piby
04/12/2024, 6:55 AM3 * Server (4 cores, 14 GB, 1000 GB), 3 * Controller (4 cores, 14 GB, 100 GB), 3 * Broker (4 cores, 14 GB, 100GB), 5 * Zookeeper (4 cores, 14 GB, 100 GB)
We are using 6 * c6a.8xlarge (32 cores and 64 GB) machines on AWS EKS
1. It seems like controller is hitting memory limits while zookeeper minions are barely crossing 2GB memory
2. No component is using cpu as much as we initially expected.
We are thinking of the following modifications
1. Change the machine type to memory optimized machines instead (r7g.4xlqrge with 16 cores and 128 GB memory)
2. Give 4 cores to each pod.
3. Give 32 GB to servers and controllers
4. Give 16 GB to brokers and minions and zookeeper
What do you guys suggest?