extsearchidx: close DB handles after use if FD constrained

Most distros ship with low RLIMIT_NOFILE limits and surprises
may lurk for admins who configure many inboxes.  Keep FD usage
under control to avoid EMFILE errors at inopportune times during
reindex.

From what I can tell, this is the only place where extindex can
have unpredictable FD growth when there's thousands of inboxes,
and it's in an extremely rare code path.

1 files changed, 34 insertions, 3 deletions

diff --git a/lib/PublicInbox/ExtSearchIdx.pm b/lib/PublicInbox/ExtSearchIdx.pm
index 386e1cee..3f197973 100644
--- a/lib/PublicInbox/ExtSearchIdx.pm
+++ b/lib/PublicInbox/ExtSearchIdx.pm
@@ -393,6 +393,32 @@ sub _ibx_for ($$$) {
         $self->{ibx_list}->[$pos] // die "BUG: ibx for $smsg->{blob} not mapped"
 }
 
+sub _fd_constrained ($) {
+        my ($self) = @_;
+        $self->{-fd_constrained} //= do {
+                my $soft;
+                if (eval { require BSD::Resource; 1 }) {
+                        my $NOFILE = BSD::Resource::RLIMIT_NOFILE();
+                        ($soft, undef) = BSD::Resource::getrlimit($NOFILE);
+                } else {
+                        chomp($soft = `sh -c 'ulimit -n'`);
+                }
+                if (defined($soft)) {
+                        my $want = scalar(@{$self->{ibx_list}}) + 64; # estimate
+                        my $ret = $want > $soft;
+                        if ($ret) {
+                                warn <<EOF;
+RLIMIT_NOFILE=$soft insufficient (want: $want), will close DB handles early
+EOF
+                        }
+                        $ret;
+                } else {
+                        warn "Unable to determine RLIMIT_NOFILE: $@\n";
+                        1;
+                }
+        };
+}
+
 sub _reindex_finalize ($$$) {
         my ($req, $smsg, $eml) = @_;
         my $sync = $req->{sync};
@@ -429,11 +455,16 @@ sub _reindex_finalize ($$$) {
                 my $x = pop(@$ary) // die "BUG: #$docid {by_chash} empty";
                 $x->{num} = delete($x->{xnum}) // die '{xnum} unset';
                 $ibx = _ibx_for($self, $sync, $x);
-                my $e = $ibx->over->get_art($x->{num});
-                $e->{blob} eq $x->{blob} or die <<EOF;
+                if (my $over = $ibx->over) {
+                        my $e = $over->get_art($x->{num});
+                        $e->{blob} eq $x->{blob} or die <<EOF;
 $x->{blob} != $e->{blob} (${\$ibx->eidx_key}:$e->{num});
 EOF
-                push @todo, $ibx, $e;
+                        push @todo, $ibx, $e;
+                        $over->dbh_close if _fd_constrained($self);
+                } else {
+                        die "$ibx->{inboxdir}: over.sqlite3 unusable: $!\n";
+                }
         }
         undef $by_chash;
         while (my ($ibx, $e) = splice(@todo, 0, 2)) {