From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-ASN:  
X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,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 8825D1FA11
	for <meta@public-inbox.org>; Sun, 10 Oct 2021 14:25:19 +0000 (UTC)
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 4/8] extindex: speed up Xapian cleanup in --gc
Date: Sun, 10 Oct 2021 14:25:14 +0000
Message-Id: <20211010142518.7012-5-e@80x24.org>
In-Reply-To: <20211010142518.7012-1-e@80x24.org>
References: <20211010142518.7012-1-e@80x24.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

Avoiding repeated SQL statements brings --gc down to 2-3 minutes
from around 10.  We'll also add some checkpoints around over and
xref3 cleanups.
---
 lib/PublicInbox/ExtSearchIdx.pm | 37 ++++++++++++++++++++-------------
 lib/PublicInbox/SearchIdx.pm    |  3 +++
 2 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/lib/PublicInbox/ExtSearchIdx.pm b/lib/PublicInbox/ExtSearchIdx.pm
index 20c4cf78..04948b8b 100644
--- a/lib/PublicInbox/ExtSearchIdx.pm
+++ b/lib/PublicInbox/ExtSearchIdx.pm
@@ -421,34 +421,43 @@ sub eidx_gc_scan_shards ($$) { # TODO: use for lei/store
 DELETE FROM xref3 WHERE docid NOT IN (SELECT num FROM over)
 
 	warn "I: eliminated $nr stale xref3 entries\n" if $nr != 0;
+	reindex_checkpoint($self, $sync) if checkpoint_due($sync);
 
 	# fixup from old bugs:
 	$nr = $self->{oidx}->dbh->do(<<'');
 DELETE FROM over WHERE num NOT IN (SELECT docid FROM xref3)
 
 	warn "I: eliminated $nr stale over entries\n" if $nr != 0;
+	reindex_checkpoint($self, $sync) if checkpoint_due($sync);
 
 	my ($cur) = $self->{oidx}->dbh->selectrow_array(<<EOM);
 SELECT MIN(num) FROM over
 EOM
-	my ($max) = $self->{oidx}->dbh->selectrow_array(<<EOM);
-SELECT MAX(num) FROM over
-EOM
-	my $exists;
-restart:
-	$exists = $self->{oidx}->dbh->prepare(<<EOM);
-SELECT COUNT(num) FROM over WHERE num = ?
-EOM
-	for (; $cur <= $max; $cur++) {
-		$exists->execute($cur);
-		next if $exists->fetchrow_array != 0;
-		$self->idx_shard($cur)->ipc_do('xdb_remove_quiet', $cur);
+	$cur // return; # empty
+	my ($r, $n, %active);
+	$nr = 0;
+	while (1) {
+		$r = $self->{oidx}->dbh->selectcol_arrayref(<<"", undef, $cur);
+SELECT num FROM over WHERE num >= ? ORDER BY num ASC LIMIT 10000
+
+		last unless scalar(@$r);
+		while (defined($n = shift @$r)) {
+			for my $i ($cur..($n - 1)) {
+				my $idx = idx_shard($self, $i);
+				$idx->ipc_do('xdb_remove_quiet', $i);
+				$active{$idx} = $idx;
+			}
+			$cur = $n + 1;
+		}
 		if (checkpoint_due($sync)) {
-			$exists = undef;
+			for my $idx (values %active) {
+				$nr += $idx->ipc_do('nr_quiet_rm')
+			}
+			%active = ();
 			reindex_checkpoint($self, $sync);
-			goto restart;
 		}
 	}
+	warn "I: eliminated $nr stale Xapian documents\n" if $nr != 0;
 }
 
 sub eidx_gc {
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 78db329d..bebe904b 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -650,8 +650,11 @@ sub xdb_remove_quiet {
 	begin_txn_lazy($self);
 	my $xdb = $self->{xdb} // die 'BUG: missing {xdb}';
 	eval { $xdb->delete_document($docid) };
+	++$self->{-quiet_rm} unless $@;
 }
 
+sub nr_quiet_rm { delete($_[0]->{-quiet_rm}) // 0 }
+
 sub index_git_blob_id {
 	my ($doc, $pfx, $objid) = @_;