extindex: fix --reindex

`public-inbox-extindex --reindex' deprioritizes itself for
public-inbox-extindex invocations without --reindex by shutting
down shard processes to let other processes acquire the lock and
process new messages, first.

Restarting shard processes during --reindex was causing new
Xapian shards to be written to v2 inboxes instead of the
extindex itself.  This bug was introduced with the
simplifications to internal data structures to eliminate the
ad-hoc $sync structure.

The local-ized use of ExtSearchIdx->{ibx} tricked
PublicInbox::SearchIdxShard::new into using the standard v2 code
path.  So make SearchIdxShard->new check the `$v2w' object for
the ability to call `eidx_sync' rather than the existence of the
{ibx} field.

I only noticed this bug while working on the --split-shards
feature for performance.

Fixes: 922b765d ((ext)index: move {max_size} and related bits to $self, 2025-01-10)

diff --git a/lib/PublicInbox/SearchIdxShard.pm b/lib/PublicInbox/SearchIdxShard.pm
index 8f340071f39381c688d3f6adae272db9d45b5510..8de79b78229d2a978f1cf9b6eca4301c928d93d6 100644 (file)
--- a/lib/PublicInbox/SearchIdxShard.pm
+++ b/lib/PublicInbox/SearchIdxShard.pm
@@ -10,10 +10,9 @@ use PublicInbox::OnDestroy;
 use PublicInbox::Syscall qw($F_SETPIPE_SZ);
 
 sub new {
-       my ($class, $v2w, $shard) = @_; # v2w may be ExtSearchIdx
-       my $ibx = $v2w->{ibx};
-       my $self = $ibx ? $class->SUPER::new($ibx, $v2w->{-opt}, $shard)
-                       : $class->eidx_shard_new($v2w, $shard);
+       my ($cls, $v2w, $shard) = @_; # v2w may be ExtSearchIdx
+       my $self = $v2w->can('eidx_sync') ? $cls->eidx_shard_new($v2w, $shard)
+                       : $cls->SUPER::new(@$v2w{qw(ibx -opt)}, $shard);
        # create the DB before forking:
        $self->idx_acquire;
        $self->set_metadata_once;

diff --git a/t/extsearch.t b/t/extsearch.t
index 08fdc6148238080dc07e385198bb0ed328c83a7d..aa9da3fae50c0ca1bdfb4ea82f82b019d64eef73 100644 (file)
--- a/t/extsearch.t
+++ b/t/extsearch.t
@@ -752,4 +752,35 @@ SKIP: {
        unlike $lsa, qr/No_COW/i, '--cow respected';
 }
 
+{
+       my $many = create_inbox 'many', version => 2, indexlevel => 'basic',
+                               tmpdir => "$home/many", sub {
+               my $eml = PublicInbox::Eml->new(<<'EOM');
+From: a@example.com
+To: b@example.com
+Subject: s
+Date: Fri, 02 Oct 1993 00:00:00 +0000
+
+EOM
+               my ($im, $ibx) = @_;
+               for my $i (0..6) { # >(PublicInbox::Git::MAX_INFLIGHT/3)
+                       $eml->header_set('Message-ID', "<$i\@a>");
+                       $im->add($eml);
+               }
+               $im->done;
+       };
+       my @before = glob("$many->{inboxdir}/xap*/?");
+       is_deeply \@before, [],
+               'no Xapian shards in v2 to be reindexed by -extindex';
+       my $opt = { 2 => \(my $err = '') };
+       ok run_script([qw(-extindex --reindex --batch-size=1),
+                       "$home/fresh", $many->{inboxdir}],
+                       undef, $opt),
+                       '--reindex fresh on fresh directory';
+       my @after = glob("$many->{inboxdir}/xap*/?");
+       is_deeply \@after, [],
+               'no Xapian shards in v2 after reindexed by -extindex';
+       is $err, '', 'no warnings on --reindex';
+}
+
 done_testing;