www+httpd: lower priority of large mbox downloads

While each git blob request is treated fairly w.r.t other git
blob requests, responses triggering thousands of git blob
requests can still noticeably increase latency for
less-expensive responses.

Move large mbox results and the nasty all.mbox endpoint to
a low priority queue which only fires once per-event loop
iteration.  This reduces the response time of short HTTP
responses while many gigantic mboxes are being downloaded
simultaneously, but still maximizes use of available I/O
when there's no inexpensive HTTP responses happening.

This only affects PublicInbox::WWW users who use
public-inbox-httpd, not generic PSGI servers.

diff --git a/lib/PublicInbox/GzipFilter.pm b/lib/PublicInbox/GzipFilter.pm
index 334d658109be102465c79e690c3afed164b54fc0..c50c26c5c21cfe418b66f0430d2c375b2a402679 100644 (file)
--- a/lib/PublicInbox/GzipFilter.pm
+++ b/lib/PublicInbox/GzipFilter.pm
@@ -175,7 +175,12 @@ sub async_blob_cb { # git->cat_async callback
        $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 $@;
-       $http->next_step($self->can('async_next'));
+       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 {

diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index f72af26baeadc9602bbccbd75a6e2395bcf7bdae..cec76182933fabf4979c33f2f4406f4f0ece80ef 100644 (file)
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -174,6 +174,7 @@ sub mbox_all_ids {
                [404, [qw(Content-Type text/plain)], ["No results found\n"]];
        $ctx->{ids} = $ids;
        $ctx->{prev} = $prev;
+       $ctx->{-low_prio} = 1;
        require PublicInbox::MboxGz;
        PublicInbox::MboxGz::mbox_gz($ctx, \&all_ids_cb, 'all');
 }
@@ -192,12 +193,13 @@ sub results_cb {
                        my $smsg = $over->get_art($num) or next;
                        return $smsg;
                }
-               # refill result set
+               # refill result set, deprioritize since there's many results
                my $srch = $ctx->{ibx}->isrch or return gone($ctx, 'search');
                my $mset = $srch->mset($ctx->{query}, $ctx->{qopts});
                my $size = $mset->size or return;
                $ctx->{qopts}->{offset} += $size;
                $ctx->{ids} = $srch->mset_to_artnums($mset, $ctx->{qopts});
+               $ctx->{-low_prio} = 1;
        }
 }
 
@@ -214,12 +216,13 @@ sub results_thread_cb {
                # refills ctx->{xids}
                next if $over->expand_thread($ctx);
 
-               # refill result set
+               # refill result set, deprioritize since there's many results
                my $srch = $ctx->{ibx}->isrch or return gone($ctx, 'search');
                my $mset = $srch->mset($ctx->{query}, $ctx->{qopts});
                my $size = $mset->size or return;
                $ctx->{qopts}->{offset} += $size;
                $ctx->{ids} = $srch->mset_to_artnums($mset, $ctx->{qopts});
+               $ctx->{-low_prio} = 1;
        }
 
 }

diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index 570e690ec8136ca7cf6c98b4ea0138da42c57032..a7c961f4982a962c43071035660c90ed3a697d0a 100644 (file)
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -659,4 +659,13 @@ sub get_description {
        };
 }
 
+sub event_step { # called via requeue
+       my ($self) = @_;
+       # gzf = PublicInbox::GzipFilter == $ctx
+       my $gzf = shift(@{$self->{-low_prio_q}}) // return;
+       PublicInbox::DS::requeue($self) if scalar(@{$self->{-low_prio_q}});
+       my $http = $gzf->{env}->{'psgix.io'}; # PublicInbox::HTTP
+       $http->next_step($gzf->can('async_next'));
+}
+
 1;