| 摘要 |
A method for operating a cluster of N server nodes to service client requests received on a network. Each client request is directed to one of C customers hosted on the server cluster. Each customer is identified by a domain name, and each server node is identified by an address on a network. In the method of the present invention, the customers are grouped into N groups, each group being assigned to a corresponding one of the server nodes. Configuration information is provided to a Domain Name Server (DNS), the information defining the correspondence between each of the customers and one of the server nodes assigned to one of the groups containing that customer. The DNS provides the address of the server node in response to a message specifying the domain name of the customer. The client then directs its request to the identified server node utilizing the address provided by the DNS. In the preferred embodiment of the present invention, the grouping of the customers depends on a measurement of the computational resources required to service the client requests for each of the customers. In embodiments in which the activity associated with each request is primarily the return of files stored in the cluster, the measurement of computational resources includes the size of the files returned by each client-within a time period and the communication bandwidth needed to service the requests.
|
