A virtual machine dynamic migration method based on differences in user service quality requirements

Abstract

The invention belongs to the technical field of devices for executing special programs, and discloses a method for dynamic migration of virtual machines based on differences in user service quality requirements. According to the differences in QoS requirements requested by different users in the system, the distribution in physical hosts is changed. ;Determine the adaptive virtual machine overload migration threshold according to the current system load; use the light load host detection algorithm to find out the physical host with the current load too low, and migrate and merge the virtual machine instances. The present invention can optimize the overall energy consumption of the cloud data center on the basis of guaranteeing the user's QoS requirement, and obtain superior performance compared with the existing algorithm. The present invention improves the CPU utilization rate of the physical host by changing the difference of the requested QoS requirements in each physical host, thereby reducing the number of physical machines required to carry requests and reducing the energy consumption of the data center.

Description

technical field [0001] The invention belongs to the technical field of devices for executing special programs, and in particular relates to a virtual machine dynamic migration method based on differences in user service quality requirements. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: With the rapid development of the Internet and the rapid growth of user data, cloud computing is widely used for real-time processing of large-scale data. The cloud data center can provide services by allocating virtualized resources on demand according to the needs of users. Although the emergence of cloud computing can effectively meet the large-scale computing needs of users, it also leads to a large amount of energy consumption. The emergence of virtualization technology enables multiple virtual machines to run on one physical machine, and applications run directly on the virtual machines, thereby reducing the number of ...

AI Technical Summary

Problems solved by technology

As a result, the lower CPU utilization of the physical server requires more physical hosts to provide services for the same number of requests, which increases the overall energy consumption of the system.

[0003] To sum up, the problem existing in the prior art is that currently, the influence of the differences in QoS requirements of users on the allocation of server resources is not considered in the dynamic migration of virtual machines, thus causing a waste of server resources to a certain extent.

The CPU utilization of each server will be limited by the most stringent QoS requirements among all user requests within the host. Therefore, when the QoS of a host's internal requests is too different, the host's CPU will be severely limited. , leading to the inability of resources to be fully utilized, thus requiring more physical hosts to carry requests of the same scale, which also leads to an increase in the overall energy consumption of the system

[0004] The difficulty and significance of solving the above technical problems: When adjusting the differences in user QoS requirements of each physical host in the system, it is necessary to face such a problem: when the system first starts serving, the number of internal user requests is small, With the arrival of user requests, the user QoS differences within the host are unstable, and due to the low system load, optimizing the QoS differences at this time has little impact on energy consumption and may even worsen performance

When the load of the system is close to saturation, because the remaining resources of each host in the system are less, and the live migration process of the virtual machine requires additional resources, there may not be enough resources for the algorithm to perform the live migration process of the virtual machine.

Images