[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2016183799A1 - 一种硬件加速方法以及相关设备 - Google Patents

一种硬件加速方法以及相关设备 Download PDF

Info

Publication number
WO2016183799A1
WO2016183799A1 PCT/CN2015/079274 CN2015079274W WO2016183799A1 WO 2016183799 A1 WO2016183799 A1 WO 2016183799A1 CN 2015079274 W CN2015079274 W CN 2015079274W WO 2016183799 A1 WO2016183799 A1 WO 2016183799A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
vim
size
hardware
vnf
Prior art date
Application number
PCT/CN2015/079274
Other languages
English (en)
French (fr)
Inventor
彭俊
彭展
杨旭
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority to EP24177552.7A priority Critical patent/EP4462251A1/en
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to RU2017144205A priority patent/RU2687711C1/ru
Priority to CN202010529799.9A priority patent/CN111831392A/zh
Priority to JP2017560311A priority patent/JP6568238B2/ja
Priority to EP15892178.3A priority patent/EP3287897B1/en
Priority to CN201580000939.0A priority patent/CN106663012B/zh
Priority to BR112017024661-9A priority patent/BR112017024661B1/pt
Priority to PCT/CN2015/079274 priority patent/WO2016183799A1/zh
Priority to KR1020177036054A priority patent/KR102022441B1/ko
Publication of WO2016183799A1 publication Critical patent/WO2016183799A1/zh
Priority to US15/817,264 priority patent/US10620986B2/en
Priority to US16/829,871 priority patent/US11068298B2/en
Priority to US17/379,539 priority patent/US11544100B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors
    • G06F9/45558—Hypervisor-specific management and integration aspects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/445—Program loading or initiating
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/445—Program loading or initiating
    • G06F9/44505—Configuring for program initiating, e.g. using registry, configuration files
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/40—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using virtualisation of network functions or resources, e.g. SDN or NFV entities
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/5041—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the time relationship between creation and deployment of a service
    • H04L41/5048—Automatic or semi-automatic definitions, e.g. definition templates
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/5041—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the time relationship between creation and deployment of a service
    • H04L41/5054—Automatic deployment of services triggered by the service manager, e.g. service implementation by automatic configuration of network components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors
    • G06F9/45558—Hypervisor-specific management and integration aspects
    • G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors
    • G06F9/45558—Hypervisor-specific management and integration aspects
    • G06F2009/45579—I/O management, e.g. providing access to device drivers or storage
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors
    • G06F9/45558—Hypervisor-specific management and integration aspects
    • G06F2009/45595—Network integration; Enabling network access in virtual machine instances
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/12—Discovery or management of network topologies

Definitions

  • the present invention relates to the field of cloud computing, and in particular, to a hardware acceleration method and related equipment.
  • Cloud computing distributes computing operations on distributed virtual computing resources. Through the network central data center, enterprises or users can switch resources to different applications that need to access different computers and storage systems according to their needs.
  • Cloud computing is a traditional computer and network such as Distributed Computing, Parallel Computing, Utility Computing, Network Storage, Virtualization, and Load Balance. The product of technological development integration.
  • the cloud computing system contains many modules and components.
  • the cloud architecture is divided into two parts: service and management.
  • service and management In terms of services, the main focus is on providing users with various cloud-based services, including three levels.
  • the first layer is Software as a Service (SaaS).
  • SaaS Software as a Service
  • the role of this layer is to provide applications to customers mainly in a Web-based manner.
  • the second layer is Platform as a Service (PaaS, Platform as a Service).
  • PaaS Platform as a Service
  • the role of the layer is to provide an application development and deployment platform as a service to the user;
  • the third layer is Infrastructure as a Service (IaaS, Infrastructure as a Service), the role of this layer is to put various underlying computing (such as virtual machines) And resources such as storage are provided to the user as a service.
  • IaaS Infrastructure as a Service
  • these three layers of services are independent because the services they provide are completely different and the users are not the same. But from a technical point of view, the three layers of cloud services are somewhat dependent.
  • a SaaS layer of products and services not only need to use the technology of the SaaS layer itself, but also rely on the development and deployment platform provided by the PaaS layer, or directly deployed on the computing resources provided by the IaaS layer, while the PaaS layer products And the service is also likely to be built on top of the IaaS layer service.
  • management it is mainly based on cloud management. Its function is to ensure that the entire cloud computing system can run safely and stably, and can be effectively managed.
  • NFV network function virtualization
  • the structure of the architecture can be seen in Figure 1.
  • the network architecture virtualized infrastructure is defined in the new architecture.
  • NFVI virtual infrastructure manager VIM, virtual network function management VNFM (VNF Manager), network function virtualization orchestrator NFVO (Orchestrator), virtualized network element VNF and other functional objects.
  • NFVI provides a cloud-based infrastructure layer
  • VNF is a cloud-based network element application
  • virtual infrastructure manager VIM is responsible for infrastructure layer management
  • VNFM is responsible for VNF lifecycle management
  • NFVO is responsible for service lifecycle management
  • E/NMS It is the network management of the traditional CT telecommunication network element
  • the OSS/BSS is the network management system of the cloud system.
  • VNFD VNFD template and stored in the VNF Catalog (VNF Catalog).
  • NFVI resources are assigned to the VNF.
  • the NFV MANO is at least the unit consisting of the NFVO, the VNF, the VNF directory, and the VIM; according to the industry's prediction of data traffic in the next ten years (increased by 100 to 200 times), in addition to factors such as an increase in equipment size
  • DPDK Data Platform Development Kit
  • SOC System-On-a-Chip
  • MANO knows nothing about the resources to be accelerated in the VNF and the acceleration unit of the Host.
  • the prior art adopts the random or sequential VNF. Deployed to the Host of each DC, because the existing technical solution is unable to match the type of resources that the VNF needs to accelerate and the type of acceleration resources that the Host can provide, so that the type of the resource to be accelerated in the VNF and the host to be deployed are prone to occur. If the acceleration resource type does not match, the acceleration resource of the Host where the VNF is located cannot meet the acceleration requirement of the VNF, thereby reducing the performance of the VNF.
  • the invention provides a hardware acceleration method and related equipment
  • a first aspect of the embodiments of the present invention provides a hardware acceleration method, including:
  • the function entity determines the type and size of hardware acceleration resources required to be accelerated in the virtualized network element VNF in the management domain of the functional entity;
  • the functional entity determines a target virtual infrastructure manager VIM
  • the function entity deploys the to-be-accelerated VNF to the target host in the target VIM management domain by using the target VIM, where the size of the hardware matching resource of the target host is greater than the requirement in the VNF to be accelerated
  • the hardware accelerates the size of the resource, and the type of the hardware matching resource is consistent with the type of the hardware acceleration resource required.
  • the function entity is a network function virtualization orchestrator NFVO, and the function entity determines the type and size of hardware acceleration resources required to be accelerated in the virtualized network element VNF in the management domain of the functional entity, including:
  • the functional entity determining the target virtual infrastructure manager VIM includes:
  • the NFVO receives the hardware acceleration information sent by each VIM in the management domain of the NFVO, where the hardware acceleration information includes a size of the hardware matching resource, and the size of the reported hardware matching resource is within the management domain of each VIM.
  • the hardware matches the size of the hardware matching resource that the host with the largest resource has;
  • the NFVO determines a size of the target hardware matching resource, where the size of the target hardware matching resource is a maximum value of the size of each of the reported hardware matching resources;
  • the NFVO determines that the VIM corresponding to the target host is the target VIM.
  • the function entity deploying the to-be-accelerated VNF to the target host in the target VIM management domain by using the target VIM includes:
  • the NFVO sends first indication information to the virtual network function management VNFM, where the first indication information is used to enable the VNFM to send a second request message to the target VIM, where the second request information is used to make the target
  • the VIM deploys the to-accelerated VNF to the target host within the management domain of the target VIM.
  • the function entity is a virtual network function management VNFM, and the function entity determines the type and size of the hardware acceleration resource required to be accelerated in the virtualized network element VNF in the management domain of the functional entity, including:
  • VNFM Determining, by the VNFM, a type and a size of a hardware acceleration resource required in the VNF to be accelerated in the management domain of the NFVO according to a target field in a VNF descriptor template corresponding to the to-be-accelerated VNF;
  • the method further includes:
  • the VNFM sends the type and size of hardware acceleration resources required in the VNF to be accelerated to the NFVO.
  • the functional entity determining the target virtual infrastructure manager VIM includes:
  • the VNFM sends the third request information to the NFVO, so that the NFVO determines the target VIM according to the third request information and the type and size of hardware acceleration resources required in the to-be-accelerated VNF;
  • the functional entity deploys the to-accelerated VNF to the target VIM through the target VIM
  • the target hosts in the management domain include:
  • the VNFM receives the second indication information sent by the NFVO, where the second indication information is used to indicate the target VIM;
  • a second aspect of the embodiments of the present invention provides a hardware acceleration method, including:
  • the target virtual infrastructure management VIM sends the size of the hardware matching resource of the target host in the management domain of the target VIM to the functional entity, so that the functional entity determines the target VIM according to the size of the hardware matching resource of the target host.
  • the function entity is further configured to determine a type and a size of a hardware acceleration resource required to be accelerated in the virtualized network element VNF in the management domain of the functional entity;
  • the target VIM deploys the to-be-accelerated VNF to the target host in the target VIM management domain under the control of the functional entity, where the size of the hardware matching resource of the target host is greater than the to-be-accelerated The size of the required hardware acceleration resource in the VNF, the type of the hardware matching resource is consistent with the type of the required hardware acceleration resource.
  • the function entity is a network function virtualization orchestrator NFVO, and the target virtual infrastructure management VIM sends the size of the hardware matching resource of the target host in the management domain of the target VIM to the functional entity, including:
  • the target VIM sends the hardware acceleration information to the NFVO, where the hardware acceleration information includes a size of the hardware matching resource, where the size of the reported hardware matching resource is the largest hardware matching resource in the management domain of the target VIM.
  • the hardware of the target host matches the size of the resource, so that the NFVO determines the size of the target hardware matching resource according to the hardware acceleration information, where the size of the target hardware matching resource is the VIM of the NFVO management domain. Reporting a maximum value of the size of the hardware matching resource, so that the NFVO determines that the host corresponding to the size of the target hardware matching resource is the target host, so that the NFVO determines that the VIM corresponding to the target host is The target VIM.
  • Deploying the to-be-accelerated VNF to the target host in the target VIM management domain under the control of the functional entity includes:
  • the target VIM deploys the to-accelerated VNF to the target host in the management domain of the target VIM according to the first request information
  • the target VIM receives a second request message sent by the virtual network function management VNFM, where the VNFM is configured to receive first indication information sent by the NFVO, where the first indication information is used to send the VNFM to the target VIM. Sending a second request message;
  • the target VIM deploys the to-accelerated VNF to the target host in the management domain of the target VIM according to the second request message.
  • the function entity is a virtual network function management VNFM, and the target VIM deploys the to-be-accelerated VNF to the target host in the target VIM management domain under the control of the functional entity, including:
  • the target VIM receives the fourth request information sent by the VNFM, and the VNFM is configured to send fourth request information to the target VIM according to the second indication information, where the VNFM is further configured to receive the Two indication information, the second indication information is used to indicate the target VIM;
  • the target VIM deploys the to-be-accelerated VNF to the target host in the management domain of the target VIM according to the fourth request information.
  • a third aspect of the embodiments of the present invention provides a functional entity, including:
  • a first determining unit configured to determine a type and a size of a hardware acceleration resource required to be accelerated in the virtualized network element VNF in the management domain of the functional entity
  • a second determining unit configured to determine a target virtual infrastructure manager VIM
  • a first deployment unit configured to deploy the to-accelerated VNF to the target by using the target VIM
  • the size of the hardware matching resource of the target host is greater than the size of the hardware acceleration resource required by the VNF to be accelerated, and the type of the hardware matching resource and the required The types of hardware acceleration resources are the same.
  • the function entity is a network function virtualization orchestrator NFVO, and the first determining unit includes:
  • the first determining unit is further configured to determine, according to a target field in the VNF descriptor template corresponding to the to-be-accelerated VNF, a type and a size of a hardware acceleration resource required in the to-accelerated VNF in the management domain of the NFVO.
  • the second determining unit includes:
  • a first receiving module configured to receive hardware acceleration information sent by each VIM in the management domain of the NFVO, where the hardware acceleration information includes a size of a hardware matching resource, where the size of the reported hardware matching resource is The hardware in the management domain of the VIM matches the size of the hardware matching resource that the host with the largest resource has;
  • a first determining module configured to determine a size of the target hardware matching resource, where the size of the target hardware matching resource is a maximum value of the size of each reported hardware matching resource;
  • a second determining module configured to determine that the host corresponding to the size of the target hardware matching resource is the target host
  • a third determining module configured to determine that the VIM corresponding to the target host is the target VIM.
  • the first deployment unit includes:
  • a first sending module configured to send first request information to the target VIM, where the first request information is used to enable the target VIM to deploy the to-accelerated VNF to the target in a management domain of the target VIM On the host;
  • a second sending module configured to send, to the virtual network function management VNFM, the first indication information, where the first indication information is used to send the VNFM to send, by the VNFM, a second request message, where the second request information is used by Having the target VIM deploy the to-accelerated VNF to the target host within a management domain of the target VIM.
  • the function entity is a virtual network function management VNFM
  • the first determining unit is further configured to determine, according to the target field in the VNF descriptor template corresponding to the to-be-accelerated VNF, the to-be-served domain in the NFVO Accelerate the type and size of hardware acceleration resources required in the VNF;
  • the functional entity further includes:
  • a first sending unit configured to send, to the NFVO, a type and a size of a hardware acceleration resource required in the to-be-accelerated VNF.
  • the second determining is further configured to send the third request information to the NFVO, so that the NFVO determines, according to the third request information and a type and size of hardware acceleration resources required in the to-be-accelerated VNF.
  • Said target VIM
  • the first deployment unit includes:
  • a second receiving module configured to receive second indication information that is sent by the NFVO, where the second indication information is used to indicate the target VIM;
  • a third sending module configured to send fourth request information to the target VIM according to the second indication information, where the fourth request information is used to enable the target VIM to deploy the to-accelerated VNF to the target VIM.
  • the fourth request information is used to enable the target VIM to deploy the to-accelerated VNF to the target VIM.
  • a fourth aspect of the embodiments of the present invention provides a target virtual infrastructure management VIM, including:
  • a second sending unit configured to send, to the functional entity, a size of a hardware matching resource of the target host in the management domain of the target VIM, so that the functional entity determines the target according to the size of the hardware matching resource of the target host a VIM, and the function entity is further configured to determine a type and a size of a hardware acceleration resource required to be accelerated in the virtualized network element VNF in the management domain of the functional entity;
  • a second deployment unit configured to deploy the to-accelerated VNF to the functional entity
  • the target VIM is configured on the target host in the domain, wherein the size of the hardware matching resource of the target host is greater than the size of the hardware acceleration resource required in the VNF to be accelerated, and the type of the hardware matching resource is The types of hardware acceleration resources required are the same.
  • the function entity is a network function virtualization orchestrator NFVO
  • the second sending unit is further configured to: send hardware acceleration information to the NFVO, where the hardware acceleration information includes reporting a size of a hardware matching resource,
  • the size of the hardware matching resource is the size of the hardware matching resource of the target host with the largest hardware matching resource in the management domain of the target VIM, so that the NFVO determines the size of the target hardware matching resource according to the hardware acceleration information.
  • the size of the target hardware matching resource is a maximum value of the size of the reported hardware matching resource of each VIM in the management domain of the NFVO, so that the NFVO determines that the host corresponding to the target hardware matching resource size is
  • the target host causes the NFVO to determine that the VIM corresponding to the target host is the target VIM.
  • the second deployment unit includes:
  • a third receiving module configured to receive first request information sent by the NFVO
  • a first deployment module configured to deploy the to-accelerated VNF to the target host in a management domain of the target VIM according to the first request information
  • a fourth receiving module configured to receive a second request message sent by the virtual network function management VNFM, where the VNFM is configured to receive first indication information sent by the NFVO, where the first indication information is used to send the VNFM to the The target VIM sends a second request message;
  • a second deployment module configured to deploy the to-be-accelerated VNF to the target host in the management domain of the target VIM according to the second request message.
  • the functional entity is a virtual network function management VNFM
  • the second deployment unit includes:
  • a fifth receiving module configured to receive fourth request information sent by the VNFM, where the VNFM is configured to send fourth request information to the target VIM according to the second indication information, where the VNFM is further configured to receive the sent by the NFVO
  • the second indication information the second indication information is used to indicate the target VIM
  • a third deployment module configured to deploy the to-be-accelerated VNF to the target host in the management domain of the target VIM according to the fourth request information.
  • a fifth aspect of the embodiments of the present invention provides a functional entity, including: a transmitter, a receiver, and a processor;
  • the processor is configured to perform the following operations:
  • the size of the hardware matching resource of the target host is greater than the required hardware acceleration resource in the VNF to be accelerated.
  • the size of the hardware matching resource is the same as the type of the hardware acceleration resource required.
  • the function entity is a network function virtualization orchestrator NFVO, and the processor is further configured to perform the following operations:
  • the receiver is configured to perform the following operations:
  • the hardware acceleration information includes a size of the hardware matching resource, where the size of the reported hardware matching resource is a hardware match in the management domain of each VIM.
  • the size of the hardware matching resource owned by the host with the largest resource;
  • the processor is further configured to perform the following operations:
  • Determining a size of the target hardware matching resource where the size of the target hardware matching resource is a maximum value of the size of each of the reported hardware matching resources
  • the transmitter is configured to perform the following operations:
  • the function entity is a virtual network function management VNFM, and the processor is further configured to perform the following operations:
  • the transmitter is configured to perform the following operations:
  • the transmitter is further configured to perform the following operations:
  • the receiver is further configured to perform the following operations:
  • the transmitter is further configured to perform the following operations:
  • a sixth aspect of the embodiments of the present invention provides a target virtual infrastructure management VIM, including: a transmitter, a receiver, and a processor;
  • the transmitter is configured to perform the following operations:
  • the method is further configured to determine a type and a size of a hardware acceleration resource required to be accelerated in the virtualized network element VNF in the management domain of the functional entity;
  • the processor is configured to perform the following operations:
  • the function entity is a network function virtualization orchestrator NFVO, and the transmitter is further configured to perform the following operations:
  • the hardware acceleration information includes a size of the hardware matching resource, where the size of the reported hardware matching resource is the target host with the largest hardware matching resource in the management domain of the target VIM.
  • the hardware matches the size of the resource, so that the NFVO determines the size of the target hardware matching resource according to the hardware acceleration information, and the target hardware matches the resource.
  • a size of a maximum of the size of the reported hardware matching resource of each VIM in the management domain of the NFVO so that the NFVO determines that the host corresponding to the size of the target hardware matching resource is the target host, such that The NFVO determines that the VIM corresponding to the target host is the target VIM.
  • the receiver is configured to perform the following operations:
  • the processor is configured to perform the following operations:
  • the receiver is further configured to perform the following operations:
  • VNFM Receiving, by the virtual network function management, a second request message sent by the VNFM, where the VNFM is configured to receive the first indication information sent by the NFVO, where the first indication information is used to send the VNFM to send the second request to the target VIM.
  • the processor is further configured to perform the following operations:
  • the function entity is a virtual network function management VNFM, and the receiver is further configured to perform the following operations:
  • the VNFM is configured to send fourth request information to the target VIM according to the second indication information
  • the VNFM is further configured to receive the second indication information that is sent by the NFVO,
  • the second indication information is used to indicate the target VIM
  • the processor is configured to perform the following operations:
  • the present invention provides a hardware acceleration method and related device, the hardware acceleration method includes: determining, by a functional entity, a type and a size of a hardware acceleration resource required to be accelerated in a virtualized network element VNF in a management domain of the functional entity, The functional entity determines the target virtual infrastructure manager VIM, and the functional entity deploys the to-be-accelerated VNF to the target host in the target VIM management domain by using the target VIM.
  • the hardware of the target host The size of the matching resource is greater than the size of the required hardware acceleration resource in the VNF to be accelerated, and the type of the hardware matching resource is consistent with the type of the required hardware acceleration resource, so as to be adopted by the embodiment.
  • the hardware acceleration method can match the type of the required hardware acceleration resource of the VNF to be accelerated with the type of the hardware matching resource of the target host, so that the hardware matching resource of the target host can satisfy the VNF to be accelerated.
  • the acceleration demand effectively improves the performance of the VNF to be accelerated.
  • FIG. 1 is a schematic structural diagram of a network function virtualization architecture provided by the prior art
  • FIG. 2 is a flow chart of steps of a preferred embodiment of a hardware acceleration method according to an embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of a network function virtualization architecture according to an embodiment of the present invention.
  • FIG. 4 is a flow chart of steps of another preferred embodiment of a hardware acceleration method according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of another preferred embodiment of a network function virtualization architecture according to an embodiment of the present disclosure.
  • FIG. 6 is a flowchart of another preferred embodiment of a hardware acceleration method according to an embodiment of the present invention.
  • FIG. 7 is a flow chart of steps of a preferred embodiment of a hardware acceleration method according to an embodiment of the present invention.
  • FIG. 8 is a flowchart of another preferred embodiment of a hardware acceleration method according to an embodiment of the present invention.
  • FIG. 9 is a flowchart of another preferred embodiment of a hardware acceleration method according to an embodiment of the present invention.
  • FIG. 10 is a schematic structural diagram of a preferred embodiment of a functional entity according to an embodiment of the present disclosure.
  • FIG. 11 is a schematic structural diagram of another preferred embodiment of a functional entity according to an embodiment of the present disclosure.
  • FIG. 12 is a schematic structural diagram of another preferred embodiment of a functional entity according to an embodiment of the present disclosure.
  • FIG. 13 is a schematic structural diagram of a preferred embodiment of a target VIM according to an embodiment of the present disclosure.
  • FIG. 14 is a schematic structural diagram of another preferred embodiment of a target VIM according to an embodiment of the present disclosure.
  • FIG. 15 is a schematic structural diagram of another preferred embodiment of a target VIM according to an embodiment of the present disclosure.
  • FIG. 16 is a schematic structural diagram of another preferred embodiment of a functional entity according to an embodiment of the present disclosure.
  • FIG. 17 is a schematic structural diagram of another preferred embodiment of a target VIM according to an embodiment of the present invention.
  • the embodiment of the invention provides a hardware acceleration method, which enables the acceleration resource of the host where the VNF is located to meet the acceleration requirement of the VNF;
  • the hardware acceleration method provided in this embodiment is described in detail below with reference to FIG. 2, where the hardware acceleration method includes:
  • the function entity determines a type and a size of a hardware acceleration resource required to be accelerated in the virtualized network element VNF in the management domain of the functional entity.
  • the structure of the network function virtualization architecture provided in this embodiment is shown in FIG. 3, and the specific implementation structure of the functional entity is not limited in this embodiment;
  • a plurality of VNFs are included in the management domain of the functional entity, and the functional entity is capable of creating a VNF instance using a VNFD (Virtualized Network Function Descriptor), and deploying each VNF and The operational behavior is described by the VNFD template and stored in the VNF Catalog (VNF Catalog) and manages the lifecycle of these instances;
  • VNFD Virtualized Network Function Descriptor
  • VNFD has a one-to-one correspondence with VNF.
  • VNFD fully describes the implementation of a VNF. Required features and requirements.
  • the function entity can determine the VNF to be accelerated in hardware VNF in each VNF in the management domain of the functional entity by reading each of the VNFDs, and can determine by reading the VNFD corresponding to the VNF to be accelerated.
  • the specific implementation manner of the VNFD is not limited in this embodiment, as long as the VNFD can fully describe the characteristics and requirements necessary for each VNF in the management domain of the functional entity, that is, the functional entity reads the VNFD by reading the VNFD.
  • the requirement of the VNF to be accelerated can be determined, and the requirements of the VNF to be accelerated include, but are not limited to, the type and size of hardware acceleration resources required in the VNF to be accelerated, and compatibility and performance, and the like.
  • the network management system OSS/BSS of the cloud system, the network management E/NMS of the traditional CT telecommunication network element, and the network function virtualization infrastructure NFVI in the network function virtualization architecture shown in FIG. 3 are specifically shown in the prior art. Specifically, it is not described in this embodiment;
  • the specific type of the hardware acceleration resource is not limited in this embodiment, and may be any hardware resource that needs to be accelerated, such as a video acceleration resource.
  • the functional entity determines a target virtual infrastructure manager VIM
  • Determining, by the functional entity, that the VIM that meets the preset condition in the plurality of VIMs in the management domain of the functional entity is the target VIM, so that the target VIM determines the target host in the management domain of the target VIM;
  • the preset condition is that the target host is in the management domain of the target VIM
  • the size of the hardware matching resource of the target host is greater than the size of the hardware acceleration resource required in the VNF to be accelerated;
  • the type of the hardware matching resource is consistent with the type of the hardware acceleration resource required.
  • the function entity deploys the to-accelerated VNF to a target host in the target VIM management domain by using the target VIM.
  • the functional entity deploys the to-accelerated VNF to a target host within the target VIM management domain by the determined target VIM.
  • the functional entity is in the process of deploying the VNF to be accelerated to the host, Not being deployed in order or being deployed, but the functional entity deploys the to-accelerated VNF to a target host whose size of the hardware matching resource is larger than the size of the hardware acceleration resource required in the VNF to be accelerated.
  • the type of the hardware matching resource on the target host is consistent with the type of the required hardware acceleration resource, so that the hardware acceleration method shown in this embodiment can enable the need for the VNF to be accelerated.
  • the type of the hardware acceleration resource of the target host can be matched with the type of the hardware matching resource of the target host, and the size of the hardware matching resource of the target host is greater than the size of the hardware acceleration resource required in the VNF to be accelerated, thereby
  • the hardware matching resources of the target host can meet the acceleration requirement of the VNF to be accelerated, and effectively improve the performance of the VNF to be accelerated.
  • the following is a detailed description of an implementation manner in which the functional entity specifically determines the target VIM in conjunction with FIG. 4, and it is to be clarified that the following is a preferred example of how to determine the target VIM.
  • the accelerated VNF can be deployed to the target host;
  • the specific structure of the network function virtualization architecture can be shown in FIG. 5, and the embodiment is described by taking the functional entity as a network function virtualization orchestrator NFVO as an example;
  • the NFVO determines, according to a target field in a VNF descriptor template corresponding to the to-be-accelerated VNF, a type and a size of a hardware acceleration resource required in the to-be-accelerated VNF in the management domain of the NFVO.
  • the NFVO obtains the type and size of hardware acceleration resources required in the VNF to be accelerated in the NFVO management domain by reading the VNFD template in the VNF directory.
  • each VNF is described by the VNFD template and stored in the VNF directory (VNF Catalog), and the VNFD and the VNF are in a one-to-one correspondence.
  • the NFVO is read by The VNFD corresponding to the VNF to be accelerated that requires hardware acceleration can acquire the type and size of the hardware acceleration resource required for the hardware-accelerated VNF to be accelerated.
  • VNFD template in the VNF directory describes the type and size of hardware acceleration resources required in the VNF to be accelerated. It should be clarified that the following is only one type of the VNFD template. Preferred examples are not limited;
  • the VNFD template in the VNF directory is set with a target field vdu, and the target field vdu is as shown in Table 1;
  • a hardware accelerator parameter is added to the target field vdu, as shown in Table 2;
  • the NFVO can determine the type of the hardware acceleration resource of the VNF to be accelerated by reading the target field in the VNFD template corresponding to the to-be-accelerated VNF to obtain the hardware accelerator parameter. size;
  • the form of the hardware accelerator may be a dedicated hardware or a chip, which is not limited in this embodiment.
  • the NFVI includes, but is not limited to, a setting:
  • Accelerated device adaptation layer it is used to provide a unified adaptation framework for services
  • Accelerate device abstraction layer it is used to accelerate device installation, startup, monitoring, and deployment of administrators for server nodes;
  • Accelerated device pool hardware layer It is equipped with acceleration hardware including FPGA, South Bridge chip, processor-related accelerated SoC, and corresponding physical and virtual drivers.
  • the NFVO receives hardware acceleration information sent by each VIM in the management domain of the NFVO.
  • the hardware acceleration information includes reporting a size of a hardware matching resource
  • the size of the reported hardware matching resource is the size of the hardware matching resource of the host with the largest hardware matching resource in the management domain of each VIM;
  • the NFVO determines a size of a target hardware matching resource.
  • the size of the target hardware matching resource is a maximum value of the size of each reported hardware matching resource
  • the NFVO determines, that the host corresponding to the size of the target hardware matching resource is the target host.
  • the NFVO determines that the VIM corresponding to the target host is the target VIM.
  • the NFVO determines that the VIM of the maximum value of each of the reported hardware matching resources in the management domain of the NFVO is the target VIM, and determines the target.
  • An example of the VIM is not limited, and other manners of determining the target VIM may be adopted, as long as the type of the required hardware acceleration resource of the VNF to be accelerated is matched with the type of the hardware matching resource of the target host. And the size of the hardware matching resource of the target host is greater than the size of the hardware acceleration resource required in the VNF to be accelerated.
  • the NFVO determines, according to the determined type of hardware acceleration resource required in the to-be-accelerated VNF, the hardware acceleration information that each VIM in the NFVO management domain has;
  • the VIM is configured with at least an acceleration device cloud management layer, which is a cloud management system of the acceleration device, and the cloud management system is configured to allocate and deploy resources.
  • the acceleration device cloud management layer of the VIM determines the size of the hardware matching resource of the host with the largest hardware matching resource in the management domain of the VIM, so that the VIM has the largest host matching resource in the management domain.
  • the size of the hardware matching resource that is available can be reported to the NFVO.
  • the NFVO generates first request information.
  • the first request information is used by the NFVO to notify the target VIM to deploy the to-accelerated VNF to the target host in the management domain of the target VIM.
  • the NFVO sends the first request information to the target VIM.
  • the VNF to be accelerated may be deployed to the target host in the management domain of the target VIM;
  • Step 406 to step 407 are used for the step of the NFVO deploying the to-be-accelerated VNF to the target host by using the target VIM. It is to be noted that the steps 406 to 407 are exemplified and not limited. Other deployment methods may be employed, such as steps 408 to 409 described below. Shown
  • the NFVO generates first indication information.
  • the first indication information is used to indicate the target VIM to the virtual network function management VNFM, so that the VNFM can determine the target VIM according to the first indication information, and perform deployment of the VNF to be accelerated;
  • the NFVO sends the first indication information to the virtual network function management VNFM.
  • the first indication information is used to enable the VNFM to send a second request message to the target VIM, where the second request information is used to enable the target VIM to deploy the to-accelerated VNF to the target VIM.
  • the target host within the domain.
  • the NFVO determines that the target VIM is the VIM corresponding to the target host as the target VIM, and the target host matches the target hardware in the process of deploying the to-be-accelerated VNF to the host.
  • the type of the acceleration resource is matched with the type of the hardware matching resource of the target host, and the size of the hardware matching resource of the target host is greater than the size of the hardware acceleration resource required in the VNF to be accelerated, thereby causing the target host
  • the hardware matching resource can meet the acceleration requirement of the VNF to be accelerated, and effectively improve the performance of the VNF to be accelerated.
  • the following is a detailed description of an implementation manner in which the functional entity specifically determines the target VIM in conjunction with FIG. 6. It is to be clarified that the following is a preferred example of how to determine the target VIM, and the following is not limited.
  • the accelerated VNF can be deployed to the target host;
  • the specific structure of the network function virtualization architecture can be as shown in FIG. 5, and the embodiment is described by taking the functional entity as a virtual network function management VNFM as an example;
  • the VNFM determines, according to a target field in a VNF descriptor template corresponding to the to-be-accelerated VNF, a type and a size of a hardware acceleration resource required in the to-accelerated VNF in the management domain of the NFVO.
  • the VNFM is obtained by reading a VNFD template in a VNF directory. Taking the type and size of hardware acceleration resources required in the VNF to be accelerated in the NFVO management domain that requires hardware acceleration;
  • the VNFD is read and stored in the VNF directory (VNF Catalog), and the VNFD and the VNF are in a one-to-one correspondence.
  • the VNFM is read by The VNFD corresponding to the VNF to be accelerated that requires hardware acceleration can acquire the type and size of the hardware acceleration resource required for the hardware-accelerated VNF to be accelerated.
  • the VNFD template in the VNF directory is provided with a target field vdu to enable the VNFM to determine the to-accelerated VNF in the management domain of the NFVO according to a target field in a VNF descriptor template corresponding to the to-accelerated VNF.
  • the VNFM sends the type and size of the hardware acceleration resource required in the VNF to be accelerated to the NFVO.
  • the VNFM sends the NFVO to the NFVO by reading the type and size of hardware acceleration resources required in the to-accelerated VNF that the target field has acquired.
  • the VNFM sends third request information to the NFVO.
  • the third request information is used to cause the NFVO to determine the target VIM according to the third request information and the type and size of hardware acceleration resources required in the to-be-accelerated VNF;
  • the VNFM receives the second indication information sent by the NFVO.
  • the NFVO generates the second indication information according to the determined target VIM, and the second indication information is used to indicate the target VIM.
  • the VNFM sends fourth request information to the target VIM according to the second indication information.
  • the fourth request information is used to enable the target VIM to deploy the to-accelerated VNF to the target host in a management domain of the target VIM.
  • the hardware acceleration method shown in this embodiment can enable the type of the required hardware acceleration resource of the VNF to be accelerated to match the type of the hardware matching resource of the target host, and the hardware of the target host
  • the size of the matching resource is greater than the hardness required in the VNF to be accelerated
  • the size of the resource is accelerated, so that the hardware matching resource of the target host can meet the acceleration requirement of the VNF to be accelerated, and the performance of the VNF to be accelerated is effectively improved.
  • the target virtual infrastructure management VIM sends the size of the hardware matching resource of the target host in the management domain of the target VIM to the functional entity.
  • the target VIM is a VIM that meets a preset condition among a plurality of VIMs in the management domain of the functional entity is the target VIM;
  • the preset condition is that the target host is in the management domain of the target VIM
  • the function entity is further configured to determine a type and a size of a hardware acceleration resource required to be accelerated in the virtualized network element VNF in the management domain of the functional entity;
  • the target VIM deploys the to-accelerated VNF to the target host in the target VIM management domain under the control of the functional entity.
  • the size of the hardware matching resource of the target host in the management domain of the target VIM is greater than the size of the hardware acceleration resource required in the VNF to be accelerated, the type of the hardware matching resource and the required hardware.
  • the types of accelerated resources are consistent.
  • the target VIM sends the size of the hardware matching resource of the target host in the management domain of the target VIM to the functional entity, so that the functional entity can determine the target VIM, and the target VIM can be
  • the VNF to be accelerated is deployed under the control of the functional entity to
  • the target VIM is configured on the target host in the domain, and the target VIM is deployed in the process of deploying the to-accelerated VNF to the target host in the target VIM management domain, not in order or immediately Deploying, but deploying the to-accelerated VNF to a target host whose size of the hardware matching resource is greater than the size of the hardware acceleration resource required in the to-be-expanded VNF, and the hardware matching resource on the target host
  • the type of the hardware acceleration resource is the same as the type of the hardware acceleration resource required to enable the type of the hardware acceleration resource of the required VNF to be accelerated and the target host by the hardware acceleration method shown in this embodiment.
  • the type of the hardware matching resource can be matched, and the size of the hardware matching resource of the target host is greater than the size of the hardware acceleration resource required in the VNF to be accelerated, so that the hardware matching resource of the target host can satisfy the waiting Accelerating the acceleration demand of VNF effectively improves the performance of the VNF to be accelerated.
  • the following describes, in conjunction with FIG. 8, how the target VIM implements the hardware acceleration method if the functional entity is a network function virtualization orchestrator NFVO;
  • the specific structure of the network function virtualization architecture for implementing the hardware acceleration method shown in this embodiment can be shown in FIG. 5, and the specific description of the network function virtualization architecture shown in FIG. As shown, it is not described in detail in this embodiment;
  • the target VIM sends hardware acceleration information to the NFVO.
  • the hardware acceleration information includes a size of the hardware matching resource, where the size of the hardware matching resource is the size of the hardware matching resource of the target host with the largest hardware matching resource in the management domain of the target VIM;
  • the hardware acceleration information sent by each of the VIMs in the management domain of the NFVO includes a size of the hardware matching resource
  • the size of the reported hardware matching resource is the hardware in the management domain of each of the VIMs. Matches the size of the hardware matching resource that the host with the largest resource has;
  • the NFVO is configured to determine, according to the hardware acceleration information, a size of a target hardware matching resource, where the size of the target hardware matching resource is a maximum value of the reported hardware matching resources of each VIM in the management domain of the NFVO,
  • the host that determines that the NFVO corresponds to the size of the target hardware matching resource is the target host, so that the NFVO determines that the VIM corresponding to the target host is the target VIM.
  • the target VIM is the reported hardware of each of the NFVO management domains.
  • the VIM of the maximum value of the allocated resources is an example of determining the target VIM, and is not limited, and other methods of determining the target VIM may be adopted as long as the required hardware of the VNF to be accelerated is made.
  • the type of the acceleration resource is matched with the type of the hardware matching resource of the target host, and the size of the hardware matching resource of the target host is greater than the size of the hardware acceleration resource required in the VNF to be accelerated.
  • the target VIM receives the first request information sent by the NFVO.
  • the target VIM deploys the to-be-accelerated VNF to the target host in the management domain of the target VIM according to the first request information.
  • Steps 802 to 803 are used for the step of the target VIM to deploy the VNF to be deployed to the target host. It should be clarified that the steps 802 to 803 are exemplified, and are not limited, and other deployments may be adopted. The method is as shown in the following steps 804 to 805;
  • the target VIM receives a second request message sent by the virtual network function management VNFM.
  • the VNFM is configured to receive first indication information that is sent by the NFVO, where the first indication information is used to enable the VNFM to send a second request message to the target VIM;
  • the target VIM deploys the to-be-accelerated VNF to the target host in a management domain of the target VIM according to the second request message.
  • the target VIM sends hardware acceleration information to the NFVO, so that the NFVO determines that the target VIM is corresponding to the target host in the process of deploying the VNF to be accelerated to the host.
  • the VIM is the target VIM, and the target host matches the target hardware matching resource size, and the target hardware matching resource matches the hardware in the management domain of each VIM sent by each VIM in the management domain of the NFVO.
  • the size of the hardware matching resource of the host with the largest resource is such that the type of the hardware matching resource on the target host is consistent with the type of the required hardware acceleration resource, so as to be described by the embodiment.
  • the hardware acceleration method can match the type of the required hardware acceleration resource of the VNF to be accelerated with the type of the hardware matching resource of the target host, and the size of the hardware matching resource of the target host is greater than the to-be-accelerated The required hardware acceleration resource size in the VNF, so that the hardware matching resource of the target host can meet the acceleration requirement of the VNF to be accelerated Effectively enhance the performance of VNF to be accelerated.
  • the specific structure of the network function virtualization architecture for implementing the hardware acceleration method shown in this embodiment can be shown in FIG. 5, and the specific description of the network function virtualization architecture shown in FIG. As shown, it is not described in detail in this embodiment;
  • the target VIM sends hardware acceleration information to the NFVO.
  • step 801 shown in FIG. 8 which is not described in detail in this embodiment.
  • the target VIM receives the fourth request information sent by the VNFM.
  • the VNFM is configured to send fourth request information to the target VIM according to the second indication information, where the VNFM is further configured to receive the second indication information that is sent by the NFVO, where the second indication information is used to indicate the Target VIM;
  • the target VIM deploys the to-be-accelerated VNF to the target host in the management domain of the target VIM according to the fourth request information.
  • the hardware acceleration method shown in this embodiment can enable the type of the required hardware acceleration resource of the VNF to be accelerated to match the type of the hardware matching resource of the target host, and the hardware of the target host
  • the size of the matching resource is greater than the size of the hardware acceleration resource required in the VNF to be accelerated, so that the hardware matching resource of the target host can meet the acceleration requirement of the VNF to be accelerated, and the performance of the VNF to be accelerated is effectively improved.
  • the functional entities include:
  • the first determining unit 1001 is configured to determine a type and a size of a hardware acceleration resource required to be accelerated in the virtualized network element VNF in the management domain of the functional entity;
  • the structure of the network function virtualization architecture provided in this embodiment is shown in FIG. 3, and the specific implementation structure of the functional entity is not limited in this embodiment;
  • a second determining unit 1002 configured to determine a target virtual infrastructure manager VIM
  • the VIM is the target VIM such that the target VIM determines the target host within the administrative domain of the target VIM;
  • the preset condition is that the target host is in the management domain of the target VIM
  • the size of the hardware matching resource of the target host is greater than the size of the hardware acceleration resource required in the VNF to be accelerated;
  • the type of the hardware matching resource is consistent with the type of the hardware acceleration resource required.
  • the first deployment unit 1003 is configured to deploy the to-be-accelerated VNF to the target host in the target VIM management domain by using the target VIM, where the size of the hardware matching resource of the target host is greater than the to-be-accelerated VNF The size of the required hardware acceleration resource, where the type of the hardware matching resource is consistent with the type of the hardware acceleration resource required.
  • the function entity deploys the VNF to be accelerated to the host, is not deployed in order, or is deployed immediately, but the functional entity deploys the to-accelerated VNF to hardware matching.
  • the size of the resource is greater than the size of the required hardware acceleration resource in the VNF to be accelerated, and the type of the hardware matching resource on the target host is consistent with the type of the required hardware acceleration resource.
  • the hardware acceleration method shown in this embodiment enables the type of the hardware acceleration resource of the required VNF to be accelerated to match the type of the hardware matching resource of the target host, and the target host
  • the size of the hardware matching resource is greater than the size of the hardware acceleration resource required in the VNF to be accelerated, so that the hardware matching resource of the target host can meet the acceleration requirement of the VNF to be accelerated, thereby effectively improving the performance of the VNF to be accelerated.
  • the specific structure of the network function virtualization architecture can be shown in FIG. 5, and the embodiment is described by taking the functional entity as a network function virtualization orchestrator NFVO as an example;
  • the functional entities include:
  • the first determining unit 1101 is further configured to determine, according to a target field in the VNF descriptor template corresponding to the to-be-accelerated VNF, a type and a size of a hardware acceleration resource required in the to-accelerated VNF in the management domain of the NFVO.
  • the NFVO is obtained by reading a VNFD template in a VNF directory. Taking the type and size of hardware acceleration resources required in the VNF to be accelerated in the NFVO management domain that requires hardware acceleration;
  • a second determining unit 1102 configured to determine a target virtual infrastructure manager VIM
  • the second determining unit 1102 further includes:
  • the first receiving module 11021 is configured to receive hardware acceleration information sent by each VIM in the management domain of the NFVO, where the hardware acceleration information includes a size of a hardware matching resource, where the size of the reported hardware matching resource is The size of the hardware matching resource possessed by the host with the largest hardware matching resource in the management domain of the VIM;
  • the first determining module 11022 is configured to determine a size of the target hardware matching resource, where the size of the target hardware matching resource is a maximum value of the size of each of the reported hardware matching resources;
  • the second determining module 11023 is configured to determine that the host corresponding to the size of the target hardware matching resource is the target host;
  • the third determining module 11024 is configured to determine that the VIM corresponding to the target host is the target VIM;
  • the first deployment unit 1103 is configured to deploy the to-be-accelerated VNF to the target host in the target VIM management domain by using the target VIM, where the size of the hardware matching resource of the target host is greater than the to-be-accelerated VNF The size of the required hardware acceleration resource, where the type of the hardware matching resource is consistent with the type of the hardware acceleration resource required;
  • the first deployment unit 1103 includes:
  • the first sending module 11031 is configured to send first request information to the target VIM, where the first request information is used to enable the target VIM to deploy the to-accelerated VNF to the management domain of the target VIM.
  • the target host On the target host;
  • the first deployment unit 1103 includes:
  • the second sending module 11032 is configured to send the first indication information to the virtual network function management VNFM, where the first indication information is used to send the VNFM to send the second request message to the target VIM.
  • the second request information is used to cause the target VIM to deploy the to-accelerated VNF to the target host in a management domain of the target VIM.
  • the NFVO determines that the target VIM is the VIM corresponding to the target host as the target VIM, and the target host matches the target hardware in the process of deploying the to-be-accelerated VNF to the host.
  • the type of the acceleration resource is matched with the type of the hardware matching resource of the target host, and the size of the hardware matching resource of the target host is greater than the size of the hardware acceleration resource required in the VNF to be accelerated, thereby causing the target host
  • the hardware matching resource can meet the acceleration requirement of the VNF to be accelerated, and effectively improve the performance of the VNF to be accelerated.
  • the specific structure of the network function virtualization architecture can be as shown in FIG. 5, and the embodiment is described by taking the functional entity as a virtual network function management VNFM as an example;
  • the functional entities include:
  • the first determining unit 1201 is further configured to determine, according to a target field in the VNF descriptor template corresponding to the to-be-accelerated VNF, a type and a size of a hardware acceleration resource required in the to-be-accelerated VNF in the management domain of the NFVO.
  • the first determining unit 1201 is further configured to determine, according to a target field in the VNF descriptor template corresponding to the to-be-accelerated VNF, a type of hardware acceleration resource required in the to-accelerated VNF in the management domain of the NFVO and size;
  • the VNFM specifically reads the VNFD template in the VNF directory, and obtains the type and size of the hardware acceleration resource required in the VNF to be accelerated in the management domain of the NFVO, as shown in the above embodiment. The details are not described in the embodiments.
  • the first sending unit 1202 is configured to send the type and size of the hardware acceleration resource required in the to-be-accelerated VNF to the NFVO;
  • a second determining unit 1203, configured to determine a target virtual infrastructure manager VIM
  • the second determining unit 1203 is further configured to send third request information to the NFVO, so that the NFVO is based on the third request information and a type and size of hardware acceleration resources required in the to-be-accelerated VNF. Determining the target VIM;
  • the first deployment unit 1204 is configured to deploy the to-be-accelerated VNF to the target host in the target VIM management domain by using the target VIM, where the size of the hardware matching resource of the target host is greater than the to-be-accelerated VNF The size of the required hardware acceleration resource, where the type of the hardware matching resource is consistent with the type of the hardware acceleration resource required;
  • the first deployment unit 1204 includes:
  • the second receiving module 12041 is configured to receive second indication information that is sent by the NFVO, where the second indication information is used to indicate the target VIM;
  • the third sending module 12042 is configured to send fourth request information to the target VIM according to the second indication information, where the fourth request information is used to enable the target VIM to deploy the to-accelerated VNF to the target VIM. Manage the target host within the domain.
  • the type of the hardware acceleration resource that can be used to enable the VNF to be accelerated is matched with the type of the hardware matching resource of the target host, and the size of the hardware matching resource of the target host is larger than that of the target host.
  • the size of the hardware acceleration resource required for accelerating the VNF is described, so that the hardware matching resource of the target host can meet the acceleration requirement of the VNF to be accelerated, and the performance of the VNF to be accelerated is effectively improved.
  • the structure of the target VIM capable of realizing the acceleration resource of the host where the VNF is located can meet the acceleration requirement of the VNF is described in detail below with reference to FIG. 13 :
  • the target virtual infrastructure management VIM includes:
  • the second sending unit 1301 is configured to send, to the functional entity, a size of a hardware matching resource of the target host in the management domain of the target VIM, so that the functional entity determines the size according to the size of the hardware matching resource of the target host.
  • a target VIM and the function entity is further configured to determine a type and a size of a hardware acceleration resource required to be accelerated in the virtualized network element VNF in the management domain of the functional entity;
  • a second deployment unit 1302 configured to deploy the to-be-accelerated VNF to the target host in the target VIM management domain under control of the functional entity, where a size of a hardware matching resource of the target host is greater than The size of the required hardware acceleration resource in the to-be-accelerated VNF, the type of the hardware matching resource being consistent with the type of the required hardware acceleration resource.
  • the target VIM sends the size of the hardware matching resource of the target host in the management domain of the target VIM to the functional entity, so that the functional entity can determine the target VIM, and the target VIM can be Deploying the to-be-accelerated VNF to the target host in the target VIM management domain under the control of the functional entity, and deploying the to-be-accelerated VNF to the target VIM management domain
  • the system is not deployed in order or deployed, but the size of the hardware-matching resource to be accelerated to be deployed to the hardware matching resource is larger than the size of the hardware acceleration resource required in the VNF to be accelerated.
  • the type of the hardware matching resource on the target host is consistent with the type of the required hardware acceleration resource, so that the hardware acceleration method shown in this embodiment can enable the VNF to be accelerated.
  • the type of the required hardware acceleration resource can be matched with the type of the hardware matching resource of the target host, and the hardware matching resource of the target host is large.
  • VNF be greater than the hardware acceleration in the acceleration required size of the resource, and then match the hardware resources so that the target host to be able to meet the acceleration demand VNF of the acceleration, the acceleration to be effective to enhance the performance of VNF.
  • the specific structure for implementing the network function virtualization architecture shown in this embodiment can be as shown in FIG. 5, and the specific description of the network function virtualization architecture shown in FIG. It will not be described in this embodiment;
  • the second sending unit 1401 is further configured to send the hardware acceleration information to the NFVO, where the hardware acceleration information includes a size of the hardware matching resource, where the size of the reported hardware matching resource is within the management domain of the target VIM.
  • the hardware matches the size of the hardware matching resource that the target host has the largest resource, so that the NFVO determines the size of the target hardware matching resource according to the hardware acceleration information, where the size of the target hardware matching resource is within the management domain of the NFVO.
  • the reporting hardware of each VIM matches a maximum value of the size of the resource, such that the NFVO determines that the host corresponding to the size of the target hardware matching resource is the target host, such that the NFVO is determined and the The VIM corresponding to the target host is the target VIM.
  • the second deployment unit 1402 is configured to deploy the to-be-accelerated VNF to the target host in the target VIM management domain under the control of the functional entity, where the hardware matching resource size of the target host is greater than The size of the required hardware acceleration resource in the to-be-accelerated VNF, the type of the hardware matching resource being consistent with the type of the required hardware acceleration resource.
  • the second deployment unit 1402 includes:
  • the third receiving module 14021 is configured to receive first request information sent by the NFVO.
  • the first deployment module 14022 is configured to deploy the to-be-accelerated VNF to the target host in the management domain of the target VIM according to the first request information.
  • the fourth receiving module 14023 is configured to receive a second request message sent by the virtual network function management VNFM, where the VNFM is used to receive the first indication information sent by the NFVO, where the first indication information is used to enable the VNFM to Sending, by the target VIM, a second request message;
  • the second deployment module 14024 is configured to deploy the to-accelerated VNF to the target host in the management domain of the target VIM according to the second request message.
  • the target VIM sends hardware acceleration information to the NFVO, so that the NFVO determines that the target VIM is corresponding to the target host in the process of deploying the VNF to be accelerated to the host.
  • the VIM is the target VIM, and the target host matches the target hardware matching resource size, and the target hardware matching resource matches the hardware in the management domain of each VIM sent by each VIM in the management domain of the NFVO.
  • the size of the hardware matching resource of the host with the largest resource is such that the type of the hardware matching resource on the target host is consistent with the type of the required hardware acceleration resource, so as to be described by the embodiment.
  • the hardware acceleration method can match the type of the required hardware acceleration resource of the VNF to be accelerated with the type of the hardware matching resource of the target host, and the size of the hardware matching resource of the target host is greater than the to-be-accelerated The required hardware acceleration resource size in the VNF, so that the hardware matching resource of the target host can meet the acceleration requirement of the VNF to be accelerated Effectively enhance the performance of VNF to be accelerated.
  • the target virtual infrastructure management VIM includes:
  • a second sending unit 1501 configured to send, to the functional entity, a size of a hardware matching resource of the target host in the management domain of the target VIM, so that the functional entity determines the size according to the size of the hardware matching resource of the target host.
  • a target VIM, and the function entity is further configured to determine a type and a size of a hardware acceleration resource required to be accelerated in the virtualized network element VNF in the management domain of the functional entity;
  • a second deployment unit 1502 configured to deploy the to-be-accelerated VNF to the target host in the target VIM management domain under control of the functional entity, where a size of a hardware matching resource of the target host is greater than The size of the required hardware acceleration resource in the to-be-accelerated VNF, the type of the hardware matching resource being consistent with the type of the required hardware acceleration resource.
  • the second deployment unit 1502 includes:
  • the fifth receiving module 15021 is configured to receive fourth request information sent by the VNFM, where the VNFM is configured to send fourth request information to the target VIM according to the second indication information, where the VNFM is further configured to receive the NFVO sent by the NFVO.
  • the second indication information the second indication information is used to indicate the target VIM;
  • the third deployment module 15022 is configured to deploy the to-accelerated VNF to the target host in the management domain of the target VIM according to the fourth request information.
  • the type of the hardware acceleration resource that can be used to enable the VNF to be accelerated is matched with the type of the hardware matching resource of the target host, and the size of the hardware matching resource of the target host is larger than that of the target host.
  • the size of the hardware acceleration resource required for accelerating the VNF is described, so that the hardware matching resource of the target host can meet the acceleration requirement of the VNF to be accelerated, and the performance of the VNF to be accelerated is effectively improved.
  • the following is a hardware structure that enables the implementation of the acceleration resources of the host where the VNF is located to meet the acceleration requirements of the VNF:
  • the functional entity includes: a transmitter 1601, a receiver 1602, and a processor 1603;
  • the processor 1603 is configured to perform the following operations:
  • the size of the hardware matching resource of the target host is greater than the required hardware acceleration resource in the VNF to be accelerated.
  • the size of the hardware matching resource is the same as the type of the hardware acceleration resource required.
  • the function entity is a network function virtualization orchestrator NFVO
  • the processor 1603 is further configured to perform the following operations:
  • receiver 1602 is configured to perform the following operations:
  • the hardware acceleration information includes a size of the hardware matching resource, where the size of the reported hardware matching resource is a hardware match in the management domain of each VIM.
  • the size of the hardware matching resource owned by the host with the largest resource;
  • the processor 1603 is further configured to perform the following operations:
  • Determining a size of the target hardware matching resource where the size of the target hardware matching resource is a maximum value of the size of each of the reported hardware matching resources
  • the transmitter 1601 is configured to perform the following operations:
  • the function entity is a virtual network function management VNFM
  • the processor 1603 is further configured to perform the following operations:
  • the transmitter 1601 is configured to perform the following operations:
  • the transmitter 1601 is further configured to perform the following operations:
  • the receiver 1602 is further configured to perform the following operations:
  • the transmitter 1601 is further configured to perform the following operations:
  • the following is a hardware-oriented structure of a target VIM that enables the acceleration resources of the host where the VNF is located to meet the acceleration requirements of the VNF:
  • the target virtual infrastructure management VIM includes: a transmitter 1701, a receiver 1702, and a processor 1703;
  • the transmitter 1701 is configured to perform the following operations:
  • the method is further configured to determine a type and a size of a hardware acceleration resource required to be accelerated in the virtualized network element VNF in the management domain of the functional entity;
  • the processor 1703 is configured to perform the following operations:
  • the function entity is a network function virtualization orchestrator NFVO
  • the transmitter 1701 is further configured to perform the following operations:
  • the hardware acceleration information includes a size of the hardware matching resource, where the size of the reported hardware matching resource is the target host with the largest hardware matching resource in the management domain of the target VIM.
  • the hardware matches the size of the resource, so that the NFVO determines the size of the target hardware matching resource according to the hardware acceleration information, where the size of the target hardware matching resource is the reported hardware matching resource of each VIM in the management domain of the NFVO.
  • the maximum of the sizes such that the NFVO determines that the host corresponding to the size of the target hardware matching resource is the target host, such that the NFVO determines that the VIM corresponding to the target host is the target VIM.
  • receiver 1702 is configured to perform the following operations:
  • the processor 1703 is configured to perform the following operations:
  • the receiver 1702 is further configured to perform the following operations:
  • VNFM Receiving, by the virtual network function management, a second request message sent by the VNFM, where the VNFM is configured to receive the first indication information sent by the NFVO, where the first indication information is used to send the VNFM to send the second request to the target VIM.
  • the processor 1703 is further configured to perform the following operations:
  • the function entity is a virtual network function management VNFM
  • the receiver 1702 is further configured to perform the following operations:
  • the VNFM is configured to send fourth request information to the target VIM according to the second indication information
  • the VNFM is further configured to receive the second indication information that is sent by the NFVO,
  • the second indication information is used to indicate the target VIM
  • the processor 1703 is configured to perform the following operations:

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

一种硬件加速方法以及相关设备，所述硬件加速方法包括：功能实体确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小（201），所述功能实体确定目标虚拟基础设施管理器VIM（202），所述功能实体通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上（203）。所述功能实体将所述待加速VNF部署至硬件匹配资源的大小大于所述待加速VNF中所需要的硬件加速资源的大小的目标主机上，使得所述待加速VNF的所需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效地提升了待加速VNF的性能。

Description

一种硬件加速方法以及相关设备 技术领域
本发明涉及云计算领域，尤其涉及的是一种硬件加速方法以及相关设备。
背景技术
云计算是将计算作业分布在分布式虚拟计算资源上，通过网络中央数据中心，企业或用户能够将资源切换到需要的不同应用上，根据需求访问不同的计算机和存储系统。云计算是分布式计算(Distributed Computing)、并行计算(Parallel Computing)、效用计算(Utility Computing)、网络存储(Network Storage)、虚拟化(Virtualization)，以及负载均衡(Load Balance)等传统计算机和网络技术发展融合的产物。
云计算系统作为一个非常复杂的大型软件系统，其中包含着许许多多的模块和组件，云架构共分为服务和管理两大部分。在服务方面，主要以提供用户基于云的各种服务为主，共包含3个层次。第一层是软件即服务(SaaS，Software as a Service)，这层的作用是将应用主要以基于Web的方式提供给客户；第二层是平台即服务(PaaS，Platform as a Service)，这层的作用是将一个应用的开发和部署平台作为服务提供给用户；第三层是基础设施即服务(IaaS，Infrastructure as a Service)，这层的作用是将各种底层的计算(比如虚拟机)和存储等资源作为服务提供给用户。从用户角度而言，这3层服务是独立的，因为它们提供的服务是完全不同的，而且面向的用户也不尽相同。但从技术角度而言，云服务的这3层是有一定依赖关系的。比如，一个SaaS层的产品和服务不仅需要用到SaaS层本身的技术，而且还依赖PaaS层所提供的开发和部署平台，或者直接部署于IaaS层所提供的计算资源上，而PaaS层的产品和服务也很有可能构建于IaaS层服务之上。在管理方面，主要以云管理层为主，它的功能是确保整个云计算系统能够安全、稳定地运行，并且能够被有效管理。
随着云计算技术的不断成熟，IT与CT领域相互渗透融合，CT运营商为应对未来竞争挑战，顺应当前虚拟化、云计算的技术发展趋势，提出了ICT领域的网络功能虚拟化(NFV，Network Functions Virtualization)架构。该架构的结构示意图可参见图1所示，新架构中定义了网络功能虚拟化基础设施 NFVI、虚拟基础设施管理器VIM、虚拟网络功能管理VNFM(VNF Manager)、网络功能虚拟化编排器NFVO(Orchestrator)、虚拟化网元VNF等功能对象。NFVI提供云化的基础设施层，VNF为云化后的网元应用；虚拟基础设施管理器VIM负责基础设施层管理，VNFM负责VNF的生命周期管理，NFVO负责服务的生命周期管理；E/NMS为传统CT电信网元的网管，OSS/BSS为云化系统的网管。每个VNF的部署和操作行为都由VNFD的模板描述并存放在VNF目录(VNF Catalog)中。
基于VNFD中描述的需求，同时也考虑预先设定的特定需求、约束和策略，NFVI资源被分配给VNF。随着电信业务的增长，在NFV MANO的架构下，运营商认可加速器是NFVI的关键元素，和CPU、网卡(NIC，Network Interface Card)以及存储并列。其中，所述NFV MANO至少为所述NFVO、所述VNF、VNF目录以及所述VIM组成的单元；根据业界对未来十年数据流量的预测(增长100～200倍)，除开设备规模增加等因素，折算到对未来单个server的能力，保守估算至少要增长10倍，这个也是对每个CPU的能力诉求。通过数据平台开发套件(DPDK，Data Platform Development Kit)优化、软件性能优化等手段，最多也只能提升到4～5倍，远远达不到server能力诉求。这个巨大的性能差距，整个业界都在积极通过片上系统(SOC，System-On-a-Chip)、硬件加速等手段来解决。
在现有的架构下，MANO对于VNF内的待加速资源和Host的加速单元的情况一无所知，在将VNF部署至Host上的过程中，现有技术采用的是将VNF随机或按顺序部署到各DC的Host上的，因为现有技术方案是无法匹配VNF所需要加速的资源与其Host能够提供的加速资源的类型，从而容易出现VNF内的待加速资源类型和部署到的Host上的加速资源类型不匹配，会导致VNF所在的Host的加速资源无法满足VNF的加速需求，从而降低了VNF的性能。
发明内容
本发明提供了一种硬件加速方法以及相关设备；
本发明实施例第一方面提供了一种硬件加速方法，包括：
功能实体确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
所述功能实体确定目标虚拟基础设施管理器VIM；
所述功能实体通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
结合本发明实施例第一方面，本发明实施例第一方面的第一种实现方式中，
所述功能实体为网络功能虚拟化编排器NFVO，则所述功能实体确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小包括：
所述NFVO根据与所述待加速VNF对应的VNF描述符模板中的目标字段确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小。
结合本发明实施例第一方面的第一种实现方式，本发明实施例第一方面的第二种实现方式中，
所述功能实体确定目标虚拟基础设施管理器VIM包括：
所述NFVO接收所述NFVO的管理域内各所述VIM发送的硬件加速信息，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小；
所述NFVO确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为各所述上报硬件匹配资源的大小中的最大值；
所述NFVO确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机；
所述NFVO确定与所述目标主机对应的VIM为所述目标VIM。
结合本发明实施例第一方面的第一种实现方式或本发明实施例第一方面的第二种实现方式，本发明实施例第一方面的第三种实现方式中，
所述功能实体通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上包括：
所述NFVO向所述目标VIM发送第一请求信息，所述第一请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
或，
所述NFVO向虚拟网络功能管理VNFM发送第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息，所述第二请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
结合本发明实施例第一方面的第一种实现方式，本发明实施例第一方面的第四种实现方式中，
所述功能实体为虚拟网络功能管理VNFM，则所述功能实体确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小包括：
所述VNFM根据与所述待加速VNF对应的VNF描述符模板中的目标字段以确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小；
所述功能实体确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小之后，所述方法还包括：
所述VNFM将所述待加速VNF中需要的硬件加速资源的类型和大小发送给所述NFVO。
结合本发明实施例第一方面的第四种实现方式，本发明实施例第一方面的第五种实现方式中，
所述功能实体确定目标虚拟基础设施管理器VIM包括：
所述VNFM将第三请求信息发送给所述NFVO，以使所述NFVO根据所述第三请求信息以及所述待加速VNF中需要的硬件加速资源的类型和大小确定所述目标VIM；
所述功能实体通过所述目标VIM将所述待加速VNF部署至所述目标VIM 管理域内的目标主机上包括：
所述VNFM接收所述NFVO所发送的第二指示信息，所述第二指示信息用于指示所述目标VIM；
所述VNFM根据所述第二指示信息向目标VIM发送第四请求信息，所述第四请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
本发明实施例第二方面提供了一种硬件加速方法，包括：
目标虚拟基础设施管理VIM将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体，以使所述功能实体根据所述目标主机的硬件匹配资源的大小确定所述目标VIM，且所述功能实体还用于确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
所述目标VIM在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
结合本发明实施例第二方面，本发明实施例第二方面的第一种实现方式中，
所述功能实体为网络功能虚拟化编排器NFVO，则所述目标虚拟基础设施管理VIM将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体包括：
所述目标VIM将硬件加速信息发送给所述NFVO，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为所述目标VIM的管理域内的硬件匹配资源最大的目标主机所具有的硬件匹配资源的大小，以使所述NFVO根据所述硬件加速信息确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为所述NFVO的管理域内各VIM的所述上报硬件匹配资源的大小中的最大值，以使所述NFVO确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机，使得所述NFVO确定与所述目标主机对应的VIM为所述目标VIM。
结合本发明实施例第二方面的第一种实现方式，本发明实施例第二方面的第二种实现方式中，
所述目标VIM在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上包括：
所述目标VIM接收所述NFVO发送的第一请求信息；
所述目标VIM根据所述第一请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
或，
所述目标VIM接收虚拟网络功能管理VNFM发送的第二请求消息，所述VNFM用于接收所述NFVO发送的第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息；
所述目标VIM根据所述第二请求消息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
结合本发明实施例第二方面，本发明实施例第二方面的第三种实现方式中，
所述功能实体为虚拟网络功能管理VNFM，则所述目标VIM在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上包括：
所述目标VIM接收所述VNFM发送的第四请求信息，所述VNFM用于根据第二指示信息向目标VIM发送第四请求信息，所述VNFM还用于接收所述NFVO所发送的所述第二指示信息，所述第二指示信息用于指示所述目标VIM；
所述目标VIM根据所述第四请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
本发明实施例第三方面提供了一种功能实体，包括：
第一确定单元，用于确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
第二确定单元，用于确定目标虚拟基础设施管理器VIM；
第一部署单元，用于通过所述目标VIM将所述待加速VNF部署至所述目 标VIM管理域内的目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
结合本发明实施例第三方面，本发明实施例第三方面的第一种实现方式中，
所述功能实体为网络功能虚拟化编排器NFVO，则所述第一确定单元包括：
第一确定单元还用于，根据与所述待加速VNF对应的VNF描述符模板中的目标字段确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小。
结合本发明实施例第三方面的第一种实现方式，本发明实施例第三方面的第二种实现方式中，
所述第二确定单元包括：
第一接收模块，用于接收所述NFVO的管理域内各所述VIM发送的硬件加速信息，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小；
第一确定模块，用于确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为各所述上报硬件匹配资源的大小中的最大值；
第二确定模块，用于确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机；
第三确定模块，用于确定与所述目标主机对应的VIM为所述目标VIM。
结合本发明实施例第三方面的第一种实现方式或本发明实施例第三方面的第二种实现方式，本发明实施例第三方面的第三种实现方式中，
所述第一部署单元包括：
第一发送模块，用于向所述目标VIM发送第一请求信息，所述第一请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
或，
第二发送模块，用于向虚拟网络功能管理VNFM发送第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息，所述第二请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
结合本发明实施例第三方面，本发明实施例第三方面的第四种实现方式中，
所述功能实体为虚拟网络功能管理VNFM，则所述第一确定单元还用于，根据与所述待加速VNF对应的VNF描述符模板中的目标字段以确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小；
所述功能实体还包括：
第一发送单元，用于将所述待加速VNF中需要的硬件加速资源的类型和大小发送给所述NFVO。
结合本发明实施例第三方面的第四种实现方式，本发明实施例第三方面的第五种实现方式中，
所述第二确定还用于，将第三请求信息发送给所述NFVO，以使所述NFVO根据所述第三请求信息以及所述待加速VNF中需要的硬件加速资源的类型和大小确定所述目标VIM；
所述第一部署单元包括：
第二接收模块，用于接收所述NFVO所发送的第二指示信息，所述第二指示信息用于指示所述目标VIM；
第三发送模块，用于根据所述第二指示信息向目标VIM发送第四请求信息，所述第四请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
本发明实施例第四方面提供了一种目标虚拟基础设施管理VIM，包括：
第二发送单元，用于将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体，以使所述功能实体根据所述目标主机的硬件匹配资源的大小确定所述目标VIM，且所述功能实体还用于确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
第二部署单元，用于在所述功能实体的控制下将所述待加速VNF部署至 所述目标VIM管理域内的所述目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
结合本发明实施例第四方面，本发明实施例第四方面的第一种实现方式中，
所述功能实体为网络功能虚拟化编排器NFVO，则所述第二发送单元还用于，将硬件加速信息发送给所述NFVO，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为所述目标VIM的管理域内的硬件匹配资源最大的目标主机所具有的硬件匹配资源的大小，以使所述NFVO根据所述硬件加速信息确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为所述NFVO的管理域内各VIM的所述上报硬件匹配资源的大小中的最大值，以使所述NFVO确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机，使得所述NFVO确定与所述目标主机对应的VIM为所述目标VIM。
结合本发明实施例第四方面的第一种实现方式，本发明实施例第四方面的第二种实现方式中，
所述第二部署单元包括：
第三接收模块，用于接收所述NFVO发送的第一请求信息；
第一部署模块，用于根据所述第一请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
或，
第四接收模块，用于接收虚拟网络功能管理VNFM发送的第二请求消息，所述VNFM用于接收所述NFVO发送的第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息；
第二部署模块，用于根据所述第二请求消息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
结合本发明实施例第四方面，本发明实施例第四方面的第三种实现方式中，
所述功能实体为虚拟网络功能管理VNFM，则所述第二部署单元包括：
第五接收模块，用于接收所述VNFM发送的第四请求信息，所述VNFM用于根据第二指示信息向目标VIM发送第四请求信息，所述VNFM还用于接收所述NFVO所发送的所述第二指示信息，所述第二指示信息用于指示所述目标VIM；
第三部署模块，用于根据所述第四请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
本发明实施例第五方面提供了一种功能实体，包括：发送器、接收器和处理器；
所述处理器用于执行如下操作：
确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
确定目标虚拟基础设施管理器VIM；
通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
结合本发明实施例第五方面，本发明实施例第五方面的第一种实现方式中，
所述功能实体为网络功能虚拟化编排器NFVO，则所述处理器还用于执行如下操作：
根据与所述待加速VNF对应的VNF描述符模板中的目标字段确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小。
结合本发明实施例第五方面的第一种实现方式，本发明实施例第五方面的第二种实现方式中，
所述接收器用于执行如下操作：
接收所述NFVO的管理域内各所述VIM发送的硬件加速信息，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小；
所述处理器还用于执行如下操作：
确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为各所述上报硬件匹配资源的大小中的最大值；
确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机；
确定与所述目标主机对应的VIM为所述目标VIM。
结合本发明实施例第五方面的第一种实现方式或本发明实施例第五方面的第二种实现方式，本发明实施例第五方面的第三种实现方式中，
所述发送器用于执行如下操作：
向所述目标VIM发送第一请求信息，所述第一请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
或，
向虚拟网络功能管理VNFM发送第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息，所述第二请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
结合本发明实施例第五方面，本发明实施例第五方面的第四种实现方式中，
所述功能实体为虚拟网络功能管理VNFM，则所述处理器还用于执行如下操作：
根据与所述待加速VNF对应的VNF描述符模板中的目标字段以确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小；
所述发送器用于执行如下操作：
将所述待加速VNF中需要的硬件加速资源的类型和大小发送给所述NFVO。
结合本发明实施例第五方面的第四种实现方式，本发明实施例第五方面的第五种实现方式中，
所述发送器还用于执行如下操作：
将第三请求信息发送给所述NFVO，以使所述NFVO根据所述第三请求 信息以及所述待加速VNF中需要的硬件加速资源的类型和大小确定所述目标VIM；
所述接收器还用于执行如下操作：
接收所述NFVO所发送的第二指示信息，所述第二指示信息用于指示所述目标VIM；
所述发送器还用于执行如下操作：
根据所述第二指示信息向目标VIM发送第四请求信息，所述第四请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
本发明实施例第六方面提供了一种目标虚拟基础设施管理VIM，包括：发送器、接收器和处理器；
所述发送器用于执行如下操作：
将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体，以使所述功能实体根据所述目标主机的硬件匹配资源的大小确定所述目标VIM，且所述功能实体还用于确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
所述处理器用于执行如下操作：
在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
结合本发明实施例第六方面，本发明实施例第六方面的第一种实现方式中，
所述功能实体为网络功能虚拟化编排器NFVO，则所述发送器还用于执行如下操作：
将硬件加速信息发送给所述NFVO，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为所述目标VIM的管理域内的硬件匹配资源最大的目标主机所具有的硬件匹配资源的大小，以使所述NFVO根据所述硬件加速信息确定目标硬件匹配资源的大小，所述目标硬件匹配资源 的大小为所述NFVO的管理域内各VIM的所述上报硬件匹配资源的大小中的最大值，以使所述NFVO确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机，使得所述NFVO确定与所述目标主机对应的VIM为所述目标VIM。
结合本发明实施例第六方面的第一种实现方式，本发明实施例第六方面的第二种实现方式中，
所述接收器用于执行如下操作：
接收所述NFVO发送的第一请求信息；
所述处理器用于执行如下操作：
根据所述第一请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
或，
所述接收器还用于执行如下操作：
接收虚拟网络功能管理VNFM发送的第二请求消息，所述VNFM用于接收所述NFVO发送的第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息；
所述处理器还用于执行如下操作：
根据所述第二请求消息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
结合本发明实施例第六方面，本发明实施例第六方面的第三种实现方式中，
所述功能实体为虚拟网络功能管理VNFM，则所述接收器还用于执行如下操作：
接收所述VNFM发送的第四请求信息，所述VNFM用于根据第二指示信息向目标VIM发送第四请求信息，所述VNFM还用于接收所述NFVO所发送的所述第二指示信息，所述第二指示信息用于指示所述目标VIM；
所述处理器用于执行如下操作：
根据所述第四请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
本发明提供了一种硬件加速方法以及相关设备，所述硬件加速方法包括：功能实体确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小，所述功能实体确定目标虚拟基础设施管理器VIM，所述功能实体通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上，本实施例中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致，以使通过本实施例所示的所述硬件加速方法能够使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效的提升了待加速VNF的性能。
附图说明
图1为现有技术所提供的网络功能虚拟化架构的结构示意图；
图2为本发明实施例所提供的硬件加速方法的一种较佳实施例步骤流程图；
图3为本发明实施例所提供的网络功能虚拟化架构的一种较佳实施例结构示意图；
图4为本发明实施例所提供的硬件加速方法的另一种较佳实施例步骤流程图；
图5为本发明实施例所提供的网络功能虚拟化架构的另一种较佳实施例结构示意图；
图6为本发明实施例所提供的硬件加速方法的另一种较佳实施例步骤流程图；
图7为本发明实施例所提供的硬件加速方法的一种较佳实施例步骤流程图；
图8为本发明实施例所提供的硬件加速方法的另一种较佳实施例步骤流程图；
图9为本发明实施例所提供的硬件加速方法的另一种较佳实施例步骤流程图；
图10为本发明实施例所提供的功能实体的一种较佳实施例结构示意图；
图11为本发明实施例所提供的功能实体的另一种较佳实施例结构示意图；
图12为本发明实施例所提供的功能实体的另一种较佳实施例结构示意图；
图13为本发明实施例所提供的目标VIM的一种较佳实施例结构示意图；
图14为本发明实施例所提供的目标VIM的另一种较佳实施例结构示意图；
图15为本发明实施例所提供的目标VIM的另一种较佳实施例结构示意图；
图16为本发明实施例所提供的功能实体的另一种较佳实施例结构示意图；
图17为本发明实施例所提供的目标VIM的另一种较佳实施例结构示意图。
具体实施方式
本发明实施例提供一种硬件加速方法，该硬件加速方法使得VNF所在的主机的加速资源能够满足VNF的加速需求；
以下结合图2所示对本实施例所提供的硬件加速方法进行详细说明，所述硬件加速方法包括：
201、功能实体确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
本实施例所提供的网络功能虚拟化架构的结构请参见图3所示，本实施例对所述功能实体具体实现结构不做限定；
由图3所示可知，所述功能实体的管理域内包括多个VNF，且所述功能实体能够使用VNF描述符(VNFD，Virtualised Network Function Descriptor)来创建VNF实例，且对每个VNF的部署和操作行为都由VNFD的模板描述并存放在VNF目录(VNF Catalog)中，并管理这些实例的生命周期；
且VNFD与VNF有一对一的对应关系，VNFD充分描述了实现一个VNF 所必需的特性和要求。
所述功能实体能够通过读取各所述VNFD从而确定所述功能实体的管理域内的各VNF中需要进行硬件加速的待加速VNF，且通过读取与所述待加速VNF对应的VNFD即可确定该待加速VNF中需要的硬件加速资源的类型和大小；
本实施例对所述VNFD具体实现方式不做限定，只要所述VNFD能够充分描述所述功能实体的管理域内各VNF所必需的特性和要求即可，即所述功能实体通过读取所述VNFD能够确定所述待加速VNF的需求，所述待加速VNF的需求包括但不限于所述待加速VNF中需要的硬件加速资源的类型和大小，以及兼容性和性能等。
图3所示的网络功能虚拟化架构中的所述云化系统的网管OSS/BSS、传统CT电信网元的网管E/NMS以及网络功能虚拟化基础设施NFVI具体请参见现有技术所示，具体在本实施例中不做赘述；
本实施例对所述硬件加速资源的具体类型不做限定，例如可为视频加速资源等任意需要加速的硬件资源。
202、所述功能实体确定目标虚拟基础设施管理器VIM；
所述功能实体确定所述功能实体的管理域内的多个VIM中满足预设条件的VIM为所述目标VIM，以使目标VIM确定所述目标VIM的管理域内的所述目标主机；
所述预设条件为所述目标VIM的管理域内有所述目标主机；
具体的，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小；
更具体的，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
203、所述功能实体通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上。
所述功能实体通过已确定的所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上。
本实施例中，所述功能实体在将待加速VNF部署至所述主机上的过程中， 不是按序部署或者是随即部署的，而是所述功能实体将所述待加速VNF部署至硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小的目标主机上，且该目标主机上的所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致，以使通过本实施例所示的所述硬件加速方法能够使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效的提升了待加速VNF的性能。
以下结合图4对所述功能实体具体确定目标VIM的一种实现方式进行详细说明，需明确的是，下述对如何确定目标VIM的为较佳的示例，不做限定，只要使得所述待加速VNF能够部署至所述目标主机上即可；
本实施例中，所述网络功能虚拟化架构的具体结构可参加图5所示，且本实施例以所述功能实体为网络功能虚拟化编排器NFVO为例进行说明；
401、所述NFVO根据与所述待加速VNF对应的VNF描述符模板中的目标字段确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小；
具体的，如图5所示，所述NFVO通过读取VNF目录中的VNFD模板获取所述NFVO的管理域内需要硬件加速的待加速VNF中需要的硬件加速资源的类型和大小；
其中，对每个VNF的部署和操作行为都由VNFD模板描述并存放在VNF目录(VNF Catalog)中，而且VNFD与VNF是一一对应的关系，则本实施例中，所述NFVO通过读取与需要硬件加速的待加速VNF对应的VNFD，即可获取该需要硬件加速的待加速VNF的需要的硬件加速资源的类型和大小。
以下对所述VNF目录中的VNFD模板是如何描述所述待加速VNF中需要的硬件加速资源的类型和大小的进行举例说明，需明确的是，下述仅仅是对所述VNFD模板的一种较佳的举例，不做限定；
所述VNF目录中的VNFD模板设置有目标字段vdu，所述目标字段vdu如表1所示；
表1
Figure PCTCN2015079274-appb-000001
本实施例中，在所述目标字段vdu中加入硬件加速器参数，具体如表2所示；
表2
Figure PCTCN2015079274-appb-000002
即本实施例中，所述NFVO通过读取与所述待加速VNF对应的VNFD模板中的所述目标字段以获取所述硬件加速器参数即可确定所述待加速VNF的硬件加速资源的类型和大小；
其中，所述硬件加速器的形式可能为专用硬件或芯片，具体在本实施例中不做限定。
具体的，如图5所示，所述NFVI包括但不限于设置有：
加速设备适配层：其用于为业务提供统一适配框架；
加速设备抽象层：其用于为服务器节点加速设备安装、启动、监控、部署管理者；
加速设备池硬件层：其设置有加速硬件包含FPGA、南桥芯片、处理器相关加速SoC以及对应物理和虚拟驱动。
402、所述NFVO接收所述NFVO的管理域内的各所述VIM发送的硬件加速信息；
所述硬件加速信息中包括上报硬件匹配资源的大小；
所述上报硬件匹配资源的大小为各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小；
403、所述NFVO确定目标硬件匹配资源的大小；
其中，所述目标硬件匹配资源的大小为各所述上报硬件匹配资源的大小中的最大值；
404、所述NFVO确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机；
405、所述NFVO确定与所述目标主机对应的VIM为所述目标VIM；
由步骤402至步骤405所示可知，本实施例中，所述NFVO确定所述NFVO的管理域内各所述上报硬件匹配资源的大小中的最大值的VIM为目标VIM为一种确定所述目标VIM的示例，不做限定，还可采用其他确定所述目标VIM的方式，只要使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小即可。
具体的，所述NFVO根据已确定的所述待加速VNF中需要的硬件加速资源的类型确定所述NFVO管理域内各VIM所具有的所述硬件加速信息；
具体的，如图5所示，所述VIM至少设置有加速设备云管理层，其为加速设备的云管理系统，该云管理系统用于对资源进行分配部署。
更具体的，所述VIM的加速设备云管理层确定所述VIM的管理域内硬件匹配资源最大的主机所具有的硬件匹配资源的大小，以使所述VIM将其管理域内硬件匹配资源最大的主机所具有的硬件匹配资源的大小能够上报给所述NFVO。
406、所述NFVO生成第一请求信息；
其中，所述第一请求信息用于所述NFVO通知所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
407、所述NFVO向所述目标VIM发送所述第一请求信息；
所述目标VIM接收到所述第一请求消息后，即可将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
其中，步骤406至步骤407用于所述NFVO通过所述目标VIM将待加速VNF部署至所述目标主机上的步骤，需明确的是，步骤406至步骤407为举例说明，不做限定，还可采用其他部署方式，例如下述步骤408至步骤409 所示；
408、所述NFVO生成第一指示信息；
其中，所述第一指示信息用于将所述目标VIM指示给虚拟网络功能管理VNFM，以使所述VNFM能够根据所述第一指示信息确定所述目标VIM，并进行待加速VNF的部署；
409、所述NFVO向虚拟网络功能管理VNFM发送第一指示信息；
所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息，所述第二请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
本实施例中，所述NFVO在将待加速VNF部署至所述主机上的过程中，确定目标VIM为与所述目标主机对应的VIM为所述目标VIM，所述目标主机与目标硬件匹配资源的大小对应的主机，所述目标硬件匹配资源所述NFVO的管理域内各所述VIM发送的各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小，使得所述目标主机上的所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致，以使通过本实施例所示的所述硬件加速方法能够使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效的提升了待加速VNF的性能。
以下结合图6对所述功能实体具体确定目标VIM的一种实现方式进行详细说明，需明确的是，下述对如何确定目标VIM的为较佳的示例，不做限定，只要使得所述待加速VNF能够部署至所述目标主机上即可；
本实施例中，所述网络功能虚拟化架构的具体结构可参加图5所示，且本实施例以所述功能实体为虚拟网络功能管理VNFM为例进行说明；
601、所述VNFM根据与所述待加速VNF对应的VNF描述符模板中的目标字段以确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小；
具体的，如图5所示，所述VNFM通过读取VNF目录中的VNFD模板获 取所述NFVO的管理域内需要硬件加速的待加速VNF中需要的硬件加速资源的类型和大小；
其中，对每个VNF的部署和操作行为都由VNFD模板描述并存放在VNF目录(VNF Catalog)中，而且VNFD与VNF是一一对应的关系，则本实施例中，所述VNFM通过读取与需要硬件加速的待加速VNF对应的VNFD，即可获取该需要硬件加速的待加速VNF的需要的硬件加速资源的类型和大小。
所述VNF目录中的VNFD模板设置有目标字段vdu，以使所述VNFM能够根据与所述待加速VNF对应的VNF描述符模板中的目标字段以确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小；
其中，所述目标字段的具体设置方式请参见表1以及表2所示，具体在本实施例中不做赘述。
602、所述VNFM将所述待加速VNF中需要的硬件加速资源的类型和大小发送给所述NFVO；
所述VNFM通过读取所述目标字段已获取的所述待加速VNF中需要的硬件加速资源的类型和大小发送给所述NFVO。
603、所述VNFM将第三请求信息发送给所述NFVO；
所述第三请求信息用于使得所述NFVO根据所述第三请求信息以及所述待加速VNF中需要的硬件加速资源的类型和大小确定所述目标VIM；
其中，所述NFVO所确定的目标VIM的具体过程可参见图4所示的步骤402至步骤405所示，具体在本实施例中不做赘述。
604、所述VNFM接收所述NFVO所发送的第二指示信息；
所述NFVO根据已确定的所述目标VIM生成所述第二指示信息，且所述第二指示信息用于指示所述目标VIM。
605、所述VNFM根据所述第二指示信息向目标VIM发送第四请求信息；
其中，所述第四请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
通过本实施例所示的所述硬件加速方法能够使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬 件加速资源的大小，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效的提升了待加速VNF的性能。
以上从功能实体的角度对如何实现本实施例所示的硬件加速方法的进行详细说明，以下从虚拟基础设施管理VIM角度对如何实现本实施例所示的硬件加速方法的进行详细说明；
以下结合图7对所述硬件加速方法的另一种实施例进行详细说明；
其中，能够实现本实施例所示的所述硬件加速方法的网络功能虚拟化架构请参见图3所示，对图3所示的所述网络功能虚拟化架构的具体说明请详见上述实施例所示，具体在本实施例中不做赘述。
701、目标虚拟基础设施管理VIM将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体；
所述目标VIM为所述功能实体的管理域内多个VIM中满足预设条件的VIM为所述目标VIM；
所述预设条件为所述目标VIM的管理域内有所述目标主机；
所述功能实体根据所述目标主机的硬件匹配资源的大小确定所述目标VIM；
且所述功能实体还用于确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
其中，所述功能实体具体如何确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小的请见图2所示的实施例，具体在本实施例中不做赘述。
702、所述目标VIM在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上。
其中，所述目标VIM的管理域内的所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
本实施例中，所述目标VIM将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体，以使所述功能实体能够确定所述目标VIM，所述目标VIM能够在所述功能实体的控制下将所述待加速VNF部署至 所述目标VIM管理域内的所述目标主机上，且所述目标VIM在将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上的过程中，不是按序部署或者是随即部署的，而是将所述待加速VNF部署至硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小的目标主机上，且该目标主机上的所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致，以使通过本实施例所示的所述硬件加速方法能够使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效的提升了待加速VNF的性能。
以下结合图8说明若所述功能实体为网络功能虚拟化编排器NFVO时，所述目标VIM是如何实现所述硬件加速方法的；
用于实现本实施例所示的硬件加速方法的网络功能虚拟化架构的具体结构可参加图5所示，且对图5所示的所述网络功能虚拟化架构的具体说明请参见上述实施例所示，具体在本实施例中不做赘述；
801、所述目标VIM将硬件加速信息发送给所述NFVO；
其中，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为所述目标VIM的管理域内的硬件匹配资源最大的目标主机所具有的硬件匹配资源的大小；
即所述NFVO的管理域内的各所述VIM发送的硬件加速信息，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小；
所述NFVO用于根据所述硬件加速信息确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为所述NFVO的管理域内各VIM的所述上报硬件匹配资源的大小中的最大值，以使所述NFVO确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机，使得所述NFVO确定与所述目标主机对应的VIM为所述目标VIM。
本实施例中，所述目标VIM为所述NFVO的管理域内各所述上报硬件匹 配资源的大小中的最大值的VIM为一种确定所述目标VIM的示例，不做限定，还可采用其他确定所述目标VIM的方式，只要使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小即可。
802、所述目标VIM接收所述NFVO发送的第一请求信息；
803、所述目标VIM根据所述第一请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
其中，步骤802至步骤803用于所述目标VIM将待加速VNF部署至所述目标主机上的步骤，需明确的是，步骤802至步骤803为举例说明，不做限定，还可采用其他部署方式，例如下述步骤804至步骤805所示；
804、所述目标VIM接收虚拟网络功能管理VNFM发送的第二请求消息；
所述VNFM用于接收所述NFVO发送的第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息；
805、所述目标VIM根据所述第二请求消息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
本实施例中，所述目标VIM将硬件加速信息发送给所述NFVO，以使所述NFVO在将待加速VNF部署至所述主机上的过程中，确定目标VIM为与所述目标主机对应的VIM为所述目标VIM，所述目标主机与目标硬件匹配资源的大小对应的主机，所述目标硬件匹配资源所述NFVO的管理域内各所述VIM发送的各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小，使得所述目标主机上的所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致，以使通过本实施例所示的所述硬件加速方法能够使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效的提升了待加速VNF的性能。
以下结合图9说明若所述功能实体为虚拟网络功能管理VNFM时，所述 目标VIM是如何实现所述硬件加速方法的；
用于实现本实施例所示的硬件加速方法的网络功能虚拟化架构的具体结构可参加图5所示，且对图5所示的所述网络功能虚拟化架构的具体说明请参见上述实施例所示，具体在本实施例中不做赘述；
901、所述目标VIM将硬件加速信息发送给所述NFVO；
本实施例中的步骤901具体请参见图8所示的步骤801所示，具体在本实施例中不做赘述。
902、所述目标VIM接收所述VNFM发送的第四请求信息；
所述VNFM用于根据第二指示信息向目标VIM发送第四请求信息，所述VNFM还用于接收所述NFVO所发送的所述第二指示信息，所述第二指示信息用于指示所述目标VIM；
903、所述目标VIM根据所述第四请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
通过本实施例所示的所述硬件加速方法能够使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效的提升了待加速VNF的性能。
以下结合图10所示对能够实现使得VNF所在的主机的加速资源能够满足VNF的加速需求的功能实体的结构进行详细说明：
所述功能实体包括：
第一确定单元1001，用于确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
本实施例所提供的网络功能虚拟化架构的结构请参见图3所示，本实施例对所述功能实体具体实现结构不做限定；
其中，图3所示的所述网络功能虚拟化架构的具体说明请详见上述实施例所示，具体在本实施例中不做赘述。
第二确定单元1002，用于确定目标虚拟基础设施管理器VIM；
所述功能实体确定所述功能实体的管理域内的多个VIM中满足预设条件 的VIM为所述目标VIM，以使目标VIM确定所述目标VIM的管理域内的所述目标主机；
所述预设条件为所述目标VIM的管理域内有所述目标主机；
具体的，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小；
更具体的，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
第一部署单元1003，用于通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
本实施例中，所述功能实体在将待加速VNF部署至所述主机上的过程中，不是按序部署或者是随即部署的，而是所述功能实体将所述待加速VNF部署至硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小的目标主机上，且该目标主机上的所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致，以使通过本实施例所示的所述硬件加速方法能够使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效的提升了待加速VNF的性能。
以下结合图11所示对能够确定目标VIM的一种所述功能实体的结构进行详细说明；
本实施例中，所述网络功能虚拟化架构的具体结构可参加图5所示，且本实施例以所述功能实体为网络功能虚拟化编排器NFVO为例进行说明；
所述功能实体包括：
第一确定单元1101，还用于根据与所述待加速VNF对应的VNF描述符模板中的目标字段确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小。
具体的，如图5所示，所述NFVO通过读取VNF目录中的VNFD模板获 取所述NFVO的管理域内需要硬件加速的待加速VNF中需要的硬件加速资源的类型和大小；
其中，所述NFVO具体如何获取所述NFVO的管理域内需要硬件加速的待加速VNF中需要的硬件加速资源的类型和大小的请详见上述实施例所示，具体在本实施例中不做赘述；
第二确定单元1102，用于确定目标虚拟基础设施管理器VIM；
具体的，所述第二确定单元1102还包括：
第一接收模块11021，用于接收所述NFVO的管理域内各所述VIM发送的硬件加速信息，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小；
第一确定模块11022，用于确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为各所述上报硬件匹配资源的大小中的最大值；
第二确定模块11023，用于确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机；
第三确定模块11024，用于确定与所述目标主机对应的VIM为所述目标VIM；
第一部署单元1103，用于通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致；
具体的，所述第一部署单元1103包括：
第一发送模块11031，用于向所述目标VIM发送第一请求信息，所述第一请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
或，
所述第一部署单元1103包括：
第二发送模块11032，用于向虚拟网络功能管理VNFM发送第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息， 所述第二请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
本实施例中，所述NFVO在将待加速VNF部署至所述主机上的过程中，确定目标VIM为与所述目标主机对应的VIM为所述目标VIM，所述目标主机与目标硬件匹配资源的大小对应的主机，所述目标硬件匹配资源所述NFVO的管理域内各所述VIM发送的各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小，使得所述目标主机上的所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致，以使通过本实施例所示的所述硬件加速方法能够使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效的提升了待加速VNF的性能。
以下结合图12所示对能够确定目标VIM的一种所述功能实体的结构进行详细说明；
本实施例中，所述网络功能虚拟化架构的具体结构可参加图5所示，且本实施例以所述功能实体为虚拟网络功能管理VNFM为例进行说明；
所述功能实体包括：
第一确定单元1201，还用于根据与所述待加速VNF对应的VNF描述符模板中的目标字段确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小。
且所述第一确定单元1201还用于根据与所述待加速VNF对应的VNF描述符模板中的目标字段以确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小；
所述VNFM具体如何读取VNF目录中的VNFD模板获取所述NFVO的管理域内需要硬件加速的待加速VNF中需要的硬件加速资源的类型和大小的请详见上述实施例所示，具体在本实施例中不做赘述。
第一发送单元1202，用于将所述待加速VNF中需要的硬件加速资源的类型和大小发送给所述NFVO；
第二确定单元1203，用于确定目标虚拟基础设施管理器VIM；
所述第二确定单元1203还用于，将第三请求信息发送给所述NFVO，以使所述NFVO根据所述第三请求信息以及所述待加速VNF中需要的硬件加速资源的类型和大小确定所述目标VIM；
第一部署单元1204，用于通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致；
具体的，所述第一部署单元1204包括：
第二接收模块12041，用于接收所述NFVO所发送的第二指示信息，所述第二指示信息用于指示所述目标VIM；
第三发送模块12042，用于根据所述第二指示信息向目标VIM发送第四请求信息，所述第四请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
通过本实施例所示能够使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效的提升了待加速VNF的性能。
以下结合图13所示对能够实现使得VNF所在的主机的加速资源能够满足VNF的加速需求的目标VIM的结构进行详细说明：
其中，能够实现本实施例所示的所述硬件加速方法的网络功能虚拟化架构请参见图3所示，对图3所示的所述网络功能虚拟化架构的具体说明请详见上述实施例所示，具体在本实施例中不做赘述。
所述目标虚拟基础设施管理VIM包括：
第二发送单元1301，用于将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体，以使所述功能实体根据所述目标主机的硬件匹配资源的大小确定所述目标VIM，且所述功能实体还用于确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
第二部署单元1302，用于在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
本实施例中，所述目标VIM将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体，以使所述功能实体能够确定所述目标VIM，所述目标VIM能够在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上，且所述目标VIM在将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上的过程中，不是按序部署或者是随即部署的，而是将所述待加速VNF部署至硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小的目标主机上，且该目标主机上的所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致，以使通过本实施例所示的所述硬件加速方法能够使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效的提升了待加速VNF的性能。
以下结合图14所示说明若所述功能实体为网络功能虚拟化编排器NFVO时，所述目标VIM的具体结构；
用于实现本实施例所示的网络功能虚拟化架构的具体结构可参加图5所示，且对图5所示的所述网络功能虚拟化架构的具体说明请参见上述实施例所示，具体在本实施例中不做赘述；
第二发送单元1401还用于，将硬件加速信息发送给所述NFVO，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为所述目标VIM的管理域内的硬件匹配资源最大的目标主机所具有的硬件匹配资源的大小，以使所述NFVO根据所述硬件加速信息确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为所述NFVO的管理域内各VIM的所述上报硬件匹配资源的大小中的最大值，以使所述NFVO确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机，使得所述NFVO确定与所述 目标主机对应的VIM为所述目标VIM。
第二部署单元1402，用于在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
具体的，所述第二部署单元1402包括：
第三接收模块14021，用于接收所述NFVO发送的第一请求信息；
第一部署模块14022，用于根据所述第一请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
或，
第四接收模块14023，用于接收虚拟网络功能管理VNFM发送的第二请求消息，所述VNFM用于接收所述NFVO发送的第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息；
第二部署模块14024，用于根据所述第二请求消息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
本实施例中，所述目标VIM将硬件加速信息发送给所述NFVO，以使所述NFVO在将待加速VNF部署至所述主机上的过程中，确定目标VIM为与所述目标主机对应的VIM为所述目标VIM，所述目标主机与目标硬件匹配资源的大小对应的主机，所述目标硬件匹配资源所述NFVO的管理域内各所述VIM发送的各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小，使得所述目标主机上的所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致，以使通过本实施例所示的所述硬件加速方法能够使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效的提升了待加速VNF的性能。
以下结合图15所示说明若所述功能实体为虚拟网络功能管理VNFM时，所述目标VIM的具体结构；
所述目标虚拟基础设施管理VIM包括：
第二发送单元1501，用于将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体，以使所述功能实体根据所述目标主机的硬件匹配资源的大小确定所述目标VIM，且所述功能实体还用于确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
第二部署单元1502，用于在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
具体的，所述第二部署单元1502包括：
第五接收模块15021，用于接收所述VNFM发送的第四请求信息，所述VNFM用于根据第二指示信息向目标VIM发送第四请求信息，所述VNFM还用于接收所述NFVO所发送的所述第二指示信息，所述第二指示信息用于指示所述目标VIM；
第三部署模块15022，用于根据所述第四请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
通过本实施例所示能够使得所述待加速VNF的所述需要的硬件加速资源的类型与所述目标主机的硬件匹配资源的类型能够匹配，且所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，进而使得目标主机的硬件匹配资源能够满足所述待加速VNF的加速需求，有效的提升了待加速VNF的性能。
以下从硬件角度对能够实现使得VNF所在的主机的加速资源能够满足VNF的加速需求的功能实体的结构：
如图16所示，所述功能实体包括：发送器1601、接收器1602和处理器1603；
所述处理器1603用于执行如下操作：
确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
确定目标虚拟基础设施管理器VIM；
通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
进一步的，所述功能实体为网络功能虚拟化编排器NFVO，则所述处理器1603还用于执行如下操作：
根据与所述待加速VNF对应的VNF描述符模板中的目标字段确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小。
进一步的，所述接收器1602用于执行如下操作：
接收所述NFVO的管理域内各所述VIM发送的硬件加速信息，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小；
所述处理器1603还用于执行如下操作：
确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为各所述上报硬件匹配资源的大小中的最大值；
确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机；
确定与所述目标主机对应的VIM为所述目标VIM。
进一步的，所述发送器1601用于执行如下操作：
向所述目标VIM发送第一请求信息，所述第一请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
或，
向虚拟网络功能管理VNFM发送第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息，所述第二请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
进一步的，所述功能实体为虚拟网络功能管理VNFM，则所述处理器1603还用于执行如下操作：
根据与所述待加速VNF对应的VNF描述符模板中的目标字段以确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小；
所述发送器1601用于执行如下操作：
将所述待加速VNF中需要的硬件加速资源的类型和大小发送给所述NFVO。
进一步的，所述发送器1601还用于执行如下操作：
将第三请求信息发送给所述NFVO，以使所述NFVO根据所述第三请求信息以及所述待加速VNF中需要的硬件加速资源的类型和大小确定所述目标VIM；
所述接收器1602还用于执行如下操作：
接收所述NFVO所发送的第二指示信息，所述第二指示信息用于指示所述目标VIM；
所述发送器1601还用于执行如下操作：
根据所述第二指示信息向目标VIM发送第四请求信息，所述第四请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
以下从硬件角度对能够实现使得VNF所在的主机的加速资源能够满足VNF的加速需求的目标VIM的结构：
如图17所示，目标虚拟基础设施管理VIM包括：发送器1701、接收器1702和处理器1703；
所述发送器1701用于执行如下操作：
将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体，以使所述功能实体根据所述目标主机的硬件匹配资源的大小确定所述目标VIM，且所述功能实体还用于确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
所述处理器1703用于执行如下操作：
在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所 述需要的硬件加速资源的类型一致。
进一步的，所述功能实体为网络功能虚拟化编排器NFVO，则所述发送器1701还用于执行如下操作：
将硬件加速信息发送给所述NFVO，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为所述目标VIM的管理域内的硬件匹配资源最大的目标主机所具有的硬件匹配资源的大小，以使所述NFVO根据所述硬件加速信息确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为所述NFVO的管理域内各VIM的所述上报硬件匹配资源的大小中的最大值，以使所述NFVO确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机，使得所述NFVO确定与所述目标主机对应的VIM为所述目标VIM。
进一步的，所述接收器1702用于执行如下操作：
接收所述NFVO发送的第一请求信息；
所述处理器1703用于执行如下操作：
根据所述第一请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
或，
所述接收器1702还用于执行如下操作：
接收虚拟网络功能管理VNFM发送的第二请求消息，所述VNFM用于接收所述NFVO发送的第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息；
所述处理器1703还用于执行如下操作：
根据所述第二请求消息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
进一步的，所述功能实体为虚拟网络功能管理VNFM，则所述接收器1702还用于执行如下操作：
接收所述VNFM发送的第四请求信息，所述VNFM用于根据第二指示信息向目标VIM发送第四请求信息，所述VNFM还用于接收所述NFVO所发送的所述第二指示信息，所述第二指示信息用于指示所述目标VIM；
所述处理器1703用于执行如下操作：
根据所述第四请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。

Claims (30)

  1. 一种硬件加速方法，其特征在于，包括：
    功能实体确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
    所述功能实体确定目标虚拟基础设施管理器VIM；
    所述功能实体通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
  2. 根据权利要求1所述的硬件加速方法，其特征在于，所述功能实体为网络功能虚拟化编排器NFVO，则所述功能实体确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小包括：
    所述NFVO根据与所述待加速VNF对应的VNF描述符模板中的目标字段确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小。
  3. 根据权利要求2所述的硬件加速方法，其特征在于，所述功能实体确定目标虚拟基础设施管理器VIM包括：
    所述NFVO接收所述NFVO的管理域内各所述VIM发送的硬件加速信息，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小；
    所述NFVO确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为各所述上报硬件匹配资源的大小中的最大值；
    所述NFVO确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机；
    所述NFVO确定与所述目标主机对应的VIM为所述目标VIM。
  4. 根据权利要求2或3所述的硬件加速方法，其特征在于，所述功能实体通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上包括：
    所述NFVO向所述目标VIM发送第一请求信息，所述第一请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
    或，
    所述NFVO向虚拟网络功能管理VNFM发送第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息，所述第二请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
  5. 根据权利要求1所述的硬件加速方法，其特征在于，所述功能实体为虚拟网络功能管理VNFM，则所述功能实体确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小包括：
    所述VNFM根据与所述待加速VNF对应的VNF描述符模板中的目标字段以确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小；
    所述功能实体确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小之后，所述方法还包括：
    所述VNFM将所述待加速VNF中需要的硬件加速资源的类型和大小发送给所述NFVO。
  6. 根据权利要求5所述的硬件加速方法，其特征在于，所述功能实体确定目标虚拟基础设施管理器VIM包括：
    所述VNFM将第三请求信息发送给所述NFVO，以使所述NFVO根据所述第三请求信息以及所述待加速VNF中需要的硬件加速资源的类型和大小确定所述目标VIM；
    所述功能实体通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上包括：
    所述VNFM接收所述NFVO所发送的第二指示信息，所述第二指示信息用于指示所述目标VIM；
    所述VNFM根据所述第二指示信息向目标VIM发送第四请求信息，所述第四请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM 的管理域内的所述目标主机上。
  7. 一种硬件加速方法，其特征在于，包括：
    目标虚拟基础设施管理VIM将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体，以使所述功能实体根据所述目标主机的硬件匹配资源的大小确定所述目标VIM，且所述功能实体还用于确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
    所述目标VIM在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
  8. 根据权利要求7所述的硬件加速方法，其特征在于，所述功能实体为网络功能虚拟化编排器NFVO，则所述目标虚拟基础设施管理VIM将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体包括：
    所述目标VIM将硬件加速信息发送给所述NFVO，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为所述目标VIM的管理域内的硬件匹配资源最大的目标主机所具有的硬件匹配资源的大小，以使所述NFVO根据所述硬件加速信息确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为所述NFVO的管理域内各VIM的所述上报硬件匹配资源的大小中的最大值，以使所述NFVO确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机，使得所述NFVO确定与所述目标主机对应的VIM为所述目标VIM。
  9. 根据权利要求8所述的硬件加速方法，其特征在于，所述目标VIM在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上包括：
    所述目标VIM接收所述NFVO发送的第一请求信息；
    所述目标VIM根据所述第一请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
    或，
    所述目标VIM接收虚拟网络功能管理VNFM发送的第二请求消息，所述VNFM用于接收所述NFVO发送的第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息；
    所述目标VIM根据所述第二请求消息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
  10. 根据权利要求7所述的硬件加速方法，其特征在于，所述功能实体为虚拟网络功能管理VNFM，则所述目标VIM在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上包括：
    所述目标VIM接收所述VNFM发送的第四请求信息，所述VNFM用于根据第二指示信息向目标VIM发送第四请求信息，所述VNFM还用于接收所述NFVO所发送的所述第二指示信息，所述第二指示信息用于指示所述目标VIM；
    所述目标VIM根据所述第四请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
  11. 一种功能实体，其特征在于，包括：
    第一确定单元，用于确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
    第二确定单元，用于确定目标虚拟基础设施管理器VIM；
    第一部署单元，用于通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
  12. 根据权利要求11所述的功能实体，其特征在于，所述功能实体为网络功能虚拟化编排器NFVO，则所述第一确定单元包括：
    第一确定单元还用于，根据与所述待加速VNF对应的VNF描述符模板中的目标字段确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小。
  13. 根据权利要求12所述的功能实体，其特征在于，所述第二确定单元包括：
    第一接收模块，用于接收所述NFVO的管理域内各所述VIM发送的硬件加速信息，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小；
    第一确定模块，用于确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为各所述上报硬件匹配资源的大小中的最大值；
    第二确定模块，用于确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机；
    第三确定模块，用于确定与所述目标主机对应的VIM为所述目标VIM。
  14. 根据权利要求12或13所述的功能实体，其特征在于，所述第一部署单元包括：
    第一发送模块，用于向所述目标VIM发送第一请求信息，所述第一请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
    或，
    第二发送模块，用于向虚拟网络功能管理VNFM发送第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息，所述第二请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
  15. 根据权利要求11所述的功能实体，其特征在于，所述功能实体为虚拟网络功能管理VNFM，则所述第一确定单元还用于，根据与所述待加速VNF对应的VNF描述符模板中的目标字段以确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小；
    所述功能实体还包括：
    第一发送单元，用于将所述待加速VNF中需要的硬件加速资源的类型和大小发送给所述NFVO。
  16. 根据权利要求15所述的功能实体，其特征在于，所述第二确定还用于，将第三请求信息发送给所述NFVO，以使所述NFVO根据所述第三请求信息以及所述待加速VNF中需要的硬件加速资源的类型和大小确定所述目标 VIM；
    所述第一部署单元包括：
    第二接收模块，用于接收所述NFVO所发送的第二指示信息，所述第二指示信息用于指示所述目标VIM；
    第三发送模块，用于根据所述第二指示信息向目标VIM发送第四请求信息，所述第四请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
  17. 一种目标虚拟基础设施管理VIM，其特征在于，包括：
    第二发送单元，用于将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体，以使所述功能实体根据所述目标主机的硬件匹配资源的大小确定所述目标VIM，且所述功能实体还用于确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
    第二部署单元，用于在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
  18. 根据权利要求17所述的目标VIM，其特征在于，所述功能实体为网络功能虚拟化编排器NFVO，则所述第二发送单元还用于，将硬件加速信息发送给所述NFVO，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为所述目标VIM的管理域内的硬件匹配资源最大的目标主机所具有的硬件匹配资源的大小，以使所述NFVO根据所述硬件加速信息确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为所述NFVO的管理域内各VIM的所述上报硬件匹配资源的大小中的最大值，以使所述NFVO确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机，使得所述NFVO确定与所述目标主机对应的VIM为所述目标VIM。
  19. 根据权利要求18所述的目标VIM，其特征在于，所述第二部署单元包括：
    第三接收模块，用于接收所述NFVO发送的第一请求信息；
    第一部署模块，用于根据所述第一请求信息将所述待加速VNF部署至所 述目标VIM的管理域内的所述目标主机上；
    或，
    第四接收模块，用于接收虚拟网络功能管理VNFM发送的第二请求消息，所述VNFM用于接收所述NFVO发送的第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息；
    第二部署模块，用于根据所述第二请求消息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
  20. 根据权利要求17所述的目标VIM，其特征在于，所述功能实体为虚拟网络功能管理VNFM，则所述第二部署单元包括：
    第五接收模块，用于接收所述VNFM发送的第四请求信息，所述VNFM用于根据第二指示信息向目标VIM发送第四请求信息，所述VNFM还用于接收所述NFVO所发送的所述第二指示信息，所述第二指示信息用于指示所述目标VIM；
    第三部署模块，用于根据所述第四请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
  21. 一种功能实体，其特征在于，包括：发送器、接收器和处理器；
    所述处理器用于执行如下操作：
    确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
    确定目标虚拟基础设施管理器VIM；
    通过所述目标VIM将所述待加速VNF部署至所述目标VIM管理域内的目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
  22. 根据权利要求21所述的功能实体，其特征在于，所述功能实体为网络功能虚拟化编排器NFVO，则所述处理器还用于执行如下操作：
    根据与所述待加速VNF对应的VNF描述符模板中的目标字段确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小。
  23. 根据权利要求22所述的功能实体，其特征在于，所述接收器用于执 行如下操作：
    接收所述NFVO的管理域内各所述VIM发送的硬件加速信息，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为各所述VIM的管理域内的硬件匹配资源最大的主机所具有的硬件匹配资源的大小；
    所述处理器还用于执行如下操作：
    确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为各所述上报硬件匹配资源的大小中的最大值；
    确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机；
    确定与所述目标主机对应的VIM为所述目标VIM。
  24. 根据权利要求22或23所述的功能实体，其特征在于，所述发送器用于执行如下操作：
    向所述目标VIM发送第一请求信息，所述第一请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
    或，
    向虚拟网络功能管理VNFM发送第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息，所述第二请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
  25. 根据权利要求21所述的功能实体，其特征在于，所述功能实体为虚拟网络功能管理VNFM，则所述处理器还用于执行如下操作：
    根据与所述待加速VNF对应的VNF描述符模板中的目标字段以确定所述NFVO的管理域内所述待加速VNF中需要的硬件加速资源的类型和大小；
    所述发送器用于执行如下操作：
    将所述待加速VNF中需要的硬件加速资源的类型和大小发送给所述NFVO。
  26. 根据权利要求25所述的功能实体，其特征在于，所述发送器还用于执行如下操作：
    将第三请求信息发送给所述NFVO，以使所述NFVO根据所述第三请求信息以及所述待加速VNF中需要的硬件加速资源的类型和大小确定所述目标VIM；
    所述接收器还用于执行如下操作：
    接收所述NFVO所发送的第二指示信息，所述第二指示信息用于指示所述目标VIM；
    所述发送器还用于执行如下操作：
    根据所述第二指示信息向目标VIM发送第四请求信息，所述第四请求信息用于使得所述目标VIM将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
  27. 一种目标虚拟基础设施管理VIM，其特征在于，包括：发送器、接收器和处理器；
    所述发送器用于执行如下操作：
    将所述目标VIM的管理域内的目标主机的硬件匹配资源的大小发送给功能实体，以使所述功能实体根据所述目标主机的硬件匹配资源的大小确定所述目标VIM，且所述功能实体还用于确定所述功能实体的管理域内待加速虚拟化网元VNF中需要的硬件加速资源的类型和大小；
    所述处理器用于执行如下操作：
    在所述功能实体的控制下将所述待加速VNF部署至所述目标VIM管理域内的所述目标主机上，其中，所述目标主机的硬件匹配资源的大小大于所述待加速VNF中所述需要的硬件加速资源的大小，所述硬件匹配资源的类型与所述需要的硬件加速资源的类型一致。
  28. 根据权利要求27所述的目标VIM，其特征在于，所述功能实体为网络功能虚拟化编排器NFVO，则所述发送器还用于执行如下操作：
    将硬件加速信息发送给所述NFVO，所述硬件加速信息中包括上报硬件匹配资源的大小，所述上报硬件匹配资源的大小为所述目标VIM的管理域内的硬件匹配资源最大的目标主机所具有的硬件匹配资源的大小，以使所述NFVO根据所述硬件加速信息确定目标硬件匹配资源的大小，所述目标硬件匹配资源的大小为所述NFVO的管理域内各VIM的所述上报硬件匹配资源的大小中的 最大值，以使所述NFVO确定与所述目标硬件匹配资源的大小对应的主机为所述目标主机，使得所述NFVO确定与所述目标主机对应的VIM为所述目标VIM。
  29. 根据权利要求28所述的目标VIM，其特征在于，所述接收器用于执行如下操作：
    接收所述NFVO发送的第一请求信息；
    所述处理器用于执行如下操作：
    根据所述第一请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上；
    或，
    所述接收器还用于执行如下操作：
    接收虚拟网络功能管理VNFM发送的第二请求消息，所述VNFM用于接收所述NFVO发送的第一指示信息，所述第一指示信息用于使所述VNFM向所述目标VIM发送第二请求消息；
    所述处理器还用于执行如下操作：
    根据所述第二请求消息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
  30. 根据权利要求27所述的目标VIM，其特征在于，所述功能实体为虚拟网络功能管理VNFM，则所述接收器还用于执行如下操作：
    接收所述VNFM发送的第四请求信息，所述VNFM用于根据第二指示信息向目标VIM发送第四请求信息，所述VNFM还用于接收所述NFVO所发送的所述第二指示信息，所述第二指示信息用于指示所述目标VIM；
    所述处理器用于执行如下操作：
    根据所述第四请求信息将所述待加速VNF部署至所述目标VIM的管理域内的所述目标主机上。
PCT/CN2015/079274 2015-05-19 2015-05-19 一种硬件加速方法以及相关设备 WO2016183799A1 (zh)

Priority Applications (12)

Application Number Priority Date Filing Date Title
CN201580000939.0A CN106663012B (zh) 2015-05-19 2015-05-19 一种硬件加速方法以及相关设备
RU2017144205A RU2687711C1 (ru) 2015-05-19 2015-05-19 Способ аппаратного ускорения и связанное устройство
CN202010529799.9A CN111831392A (zh) 2015-05-19 2015-05-19 一种硬件加速方法以及相关设备
JP2017560311A JP6568238B2 (ja) 2015-05-19 2015-05-19 ハードウェアアクセラレーション方法及び関連デバイス
EP15892178.3A EP3287897B1 (en) 2015-05-19 2015-05-19 Hardware acceleration method and relevant device
EP24177552.7A EP4462251A1 (en) 2015-05-19 2015-05-19 Hardware acceleration method and related device
BR112017024661-9A BR112017024661B1 (pt) 2015-05-19 Método de aceleração de hardware, dispositivo e sistema relacionado
PCT/CN2015/079274 WO2016183799A1 (zh) 2015-05-19 2015-05-19 一种硬件加速方法以及相关设备
KR1020177036054A KR102022441B1 (ko) 2015-05-19 2015-05-19 하드웨어 가속 방법 및 관련 장치
US15/817,264 US10620986B2 (en) 2015-05-19 2017-11-19 Hardware acceleration method and related device
US16/829,871 US11068298B2 (en) 2015-05-19 2020-03-25 Hardware acceleration method and related device
US17/379,539 US11544100B2 (en) 2015-05-19 2021-07-19 Hardware acceleration method and related device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2015/079274 WO2016183799A1 (zh) 2015-05-19 2015-05-19 一种硬件加速方法以及相关设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/817,264 Continuation US10620986B2 (en) 2015-05-19 2017-11-19 Hardware acceleration method and related device

Publications (1)

Publication Number Publication Date
WO2016183799A1 true WO2016183799A1 (zh) 2016-11-24

Family

ID=57319164

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/079274 WO2016183799A1 (zh) 2015-05-19 2015-05-19 一种硬件加速方法以及相关设备

Country Status (7)

Country Link
US (3) US10620986B2 (zh)
EP (2) EP4462251A1 (zh)
JP (1) JP6568238B2 (zh)
KR (1) KR102022441B1 (zh)
CN (2) CN111831392A (zh)
RU (1) RU2687711C1 (zh)
WO (1) WO2016183799A1 (zh)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10545779B2 (en) * 2015-01-23 2020-01-28 Nec Corporation Network functions virtualization management and orchestration method, network functions virtualization management and orchestration system, and program
US11050623B2 (en) * 2015-10-30 2021-06-29 Hewlett Packard Enterprise Development Lp Managing virtual network functions
EP3639474B1 (en) * 2017-06-16 2022-08-31 Telefonaktiebolaget LM Ericsson (publ) Derivation of network service descriptor from network service requirements
EP3735765A4 (en) * 2018-06-01 2021-01-13 Huawei Technologies Co., Ltd. CLUSTER WITH MULTI-SERVER ARCHITECTURE TO ENSURE VIRTUAL NETWORK FUNCTION
JP7077895B2 (ja) * 2018-09-21 2022-05-31 トヨタ自動車株式会社 運転評価装置、運転評価システム、運転評価方法、及び運転評価用コンピュータプログラム
CN109976876B (zh) * 2019-03-20 2021-11-16 联想(北京)有限公司 加速器管理方法和装置
CN110445886B (zh) * 2019-07-05 2020-11-06 网宿科技股份有限公司 一种实现域名访问加速的方法和系统
US11687355B1 (en) * 2020-03-26 2023-06-27 Cisco Technology, Inc. Methods to extract cloud infrastructure requirements from virtualized applications and autodeploy
US11863450B1 (en) 2022-12-08 2024-01-02 Cisco Technology, Inc. Method using network controller to deploy virtual environment in production network
FR3145630A1 (fr) * 2023-02-06 2024-08-09 Orange Procédé de détermination d’un groupe de serveurs

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102685162A (zh) * 2011-03-11 2012-09-19 中国电信股份有限公司 云计算加速方法和系统
US20130347009A1 (en) * 2012-06-22 2013-12-26 Microsoft Corporation API Redirection for Limited Capability Operating Systems
CN103699577A (zh) * 2013-11-29 2014-04-02 小米科技有限责任公司 一种页面显示加速方法、装置及移动终端
WO2015026373A1 (en) * 2013-08-23 2015-02-26 Empire Technology Development, Llc Detacenter-based hardware accelerator integration
CN104699508A (zh) * 2015-03-25 2015-06-10 南京大学 云计算平台中快速部署和更新虚拟环境系统及其方法

Family Cites Families (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002055892A (ja) * 2000-08-09 2002-02-20 Nippon Telegr & Teleph Corp <Ntt> ネットワーク管理方法及び仮想ネットワーク機器システム
US8274518B2 (en) 2004-12-30 2012-09-25 Microsoft Corporation Systems and methods for virtualizing graphics subsystems
RU91204U1 (ru) * 2009-10-01 2010-01-27 ЗАО "Лаборатория Касперского" Система определения новых версий программ
EP2606448B1 (en) 2010-08-18 2016-02-10 Security First Corp. Systems and methods for securing virtual machine computing environments
US9098326B1 (en) * 2011-11-09 2015-08-04 BigML, Inc. Evolving parallel system to automatically improve the performance of multiple concurrent tasks on large datasets
US9223604B2 (en) 2011-12-08 2015-12-29 Hitachi, Ltd. Control method of virtual machine and virtual machine system
EP2936754B1 (en) * 2013-01-11 2020-12-02 Huawei Technologies Co., Ltd. Network function virtualization for a network device
US9973375B2 (en) * 2013-04-22 2018-05-15 Cisco Technology, Inc. App store portal providing point-and-click deployment of third-party virtualized network functions
EP2849064B1 (en) * 2013-09-13 2016-12-14 NTT DOCOMO, Inc. Method and apparatus for network virtualization
CN105122738B (zh) * 2014-03-26 2018-06-15 华为技术有限公司 基于网络功能虚拟化的证书配置方法、装置和系统
US10698569B2 (en) * 2014-04-03 2020-06-30 Centurylink Intellectual Property Llc System and method for implementing customer control point or customer portal
US10616377B2 (en) * 2014-04-03 2020-04-07 Centurylink Intellectual Property Llc System and method for implementing network enhanced gateway functionality
EP2940968A1 (en) * 2014-04-30 2015-11-04 Hewlett-Packard Development Company, L.P. Network infrastructure management
US10348825B2 (en) * 2014-05-07 2019-07-09 Verizon Patent And Licensing Inc. Network platform-as-a-service for creating and inserting virtual network functions into a service provider network
US9672502B2 (en) * 2014-05-07 2017-06-06 Verizon Patent And Licensing Inc. Network-as-a-service product director
EP3158686B1 (en) * 2014-06-26 2020-01-08 Huawei Technologies Co., Ltd. System and method for virtual network function policy management
CN104050045B (zh) * 2014-06-27 2017-06-27 华为技术有限公司 基于磁盘io的虚拟资源分配方法及装置
EP3855681A1 (en) * 2014-09-25 2021-07-28 Apple Inc. Network functions virtualization
CN104410672B (zh) * 2014-11-12 2017-11-24 华为技术有限公司 网络功能虚拟化应用升级的方法、转发业务的方法及装置
EP3257212A1 (en) * 2015-02-13 2017-12-20 Nokia Solutions and Networks Oy Security mechanism for hybrid networks
WO2016146878A1 (en) * 2015-03-13 2016-09-22 Comptel Corporation Network management
JPWO2017170937A1 (ja) * 2016-04-01 2019-02-21 株式会社Ｎｔｔドコモ スライス変更方法及びスライス変更装置
EP3456001A4 (en) * 2016-05-10 2020-01-01 Nokia Solutions and Networks Oy METHOD AND APPARATUS FOR COORDINATED SCHEDULING OF NETWORK FUNCTION VIRTUALIZATION INFRASTRUCTURE MAINTENANCE
CN111262715B (zh) * 2018-11-30 2021-04-02 贵州白山云科技股份有限公司 一种虚拟内网加速方法、系统和计算机设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102685162A (zh) * 2011-03-11 2012-09-19 中国电信股份有限公司 云计算加速方法和系统
US20130347009A1 (en) * 2012-06-22 2013-12-26 Microsoft Corporation API Redirection for Limited Capability Operating Systems
WO2015026373A1 (en) * 2013-08-23 2015-02-26 Empire Technology Development, Llc Detacenter-based hardware accelerator integration
CN103699577A (zh) * 2013-11-29 2014-04-02 小米科技有限责任公司 一种页面显示加速方法、装置及移动终端
CN104699508A (zh) * 2015-03-25 2015-06-10 南京大学 云计算平台中快速部署和更新虚拟环境系统及其方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3287897A4 *

Also Published As

Publication number Publication date
RU2687711C1 (ru) 2019-05-15
JP2018521389A (ja) 2018-08-02
BR112017024661A2 (zh) 2018-07-24
EP3287897A1 (en) 2018-02-28
CN106663012A (zh) 2017-05-10
JP6568238B2 (ja) 2019-08-28
EP3287897B1 (en) 2024-07-03
CN111831392A (zh) 2020-10-27
KR20180006971A (ko) 2018-01-19
US20220012082A1 (en) 2022-01-13
EP4462251A1 (en) 2024-11-13
US10620986B2 (en) 2020-04-14
CN106663012B (zh) 2020-07-07
US20180121227A1 (en) 2018-05-03
KR102022441B1 (ko) 2019-09-18
EP3287897A4 (en) 2018-05-16
US11068298B2 (en) 2021-07-20
US11544100B2 (en) 2023-01-03
US20200225976A1 (en) 2020-07-16

Similar Documents

Publication Publication Date Title
WO2016183799A1 (zh) 一种硬件加速方法以及相关设备
US11429408B2 (en) System and method for network function virtualization resource management
US9780998B2 (en) Method and apparatus for managing physical network interface card, and physical host
US10701139B2 (en) Life cycle management method and apparatus
AU2015419073B2 (en) Life cycle management method and device for network service
WO2018024059A1 (zh) 一种虚拟化网络中业务部署的方法和装置
US11301303B2 (en) Resource pool processing to determine to create new virtual resource pools and storage devices based on currebt pools and devices not meeting SLA requirements
WO2015196931A1 (zh) 基于磁盘io的虚拟资源分配方法及装置
WO2018006676A1 (zh) 加速资源处理方法、装置及网络功能虚拟化系统
WO2018149272A1 (zh) 基于sla的资源分配方法和nfvo
US10924966B2 (en) Management method, management unit, and system
EP3358790A1 (en) Network function virtualization resource processing method and virtualized network function manager
US10911315B2 (en) Inter-connecting local control planes for state data exchange
WO2018014351A1 (zh) 一种资源配置方法及装置
WO2018099301A1 (zh) 一种数据分析方法及装置
WO2016090608A1 (zh) 确定虚拟机资源的方法、装置及程序产品
BR112017024661B1 (pt) Método de aceleração de hardware, dispositivo e sistema relacionado

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15892178

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2017560311

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2015892178

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 20177036054

Country of ref document: KR

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2017144205

Country of ref document: RU

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112017024661

Country of ref document: BR

ENP Entry into the national phase

Ref document number: 112017024661

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20171117