Search

CN-112333279-B - Server deployment method, device, equipment and storage medium

CN112333279BCN 112333279 BCN112333279 BCN 112333279BCN-112333279-B

Abstract

The invention relates to the technical field of clouds and discloses a server allocation method, device and equipment and a storage medium. The cloud computing task management method comprises the steps of obtaining cloud computing tasks and corresponding task deadlines, determining a plurality of servers for processing the cloud computing tasks, dividing the plurality of servers into reliable servers and unreliable servers according to the task deadlines of the cloud computing tasks by adopting a preset task failure prediction method, performing task migration matching on each unreliable server and each reliable server to obtain a plurality of server groups capable of being used for completing the cloud computing tasks, respectively calculating first allocation benefits of each server group and second allocation benefits of each reliable server, and selecting one reliable server or server group with the highest allocation benefits to execute the cloud computing tasks based on the first allocation benefits and the second allocation benefits. According to the method and the device, each influence factor of the cloud computing task on the server selection is considered, and the matching degree of the cloud computing task and the corresponding processing server is improved.

Inventors

  • HUANG LIYUAN

Assignees

  • 平安科技（深圳）有限公司

Dates

Publication Date
20260508
Application Date
20201111

Claims (10)

  1. 1. The server allocation method is characterized by comprising the following steps: Acquiring a cloud computing task and corresponding task deadlines, and determining a plurality of servers for processing the cloud computing task; dividing the servers into reliable servers and unreliable servers by adopting a preset task failure prediction method according to the task deadline; performing task migration matching on each unreliable server and each reliable server in sequence to obtain a plurality of server groups capable of being used for completing the cloud computing task, wherein each server group comprises one unreliable server and one reliable server; Respectively calculating first allocation benefits of each server group and second allocation benefits of each reliable server; And selecting a reliable server or a server group with the highest allocation benefit to execute the cloud computing task based on the first allocation benefit and the second allocation benefit.
  2. 2. The server deployment method of claim 1, wherein the dividing the plurality of servers into reliable servers and unreliable servers using a preset task failure prediction method according to the task deadline comprises: respectively predicting the completion time of the plurality of servers for processing the cloud computing task by adopting the preset task failure prediction method; sequentially judging whether each completion time is before the task deadline; If yes, the corresponding server is divided into reliable servers, otherwise, the corresponding server is divided into unreliable servers.
  3. 3. The server deployment method according to claim 2, wherein the employing the preset task failure prediction method to respectively predict the completion time of the plurality of servers to process the cloud computing task includes: Determining the load capacity of the cloud computing task and the computing capacity of each server; and based on the load capacity and the computing capacity, respectively predicting the completion time of the plurality of servers for processing the cloud computing task by adopting the preset task failure prediction method.
  4. 4. The server deployment method of claim 3, wherein performing task migration matching on each unreliable server and each reliable server in turn, obtaining a plurality of server groups available for completing the cloud computing task comprises: Sequentially selecting an unreliable server and a reliable server, and respectively determining the computing capacities of the unreliable server and the reliable server; Calculating a migration time node of the cloud computing task from the unreliable server to the reliable server based on the computing capacity and the load amount of the two; Judging whether the migration time node is before a preset time node or not; If yes, the corresponding unreliable server and the reliable server are paired, and a plurality of corresponding server groups are obtained.
  5. 5. The server deployment method of claim 4, wherein the calculating the first deployment proceeds for each of the server groups, respectively, comprises: determining a first cost factor of an unreliable server and a second cost factor of a reliable server in each server group respectively; Based on the first cost factors and the computing capacities of unreliable servers, respectively computing first initial allocation benefits of each server group before the migration time node; Based on the second cost factors and the computing power of the reliable servers, respectively computing second initial allocation benefits of each server group after the migration time node; and determining a first allocation benefit of each server group based on the first initial allocation benefit and the second initial allocation benefit.
  6. 6. The server deployment method of claim 5, wherein said separately calculating the second deployment proceeds for each of the reliable servers comprises: Calculating the reliability factor of each reliable server based on the completion time of each reliable server; and respectively calculating second allocation benefits of each reliable server based on the reliability factors, the second cost factors and the calculation capacities of the reliable servers.
  7. 7. A server allocation device is characterized in that, the server deployment device includes: the cloud computing system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a cloud computing task and corresponding task deadlines and determining a plurality of servers for processing the cloud computing task; the dividing module is used for dividing the servers into reliable servers and unreliable servers by adopting a preset task failure prediction method according to the task deadline; The matching module is used for carrying out task migration matching on each unreliable server and each reliable server in sequence to obtain a plurality of server groups which can be used for completing the cloud computing task, wherein the server groups comprise one unreliable server and one reliable server; The computing module is used for computing first allocation benefits of the server groups respectively and computing second allocation benefits of the reliable servers respectively; and the allocation module is used for selecting a reliable server or a server group with the highest allocation benefit to execute the cloud computing task based on the first allocation benefit and the second allocation benefit.
  8. 8. The server deployment device of claim 7, wherein the partitioning module comprises: The prediction unit is used for respectively predicting the completion time of the plurality of servers for processing the cloud computing task by adopting the preset task failure prediction method; the judging unit is used for judging whether each completion time is before the task deadline in sequence; and the dividing unit is used for dividing the corresponding server into reliable servers if the completion time is before the task deadline, and dividing the corresponding server into unreliable servers if the completion time is not before the task deadline.
  9. 9. The server deployment device is characterized by comprising a memory and at least one processor, wherein the memory stores instructions; The at least one processor invokes the instructions in the memory to cause the server provisioning device to perform the server provisioning method of any of claims 1-6.
  10. 10. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the server provisioning method according to any of claims 1-6.

Description

Server deployment method, device, equipment and storage medium Technical Field The present invention relates to cloud technologies, and in particular, to a server deployment method, device, equipment, and storage medium. Background At the heart of cloud computing is the provision of services in the form of leased computing resources to users after the virtualization of computing resources of one or more data centers. The function of the cloud computing resource management system is to receive resource requests from cloud computing users and package specific resources into services to resource requesters. The prior art selects appropriate computing resources from the standpoint of computing power, reliability, cost factors, etc. of the resources. However, from any point of view, only one or more factors are considered, and comprehensive factors are not comprehensively considered. The prior art only randomly selects the physical resources meeting the task computing capability request, not only does not consider the reliability of the resources, but also does not consider the cost factor of the resources, and meanwhile, the resources with sufficient computing capability but unreliable are not utilized, so that the waste of the resources can be caused, the waste of the computing resources can be caused when the resources with the best computing capability are selected for the task each time, and the operation cost factor of a cloud service provider is ignored. The matching degree of the existing computing resource adjustment to the computing task is not high enough. Disclosure of Invention The invention mainly aims to solve the technical problem that the matching degree of the existing computing resource allocation to the computing task is not high enough. The first aspect of the present invention provides a server deployment method, including: Acquiring a cloud computing task and corresponding task deadlines, and determining a plurality of servers for processing the cloud computing task; dividing the servers into reliable servers and unreliable servers by adopting a preset task failure prediction method according to the task deadline; Performing task migration matching on each unreliable server and each reliable server in sequence to obtain a plurality of server groups capable of being used for completing the cloud computing task, wherein each server group comprises one unreliable server and one reliable server; Respectively calculating first allocation benefits of each server group and second allocation benefits of each reliable server; And selecting a reliable server or a server group with the highest allocation benefit to execute the cloud computing task based on the first allocation benefit and the second allocation benefit. Optionally, in a first implementation manner of the first aspect of the present invention, the dividing the plurality of servers into reliable servers and unreliable servers according to the task deadline by using a preset task failure prediction method includes: respectively predicting the completion time of the plurality of servers for processing the cloud computing task by adopting the preset task failure prediction method; sequentially judging whether each completion time is before the task deadline; If yes, the corresponding server is divided into reliable servers, otherwise, the corresponding server is divided into unreliable servers. Optionally, in a second implementation manner of the first aspect of the present invention, the predicting, by using the preset task failure prediction method, the completion time of the processing of the cloud computing task by the plurality of servers includes: Determining the load capacity of the cloud computing task and the computing capacity of each server; and based on the load capacity and the computing capacity, respectively predicting the completion time of the plurality of servers for processing the cloud computing task by adopting the preset task failure prediction method. Optionally, in a third implementation manner of the first aspect of the present invention, the performing task migration matching on each unreliable server and each reliable server sequentially obtains a plurality of server groups that may be used to complete the cloud computing task, where the server group includes one unreliable server and one reliable server, and the method includes: Sequentially selecting an unreliable server and a reliable server, and respectively determining the computing capacities of the unreliable server and the reliable server; Calculating a migration time node of the cloud computing task from the unreliable server to the reliable server based on the computing capacity and the load amount of the two; Judging whether the migration time node is before a preset time node or not; If yes, the corresponding unreliable server and the reliable server are paired, and a plurality of corresponding server groups are obtained. Optionally, in a fourth imple