| 摘要 |
A method and apparatus for distributing load between a plurality of servers, for handling incoming service requests in a server system. When a service request in received in an access node, a primary server is assigned out of a set of primary servers, using a first scheduling algorithm, for performing a processing task for the received service request. The first scheduling algorithm is capable of selecting any primary server. Further, a secondary server is assigned out of a set of secondary servers, using a second scheduling algorithm, for performing a storing task for the received service request. The second scheduling algorithm is capable of selecting one specific secondary servers for a storing task.
|
