Triggering method for dynamic migration of virtual machine on the basis of prediction, and implementation system
A dynamic migration and virtual machine technology, applied in the field of cloud computing virtualization, can solve problems such as wasting resources, thresholds cannot be effectively determined, server downtime, etc., and achieve the effects of ensuring load balancing, preventing frequent migration, and avoiding uncertainty
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0055] A method for triggering dynamic migration of virtual machines based on prediction, such as figure 1 As shown, the initial setting is Count=0, N=0, and Count refers to the sum of the number of times the predicted resource value of the virtual machine is greater than the upper threshold H of resource utilization and the number of times the predicted resource value of the virtual machine is smaller than the lower threshold L, and N is Refers to the number of times to obtain the resource forecast value of the virtual machine; it includes the following steps:
[0056] (1) monitor the utilization rate of the resource of virtual machine, the total size of the resource of virtual machine by libvirt coding, suppose the upper and lower thresholds of the resource utilization rate of virtual machine are respectively H, L; H=80% and L=20 %; The resource of the virtual machine is CPU, memory or bandwidth;
[0057] (2) Assuming that at a certain moment step (1) obtains the resource u...
Embodiment 2
[0084] The implementation system of the method for triggering virtual machine live migration based on prediction described in Embodiment 1, such as figure 2 As shown, it includes a monitoring module, a probability prediction module, a running module, a freezing module, and a wake-up module;
[0085] The monitoring module, the probability prediction module, and the running module are connected in sequence; the running module is connected to the freezing module and the waking module respectively;
[0086] The monitoring module is used for: monitoring the resource utilization rate of the virtual machine and the total size of the resource of the virtual machine;
[0087] The probability prediction module is used to: use the gray prediction method to predict the predicted value of the resource utilization of the virtual machine through the resource information obtained from the monitoring module; the gray prediction method described in this paper is mainly implemented in this modu...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


