We have neo4j configured in casual cluster on Kubernetnes based setup. All components are deployed on individual machine with size: t2.xlarge on aws. And we use pod affinity to schedule a deployment. While working with application under stress, we observed that there is considerable system load only one machine. For example see this: First neo4j machine for core:

and second machine for core in same cluster:

We have bolt+router protocol configured in backend. I am not sure what causing this much resource utilization on one machine whereas others work in minimum.

I checked memory consumption on pod level as well. Neo4j-1 takes 9gb of memory whereas others are taking around 4gb. So my questions is, is this expected behavior?