I have a many cluster servers. Each cluster typically has 4 servers. Thousands of users use the cluster. What would be the best strategy to load balance ? Right now every user request is directed in such a way so utilization is divided among 4 servers - so if there are 100 requests, every server in the cluster of 4 will end up handling 25 each. I was wondering if there is a better strategy to follow so that every server is utilized well and we still end up with a scalable system ?
feedback
|
|
It really does depend on the way they are being used, what services are being used, and how they are configured. A little more info would be extremely helpful. Without more info, I would say first identify if you are having problems, and if so at what point are you seeing them, network layer, application layer, etc. | |||
|
feedback
|
