searchview: use over.sqlite3 instead of Xapian docdata

This is a step towards improving kernel page cache hit rates by
relying on over.sqlite3 for document data instead of Xapian.
Some micro-optimization to over->get_art was required to
maintain performance.

diff --git a/lib/PublicInbox/Over.pm b/lib/PublicInbox/Over.pm
index 81b9fca7a75d7354a75f92f9e6b655c0b4eb806d..80e57e624c9572b2d7623db042c6bafeae3e503f 100644 (file)
--- a/lib/PublicInbox/Over.pm
+++ b/lib/PublicInbox/Over.pm
@@ -57,6 +57,7 @@ sub new {
 sub disconnect {
        my ($self) = @_;
        if (my $dbh = delete $self->{dbh}) {
+               delete $self->{-get_art};
                $self->{filename} = $dbh->sqlite_db_filename;
        }
 }
@@ -201,8 +202,8 @@ SELECT COUNT(num) FROM over WHERE num > 0
 
 sub get_art {
        my ($self, $num) = @_;
-       my $dbh = $self->connect;
-       my $sth = $dbh->prepare_cached(<<'', undef, 1);
+       # caching $sth ourselves is faster than prepare_cached
+       my $sth = $self->{-get_art} //= $self->connect->prepare(<<'');
 SELECT num,ds,ts,ddd FROM over WHERE num = ? LIMIT 1
 
        $sth->execute($num);
@@ -230,13 +231,7 @@ ORDER BY num ASC LIMIT 1
        $sth->execute($$id, $$prev);
        my $num = $sth->fetchrow_array or return;
        $$prev = $num;
-
-       $sth = $dbh->prepare_cached(<<"", undef, 1);
-SELECT num,ts,ds,ddd FROM over WHERE num = ? LIMIT 1
-
-       $sth->execute($num);
-       my $smsg = $sth->fetchrow_hashref or return;
-       load_from_row($smsg);
+       get_art($self, $num);
 }
 
 # IMAP search, this is limited by callers to UID_SLICE size (50K)
@@ -278,10 +273,7 @@ sub check_inodes {
                my $st = pack('dd', $st[0], $st[1]);
 
                # don't actually reopen, just let {dbh} be recreated later
-               if ($st ne ($self->{st} // $st)) {
-                       delete($self->{dbh});
-                       $self->{filename} = $f;
-               }
+               disconnect($self) if $st ne ($self->{st} // $st);
        } else {
                warn "W: stat $f: $!\n";
        }

diff --git a/lib/PublicInbox/SearchView.pm b/lib/PublicInbox/SearchView.pm
index 28d9ce5dd940ba337079ba39f2ae61fadec056b4..61534c2509a4888efc3858c8919e4c51209327fb 100644 (file)
--- a/lib/PublicInbox/SearchView.pm
+++ b/lib/PublicInbox/SearchView.pm
@@ -13,6 +13,7 @@ use PublicInbox::WwwAtomStream;
 use PublicInbox::WwwStream qw(html_oneshot);
 use PublicInbox::SearchThread;
 use PublicInbox::SearchQuery;
+use PublicInbox::Search qw(mdocid);
 my %rmap_inc;
 
 sub mbox_results {
@@ -90,19 +91,22 @@ sub mset_summary {
        my $pfx = ' ' x $pad;
        my $res = \($ctx->{-html_tip});
        my $ibx = $ctx->{-inbox};
-       my $srch = $ibx->search;
+       my $over = $ibx->over;
+       my $nshard = $ibx->search->{nshard} // 1;
        my $obfs_ibx = $ibx->{obfuscate} ? $ibx : undef;
        foreach my $m ($mset->items) {
                my $rank = sprintf("%${pad}d", $m->get_rank + 1);
                my $pct = get_pct($m);
-               my $smsg = PublicInbox::Smsg::from_mitem($m, $srch);
+               my $num = mdocid($nshard, $m);
+               my $smsg = $over->get_art($num, 1);
                unless ($smsg) {
                        eval {
-                               $m = "$m ".$m->get_docid . " expired\n";
+                               $m = "$m $num expired\n";
                                $ctx->{env}->{'psgi.errors'}->print($m);
                        };
                        next;
                }
+               PublicInbox::Smsg::psgi_cull($smsg);
                my $s = ascii_html($smsg->{subject});
                my $f = ascii_html($smsg->{from_name});
                if ($obfs_ibx) {