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 28F101F670
	for <meta@public-inbox.org>; Thu, 14 Oct 2021 05:49:33 +0000 (UTC)
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH] extindex: guard against buggy unrefs
Date: Thu, 14 Oct 2021 05:49:33 +0000
Message-Id: <20211014054933.5104-1-e@80x24.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

I noticed some unref messages which shouldn't have been
happening, but they were.  Which is troubling.  So add
a guard around an unref path until we can get to the bottom
of this.
---
 lib/PublicInbox/ExtSearchIdx.pm | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/lib/PublicInbox/ExtSearchIdx.pm b/lib/PublicInbox/ExtSearchIdx.pm
index 750ced5c..363e5665 100644
--- a/lib/PublicInbox/ExtSearchIdx.pm
+++ b/lib/PublicInbox/ExtSearchIdx.pm
@@ -18,6 +18,7 @@ use strict;
 use v5.10.1;
 use parent qw(PublicInbox::ExtSearch PublicInbox::Lock);
 use Carp qw(croak carp);
+use Scalar::Util qw(blessed);
 use Sys::Hostname qw(hostname);
 use POSIX qw(strftime);
 use File::Glob qw(bsd_glob GLOB_NOSORT);
@@ -143,6 +144,14 @@ sub _unref_doc ($$$$$;$) {
 		$smsg = $docid;
 		$docid = $smsg->{num};
 	}
+	if (defined($oidbin) && defined($xnum) && blessed($ibx) $ibx->over) {
+		my $smsg = $ibx->over->get_art($xnum);
+		if ($smsg && pack('H*', $smsg->{blob}) eq $oidbin) {
+			carp("BUG: (non-fatal) ".$ibx->eidx_key.
+				" #$xnum $smsg->{blob} still valid");
+			return;
+		}
+	}
 	my $s = 'DELETE FROM xref3 WHERE oidbin = ?';
 	$s .= ' AND ibx_id = ?' if defined($ibx);
 	$s .= ' AND xnum = ?' if defined($xnum);