Cloud computing load balancing method and equipment

Abstract

The invention discloses a cloud computing load balancing method and cloud computing load balancing equipment, and belongs to the technical field of computer networks. The cloud computing load balancing method comprises the following steps of: selecting a service copy according to the load capacity of each server in a service combination request raised by a user, establishing a service path for a server application distributed service routing method, and transmitting the service combination request raised by the user to the user along the service path. The cloud computing load balancing equipment comprises a service combination request module, a service copy selecting module and a service path establishing module. The load capacity of the server is acquired according to the load fluctuation condition of the server; because the load fluctuation condition of the server is continuously and adaptively adjusted, the load capacity of the server is adaptively changed; and the proper service copy is selected according to the load capacity of the server so as to ensure comparatively uniform load distribution on each copy and realize adaptive load balance of the server.

Description

technical field [0001] The invention relates to the technical field of computer networks, in particular to a cloud computing load balancing method and equipment. Background technique [0002] Cloud Computing is the development of Distributed Computing, Parallel Computing and Grid Computing. Its basic principle is to distribute computing tasks to multiple computers through the network. The computer becomes a node of the cloud computing network. In addition to public computing and SaaS (Software-as-a-service, software as a service), cloud computing provides services including network services, platform as a service, and MSP (Management Service Provider, management service provider) and other forms. Cloud computing services transmit programs to thousands of users through browsers. The advantage of "cloud" lies in its infrastructure management. The increasingly mature virtual technology provides powerful technical support for this service, enabling "cloud" to pass Automate dep...

AI Technical Summary

Problems solved by technology

[0007] 1. The multi-layer conversion graph of the LIAC method needs to copy the overlay network graph k+1 times, and the storage space overhead and calculation time overhead are relatively large;

[0008] 2. The LIAC method needs to know the global topology of the service coverage network when constructing a multi-layer transition graph. The calculation of the LIAC measure needs to know the current load and the maximum load value of each server. In the actual network environment, the maximum load of the server is often It is difficult to estimate in advance, and the current load of the server is also difficult to measure

[0009] 3. Each server needs to maintain the global network topology and load information. If a server joins or exits the system, the topology of the entire multi-layer conversion graph will change. The LIAC method needs to be recalculated, and the cost is relatively large

The LIAC method is actually suitable for a centralized computing environment, and is not suitable for the dynamic joining and exit of service nodes in large-scale networks.

Images