Our ES cluster lives on AWS.
We have 3 master nodes and 4 data nodes.
But JVM memory pressure is not distributed evenly across them.
2 of them are having usually around %10 but last one is usually fixed at %60.
Any reason why is this the case?
Garbage collection generally kicks in once heap usage reaches 75%, so as long as the heap is below this there is usually no problem. The fact that the nodes have different values may just be because they are under different load or garbage collected at different points in the past.
This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.