Hallo, what is the best way to ensure the GKE cluster autoscaler launches new nodes *before* a new pod is requested and *not* after a new pod has been requested?
I'm looking for ways to minimize the pod startup time and I was hoping that the time needed to launch a new node (cluster-scale-up) could be reliably removed from the pod-startup-time. A promising thought was to configure the GKE autoscaler to always hold free capacity for one-more-pod available, but it seem this feature is not (yet) implemented. It's unclear to me if or when the feature will be implemented: https://issuetracker.google.com/issues/69388850 Are there other ways to achieve this? Thank you very much for your ideas and suggestions! -- You received this message because you are subscribed to the Google Groups "Kubernetes user discussion and Q&A" group. To unsubscribe from this group and stop receiving emails from it, send an email to kubernetes-users+unsubscr...@googlegroups.com. To post to this group, send email to kubernetes-users@googlegroups.com. Visit this group at https://groups.google.com/group/kubernetes-users. For more options, visit https://groups.google.com/d/optout.
