Abstract: Example methods and systems for service-aware global server load balancing are described. One example may involve a first load balancer receiving, from a client device, a request to access a service associated with an application deployed in at least a first cluster and a second cluster. In response to determination that a first pool in the first cluster is associated with an unhealthy status, the first load balancer may identify a second pool implementing the service in the second cluster, the second pool being associated with a healthy status and includes one or more second backend servers selectable by a second load balancer to process the request. Failure handling may be performed by interacting with the client device, or the second load balancer, to allow the client device to access the service implemented by the second pool in the second cluster.