From d621d7fc29f0a76aecb4880001f34031c80b87ac Mon Sep 17 00:00:00 2001
From: Daniel Hilst <392820+dhilst@users.noreply.github.com>
Date: Thu, 30 Jul 2026 19:03:00 -0300
Subject: [PATCH] fix(xcat-core): treat signal-killed build workers as failures
 too

The parallel-build failure gate only inspected $exit_code in run_on_finish. A
ForkManager child killed by a signal -- SIGKILL, or the OOM-killer under the
concurrent build load -- is reaped with $exit_code == 0 but $exit_signal != 0
(and possibly $core_dump). Such a worker therefore was NOT recorded as a
failure, so the parent could still index and GPG-sign a repository that is
missing the package that worker was building -- the exact partial-repo hazard
the gate was added to prevent, via a path it did not cover.

Capture $exit_signal and $core_dump from the run_on_finish callback and fail
the build when any of $exit_code, $exit_signal, or $core_dump is set.

Signed-off-by: Daniel Hilst <392820+dhilst@users.noreply.github.com>
---
 buildrpms.pl | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/buildrpms.pl b/buildrpms.pl
index 7ddc775d3..0304de400 100755
--- a/buildrpms.pl
+++ b/buildrpms.pl
@@ -999,11 +999,13 @@ sub main {
     local $SIG{TERM} = \&abort_builds;
     $pm->run_on_start(sub { my ($pid, $chroot) = @_; $MOCK_INFLIGHT{$pid} = $chroot if defined $chroot; });
     $pm->run_on_finish(sub {
-        my ($pid, $exit_code, $ident) = @_;
+        my ($pid, $exit_code, $ident, $exit_signal, $core_dump) = @_;
         delete $MOCK_INFLIGHT{$pid};
-        # A build/update child that die()s (e.g. a failed sh_retry) exits non-zero; record it so
-        # we never index or sign a partial repository (would ship a core missing packages).
-        push @CHILD_FAILURES, ($ident // "pid=$pid") if $exit_code;
+        # A child that die()s exits non-zero; one killed by a SIGNAL (SIGKILL / OOM-killer) is reaped
+        # with $exit_code==0 but $exit_signal!=0 (and maybe $core_dump). Checking $exit_code alone
+        # would let an OOM-killed worker through and the parent would index+sign a partial repository
+        # (a core missing packages). Treat a non-zero exit, a killing signal, OR a core dump as failure.
+        push @CHILD_FAILURES, ($ident // "pid=$pid") if $exit_code || $exit_signal || $core_dump;
     });
 
     for my $pair (@rpms) {