* [PATCH 07/43] wwwlisting: use GzipFilter for HTML
2020-07-05 23:27 7% [PATCH 00/43] www: async git cat-file w/ -httpd Eric Wong
@ 2020-07-05 23:27 5% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-07-05 23:27 UTC (permalink / raw)
To: meta
The changes to GzipFilter here may be beneficial for building
HTML and XML responses in other places, too.
---
MANIFEST | 1 +
lib/PublicInbox/GzipFilter.pm | 28 ++++++++++++++++++++++++++--
lib/PublicInbox/NoopFilter.pm | 13 +++++++++++++
lib/PublicInbox/WwwListing.pm | 25 +++++++++++++++----------
t/www_listing.t | 8 +++++++-
5 files changed, 62 insertions(+), 13 deletions(-)
create mode 100644 lib/PublicInbox/NoopFilter.pm
diff --git a/MANIFEST b/MANIFEST
index 6de2c7258..dcd7a7e5f 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -159,6 +159,7 @@ lib/PublicInbox/NNTP.pm
lib/PublicInbox/NNTPD.pm
lib/PublicInbox/NNTPdeflate.pm
lib/PublicInbox/NewsWWW.pm
+lib/PublicInbox/NoopFilter.pm
lib/PublicInbox/Over.pm
lib/PublicInbox/OverIdx.pm
lib/PublicInbox/ParentPipe.pm
diff --git a/lib/PublicInbox/GzipFilter.pm b/lib/PublicInbox/GzipFilter.pm
index 95fced053..8cc5ea00b 100644
--- a/lib/PublicInbox/GzipFilter.pm
+++ b/lib/PublicInbox/GzipFilter.pm
@@ -42,7 +42,7 @@ sub gzf_maybe ($$) {
# for GetlineBody (via Qspawn) when NOT using $env->{'pi-httpd.async'}
# Also used for ->getline callbacks
sub translate ($$) {
- my $self = $_[0];
+ my $self = $_[0]; # $_[1] => input
# allocate the zlib context lazily here, instead of in ->new.
# Deflate contexts are memory-intensive and this object may
@@ -72,10 +72,34 @@ sub write {
$_[0]->{fh}->write(translate($_[0], $_[1]));
}
+# similar to ->translate; use this when we're sure we know we have
+# more data to buffer after this
+sub zmore {
+ my $self = $_[0]; # $_[1] => input
+ my $err = $self->{gz}->deflate($_[1], $self->{zbuf});
+ die "gzip->deflate: $err" if $err != Z_OK;
+ '';
+}
+
+# flushes and returns the final bit of gzipped data
+sub zflush ($;$) {
+ my $self = $_[0]; # $_[1] => final input (optional)
+ my $zbuf = delete $self->{zbuf};
+ my $gz = delete $self->{gz};
+ my $err;
+ if (defined $_[1]) {
+ $err = $gz->deflate($_[1], $zbuf);
+ die "gzip->deflate: $err" if $err != Z_OK;
+ }
+ $err = $gz->flush($zbuf, Z_FINISH);
+ die "gzip->flush: $err" if $err != Z_OK;
+ $zbuf;
+}
+
sub close {
my ($self) = @_;
my $fh = delete $self->{fh};
- $fh->write(translate($self, undef));
+ $fh->write(zflush($self));
$fh->close;
}
diff --git a/lib/PublicInbox/NoopFilter.pm b/lib/PublicInbox/NoopFilter.pm
new file mode 100644
index 000000000..b9c00ff7a
--- /dev/null
+++ b/lib/PublicInbox/NoopFilter.pm
@@ -0,0 +1,13 @@
+# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+
+package PublicInbox::NoopFilter;
+use strict;
+
+sub new { bless \(my $ignore), __PACKAGE__ }
+
+# noop workalike for PublicInbox::GzipFilter methods
+sub translate { $_[1] // '' }
+sub zmore { $_[1] }
+sub zflush { $_[1] // '' }
+1;
diff --git a/lib/PublicInbox/WwwListing.pm b/lib/PublicInbox/WwwListing.pm
index a3d4e2b35..780c97e91 100644
--- a/lib/PublicInbox/WwwListing.pm
+++ b/lib/PublicInbox/WwwListing.pm
@@ -10,6 +10,8 @@ use PublicInbox::Hval qw(ascii_html prurl);
use PublicInbox::Linkify;
use PublicInbox::View;
use PublicInbox::Inbox;
+use PublicInbox::NoopFilter;
+use PublicInbox::GzipFilter qw(gzf_maybe);
use bytes (); # bytes::length
use HTTP::Date qw(time2str);
use Digest::SHA ();
@@ -104,13 +106,15 @@ sub ibx_entry {
sub html ($$) {
my ($env, $list) = @_;
- my $title = 'public-inbox';
- my $out = '';
+ my $h = [ 'Content-Type', 'text/html; charset=UTF-8',
+ 'Content-Length', undef ];
+ my $gzf = gzf_maybe($h, $env) || PublicInbox::NoopFilter::new();
+ my $out = $gzf->zmore('<html><head><title>' .
+ 'public-inbox listing</title>' .
+ '</head><body><pre>');
my $code = 404;
if (@$list) {
- $title .= ' - listing';
$code = 200;
-
# Schwartzian transform since Inbox->modified is expensive
@$list = sort {
$b->[0] <=> $a->[0]
@@ -118,13 +122,14 @@ sub html ($$) {
my $tmp = join("\n", map { ibx_entry(@$_, $env) } @$list);
my $l = PublicInbox::Linkify->new;
- $out = '<pre>'.$l->to_html($tmp).'</pre><hr>';
+ $out .= $gzf->zmore($l->to_html($tmp));
+ } else {
+ $out .= $gzf->zmore('no inboxes, yet');
}
- $out = "<html><head><title>$title</title></head><body>" . $out;
- $out .= '<pre>'. PublicInbox::WwwStream::code_footer($env) .
- '</pre></body></html>';
-
- my $h = [ 'Content-Type', 'text/html; charset=UTF-8' ];
+ $out .= $gzf->zflush('</pre><hr><pre>'.
+ PublicInbox::WwwStream::code_footer($env) .
+ '</pre></body></html>');
+ $h->[3] = bytes::length($out);
[ $code, $h, [ $out ] ];
}
diff --git a/t/www_listing.t b/t/www_listing.t
index 0aededd43..c4511cd1f 100644
--- a/t/www_listing.t
+++ b/t/www_listing.t
@@ -35,13 +35,19 @@ like(PublicInbox::WwwListing::fingerprint($bare), qr/\A[a-f0-9]{40}\z/,
sub tiny_test {
my ($json, $host, $port) = @_;
+ my $tmp;
my $http = HTTP::Tiny->new;
my $res = $http->get("http://$host:$port/");
is($res->{status}, 200, 'got HTML listing');
like($res->{content}, qr!</html>!si, 'listing looks like HTML');
+
+ $res = $http->get("http://$host:$port/", {'Accept-Encoding'=>'gzip'});
+ is($res->{status}, 200, 'got gzipped HTML listing');
+ IO::Uncompress::Gunzip::gunzip(\(delete $res->{content}) => \$tmp);
+ like($tmp, qr!</html>!si, 'unzipped listing looks like HTML');
+
$res = $http->get("http://$host:$port/manifest.js.gz");
is($res->{status}, 200, 'got manifest');
- my $tmp;
IO::Uncompress::Gunzip::gunzip(\(delete $res->{content}) => \$tmp);
unlike($tmp, qr/"modified":\s*"/, 'modified is an integer');
my $manifest = $json->decode($tmp);
^ permalink raw reply related [relevance 5%]
* [PATCH 00/43] www: async git cat-file w/ -httpd
@ 2020-07-05 23:27 7% Eric Wong
2020-07-05 23:27 5% ` [PATCH 07/43] wwwlisting: use GzipFilter for HTML Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2020-07-05 23:27 UTC (permalink / raw)
To: meta
This allows -httpd to make better use of time it spends waiting
on git-cat-file to respond. It allows us to deal with
high-latency HDD storage without a client monopolizing the event
loop. Even on a mid-range consumer-grade SSD, this seems to
give a 10+% speed improvement for HTTP responses requiring many
blobs, including all /T/, /t/, and /t.mbox.gz endpoints.
This only benefits indexed inboxes (both v1 and v2); I'm not
sure if anybody still uses unindexed v1 inboxes nowadays.
A new xt/httpd-async-stream.t maintainer test ensures checksums
for responses before and after this series match exactly as
before.
This builds off a branch I started several months ago (but never
published here) to integrate gzip responses into our codebase
and remove our optional dependency on Plack::Middleware::Deflater.
We already gzip a bunch of things independent of
Plack::Middleware::Deflater: manifest.js.gz, altid SQLite3 dumps
and all the *.mbox.gz endpoints; so being able to use gzip on
all of our responses without an extra dependency seemed logical.
Being able to consistently use our GzipFilter API to perform
buffering via ->zmore made it significantly easier to reason
about small response chunks for ghost messages interspersed with
large ones when streaming /$INBOX/$MSGID/t/ endpoints.
I'm not yet maximizing use of ->zmore for all buffering of HTTP
responses, yet; measurements need to happen, first. That may
happen in the 1.7 time frame. In particular, we would need to
ensure the Perl method dispatch and DSO overhead to Zlib.so and
libz.so of making many ->zmore calls doesn't cause performance
regressions compared to the current `.=' use and calling
->zmore/->translate fewer times.
Eric Wong (43):
gzipfilter: minor cleanups
wwwstream: oneshot: perform gzip without middleware
www*stream: gzip ->getline responses
wwwtext: gzip text/plain responses, as well
wwwtext: switch to html_oneshot
www: need: use WwwStream::html_oneshot
wwwlisting: use GzipFilter for HTML
gzipfilter: replace Compress::Raw::Deflate usages
{gzip,noop}filter: ->zmore returns undef, always
mbox: remove html_oneshot import
wwwstatic: support gzipped response directory listings
qspawn: learn to gzip streaming responses
stop auto-loading Plack::Middleware::Deflater
mboxgz: do asynchronous git blob retrievals
mboxgz: reduce object hash depth
mbox: async blob retrieval for "single message" raw mboxrd
wwwatomstream: simplify feed_update callers
wwwatomstream: use PublicInbox::Inbox->modified for feed_updated
wwwatomstream: reuse $ctx as $self
xt/httpd-async-stream: allow more options
wwwatomstream: support asynchronous blob retrievals
wwwstream: reduce object graph depth
wwwstream: reduce blob retrieval paths for ->getline
www: start making gzipfilter the parent response class
remove unused/redundant zlib-related imports
wwwstream: use parent.pm and no warnings
wwwstream: subclass off GzipFilter
view: wire up /$INBOX/$MESSAGE_ID/ permalink to async
view: /$INBOX/$MSGID/t/ reads blobs asynchronously
view: update /$INBOX/$MSGID/T/ to be async
feed: generate_i: eliminate pointless loop
feed: /$INBOX/new.html retrieves blobs asynchronously
ssearchview: /$INBOX/?q=$QUERY&x=t uses async blobs
view: eml_entry: reduce parameters
view: /$INBOX/$MSGID/t/: avoid extra hash lookup in eml case
wwwstream: eliminate ::response, use html_oneshot
www: update internal docs
view: simplify eml_entry callers further
wwwtext: simplify gzf_maybe use
wwwattach: support async blob retrievals
gzipfilter: drop HTTP connection on bugs or data corruption
daemon: warn on missing blobs
gzipfilter: check http->{forward} for client disconnects
Documentation/mknews.perl | 20 +--
Documentation/public-inbox-httpd.pod | 1 -
Documentation/technical/ds.txt | 4 +-
INSTALL | 5 -
MANIFEST | 2 +
ci/deps.perl | 1 -
examples/cgit.psgi | 8 -
examples/newswww.psgi | 8 -
examples/public-inbox.psgi | 9 --
examples/unsubscribe.psgi | 1 -
lib/PublicInbox/CompressNoop.pm | 22 +++
lib/PublicInbox/Feed.pm | 22 ++-
lib/PublicInbox/GetlineBody.pm | 4 +-
lib/PublicInbox/GzipFilter.pm | 168 +++++++++++++++++---
lib/PublicInbox/HTTP.pm | 7 +
lib/PublicInbox/HTTPD.pm | 5 +-
lib/PublicInbox/IMAP.pm | 1 +
lib/PublicInbox/Mbox.pm | 137 +++++++++--------
lib/PublicInbox/MboxGz.pm | 81 ++++------
lib/PublicInbox/NNTP.pm | 1 +
lib/PublicInbox/Qspawn.pm | 6 +-
lib/PublicInbox/SearchView.pm | 40 ++---
lib/PublicInbox/View.pm | 219 ++++++++++++++-------------
lib/PublicInbox/WWW.pm | 9 +-
lib/PublicInbox/WwwAtomStream.pm | 66 ++++----
lib/PublicInbox/WwwAttach.pm | 63 ++++++--
lib/PublicInbox/WwwListing.pm | 24 +--
lib/PublicInbox/WwwStatic.pm | 14 +-
lib/PublicInbox/WwwStream.pm | 110 ++++++++------
lib/PublicInbox/WwwText.pm | 26 ++--
script/public-inbox-httpd | 9 --
script/public-inbox.cgi | 7 -
t/httpd-corner.psgi | 7 +
t/httpd-corner.t | 9 +-
t/plack.t | 4 +
t/psgi_attach.t | 162 +++++++++++---------
t/psgi_text.t | 33 +++-
t/psgi_v2.t | 80 ++++++++--
t/www_listing.t | 8 +-
t/www_static.t | 11 +-
xt/httpd-async-stream.t | 104 +++++++++++++
41 files changed, 964 insertions(+), 554 deletions(-)
create mode 100644 lib/PublicInbox/CompressNoop.pm
create mode 100644 xt/httpd-async-stream.t
^ permalink raw reply [relevance 7%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2020-07-05 23:27 7% [PATCH 00/43] www: async git cat-file w/ -httpd Eric Wong
2020-07-05 23:27 5% ` [PATCH 07/43] wwwlisting: use GzipFilter for HTML Eric Wong
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).