WO2017100981A1 - 一种处理业务的方法及系统 - Google Patents

一种处理业务的方法及系统 Download PDF

Info

Publication number
WO2017100981A1
WO2017100981A1 PCT/CN2015/097290 CN2015097290W WO2017100981A1 WO 2017100981 A1 WO2017100981 A1 WO 2017100981A1 CN 2015097290 W CN2015097290 W CN 2015097290W WO 2017100981 A1 WO2017100981 A1 WO 2017100981A1
Authority
WO
WIPO (PCT)
Prior art keywords
hardware
virtual machine
hardware acceleration
network element
supporting
Prior art date
Application number
PCT/CN2015/097290
Other languages
English (en)
French (fr)
Inventor
胡翔
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
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to PCT/CN2015/097290 priority Critical patent/WO2017100981A1/zh
Publication of WO2017100981A1 publication Critical patent/WO2017100981A1/zh

Links

Images

Classifications

    • 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
    • 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
    • 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
    • H04L41/34—Signalling channels for network management communication
    • H04L41/342—Signalling channels for network management communication between virtual entities, e.g. orchestrators, 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
    • H04L41/5054—Automatic deployment of services triggered by the service manager, e.g. service implementation by automatic configuration of network components
    • 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
    • H04L41/508—Network service management, e.g. ensuring proper service fulfilment according to agreements based on type of value added network service under agreement
    • H04L41/5096—Network service management, e.g. ensuring proper service fulfilment according to agreements based on type of value added network service under agreement wherein the managed service relates to distributed or central networked applications

Definitions

  • the present invention relates to the field of computers, and in particular, to a method and system for processing a service.
  • resources include: virtualized processor resources, virtualized memory resources, virtualized hard disk resources, and so on.
  • a virtual network element has a large number of virtualized resources.
  • the virtual network element When a virtual network element is facing a service that needs to perform hardware acceleration processing, the virtual network element requires a large number of virtualized resources to be configured for the general virtual machine. Therefore, the virtual network element needs to perform hardware acceleration processing by running a general virtual machine pair. During the processing of the service, a large amount of virtualized resources are consumed, resulting in a serious degradation of the performance of the virtual network element.
  • the embodiment of the invention provides a method and a system for processing a service, which are used to solve the problem that a virtual network element consumes a large amount of virtual power in a process of processing a service requiring hardware acceleration processing by running a general virtual machine in the prior art.
  • a first aspect of the embodiments of the present invention provides a method for processing a service, where the method includes:
  • the virtual network element determines that the to-be-processed service is a service that needs to perform hardware acceleration processing
  • the virtual network element sends a virtual machine allocation request to the cloud operating system, where the virtual machine allocation request carries a virtual machine VM template supporting the hardware acceleration function and a number of virtual machines supporting the hardware acceleration function, and the VM supporting the hardware acceleration function Template contains an indication of virtualized hardware accelerator resources information;
  • the cloud operating system allocates the number of the virtual machines supporting the hardware acceleration function, and drives the virtualized hardware accelerator resources configured for the virtual machine supporting the hardware acceleration function;
  • the virtual network element performs hardware acceleration processing on the to-be-processed service by running the virtual machine supporting the hardware acceleration function.
  • the cloud operating system allocates a virtual machine that supports the hardware acceleration function to the virtual network element. Therefore, the virtual network element performs hardware acceleration processing on the hardware that needs to perform hardware acceleration processing by running a virtual machine that supports the hardware acceleration function, and is a virtual device that supports the hardware acceleration function.
  • the virtualized hardware accelerator resources configured by the machine can replace a large number of virtualized resources occupied by the general virtual machine. Therefore, all the virtualized resources occupied by the virtual network element are consumed by a single service (that is, a service requiring hardware acceleration processing).
  • the virtualized resources are reduced, and a large number of remaining virtualized resources are consumed by other services, which improves the performance of the virtual network element, and prevents the virtual network element from processing the services that need to be hardware accelerated processing through the general virtual machine, thereby avoiding the The performance of virtual network elements is seriously degraded.
  • the method before the sending, by the virtual network element, a virtual machine allocation request to the cloud operating system, the method further includes:
  • the management and orchestration MANO module sends a virtual network function description VNFD template to the virtual network element, where the VNFD template includes at least one virtual machine VM template and service processing capability of the virtual network element;
  • the virtual network element Determining, by the virtual network element, the VM template supporting the hardware acceleration function from the at least one VM template; the virtual network element determining a service processing capability of the virtual machine supporting the hardware acceleration function, the supporting hardware
  • the virtual machine of the acceleration function is configured according to the VM template supporting the hardware acceleration function;
  • the virtual network element determines the number of the virtual machines supporting the hardware acceleration function according to the service processing capability of the virtual machine supporting the hardware acceleration function and the service processing capability of the virtual network element.
  • the VNFD template stored in the MANO module includes a VM template that supports the hardware acceleration function, so that the virtual network element uses the VM that supports the hardware acceleration function.
  • Template to apply for support hardware to the cloud operating system A virtual machine that accelerates functionality.
  • the cloud operating system allocates the supported hardware acceleration function that meets the quantity Before the virtual machine, it also includes:
  • the cloud operating system After receiving the virtual machine allocation request, the cloud operating system sends a resource allocation request to the hardware accelerator resource management module, where the resource allocation request is used to request a virtualized hardware accelerator resource;
  • the hardware accelerator resource management module allocates a virtualized hardware accelerator resource
  • the cloud operating system allocates the number of the virtual machines supporting the hardware acceleration function, including:
  • the cloud operating system utilizes the allocated virtualized hardware accelerator resources to allocate the virtual machines that meet the number of the supported hardware acceleration functions.
  • a hardware accelerator resource management module for managing hardware accelerator resources in the virtualized network a hardware accelerator resource management module and cloud operation are proposed.
  • the system cooperates to realize the allocation of virtual machines that support hardware acceleration.
  • the cloud operating system drives a virtualized hardware accelerator configured for the virtual machine supporting the hardware acceleration function Resources, including:
  • the cloud operating system After completing the allocation of the virtual machine supporting the hardware acceleration function, the cloud operating system sends a resource driving request to the hardware accelerator resource driving module, where the resource driving request is used to request to drive the allocated virtualization.
  • Hardware accelerator resources ;
  • the hardware accelerator resource driver module drives the allocated virtualized hardware accelerator resources.
  • a hardware accelerator resource driving module for driving hardware accelerator resources in the virtualized network a hardware accelerator resource driving module and a cloud operation are proposed. System cooperation, to achieve the driver support hardware plus Speed function virtual machine.
  • the method further includes:
  • the cloud operating system is configured to invoke an application interface API of the virtualized hardware accelerator resource
  • the virtual network element performs hardware acceleration processing on the to-be-processed service by running the virtual machine that supports the hardware acceleration function, including:
  • the virtual network element invokes, by using the API, a virtualized hardware accelerator resource configured for the virtual machine supporting the hardware acceleration function, and performs hardware acceleration processing on the processed service by the invoked virtualized hardware accelerator resource.
  • an API for interacting between the virtual network element and the virtualized hardware accelerator resource is proposed, so that the virtual network element is accelerated by running the support hardware.
  • a functional virtual machine performs hardware accelerated processing on services that require hardware acceleration processing.
  • a second aspect of the embodiments of the present invention provides a system for processing a service, where the system for processing a service includes:
  • the virtual network element and the cloud operating system cooperate with each other to perform the method for processing a service according to the first aspect.
  • system for the service processing further includes:
  • the MANO module being respectively connected to the virtual network element and the cloud operating system;
  • the MANO module cooperates with the cloud operating system to perform the method for processing a service according to the first aspect.
  • the system for processing a service further includes: a hardware accelerator resource management module Block, connected to the cloud operating system;
  • the cloud operating system cooperates with the hardware accelerator resource management module to execute the method for processing a service according to the first aspect.
  • the system for processing a service further includes: a hardware accelerator resource driving module, connected to the cloud operating system;
  • the cloud operating system cooperates with the hardware accelerator resource driving module to execute the method for processing a service according to the first aspect.
  • a third aspect of the embodiments of the present invention provides a method for allocating resources, which is applied to a cloud operating system, where the method includes:
  • the cloud operating system receives a virtual machine allocation request sent by a virtual network element, where the virtual machine allocation request carries a VM template supporting a hardware acceleration function and a number of virtual machines supporting a hardware acceleration function, and the VM template supporting the hardware acceleration function An indication of the virtualized hardware accelerator resource that contains the virtual machine configuration;
  • the cloud operating system allocates the number of the virtual machines supporting the hardware acceleration function and drives the virtualized hardware accelerator resources configured for the virtual machine supporting the hardware acceleration function.
  • the method before the cloud operating system allocates the virtual machine that supports the hardware acceleration function, the method further includes:
  • the cloud operating system After receiving the virtual machine allocation request, the cloud operating system sends a resource allocation request to the hardware accelerator resource management module, where the resource allocation request is used to request a virtualized hardware accelerator resource;
  • the cloud operating system utilizes the allocated virtualized hardware accelerator resources to allocate the virtual machines that meet the number of the supported hardware acceleration functions.
  • the cloud operating system configured for the virtual machine supporting the hardware acceleration function, including:
  • the cloud operating system After completing the allocation of the virtual machine supporting the hardware acceleration function, the cloud operating system sends a resource driving request to the hardware accelerator resource driving module, where the resource driving request is used to request to drive the allocated virtualization.
  • Hardware accelerator resources ;
  • the cloud operating system receives a second notification message sent by the hardware accelerator resource driving module, and the second notification message indicates that the hardware accelerator resource driving module completes driving the allocated virtualized hardware accelerator resource.
  • the method further includes:
  • the cloud operating system is configured to invoke an application interface API of the virtualized hardware accelerator resource, where the API is used by the virtual network element to invoke a virtualized hardware accelerator resource configured for the virtual machine supporting the hardware acceleration function And hardware accelerated processing of the processing service by the invoked virtualized hardware accelerator resource.
  • a fourth aspect of the embodiments of the present invention provides a cloud operating system, where the cloud operating system includes: a receiving interface, a processor; and the cloud operating system is configured to perform the method for allocating resources according to the third aspect.
  • a fifth aspect of the embodiments of the present invention provides a method for processing a service, where the method is applied to a virtual network element, where the method includes:
  • the to-be-processed service is a service that needs to perform hardware acceleration processing
  • the virtual network element sends a virtual machine allocation request to the cloud operating system, where the virtual machine allocation request carries a VM template supporting the hardware acceleration function and a number of virtual machines supporting the hardware acceleration function, where the VM template supporting the hardware acceleration function includes An indication of the virtualized hardware accelerator resource;
  • the virtual network element performs hardware acceleration processing on the to-be-processed service by running the virtual machine supporting the hardware acceleration function.
  • the method before the sending, by the virtual network element, a virtual machine allocation request to the cloud operating system, the method further includes:
  • the virtual network element receives and manages a virtual network function description VNFD template sent by the MANO module, where the VNFD template includes at least one virtual machine VM template and a service processing capability of the virtual network element;
  • the virtual network element determines the number of the virtual machines supporting the hardware acceleration function according to the service processing capability of the virtual machine supporting the hardware acceleration function and the service processing capability of the virtual network element.
  • the virtual network element is configured by running the virtual machine that supports the hardware acceleration function
  • the hardware to be processed is hardware accelerated, including:
  • the virtual network element invokes a virtualized hardware accelerator resource configured for the virtual machine supporting the hardware acceleration function through an application program interface API, and performs hardware acceleration processing on the processed service by the invoked virtualized hardware accelerator resource.
  • the API is an interface for calling virtualized hardware accelerator resources.
  • a sixth aspect of the embodiments of the present invention provides a virtual network element, where the virtual network element includes:
  • the virtual network element is configured to perform the method for processing a service according to the fifth aspect.
  • the cloud operating system allocates a virtual machine that supports the hardware acceleration function to the virtual network element. Therefore, the virtual network element performs hardware acceleration on the service that needs to perform hardware acceleration processing by running a virtual machine that supports the hardware acceleration function. Processing, for virtual machines that support hardware acceleration
  • the configured virtualized hardware accelerator resources can replace a large number of virtualized resources occupied by the general virtual machine. Therefore, all the virtualized resources occupied by the virtual network element are consumed by a single service (that is, a service that needs to be subjected to hardware acceleration processing).
  • the resources are reduced, and a large number of remaining virtualized resources are consumed by other services, which improves the performance of the virtual network element, and prevents the virtual network element from processing the service that needs to be accelerated by the hardware through the general virtual machine, thereby avoiding the virtual The performance of the network element is seriously degraded.
  • FIG. 1 is a schematic diagram of a system for processing a service according to an embodiment of the present invention
  • FIG. 2 is a flowchart of a method for processing a service performed by a system for processing a service according to an embodiment of the present invention
  • FIG. 3 is a flowchart of a method for allocating resources according to an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a cloud operating system according to an embodiment of the present invention.
  • FIG. 5 is a flowchart of a method for processing a service performed by a virtual network element according to an embodiment of the present invention
  • FIG. 6 is a schematic diagram of a virtual network element according to an embodiment of the present invention.
  • FIG. 1 is a schematic diagram of a system for processing a service according to an embodiment of the present invention.
  • the system includes: virtual network element, MANO (Chinese: Management and Orchestration) module and cloud operating system.
  • MANO Management and Orchestration
  • the virtual network element may be a virtualized gateway device, for example, vUGW (Chinese: virtual unified gateway; English: Virtual Unified Gateway), and vUGW can be used as TD-SCDMA (medium) Text: Time Division Synchronous Code Division Multiple Access; English: Time Division-Synchronous Code Division Multiple Access), UMTS (Chinese: Universal Mobile Telecommunications System; English: Universal Mobile Telecommunications System), LTE (Chinese: Long Term Evolution; English: Long Term Evolution In addition to the gateway device of the mobile core network in the field, it can also be used as the PDSN in the field of CDMA2000 (Code Division Multiple Access 2000), Wimax (Chinese: Worldwide Interoperability for Microwave Access) (Chinese: Packet Data) Service node; English: Packet Data Serving Node) device or ePDG (Chinese: Evolved Packet Data Gateway; English: evoloved Packet Data GateWay) and other mobile core network gateway devices.
  • the vUGW may be a GGSN (Chinese: Gateway GPRS Support Node; English: Gateway GPRS Support Node) defined in the 3GPP (Chinese: 3rd Generation Partnership Project) standard, SGW (Chinese: Service Gateway; English: Serving GateWay), PGW (Chinese: PDN Gateway; English: PDN GateWay).
  • GGSN Gateway GPRS Support Node
  • SGW Service Gateway
  • PGW Choinese: PDN Gateway; English: PDN GateWay
  • the virtual network element may also be a network element that supports some services that need to perform hardware acceleration processing.
  • the services that need to perform hardware acceleration processing may be: comprehensive scanning of the packet, IPSec (Chinese: Internet Protocol Security; English: Internet Protocol Security), video codec, video transcoding, picture and text compression, TCP Proxy protocol stack, etc.
  • the full scan of the packet can be called DPI (Chinese: Deep Packet Inspection; English: Deep Packet Inspection), also known as SA (Chinese: Service Awareness; English: Service Awareness).
  • the prior art has applied processor resources, memory resources, hard disk resources, and the like to an environment of virtualization and cloudization.
  • a processor resource management module, a memory resource management module, and a hard disk resource management module are respectively deployed to manage virtualized processor resources, virtualized memory resources, and virtualized hard disks in the virtualized network.
  • Resources In addition, a processor resource driver module, a memory resource driver module, and a hard disk resource driver module are respectively deployed to drive virtualized processor resources, virtualized memory resources, and virtualized hard disk resources configured for a common virtual machine. .
  • Cloud OS and processor resource management module, memory resource management module, The hard disk resource management module is connected, and the virtualized processor resources, the virtualized memory resources, and the virtualized hard disk resources in the virtualized network are virtualized by the cloud operating system for processor resources, memory resources, and hard disk resources.
  • the processor resource, the memory resource, and the hard disk resource may be provided by a dedicated processor resource server, a memory resource server, and a hard disk resource server, or may be provided by each virtual network element in the virtualized network, and the virtualized network
  • Each of the virtual network elements is configured with a processor resource, a memory resource, and a hard disk resource.
  • Virtualized processor resources, virtualized memory resources, and virtualized hard disk resources in the virtualized network are shared by virtual virtual network elements in the virtualized network.
  • the virtual network element applies for a general-purpose virtual machine to the cloud operating system.
  • the virtualized resources configured for the general-purpose virtual machine include: virtualized processor resources, virtualized memory resources, and virtual
  • the virtual disk element implements a portion of the virtualized processor resources, partially virtualized memory resources, and partially virtualized hard disk resources in the virtualized network.
  • a virtual network element faces a service that needs to perform hardware acceleration processing
  • a general-purpose virtual machine running on a virtual network element occupies a large number of virtualized resources in the virtualized network, resulting in a serious decline in the performance of the virtual network element, mainly Because: a large number of virtualized resources in all the virtualized resources occupied by the virtual network element are consumed by a single service (that is, a service that needs to be accelerated by hardware), and only a small amount or even no virtualized resources are consumed by other services. Therefore, the embodiment of the present invention proposes to apply hardware accelerator resources to the environment of virtualization and cloudization.
  • a hardware accelerator resource is required in a virtualized network, which is similar to a processor resource, a memory resource, and a hard disk resource.
  • the hardware accelerator resource in the virtualized network may be provided by a dedicated hardware accelerator resource server.
  • the virtual network element in the virtualized network is configured with a hardware accelerator resource.
  • the hardware accelerator resource management module and the hardware accelerator resource driving module shown in FIG. 1 are added, and the hardware accelerator resource management module is used to manage virtualization in the virtualized network.
  • Hardware Accelerator Resources, Hardware Accelerator Resource Driver Modules are used to drive virtualized hardware accelerator resources configured for virtual machines that support hardware acceleration.
  • the cloud operating system is connected with the hardware accelerator resource management module, and the virtualized hardware accelerator resource in the virtualized network is the cloud operating system virtualizing the hardware accelerator resource. After the treatment.
  • the virtualized hardware accelerator resource can replace a large number of virtualized resources occupied by the general virtual machine, and therefore, all the virtualized resources occupied by the virtual network element are A single service (that is, a service that needs to perform hardware acceleration processing) consumes less virtualized resources, and a large number of remaining virtualized resources are consumed by other services, thereby improving the performance of the virtual network element.
  • virtualized hardware accelerator resources are shared by virtual virtual network elements in the virtualized network.
  • the virtual network element applies to the cloud operating system for a virtual machine that supports the hardware acceleration function, and the virtualized resource configured for the virtual machine supporting the hardware acceleration function includes virtualization processing.
  • the virtual network element implements hardware accelerator resources that occupy part of the virtualization in the virtualized network.
  • the virtual network element can apply to the cloud operating system for a virtual machine supporting the hardware acceleration function.
  • the following describes the process of applying for a virtual machine that supports the hardware acceleration function from the virtual network element to the cloud operating system.
  • FIG. 2 is a flowchart of a method for processing a service according to an embodiment of the present invention. The method is applied to the system for processing services shown in FIG. The method includes the following steps:
  • Step 21 The virtual network element determines that the to-be-processed service is a service that needs to perform hardware acceleration processing.
  • Step 22 The virtual network element sends a virtual machine allocation request to the cloud operating system, where the virtual machine allocation request carries a VM template supporting the hardware acceleration function and a number of virtual machines supporting the hardware acceleration function, where the hardware acceleration function is supported.
  • the VM template contains indication information of the virtualized hardware accelerator resource;
  • Step 23 The cloud operating system allocates the number of the virtual machines supporting the hardware acceleration function, and drives the virtualized hardware acceleration configured for the virtual machine supporting the hardware acceleration function.
  • Step 24 The virtual network element performs hardware acceleration processing on the to-be-processed service by running the virtual machine supporting the hardware acceleration function.
  • the service to be processed faced by the virtual network element may be a normal service (that is, a service that does not require hardware acceleration processing), or may be a service that requires hardware acceleration processing.
  • the virtual network element can process the common service by running the general virtual machine.
  • the virtual network element can apply for the general virtual machine to the cloud operating system as in the prior art.
  • the virtual network element can perform hardware acceleration processing on the service that needs hardware acceleration processing by running a virtual machine supporting the hardware acceleration function in the solution provided by the real-time example of the present application.
  • the virtualized gateway device may apply to the cloud operating system for a virtual machine that supports the DPI function.
  • the virtual network device when the virtual network element is to process the service, the virtual network device does not directly apply for the general virtual machine to the cloud operating system, but first determines whether the to-be-processed service is a service that needs to perform hardware acceleration processing, if virtual The network element determines that the to-be-processed service is a service that needs to perform hardware acceleration processing, and the virtual network element applies to the cloud operating system for the virtual machine that supports the hardware acceleration function; if the virtual network element determines that the to-be-processed service is not a service that needs to perform hardware acceleration processing, The virtual network element applies for a general virtual machine to the cloud operating system.
  • the threshold value may be set by the system or artificially. If the number of the virtualized resources to be processed is greater than the threshold, the service to be processed is a service that needs to be subjected to hardware acceleration processing; otherwise, the service to be processed is not required to be hardware. Accelerated processing of business. Generally, for a service that requires hardware accelerated processing, there is a hardware accelerator dedicated to processing the service in the prior art. For example, for a service that needs to perform a full scan of a message, a hardware accelerator with DPI function already exists in the prior art.
  • the VM template supporting the hardware acceleration function in Step 22 (Chinese: Virtual Machine; English: Virtual Machine) is included in the VNFD template.
  • the VNFD template In addition to defining multiple VM templates, the VNFD template also defines the service processing capabilities of each virtual network element in the virtualized network.
  • the VNFD template is used by the operator or the device vendor according to various resources in the virtualized network (for example, processor resources, memory resources, hard disk resources, hardware accelerator resources) and cloud operating systems. The ability of the source to be virtualized is defined.
  • VNFD virtual network function description
  • English Virtual Network Function
  • the Description template contains at least one VM template that supports hardware acceleration.
  • VM template 1 Virtualized processor resources: 10 cores; virtualized memory resources: 64G; virtualized hard disk resources: 512G; virtualized hardware accelerator resources with DPI capabilities: 10Gbps.
  • VM template 2 virtualized processor resources: 10 cores; virtualized memory resources: 64G; virtualized hard disk accelerator resources: 512G; hardware accelerator resources with DPI function virtualization: not supported.
  • the VNFD template is stored in the MANO module shown in FIG. 1.
  • the MANO module is a functional entity that implements management and orchestration of virtual network elements in a virtualized network.
  • the MAN sends the VNFD template to the virtual NE.
  • step 22 the method further comprises the following steps:
  • the MANO module sends a virtual network function description VNFD template to the virtual network element, where the VNFD template includes at least one virtual machine VM template and a service processing capability of the virtual network element;
  • the virtual network element Determining, by the virtual network element, the VM template supporting the hardware acceleration function from the at least one VM template, where the virtual machine supporting the hardware acceleration function is configured according to the VM template supporting the hardware acceleration function;
  • the virtual network element determines the number of the virtual machines supporting the hardware acceleration function according to the service processing capability of the virtual machine supporting the hardware acceleration function and the service processing capability of the virtual network element.
  • the virtual network element after receiving the VNFD template sent by the MANO module, the virtual network element first determines a VM template that supports the hardware acceleration function from at least one VM template included in the VNFD template.
  • the virtual network element may be VM template 1 is selected because VM template 1 is a VM template supporting hardware acceleration function, specifically, virtualized hardware accelerator resources included in VM template 1
  • the instructions are: Virtualized hardware accelerator resources with DPI capabilities: 10Gbps.
  • the virtual network element determines the service processing capability of the virtual machine supporting the hardware acceleration function configured according to the VM template supporting the hardware acceleration function.
  • the virtual network element determines the virtual machine supporting the DPI function configured according to the VM template 1.
  • the service processing capability is: the number of users is 100,000, and the throughput is 10 Gbps.
  • the virtual network element divides its own service processing capability from the service processing capability of the virtual machine that supports the hardware acceleration function configured according to the VM template supporting the hardware acceleration function, and the result of the division is that the virtual network element needs to be
  • the service processing capability of the virtual network element is: the total number of users is 1 million, and the total throughput is 100 Gpbs.
  • the service processing capability of the virtual machine supporting the DPI function configured according to the VM template 1 is: the number of users is 10. If the throughput is 10 Gbps, the virtual network element can determine that it needs to apply for 10 virtual machines supporting the DPI function to the cloud operating system.
  • the 10 virtual machines supporting the DPI function are configured according to the VM template 1.
  • step 22 may be performed.
  • the virtual network element carries the VM template supporting the hardware acceleration function and the number of the virtual machine supporting the hardware acceleration function in the virtual machine allocation request, and sends the virtual machine allocation request to the cloud operating system.
  • the number in the allocation request indicates how many virtual machines supporting the hardware acceleration function are allocated by the cloud operating system.
  • the VM template supporting the hardware acceleration function in the allocation request characterizes the virtual machine supported by the cloud operating system to support the hardware acceleration function. What kind of VM template is configured.
  • the virtual machine allocation request sent by the virtual network element to the cloud operating system carries the VM template 1 and the number 10, and the cloud operating system needs to configure 10 virtual machines supporting the DPI function, and the 10 supports the DPI function.
  • the virtual machines are all configured according to VM template 1. That is, the 10 DPI-capable virtual machines are configured with 10 cores of virtualized processor resources, 64G of virtualized memory resources, and 512G of virtualized hard disks. Resources, 10Gbps virtualized hardware accelerator resources with DPI capabilities.
  • the cloud operating system allocation in step 23 is performed in accordance with the number of the supporting hardware plus Before the speed function virtual machine, it also includes:
  • the cloud operating system After receiving the virtual machine allocation request, the cloud operating system sends a resource allocation request to the hardware accelerator resource management module, where the resource allocation request is used to request a virtualized hardware accelerator resource;
  • the hardware accelerator resource management module allocates a virtualized hardware accelerator resource
  • the cloud operating system in step 23 allocates the number of the virtual machines that support the hardware acceleration function, and further includes:
  • the cloud operating system utilizes the allocated virtualized hardware accelerator resources to allocate the virtual machines that meet the number of the supported hardware acceleration functions.
  • the cloud operating system receives the virtual machine allocation request, and then discovers that the virtual machine allocation request is a virtual machine requesting to allocate hardware acceleration support, and therefore, the cloud The operating system sends the virtual machine allocation request to the processor resource management module, the memory resource management module, and the hard disk resource management module.
  • the processor resource management module, the memory resource management module, and the hard disk resource management module respectively allocate corresponding virtualization.
  • the processor resource, the virtualized memory resource, and the virtualized hard disk resource; on the other hand, the virtual machine allocation request is sent to the accelerator resource management module, and the corresponding virtualized hardware accelerator resource is allocated by the accelerator resource management module.
  • the cloud operating system utilizes the allocated virtualized processor resources, virtualized memory resources, and virtualized hard disk resources and virtualized hardware accelerator resources to configure the virtual machines that support hardware acceleration.
  • the virtual machine allocation request sent by the virtual network element to the cloud operating system carries the VM template 1 and the number 10, and the cloud operating system receives the virtual machine allocation request, and then finds that the virtual machine allocation request is requested to be allocated according to the request.
  • the virtual machine supporting the DPI acceleration function configured by the VM template 1 is configured to send the virtual machine allocation request to the processor resource management module, the memory resource management module, and the hard disk resource management module by the processor resource management module.
  • the memory resource management module and the hard disk resource management module respectively allocate 100 core virtualized processor resources, 640G virtualized memory resources, and 5120G virtualized hard disk resources, and send the virtual machine allocation request on the other hand.
  • Hardware accelerator resource management module managed by hardware accelerator resources The module allocates 100 Gbps of virtualized hardware accelerator resources with DPI capabilities. Finally, since 10 virtual machines supporting DPI functions are to be allocated, the cloud operating system allocates 100 cores of virtualized processor resources, 640G of virtualized memory resources, and 5120G of virtualized hard disk resources. And 100Gbps DPI-enabled virtualized hardware accelerator resources are divided into 10 groups, each group is configured to a DPI-capable virtual machine, so that each virtual machine that supports DPI functions is configured with virtualization processing.
  • the resource is 10 cores
  • the virtualized memory resource is 64G
  • the virtualized hard disk resource is 512G
  • the DPI-enabled virtualized hardware accelerator resource is 10Gbps.
  • the cloud operating system driver in step 23 drives the virtualized hardware accelerator resource configured for the virtual machine supporting the hardware acceleration function, including:
  • the cloud operating system After completing the allocation of the virtual machine supporting the hardware acceleration function, the cloud operating system sends a resource driving request to the hardware accelerator resource driving module, where the resource driving request is used to request to drive the allocated virtualization.
  • Hardware accelerator resources ;
  • the hardware accelerator resource driver module drives the allocated virtualized hardware accelerator resources.
  • the cloud operating system triggers the processor resource driving module, the memory resource driving module, and the hard disk resource.
  • the driver module drives the allocated virtualized processor resources, the virtualized memory resources, and the virtualized hard disk resources, respectively; on the other hand, the accelerator resource driver module is triggered to drive the allocated virtualized hardware accelerator resources.
  • the cloud operating system triggers the processor resources on the one hand.
  • the driver module, the memory resource driver module, and the hard disk resource driver module respectively drive the group virtualized processor resources allocated 10, 10 sets of virtualized memory resources, and 10 sets of virtualized hard disk resources, and trigger the hardware accelerator on the other hand.
  • the resource driver module drives the assigned 10 sets of DPI-enabled virtualized hardware accelerator resources.
  • Virtual network element after driving virtualized resources configured for virtual machines that support hardware acceleration A virtual machine that supports hardware acceleration can be run on it.
  • the interaction between the virtual network element and the virtualized hardware accelerator resource may be implemented through an API (Chinese: Application Interface; English: Application Interface), or through message communication or shared memory reading and writing. If the interaction between the virtual network element and the virtualized hardware accelerator resource is through the API, the cloud operating system can also perform the following steps:
  • the cloud operating system is configured to invoke an application interface API of the virtualized hardware accelerator resource
  • step 24 includes:
  • the virtual network element invokes, by using the API, a virtualized hardware accelerator resource configured for the virtual machine supporting the hardware acceleration function, and performs hardware acceleration processing on the processed service by the invoked virtualized hardware accelerator resource.
  • the virtualized resources configured for the virtual machine supporting the hardware acceleration function include virtualized processor resources, virtualized memory resources, and virtualized hard disk resources, including virtualized hardware accelerator resources, and virtualization.
  • the hardware accelerator resource is the cloud operating system virtualizing the hardware accelerator resources. Therefore, after the cloud operating system virtualizes the hardware accelerator, the API can also be configured for the virtual network element and virtualization. Data transfer between hardware accelerator resources.
  • the service to be processed is first divided into a common task and a task of performing hardware acceleration processing by using the virtualized hardware accelerator resource.
  • a service that needs to perform a full scan of a packet can be split into two tasks.
  • One task is to perform a comprehensive scan and analysis of the service data packets accessed by the user, and obtain key information such as a corresponding seven-layer protocol and a URL.
  • Another task is to feed back the key information such as the corresponding seven-layer protocol and URL to the CPU's service processing module for matching and synthesis.
  • DPI-based user business policy control is implemented.
  • the first task is to use the virtualized DPI hardware accelerator resources for hardware acceleration processing tasks
  • the other task is common tasks, using virtualized processor resources, virtualized memory resources, and virtualized hard disk resources. Can be completed.
  • the hardware accelerator resource utilizes virtualized hardware accelerator resources to perform hardware acceleration processing on the remaining tasks.
  • the API configured by the cloud operating system is used for data transmission between the virtual network element and the virtualized DPI hardware accelerator resource.
  • the virtualized hardware accelerator resource is 10 Gbps, and 10 Gbps of DPI-enabled virtualized hardware accelerator resources perform the above-mentioned first task, and 10 cores of a DPI-enabled virtual machine configuration running on the virtual network element
  • the virtualized processor resources, 64G of virtualized memory resources, and 512G of virtualized hard disk resources perform the second task described above.
  • the embodiment of the present invention further provides a system for processing a service as shown in FIG. 1.
  • the virtual network element in the system for processing a service is used to: determine that a service to be processed is a service that needs to perform hardware acceleration processing;
  • the cloud operating system sends a virtual machine allocation request, where the virtual machine allocation request carries a number of virtual machine VM templates supporting hardware acceleration functions and virtual machines supporting hardware acceleration functions, and the VM template supporting hardware acceleration functions includes virtualized hardware Indication information for the accelerator resource;
  • the cloud operating system in the system for processing a service is configured to: allocate a virtual machine that meets the number of the supported hardware acceleration functions, and drive a virtualized hardware accelerator resource configured for the virtual machine supporting the hardware acceleration function ;
  • the virtual network element in the system for processing the service is further configured to perform hardware acceleration processing on the to-be-processed service by running the virtual machine supporting the hardware acceleration function.
  • system for processing the service further includes:
  • the MANO module being respectively connected to the virtual network element and the cloud operating system;
  • the MANO module is configured to: send a virtual network function description VNFD template to the virtual network element, where the VNFD template includes at least one virtual machine VM template and a service processing capability of the virtual network element;
  • the virtual network element is further configured to: determine the VM template supporting the hardware acceleration function from the at least one VM template; determine a service processing capability of the virtual machine supporting the hardware acceleration function, and support the hardware acceleration
  • the functioning virtual machine is configured according to the VM template supporting the hardware acceleration function; determining the supported hardware acceleration function according to the service processing capability of the virtual machine supporting the hardware acceleration function and the service processing capability of the virtual network element. The number of virtual machines.
  • system for processing a service further includes: a hardware accelerator resource management module, and is connected to the cloud operating system;
  • the cloud operating system is configured to: after receiving the virtual machine allocation request, request the virtualized hardware accelerator resource from the hardware accelerator resource management module; and utilize the allocated virtualized hardware accelerator resource, the allocation conforms to the a number of said virtual machines that support hardware acceleration functions;
  • the hardware accelerator resource management module is configured to: allocate a virtualized hardware accelerator resource.
  • system for processing a service further includes: a hardware accelerator resource driving module, and is connected to the cloud operating system;
  • the cloud operating system is configured to: after completing the allocating the virtual machine supporting the hardware acceleration function, the resource accelerator request is sent to the hardware accelerator resource driving module, where the resource driving request is used to request the driving Allocated virtualized hardware accelerator resources;
  • the hardware accelerator resource driver module is configured to: drive the allocated virtualized hardware accelerator resource.
  • the cloud operating system is configured to: configure an application interface API for invoking a virtualized hardware accelerator resource;
  • the virtual network element is configured to: the virtual network element invokes, by using the API, a virtualized hardware accelerator resource configured for the virtual machine supporting the hardware acceleration function, and is processed by the invoked virtualized hardware accelerator resource.
  • the business performs hardware acceleration processing.
  • the embodiment of the present invention further provides a method for allocating resources, and the method for allocating resources is applied to a cloud operating system in a system for processing services shown in FIG. 1 .
  • the method for allocating resources includes:
  • Step 31 The cloud operating system receives a virtual machine allocation request sent by a virtual network element, where the virtual machine allocation request carries a VM template supporting a hardware acceleration function and a number of virtual machines supporting a hardware acceleration function, where the hardware acceleration function is supported.
  • VM template contains instructions for virtualized hardware accelerator resources configured by the virtual machine;
  • Step 32 The cloud operating system allocates the virtual machine supporting the hardware acceleration function according to the quantity, and drives a virtualized hardware accelerator resource configured for the virtual machine supporting the hardware acceleration function.
  • the method further includes:
  • the cloud operating system After receiving the virtual machine allocation request, the cloud operating system sends a resource allocation request to the hardware accelerator resource management module, where the resource allocation request is used to request a virtualized hardware accelerator resource;
  • the cloud operating system utilizes the allocated virtualized hardware accelerator resources to allocate the virtual machines that meet the number of the supported hardware acceleration functions.
  • the cloud operating system drives the virtualized hardware accelerator resources configured for the virtual machine supporting the hardware acceleration function, including:
  • the cloud operating system After completing the allocation of the virtual machine supporting the hardware acceleration function, the cloud operating system sends a resource driving request to the hardware accelerator resource driving module, where the resource driving request is used to request to drive the allocated virtualization.
  • Hardware accelerator resources ;
  • the method for allocating resources further includes:
  • the cloud operating system is configured to invoke an application interface API of the virtualized hardware accelerator resource, where the API is used by the virtual network element to invoke a virtualized hardware accelerator resource configured for the virtual machine supporting the hardware acceleration function And hardware accelerated processing of the processing service by the invoked virtualized hardware accelerator resource.
  • the embodiment of the present invention further provides a cloud operating system capable of executing the method for allocating resources shown in FIG.
  • the cloud operating system includes:
  • the receiving interface 41 is configured to: receive a virtual machine allocation request sent by a virtual network element, where the virtual machine allocation request carries a VM template supporting a hardware acceleration function and a number of virtual machines supporting a hardware acceleration function, where the hardware acceleration function is supported.
  • VM template contains instructions for virtualized hardware accelerator resources configured by the virtual machine;
  • the processor 42 is configured to: allocate the virtual machine supporting the hardware acceleration function according to the quantity, and drive the virtualized hardware accelerator resource configured for the virtual machine supporting the hardware acceleration function.
  • the cloud operating system further includes: a sending interface, configured to: after receiving the virtual machine allocation request, send a resource allocation request to the hardware accelerator resource management module, where the resource allocation request is used to request virtualization Hardware accelerator resources;
  • the receiving interface 41 is configured to: receive a first notification message sent by the hardware accelerator resource management module, where the first notification message indicates that the hardware accelerator resource management module completes allocation of the virtualized hardware accelerator resource;
  • the processor is configured to: allocate, by using the allocated virtualized hardware accelerator resources, the virtual machine that meets the quantity of the supported hardware acceleration function;
  • the sending interface is further configured to send a resource driving request to the hardware accelerator resource driving module, where the resource driving request is used to request to drive the allocated virtual Hardware accelerator resources;
  • the receiving interface 41 is further configured to receive a second notification message sent by the hardware accelerator resource driving module, where the second notification message indicates that the hardware accelerator resource driving module completes the hardware accelerator resource for the allocated virtualization. Drive.
  • the processor 42 is further configured to:
  • An application interface API configured to invoke a virtualized hardware accelerator resource, the API being used by the virtual network element to invoke a virtualized hardware accelerator resource configured for the virtual machine supporting the hardware acceleration function, and invoked by The virtualized hardware accelerator resources are processed for hardware acceleration processing.
  • the embodiment of the present invention further provides a method for processing a service, where the method for processing a service is applied to a virtual network element in a system for processing a service shown in FIG. 1.
  • the method for processing a service includes:
  • Step 51 The virtual network element determines that the to-be-processed service is a service that needs to perform hardware acceleration processing.
  • Step 52 The virtual network element sends a virtual machine allocation request to the cloud operating system, where the virtual machine allocation request carries a VM template supporting the hardware acceleration function and a number of virtual machines supporting the hardware acceleration function, where the hardware acceleration function is supported.
  • the VM template contains indication information of the virtualized hardware accelerator resource;
  • Step 53 The virtual network element receives a third notification message sent by the cloud operating system, where the third notification message indicates that the cloud operating system has allocated the support hard that meets the required amount.
  • An accelerated virtual machine that has been driven to virtualize hardware accelerator resources configured for the virtual machine that supports hardware acceleration;
  • Step 54 The virtual network element performs hardware acceleration processing on the to-be-processed service by running the virtual machine supporting the hardware acceleration function.
  • the method before the sending, by the virtual network element, the virtual machine allocation request to the cloud operating system, the method further includes:
  • the virtual network element receives and manages a virtual network function description VNFD template sent by the MANO module, where the VNFD template includes at least one virtual machine VM template and a service processing capability of the virtual network element;
  • the virtual network element determines the number of the virtual machines supporting the hardware acceleration function according to the service processing capability of the virtual machine supporting the hardware acceleration function and the service processing capability of the virtual network element.
  • the virtual network element performs hardware acceleration processing on the to-be-processed service by running the virtual machine that supports the hardware acceleration function, including:
  • the virtual network element invokes a virtualized hardware accelerator resource configured for the virtual machine supporting the hardware acceleration function through an application program interface API, and performs hardware acceleration processing on the processed service by the invoked virtualized hardware accelerator resource.
  • the API is an interface for calling virtualized hardware accelerator resources.
  • the embodiment of the present invention further provides a virtual network element, where the virtual network element can execute the method for processing the service shown in FIG. 5.
  • the virtual network element includes:
  • a processor 61 for controlling the operation of the transmitting interface 62, and a receiving interface 63;
  • the processor 61 is configured to: determine that the to-be-processed service is a service that needs to perform hardware acceleration processing;
  • the sending interface 62 is configured to: send a virtual machine allocation request to the cloud operating system, where the virtual machine allocation request carries a VM template supporting a hardware acceleration function and a number of virtual machines supporting a hardware acceleration function, where the hardware acceleration function is supported
  • the VM template contains indication information of the virtualized hardware accelerator resource
  • the receiving interface 63 is configured to: receive a third notification message sent by the cloud operating system, where the third notification message indicates that the cloud operating system has allocated the virtual hardware supporting the hardware acceleration function that meets the required amount. And hardwareized hardware accelerator resources that have been configured for the virtual machine that supports hardware acceleration;
  • the processor 61 is further configured to perform hardware acceleration processing on the to-be-processed service by running the virtual machine supporting the hardware acceleration function.
  • the receiving interface 63 is configured to: receive and manage a virtual network function description VNFD template sent by the MANO module, where the VNFD template includes at least one virtual machine VM template and service processing capability of the virtual network element;
  • the processor 61 is configured to: determine the VM template supporting the hardware acceleration function from the at least one VM template; determine a service processing capability of the virtual machine supporting the hardware acceleration function, and support the hardware acceleration function
  • the virtual machine is configured according to the VM template supporting the hardware acceleration function; determining the hardware acceleration function according to the service processing capability of the virtual machine supporting the hardware acceleration function and the service processing capability of the virtual network element. The number of virtual machines.
  • the processor 61 is configured to:
  • the API Invoking a virtualized hardware accelerator resource configured for the virtual machine supporting the hardware acceleration function through an application program interface API, and performing hardware accelerated processing on the processed service by the invoked virtualized hardware accelerator resource, the API is used for An interface that invokes a virtualized hardware accelerator resource.
  • the cloud operating system allocates a virtual machine that supports the hardware acceleration function to the virtual network element. Therefore, the virtual network element performs hardware acceleration on the service that needs to perform hardware acceleration processing by running a virtual machine that supports the hardware acceleration function.
  • the virtualized hardware accelerator resources configured for the virtual machine supporting the hardware acceleration function can replace the large number of virtualized resources occupied by the general virtual machine. Therefore, all the virtualized resources occupied by the virtual network element are single-service (that is, required)
  • the service that performs hardware acceleration processing reduces the amount of virtualized resources consumed, and the remaining large amount of virtualized resources are consumed by other services, improving the performance of the virtual network element, and avoiding the hardware acceleration required by the virtual network element through the common virtual machine.
  • the processed service is processed to avoid serious performance degradation of the virtual network element.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) including computer usable program code.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device. Having a series of operational steps performed on a computer or other programmable device to produce computer-implemented processing such that instructions executed on a computer or other programmable device are provided for implementing one or more processes and/or block diagrams in the flowchart. The steps of a function specified in a box or multiple boxes.

Landscapes

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

Abstract

本申请提供一种处理业务的方法及系统，该方法包括：云操作系统为虚拟网元分配支持硬件加速功能的虚拟机，因此，虚拟网元通过运行支持硬件加速功能的虚拟机对需要进行硬件加速处理的业务进行硬件加速处理，为支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源可以代替通用的虚拟机占用的大量的虚拟化资源，因此，虚拟网元占用的所有虚拟化资源中被单一业务(即需要进行硬件加速处理的业务)消耗的虚拟化资源减少，剩余有的大量的虚拟化资源供其他业务消耗，提高了虚拟网元的性能，避免了虚拟网元通过通用的虚拟机对需要进行硬件加速处理的业务进行处理，进而避免了虚拟网元的性能严重下降。

Description

一种处理业务的方法及系统 技术领域
本发明涉及计算机领域，特别涉及一种处理业务的方法及系统。
背景技术
随着虚拟化技术和云技术的提出，虚拟网元应运而生，相比于传统网元，虚拟网元通过运行通用的虚拟机对待处理业务进行处理，其中，为通用的虚拟机配置的虚拟化资源包括：虚拟化的处理器资源、虚拟化的存储器资源、虚拟化的硬盘资源等。
由于虚拟网元面对的待处理业务具有多样性，所以有的业务消耗少量的虚拟化资源，有的业务消耗大量的虚拟化资源，例如：需要进行硬件加速处理的业务消耗大量的虚拟化资源。在虚拟网元面对需要进行硬件加速处理的业务时，虚拟网元要求为通用的虚拟机配置大量的虚拟化资源，因此，虚拟网元在通过运行通用的虚拟机对需要进行硬件加速处理的业务进行处理的过程中，消耗了大量的虚拟化资源，导致虚拟网元的性能严重下降。
发明内容
本发明实施例提供一种处理业务的方法及系统，用于解决现有技术中虚拟网元在通过运行通用的虚拟机对需要进行硬件加速处理的业务进行处理的过程中，消耗了大量的虚拟化资源，因而导致虚拟网元的性能严重下降的技术问题。
本发明实施例第一方面提供了一种处理业务的方法，所述方法包括：
虚拟网元确定待处理业务是需要进行硬件加速处理的业务；
所述虚拟网元向云操作系统发送虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的虚拟机VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟化的硬件加速器资源的指示 信息；
所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机，并驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源；
所述虚拟网元通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理。
云操作系统为虚拟网元分配支持硬件加速功能的虚拟机，因此，虚拟网元通过运行支持硬件加速功能的虚拟机对需要进行硬件加速处理的业务进行硬件加速处理，为支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源可以代替通用的虚拟机占用的大量的虚拟化资源，因此，虚拟网元占用的所有虚拟化资源中被单一业务(即需要进行硬件加速处理的业务)消耗的虚拟化资源减少，剩余有的大量的虚拟化资源供其他业务消耗，提高了虚拟网元的性能，避免了虚拟网元通过通用的虚拟机对需要进行硬件加速处理的业务进行处理，进而避免了虚拟网元的性能严重下降。
结合第一方面，在第一方面的第一种可能的实现方式中，在所述虚拟网元向云操作系统发送虚拟机分配请求之前，所述方法还包括：
管理和编排MANO模块将虚拟网络功能描述VNFD模板发送给所述虚拟网元，所述VNFD模板包括至少一种虚拟机VM模板和所述虚拟网元的业务处理能力；
所述虚拟网元从所述至少一种VM模板中确定出所述支持硬件加速功能的VM模板；所述虚拟网元确定所述支持硬件加速功能的虚拟机的业务处理能力，所述支持硬件加速功能的虚拟机是按照所述支持硬件加速功能的VM模板配置的；
所述虚拟网元根据所述支持硬件加速功能的虚拟机的业务处理能力和所述虚拟网元的业务处理能力，确定所述支持硬件加速功能的虚拟机的数量。
本发明实施例中，为了实现将硬件加速器资源应用于虚拟化和云化的环境，MANO模块中存储的VNFD模板包括支持硬件加速功能的VM模板，以便于虚拟网元使用支持硬件加速功能的VM模板向云操作系统申请支持硬件 加速功能的虚拟机。
结合第一方面或第一方面的第一种可能的实现方式，在第一方面的第二种可能的实现方式中，在所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机之前，还包括：
所述云操作系统在接收到所述虚拟机分配请求之后，向硬件加速器资源管理模块发送资源分配请求，所述资源分配请求用于请求虚拟化的硬件加速器资源；
所述硬件加速器资源管理模块分配虚拟化的硬件加速器资源；
所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机，包括：
所述云操作系统利用已分配的虚拟化的硬件加速器资源，分配符合所述数量的所述支持硬件加速功能的虚拟机。
本发明实施例中，为了实现将硬件加速器资源应用于虚拟化和云化的环境，提出了用于管理虚拟化网络中的硬件加速器资源的硬件加速器资源管理模块，硬件加速器资源管理模块与云操作系统配合，实现了分配支持硬件加速功能的虚拟机。
结合第一方面的第二种可能的实现方式，在第一方面的第三种可能的实现方式中，所述云操作系统驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，包括：
所述云操作系统在完成分配符合所述数量的所述支持硬件加速功能的虚拟机之后，向硬件加速器资源驱动模块发送资源驱动请求，所述资源驱动请求用于请求驱动已分配的虚拟化的硬件加速器资源；
所述硬件加速器资源驱动模块驱动所述已分配的虚拟化的硬件加速器资源。
本发明实施例中，为了实现将硬件加速器资源应用于虚拟化和云化的环境，提出了用于驱动虚拟化网络中的硬件加速器资源的硬件加速器资源驱动模块，硬件加速器资源驱动模块与云操作系统配合，实现了驱动支持硬件加 速功能的虚拟机。
结合第一方面至第一方面的第三种可能的实现方式，在第一方面的第四种可能的实现方式中，所述方法还包括：
所述云操作系统配置用于调用虚拟化的硬件加速器资源的应用程序接口API；
所述虚拟网元通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理，包括：
所述虚拟网元通过所述API调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理。
本发明实施例中，为了实现将硬件加速器资源应用于虚拟化和云化的环境，提出了虚拟网元与虚拟化的硬件加速器资源之间交互的API，以实现虚拟网元通过运行支持硬件加速功能的虚拟机对需要进行硬件加速处理的业务进行硬件加速处理。
本发明实施例第二方面提供了一种处理业务的系统，所述处理业务的系统包括：
虚拟网元和云操作系统，所述虚拟网元与所述云操作系统连接；
所述虚拟网元和所述云操作系统相互配合，用于执行第一方面所述的处理业务的方法。
结合第二方面，在第二方面的第一种可能的实现方式中，所述业务处理的系统还包括：
管理编排MANO模块，所述MANO模块分别与所述虚拟网元和所述云操作系统连接；
所述MANO模块与所述云操作系统配合，用于执行第一方面所述的处理业务的方法。
结合第二方面或第二方面的第一种可能的实现方式，在第二方面的第二种可能的实现方式中，所述处理业务的系统还包括：硬件加速器资源管理模 块，与所述云操作系统连接；
所述云操作系统与所述硬件加速器资源管理模块配合，用于执行第一方面所述的处理业务的方法。
结合第二方面的第二种可能的实现方式，在第二方面的第三种可能的实现方式中，所述处理业务的系统还包括：硬件加速器资源驱动模块，与所述云操作系统连接；
所述云操作系统与所述硬件加速器资源驱动模块配合，用于执行第一方面所述的处理业务的方法。
本发明实施例第三方面提供一种分配资源的方法，应用于云操作系统，所述方法包括：
所述云操作系统接收虚拟网元发送的虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟机配置的虚拟化的硬件加速器资源的指示信息；
所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机，并驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源。
结合第三方面，在第三方面的第一种可能的实现方式中，在所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机之前，还包括：
所述云操作系统在接收到所述虚拟机分配请求之后，向硬件加速器资源管理模块发送资源分配请求，所述资源分配请求用于请求虚拟化的硬件加速器资源；
所述云操作系统接收所述硬件加速器资源管理模块发送的第一通知消息，所述第一通知消息表征所述硬件加速器资源管理模块完成对虚拟化的硬件加速器资源的分配；
所述云操作系统利用已分配的虚拟化的硬件加速器资源，分配符合所述数量的所述支持硬件加速功能的虚拟机。
结合第三方面，在第三方面的第二种可能的实现方式中，所述云操作系 统驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，包括：
所述云操作系统在完成分配符合所述数量的所述支持硬件加速功能的虚拟机之后，向硬件加速器资源驱动模块发送资源驱动请求，所述资源驱动请求用于请求驱动已分配的虚拟化的硬件加速器资源；
所述云操作系统接收所述硬件加速器资源驱动模块发送的第二通知消息，所述第二通知消息表征所述硬件加速器资源驱动模块完成对所述已分配的虚拟化的硬件加速器资源的驱动。
结合第三方面至第三方面的第二种可能的实现方式，在第三方面的第三种可能的实现方式中，所述方法还包括：
所述云操作系统配置用于调用虚拟化的硬件加速器资源的应用程序接口API，所述API用于所述虚拟网元调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理。
本发明实施例第四方面提供了一种云操作系统，所述云操作系统包括：接收接口、处理器；所述云操作系统用于执行第三方面所述的分配资源的方法。
本发明实施例第五方面提供了一种处理业务的方法，所述方法应用于虚拟网元，所述方法包括：
所述虚拟网元确定待处理业务是需要进行硬件加速处理的业务；
所述虚拟网元向云操作系统发送虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟化的硬件加速器资源的指示信息；
所述虚拟网元接收所述云操作系统发送的第三通知消息，所述第三通知消息表征所述云操作系统已经分配出符合所述需求量的所述支持硬件加速功能的虚拟机，并已驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源；
所述虚拟网元通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理。
结合第五方面，在第五方面的第一种可能的实现方式中，在所述虚拟网元向云操作系统发送虚拟机分配请求之前，所述方法还包括：
所述虚拟网元接收管理和编排MANO模块发送的虚拟网络功能描述VNFD模板，所述VNFD模板包括至少一种虚拟机VM模板和所述虚拟网元的业务处理能力；
所述虚拟网元从所述至少一种VM模板中确定出所述支持硬件加速功能的VM模板；
所述虚拟网元确定所述支持硬件加速功能的虚拟机的业务处理能力，所述支持硬件加速功能的虚拟机是按照所述支持硬件加速功能的VM模板配置的；
所述虚拟网元根据所述支持硬件加速功能的虚拟机的业务处理能力和所述虚拟网元的业务处理能力，确定所述支持硬件加速功能的虚拟机的数量。
结合第五方面或第五方面的第一种可能的实现方式，在第五方面的第二种可能的实现方式中，所述虚拟网元通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理，包括：
所述虚拟网元通过应用程序接口API调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理，所述API是用于调用虚拟化的硬件加速器资源的接口。
本发明实施例第六方面提供一种虚拟网元，所述虚拟网元包括：
处理器、发送接口、接收接口；所述虚拟网元用于执行第五方面所述的处理业务的方法。
本发明实施例提供的方案中，云操作系统为虚拟网元分配支持硬件加速功能的虚拟机，因此，虚拟网元通过运行支持硬件加速功能的虚拟机对需要进行硬件加速处理的业务进行硬件加速处理，为支持硬件加速功能的虚拟机 配置的虚拟化的硬件加速器资源可以代替通用的虚拟机占用的大量的虚拟化资源，因此，虚拟网元占用的所有虚拟化资源中被单一业务(即需要进行硬件加速处理的业务)消耗的虚拟化资源减少，剩余有的大量的虚拟化资源供其他业务消耗，提高了虚拟网元的性能，避免了虚拟网元通过通用的虚拟机对需要进行硬件加速处理的业务进行处理，进而避免了虚拟网元的性能严重下降。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简要介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本发明实施例提供的处理业务的系统的示意图；
图2为本发明实施例提供的处理业务的系统执行的处理业务的方法的流程图；
图3为本发明实施例提供的分配资源的方法的流程图；
图4为本发明实施例提供的云操作系统的示意图；
图5为本发明实施例提供的虚拟网元执行的处理业务的方法的流程图；
图6为本发明实施例提供的虚拟网元的示意图。
具体实施方式
首先对发明实施例提供的处理业务的系统进行说明。请参考图1，图1为本发明实施例提供的处理业务的系统的示意图。该系统包括：虚拟网元、MANO(中文：管理和编排；英文：Management and Orchestration)模块和云操作系统。
其中，虚拟网元可以是虚拟化的网关设备，例如：vUGW(中文：虚拟统一网关；英文：Virtual Unified Gateway)，vUGW除可以作为TD-SCDMA(中 文：时分同步码分多址；英文：Time Division-Synchronous Code Division Multiple Access)、UMTS(中文：通用移动通信系统；英文：Universal Mobile Telecommunications System)、LTE(中文：长期演进；英文：Long Term Evolution)领域的移动核心网的网关设备之外，还可以作为CDMA2000(Code Division Multiple Access 2000)、Wimax(中文：全球微波互联接入；英文：Worldwide Interoperability for Microwave Access)领域的PDSN(中文：分组数据服务节点；英文：Packet Data Serving Node)设备或ePDG(中文：演进的分组数据网关；英文：evoloved Packet Data GateWay)等移动核心网的网关设备。
vUGW具体可以是3GPP(中文：第三代合作伙伴计划；英文：3rd Generation Partnership Project)标准中定义的GGSN(中文：网关GPRS支持节点；英文：Gateway GPRS Support Node)、SGW(中文：服务网关；英文：Serving GateWay)、PGW(中文：PDN网关；英文：PDN GateWay)。
当然，虚拟网元还可以是支持处理一些需要进行硬件加速处理的业务的网元，这些需要进行硬件加速处理的业务可以是：对报文进行全面扫描、IPSec(中文：因特网协议安全；英文：Internet Protocol Security)、视频编解码、视频转码、图片和文本压缩、TCP代理(TCP Proxy)协议栈等。其中，对报文进行全面扫描可以称为DPI(中文：深度报文检测；英文：Deep Packet Inspection)，又称为SA(中文：业务感知；英文：Service Awareness)。
现有技术已经将处理器资源、存储器资源、硬盘资源等应用于虚拟化和云化的环境中。在虚拟化网络中，部署有处理器资源管理模块、存储器资源管理模块、硬盘资源管理模块，分别用于管理虚拟化网络中的虚拟化的处理器资源、虚拟化的存储器资源和虚拟化的硬盘资源。此外，还部署有处理器资源驱动模块、存储器资源驱动模块、硬盘资源驱动模块，分别用于驱动为通用的虚拟机配置的虚拟化的处理器资源、虚拟化的存储器资源和虚拟化的硬盘资源。
云操作系统(Cloud OS)与处理器资源管理模块、存储器资源管理模块、 硬盘资源管理模块连接，虚拟化网络中的虚拟化的处理器资源、虚拟化的存储器资源和虚拟化的硬盘资源是云操作系统对处理器资源、存储器资源和硬盘资源进行虚拟化处理后的。其中，处理器资源、存储器资源和硬盘资源可以是由专门的处理器资源服务器、存储器资源服务器和硬盘资源服务器提供的，也可以是由虚拟化网络中的各个虚拟网元提供的，虚拟化网络中的各个虚拟网元分别配置有处理器资源、存储器资源和硬盘资源。
虚拟化网络中的虚拟化的处理器资源、虚拟化的存储器资源和虚拟化的硬盘资源是供虚拟化网络中的各个虚拟网元共享的。在虚拟网元面对待处理业务时，虚拟网元向云操作系统申请通用的虚拟机，由于为通用的虚拟机配置的虚拟化资源包括：虚拟化的处理器资源、虚拟化的存储器资源、虚拟化的硬盘资源，所以虚拟网元实现了占用虚拟化网络中的部分虚拟化的处理器资源、部分虚拟化的存储器资源和部分虚拟化的硬盘资源。
考虑到在虚拟网元面对需要进行硬件加速处理的业务时，虚拟网元上运行的通用的虚拟机占用了虚拟化网络中大量的虚拟化资源，导致虚拟网元的性能严重下降，主要是因为：虚拟网元占用的所有虚拟化资源中大量的虚拟化资源被单一业务(即需要进行硬件加速处理的业务)消耗，只有少量甚至没有虚拟化资源供其他业务消耗。所以，本发明实施例提出，将硬件加速器资源应用于虚拟化和云化的环境。
首先，本发明实施例中，要求虚拟化网络中存在硬件加速器资源，与处理器资源、存储器资源和硬盘资源类似，虚拟化网络中的硬件加速器资源可以是由专门的硬件加速器资源服务器务器提供的，也可以是由虚拟化网络中的部分虚拟网元提供的，虚拟化网络中的部分虚拟网元配置有硬件加速器资源。
接着，本发明实施例中，在虚拟化网络中，增加部署了图1所示的硬件加速器资源管理模块和硬件加速器资源驱动模块，硬件加速器资源管理模块用于管理虚拟化网络中的虚拟化的硬件加速器资源，硬件加速器资源驱动模块用于驱动为支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源。 与处理器资源管理模块、存储器资源管理模块、硬盘资源管理模块类似，云操作系统与硬件加速器资源管理模块连接，虚拟化网络中的虚拟化的硬件加速器资源是云操作系统对硬件加速器资源进行虚拟化处理后的。
这样，在虚拟网元面对需要进行硬件加速处理的业务时，虚拟化的硬件加速器资源可以代替通用的虚拟机占用的大量的虚拟化资源，因此，虚拟网元占用的所有虚拟化资源中被单一业务(即需要进行硬件加速处理的业务)消耗的虚拟化资源减少，剩余有的大量的虚拟化资源供其他业务消耗，提高了虚拟网元的性能。
与虚拟化的处理器资源、虚拟化的存储器资源和虚拟化的硬盘资源类似，虚拟化的硬件加速器资源是供虚拟化网络中的各个虚拟网元共享的。在虚拟网元面对需要硬件加速处理的业务时，虚拟网元向云操作系统申请支持硬件加速功能的虚拟机，由于为支持硬件加速功能的虚拟机配置的虚拟化资源除包括虚拟化的处理器资源、虚拟化的存储器资源、虚拟化的硬盘资源外，还包括虚拟化的硬件加速器资源，所以虚拟网元实现了占用虚拟化网络中的部分虚拟化的硬件加速器资源。
最后，本发明实施例中，虚拟网元能够向云操作系统申请支持硬件加速功能的虚拟机。下面对虚拟网元向云操作系统申请支持硬件加速功能的虚拟机的流程进行说明。
请参考图2，图2为本发明实施例提供的一种处理业务的方法的流程图。该方法应用于图1所示的处理业务的系统。该方法包括以下步骤：
步骤21：虚拟网元确定待处理业务是需要进行硬件加速处理的业务；
步骤22：所述虚拟网元向云操作系统发送虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟化的硬件加速器资源的指示信息；
步骤23：所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机，并驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速 器资源；
步骤24：所述虚拟网元通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理。
在背景技术中已经提及，虚拟网元面对的待处理业务可能是普通业务(即不需要进行硬件加速处理的业务)，也可能是需要进行硬件加速处理的业务。对于普通业务，虚拟网元可以通过运行通用的虚拟机对普通业务进行处理，则虚拟网元如现有技术中一样向云操作系统申请通用的虚拟机即可。对于需要硬件加速处理的业务，虚拟网元可以通过运行本申请实时例提供的方案中的支持硬件加速功能的虚拟机，对需要硬件加速处理的业务进行硬件加速处理。例如：对于需要对报文进行全面扫描的业务，在本申请实施例中，虚拟化的网关设备可以向云操作系统申请支持DPI功能的虚拟机。
因此，在本发明实施例中，虚拟网元在面对待处理业务时，不直接向云操作系统申请通用的虚拟机，而是首先判断待处理业务是否是需要进行硬件加速处理的业务，如果虚拟网元确定待处理业务是需要进行硬件加速处理的业务，则虚拟网元向云操作系统申请支持硬件加速功能的虚拟机；如果虚拟网元确定待处理业务不是需要进行硬件加速处理的业务，则虚拟网元向云操作系统申请通用的虚拟机。
可以由系统或人为设定阈值，如果待处理业务需要消耗的虚拟化资源的数量大于该阈值，则确定待处理业务是需要进行硬件加速处理的业务；反之，则确定待处理业务不是需要进行硬件加速处理的业务。通常，对于需要进行硬件加速处理的业务，现有技术中已经存在有专用于处理该业务的硬件加速器。例如：对于需要对报文进行全面扫描的业务，现有技术中已经存在具有DPI功能的硬件加速器。步骤22中的支持硬件加速功能的VM模板(中文：虚拟机；英文：Virtual Machine)是包含在VNFD模板中的。VNFD模板除定义了多种VM模板，还定义了虚拟化网络中各个虚拟网元的业务处理能力。VNFD模板是运营商或者设备商根据虚拟化网络中的各种资源(例如：处理器资源、存储器资源、硬盘资源、硬件加速器资源)和云操作系统对各种资 源进行虚拟化处理的能力定义的。
本发明实施例中，由于虚拟化网络中的各种资源除包括处理器资源、存储器资源和硬盘资源外，还包括硬件加速器资源，所以要求VNFD(中文：虚拟网络功能描述；英文：Virtual Network Function Description)模板至少包含一种支持硬件加速功能的VM模板。
例如：VNFD模板中会定义一个虚拟网元的业务处理能力为：总用户数为1百万，总吞吐量为100Gpbs；还定义了2个VM模板，VM模板1：虚拟化的处理器资源：10个核；虚拟化的存储器资源：64G；虚拟化的硬盘资源：512G；具有DPI功能的虚拟化的硬件加速器资源：10Gbps。VM模板2：虚拟化的处理器资源：10个核；虚拟化的存储器资源：64G；虚拟化的硬盘加速器资源：512G；具有DPI功能虚拟化的硬件加速器资源：不支持。
通常，VNFD模板保存在图1所示的MANO模块中，MANO模块是虚拟化网络中实现虚拟网元的管理和编排的功能实体。MANO在部署虚拟网元时，会将VNFD模板下发到虚拟网元中。
因此，在步骤22之前，所述方法还包括以下步骤：
MANO模块将虚拟网络功能描述VNFD模板发送给所述虚拟网元，所述VNFD模板包括至少一种虚拟机VM模板和所述虚拟网元的业务处理能力；
所述虚拟网元从所述至少一种VM模板中确定出所述支持硬件加速功能的VM模板，所述支持硬件加速功能的虚拟机是按照所述支持硬件加速功能的VM模板配置的；
所述虚拟网元确定所述支持硬件加速功能的虚拟机的业务处理能力；
所述虚拟网元根据所述支持硬件加速功能的虚拟机的业务处理能力和所述虚拟网元的业务处理能力，确定所述支持硬件加速功能的虚拟机的数量。
具体来讲，虚拟网元在收到MANO模块下发的VNFD模板之后，首先从VNFD模板包含的至少一种VM模板中确定出支持硬件加速功能的VM模板，在上述例子中，虚拟网元可以选择VM模板1，因为VM模板1是支持硬件加速功能的VM模板，具体地，VM模板1包含的虚拟化的硬件加速器资源 的指示信息为：具有DPI功能的虚拟化的硬件加速器资源：10Gbps。
然后，虚拟网元确定按照支持硬件加速功能的VM模板配置的支持硬件加速功能的虚拟机的业务处理能力，在上述例子中，虚拟网元确定按照VM模板1配置的支持DPI功能的虚拟机的业务处理能力为：用户数为10万，吞吐量为10Gbps。
最后，虚拟网元将其自身的业务处理能力，与按照支持硬件加速功能的VM模板配置的支持硬件加速功能的虚拟机的业务处理能力相除，相除的结果即为该虚拟网元需要向云操作系统申请的支持硬件加速功能的虚拟机的数量。在上述例子中，虚拟网元的业务处理能力为：总用户数为1百万，总吞吐量为100Gpbs，按照VM模板1配置的支持DPI功能的虚拟机的业务处理能力为：用户数为10万，吞吐量为10Gbps，则虚拟网元可以确定需要向云操作系统申请10个支持DPI功能的虚拟机，显然，这10个支持DPI功能的虚拟机都是按照VM模板1配置的。
在虚拟网元确定出支持硬件加速功能的VM模板和支持硬件加速功能的虚拟机的数量之后，可以执行步骤22。虚拟网元将支持硬件加速功能的VM模板和支持硬件加速功能的虚拟机的数量携带在虚拟机分配请求中，将虚拟机分配请求发送给云操作系统。分配请求中的数量表征云操作系统一共要分配多少个支持硬件加速功能的虚拟机，分配请求中的支持硬件加速功能的VM模板表征云操作系统分配的支持硬件加速功能的虚拟机必须都是按照什么样的VM模板配置的。
在上述例子中，虚拟网元向云操作系统发送的虚拟机分配请求中携带有VM模板1和数字10，表征云操作系统需要配置10个支持DPI功能的虚拟机，且这10个支持DPI功能的虚拟机都是按照VM模板1配置的，即这10个支持DPI功能的虚拟机都配置有10个核的虚拟化的处理器资源，64G的虚拟化的存储器资源，512G的虚拟化的硬盘资源，10Gbps的具有DPI功能的虚拟化的硬件加速器资源。
在执行步骤23中的所述云操作系统分配符合所述数量的所述支持硬件加 速功能的虚拟机之前，还包括：
所述云操作系统在接收到所述虚拟机分配请求之后，向硬件加速器资源管理模块发送资源分配请求，所述资源分配请求用于请求虚拟化的硬件加速器资源；
所述硬件加速器资源管理模块分配虚拟化的硬件加速器资源；
步骤23中的所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机，还包括：
所述云操作系统利用已分配的虚拟化的硬件加速器资源，分配符合所述数量的所述支持硬件加速功能的虚拟机。
具体来讲，虚拟网元向云操作系统发送虚拟机分配请求之后，云操作系统会接收该虚拟机分配请求，然后发现该虚拟机分配请求是请求分配支持硬件加速功能的虚拟机，因此，云操作系统一方面将该虚拟机分配请求发送给处理器资源管理模块、存储器资源管理模块、硬盘资源管理模块，由处理器资源管理模块、存储器资源管理模块、硬盘资源管理模块分别分配相应的虚拟化的处理器资源、虚拟化的存储器资源和虚拟化的硬盘资源；另一方面将该虚拟机分配请求发送给加速器资源管理模块，由加速器资源管理模块分配相应的虚拟化的硬件加速器资源。最后，云操作系统利用已分配的虚拟化的处理器资源、虚拟化的存储器资源和虚拟化的硬盘资源和虚拟化的硬件加速器资源，为支持硬件加速功能的虚拟机进行相应地配置。
在上述例子中，虚拟网元向云操作系统发送的虚拟机分配请求中携带有VM模板1和数字10，云操作系统会接收该虚拟机分配请求，然后发现该虚拟机分配请求是请求分配按照VM模板1配置的支持DPI加速功能的虚拟机，因此，云操作系统一方面将该虚拟机分配请求发送给处理器资源管理模块、存储器资源管理模块、硬盘资源管理模块，由处理器资源管理模块、存储器资源管理模块、硬盘资源管理模块分别分配100个核的虚拟化的处理器资源、640G的虚拟化的存储器资源和5120G的虚拟化的硬盘器资源，另一方面将该虚拟机分配请求发送给硬件加速器资源管理模块，由硬件加速器器资源管理 模块分配100Gbps的具有DPI功能的虚拟化的硬件加速器资源。最后，由于要分配10个支持DPI功能的虚拟机，所以云操作系统将已分配的100个核的虚拟化的处理器资源、640G的虚拟化的存储器资源和5120G的虚拟化的硬盘器资源，以及100Gbps的具有DPI功能的虚拟化的硬件加速器资源分别分为10组，将每组配置给一个支持DPI功能的虚拟机，这样，每个每个支持DPI功能的虚拟机配置有虚拟化的处理器资源为10个核，虚拟化的存储器资源为64G，虚拟化的硬盘器资源为512G，具有DPI功能的虚拟化的硬件加速器资源为10Gbps。
步骤23中的所述云操作系统驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，包括：
所述云操作系统在完成分配符合所述数量的所述支持硬件加速功能的虚拟机之后，向硬件加速器资源驱动模块发送资源驱动请求，所述资源驱动请求用于请求驱动已分配的虚拟化的硬件加速器资源；
所述硬件加速器资源驱动模块驱动所述已分配的虚拟化的硬件加速器资源。
具体来讲，在云操作系统按照虚拟网元发送的虚拟机分配请求，完成支持硬件加速功能的虚拟机的分配之后，云操作系统一方面触发处理器资源驱动模块、存储器资源驱动模块、硬盘资源驱动模块分别驱动已分配的虚拟化的处理器资源、虚拟化的存储器资源和虚拟化的硬盘资源；另一方面触发加速器资源驱动模块驱动已分配的虚拟化的硬件加速器资源。
在上述例子中，在云操作系统按照虚拟网元发送的虚拟机分配请求，完成按照VM模板1配置的10个支持DPI硬件加速功能的虚拟机的分配之后，云操作系统一方面触发处理器资源驱动模块、存储器资源驱动模块、硬盘资源驱动模块，分别驱动已分配10的组虚拟化的处理器资源、10组虚拟化的存储器资源和10组虚拟化的硬盘器资源，另一方面触发硬件加速器资源驱动模块驱动已分配的10组具有DPI功能的虚拟化的硬件加速器资源。
在驱动为支持硬件加速功能的虚拟机配置的虚拟化资源之后，虚拟网元 上可以运行支持硬件加速功能的虚拟机。本发明实施例中，虚拟网元与虚拟化的硬件加速器资源之间的交互可以通过API(中文：应用程序接口；英文：Application Interface)，也可以通过消息通信或共享内存读写的方式实现。如果虚拟网元与虚拟化的硬件加速器资源之间的交互是通过API，则云操作系统还可以执行以下步骤：
所述云操作系统配置用于调用虚拟化的硬件加速器资源的应用程序接口API；
相应地，步骤24包括：
所述虚拟网元通过所述API调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理。
具体来讲，为支持硬件加速功能的虚拟机配置的虚拟化资源除包括虚拟化的处理器资源、虚拟化的存储器资源和虚拟化的硬盘资源外，还包括虚拟化的硬件加速器资源，虚拟化的硬件加速器资源是云操作系统对硬件加速器资源进行虚拟化处理后的，因此，在云操作系统对硬件加速器进行虚拟化处理后中，还可以配置API，该API用于虚拟网元与虚拟化的硬件加速器资源之间进行数据传输。
在虚拟网元面对的待处理业务是需要进行硬件加速处理的业务时，首先将待处理的业务拆分为普通任务和需要利用虚拟化的硬件加速器资源进行硬件加速处理的任务。例如：需要对报文进行全面扫描的业务可以拆分为两个任务，一个任务为：对用户访问的业务数据报文进行全面的扫描和分析，获取相应的七层协议和URL等关键信息，另一个任务为：将获取到的相应的七层协议和URL等关键信息反馈给CPU的业务处理模块进行匹配和综合。最终实现基于DPI能力的用户业务策略控制。其中，第一个任务是需要利用虚拟化的DPI硬件加速器资源进行硬件加速处理的任务，另一个任务是普通任务，利用虚拟化的处理器资源、虚拟化的存储器资源以及虚拟化的硬盘资源即可完成。
然后利用为支持硬件加速功能的虚拟机配置的虚拟化的处理器资源、虚拟化的存储器资源和虚拟化的硬盘资源对普通任务进行处理，通过API调用为支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，利用虚拟化的硬件加速器资源对剩余任务进行硬件加速处理。
在上述例子中，云操作系统配置的API用于虚拟网元与虚拟化的DPI硬件加速器资源之间进行数据传输，如果为虚拟网元上运行的一个支持DPI功能的虚拟机配置的支持DPI功能的虚拟化的硬件加速器资源为10Gbps，则有10Gbps的支持DPI功能的虚拟化的硬件加速器资源执行上述第一个任务，而虚拟网元上运行的一个支持DPI功能的虚拟机配置的10个核的虚拟化的处理器资源、64G的虚拟化的存储器资源、以及512G的虚拟化的硬盘器资源执行上述第二个任务。
基于同一发明构思，本发明实施例还提供如图1所示的处理业务的系统，所述处理业务的系统中的虚拟网元用于：确定待处理业务是需要进行硬件加速处理的业务；向云操作系统发送虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的虚拟机VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟化的硬件加速器资源的指示信息；
所述处理业务的系统中的云操作系统用于：分配符合所述数量的所述支持硬件加速功能的虚拟机，并驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源；
所述处理业务的系统中的虚拟网元还用于：通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理。
可选的，所述业务处理的系统还包括：
管理编排MANO模块，所述MANO模块分别与所述虚拟网元和所述云操作系统连接；
所述MANO模块用于：将虚拟网络功能描述VNFD模板发送给所述虚拟网元，所述VNFD模板包括至少一种虚拟机VM模板和所述虚拟网元的业务处理能力；
所述虚拟网元还用于：从所述至少一种VM模板中确定出所述支持硬件加速功能的VM模板；确定所述支持硬件加速功能的虚拟机的业务处理能力，所述支持硬件加速功能的虚拟机是按照所述支持硬件加速功能的VM模板配置的；根据所述支持硬件加速功能的虚拟机的业务处理能力和所述虚拟网元的业务处理能力，确定所述支持硬件加速功能的虚拟机的数量。
可选的，所述处理业务的系统还包括：硬件加速器资源管理模块，与所述云操作系统连接；
所述云操作系统用于：在接收到所述虚拟机分配请求之后，向所述硬件加速器资源管理模块请求虚拟化的硬件加速器资源；利用已分配的虚拟化的硬件加速器资源，分配符合所述数量的所述支持硬件加速功能的虚拟机；
所述硬件加速器资源管理模块用于：分配虚拟化的硬件加速器资源。
可选的，所述处理业务的系统还包括：硬件加速器资源驱动模块，与所述云操作系统连接；
所述云操作系统用于：在完成分配符合所述数量的所述支持硬件加速功能的虚拟机之后，向所述硬件加速器资源驱动模块发送资源驱动请求，所述资源驱动请求用于请求驱动已分配的虚拟化的硬件加速器资源；
所述硬件加速器资源驱动模块用于：驱动所述已分配的虚拟化的硬件加速器资源。
可选的，所述云操作系统用于：配置用于调用虚拟化的硬件加速器资源的应用程序接口API；
所述虚拟网元用于：所述虚拟网元通过所述API调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理。
前述图2实施例中的处理业务的方法中的各种变化方式和具体实例同样适用于本实施例的处理业务的系统，通过前述对处理业务的方法的详细描述，本领域技术人员可以清楚的知道本实施例中处理业务的系统的实施方法，所以为了说明书的简洁，在此不再详述。
基于同一发明构思，本发明实施例还提供一种分配资源的方法，该分配资源的方法应用于图1所示的处理业务的系统中的云操作系统。请参考图3，该分配资源的方法包括：
步骤31：所述云操作系统接收虚拟网元发送的虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟机配置的虚拟化的硬件加速器资源的指示信息；
步骤32：所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机，并驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源。
可选的，在所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机之前，还包括：
所述云操作系统在接收到所述虚拟机分配请求之后，向硬件加速器资源管理模块发送资源分配请求，所述资源分配请求用于请求虚拟化的硬件加速器资源；
所述云操作系统接收所述硬件加速器资源管理模块发送的第一通知消息，所述第一通知消息表征所述硬件加速器资源管理模块完成对虚拟化的硬件加速器资源的分配；
所述云操作系统利用已分配的虚拟化的硬件加速器资源，分配符合所述数量的所述支持硬件加速功能的虚拟机。
可选的，所述云操作系统驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，包括：
所述云操作系统在完成分配符合所述数量的所述支持硬件加速功能的虚拟机之后，向硬件加速器资源驱动模块发送资源驱动请求，所述资源驱动请求用于请求驱动已分配的虚拟化的硬件加速器资源；
所述云操作系统接收所述硬件加速器资源驱动模块发送的第二通知消息，所述第二通知消息表征所述硬件加速器资源驱动模块完成对所述已分配 的虚拟化的硬件加速器资源的驱动。
可选的，所述分配资源的方法还包括：
所述云操作系统配置用于调用虚拟化的硬件加速器资源的应用程序接口API，所述API用于所述虚拟网元调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理。
对该分配资源的方法可参考前述图2实施例中的处理业务的方法，前述图2实施例中的处理业务的方法中的各种变化方式和具体实例同样适用于本实施例的分配资源的方法，通过前述对处理业务的方法的详细描述，本领域技术人员可以清楚的知道本实施例中分配资源的的实施方法，所以为了说明书的简洁，在此不再详述。
基于同一发明构思，本发明实施例还提供一种云操作系统，该云操作系统能够执行图3所示的分配资源的方法。请参考图4，该云操作系统包括：
接收接口41、处理器42；
所述接收接口41用于：接收虚拟网元发送的虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟机配置的虚拟化的硬件加速器资源的指示信息；
所述处理器42用于：分配符合所述数量的所述支持硬件加速功能的虚拟机，并驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源。
可选的，所述云操作系统还包括：发送接口，用于：在接收到所述虚拟机分配请求之后，向硬件加速器资源管理模块发送资源分配请求，所述资源分配请求用于请求虚拟化的硬件加速器资源；
所述接收接口41用于：接收所述硬件加速器资源管理模块发送的第一通知消息，所述第一通知消息表征所述硬件加速器资源管理模块完成对虚拟化的硬件加速器资源的分配；
所述处理器用于：利用已分配的虚拟化的硬件加速器资源，分配符合所述数量的所述支持硬件加速功能的虚拟机；
在完成分配符合所述数量的所述支持硬件加速功能的虚拟机之后，所述发送接口还用于向硬件加速器资源驱动模块发送资源驱动请求，所述资源驱动请求用于请求驱动已分配的虚拟化的硬件加速器资源；
所述接收接口41还用于接收所述硬件加速器资源驱动模块发送的第二通知消息，所述第二通知消息表征所述硬件加速器资源驱动模块完成对所述已分配的虚拟化的硬件加速器资源的驱动。
可选的，所述处理器42还用于：
配置用于调用虚拟化的硬件加速器资源的应用程序接口API，所述API用于所述虚拟网元调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理。
前述图3实施例中的分配资源的方法中的各种变化方式和具体实例同样适用于本实施例的云操作系统，通过前述对分配资源的方法的详细描述，本领域技术人员可以清楚的知道本实施例中云操作系统的实施方法，所以为了说明书的简洁，在此不再详述。
基于同一发明构思，本发明实施例还提供一种处理业务的方法，该处理业务的方法应用于图1所示的处理业务的系统中的虚拟网元。请参考图5，该处理业务的方法包括：
步骤51：所述虚拟网元确定待处理业务是需要进行硬件加速处理的业务；
步骤52：所述虚拟网元向云操作系统发送虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟化的硬件加速器资源的指示信息；
步骤53：所述虚拟网元接收所述云操作系统发送的第三通知消息，所述第三通知消息表征所述云操作系统已经分配出符合所述需求量的所述支持硬 件加速功能的虚拟机，并已驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源；
步骤54：所述虚拟网元通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理。
可选的，在所述虚拟网元向云操作系统发送虚拟机分配请求之前，所述方法还包括：
所述虚拟网元接收管理和编排MANO模块发送的虚拟网络功能描述VNFD模板，所述VNFD模板包括至少一种虚拟机VM模板和所述虚拟网元的业务处理能力；
所述虚拟网元从所述至少一种VM模板中确定出所述支持硬件加速功能的VM模板；
所述虚拟网元确定所述支持硬件加速功能的虚拟机的业务处理能力，所述支持硬件加速功能的虚拟机是按照所述支持硬件加速功能的VM模板配置的；
所述虚拟网元根据所述支持硬件加速功能的虚拟机的业务处理能力和所述虚拟网元的业务处理能力，确定所述支持硬件加速功能的虚拟机的数量。
可选的，所述虚拟网元通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理，包括：
所述虚拟网元通过应用程序接口API调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理，所述API是用于调用虚拟化的硬件加速器资源的接口。
对该处理业务的方法可参考前述图2实施例中的处理业务的方法，前述图2实施例中的处理业务的方法中的各种变化方式和具体实例同样适用于本实施例的处理业务的方法，通过前述对处理业务的方法的详细描述，本领域技术人员可以清楚的知道本实施例中处理业务的的实施方法，所以为了说明书的简洁，在此不再详述。
基于同一发明构思，本发明实施例还提供一种虚拟网元，该虚拟网元能够执行图5所示的处理业务的方法。请参考图6，该虚拟网元包括：
处理器61、发送接口62、接收接口63；
所述处理器61用于：确定待处理业务是需要进行硬件加速处理的业务；
所述发送接口62用于：向云操作系统发送虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟化的硬件加速器资源的指示信息；
所述接收接口63用于：接收所述云操作系统发送的第三通知消息，所述第三通知消息表征所述云操作系统已经分配出符合所述需求量的所述支持硬件加速功能的虚拟机，并已驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源；
所述处理器61还用于：通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理。
可选的，所述接收接口63用于：接收管理和编排MANO模块发送的虚拟网络功能描述VNFD模板，所述VNFD模板包括至少一种虚拟机VM模板和所述虚拟网元的业务处理能力；
所述处理器61用于：从所述至少一种VM模板中确定出所述支持硬件加速功能的VM模板；确定所述支持硬件加速功能的虚拟机的业务处理能力，所述支持硬件加速功能的虚拟机是按照所述支持硬件加速功能的VM模板配置的；根据所述支持硬件加速功能的虚拟机的业务处理能力和所述虚拟网元的业务处理能力，确定所述支持硬件加速功能的虚拟机的数量。
可选的，所述处理器61用于：
通过应用程序接口API调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理，所述API是用于调用虚拟化的硬件加速器资源的接口。
本发明实施例提供的方案中，云操作系统为虚拟网元分配支持硬件加速功能的虚拟机，因此，虚拟网元通过运行支持硬件加速功能的虚拟机对需要进行硬件加速处理的业务进行硬件加速处理，为支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源可以代替通用的虚拟机占用的大量的虚拟化资源，因此，虚拟网元占用的所有虚拟化资源中被单一业务(即需要进行硬件加速处理的业务)消耗的虚拟化资源减少，剩余有的大量的虚拟化资源供其他业务消耗，提高了虚拟网元的性能，避免了虚拟网元通过通用的虚拟机对需要进行硬件加速处理的业务进行处理，进而避免了虚拟网元的性能严重下降。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器和光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上， 使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
显然，本领域的技术人员可以对本申请进行各种改动和变型而不脱离本申请的精神和范围。这样，倘若本申请的这些修改和变型属于本申请权利要求及其等同技术的范围之内，则本申请也意图包含这些改动和变型在内。

Claims (23)

  1. 一种处理业务的方法，其特征在于，所述方法包括：
    虚拟网元确定待处理业务是需要进行硬件加速处理的业务；
    所述虚拟网元向云操作系统发送虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的虚拟机VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟化的硬件加速器资源的指示信息；
    所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机，并驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源；
    所述虚拟网元通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理。
  2. 如权利要求1所述的方法，其特征在于，在所述虚拟网元向云操作系统发送虚拟机分配请求之前，所述方法还包括：
    管理和编排MANO模块将虚拟网络功能描述VNFD模板发送给所述虚拟网元，所述VNFD模板包括至少一种虚拟机VM模板和所述虚拟网元的业务处理能力；
    所述虚拟网元从所述至少一种VM模板中确定出所述支持硬件加速功能的VM模板；所述虚拟网元确定所述支持硬件加速功能的虚拟机的业务处理能力，所述支持硬件加速功能的虚拟机是按照所述支持硬件加速功能的VM模板配置的；
    所述虚拟网元根据所述支持硬件加速功能的虚拟机的业务处理能力和所述虚拟网元的业务处理能力，确定所述支持硬件加速功能的虚拟机的数量。
  3. 如权利要求1或2所述的方法，其特征在于，在所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机之前，还包括：
    所述云操作系统在接收到所述虚拟机分配请求之后，向硬件加速器资源管理模块发送资源分配请求，所述资源分配请求用于请求虚拟化的硬件加速 器资源；
    所述硬件加速器资源管理模块分配虚拟化的硬件加速器资源；
    所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机，包括：
    所述云操作系统利用已分配的虚拟化的硬件加速器资源，分配符合所述数量的所述支持硬件加速功能的虚拟机。
  4. 如权利要求3所述的方法，其特征在于，所述云操作系统驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，包括：
    所述云操作系统在完成分配符合所述数量的所述支持硬件加速功能的虚拟机之后，向硬件加速器资源驱动模块发送资源驱动请求，所述资源驱动请求用于请求驱动已分配的虚拟化的硬件加速器资源；
    所述硬件加速器资源驱动模块驱动所述已分配的虚拟化的硬件加速器资源。
  5. 如权利要求1-4任一所述的方法，其特征在于，所述方法还包括：
    所述云操作系统配置用于调用虚拟化的硬件加速器资源的应用程序接口API；
    所述虚拟网元通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理，包括：
    所述虚拟网元通过所述API调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理。
  6. 一种处理业务的系统，其特征在于，所述处理业务的系统包括：
    虚拟网元和云操作系统，所述虚拟网元与所述云操作系统连接；
    所述虚拟网元用于：确定待处理业务是需要进行硬件加速处理的业务；向云操作系统发送虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的虚拟机VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟化的硬件加速器资源的指示信息；
    所述云操作系统用于：分配符合所述数量的所述支持硬件加速功能的虚拟机，并驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源；
    所述虚拟网元还用于：通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理。
  7. 如权利要求6所述的业务处理的系统，其特征在于，所述业务处理的系统还包括：
    管理编排MANO模块，所述MANO模块分别与所述虚拟网元和所述云操作系统连接；
    所述MANO模块用于：将虚拟网络功能描述VNFD模板发送给所述虚拟网元，所述VNFD模板包括至少一种虚拟机VM模板和所述虚拟网元的业务处理能力；
    所述虚拟网元还用于：从所述至少一种VM模板中确定出所述支持硬件加速功能的VM模板；确定所述支持硬件加速功能的虚拟机的业务处理能力，所述支持硬件加速功能的虚拟机是按照所述支持硬件加速功能的VM模板配置的；根据所述支持硬件加速功能的虚拟机的业务处理能力和所述虚拟网元的业务处理能力，确定所述支持硬件加速功能的虚拟机的数量。
  8. 如权利要求6或7所述的处理业务的系统，其特征在于，所述处理业务的系统还包括：硬件加速器资源管理模块，与所述云操作系统连接；
    所述云操作系统用于：在接收到所述虚拟机分配请求之后，向所述硬件加速器资源管理模块请求虚拟化的硬件加速器资源；利用已分配的虚拟化的硬件加速器资源，分配符合所述数量的所述支持硬件加速功能的虚拟机；
    所述硬件加速器资源管理模块用于：分配虚拟化的硬件加速器资源。
  9. 如权利要求8所述的处理业务的系统，其特征在于，所述处理业务的系统还包括：硬件加速器资源驱动模块，与所述云操作系统连接；
    所述云操作系统用于：在完成分配符合所述数量的所述支持硬件加速功能的虚拟机之后，向所述硬件加速器资源驱动模块发送资源驱动请求，所述 资源驱动请求用于请求驱动已分配的虚拟化的硬件加速器资源；
    所述硬件加速器资源驱动模块用于：驱动所述已分配的虚拟化的硬件加速器资源。
  10. 如权利要求6-9任一所述的处理业务的系统，其特征在于，所述云操作系统用于：配置用于调用虚拟化的硬件加速器资源的应用程序接口API；
    所述虚拟网元用于：所述虚拟网元通过所述API调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理。
  11. 一种分配资源的方法，其特征在于，应用于云操作系统，所述方法包括：
    所述云操作系统接收虚拟网元发送的虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟机配置的虚拟化的硬件加速器资源的指示信息；
    所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机，并驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源。
  12. 如权利要求11所述的方法，其特征在于，在所述云操作系统分配符合所述数量的所述支持硬件加速功能的虚拟机之前，还包括：
    所述云操作系统在接收到所述虚拟机分配请求之后，向硬件加速器资源管理模块发送资源分配请求，所述资源分配请求用于请求虚拟化的硬件加速器资源；
    所述云操作系统接收所述硬件加速器资源管理模块发送的第一通知消息，所述第一通知消息表征所述硬件加速器资源管理模块完成对虚拟化的硬件加速器资源的分配；
    所述云操作系统利用已分配的虚拟化的硬件加速器资源，分配符合所述数量的所述支持硬件加速功能的虚拟机。
  13. 如权利要求11所述的方法，其特征在于，所述云操作系统驱动为所 述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，包括：
    所述云操作系统在完成分配符合所述数量的所述支持硬件加速功能的虚拟机之后，向硬件加速器资源驱动模块发送资源驱动请求，所述资源驱动请求用于请求驱动已分配的虚拟化的硬件加速器资源；
    所述云操作系统接收所述硬件加速器资源驱动模块发送的第二通知消息，所述第二通知消息表征所述硬件加速器资源驱动模块完成对所述已分配的虚拟化的硬件加速器资源的驱动。
  14. 如权利要求11-13任一所述的方法，其特征在于，所述方法还包括：
    所述云操作系统配置用于调用虚拟化的硬件加速器资源的应用程序接口API，所述API用于所述虚拟网元调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理。
  15. 一种云操作系统，其特征在于，所述云操作系统包括：
    接收接口、处理器；
    所述接收接口用于：接收虚拟网元发送的虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟机配置的虚拟化的硬件加速器资源的指示信息；
    所述处理器用于：分配符合所述数量的所述支持硬件加速功能的虚拟机，并驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源。
  16. 如权利要求15所述的云操作系统，其特征在于，所述云操作系统还包括：发送接口，用于在接收到所述虚拟机分配请求之后，向硬件加速器资源管理模块发送资源分配请求，所述资源分配请求用于请求虚拟化的硬件加速器资源；
    所述接收接口还用于接收所述硬件加速器资源管理模块发送的第一通知消息，所述第一通知消息表征所述硬件加速器资源管理模块完成对虚拟化的硬件加速器资源的分配；
    所述处理器用于：利用已分配的虚拟化的硬件加速器资源，分配符合所述数量的所述支持硬件加速功能的虚拟机；
    在完成分配符合所述数量的所述支持硬件加速功能的虚拟机之后，所述发送接口还用于向硬件加速器资源驱动模块发送资源驱动请求，所述资源驱动请求用于请求驱动已分配的虚拟化的硬件加速器资源；
    所述接收接口还用于接收所述硬件加速器资源驱动模块发送的第二通知消息，所述第二通知消息表征所述硬件加速器资源驱动模块完成对所述已分配的虚拟化的硬件加速器资源的驱动。
  17. 如权利要求15或16所述的云操作系统，其特征在于，所述处理器还用于：
    配置用于调用虚拟化的硬件加速器资源的应用程序接口API，所述API用于所述虚拟网元调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理。
  18. 一种处理业务的方法，其特征在于，所述方法应用于虚拟网元，所述方法包括：
    所述虚拟网元确定待处理业务是需要进行硬件加速处理的业务；
    所述虚拟网元向云操作系统发送虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟化的硬件加速器资源的指示信息；
    所述虚拟网元接收所述云操作系统发送的第三通知消息，所述第三通知消息表征所述云操作系统已经分配出符合所述需求量的所述支持硬件加速功能的虚拟机，并已驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源；
    所述虚拟网元通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理。
  19. 如权利要求18所述的方法，其特征在于，在所述虚拟网元向云操作 系统发送虚拟机分配请求之前，所述方法还包括：
    所述虚拟网元接收管理和编排MANO模块发送的虚拟网络功能描述VNFD模板，所述VNFD模板包括至少一种虚拟机VM模板和所述虚拟网元的业务处理能力；
    所述虚拟网元从所述至少一种VM模板中确定出所述支持硬件加速功能的VM模板；
    所述虚拟网元确定所述支持硬件加速功能的虚拟机的业务处理能力，所述支持硬件加速功能的虚拟机是按照所述支持硬件加速功能的VM模板配置的；
    所述虚拟网元根据所述支持硬件加速功能的虚拟机的业务处理能力和所述虚拟网元的业务处理能力，确定所述支持硬件加速功能的虚拟机的数量。
  20. 如权利要求18或19所述的方法，其特征在于，所述虚拟网元通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理，包括：
    所述虚拟网元通过应用程序接口API调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理，所述API是用于调用虚拟化的硬件加速器资源的接口。
  21. 一种虚拟网元，其特征在于，所述虚拟网元包括：
    处理器、发送接口、接收接口；
    所述处理器用于：确定待处理业务是需要进行硬件加速处理的业务；
    所述发送接口用于：向云操作系统发送虚拟机分配请求，所述虚拟机分配请求携带支持硬件加速功能的VM模板和支持硬件加速功能的虚拟机的数量，所述支持硬件加速功能的VM模板包含虚拟化的硬件加速器资源的指示信息；
    所述接收接口用于：接收所述云操作系统发送的第三通知消息，所述第三通知消息表征所述云操作系统已经分配出符合所述需求量的所述支持硬件 加速功能的虚拟机，并已驱动为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源；
    所述处理器还用于：通过运行所述支持硬件加速功能的虚拟机对所述待处理业务进行硬件加速处理。
  22. 如权利要求21所述的虚拟网元，其特征在于，所述接收接口用于：接收管理和编排MANO模块发送的虚拟网络功能描述VNFD模板，所述VNFD模板包括至少一种虚拟机VM模板和所述虚拟网元的业务处理能力；
    所述处理器用于：从所述至少一种VM模板中确定出所述支持硬件加速功能的VM模板；确定所述支持硬件加速功能的虚拟机的业务处理能力，所述支持硬件加速功能的虚拟机是按照所述支持硬件加速功能的VM模板配置的；根据所述支持硬件加速功能的虚拟机的业务处理能力和所述虚拟网元的业务处理能力，确定所述支持硬件加速功能的虚拟机的数量。
  23. 如权利要求21或22所述的虚拟网元，其特征在于，所述处理器用于：
    通过应用程序接口API调用为所述支持硬件加速功能的虚拟机配置的虚拟化的硬件加速器资源，并通过被调用的虚拟化的硬件加速器资源对待处理业务进行硬件加速处理，所述API是用于调用虚拟化的硬件加速器资源的接口。
PCT/CN2015/097290 2015-12-14 2015-12-14 一种处理业务的方法及系统 WO2017100981A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2015/097290 WO2017100981A1 (zh) 2015-12-14 2015-12-14 一种处理业务的方法及系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2015/097290 WO2017100981A1 (zh) 2015-12-14 2015-12-14 一种处理业务的方法及系统

Publications (1)

Publication Number Publication Date
WO2017100981A1 true WO2017100981A1 (zh) 2017-06-22

Family

ID=59055582

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/097290 WO2017100981A1 (zh) 2015-12-14 2015-12-14 一种处理业务的方法及系统

Country Status (1)

Country Link
WO (1) WO2017100981A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115629876A (zh) * 2022-10-19 2023-01-20 慧之安信息技术股份有限公司 一种基于可扩展硬件加速的智能视频处理方法和系统
WO2024027515A1 (zh) * 2022-08-05 2024-02-08 中国移动通信有限公司研究院 一种信息传输方法、装置、云平台、网元和存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110010721A1 (en) * 2009-07-13 2011-01-13 Vishakha Gupta Managing Virtualized Accelerators Using Admission Control, Load Balancing and Scheduling
CN103428582A (zh) * 2013-09-02 2013-12-04 贝壳网际（北京）安全技术有限公司 播放视频的方法、装置和客户端
CN103797462A (zh) * 2013-10-23 2014-05-14 华为技术有限公司 一种创建虚拟机的方法和装置
CN104050045A (zh) * 2014-06-27 2014-09-17 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
CN104951353A (zh) * 2014-03-28 2015-09-30 华为技术有限公司 一种对vnf实现加速处理的方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110010721A1 (en) * 2009-07-13 2011-01-13 Vishakha Gupta Managing Virtualized Accelerators Using Admission Control, Load Balancing and Scheduling
CN103428582A (zh) * 2013-09-02 2013-12-04 贝壳网际（北京）安全技术有限公司 播放视频的方法、装置和客户端
CN103797462A (zh) * 2013-10-23 2014-05-14 华为技术有限公司 一种创建虚拟机的方法和装置
CN104951353A (zh) * 2014-03-28 2015-09-30 华为技术有限公司 一种对vnf实现加速处理的方法及装置
CN104050045A (zh) * 2014-06-27 2014-09-17 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

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024027515A1 (zh) * 2022-08-05 2024-02-08 中国移动通信有限公司研究院 一种信息传输方法、装置、云平台、网元和存储介质
CN115629876A (zh) * 2022-10-19 2023-01-20 慧之安信息技术股份有限公司 一种基于可扩展硬件加速的智能视频处理方法和系统

Similar Documents

Publication Publication Date Title
US10698717B2 (en) Accelerator virtualization method and apparatus, and centralized resource manager
US11029990B2 (en) Delivering a single end user experience to a client from multiple servers
US10810045B2 (en) Method and apparatus for allocating central processing unit (CPU) resources in a default resource pool
US9959139B2 (en) Partitioning processes across clusters by process type to optimize use of cluster specific configurations
US9069438B2 (en) Allocating virtual machines according to user-specific virtual machine metrics
US10708232B2 (en) Techniques for communication in hybrid cloud system
US11210121B2 (en) Management of advanced connection state during migration
WO2015196931A1 (zh) 基于磁盘io的虚拟资源分配方法及装置
US10120705B2 (en) Method for implementing GPU virtualization and related apparatus, and system
US10489207B2 (en) System for resource management using performance specification and description information of the process
EP3913859A1 (en) Vnf life cycle management method and apparatus
US10897428B2 (en) Method, server system and computer program product for managing resources
US11201836B2 (en) Method and device for managing stateful application on server
US9507624B2 (en) Notification conversion program and notification conversion method
US10164835B2 (en) Accessing peripheral devices from a container within virtual machines running on different host computing systems
EP3000024A1 (en) Dynamically provisioning storage
WO2017100981A1 (zh) 一种处理业务的方法及系统
CN113424149A (zh) 跨虚拟机边界的低时延事件
WO2018057165A1 (en) Technologies for dynamically transitioning network traffic host buffer queues
US11720309B2 (en) Feature-based flow control in remote computing environments
US9668082B2 (en) Virtual machine based on a mobile device
US9792139B2 (en) Service driven virtual machine scheduling

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: 15910454

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15910454

Country of ref document: EP

Kind code of ref document: A1