We have a pod with ES 5.6.16 container running in Kubernetes cluster. Only one instance running. Can not update the version or horizontally scale. This poor instance needs to deal with significant amount of load. Gave it 32 gb heap, 64 gb mem, 32 cpu. Still struggling, long gc and suspensions. Any one tried giving ES very big amount of cpu and mem? Like insane amount, e.g. 64 cpu, 96 gb of heap, 120 mem? Yes we can run a c5.18xlarge for now. Thanks in advance.
Welcome to our community! 
Unfortunately;
You can go a larger instance, but with both of these limits you are not going to be able to do much to improve the situation.
1 Like
Thanks for the reply @warkolm. Just need to stabilise it till we move to a newer solution. Any other suggestions? Currently it’s needing multiple restarts daily given the load. Even if the full gc goes less frequent so that a daily restart fixes it will be a good option for now.
This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.