fix(#636): stop before kill in cold-start fallback (argus)

This commit is contained in:
damocles 2026-05-31 21:00:35 +02:00
commit fdd5fa2977

View file

@ -444,17 +444,26 @@ pub async fn rebuild_no_meta(
// the old-generation activation references units that no longer
// exist in the new closure, causing systemd to exit non-zero.
//
// Fallback: kill + start (cold-start). `kill` SIGKILLs any
// lingering container processes so the next `start` enters a
// clean state without a generation transition, letting the
// activation succeed.
// Fallback: stop + kill + start (cold-start). The activation
// script can fail when packages are removed between generations —
// `start` exits non-zero but the container may be half-started.
// `stop` requests a graceful SIGTERM drain; `kill` then SIGKILLs
// any lingering processes so the next `start` enters a clean state
// without a generation transition, letting the activation succeed.
if let Err(start_err) = run(&["start", &container]).await {
tracing::warn!(
container = %container,
error = %start_err,
"start after rebuild failed (possible activation error); \
retrying via kill + start"
retrying via stop + kill + start"
);
run(&["stop", &container]).await.unwrap_or_else(|e| {
tracing::warn!(
container = %container,
error = %e,
"stop before cold-start retry failed (ignored)"
);
});
run(&["kill", &container]).await.unwrap_or_else(|e| {
tracing::warn!(
container = %container,