From 166532d5a7fb7409db8e7877ca961afb60ad28e5 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Mon, 11 Mar 2024 19:40:10 +0000
Subject: codesearch: deduplicate {ibx_score} name pairs

With my current mirror of lore + gko, this saves over 300K
allocations and brings the allocation count in this area down
to under 5K.  The reduction in AV refs saves around 45MB RAM
according to measurements done live via Devel::Mwrap.
---
 lib/PublicInbox/CodeSearch.pm | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/lib/PublicInbox/CodeSearch.pm b/lib/PublicInbox/CodeSearch.pm
index 1f95a726..48033bb5 100644
--- a/lib/PublicInbox/CodeSearch.pm
+++ b/lib/PublicInbox/CodeSearch.pm
@@ -292,6 +292,7 @@ W: cindex.$name.topdir=$self->{topdir} has no usable join data for $cfg_f
 EOM
 	my ($ekeys, $roots, $ibx2root) = @$jd{qw(ekeys roots ibx2root)};
 	my $roots2paths = roots2paths($self);
+	my %dedupe; # 50x alloc reduction w/ lore + gko mirror (Mar 2024)
 	for my $root_offs (@$ibx2root) {
 		my $ekey = shift(@$ekeys) // die 'BUG: {ekeys} empty';
 		scalar(@$root_offs) or next;
@@ -320,9 +321,15 @@ EOM
 				if (my $git = $dir2cr{$_}) {
 					$ibx_p2g{$_} = $git;
 					$ibx2self = 1;
-					$ibx->{-hide_www} or
-						push @{$git->{ibx_score}},
+					if (!$ibx->{-hide_www}) {
+						# don't stringify $nr directly
+						# to avoid long-lived PV
+						my $k = ($nr + 0)."\0".
+							($ibx + 0);
+						my $s = $dedupe{$k} //=
 							[ $nr, $ibx->{name} ];
+						push @{$git->{ibx_score}}, $s;
+					}
 					push @$gits, $git;
 				} else {
 					warn <<EOM;
-- 
cgit v1.2.3-24-ge0c7