From: Eric Wong <e@80x24.org>
Date: Mon, 10 Jun 2024 11:34:27 +0000 (+0000)
Subject: www: deduplicate Message-ID in threading + skeleton
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=15470b46d7add99d2f4925ce5b0e45a818e00bc6;p=thirdparty%2Fpublic-inbox.git

www: deduplicate Message-ID in threading + skeleton

xt/perf-threading.t reports a small 0.5-1.0% memory reduction in
non-ancient Perls with CoW strings for threading alone (w/o
rendering the View.pm stuff).

On informal tests using -httpd and giant Linux stable patch set
threads (700+ messages), this ends up being roughly 5MB saved in
/T/ rendering since we use the {mid} field again in the
$ctx->{mapping} table.  This becomes even more beneficial if
handling parallel HTTP requests for messages in the same message
thread, even across different endpoints.
---

diff --git a/lib/PublicInbox/SearchThread.pm b/lib/PublicInbox/SearchThread.pm
index 00ae9facc..672c53ad9 100644
--- a/lib/PublicInbox/SearchThread.pm
+++ b/lib/PublicInbox/SearchThread.pm
@@ -33,19 +33,24 @@ sub thread {
 	# can be shakier if somebody used In-Reply-To with multiple, disparate
 	# messages.  So, take the client Date: into account since we can't
 	# always determine ordering when somebody uses multiple In-Reply-To.
+	my (%dedupe, $mid);
 	my @kids = sort { $a->{ds} <=> $b->{ds} } grep {
 		# this delete saves around 4K across 1K messages
 		# TODO: move this to a more appropriate place, breaks tests
 		# if we do it during psgi_cull
 		delete $_->{num};
 		bless $_, 'PublicInbox::SearchThread::Msg';
-		if (exists $id_table{$_->{mid}}) {
+		$mid = $_->{mid};
+		if (exists $id_table{$mid}) {
 			$_->{children} = [];
 			push @imposters, $_; # we'll deal with them later
 			undef;
 		} else {
 			$_->{children} = {}; # will become arrayref later
-			$id_table{$_->{mid}} = $_;
+			%dedupe = ($mid => undef);
+			($mid) = keys %dedupe;
+			$_->{mid} = $mid;
+			$id_table{$mid} = $_;
 			defined($_->{references});
 		}
 	} @$msgs;
diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm
index 958efa417..dcceb3112 100644
--- a/lib/PublicInbox/View.pm
+++ b/lib/PublicInbox/View.pm
@@ -432,6 +432,7 @@ sub walk_thread ($$$) {
 
 sub pre_thread  { # walk_thread callback
 	my ($ctx, $level, $node, $idx) = @_;
+	# node->{mid} is deduplicated in PublicInbox::SearchThread::thread
 	$ctx->{mapping}->{$node->{mid}} = [ '', $node, $idx, $level ];
 	skel_dump($ctx, $level, $node);
 }