From fec19e492eacb10f990091592f423542ab4249bd Mon Sep 17 00:00:00 2001
From: Eric Wong <e@yhbt.net>
Date: Sun, 5 Apr 2020 07:53:47 +0000
Subject: [PATCH] release large (non ref) scalars using `undef $sv'

Using `undef EXPR' like a function call actually frees the heap
memory associated with the scalar, whereas `$sv = undef' or
`$sv = ""' will hold the buffer around until $sv goes out
of scope.

The `sv_set_undef' documentation in the perlapi(1) manpage
explicitly states this:

  The perl equivalent is "$sv = undef;". Note that it doesn't
  free any string buffer, unlike "undef $sv".

And I've confirmed by reading Dump() output from Devel::Peek.

We'll also inline the old index_body sub in SearchIdx.pm to make
the scope of the scalar more obvious.

This change saves several hundred kB RSS on both -index and
-httpd when hitting large emails with thousands of lines.
---
 lib/PublicInbox/SearchIdx.pm | 33 ++++++++++++++++-----------------
 lib/PublicInbox/View.pm      |  4 ++--
 lib/PublicInbox/ViewDiff.pm  |  2 +-
 3 files changed, 19 insertions(+), 20 deletions(-)

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 89d8bc2b..9a5484e3 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -275,22 +275,8 @@ sub index_diff ($$$) {
 	index_text($self, join("\n", @xnq), 1, 'XNQ');
 }
 
-sub index_body ($$$) {
-	my ($self, $txt, $doc) = @_;
-	if ($doc) {
-		# does it look like a diff?
-		if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
-			index_diff($self, $txt, $doc);
-		} else {
-			index_text($self, $txt, 1, 'XNQ');
-		}
-	} else {
-		index_text($self, $txt, 0, 'XQUOT');
-	}
-}
-
 sub index_xapian { # msg_iter callback
-	my ($part, $depth, @idx) = @{$_[0]};
+	my $part = $_[0]->[0]; # ignore $depth and @idx
 	my ($self, $doc) = @{$_[1]};
 	my $ct = $part->content_type || 'text/plain';
 	my $fn = $part->filename;
@@ -300,11 +286,24 @@ sub index_xapian { # msg_iter callback
 
 	my ($s, undef) = msg_part_text($part, $ct);
 	defined $s or return;
+	$_[0]->[0] = $part = undef; # free memory
 
 	# split off quoted and unquoted blocks:
 	my @sections = PublicInbox::MsgIter::split_quotes($s);
-	$part = $s = undef;
-	index_body($self, $_, /\A>/ ? 0 : $doc) for @sections;
+	undef $s; # free memory
+	for my $txt (@sections) {
+		if ($txt =~ /\A>/) {
+			index_text($self, $txt, 0, 'XQUOT');
+		} else {
+			# does it look like a diff?
+			if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
+				index_diff($self, $txt, $doc);
+			} else {
+				index_text($self, $txt, 1, 'XNQ');
+			}
+		}
+		undef $txt; # free memory
+	}
 }
 
 sub add_xapian ($$$$) {
diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm
index 1e53d8dc..ddd94e48 100644
--- a/lib/PublicInbox/View.pm
+++ b/lib/PublicInbox/View.pm
@@ -566,7 +566,7 @@ sub add_text_body { # callback for msg_iter
 
 	# split off quoted and unquoted blocks:
 	my @sections = PublicInbox::MsgIter::split_quotes($s);
-	$s = '';
+	undef $s; # free memory
 	my $rv = $ctx->{obuf};
 	if (defined($fn) || $depth > 0 || $err) {
 		# badly-encoded message with $err? tell the world about it!
@@ -587,7 +587,7 @@ sub add_text_body { # callback for msg_iter
 			# regular lines, OK
 			$$rv .= $l->to_html($cur);
 		}
-		$cur = undef;
+		undef $cur; # free memory
 	}
 
 	obfuscate_addrs($ibx, $$rv) if $ibx->{obfuscate};
diff --git a/lib/PublicInbox/ViewDiff.pm b/lib/PublicInbox/ViewDiff.pm
index f7422712..3d6058a9 100644
--- a/lib/PublicInbox/ViewDiff.pm
+++ b/lib/PublicInbox/ViewDiff.pm
@@ -192,7 +192,7 @@ sub flush_diff ($$) {
 	my ($ctx, $cur) = @_;
 
 	my @top = split($EXTRACT_DIFFS, $$cur);
-	$$cur = undef;
+	undef $$cur; # free memory
 
 	my $linkify = $ctx->{-linkify};
 	my $dst = $ctx->{obuf};
-- 
2.44.0