CN111106945B

CN111106945B - VNF instantiation method, device, equipment and storage medium

Info

Publication number: CN111106945B
Application number: CN201811260205.8A
Authority: CN
Inventors: 王升
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Communications Ltd Research Institute
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Communications Ltd Research Institute
Priority date: 2018-10-26
Filing date: 2018-10-26
Publication date: 2022-09-06
Anticipated expiration: 2038-10-26
Also published as: CN111106945A

Abstract

The embodiment of the application discloses a VNF instantiation method, a VNF instantiation device, VNF instantiation equipment and a VNF storage medium, wherein the VNF instantiation method comprises the following steps: acquiring a VNF resource set according to a resource demand condition of a VNFM, wherein the VNF resource set comprises state parameters of at least two VNFCs; generating a virtual machine pre-deployment graph according to the state parameters of the at least two VNFCs and a preset algorithm; deploying virtual machines corresponding to at least two VNFCs in the VNF resource set according to the virtual machine pre-deployment graph so as to realize that the virtual machines execute functions corresponding to the virtual machines after being deployed.

Description

VNF instantiation method, device, equipment and storage medium

Technical Field

The embodiment of the application relates to the field of virtual technologies, and relates to but is not limited to a VNF instantiation method, a VNF instantiation device, a VNF equipment and a VNF storage medium.

Background

In a Network Function Virtualization (NFV) environment, after a virtualized cloud platform is installed and integrated, a condition for instantiating a Virtualized Network Function (VNF) Network element is provided.

In the existing European telecommunications Standards Institute (ETSI NFV) architecture, VNF instantiation requires a Virtualized Network Function Manager (VNFM) to parse Virtualized Network Function Descriptor (VNFD) entries, acquiring requirements for each virtualized Network Function module Component (VNFC). Regardless of a direct mode or an indirect mode, the VNF instantiation process requires that the VNFM acquires the specification of each VNFC, then, with the VNFCs as a unit, instantiation requests are sequentially initiated to the virtualization cloud platform, and the virtualization cloud platform selects an appropriate computing node to instantiate a single VNFC according to the requirement of each VNFC for starting resources and the local resource view condition. After the Virtual Infrastructure Manager (VIM) completes the assembly of one VNFC, it reassembles the received instantiation requests of other VNFCs, and repeats the process until all VNFCs forming the VNF complete the assembly and start, so that the instantiation process of the whole network element is declared to be completed.

However, in the existing instantiation process of the virtualized network element in the NFV environment, when each VNFC is assembled, only the requirement of a single VNFC at this time is considered to be met, and the VNFCs are assembled to the computing nodes without a coordinated planning and a global view, so that the virtual machines are unevenly distributed on each computing node, and thus a large amount of resource fragments occur, and the resource utilization rate is low.

Disclosure of Invention

In view of this, embodiments of the present application provide a VNF instantiation method, apparatus, device, and storage medium, which can optimize the use of physical resources, reduce resource fragmentation, and improve resource utilization.

The technical scheme of the embodiment of the application is realized as follows:

in a first aspect, an embodiment of the present application provides a VNF instantiation method, where the method includes:

acquiring a VNF resource set according to a resource demand condition of a VNFM, wherein the VNF resource set comprises state parameters of at least two VNFCs;

generating a virtual machine pre-deployment graph according to the state parameters of the at least two VNFCs and a preset algorithm;

deploying virtual machines corresponding to at least two VNFCs in the VNF resource set according to the virtual machine pre-deployment graph so as to realize that the virtual machines execute functions corresponding to the virtual machines after being deployed.

In a second aspect, an embodiment of the present application provides a VNF instantiation apparatus, where the apparatus includes:

the VNFM resource management system comprises an obtaining unit, a setting unit and a processing unit, wherein the obtaining unit is used for obtaining a VNF resource set according to a resource demand condition of a VNFM, and the VNF resource set comprises at least two VNFC state parameters;

the generating unit is used for generating a virtual machine pre-deployment graph according to the state parameters of the at least two VNFCs and a preset algorithm;

a deployment unit, configured to deploy, according to the virtual machine pre-deployment graph, virtual machines corresponding to at least two VNFCs in the VNF resource set, so as to implement that the virtual machines execute functions corresponding to the virtual machines after being deployed.

In a third aspect, an embodiment of the present application provides a VNF instantiation device, where the VNF instantiation device includes at least: a processor and a storage medium configured to store executable instructions, wherein: the processor is configured to execute stored executable instructions;

the executable instructions are configured to perform the VNF instantiation method described above.

In a fourth aspect, an embodiment of the present application provides a storage medium, where computer-executable instructions are stored, and the computer-executable instructions are configured to perform the VNF instantiation method described above.

The embodiment of the application provides a VNF instantiation method, device, equipment and storage medium, wherein the method comprises the following steps: acquiring a VNF resource set according to a resource demand condition of a VNFM, wherein the VNF resource set comprises state parameters of at least two VNFCs; generating a virtual machine pre-deployment graph according to the state parameters of the at least two VNFCs and a preset algorithm; deploying virtual machines corresponding to at least two VNFCs in the VNF resource set according to the virtual machine pre-deployment graph so as to realize that the virtual machines execute functions corresponding to the virtual machines after being deployed. In this way, the acquired VNF resource set includes the state parameters of at least two VNFCs, so that the generated virtual machine pre-deployment graph is a pre-deployment graph in which the association relationship between multiple VNFCs is considered, and thus, when a virtual machine is deployed, physical resources can be optimally utilized, resource fragmentation is reduced, and resource utilization rate is improved.

Drawings

In the drawings, which are not necessarily drawn to scale, like reference numerals may describe similar components in different views. Like reference numerals having different letter suffixes may represent different examples of similar components. The drawings illustrate generally, by way of example, but not by way of limitation, various embodiments discussed herein.

Fig. 1 is a schematic flowchart illustrating an implementation flow of a VNF instantiation method according to an embodiment of the present application;

fig. 2 is a schematic flowchart illustrating an implementation flow of a VNF instantiation method according to an embodiment of the present application;

fig. 3 is a schematic flowchart illustrating an implementation flow of a VNF instantiation method according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of a VNF instantiation apparatus according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of a VNF instantiation device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following detailed descriptions of specific technical solutions of the present application are made with reference to the accompanying drawings in the embodiments of the present application. The following examples are intended to illustrate the present application but are not intended to limit the scope of the present application.

In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for the convenience of description of the present application, and have no specific meaning by themselves. Thus, "module", "component" or "unit" may be used mixedly.

In the related art, instantiation of a VNF requires a VNFM to parse VNFD entries, and to obtain the requirements of each VNFC. Generally, the instantiation of the VNF includes a direct mode and an indirect mode, and in the direct mode, the VNFM reserves relevant resources to the virtualized cloud platform, and initiates an instantiation request; in the indirect mode, the VNFM reserves relevant resources to the virtualized cloud platform through the NFVO, and initiates an instantiation request.

Regardless of the direct mode or the indirect mode, the VNF instantiation process requires the VNFM to first obtain the specification of each VNFC, where the specification of the VNFC includes the number of Central Processing Unit (CPU) cores, the memory size, the hard disk requirement, the number of virtual network cards, and the like, and the association relationship between the VNFCs, where the association relationship between the VNFCs includes affinity and anti-affinity. And then, the VIM sequentially sends instantiation requests to the virtual layer by taking the VNFC as a unit, and the virtual layer selects a proper computing node to instantiate a single VNFC according to the requirement of each VNFC for starting resources and the condition of a local resource view and by combining a self-packing weighing algorithm. After the VIM completes the assembly of one VNFC, the VIM reassembles the received instantiation requests of other VNFCs, and the process is repeated until all VNFCs forming the VNF complete the assembly and start, so that the instantiation process of the whole network element is declared to be completed.

As can be seen from the VNF instantiation process in the related art, the virtualization network element instantiation process in the NFV environment in the related art is initiated by VNFM or NFVO, the unit initiating instantiation is a single VNFC, and a request is sequentially initiated to the VIM according to VNFC requirements defined in the VNFD. This means that VNFC instantiation requests received by the VIM side are queued, and therefore, the VIM processes the VNFCs one by one, and when each VNFC is assembled, only the requirement of a single VNFC at this time is satisfied, but the VNFCs are assembled to the computing nodes without a coordinated planning and a global view, so that the virtual machines are unevenly distributed in each computing node, and thus a large amount of resource fragmentation occurs, and the resource utilization rate is low.

Based on the above problems in the related art, this embodiment provides a VNF instantiation method, where the VNF instantiation method includes a pre-assembly process and an algorithm for NFV network element instantiation, and obtains instantiation requirements of the entire service field in advance, for example, instantiation requirements of System network elements such as an IP Multimedia Subsystem (IMS) or an Evolved Packet System (EPS) or a fifth Generation mobile communication network (5th Generation, 5G) System, analyzes resource requirements constituting VNFCs of each network element and association information between VNFCs of each network element, generates a virtual machine pre-deployment map, and deploys the pre-deployment map on NFVO/VNFM or VIM according to a corresponding binning weighing algorithm, so as to effectively reduce the number of resource fragments and improve the resource utilization rate of a data center.

Fig. 1 is a schematic flow chart illustrating an implementation process of a VNF instantiation method provided in an embodiment of the present application, and as shown in fig. 1, the method includes the following steps:

step S101, obtaining a VNF resource set according to the resource demand condition of the VNFM.

Here, the VNFM includes state parameters and resource demand conditions of each virtual machine and state parameters and resource demand conditions of each server, accesses the VNFM through the NFVO to obtain the resource demand conditions of the VNFM, and then acquires the VNF resource set according to the resource demand conditions of the VNFM.

The VNF resource set includes state parameters of at least two VNFCs, for example, the state parameters of the VNFCs may include at least one of: the number of virtual machines, the specifications of the virtual machines (e.g., CPU, Non-Uniform Memory Access (NUMA), macro pages, etc.), and the relationships between the virtual machines (e.g., affinity, anti-affinity, etc.).

In this embodiment, the VIM acquires the VNF resource set, and the VIM may acquire the VNF resource set according to the resource demand condition of the VNFM through the VNFO.

In the implementation process, the VNFO accesses the VNFM, determines the resource demand condition of the VNFM, then acquires the state parameters of the VNFCs according to the resource demand condition of the VNFM, and sends the state parameters of the VNFCs to the VIM so as to implement the pre-deployment of the VIM on the virtual machine to be deployed.

And step S102, generating a virtual machine pre-deployment graph according to the state parameters of the at least two VNFCs and a preset algorithm.

Here, the VIM realizes pre-deployment of the virtual machine according to the state parameters of the at least two VNFCs, and generates a virtual machine pre-deployment graph according to a preset algorithm.

In this embodiment, the step S102 of generating the virtual machine pre-deployment graph according to the preset algorithm based on the state parameters of the at least two VNFCs may be implemented by:

and step S1021, acquiring a virtual machine set according to the state parameters of the at least two VNFCs.

Here, the virtual machine group set includes at least two virtual machine group identifiers and a virtual machine group parameter corresponding to each virtual machine group identifier.

The virtual machine group identification is an identification of a virtual machine group, the virtual machine group comprises at least one virtual machine, and all the virtual machines in the virtual machine group are virtual machines of the same type. The virtual machine group parameter corresponding to each virtual machine group identifier is a parameter of a virtual machine in the virtual machine group corresponding to the virtual machine group identifier, for example, the virtual machine group parameter may include: the number of cores of a single virtual machine, the number of affinity groups, the minimum number of servers required by each group of virtual machines, and the like, and of course, the parameters of the virtual machine group may also include other parameters of the virtual machine, such as a memory of the virtual machine, a bandwidth of the virtual machine, and the like, which may be specifically selected according to actual needs, and this embodiment does not limit this.

Step S1022, according to the virtual machine group parameters, processing the virtual machine group set according to the preset algorithm, so as to obtain the virtual machine pre-deployment map.

Here, the preset algorithm may be a preset sorting algorithm or a preset sorting rule, and after the virtual machine group parameters are obtained, all virtual machine group identifiers in the virtual machine group set are processed according to the preset sorting algorithm or the preset sorting rule, so that the processed virtual machine group set is obtained as the virtual machine pre-deployment map. Wherein the virtual machine pre-deployment graph is a pre-deployment graph that takes into account an association between multiple VNFCs. The association may be an affinity or an anti-affinity between the VNFCs.

Step S103, deploying virtual machines corresponding to at least two VNFCs in the VNF resource set according to the virtual machine pre-deployment graph.

And after the virtual machine pre-deployment graph is obtained, the VIM deploys all the virtual machines corresponding to the global VNF according to the virtual machine pre-deployment graph.

In this embodiment, according to the virtual machine pre-deployment graph, virtual machines corresponding to at least two VNFCs in the VNF resource set are deployed, so that the virtual machines execute functions corresponding to the virtual machines after being deployed.

According to the VNF instantiation method provided by the embodiment of the application, a VNF resource set is obtained according to the resource demand condition of the VNFM; generating a virtual machine pre-deployment graph according to the state parameters of the at least two VNFCs and a preset algorithm; and deploying the virtual machine according to the virtual machine pre-deployment graph. In this way, the acquired VNF resource set includes the state parameters of at least two VNFCs, so that the generated virtual machine pre-deployment graph is a pre-deployment graph in which the association relationship between multiple VNFCs is considered, and thus, when a virtual machine is deployed, physical resources can be optimally utilized, resource fragmentation is reduced, and resource utilization rate is improved.

Fig. 2 is a schematic flow chart illustrating an implementation process of a VNF instantiation method provided in an embodiment of the present application, and as shown in fig. 2, the method includes the following steps:

step S201, acquiring a VNF resource set according to a resource demand condition of the VNFM.

Here, the VNFM includes state parameters and resource demand conditions of each virtual machine and state parameters and resource demand conditions of each server, accesses the VNFM through the NFVO to obtain the resource demand conditions of the VNFM, and then acquires the VNF resource set according to the resource demand conditions of the VNFM. Wherein the VNF resource set includes state parameters of at least two VNFCs; the state parameters of the VNFC may include one or more of the following parameters: the number of virtual machines, the CPU (physical core) of each virtual machine, the memory of each virtual machine, the total capacity of a cloud disk, the bandwidth of each virtual machine, the affinity attribute (affinity group number), the anti-affinity attribute (anti-affinity group number) and the backup relation.

Step S202, acquiring a virtual machine set according to the state parameters of the at least two VNFCs.

The virtual machine group identification is an identification of a virtual machine group, the virtual machine group comprises at least one virtual machine, and all the virtual machines in the virtual machine group are virtual machines of the same type. The virtual machine set parameters include: number of server requirements, number of virtual machine cores, and affinity group number.

After the VNF resource set is obtained, the affinity group number and the number of virtual machine cores may be directly obtained according to state parameters of at least two VNFCs in the VNF resource set; the server demand quantity may be indirectly obtained by calculating state parameters of at least two VNFCs in the VNF resource set.

Step S203, according to the number of server demands, sorting all the virtual machine group identifiers in the virtual machine group set according to a first preset rule, so as to obtain a first virtual machine group list.

Here, the first preset rule is a first ordering rule, and the first ordering rule is to order all virtual machine group identifiers in the virtual machine group set in an order from large to small server demand quantities corresponding to each virtual machine group identifier; or, the first ordering rule is that all the virtual machine group identifications in the virtual machine group set are ordered according to the sequence from small to large of the required number of the servers corresponding to each virtual machine group identification.

After all the virtual machine set identifications in the virtual machine set are sorted through a first sorting rule, a first virtual machine set list is obtained, wherein the first virtual machine set list comprises: all the virtual machine group identifications in the virtual machine group set and the virtual machine group parameters corresponding to each virtual machine group identification.

Step S204, according to the virtual machine core number, sequencing all the virtual machine group identifications in the first virtual machine group list according to a second preset rule to obtain a second virtual machine group list.

Here, the second preset rule is a second sorting rule, and the second sorting rule is to sort all the virtual machine group identifiers in the first virtual machine group list in order from large to small the virtual machine cores corresponding to each virtual machine group identifier; or, the second sorting rule is to sort all the virtual machine group identifiers in the first virtual machine group list according to the order from small to large of the virtual machine core number corresponding to each virtual machine group identifier.

After all the virtual machine group identifiers in the first virtual machine group list are sorted through a second sorting rule, the second virtual machine group list is obtained, and the second virtual machine group list comprises: all the virtual machine group identifications in the first virtual machine group list and virtual machine group parameters corresponding to each virtual machine group identification.

Step S205, according to the affinity group number, sorting all the virtual machine group identifiers in the second virtual machine group list according to a third preset rule, so as to obtain a third virtual machine group list.

Here, the third preset rule is an adjustment rule, and the adjustment rule is to adjust, starting from the starting list row of the second virtual machine group list, virtual machine group identifiers included in other list rows having the same affinity group number as that in the current list row to be adjacent to the current list row for all virtual machine group identifiers in the second virtual machine group list.

The starting list is the first row of the second virtual machine group list, and each list row in the second virtual machine group list comprises a virtual machine group identifier, the number of single virtual machine cores corresponding to the virtual machine group identifier, an affinity group number corresponding to the virtual machine group identifier, and the number of server demands corresponding to the virtual machine group identifier.

Here, each affinity group number corresponds to an affinity, for example, when an affinity group number corresponding to a certain virtual machine group identifier is 1, the virtual machine group has the affinity corresponding to the affinity group number of 1.

The adjusting the virtual machine group identifier included in the other list rows having the same affinity group number as the current list row to be adjacent to the current list row means that for the other list rows except the current list row and the adjusted list row, a list row having the same affinity group number as the current list row is searched, and if the affinity group number of a certain list row is the same as the affinity group number of the current list row, the list row is adjusted to be below the adjacent list row of the current list row. Wherein the adjusted list behavior is located all list rows before the current list row.

After all the virtual machine set identifiers in the second virtual machine set list are adjusted through an adjustment rule, a third virtual machine set list is obtained, wherein the third virtual machine set list comprises: all the virtual machine group identifications in the second virtual machine group list and the virtual machine group parameters corresponding to each virtual machine group identification.

Step S206, acquiring the number of virtual machines that can be deployed by each server according to the state parameters of the at least two VNFCs.

Here, the number of virtual machines deployable to each server may be obtained according to the obtained backup relationship in the state parameters of the at least two VNFCs.

For example, for an N + M type backup relationship, the number Y of virtual machines that can be deployed by a corresponding server is determined to be M, where N is the number of virtual machines that carry traffic in the NFV resource pool, and M is the number of virtual machines for backup in the NFV resource pool.

Step S207, obtaining the virtual machine pre-deployment map according to the third virtual machine group list.

In this embodiment, step S207 obtains the virtual machine pre-deployment map according to the third virtual machine group list, and may be implemented by the following steps:

step S2071, obtaining the virtual machine pre-deployment map according to the number of virtual machines that can be deployed by each server and the third virtual machine group list.

In other embodiments, step S2071 obtains the virtual machine pre-deployment map according to the number of virtual machines that can be deployed by each server and the third virtual machine group list, and includes:

step S2072, sequentially deploying, according to the number of virtual machines that can be deployed by each server, virtual machines to be deployed corresponding to all virtual machines in the third virtual machine group list to a target server according to the order of the virtual machines in the third virtual machine group list, so as to obtain the virtual machine pre-deployment map.

Here, since the order of the virtual machine group identifiers in the third virtual machine group list is arranged in consideration of the association relationship between all the virtual machine groups, the virtual machine pre-deployment map obtained according to the order of the virtual machine groups in the third virtual machine group list will also be a pre-deployment map in consideration of the association relationship between the virtual machines.

Step S208, if the virtual machine to be deployed and at least one deployed virtual machine on the target server have the same affinity group number, prohibiting the virtual machine to be deployed from being deployed to the target server.

Here, the target server is a target server to be deployed of the virtual machine to be deployed, and the target server may have at least one deployed virtual machine or may not have any deployed virtual machine.

If at least one deployed virtual machine exists on the target server, it is necessary to determine whether the affinity group numbers of the virtual machine to be deployed and all deployed virtual machines deployed on the target server are the same, that is, whether the virtual machine to be deployed and all deployed virtual machines belong to the same affinity group. And if the judgment result shows that the virtual machine to be deployed and one deployed virtual machine belong to the same affinity group, not deploying the virtual machine to be deployed to the target server.

And if any virtual machine is not deployed on the target server, directly deploying the virtual machine to be deployed to the target server.

Step S209, if the virtual machine to be deployed is prohibited to be deployed on all servers, adding a new server as a new target server of the virtual machine to be deployed.

Here, the new server is a server other than all the current servers, and no virtual machine is deployed on the new server. And if all the servers cannot deploy the virtual machine to be deployed, adding a new server to deploy the virtual machine to be deployed.

And step S210, deploying the virtual machine according to the virtual machine pre-deployment graph.

And after the virtual machine pre-deployment graph is obtained, the VIM deploys all virtual machines corresponding to the global VNF according to the virtual machine pre-deployment graph.

In the VNF instantiation method provided in the embodiment of the present application, all the virtual machine group identifiers in the virtual machine group set are sequentially processed according to a first preset rule, a second preset rule, and a third preset rule to obtain a third virtual machine group list, where the third virtual machine group list is a list obtained by considering an association relationship between all the virtual machine groups, and then the virtual machine pre-deployment map obtained according to the third virtual machine group list is also a pre-deployment map considering an association relationship between each virtual machine. Therefore, the virtual machine deployment according to the virtual machine pre-deployment diagram can be considered in a global view, physical resources are optimally utilized, resource fragments are reduced, and the utilization rate is improved.

Fig. 3 is a schematic implementation flow diagram of a VNF instantiation method provided in an embodiment of the present application, and as shown in fig. 1, the method includes the following steps:

step S301, the NFVO acquires the resource list of the global VNF through the VNFM, and sends the acquired resource list to the VIM.

Here, the resource list of the VNF corresponds to the VNF resource set in any one of the embodiments described above. The NFVO acquires the resource list of the global VNF through the VNFM, that is, the NFVO acquires the resource list of the global VNF according to the resource requirement of the VNFM by acquiring the resource requirement of the VNFM. Therefore, when the NFVO needs to obtain the resource list, the VNFM may be queried first to determine the resource requirement of the VNFM, and then the resource list of the global VNF is obtained according to the resource requirement of the VNFM.

In this embodiment, the resource list of the global VNF is a list formed by resource requirements of all VNF network elements in the NFV environment, and the resource list of the global VNF includes the resource requirements of all VNF network elements and state parameters of a plurality of VNFCs. For example, the resource list of the global VNF may include: the number of virtual machines, the virtual machine specifications (e.g., CPU, NUMA, megapages, etc.), the relationships between virtual machines (e.g., affinity, anti-affinity, etc.).

As shown in table 1 below, a resource list of VNFs in a certain field is obtained for the NFVO through the VNFM. Of course, table 1 is only exemplary, and the actually obtained resource list may further include other network element types besides a Mobility Management Entity (MME) and a Serving GateWay (S-GW).

As can be seen from table 1, the current NFVO obtains parameters of an MME network element and an S-GW network element through a VNFM, where the MME network element includes two virtual machine types, namely, an Open Multi-Processing (OMP) type and a symmetric Multi-Processing (SMP) type, and in table 1, the MME network element further includes a number of virtual machines corresponding to each virtual machine type, a CPU (physical core) of each virtual machine, a memory of each virtual machine, a total capacity of a cloud disk, a bandwidth of each virtual machine, an affinity attribute (affinity group number), a reverse affinity attribute (reverse affinity group number), and a backup relationship.

TABLE 1 resource List of VNFs

And after acquiring the resource list of the global VNF through the VNFM, the NFVO sends the acquired resource list to the VIM.

Step S302, the VIM realizes pre-deployment, and generates a virtual machine pre-deployment graph according to a preset assembly algorithm.

Here, the performing of pre-deployment by the VIM means that the VIM generates a virtual machine pre-deployment graph of all virtual machines according to a preset assembly algorithm, where the virtual machine pre-deployment graph is obtained according to the resource list of the global VNF according to the preset assembly algorithm.

In this embodiment, the step S302 of generating the virtual machine pre-deployment map according to the preset assembly algorithm may be implemented by the following steps:

step S3021, calculating the maximum number of virtual machines that can be deployed per server and the minimum number of servers per group of virtual machines.

Here, for each row of virtual machines in the resource list of the VNF, the maximum number Y of virtual machines that can be deployed per server is calculated, where each row corresponds to one virtual machine group, that is, each virtual machine type corresponds to one virtual machine group, and the number of virtual machines in each virtual machine group is X; and calculating the minimum server quantity Z required by each group of virtual machines according to the backup relation. The calculation method is as follows: according to a backup relation N + M in a VNF resource list, determining that the maximum number Y of virtual machines that can be deployed per server is M, the minimum number Z of servers is X/M, and Z is a maximum integer, where N is the number of virtual machines that carry services in an NFV resource pool, and M is the number of virtual machines for backup in the NFV resource pool.

For example, for the type of OMP virtual machine in table 1 above, the corresponding backup relationship is 1+1, and the number of virtual machines is 2, that is, N is 1, M is 1, and X is 2, so that the following calculation method can be obtained: the maximum number of the virtual machines which can be deployed per server is 1, and the minimum number of the servers is 2.

For another example, for the SMP virtual machine type in table 1 above, the corresponding backup relationship is 5+3, and the number of virtual machines is 8, that is, N is 5, M is 3, and X is 8, so that the following calculation method can be obtained: the maximum number Y of the virtual machines that can be deployed per server is 3, the minimum number Z of the servers is 8/3, and if the maximum integer is taken, Z is 3.

Step S3022, traversing all the virtual machines in the VNF resource list, and sorting all the virtual machine groups in the VNF resource list from large to small according to the minimum number of servers.

Here, each virtual machine group includes at least one virtual machine, and each virtual machine group is composed of virtual machines of one virtual machine type. For example, in table 1, the number of virtual machines in a virtual machine group of an OMP virtual machine type is 2; in the SMP virtual machine type virtual machine group, the number of virtual machines is 8.

After obtaining a VNF resource list and calculating the minimum number of servers of each group of virtual machines, a virtual machine set resource list is formed by taking a virtual machine set as a unit, wherein the virtual machine set resource list comprises: the virtual machine group name, the number of single virtual machine cores (corresponding to the number of virtual machine cores), the affinity group number and the minimum number of servers (corresponding to the number of server requirements).

In this embodiment, traversing all the virtual machines in the VNF resource list, and sorting all the virtual machine groups in the VNF resource list from large to small according to the minimum number of servers means that the virtual machine group resource list formed by all the virtual machines in the VNF resource list is sorted from large to small according to the minimum number of servers of all the virtual machine groups in the virtual machine group resource list, and a once-sorted virtual machine group resource list is obtained.

As shown in table 2, the virtual machine group resource list after one sort is obtained after sorting all the virtual machine groups in the VNF resource list from large to small according to the minimum number of servers.

Table 2 once sorted virtual machine set resource list

Virtual machine group name	Number of cores per virtual machine	Affinity group number	Minimum number of servers
				G	4	0	20
B	8	1	10
				F	12	2	6
E	4	2	4
				C	16	0	4
A	10	1	3
				D	9	0	2

It should be noted that, in other embodiments, all the virtual machine groups in the VNF resource list may also be sorted in a sorting manner from small to large, and the sorting manner may be selected according to actual needs, which is not limited in this embodiment.

Step S3023, sorting the virtual machine groups with the same minimum number of servers in the once sorted virtual machine group resource list according to the number of cores of a single virtual machine from large to small.

Here, for the once sorted virtual machine group resource list obtained in step S3022, the virtual machine groups with the same minimum number of servers are searched, and it is determined whether the virtual machine groups with the same minimum number of servers are arranged in the order from the largest to the smallest number of single virtual machine cores, if so, step S3023 is skipped, and if not, step S3023 is executed.

And performing secondary sorting on the primary sorted virtual machine set resource list by executing the step S3023 to obtain a secondary sorted virtual machine set resource list.

As shown in table 3, the virtual machine groups in the primary sorted virtual machine group resource list in table 2 are sorted from large to small according to the number of single virtual machine cores, and the secondary sorted virtual machine group resource list is obtained.

TABLE 3 virtual machine set resource List after secondary sorting

Virtual machine group name	Number of cores per virtual machine	Affinity group number	Minimum number of servers
				G	4	0	20
B	8	1	10
				F	12	2	6
C	16	0	4
				E	4	2	4
A	10	1	3
				D	9	0	2

It should be noted that, in other embodiments, the virtual machine groups with the same minimum number of servers in the virtual machine group resource list after one-time sorting may also be sorted in a sorting manner that the number of single virtual machine cores is from small to large, and the sorting manner may be selected according to actual needs, which is not limited in this embodiment.

Step S3024, traversing the secondarily sorted virtual machine group resource list, and inserting the virtual machine groups with the same affinity group number into the current virtual machine group from the first row of virtual machine groups.

Here, step S3024 is executed to perform tertiary sorting on the secondarily sorted virtual machine group resource list, so as to obtain a thirdly sorted virtual machine group resource list.

In this embodiment, the virtual machine groups having the same affinity group number are inserted into the current virtual machine group, and the purpose is to continuously arrange the virtual machine groups having the same affinity. By inserting the virtual machine groups with the same affinity group number into the current virtual machine group from the first row of virtual machine groups, the virtual machine groups with the same affinity can be continuously arranged in the obtained three-time sequenced virtual machine group resource list.

As shown in table 4, in order to obtain the three-time sorted virtual machine group resource list after inserting the virtual machine group with the same affinity group number into the current virtual machine group for the two-time sorted virtual machine group resource list in table 3.

TABLE 4 virtual machine set resource list after three-time sorting

Name of virtual machine set	Number of cores per virtual machine	Affinity group number	Minimum number of servers
				G	4	0	20
C	16	0	4
				D	9	0	2
B	8	1	10
				A	10	1	3
F	12	2	6
				E	4	2	4

Step S3025, deploying virtual machines from the first row of virtual machine groups in the three-time sorted virtual machine group resource list.

Here, when the virtual machines are deployed from the first row of virtual machine groups, since a maximum number of Y virtual machines are deployed on each server, and the number of virtual machines included in each virtual machine group is X, the virtual machines are deployed to each server according to the maximum number of virtual machines deployed on each server Y and the number of virtual machines included in each virtual machine group X until all virtual machines of the group are deployed.

And step S3026, starting from the second row of the three-time sorted virtual machine group resource list, checking the anti-affinity attribute of the virtual machine group resource list.

Here, when all the virtual machines in the first row of virtual machine groups are deployed, starting from the second row, before deploying the virtual machines, first checking an affinity group number of the second row of virtual machine groups, if the affinity group number of the second row of virtual machine groups is the same as an affinity group number of any one or more virtual machines on the current server, indicating that the current virtual machine to be deployed and the current server are in the same anti-affinity group, skipping the current server, prohibiting the current server from deploying the virtual machine to be deployed, and attempting to deploy on the next server; on the contrary, if the affinity group number of the second row of virtual machine groups is different from the affinity group numbers of all the virtual machines on the current server, it indicates that the current virtual machine to be deployed and the current server are not in the same anti-affinity group, and therefore the virtual machine to be deployed is deployed on the current server.

Step S3027, if the virtual machines to be deployed cannot be deployed on all current servers, adding a new server.

Here, if the virtual machine to be deployed and all current servers are located in the same anti-affinity group, the virtual machine to be deployed cannot be deployed to all current servers, and therefore, a new server is added as a target server of the virtual machine to be deployed to deploy the virtual machine to be deployed.

And step S3028, counting the total number of servers at last until the last line of virtual machines is deployed.

Here, after the deployment of all the virtual machines is completed, the total number of the servers is counted, and it should be noted that, the total number of the servers finally counted is greater than or equal to the number of the original servers.

Through the steps S3021 to S3028, pre-deployment of all virtual machines can be achieved, and the virtual machine pre-deployment graph is generated according to the final deployment results formed in the steps S3021 to S3028.

Step S303, deploying the virtual machine according to the virtual machine pre-deployment graph.

Here, the VIM deploys all virtual machines corresponding to the global VNF according to the virtual machine pre-deployment graph.

According to the VNF instantiation method provided by the embodiment of the application, the virtual machine pre-deployment graphs of all the virtual machines are generated through the preset assembly algorithm, when the pre-assembly is carried out on the VIM, the resource list of the global VNF is integrated, the global view is carried out according to the incidence relation among all the virtual machines, so that the physical resources are optimally utilized, the resource fragments are reduced, and the resource utilization rate is improved.

Based on the foregoing embodiments, the present application provides a VNF instantiation apparatus, where the apparatus includes units and modules included in the units, and the apparatus may be implemented by a processor in a VNF instantiation device, for example, the VNF instantiation device may be a terminal or a computer device; of course, the implementation can also be realized through a specific logic circuit; in implementation, the processor may be a Central Processing Unit (CPU), a Microprocessor (MPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), or the like.

Fig. 4 is a schematic structural diagram of a VNF instantiation apparatus according to an embodiment of the present application, and as shown in fig. 4, the VNF instantiation apparatus 400 includes:

an obtaining unit 401, configured to obtain a VNF resource set according to a resource demand condition of a VNFM, where the VNF resource set includes state parameters of at least two VNFCs;

a generating unit 402, configured to generate a virtual machine pre-deployment graph according to a preset algorithm according to the state parameters of the at least two VNFCs;

a deployment unit 403, configured to deploy the virtual machine according to the virtual machine pre-deployment graph.

In other embodiments, the generating unit includes:

the first obtaining module is used for obtaining a virtual machine set according to the state parameters of the at least two VNFCs; the virtual machine group set comprises at least two virtual machine group identifications and virtual machine group parameters corresponding to each virtual machine group identification;

and the processing module is used for processing the virtual machine set according to the virtual machine set parameters and the preset algorithm to obtain the virtual machine pre-deployment graph.

In other embodiments, the virtual machine group parameters include: the number of server demands, the number of virtual machine cores and the affinity group number;

correspondingly, the processing module comprises:

the first sequencing module is used for sequencing all the virtual machine group identifications in the virtual machine group set according to the quantity required by the server and a first preset rule to obtain a first virtual machine group list;

sequencing all virtual machine group identifications in the first virtual machine group list according to the virtual machine core number and a second preset rule to obtain a second virtual machine group list;

the second sorting module is used for sorting all the virtual machine group identifications in the second virtual machine group list according to the affinity group number and a third preset rule to obtain a third virtual machine group list;

and the second obtaining module is used for obtaining the virtual machine pre-deployment drawing according to the third virtual machine group list.

In other embodiments, the apparatus further comprises:

a second obtaining unit, configured to obtain, according to the state parameters of the at least two VNFCs, the number of virtual machines that can be deployed by each server;

correspondingly, the second obtaining module includes:

and a third obtaining module, configured to obtain the virtual machine pre-deployment graph according to the number of virtual machines that can be deployed by each server and the third virtual machine group list.

In other embodiments, the third obtaining module comprises:

and a fourth obtaining module, configured to sequentially deploy, according to the number of virtual machines that can be deployed by each server and according to the order of the virtual machine groups in the third virtual machine group list, virtual machines to be deployed, which correspond to all virtual machine groups in the third virtual machine group list, to a target server, so as to obtain the virtual machine pre-deployment map.

In other embodiments, the apparatus further comprises:

a deployment prohibiting unit, configured to prohibit the to-be-deployed virtual machine from being deployed to the target server if the to-be-deployed virtual machine and at least one deployed virtual machine on the target server have the same affinity group number.

In other embodiments, the apparatus further comprises:

and the adding unit is used for adding a new server as a new target server of the virtual machine to be deployed if the virtual machine to be deployed is prohibited to be deployed on all servers.

The above description of the apparatus embodiments, similar to the above description of the method embodiments, has similar beneficial effects as the method embodiments. For technical details not disclosed in the embodiments of the apparatus according to the invention, reference is made to the description of the embodiments of the method according to the invention for understanding.

It should be noted that, in the embodiment of the present application, if the VNF instantiation method described above is implemented in the form of a software functional module and is sold or used as a standalone product, it may also be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a terminal to execute all or part of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read Only Memory (ROM), a magnetic disk, or an optical disk. Thus, embodiments of the invention are not limited to any specific combination of hardware and software.

Correspondingly, an embodiment of the present application provides a VNF instantiation device, and fig. 5 is a schematic structural diagram of the VNF instantiation device provided in the embodiment of the present application, and as shown in fig. 5, the VNF instantiation device 500 at least includes: a processor 501, a communication interface 502, and a storage medium 503 configured to store executable instructions, wherein:

the processor 501 typically controls the overall operation of the VNF instantiation device 500.

The communication interface 502 may enable the VNF instantiation device to communicate with other terminals or servers over a network.

The storage medium 503 is configured to store instructions and applications executable by the processor 501, and may also cache data to be processed or already processed by each module in the processor 501 and the VNF instantiation device 500, and may be implemented by a FLASH Memory (FLASH) or a Random Access Memory (RAM).

It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in various embodiments of the present invention, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention. The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment. In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

Those of ordinary skill in the art will understand that: all or part of the steps of implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer-readable storage medium, and when executed, executes the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk. Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention or portions thereof that contribute to the related art may be embodied in the form of a software product, where the computer software product is stored in a storage medium and includes several instructions for enabling a terminal to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: various media that can store program code, such as removable storage devices, ROMs, magnetic or optical disks, etc.

The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the present invention, and all such changes or substitutions are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

Claims

1. A VNF instantiation method, the method comprising:

acquiring a Virtual Network Function (VNF) resource set according to resource demand conditions of a VNFM (virtual network function manager), wherein the VNF resource set comprises state parameters of at least two VNFCs (virtual network function module assemblies);

acquiring a virtual machine set according to the state parameters of the at least two VNFCs; the virtual machine group set comprises at least two virtual machine group identifications and virtual machine group parameters corresponding to each virtual machine group identification; the virtual machine set parameters include: the number of server requirements, the number of virtual machine cores and the affinity group number;

sequencing all the virtual machine group identifications in the virtual machine group set according to the quantity required by the server and a first preset rule to obtain a first virtual machine group list;

sequencing all the virtual machine group identifications in the first virtual machine group list according to the virtual machine core number and a second preset rule to obtain a second virtual machine group list;

sequencing all the virtual machine set identifications in the second virtual machine set list according to the affinity group number and a third preset rule to obtain a third virtual machine set list;

obtaining a virtual machine pre-deployment graph according to the third virtual machine group list;

2. The method of claim 1, further comprising:

acquiring the number of virtual machines which can be deployed by each server according to the state parameters of the at least two VNFCs;

correspondingly, the obtaining the virtual machine pre-deployment graph according to the third virtual machine group list includes:

and obtaining the virtual machine pre-deployment graph according to the number of the virtual machines which can be deployed by each server and the third virtual machine group list.

3. The method according to claim 2, wherein obtaining the virtual machine pre-deployment graph according to the number of virtual machines that can be deployed by each server and the third virtual machine group list comprises:

according to the number of the virtual machines which can be deployed by each server, deploying the virtual machines to be deployed corresponding to all the virtual machine groups in the third virtual machine group list to a target server in sequence according to the sequence of the virtual machine groups in the third virtual machine group list, and obtaining the virtual machine pre-deployment graph.

4. The method of claim 3, further comprising:

and if the virtual machine to be deployed and at least one deployed virtual machine on the target server have the same affinity group number, forbidding to deploy the virtual machine to be deployed to the target server.

5. The method of claim 4, further comprising:

and if the virtual machine to be deployed is prohibited to be deployed on all the servers, adding a new server as a new target server of the virtual machine to be deployed.

6. A VNF instantiation apparatus, the apparatus comprising:

a generating unit, configured to obtain a virtual machine group set according to the state parameters of the at least two VNFCs; the virtual machine group set comprises at least two virtual machine group identifications and virtual machine group parameters corresponding to each virtual machine group identification; the virtual machine set parameters include: the number of server demands, the number of virtual machine cores and the affinity group number; sequencing all the virtual machine group identifications in the virtual machine group set according to the quantity required by the server and a first preset rule to obtain a first virtual machine group list; sequencing all the virtual machine group identifications in the first virtual machine group list according to the virtual machine core number and a second preset rule to obtain a second virtual machine group list; sequencing all the virtual machine set identifications in the second virtual machine set list according to the affinity group number and a third preset rule to obtain a third virtual machine set list; obtaining the virtual machine pre-deployment graph according to the third virtual machine group list;

7. A VNF instantiation device, characterized in that the device comprises at least: a processor and a storage medium configured to store executable instructions, wherein: the processor is configured to execute stored executable instructions;

the executable instructions are configured to perform the VNF instantiation method provided in any one of the preceding claims 1 to 5.

8. A storage medium having stored therein computer-executable instructions configured to perform the VNF instantiation method provided in any one of claims 1 to 5.