Method and apparatus for cluster data processing

摘要

A cluster data processing method and system based on a unique identity control without requiring continuous network connection between the servers in the cluster and an external computer. The cluster sends a first data containing a controlling identity record to the external computer. The controlling identity record includes a unique identity and a control information. A load-balancing device of the cluster receives from the external computer a second data, which contains a controlling identity record corresponding to that of the first data. The cluster routes the second data according to the control information in the controlling identity record of the second data. The disclosed method and system may help avoid the overload problem of server resources and prevent low performance caused by continuous network connection that has to be maintained between the cluster and external server 190 in existing technology.

主权项

1. A method for processing data of a server cluster including at least two servers, the method comprising:
adding control information to a unique identity to expand the unique identity into a controlling identity record; generating first data including the controlling identity record and processing data; sending the first data to an external computing device; receiving second data from the external computing device, the second data including the controlling identity record and a processing result of the processing data; and transmitting the second data to a first server based at least on the control information, wherein the control information comprises one or more of version information of a program that processes the second data or a time threshold for the first server to process the second data, and the controlling identity record comprises information associated with a purchase order.