From 8cde2ff5987db5fcd8a7792cc5e064a6cff817cd Mon Sep 17 00:00:00 2001 From: bong-water-water-bong Date: Tue, 10 Nov 2026 22:02:25 -0400 Subject: [PATCH] weekly: the runner preflight names a restart-policy failure as one (refs #1504) Since #2082, ci-runner-health.sh also fails a unit that is up but whose restart policy would leave it down after the next OOM kill. weekly.sh still summarised every such failure as "a runner unit is not accepting jobs". On strixhalo tonight all three runners are active/running, and only their policy fails. The behaviour is unchanged: the preflight still refuses. Only the summary line changes. Co-authored-by: bong-water-water-bong Co-Authored-By: Claude Opus 5.5 --- scripts/weekly.sh | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/scripts/weekly.sh b/scripts/weekly.sh index ea861f9a8..468864481 100755 --- a/scripts/weekly.sh +++ b/scripts/weekly.sh @@ -706,7 +706,10 @@ preflight() { say "preflight: no actions.runner.* units on this host: systemd has nothing to inspect" else printf '%s\n' "$health_out" | sed 's/^/preflight: /' - echo "preflight: a runner unit is not accepting jobs (scripts/ci-runner-health.sh): $health_rc" + # Two kinds of FAIL reach here (engine#1504): a unit that is down NOW, and since #2082 a unit that is up + # but whose restart policy would leave it down after the next OOM kill. The FAIL lines above say which; + # this line must not claim "not accepting jobs" for the second, where every runner is active/running. + echo "preflight: a runner unit is down, or its restart policy would leave it down after the next OOM kill (scripts/ci-runner-health.sh exit $health_rc; the FAIL lines above say which, and scripts/install-ci-runner.sh fixes a policy line)" bad=1 fi fi