* [PATCH 2/2] mbox: switch generation over to pull model
2016-05-21 3:03 7% [PATCH 0/2] http: start migrating to pull-based I/O Eric Wong
@ 2016-05-21 3:03 5% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2016-05-21 3:03 UTC (permalink / raw)
To: meta
This allows us to easily provide gigantic inboxes
with proper backpressure handling for slow clients.
It also eliminates public-inbox-httpd and Danga::Socket-specific
knowledge from this class, making it easier to follow for
those used to generic PSGI applications.
---
lib/PublicInbox/Git.pm | 2 +
lib/PublicInbox/Mbox.pm | 157 +++++++++++++++---------------------------------
2 files changed, 52 insertions(+), 107 deletions(-)
diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm
index d821182..473cdff 100644
--- a/lib/PublicInbox/Git.pm
+++ b/lib/PublicInbox/Git.pm
@@ -41,6 +41,7 @@ sub cat_file {
$self->{out}->print($obj, "\n") or fail($self, "write error: $!");
my $in = $self->{in};
+ local $/ = "\n";
my $head = $in->getline;
$head =~ / missing$/ and return undef;
$head =~ /^[0-9a-f]{40} \S+ (\d+)$/ or
@@ -90,6 +91,7 @@ sub check {
my ($self, $obj) = @_;
$self->_bidi_pipe(qw(--batch-check in_c out_c pid_c));
$self->{out_c}->print($obj, "\n") or fail($self, "write error: $!");
+ local $/ = "\n";
chomp(my $line = $self->{in_c}->getline);
my ($hex, $type, $size) = split(' ', $line);
return if $type eq 'missing';
diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index 4c4b74f..40ca611 100644
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -6,18 +6,11 @@
package PublicInbox::Mbox;
use strict;
use warnings;
-use PublicInbox::MID qw/mid2path mid_clean/;
+use PublicInbox::MID qw/mid_clean/;
use URI::Escape qw/uri_escape_utf8/;
+use Plack::Util;
require Email::Simple;
-sub thread_mbox {
- my ($ctx, $srch, $sfx) = @_;
- sub {
- my ($response) = @_; # Plack callback
- emit_mbox($response, $ctx, $srch, $sfx);
- }
-}
-
sub emit1 {
my $simple = Email::Simple->new(pop);
my $ctx = pop;
@@ -84,104 +77,35 @@ sub emit_msg {
$fh->write($buf .= "\n");
}
-sub emit_mbox {
- my ($response, $ctx, $srch, $sfx) = @_;
- my $type = 'mbox';
- if ($sfx) {
- eval { require IO::Compress::Gzip };
- return need_gzip($response) if $@;
- $type = 'gzip';
- }
-
- # http://www.iana.org/assignments/media-types/application/gzip
- # http://www.iana.org/assignments/media-types/application/mbox
- my $fh = $response->([200, ['Content-Type' => "application/$type"]]);
- $fh = PublicInbox::MboxGz->new($fh) if $sfx;
-
- require PublicInbox::Git;
- my $mid = $ctx->{mid};
- my $git = $ctx->{git} ||= PublicInbox::Git->new($ctx->{git_dir});
- my %opts = (offset => 0, asc => 1);
- my $nr;
- do {
- my $res = $srch->get_thread($mid, \%opts);
- my $msgs = $res->{msgs};
- $nr = scalar @$msgs;
- while (defined(my $smsg = shift @$msgs)) {
- my $msg = eval {
- my $p = 'HEAD:'.mid2path($smsg->mid);
- Email::Simple->new($git->cat_file($p));
- };
- emit_msg($ctx, $fh, $msg) if $msg;
- }
+sub noop {}
- $opts{offset} += $nr;
- } while ($nr > 0);
+sub thread_mbox {
+ my ($ctx, $srch, $sfx) = @_;
+ eval { require IO::Compress::Gzip };
+ return sub { need_gzip(@_) } if $@;
- $fh->close;
+ my $cb = sub { $srch->get_thread($ctx->{mid}, @_) };
+ # http://www.iana.org/assignments/media-types/application/gzip
+ [200, ['Content-Type' => 'application/gzip'],
+ PublicInbox::MboxGz->new($ctx, $cb) ];
}
sub emit_range {
my ($ctx, $range) = @_;
- sub { _emit_range($_[0], $ctx, $range) };
-}
-
-sub _emit_range {
- my ($res, $ctx, $range) = @_;
eval { require IO::Compress::Gzip };
- return need_gzip($res) if $@;
+ return sub { need_gzip(@_) } if $@;
my $query;
if ($range eq 'all') { # TODO: YYYY[-MM]
$query = '';
} else {
- $res->([404, [qw(Content-Type text/plain)], []]);
- return;
+ return [404, [qw(Content-Type text/plain)], []];
}
+ my $cb = sub { $ctx->{srch}->query($query, @_) };
# http://www.iana.org/assignments/media-types/application/gzip
- my $fh = $res->([200, [qw(Content-Type application/gzip)]]);
- $fh = PublicInbox::MboxGz->new($fh);
- my $env = $ctx->{cgi}->env;
- my $srch = $ctx->{srch};
- my $git = $ctx->{git};
- my %opts = (offset => 0, asc => 1);
- my $nr;
- my $cb = sub {
- my $res = $srch->query($query, \%opts);
- my $msgs = $res->{msgs};
- $nr = scalar @$msgs;
- while (defined(my $smsg = shift @$msgs)) {
- my $msg = eval {
- my $p = 'HEAD:'.mid2path($smsg->mid);
- Email::Simple->new($git->cat_file($p));
- };
- emit_msg($ctx, $fh, $msg) if $msg;
- }
-
- $opts{offset} += $nr;
- };
-
- $cb->(); # first part is free
- return $fh->close if $nr == 0;
-
- if ($env->{'pi-httpd.async'}) {
- my $io = $env->{'psgix.io'} or die "no IO";
- my $next;
- $next = sub {
- $cb->();
- if ($nr > 0) {
- $io->write($next);
- } else {
- $next = undef;
- $fh->close;
- }
- };
- $io->write($next); # Danga::Socket::write
- return;
- }
- $cb->() while ($nr > 0);
- $fh->close;
+ [200, [qw(Content-Type application/gzip)],
+ PublicInbox::MboxGz->new($ctx, $cb) ];
}
sub need_gzip {
@@ -198,40 +122,59 @@ EOF
1;
-# fh may not be a proper IO, so we wrap the write and close methods
-# to prevent IO::Compress::Gzip from complaining
package PublicInbox::MboxGz;
use strict;
use warnings;
+use PublicInbox::MID qw(mid2path);
sub new {
- my ($class, $fh) = @_;
+ my ($class, $ctx, $cb) = @_;
my $buf;
bless {
buf => \$buf,
gz => IO::Compress::Gzip->new(\$buf),
- fh => $fh,
+ cb => $cb,
+ ctx => $ctx,
+ msgs => [],
+ opts => { asc => 1, offset => 0 },
}, $class;
}
sub _flush_buf {
my ($self) = @_;
- if (defined ${$self->{buf}}) {
- $self->{fh}->write(${$self->{buf}});
- ${$self->{buf}} = undef;
- }
+ my $ret = $self->{buf};
+ $ret = $$ret;
+ ${$self->{buf}} = undef;
+ $ret;
}
-sub write {
- $_[0]->{gz}->write($_[1]);
- _flush_buf($_[0]);
-}
-
-sub close {
+# called by Plack::Util::foreach or similar
+sub getline {
my ($self) = @_;
+ my $res;
+ my $ctx = $self->{ctx};
+ my $git = $ctx->{git};
+ do {
+ while (defined(my $smsg = shift @{$self->{msgs}})) {
+ my $msg = eval {
+ my $p = 'HEAD:'.mid2path($smsg->mid);
+ Email::Simple->new($git->cat_file($p));
+ };
+ $msg or next;
+
+ PublicInbox::Mbox::emit_msg($ctx, $self->{gz}, $msg);
+ my $ret = _flush_buf($self);
+ return $ret if $ret;
+ }
+ $res = $self->{cb}->($self->{opts});
+ $self->{msgs} = $res->{msgs};
+ $res = scalar @{$self->{msgs}};
+ $self->{opts}->{offset} += $res;
+ } while ($res);
$self->{gz}->close;
_flush_buf($self);
- $self->{fh}->close;
}
+sub close {} # noop
+
1;
--
EW
^ permalink raw reply related [relevance 5%]
* [PATCH 0/2] http: start migrating to pull-based I/O
@ 2016-05-21 3:03 7% Eric Wong
2016-05-21 3:03 5% ` [PATCH 2/2] mbox: switch generation over to pull model Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2016-05-21 3:03 UTC (permalink / raw)
To: meta
There'll be more conversions coming, but this should decouple
some of our PSGI code from Danga::Socket internals while also
providing better backpressure handling inside PublicInbox::HTTP
to avoid excessive buffering.
Eric Wong (2):
http: reduce over-buffering for getline responses
mbox: switch generation over to pull model
lib/PublicInbox/Git.pm | 2 +
lib/PublicInbox/HTTP.pm | 26 ++++++--
lib/PublicInbox/Mbox.pm | 157 +++++++++++++++---------------------------------
3 files changed, 74 insertions(+), 111 deletions(-)
^ 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 --
2016-05-21 3:03 7% [PATCH 0/2] http: start migrating to pull-based I/O Eric Wong
2016-05-21 3:03 5% ` [PATCH 2/2] mbox: switch generation over to pull model 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).