CN-121996355-A - Virtual machine scheduling method, device, equipment, storage medium and product

CN121996355ACN 121996355 ACN121996355 ACN 121996355ACN-121996355-A

Abstract

The invention discloses a virtual machine scheduling method, a virtual machine scheduling device, virtual machine scheduling equipment, a storage medium and a virtual machine scheduling product. The method comprises the steps of determining resource demand of a virtual machine to be migrated in multiple resource dimensions, obtaining multi-dimensional allocable resource information of physical nodes in a cluster, determining a first candidate node list according to preset resource priority and the multi-dimensional allocable resource information of the physical nodes, obtaining multi-dimensional available resource information of the physical nodes in the cluster, determining a second candidate node list according to the preset resource priority and the multi-dimensional available resource information of the physical nodes, and determining target migration physical nodes corresponding to the virtual machine to be migrated according to the first candidate node list and the second candidate node list. The invention comprehensively considers the demand of the virtual machine in a plurality of resource dimensions and the allocable resources and the available resources of each physical node in the corresponding resource dimensions, and ensures that the screened target migration physical node is more adaptive to the virtual machine.

Inventors

FAN PENGPENG
WANG SHUAI
WANG TONG
HU YUAN
HuangFu Yuhua

Assignees

北京联创信安科技股份有限公司

Dates

Publication Date: 20260508
Application Date: 20260127

Claims (10)

1. A virtual machine scheduling method, comprising: Determining resource demand of the virtual machine to be migrated in a plurality of resource dimensions; Acquiring multidimensional allocatable resource information of each physical node in a cluster, and determining a first candidate node list according to a preset resource priority and the multidimensional allocatable resource information of each physical node, wherein the cluster is associated with the virtual machine to be migrated, and the multidimensional allocatable resource information comprises the residual allocatable quantity of the physical node in a resource dimension corresponding to the resource demand; Acquiring multidimensional available resource information of each physical node in the cluster, and determining a second candidate node list according to the preset resource priority and the multidimensional available resource information of each physical node, wherein the multidimensional available resource information comprises the residual available quantity of the physical node in a resource dimension corresponding to the resource demand; And determining a target migration physical node corresponding to the virtual machine to be migrated according to the first candidate node list and the second candidate node list.
2. The virtual machine scheduling method of claim 1, wherein determining the resource demand of the virtual machine to be migrated in the plurality of resource dimensions comprises: determining resource demand coefficients of the virtual machine to be migrated on each resource dimension according to the historical running state of the virtual machine to be migrated, wherein the resource dimensions comprise at least one of computing resources, memory resources, network resources and storage resources; and determining the resource demand of the virtual machine to be migrated in each resource dimension according to the resource initial set value of the virtual machine to be migrated in each resource dimension and the corresponding resource demand coefficient in each resource dimension.
3. The virtual machine scheduling method of claim 1, wherein the multi-dimensional allocatable resource information comprises at least one of allocatable computing resource information, allocatable memory resource information, allocatable network resource information, and allocatable storage resource information, wherein the multi-dimensional available resource information comprises at least one of available computing resource information, available memory resource information, available network resource information, and available storage resource information; the acquiring the multidimensional allocable resource information of each physical node in the cluster comprises at least one of the following steps: for each physical node, determining the allocable computing resource information of the current physical node according to the computing resource total amount, the preset computing resource excess ratio and the resource initial set value total amount of the computing resources of all virtual machines in the current physical node; For each physical node, determining the assignable memory resource information of the current physical node according to the total memory resource amount in the current physical node, the preset memory resource excess ratio and the total resource initial set value total amount of the memory resources of all virtual machines in the current physical node; For each physical node, determining the allocable network resource information of the current physical node according to the total network resource amount in the current physical node and the average value of the network resource usage amount of the current physical node in a first preset history period; for each physical node, determining the allocable storage resource information of the current physical node according to the total amount of storage resources in the current physical node and the average value of the storage resource usage amount of the current physical node in a second preset history period; The obtaining multidimensional available resource information of each physical node in the cluster comprises at least one of the following steps: For each physical node, determining available computing resource information of the current physical node according to the total computing resource amount in the current physical node and the average computing resource utilization rate of the current physical node in a third preset history period; for each physical node, determining available memory resource information of the current physical node according to the total memory resource amount in the current physical node and the average memory resource utilization rate of the current physical node in a fourth preset history period; For each physical node, determining available network resource information of the current physical node according to the total network resource amount in the current physical node and the highest network resource usage amount of the current physical node in a fifth preset history period; And for each physical node, determining the available storage resource information of the current physical node according to the total amount of storage resources in the current physical node and the highest usage amount of the storage resources of the current physical node in a sixth preset history period.
4. The virtual machine scheduling method according to claim 1, wherein the determining the first candidate node list according to the preset resource priority and the multidimensional allocatable resource information of each physical node includes: determining a target resource dimension with highest priority in a plurality of resource dimensions according to the preset resource priority; taking the allocatable resource information corresponding to the target resource dimension in the multidimensional allocatable resource information of each physical node as target dimension allocatable resource information; Sequencing all the physical nodes according to the target dimension allocable resource information so as to determine first ranking information of all the physical nodes; And screening out physical nodes meeting the resource demand in each resource dimension according to the multidimensional allocable resource information of each physical node, and determining a first candidate node list according to screening results, wherein each physical node in the first candidate node list is arranged according to the first ranking information.
5. The method for scheduling virtual machines according to claim 1, wherein determining the second candidate node list according to the preset resource priority and the multidimensional available resource information of each physical node includes: determining a target resource dimension with highest priority in a plurality of resource dimensions according to the preset resource priority; Taking available resource information corresponding to the target resource dimension in the multidimensional available resource information of each physical node as target dimension available resource information; sorting all the physical nodes according to the available resource information of the target dimension so as to determine second ranking information of all the physical nodes; And screening out physical nodes meeting the resource demand in each resource dimension according to the multidimensional available resource information of each physical node, and determining a second candidate node list according to screening results, wherein each physical node in the second candidate node list is arranged according to the second ranking information.
6. The virtual machine scheduling method according to claim 1, wherein physical nodes in the first candidate node list and the second candidate node list each carry ranking information, and the ranking information is determined according to the preset resource priority and multidimensional allocatable resource information of the physical nodes or multidimensional available resource information of the physical nodes; The determining, according to the first candidate node list and the second candidate node list, the target migration physical node corresponding to the virtual machine to be migrated includes: For each physical node in the first candidate node list, finding a target physical node with the same node label in the second candidate node list according to the node label of the current physical node; adding the first ranking of the current physical node in the first candidate node list and the second ranking of the target physical node in the second candidate node list to obtain the comprehensive ranking of the current physical node; And taking the physical node with the highest comprehensive ranking as the target migration physical node corresponding to the virtual machine to be migrated.
7. A virtual machine scheduling apparatus, comprising: the resource demand determining module is used for determining the resource demand of the virtual machine to be migrated in a plurality of resource dimensions; The first candidate node list determining module is used for acquiring multi-dimensional allocatable resource information of each physical node in the cluster, and determining a first candidate node list according to a preset resource priority and the multi-dimensional allocatable resource information of each physical node, wherein the cluster is associated with the virtual machine to be migrated, and the multi-dimensional allocatable resource information comprises the residual allocatable quantity of the physical node in a resource dimension corresponding to the resource demand; The second candidate node list determining module is used for acquiring multidimensional available resource information of each physical node in the cluster and determining a second candidate node list according to the preset resource priority and the multidimensional available resource information of each physical node, wherein the multidimensional available resource information comprises the residual available quantity of the physical node in a resource dimension corresponding to the resource demand; And the target migration physical node determining module is used for determining the target migration physical node corresponding to the virtual machine to be migrated according to the first candidate node list and the second candidate node list.
8. An electronic device, the electronic device comprising: At least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the virtual machine scheduling method of any one of claims 1-6.
9.A computer readable storage medium storing computer instructions for causing a processor to implement the virtual machine scheduling method of any one of claims 1-6 when executed.
10. A computer program product, characterized in that the computer program product comprises a computer program which, when executed by a processor, implements the virtual machine scheduling method according to any one of claims 1-6.

Description

Virtual machine scheduling method, device, equipment, storage medium and product Technical Field The present invention relates to the field of resource scheduling technologies, and in particular, to a virtual machine scheduling method, device, apparatus, storage medium, and product. Background With the development of computer technology and virtualization technology, the application of super-fusion platform and distributed architecture is more and more extensive, and the deployment and scheduling of virtual machines serving as core carriers of the virtualization technology have become key links of resource scheduling. How to formulate a reasonable virtual machine scheduling strategy to realize the efficient utilization of physical resources in a super-fusion platform and a distributed architecture becomes the key point of current research and practice. In the prior art, when determining a target physical node for virtual machine migration, a fixed scheduling policy is adopted to select the target migration node by taking a single resource index (for example, CPU utilization) as a reference basis. For example, taking the CPU resource allowance as a reference index, selecting a physical node with the most abundant CPU resource in the cluster as a target migration node of the virtual machine. However, the above solution only depends on a single resource to determine the target migration node, which often results in a new resource bottleneck after the migration of the virtual machine, and it is difficult to adapt to the resource allocation requirement in a complex scenario. Disclosure of Invention The invention provides a virtual machine scheduling method, a device, equipment, a storage medium and a product, which are used for screening out target migration physical nodes of a virtual machine rapidly and efficiently. According to an aspect of the present invention, there is provided a virtual machine scheduling method, including: Determining resource demand of the virtual machine to be migrated in a plurality of resource dimensions; Acquiring multidimensional allocatable resource information of each physical node in a cluster, and determining a first candidate node list according to a preset resource priority and the multidimensional allocatable resource information of each physical node, wherein the cluster is associated with the virtual machine to be migrated, and the multidimensional allocatable resource information comprises the residual allocatable quantity of the physical node in a resource dimension corresponding to the resource demand; Acquiring multidimensional available resource information of each physical node in the cluster, and determining a second candidate node list according to the preset resource priority and the multidimensional available resource information of each physical node, wherein the multidimensional available resource information comprises the residual available quantity of the physical node in a resource dimension corresponding to the resource demand; And determining a target migration physical node corresponding to the virtual machine to be migrated according to the first candidate node list and the second candidate node list. According to another aspect of the present invention, there is provided a virtual machine scheduling apparatus, including: the resource demand determining module is used for determining the resource demand of the virtual machine to be migrated in a plurality of resource dimensions; The first candidate node list determining module is used for acquiring multi-dimensional allocatable resource information of each physical node in the cluster, and determining a first candidate node list according to a preset resource priority and the multi-dimensional allocatable resource information of each physical node, wherein the cluster is associated with the virtual machine to be migrated, and the multi-dimensional allocatable resource information comprises the residual allocatable quantity of the physical node in a resource dimension corresponding to the resource demand; The second candidate node list determining module is used for acquiring multidimensional available resource information of each physical node in the cluster and determining a second candidate node list according to the preset resource priority and the multidimensional available resource information of each physical node, wherein the multidimensional available resource information comprises the residual available quantity of the physical node in a resource dimension corresponding to the resource demand; And the target migration physical node determining module is used for determining the target migration physical node corresponding to the virtual machine to be migrated according to the first candidate node list and the second candidate node list. According to another aspect of the present invention, there is provided an electronic apparatus including: At least one processor, and A memory communicatively c