From: Eric Wong <e@80x24.org>
Date: Sat, 23 Jul 2022 06:12:16 +0000 (+0000)
Subject: pop3: reduce memory use while generating the mailbox cache
X-Git-Tag: v1.9.0~80
X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=commitdiff_plain;h=0ae89efce11e1e3b10a067c61c5b4cde30fa2b3b

pop3: reduce memory use while generating the mailbox cache

While the cache itself is relatively compact for 50K messages,
generating it was inefficient due to our schema and Over.pm APIs
being designed for NNTP.  While we won't change our schema for
now, we can choose better DBI APIs to use and limit our ephemeral
memory use.

This amounts to a 60% reduction in memory usage and a 5-10%
speedup against org.kernel.vger.git.0:

	{
		echo 'USER '$(uuidgen)'@org.kernel.vger.git.0'
		echo PASS anonymous
		echo STAT
		echo QUIT
	} | nc $HOST $PORT
---

diff --git a/lib/PublicInbox/POP3.pm b/lib/PublicInbox/POP3.pm
index 60eedea7..203c91a6 100644
--- a/lib/PublicInbox/POP3.pm
+++ b/lib/PublicInbox/POP3.pm
@@ -148,12 +148,21 @@ sub _stat_cache ($) {
 	my ($self) = @_;
 	my ($beg, $end) = (($self->{uid_dele} // -1) + 1, $self->{uid_max});
 	PublicInbox::IMAP::uid_clamp($self, \$beg, \$end);
-	my $opt = { limit => PublicInbox::IMAP::UID_SLICE };
-	my $m = $self->{ibx}->over(1)->do_get(<<'', $opt, $beg, $end);
+	my (@cache, $m);
+	my $sth = $self->{ibx}->over(1)->dbh->prepare_cached(<<'', undef, 1);
 SELECT num,ddd FROM over WHERE num >= ? AND num <= ?
 ORDER BY num ASC
 
-	[ map { ($_->{num}, $_->{bytes} + 0, $_->{blob}) } @$m ];
+	$sth->execute($beg, $end);
+	do {
+		$m = $sth->fetchall_arrayref({}, 1000);
+		for my $x (@$m) {
+			PublicInbox::Over::load_from_row($x);
+			push(@cache, $x->{num}, $x->{bytes} + 0, $x->{blob});
+			undef $x; # saves ~1.5M memory w/ 50k messages
+		}
+	} while (scalar(@$m) && ($beg = $cache[-3] + 1));
+	\@cache;
 }
 
 sub cmd_stat {