Skip to content

systemdunitcheck: Do not report unhealthy status for a disabled unit that is in failed state #171

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ske-prow merged 1 commit into from
Apr 30, 2026
Merged

systemdunitcheck: Do not report unhealthy status for a disabled unit that is in failed state #171

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion pkg/nodeagent/controller/systemdunitcheck/reconciler.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -168,7 +168,10 @@ func (r *Reconciler) checkUnits(ctx context.Context, units []unitInfo) (unhealth
}

case "failed":
unhealthyMessages = append(unhealthyMessages, fmt.Sprintf("%s: failed", unit.name))
// Only enabled units should be marked as erroring in case they are in a failed state.
if unit.enabled {
unhealthyMessages = append(unhealthyMessages, fmt.Sprintf("%s: failed", unit.name))
}

case "activating", "deactivating":
// Services configured with Restart=always/on-success cycle through "activating (auto-restart)"
Expand Down
22 changes: 22 additions & 0 deletions test/integration/nodeagent/systemdunitcheck/systemdunitcheck_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -302,6 +302,28 @@ var _ = Describe("SystemdUnitCheck controller tests", func() {
})))
})

It("should not report unhealthy for a disabled unit that is in a failed state", func() {
writeOSC(&extensionsv1alpha1.OperatingSystemConfig{
Spec: extensionsv1alpha1.OperatingSystemConfigSpec{
Units: []extensionsv1alpha1.Unit{
{Name: "optional.service", Enable: ptr.To(false)},
},
},
})

fakeDBus.AddUnitsToList(
systemddbus.UnitStatus{Name: "optional.service", ActiveState: "failed"},
)

Eventually(func(g Gomega) *corev1.NodeCondition {
return getNodeCondition(g)
}).Should(PointTo(MatchFields(IgnoreExtras, Fields{
"Type": Equal(nodeagentconfigv1alpha1.ConditionTypeSystemdUnitsReady),
"Status": Equal(corev1.ConditionTrue),
"Reason": Equal("AllUnitsHealthy"),
})))
})

It("should also monitor gardener-node-agent's own units", func() {
writeOSC(&extensionsv1alpha1.OperatingSystemConfig{
Spec: extensionsv1alpha1.OperatingSystemConfigSpec{
Expand Down