| 摘要 |
The invention relates to the field of content delivery networks (CDN networks), and more particularly to a method for distributing the load among servers in such networks. In the present method: a request for a service is received from a user terminal by a server, the user address is identified, a CDN server address selected from a plurality of CDN server addresses is matched to the user address, and a path is selected for connecting the user to the relevant CDN server. The path is selected on the basis of at least one route metric selected from the group: delay, delay variation, load, percentage (or number) of packets lost, hop count, autonomous system count and Q-criterion, and a range of permissible values is provided for each route metric. The activity of all of the CDN servers is monitored in real time using a failure detection means connected to a server; in the event that a CDN server failure is detected, information about the status and address of the CDN server in question is entered into the relevant database of a server and is no longer taken into consideration during selection of a route. |
