Best-effort high availability for single-replica Kubernetes workloads: no downtime from announced node disruptions (drains, upgrades, consolidation, spot reclaims) without a standing second replica.
kubernetes golang spot-instances high-availability sre kubernetes-operator eviction cost-optimization cluster-autoscaler helm-chart finops eks admission-webhook karpenter pod-disruption-budget node-drain single-replica
-
Updated
Aug 25, 2026 - Go