Horizontal Pod Autoscaler: why it scales late, or not at all
The requests dependency nobody mentions, how the HPA replica formula really works, stabilisation windows, and why CPU is the wrong signal for most queue workloads.
Tag
SRE
Every post tagged SRE — practitioner notes from running Kubernetes, OpenShift and DevOps tooling in production for clients across the EU and the Gulf.
3 posts
PodDisruptionBudgets: the reason your node drain hangs
What a PDB does and does not protect against, the single-replica trap that blocks upgrades forever, and how to set minAvailable so maintenance can still happen.
Why OpenShift upgrades stall, and how to clear them
Upgrade channels, MachineConfigPools and the four things that block a cluster upgrade, plus how to tell a slow upgrade from a stuck one before you intervene.