Scheduling method and device, scheduling server, edge server and scheduling system

Abstract

The embodiment of the invention provides a scheduling method and device, a scheduling server, an edge server and a scheduling system. The method comprises the steps that a first edge server sends a flow information query request for a target data flow, and the scheduling server sends a flow pulling instruction when determining that the target data flow is a hot flow, so the first edge server obtains the target data stream from the upper layer server and sends the target data stream to the client, and when the target data stream is determined to be a cold stream, the identification information of the target edge server is sent to the first edge server, so that the first client obtains the target data stream based on the forwarded identification information of the target edge server. When the target data stream requested to be acquired by the client is the hot stream, the target data stream is acquired from the upper server, and the target data stream does not need to be acquired from the target edge server. Therefore, the acquisition request of the client with the target data stream requested to be acquired as the hot stream does not need to be scheduled, so that the time expenditure for acquiring data by part of clients using the CDN is reduced.

Description

technical field [0001] The present invention relates to the technical field of network communication, in particular to a scheduling method, device, scheduling server, edge server and scheduling system. Background technique [0002] CDN (Content Delivery Network, Content Distribution Network) is an intelligent virtual network built on the basis of existing networks. By caching content on edge servers deployed in various places, users can obtain the required content nearby and reduce network congestion. Improve user access response speed and hit rate. [0003] In order to make CDN transmission content faster and more stable, in the prior art, CDN scheduling is usually performed. Specifically, after receiving a data acquisition request sent by any client, the edge server in the CDN will send the data acquisition request forward to the scheduling server, and the scheduling server re-determines an edge server, and then returns the IP address of the re-determined edge server to t...

AI Technical Summary

Problems solved by technology

[0004] It can be seen that in the prior art, the above scheduling operations are usually performed for all data acquisition requests sent by clients, and since all clients need to send two data fetching requests, therefore, the time overhead for all clients using the CDN to fetch data is increased

Images