Method, system, device and storage medium for initial deployment of virtual machines in cloud computing

Abstract

The present invention provides a method, a system, a device and a storage medium for initial deployment of virtual machines in cloud computing. The method includes: setting a weight vector according to the importance of CPU, memory, network and storage on a physical host, and setting a real-time load vector of CPU, memory, network and storage according to the current load condition; calculating the comprehensive weighted load of the physical host according to the weight vector and the real-time load vector; calculating the dynamic weighted load of the physical host and the predicted weighted load of the virtual machine deployed on the physical host according to the comprehensive weighted load; and determining the location of the initial deployment of the virtual machine according to the dynamic weighted load and the predicted weighted load. The present invention ensures the balanced utilization and maximized utilization rate of basic resources in the cloud data center, thereby reducing the number of physical servers, reducing energy consumption, and on the other hand, reducing the competition of various basic resources, thereby reducing the impact on the performance of virtual machines.

Description

Technical Field

[0001] The present invention relates to the field of cloud computing, and more particularly, to a method, system, device, and storage medium for initial deployment of virtual machines in cloud computing. Background Art

[0002] Cloud computing can provide enterprises with on-demand computing resources. The modern enterprise IT (Information Technology) infrastructure is gradually migrating from the traditional architecture to the cloud. Cloud computing can make full use of expensive hardware resources through virtualization technology and can also isolate the dependencies between the hardware architecture and the software system, improve the security performance of the system, and increase the utilization rate of computing resources. Virtual servers are easy to expand and create, and they can allocate the required hardware infrastructure according to customer needs, achieving the goals of rapid deployment of customer services, reducing the time for customer services to go online, and saving customer costs.

[0003] With the development of informatization, the scale of cloud data centers is constantly increasing, and the number of physical hosts and virtual hosts in cloud data centers increases with the continuous increase of user needs. The initial deployment of virtual machines, as an important part of cloud platform resource management, its initial deployment location will directly affect the energy consumption of the cloud data center, and different initial deployment locations will also have different impacts on other virtual machines. The existing initial placement strategies of cloud platforms are basically random placement or only detecting whether the memory of the physical machine meets the startup conditions, which will lead to low utilization rate of physical machine resources, increase in energy consumption of the cloud data center and waste of resources. On the other hand, due to the lack of consideration of other dimension resources, it may lead to resource competition with other virtual machines deployed on the same physical host, such as network resources or computing resources, which will not only affect its own performance but also cause the performance of other virtual machines to decline. Summary of the Invention

[0004] In view of this, the purpose of the embodiments of the present invention is to provide a method, system, computer device, and computer-readable storage medium for initial deployment of virtual machines in cloud computing. The present invention comprehensively considers the usage of cpu, memory, network, and storage resources when initially deploying virtual machines, ensuring the balanced utilization and maximized utilization rate of basic resources in the cloud data center, thereby reducing the number of physical servers, reducing energy consumption, and on the other hand, reducing competition for various basic resources, thus reducing the impact on the performance of virtual machines.

[0005] For the above purposes, one aspect of the embodiments of the present invention provides a method for initial deployment of virtual machines in cloud computing, including the following steps: setting a weight vector according to the importance of CPU, memory, network, and storage on a physical host, and setting real-time load vectors of CPU, memory, network, and storage according to the current load situation; calculating the comprehensive weighted load of the physical host according to the weight vector and the real-time load vector; calculating the dynamic weighted load of the physical host and the predicted weighted load of the virtual machine deployed on the physical host according to the comprehensive weighted load; and determining the initial deployment location of the virtual machine according to the dynamic weighted load and the predicted weighted load.

[0006] In some embodiments, the determining the initial deployment location of the virtual machine according to the dynamic weighted load and the predicted weighted load includes: selecting a physical machine whose sum of the dynamic weighted load and the predicted weighted load is less than a threshold as an alternative physical machine; sorting the alternative physical machines in ascending order according to the difference between the sum of the dynamic weighted load and the predicted weighted load and the threshold, and sequentially determining whether the remaining resources in each dimension of the alternative physical machines are all greater than the resources requested by the virtual machine; and selecting the first physical machine whose remaining resources in each dimension are all greater than the resources requested by the virtual machine as the initial deployment location of the virtual machine.

[0007] In some embodiments, the setting a weight vector according to the importance of CPU, memory, network, and storage on a physical host includes: constructing a comparison matrix according to the importance levels of CPU, memory, network, and storage, geometrically averaging the row vectors of the comparison matrix, and normalizing the geometrically averaged row vectors to obtain a weight vector.

[0008] In some embodiments, the calculating the dynamic weighted load of the physical host and the predicted weighted load of the virtual machine deployed on the physical host according to the comprehensive weighted load includes: calculating the average value of the comprehensive weighted load of the physical host and the comprehensive weighted load of all virtual machines deployed on the physical host to obtain the dynamic weighted load of the physical host.

[0009] On the other hand, an embodiment of the present invention provides a system for initial deployment of virtual machines in cloud computing, including: a setting module configured to set a weight vector according to the importance of CPU, memory, network, and storage on a physical host, and set real-time load vectors of CPU, memory, network, and storage according to the current load situation; a first calculation module configured to calculate a comprehensive weighted load of the physical host according to the weight vector and the real-time load vector; a second calculation module configured to calculate a dynamic weighted load of the physical host and a predicted weighted load of a virtual machine deployed on the physical host according to the comprehensive weighted load; and a determination module configured to determine the location of initial deployment of the virtual machine according to the dynamic weighted load and the predicted weighted load.

[0010] In some embodiments, the determination module is configured to: select a physical machine whose sum of the dynamic weighted load and the predicted weighted load is less than a threshold as an alternative physical machine; sort the alternative physical machines in ascending order according to the difference between the sum of the dynamic weighted load and the predicted weighted load and the threshold, and sequentially determine whether each remaining dimension of resources in the alternative physical machines is greater than the resources requested by the virtual machine; and select the first physical machine whose remaining dimensions of resources are all greater than the resources requested by the virtual machine as the location of initial deployment of the virtual machine.

[0011] In some embodiments, the setting module is configured to: construct a comparison matrix according to the importance levels of CPU, memory, network, and storage, perform geometric averaging on the row vectors of the comparison matrix, and normalize the geometric-averaged row vectors to obtain a weight vector.

[0012] In some embodiments, the second calculation module is configured to: calculate the average value of the comprehensive weighted load of the physical host and the comprehensive weighted load of all virtual machines deployed on the physical host to obtain the dynamic weighted load of the physical host.

[0013] In yet another aspect, an embodiment of the present invention further provides a computer device, including: at least one processor; and a memory storing computer instructions that can be run on the processor, and when the instructions are executed by the processor, the steps of the above method are implemented.

[0014] In still another aspect, an embodiment of the present invention further provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above method.

[0015] The present invention has the following beneficial technical effects: When initially deploying virtual machines, the usage of CPU, memory, network, and storage resources is comprehensively considered, ensuring the balanced utilization and maximized utilization rate of the basic resources in the cloud data center. Thus, the number of physical servers can be reduced, energy consumption can be lowered, and on the other hand, the competition for various basic resources can also be reduced, thereby reducing the impact on the performance of virtual machines. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other embodiments can also be obtained based on these drawings.

[0017] Figure 1 Schematic diagram of an embodiment of the method for initial deployment of virtual machines in cloud computing provided by the present invention;

[0018] Figure 2 Schematic diagram of an embodiment of the system for initial deployment of virtual machines in cloud computing provided by the present invention;

[0019] Figure 3 Schematic diagram of the hardware structure of an embodiment of the computer device for initial deployment of virtual machines in cloud computing provided by the present invention;

[0020] Figure 4 Schematic diagram of an embodiment of the computer storage medium for initial deployment of virtual machines in cloud computing provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] To make the objectives, technical solutions, and advantages of the present invention clearer, the following further elaborates on the embodiments of the present invention in detail with reference to specific embodiments and the accompanying drawings.

[0022] It should be noted that all the expressions using "first" and "second" in the embodiments of the present invention are used to distinguish two entities or parameters with the same name but different identities. It can be seen that "first" and "second" are only for the convenience of expression and should not be construed as limitations on the embodiments of the present invention. This will not be elaborated one by one in the subsequent embodiments.

[0023] In the first aspect of the embodiments of the present invention, an embodiment of a method for initial deployment of virtual machines in cloud computing is proposed. Figure 1 Shown is a schematic diagram of an embodiment of the method for initial deployment of virtual machines in cloud computing provided by the present invention. As Figure 1 shown, the embodiments of the present invention include the following steps:

[0024] S1. Set the weight vector according to the importance of CPU, memory, network and storage on the physical host, and set the real-time load vector of CPU, memory, network and storage according to the current load situation;

[0025] S2. Calculating the comprehensive weighted load of the physical host according to the weight vector and the real-time load vector;

[0026] S3, calculating the dynamic weighted load of the physical host and the predicted weighted load of the virtual machine deployed on the physical host according to the comprehensive weighted load; and

[0027] S4. Determine the initial deployment location of the virtual machine according to the dynamic weighted load and the predicted weighted load.

[0028] The embodiment of the present invention fully considers the balanced utilization of various dimensional resources of the deployed physical machine when the virtual machine is initially placed. First, the relative weights of cpu, memory, network and storage are set according to the current load on the physical host. Then, the comprehensive load of the host is calculated according to the resource usage of the virtual machines deployed on the host and the resource usage of the host itself. Finally, the predicted load of the virtual machine deployed on the physical machine is calculated and combined with the comprehensive load of the physical machine to determine whether the virtual machine is suitable for deployment on the physical machine. The present invention comprehensively considers the usage of cpu, memory, network and storage resources when initially deploying virtual machines, ensuring the balanced utilization and maximized utilization of basic resources in the cloud data center, thereby reducing the number of physical servers and reducing energy consumption. On the other hand, it can also reduce the competition for various basic resources, thereby reducing the impact on the performance of virtual machines.

[0029] The cloud platform global monitor is the core module for calculating the relevant load information of each node (physical node and virtual node). It is based on the Linux system and KVM to build a virtualization system on the x86 server, which is used in the specific implementation environment of the present invention.

[0030] A local monitor is deployed on each physical node. The local monitor collects CPU, memory, network and storage usage information through the relevant tools provided by Linux. The service agent vmtools is installed inside the virtual machine. The local monitor obtains the relevant monitoring information of the virtual machine memory through the agent vmtools inside the virtual machine, including CPU, memory, network and storage monitoring information. The physical host where the cloud platform global monitor is located is connected to each physical node in the cloud data center through the network. The local monitor transmits the collected CPU, memory, network and storage usage information to the cloud platform global monitor in real time through the network.

[0031] Set a weight vector according to the importance of CPU, memory, network, and storage on the physical host, and set a real-time load vector for CPU, memory, network, and storage according to the current load situation.

[0032] In some embodiments, setting the weight vector according to the importance of CPU, memory, network, and storage on the physical host includes: constructing a comparison matrix according to the importance levels of CPU, memory, network, and storage, geometrically averaging the row vectors of the comparison matrix, and normalizing the geometrically averaged row vectors to obtain the weight vector.

[0033] Use the analytic hierarchy process to calculate the weights of the various dimensional attributes according to the dynamic utilization rates of node CPU, memory, bandwidth, and storage, where the node can be a physical node or a virtual machine node, and the specific description is as follows:

[0034] Based on the analytic hierarchy process, calculate the weight vector of the node. The 5-point scale of the relative importance of each dimensional attribute is shown in Table 1, and construct the comparison matrix R A , as shown in Equation (1.1).

[0035] Table 1

[0036] Importance Very important Somewhat important Equally important Somewhat less important Very less important Evaluation value 5 3 1 1 / 3 1 / 5

[0037]

[0038] Where C, M, N, and S represent the CPU, memory, network, and storage of the node respectively, and r ij represents the importance level of element i relative to element j, satisfying r ij = 1 / r ji , for example, r cm represents the importance level of CPU relative to memory, and R C , R M , R N , R S represent the importance levels of node CPU, memory, network, and storage respectively. Geometrically average the row vectors of matrix R A and normalize it to obtain the weight vector r as shown in Equation (1.2), where r c = r 1 , r m = r 2 , r n = r 3 , r s = r 4 , r i as shown in Equation (1.3), n is the number of rows of the comparison matrix R A n = 4.

[0039] r = (rc r m r n r s ) (1.2)

[0040]

[0041] Calculate matrix R A The maximum eigenvalue λ is shown in Equation (1.4), and its consistency is calculated according to Equation (1.5). The degree to which CI approaches 0 represents the degree of satisfaction with consistency. The greater the degree of consistency, the greater the degree of misjudgment. Therefore, in order to accurately weight each dimension attribute of the node, it is necessary to perform a consistency check on matrix R A Perform a consistency check

[0042]

[0043]

[0044] Calculate the comprehensive weighted load of the physical host according to the weight vector and the real-time load vector. Define the column vector s x as the real-time load vector of each dimension attribute on the node, as shown in Equation (1.6), where p c 、p m 、p n 、p s are the utilization rates of CPU, memory, network, and storage on node x respectively. The comprehensive weighted load of node x is defined as PL x , as shown in Equation (1.7), where r x is the weight vector of each dimension attribute of node x, which can be obtained through Equation (1.2). Here, node x can be a physical host or a virtual host

[0045] s x =(p c p m p n p s ) T (1.6)

[0046] PL x =r x ×s x (1.7)

[0047] Calculate the dynamic weighted load of the physical host and the predicted weighted load of the virtual machine deployed on the physical host according to the comprehensive weighted load

[0048] In some embodiments, calculating the dynamic weighted load of the physical host and the predicted weighted load of the virtual machines deployed on the physical host according to the comprehensive weighted load includes: calculating the average value of the comprehensive weighted load of the physical host and the comprehensive weighted load of all virtual machines deployed on the physical host to obtain the dynamic weighted load of the physical host.

[0049] Define the dynamic weighted load DPL of the physical host p x As shown in Equation (1.8), DPL x Consists of the average value of the comprehensive load of the physical host and the comprehensive load of all virtual machines deployed thereon, where X x Is the set of virtual machines on the physical machine p, k is the number of virtual machines, β ∈ (0, 1) is the weight coefficient for adjusting the weights of the physical host and the virtual host. When there are no virtual machines deployed on the physical machine, the dynamic weighted load of the physical machine is the same as its comprehensive weighted load at this time. x For the physical machine p x When the virtual machine v

[0050]

[0051] Is pre-deployed on a certain physical machine p x Its predicted weighted load is defined as PRPL x As shown in Equation (1.9), where k represents the number of virtual machines deployed on p x R is the weight vector of each dimension attribute of p x When there are virtual machines deployed on p x PRPL x For p x Is composed of the weighted average load of each dimension attribute of all virtual machines and r x When there are no virtual machines deployed on p x PRPL x For p x Is composed of the ratio of the total capacity of each dimension attribute applied by the virtual machine to each dimension attribute of p x When there are no virtual machines deployed on p x Determine the initial deployment location of the virtual machine according to the dynamic weighted load and the predicted weighted load.

[0052]

[0053] Determine the initial deployment location of the virtual machine according to the dynamic weighted load and the predicted weighted load.

[0054] In some embodiments, determining the initial deployment location of a virtual machine based on the dynamic weighted load and the predicted weighted load includes: selecting a physical machine whose sum of the dynamic weighted load and the predicted weighted load is less than a threshold as an alternative physical machine; sorting the alternative physical machines in ascending order of the difference between the sum of the dynamic weighted load and the predicted weighted load and the threshold, and sequentially determining whether the remaining resources in each dimension of the alternative physical machines are all greater than the resources requested by the virtual machine; and selecting the first physical machine whose remaining resources in each dimension are all greater than the resources requested by the virtual machine as the initial deployment location of the virtual machine.

[0055] Traverse all physical hosts to calculate their dynamic weighted loads and the predicted weighted loads of the virtual machines deployed on this physical Then the physical machine that meets the following conditions is the physical machine to be found. (1) The sum of the dynamic weighted load of the physical machine and the predicted weighted load of the virtual machine relative to this physical machine is less than the threshold set by the physical and the difference between the sum with and the threshold is the smallest, so as to ensure the maximum resource utilization rate; (2) The remaining resources in each dimension on the physical machine are greater than the resources requested by the virtual machine.

[0056] The embodiments of the present invention comprehensively consider the usage of cpu, memory, network, and storage resources during the initial deployment of virtual machines, ensuring the balanced utilization and maximum utilization rate of the basic resources in the cloud data center, thereby reducing the number of physical servers, reducing energy consumption, and on the other hand, reducing the competition for various basic resources, thereby reducing the impact on the performance of virtual machines.

[0057] It should be particularly noted that each step in each embodiment of the above method for initial deployment of virtual machines in cloud computing can be mutually crossed, replaced, added, or deleted. Therefore, these reasonable permutation and combination transformations for the method of initial deployment of virtual machines in cloud computing should also fall within the protection scope of the present invention, and the protection scope of the present invention should not be limited to the embodiments.

[0058] Based on the above purpose, the second aspect of the embodiments of the present invention proposes a system for initial deployment of virtual machines in cloud computing. As Figure 2As shown, system 200 includes the following modules: a setting module configured to set a weight vector according to the importance of the CPU, memory, network, and storage on the physical host, and set real-time load vectors of the CPU, memory, network, and storage according to the current load situation; a first calculation module configured to calculate the comprehensive weighted load of the physical host according to the weight vector and the real-time load vector; a second calculation module configured to calculate the dynamic weighted load of the physical host and the predicted weighted load of the virtual machine deployed on the physical host according to the comprehensive weighted load; and a determination module configured to determine the initial deployment location of the virtual machine according to the dynamic weighted load and the predicted weighted load.

[0059] In some embodiments, the determination module is configured to: select a physical machine whose sum of the dynamic weighted load and the predicted weighted load is less than a threshold as an alternative physical machine; sort the alternative physical machines in ascending order of the difference between the sum of the dynamic weighted load and the predicted weighted load and the threshold, and sequentially determine whether the remaining resources in each dimension of the alternative physical machines are all greater than the resources requested by the virtual machine; and select the first physical machine whose remaining resources in each dimension are all greater than the resources requested by the virtual machine as the initial deployment location of the virtual machine.

[0060] In some embodiments, the setting module is configured to: construct a comparison matrix according to the importance of the CPU, memory, network, and storage, perform geometric averaging on the row vectors of the comparison matrix, and normalize the geometric-averaged row vectors to obtain a weight vector.

[0061] In some embodiments, the second calculation module is configured to: calculate the average value of the comprehensive weighted load of the physical host and the comprehensive weighted load of all virtual machines deployed on the physical host to obtain the dynamic weighted load of the physical host.

[0062] Based on the above object, in the third aspect of the embodiments of the present invention, a computer device is proposed, including: at least one processor; and a memory storing computer instructions that can be run on the processor, and the instructions are executed by the processor to implement the following steps: S1, set a weight vector according to the importance of the CPU, memory, network, and storage on the physical host, and set real-time load vectors of the CPU, memory, network, and storage according to the current load situation; S2, calculate the comprehensive weighted load of the physical host according to the weight vector and the real-time load vector; S3, calculate the dynamic weighted load of the physical host and the predicted weighted load of the virtual machine deployed on the physical host according to the comprehensive weighted load; and S4, determine the initial deployment location of the virtual machine according to the dynamic weighted load and the predicted weighted load.

[0063] In some embodiments, determining the initial deployment location of a virtual machine according to the dynamic weighted load and the predicted weighted load includes: selecting a physical machine whose sum of the dynamic weighted load and the predicted weighted load is less than a threshold as an alternative physical machine; sorting the alternative physical machines in ascending order of the difference between the sum of the dynamic weighted load and the predicted weighted load and the threshold, and sequentially determining whether the remaining resources in each dimension of the alternative physical machines are all greater than the resources requested by the virtual machine; and selecting the first physical machine whose remaining resources in each dimension are all greater than the resources requested by the virtual machine as the initial deployment location of the virtual machine.

[0064] In some embodiments, setting a weight vector according to the importance of CPU, memory, network, and storage on a physical host includes: constructing a comparison matrix according to the importance levels of CPU, memory, network, and storage, geometrically averaging the row vectors of the comparison matrix, and normalizing the geometrically averaged row vectors to obtain a weight vector.

[0065] In some embodiments, calculating the dynamic weighted load of the physical host and the predicted weighted load of the virtual machine deployed on the physical host according to the comprehensive weighted load includes: calculating the average value of the comprehensive weighted load of the physical host and the comprehensive weighted loads of all virtual machines deployed on the physical host to obtain the dynamic weighted load of the physical host.

[0066] As Figure 3 shown, it is a schematic diagram of the hardware structure of an embodiment of the computer device for initial deployment of a virtual machine in the cloud computing provided by the present invention.

[0067] Taking the device as Figure 3 shown as an example, the device includes a processor 301 and a memory 302.

[0068] The processor 301 and the memory 302 can be connected through a bus or other means, Figure 3 and taking the connection through the bus as an example.

[0069] The memory 302, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the method for initial deployment of a virtual machine in cloud computing in the embodiments of the present application. The processor 301 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions, and modules stored in the memory 302, that is, implements the method for initial deployment of a virtual machine in cloud computing.

[0070] The memory 302 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the method for initial deployment of virtual machines in cloud computing, etc. In addition, the memory 302 may include high-speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 302 optionally includes a memory remotely provided with respect to the processor 301, and these remote memories can be connected to the local module through a network. Examples of the above network include but are not limited to the Internet, enterprise intranet, local area network, mobile communication network, and combinations thereof.

[0071] One or more computer instructions 303 corresponding to the method for initial deployment of virtual machines in cloud computing are stored in the memory 302. When executed by the processor 301, the method for initial deployment of virtual machines in cloud computing in any of the above method embodiments is executed.

[0072] Any embodiment of the computer device that executes the method for initial deployment of virtual machines in cloud computing can achieve the same or similar effects as any of the foregoing method embodiments corresponding thereto.

[0073] The present invention also provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program that, when executed by a processor, executes the method for initial deployment of virtual machines in cloud computing.

[0074] As Figure 4 shown, it is a schematic diagram of an embodiment of the computer storage medium for initial deployment of virtual machines in cloud computing provided by the present invention. Taking the computer storage medium as shown in Figure 4 shown as an example, the computer-readable storage medium 401 stores a computer program 402 that, when executed by a processor, executes the above method.

[0075] Finally, it should be noted that those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The program for the method for initial deployment of virtual machines in cloud computing can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium of the program can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. The embodiments of the above computer program can achieve the same or similar effects as any of the foregoing method embodiments corresponding thereto.

[0076] The above are exemplary embodiments disclosed by the present invention. However, it should be noted that various changes and modifications can be made without departing from the scope of the embodiments disclosed by the present invention as defined by the claims. The functions, steps, and / or actions of the method claims according to the disclosed embodiments herein need not be performed in any specific order. In addition, although the elements disclosed in the embodiments of the present invention may be described or claimed in individual form, they may also be understood as plural unless explicitly limited to the singular form.

[0077] It should be understood that, as used herein, unless the context clearly supports exceptions, the singular form "a" is also intended to include the plural form. It should also be understood that the "and / or" used herein refers to any and all possible combinations of one or more of the related listed items.

[0078] The serial numbers of the disclosed embodiments of the present invention above are only for description and do not represent the superiority or inferiority of the embodiments.

[0079] Those of ordinary skill in the art can understand that all or part of the steps to implement the above embodiments can be completed by hardware, or can be completed by instructing the relevant hardware through a program. The program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a disk, an optical disc, or the like.

[0080] Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the embodiments disclosed by the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features between the above embodiments or different embodiments can also be combined, and there are many other variations in different aspects of the embodiments of the present invention as above, which are not provided in detail for the sake of brevity. Therefore, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention shall be included within the protection scope of the embodiments of the present invention.

Claims

1. A method for initial deployment of virtual machines in cloud computing, characterized in that, it includes the following steps: Set a weight vector according to the importance of CPU, memory, network, and storage on the physical host, and set real-time load vectors of CPU, memory, network, and storage according to the current load situation; Calculate the comprehensive weighted load of the physical host according to the weight vector and the real-time load vector; Calculate the dynamic weighted load of the physical host and the predicted weighted load of the virtual machine deployed on the physical host according to the comprehensive weighted load; and Determine the initial deployment location of the virtual machine according to the dynamic weighted load and the predicted weighted load; Determining the initial deployment location of the virtual machine according to the dynamic weighted load and the predicted weighted load includes: Select physical machines whose sum of the dynamic weighted load and the predicted weighted load is less than the threshold as alternative physical machines; Sort the alternative physical machines in ascending order according to the difference between the sum of the dynamic weighted load and the predicted weighted load and the threshold, and sequentially determine whether the remaining resources in each dimension of the alternative physical machines are all greater than the resources requested by the virtual machine; and Select the first physical machine whose remaining resources in each dimension are all greater than the resources requested by the virtual machine as the initial deployment location of the virtual machine.

2. The method according to claim 1, characterized in that, the setting the weight vector according to the importance of CPU, memory, network, and storage on the physical host includes: Construct a comparison matrix according to the importance levels of CPU, memory, network, and storage, perform geometric averaging on the row vectors of the comparison matrix, and normalize the row vectors after geometric averaging to obtain the weight vector.

3. The method according to claim 1, characterized in that, the calculating the dynamic weighted load of the physical host and the predicted weighted load of the virtual machine deployed on the physical host according to the comprehensive weighted load includes: Calculate the average value of the comprehensive weighted load of the physical host and the comprehensive weighted load of all virtual machines deployed on the physical host to obtain the dynamic weighted load of the physical host.

4. A system for initial deployment of virtual machines in cloud computing, characterized in that, it includes: A setting module configured to set a weight vector according to the importance of CPU, memory, network, and storage on the physical host, and set real-time load vectors of CPU, memory, network, and storage according to the current load situation; A first calculation module configured to calculate the comprehensive weighted load of the physical host according to the weight vector and the real-time load vector; A second calculation module configured to calculate the dynamic weighted load of the physical host and the predicted weighted load of the virtual machine deployed on the physical host according to the comprehensive weighted load; and A determination module, configured to determine the initial deployment location of a virtual machine according to the dynamic weighted load and the predicted weighted load; the determination module is configured to: select a physical machine whose sum of the dynamic weighted load and the predicted weighted load is less than a threshold as an alternative physical machine; sort the alternative physical machines in ascending order of the difference between the sum of the dynamic weighted load and the predicted weighted load and the threshold, and sequentially determine whether the remaining various dimensions of resources in the alternative physical machines are all greater than the resources requested by the virtual machine; and select the first physical machine whose remaining various dimensions of resources are all greater than the resources requested by the virtual machine as the initial deployment location of the virtual machine.

5. The system according to claim 4, wherein, the setting module is configured to: construct a comparison matrix according to the importance levels of the cpu, memory, network, and storage, perform geometric averaging on the row vectors of the comparison matrix, and normalize the row vectors after geometric averaging to obtain a weight vector.

6. The system according to claim 4, wherein, the second calculation module is configured to: calculate the average value of the comprehensive weighted load of the physical host and the comprehensive weighted load of all virtual machines deployed on the physical host to obtain the dynamic weighted load of the physical host.

7. A computer device, wherein, comprising: at least one processor; and a memory, the memory stores computer instructions that can be run on the processor, and when the instructions are executed by the processor, the steps of the method according to any one of claims 1-3 are implemented.

8. A computer-readable storage medium, the computer-readable storage medium stores a computer program, wherein, when the computer program is executed by a processor, the steps of the method according to any one of claims 1-3 are implemented.

Images