From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@yhbt.net>
X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,AWL,BAYES_00
	shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id BFE8B1FB09
	for <meta@public-inbox.org>; Thu, 20 Aug 2020 20:25:00 +0000 (UTC)
From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 15/23] searchview: use over.sqlite3 instead of Xapian docdata
Date: Thu, 20 Aug 2020 20:24:49 +0000
Message-Id: <20200820202457.21042-16-e@yhbt.net>
In-Reply-To: <20200820202457.21042-1-e@yhbt.net>
References: <20200820202457.21042-1-e@yhbt.net>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

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.
---
 lib/PublicInbox/Over.pm       | 18 +++++-------------
 lib/PublicInbox/SearchView.pm | 10 +++++++---
 2 files changed, 12 insertions(+), 16 deletions(-)

diff --git a/lib/PublicInbox/Over.pm b/lib/PublicInbox/Over.pm
index 81b9fca7..80e57e62 100644
--- 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 28d9ce5d..61534c25 100644
--- 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) {