System and method for realizing energy consumption control through virtual machine migration

Abstract

The invention relates to a system and a method for realizing energy consumption control through controlling virtual machine migration in a cloud computation server cluster system, which are used for monitoring use information of virtual machines on various master servers in the sever cluster system. The method comprises the steps of: under a condition when a virtual machine on a master server is monitored to meet a virtual machine migration condition, migrating the virtual machine on the master server to other master servers; and then computing a total electricity consumption of the various master servers, and carrying out feedback control on the migration of a virtual machine load again according to the electricity consumption. According to the system and the method, by monitoring the electricity consumption of the master servers, the load migration process of the virtual machines is subjected to feedback control according to the electricity consumption, so that the loads of the various master servers are balanced after load migration, and a CPU (central processing unit) cannot be placed in an overloading working state, so that the response speed of the CPU to the user virtual machine can be guaranteed, and the energy consumption of the CPU can also be guaranteed.

Description

technical field [0001] The invention belongs to the technical field of virtualization, and in particular relates to a system and method for realizing energy consumption control through virtual machine migration in cloud computing. Background technique [0002] Currently, cloud computing technology is a technology hotspot in the IT industry. Many companies are actively deploying their own private clouds, and many companies are considering providing public cloud services to the public. It is foreseeable that future cloud computing technology will bring new opportunities to the Internet. Revolution, people's life and work will be more based on the Internet. Although cloud computing technology itself improves the efficiency of equipment use through centralized computing, and saves energy consumption. However, energy saving is the demand of the whole society for energy saving and emission reduction. A large number of computing and storage devices in the cloud computing environme...

AI Technical Summary

Problems solved by technology

[0004] In the prior art, there is a dynamic load balancing mechanism to centrally migrate low-load virtual machines (using "hot migration" technology) to a small number of physical machines, and when there are no more virtual machines on the physical machines, power off the physical machines, Therefore, energy consumption can be reduced. However, since the low-load physical machine is turned off, the load of other physical machines will inevitably increase, so that the CPUs of other physical machines are in a high-load state, and the high-load state not only makes users use virtual machines. The response speed of the system slows down, and the energy consumption of the CPU increases greatly. If some CPUs are in a high load state due to the dynamic load balancing mechanism, resulting in greater energy consumption, then this dynamic load balancing mechanism needs to be corrected. And at present this area has not proposed a kind of technical scheme that can solve this problem

Images