what: search/over/mm + my ($ctx, $what) = @_; + warn "W: `$ctx->{ibx}->{name}' $what went away unexpectedly\n"; + undef; +} + # for GetlineBody (via Qspawn) when NOT using $env->{'pi-httpd.async'} # Also used for ->getline callbacks sub translate ($$) { @@ -56,15 +108,23 @@ 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? - $_[0]->{fh}->write(translate($_[0], $_[1])); + http_out($_[0])->write(translate($_[0], $_[1])); } # similar to ->translate; use this when we're sure we know we have @@ -73,7 +133,7 @@ sub zmore { my $self = $_[0]; # $_[1] => input my $err = $self->{gz}->deflate($_[1], $self->{zbuf}); die "gzip->deflate: $err" if $err != Z_OK; - ''; + undef; } # flushes and returns the final bit of gzipped data @@ -86,16 +146,58 @@ sub zflush ($;$) { $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) = @_; - my $fh = delete $self->{fh}; - $fh->write(zflush($self)); - $fh->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'}; + $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 + 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')); + } +} + +sub smsg_blob { + my ($self, $smsg) = @_; + ibx_async_cat($self->{ibx}, $smsg->{blob}, \&async_blob_cb, $self); } 1;