WO2024041572A1 - 业务处理方法、装置、设备、介质及程序产品 - Google Patents
业务处理方法、装置、设备、介质及程序产品 Download PDFInfo
- Publication number
- WO2024041572A1 WO2024041572A1 PCT/CN2023/114474 CN2023114474W WO2024041572A1 WO 2024041572 A1 WO2024041572 A1 WO 2024041572A1 CN 2023114474 W CN2023114474 W CN 2023114474W WO 2024041572 A1 WO2024041572 A1 WO 2024041572A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- computing
- computing power
- business
- processed
- sfs
- Prior art date
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 134
- 230000008569 process Effects 0.000 claims abstract description 46
- 238000012545 processing Methods 0.000 claims description 87
- 230000006870 function Effects 0.000 claims description 85
- 238000004590 computer program Methods 0.000 claims description 8
- 230000014509 gene expression Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 claims 1
- 230000007246 mechanism Effects 0.000 abstract description 6
- 101000823089 Equus caballus Alpha-1-antiproteinase 1 Proteins 0.000 description 29
- 101000651211 Homo sapiens Transcription factor PU.1 Proteins 0.000 description 29
- 102100027654 Transcription factor PU.1 Human genes 0.000 description 29
- 101000823106 Equus caballus Alpha-1-antiproteinase 2 Proteins 0.000 description 10
- 101000823108 Equus caballus Alpha-1-antiproteinase 3 Proteins 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 230000015556 catabolic process Effects 0.000 description 5
- 238000006731 degradation reaction Methods 0.000 description 5
- 230000008447 perception Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000007774 longterm Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013468 resource allocation Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000004808 supercritical fluid chromatography Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5066—Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
Definitions
- the present invention relates to the technical field of cloud computing business service chain, and in particular, to a business processing method, device, equipment, medium and program product.
- each supported service can be modeled as a combination of one or more service functions (SFs), where the role of each service function is to perform specific operations on network data packets or data packet collections.
- SFs service functions
- Task For a given business, business functions are applied sequentially, that is, network traffic is directed through these business functions in a specified manner. This technique is called business function chaining, and these chains are often called service function chaining (SFC).
- the business function chain (including the business functions included in the business function chain) is determined by static configuration. If a computing power bottleneck or failure occurs in a certain SF during the processing of data packets through the business function chain, the chain needs to be reorganized and changed from the beginning to bypass the problematic business function. In order to reduce the load of the specific SF, it is necessary to Adjusting an SFC is expensive and lacks flexibility.
- the present disclosure provides a business processing method, device, equipment, medium and program product, which can at least overcome the problem to a certain extent in related technologies.
- a computing power bottleneck or failure occurs in a certain SF, the chain needs to be re-arranged and changed from scratch, which costs a lot of money. , the problem of lack of flexibility.
- a business processing method including: determining the computing power resource parameters corresponding to the business to be processed according to the business to be processed at the interface of the business function chain SFC; the computing power The resource parameter is at least one parameter corresponding to the computing resource that needs to be used when the service to be processed is processed by one or more business functions SF in the SFC; according to the computing resource parameter, the one or more Multiple SFs perform pre-occupation operations on the computing resources within the computing resource occupancy period to determine the allocation method of the computing resources that the to-be-processed business needs to use during the computing resource occupancy period; the routing protocol is used to The allocation method is delivered to the one or more SFs, so that the one or more SFs process the to-be-processed services according to the allocation method.
- the computing resource parameters include at least one of the following: computing resource occupancy period, SFC service path identifier SPI number, target SF index address, the amount and duration of memory occupied by SF within the computing resource occupancy period. , the number of jobs processed by the central processing unit CPU, estimated median, CPU time/each job, and memory output.
- determining the computing resource parameters corresponding to the to-be-processed services based on the to-be-processed services received at the interface of the service function chain SFC includes: extending the computing power resource parameters according to the routing protocol, and deliver the computing power resource parameters to the one or more SFs, so that the one or more SFs upload computing power resource information according to the computing power resource parameters; the computing power resource parameters are When processing business, the computing power resources that need to be used are expressed in the form of parameters; the computing power resource information is the one or When multiple SFs process services, the returned computing resource usage/remaining available computing resources are determined based on the computing resource parameters; based on the business to be processed and the computing resource information, the computing resource information is determined. Computing resource parameters corresponding to the business to be processed.
- the method of extending computing resource parameters includes: extending the routing protocol through a protocol message body TLV or a probe request option.
- a pre-occupation operation is performed on the computing resources of the one or more SFs within the computing resource occupancy period, and it is determined that the business to be processed is in the computing resource occupancy period.
- the method of allocating computing power resources that need to be used within the power resource occupation period includes: if all the computing power resource parameters corresponding to the to-be-processed business are allocated to the one or more SFs, and no overload signal is received, then the The computing power resources that the to-be-processed business needs to use within the computing power resource occupation period are allocated and the allocation method is determined; or, during the pre-occupation operation, an overload signal fed back by any SF is received.
- the overload signal is that the pre-occupied computing power resources of any one SF during the computing power resource occupation period are greater than the preset computing power
- the signal generated by the resource threshold perform a pre-occupation operation on the computing resources of the SF that has the same business function as any of the SFs until the computing resources that the to-be-processed business needs to use within the computing resource occupancy period are allocated Completed and no overload signal is received, determine the allocation method.
- the method further includes: configuring remaining computing power resource indication information according to the to-be-processed service received at the interface of the service function chain SFC; the remaining computing power resource indication information is to indicate the remaining computing power resource indication information in the SFC.
- the remaining computing power resources of the SF within the computing power resource occupation period are returned in real time; configure computing power resource adjustment indication information; wherein, the computing power resource adjustment The instruction information instructs the transponder to adjust the time for processing the to-be-processed service based on the remaining computing power resources of the SF within the computing resource occupation period returned in real time when the one or more SFs are processing the to-be-processed service.
- Instruction information of SF deliver the computing power resource adjustment indication information to the forwarder, and deliver the remaining computing power resource indication information to the one or more SFs through a routing protocol, so that all The one or more SFs and the forwarder process the to-be-processed services.
- the method further includes: configuring remaining computing resource indication information;
- the remaining computing power resource indication information indicates that one or more SFs in the SFC return in real time the remaining computing power resources of the SF within the computing power resource occupancy period when processing the to-be-processed business; configure computing power resources Adjustment instruction information; wherein the computing power resource adjustment instruction information is an instruction to the forwarder to return in real time the remaining SF within the computing resource occupancy period according to the one or more SFs when processing the to-be-processed service.
- Computing power resources adjust the instruction information of the SF that processes the to-be-processed business; deliver the allocation method to the one or more SFs through a routing protocol, including: delivering the computing power resource adjustment instruction information to the forwarder, and deliver the allocation method and the remaining computing power resource indication information to the one or more SFs through a routing protocol, so that the one or more SFs and the forwarder Process the pending business.
- an embodiment of the present disclosure provides a service processing device, including: a determining unit configured to determine the to-be-processed service according to the to-be-processed service received at the interface of the service function chain SFC.
- Corresponding computing power resource parameters; the computing power resource parameters are at least one parameter corresponding to the computing power resources that need to be used when the business to be processed is processed by one or more business functions SF in the SFC; pre-occupation A unit configured to perform a pre-occupation operation on the computing resources of the one or more SFs within the computing resource occupancy period according to the computing resource parameters, and determine the computing power resource occupancy period of the to-be-processed service.
- the allocation method of the computing power resources that need to be used in the system is configured to deliver the allocation method to the one or more SFs through the routing protocol, so that the one or more SFs can be allocated according to the allocation method. method to process the pending business.
- an embodiment of the present disclosure provides an electronic device, including: a processor; and A memory configured to store executable instructions of the processor; wherein the processor is configured to perform the method as described above via execution of the executable instructions.
- a computer-readable storage medium stores computer instructions, and the instructions are executed by a processor as described above.
- a computer program product including a computer program that implements the above method when executed by a processor.
- a business processing method, device, equipment, medium and program product provided by the embodiment of the present disclosure determines the computing resource parameters corresponding to the business to be processed based on the business to be processed received at the interface of the business function chain SFC;
- the computing power resource parameter is at least one parameter corresponding to the computing power resource that needs to be used when the business to be processed is processed by one or more business functions SF in the SFC.
- the computing power of one or more SFs is The computing resources within the resource occupancy period are pre-occupied, determine the allocation method of the computing resources that the to-be-processed business needs to use during the computing resource occupancy period, and deliver the allocation method to one or more SFs through the routing protocol.
- the computing resources of each SF are allocated in advance, and a new mechanism is introduced on the controller, which not only enables SFC to control computing resources
- the computing resource parameters of the accessed services to be processed can be determined.
- SF can be constrained according to the computing resources required by SFC, and the existing service paths can be identified through resource identifiers.
- the Service Path Identifier (SPI) processing pipeline is partially and flexibly adjusted to adapt to the differentiated needs of computing power performance and improve the overall utilization efficiency of the business chain SF.
- SPI Service Path Identifier
- the remaining computing power resource indication information is configured according to the pending business received at the interface of the business function chain SFC; the remaining computing power resource indication information indicates that one or more SFs in the SFC are pending processing.
- the remaining computing power resources of the SF within the computing power resource occupation period are returned in real time, and the computing power resource adjustment indication information is configured; wherein the computing power resource adjustment indication information is to instruct the forwarder according to one or more SFs to be processed.
- the remaining computing power resources of the SF within the computing resource occupation period are returned in real time, the instruction information of the SF for processing the pending business is adjusted, the computing power resource adjustment instruction information is sent to the forwarder, and the SF is sent to the forwarder through the routing protocol.
- the remaining computing power resource indication information is delivered to one or more SFs, so that one or more SFs and forwarders can process the to-be-processed services.
- each SF can independently refresh the branch processing logic of the local SFC in real-time feedback to the forwarder during the process of processing the pending business, without the need to re-register frequently.
- the load of SFs with high computing power overhead can be offloaded to other SFs, which can reduce the cost of rearranging SFC paths.
- each SF and transponder can also instruct each SF and transponder to process the pending business through computing resource pre-occupation and real-time feedback, effectively improving the application efficiency and scenario adaptability of SFC technology.
- Figure 1 shows one of the application scenarios of a business processing method in an embodiment of the present disclosure
- Figure 2 shows the second application scenario of a business processing method in the embodiment of the present disclosure
- Figure 3 shows one of the schematic flow diagrams of a business processing method in an embodiment of the present disclosure
- Figure 4 shows the third application scenario of a business processing method in the embodiment of the present disclosure
- Figure 5 shows a schematic representation of periodic computing resources in an embodiment of the present disclosure
- Figure 6 shows the second schematic flowchart of a business processing method in an embodiment of the present disclosure
- Figure 7 shows the fourth application scenario of a business processing method in the embodiment of the present disclosure
- Figure 8 shows a schematic structural diagram of an SFC computing power network in an embodiment of the present disclosure
- Figure 9 shows the third schematic flowchart of a business processing method in an embodiment of the present disclosure.
- Figure 10 shows a schematic structural diagram of a business processing device in an embodiment of the present disclosure
- Figure 11 shows a schematic structural diagram of an electronic device in an embodiment of the present disclosure.
- Example embodiments will now be described more fully with reference to the accompanying drawings.
- Example embodiments may, however, be embodied in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concepts of the example embodiments. To those skilled in the art.
- the described features, structures or characteristics may be combined in any suitable manner in one or more embodiments.
- SFC service function path
- the present disclosure provides a business processing method that determines the computing resource parameters corresponding to the business to be processed based on the business to be processed received at the interface of the business function chain SFC; the computing power resource parameters are used to represent the business to be processed in the SFC.
- the computing power resource parameters are used to represent the business to be processed in the SFC.
- the computing power resource parameters the computing power resources of one or more SFs within the computing power resource occupancy period are pre-occupied. Determine the allocation method of the computing resources that the business to be processed needs to use during the computing resource occupation period, and issue the allocation method to one or more SFs through the routing protocol, so that one or more SFs can use the allocation method to process the business. for processing.
- the introduction of new mechanisms can not only realize SFC's perception of computing resources and determine the computing resource parameters of the accessed services to be processed, but also enable SFC to sense computing resources. Pre-occupy the computing resources of each SF in the SFC in advance, determine the allocation method of computing resources for the business to be processed, effectively utilize the SFC processing resources, improve the service quality and service availability of the SFC from the network level, and improve the expansion of the business chain. performance and SF computing power utilization.
- Figure 1 shows an application scenario of a business processing method provided by an embodiment of the present disclosure.
- SFC computing power network 100 includes: a controller 101, a forwarder (Service Function Forwarder, SFF) 102, a classifier 103, and a series of SFs.
- SFF Service Function Forwarder
- SFC includes a series of business functions (or business function instances) residing on each network node.
- SFC defines a series of SFs and processing sequences that need to be processed after business classification. It can support Various routing protocols (Underlay) such as IPv4, IPv6, SFC, mpls, vxlan, etc.
- the SFC may include one or more service function paths (Service Function Paths, SFPs) along the SFC.
- the packets in the traffic traverse the SFP in order and are processed by various business functions, where each business function applies a specific function, such as firewall, Network access conversion (Network Access Translation, NAT), Deep Packet Inspection (DPI), etc., and then forward the data packet to the next network node.
- a specific function such as firewall, Network access conversion (Network Access Translation, NAT), Deep Packet Inspection (DPI), etc.
- the controller 101 may be configured to determine a path for processing the pending business. For example, Service Function Path (SFP). It can also be configured to monitor the status information of the classifier 103, the forwarder 102 and a series of SFs. It may also be configured to establish the determined path into the classifier 103 and the forwarder 102 . It can also be set to manage the processing method of pending business according to various policies or agreed services.
- SFP Service Function Path
- the classifier 103 is set to add a network service header NSH to the message corresponding to the service to be processed, the service path identifier SPI and service index (Service Index, SI) information included in the marked service function path SFP information, and transfer it to the forwarder 102.
- NSH Network Service header
- SI Service Index
- the forwarder 102 is responsible in the SFC for guiding traffic in and out of a series of service functions SF or other network elements processed by the forwarder 102 in a defined order according to the encapsulated SFC new message.
- SF can be a physical or virtual network element with limited processing capabilities.
- the processing capabilities can be understood as computing power, IO, storage, bandwidth, etc.
- SF can be expanded when the processing capacity for processing business is insufficient.
- the NSH header needs to be processed through a proxy device (Proxy).
- SPI uniquely marks a business chain path. After the SPI is determined, the forwarder 102 determines which SF the data needs to be forwarded to based on the service index, forwards it based on the specific next hop address queried, and traverses the predetermined and fixed sequence of serial SF business function groups for processing. It is difficult to flexibly adjust according to the actual computing power load of SF.
- the controller 101 in the SFC when the controller 101 in the SFC receives the pending business through the interface, it issues three sets of packet classification policies to the classifier 103 of the user traffic entrance, corresponding to SPI1 and SPI2 respectively. , SPI3 business function chain processing.
- 1 in Figure 1 represents SPI1
- 2 represents SPI2
- 3 represents SPI3. Traverse the corresponding set of SFs in descending order according to the SI value corresponding to the SPI number.
- the controller 101 needs to obtain the SF 3.1 performance overload signal through the virtualization infrastructure manager or the host performance monitoring system, and confirm that SF3.1 has no expansion resources. Then, the controller 101 finds that SF3.2 and SF3.1 are functionally consistent and available. The controller 101 selects to cancel the service chain SPI1 passing through SF3.1 according to the load condition of each SFC, and re-arranges the SPI1 path through SF3.2.
- the adjusted SPI1 is shown in Figure 2.
- SFC cannot sense the computing power information of the business to be processed, generally when some computing power resources experience bottlenecks or overloading, the degradation of service quality will be measured through the monitoring system, and multiple factors such as network and computing power need to be eliminated. factor. SFC cannot independently adjust the SPI pipeline based on computing power. It needs to rebuild the business function chain through head-end dismantling and reconstruction, and offload the overloaded services of SF3.1 to SF3.2.
- embodiments of the present disclosure provide a business processing method, which can be executed by any electronic device with computing processing capabilities.
- the electronic device is used as a server as an example.
- Figure 3 shows a flow chart of a business processing method in an embodiment of the present disclosure.
- the business processing method provided in an embodiment of the present disclosure includes the following steps:
- S302 Determine the computing resource parameters corresponding to the business to be processed based on the business to be processed received at the interface of the service function chain SFC.
- the computing power resource parameter is at least one parameter corresponding to the computing power resource that needs to be used when the business to be processed is processed by one or more business functions SF in the SFC.
- the computing power resource occupation period is the preset period for the controller to occupy the computing power resources of SF during the process of configuring the policy. For example, if the to-be-processed business starts processing at 5:30, the controller may occupy the computing power resources of the SF during the period from 5:30 to 5:31. This period of time can be expressed as the computing power resource occupancy period.
- the computing resource parameters are determined as follows:
- the computing resource parameters are one or more When multiple SFs are processing services, the computing resources corresponding to the services to be processed are determined based on the computing resource parameters, the usage of the returned computing resources/remaining available computing resources, the business to be processed, and the computing resource information. parameter.
- the computing power resource parameter is a way of expressing the computing power resources that need to be used when processing the business in the form of parameters.
- Methods of extending computing resource parameters include: routing protocols are extended through protocol message body TLV or probe request options. SFC's routing protocol extends computing resource parameters through TLV or option.
- the SFC controller can When the processing business is subsequently received, the received business to be processed can be expressed in the form of computing resource parameters based on the computing resource information, so that the SFC computing network can have a specific perception of the computing power.
- the SF injects the computing resource information of the SF into the SFC routing protocol, which may include: available resource data of the VNF, VM or host where the SF is located.
- the above computing resource information can be distributed to the controller, forwarder or classifier through the SFC routing protocol, and the controller can also receive it through the BGP LS or restful interface.
- S304 According to the computing resource parameters, pre-occupy the computing resources of one or more SFs within the computing resource occupancy period, and determine the allocation method of the computing resources that need to be used by the to-be-processed business during the computing resource occupancy period. .
- the business processing method provided by the embodiment of the present disclosure is explained by taking SPI1, SPI2, and SPI3 existing in Figure 1 as an example. They are all situations where SPI1, SPI2, and SPI3 process to-be-processed services, but another SFC computing power network 200 is shown in FIG. 4 .
- the SFC computing power network 200 includes a controller 201, a forwarder 202, a classifier 203, and a series of SFs.
- the computing resource parameters in the above content may include: computing resource occupancy period, SFC service path identifier SPI number, target SF index address, the amount and duration of memory occupied by SF during the computing resource occupancy period, central processing unit CPU processing Number of jobs, estimated median, CPU time/each job, memory output.
- Figure 5 shows a schematic representation of periodic computing resources. These include the amount of memory - duration, median CPU time, number of requests, etc.
- the specific processing includes:
- the controller in the SFC computing power network determines the computing resource parameters of the business to be processed.
- the controller can mark that an SFC is expected to occupy the computing power resources of one or more SFs in a fixed period, and can calculate the computing power resources of one or more SFs.
- the computing resources within the resource occupation period are pre-occupied.
- the controller directly publishes the computing resource parameters to SF through the routing protocol to perform the pre-occupation operation.
- the controller sends the computing power resource parameters to each SF to pre-occupy the computing power resources of the SF.
- the computing power resources of SF involved in SPI1 are pre-occupied.
- the process of pre-occupation may include the following two situations, as follows:
- the overload signal is a signal generated by any SF when the pre-occupied computing resources are greater than the preset computing resource threshold during the computing resource occupation period.
- the overload signal includes information about which computing resource occupies the period of insufficient computing resources.
- SF3.1 is likely to have insufficient computing resources because the computing resources have been occupied by SPI2 and SPI3 during the computing resource occupation period. Therefore, the controller can receive the overload signal sent back by SF3.1 .
- the SF can send out an overload period or an overload signal.
- the controller After the SF has finished occupying the computing resources within the computing resource occupation period, the SF can send out an overload period or an overload signal. After the controller receives the overload signal, it will not continue to occupy or add new services to the SF. It can be understood that the controller will not allocate a new business function path SFP to this SF.
- the controller of the SFC computing power network can allocate the computing power resources of the pending services originally occupied in SF3.1 to SF3.2. And determine the specific computing resource allocation method. Since the controller marks the business function chain with the service path identifier SPI1, it can be determined that the allocation method of SPI1 has changed due to the overload of SF3.1.
- S306 Deliver the allocation method to one or more SFs through the routing protocol, so that one or more SFs process the to-be-processed services according to the allocation method.
- the controller can send the determined allocation method to the forwarder, classifier, and each SF involved in SPI1 through the routing protocol, and notify each SF of the specific computing resource occupation period. , as well as the specific computing resource parameters of the business to be processed, so that each SF reserves the computing power resources that have been pre-occupied by the controller during the computing resource occupation cycle to process the business to be processed.
- the entire pre-occupation process has no impact on SPI2 and SPI3.
- S4 is the SF3.1 direction control step.
- the overload signal returned by the controller.
- the controller determines SF3.2 that has the same business functions as SF3.1, and performs a pre-occupation operation on SF3.2 to allocate the computing resources required for the business to be processed. It is pre-allocated to SF3.2, the allocation method is finally determined, and the determined allocation method is sent to the classifier and forwarder and each SF for processing of the pending business.
- the various situations in Figure 4 are not redundantly described.
- the over-limit occupation and deficit repayment of computing resources are allowed in adjacent periods. That is to say, it can be understood as: If there is surplus computing power resources in a certain computing resource occupancy period, the computing power resources of this computing resource occupancy period can be occupied in advance, and the computing power resources in the subsequent computing resource occupancy period can be occupied. The pending business is processed in advance.
- the SFC computing power network senses the computing power resources, effectively determines the computing power resource parameters, and pre-occupies the computing power resources of each SF. Under the premise of clock synchronization, it can effectively It is ensured that during the process of SF processing the pending business, SF's computing resources will not be overloaded and the business chain can work normally to complete the processing of the pending business.
- This method can be called an explicit SFC computing power strategy, which is established through the controller in the SFC computing power network and distributed to each SF, forwarder and classifier involved in the business function chain through the routing protocol. Moreover, this explicit SFC computing power strategy is issued through the routing protocol, and the entire process is notified to each SF through communication. It does not change the original SFC mechanism, and does not change the controller and classifier to be processed. The processing of data packets or data packet collections where the business is located.
- any SF when in the SFC computing power network, the controller needs to pre-occupy multiple business function chains for the SF, and each business function chain corresponds to an allocation method, all services
- the corresponding business function chain can be identified based on the SF involved in the function chain.
- the SF can identify which business function chain occupies the SF in which computing resource occupancy period, and which computing resource occupancy period other business function chains occupy.
- the SF is occupied by the resource occupation cycle, and any SF can identify the business function chain.
- the communication between the controller and SF requires the SF to have publishing capabilities, receiving capabilities and recognition capabilities.
- the publishing capability is the ability of SF to publish computing resource information and publish overload signals according to routing protocols.
- Receiving capability is the ability to receive information through routing protocols.
- the identification capability is that for any SF, it can identify which business function chain passes through the SF at this time, and determine the business performed by this business function chain in the SF and the pre-occupied computing resources, etc. For non-computing power-aware network elements, information can be transparently transmitted.
- SFs with the above capabilities can register with network elements such as OVS/vswitch routing, and regularly publish SFC-independent computing power information to intra-domain routing protocols according to the mode specified by the computing power policy.
- the present disclosure provides an implicit SFC computing power strategy in addition to the explicit SFC computing power strategy in the above business processing method, as shown in Figure 6.
- Figure 6 includes the following step:
- the remaining computing power resource indication information indicates the remaining computing power resources of one or more SFs in the SFC within the computing resource occupation period returned in real time when processing pending services.
- the computing power resource adjustment instruction information instructs the forwarder to adjust the SF for processing the pending business based on the remaining computing power resources of the SF within the computing resource occupation period returned in real time when one or more SFs are processing the pending business. Instructions.
- S606 Send the computing power resource adjustment instruction information to the forwarder, and send the remaining computing power resource instruction information to one or more SFs through the routing protocol, so that the one or more SFs and the forwarder can complete the to-be-processed services. deal with.
- the process of adjusting the computing power of the SPI1 path through the implicit SFC computing power policy is shown in Figure 7.
- the controller When the controller receives the pending service at the interface, it configures the service function chain normally. base On the basis of this, configure the remaining computing power resource indication information to instruct one or more SFs in the SFC to return the remaining computing power resources of the SF within the computing power resource occupation period to the controller or forwarder in real time when processing the pending business. That is, it can be understood as causing SF to publish the remaining computing power resource percentage information within the computing power resource occupancy period. Each SF can also be instructed to return information on the percentage of occupied computing resources in the computing resource occupancy period in real time.
- the computing power resource adjustment instruction information is an instruction transponder.
- normal logic can be executed. If the remaining computing power resources sent by SF are received, When the computing power resources do not meet the computing resource constraints, you need to report or stop sending new pending services to the SF, or search based on the address of the SF to see if there is an SF with the same business function as the SF. You can New pending services originally forwarded to the SF are sent to the SF with the same service function as the SF.
- the above computing power resource constraints can be that the remaining computing power resources of SF are greater than or equal to 15%, etc. This set computing power resource can set different thresholds according to different periods to meet the processing needs of the business function chain to be processed.
- the controller configures the computing power resource adjustment instruction information and sends it to the forwarder, so that after receiving the remaining computing power resources of the SF, the forwarding device can balance and adjust the computing power resources of the SF according to the remaining computing power resources. For example, when SF3.1 is in a certain period, it processes the pending business and returns the remaining computing power resources to the forwarder in real time. If the forwarder receives 5% of the remaining computing power resources sent by SF3.1, it can autonomously Perform equalization.
- each SF refers to the dotted line of the forwarder, indicating that the remaining computing power resources are uploaded to the forwarder.
- the forwarder After the forwarder receives the remaining computing power resources of each SF, it can calculate the remaining computing power resources according to the remaining computing power. resources for further processing.
- SF3.1 when the remaining computing power resources of SF3.1 are already 5%, but the controller allocates new pending services to SF3.1, the processing overhead of SF3.1 in SPI1 increases.
- SF3 .1, SF3.2 adopts equivalent addresses and adjusts the instruction information according to the computing power resources received by the transponder.
- the transponder When the remaining computing power resources issued by SF3.1 are not enough to meet the computing power resource constraints, the transponder will not control the subsequent Other pending services assigned to SF3.1 by the server are distributed to SF3.1, and services already being processed by SF3.1 are gradually adjusted to SF3.2 for processing.
- the pending services of SF3.1 in SPI1 are gradually offloaded to SF3.2 until SF3.1 provides services to SF3.1 within a certain period.
- the remaining computing power resources sent by the forwarder satisfy the computing power resource constraints.
- the controller did not actually issue instructions to adjust the SPI1 path, nor did it reconfigure the new SPI path, and because SF3.1 and SF3.2 use equivalent addresses. Therefore, for the entire SFC computing network, the SPI1 path has not been actually adjusted. Only the forwarder used the computing resources of SF3.2 for incremental deployment when the computing resources of SF3.1 were insufficient. SPI1 , SPI2 and SPI3 are not affected, and SF3.1 and 3.2 computing resources are normal.
- the SPI1 path is adjusted from SF3.1 to SF3.2, and the pending services are processed through SF3.2.
- the dotted line 1 represents the original SPI1 path, and the solid line 1 represents the SPI1 path after adjustment by the transponder.
- the controller after receiving the service to be processed, configures the SPI path of the service to be processed through the existing method and sends it to the classifier, so that the SF involved in the SPI path processes the service to be processed.
- the implicit SFC computing power strategy can essentially be understood as giving special instructions to the forwarder and each SF through the routing protocol during the normal processing of the business to be processed, so that the forwarder can manage and manage SPI traffic. Load balance each SF.
- the SF computing power overload situation existing in the SFC computing power network can be handled at the transponder through the above-mentioned implicit SFC computing power strategy, without the need for additional adjustment of the SPI path, reducing the cost of Instantaneous/long-term fluctuations in SF computing power resources cause SFC quality degradation and end-to-end SPI reconstruction requirements, which improves the stability of the business chain and enhances the affinity between computing power and the SFC network.
- SFC computing power network 200 can Proxy for pending business.
- SFC computing power network 200 can be divided into a control plane and a forwarding plane.
- the control plane includes a controller 201
- the forwarding plane includes a forwarder 202, a classifier 203, and a series of SFs.
- the controller 201 includes a topology information module 2011, a path calculation module 2012, a computing power policy configuration module 2013, and a routing computing power expansion module 2014.
- the path calculation module 2012 is mainly configured to configure a path for processing the business to be processed, and the path includes multiple SFs.
- the computing power policy configuration module 2013 is configured to configure the explicit SFC computing power policy and the implicit SFC computing power policy mentioned in the above content.
- the routing computing power expansion module 2014 is configured to receive the computing power resource information distributed by SF through the routing protocol, and publish the explicit SFC computing power strategy and implicit SFC computing power policy configured by the computing power policy configuration module 2013 through the routing protocol. And set to release computing power resource parameters and computing power resource constraints in the implicit SFC computing power policy.
- the forwarder 202 in the SFC computing power network 200 in the present disclosure can also be set to adjust the computing power resources according to the instruction information sent by the controller 201.
- the remaining computing power resources in SF are not enough to meet the computing power requirements.
- the traffic or job, request
- the traffic is offloaded to other SFs of the same function in proportion to the available computing power by adjusting the computing power weight of the routing protocol.
- Figure 9 shows a business processing method that jointly uses the above-mentioned explicit SFC computing power strategy and implicit SFC computing power strategy. As shown in Figure 9, it includes the following steps:
- S902 Determine the computing resource parameters corresponding to the to-be-processed services based on the to-be-processed services received at the interface of the service function chain SFC.
- S904 According to the computing resource parameters, pre-occupy the computing resources of one or more SFs within the computing resource occupancy period, and determine the allocation method of the computing resources that need to be used by the business to be processed during the computing resource occupancy period. .
- S910 Send the computing power resource adjustment indication information to the forwarder through the routing protocol, and deliver the allocation method and remaining computing power resource indication information to one or more SFs through the routing protocol, so that one or more SFs and The forwarder processes the pending business.
- the business processing method based on the business function chain in this disclosure introduces the capabilities of business function chain computing power perception, publishing and computing power policy execution, computing power routing, etc. into the existing SFC computing power network architecture, and adds new computing power resources. parameter. On the basis of maintaining the compatibility of the business function chain forwarder, it solves the problem of insufficient flexibility of the existing SFC computing power and improves the utilization of SF.
- Two SF computing power resource occupancy strategies and mechanisms, explicit and implicit, are provided based on time periods, which reduces SFC quality degradation and end-to-end SPI reconstruction requirements caused by instantaneous/long-term fluctuations in SF computing power resources, and improves the stability of the business chain. Enhanced the affinity between computing power and SFC network.
- the SFC business processing pipeline can be partially adjusted according to the implicit SFC computing power policy and the computing power resource constraints for SF without changing the entire SFC forwarding path.
- the methods of sensing computing power resources involved in this disclosure include receiving computing power resource information sent by SF, determining computing power resource parameters, etc., as well as publishing explicit SFC computing power strategies, implicit SFC computing power strategies, and publishing computing power resource constraints. Conditions, etc. are all published through routing protocols and processed through communication, without changing the existing SFC basic forwarding processing and agency mechanisms.
- embodiments of the present disclosure also provide a service processing device, such as the following embodiments. Since the problem-solving principle of this device embodiment is similar to that of the above-mentioned method embodiment, the implementation of this device embodiment can refer to the implementation of the above-mentioned method embodiment, and repeated details will not be repeated.
- Figure 10 shows a schematic structural diagram of a service processing device in an embodiment of the present disclosure.
- the service processing device 100 includes: a determining unit 1001, configured to determine the data to be received according to the interface of the service function chain SFC. Process the business and determine the computing resource parameters corresponding to the business to be processed; the computing resource parameters represent at least one parameter corresponding to the computing resources that need to be used when the business to be processed is processed by one or more business functions SF in the SFC; pre- The accounting unit 1002 is configured to pre-occupy the computing resources of one or more SFs within the computing resource occupancy period according to the computing resource parameters, and determine the computing power that the business to be processed needs to use during the computing resource occupancy period.
- Resource allocation method the delivery unit 1003 is configured to deliver the allocation method to one or more SFs through the routing protocol, so that one or more SFs process the to-be-processed services according to the allocation method.
- the determining unit 1001 is further configured to: expand the computing resource parameters according to the routing protocol, and deliver the computing resource parameters to one or more SFs, so that the one or more SFs can Computing resource parameters, upload computing resource information; computing resource parameters are the expression of the computing resources that need to be used in the form of parameters when processing services; computing resource information is when one or more SFs are processing services, According to the computing resource parameters, the returned computing resource usage/remaining available computing resources are determined; based on the business to be processed and the computing resource information, the computing resource parameters corresponding to the business to be processed are determined.
- the pre-emption unit 1002 is also configured to: if all the computing resource parameters corresponding to the to-be-processed service are allocated to one or more SFs, and no overload signal is received, the to-be-processed service is The computing resources that need to be used during the computing resource occupation period are allocated and the allocation method is determined; or, if an overload signal fed back by any SF is received during the pre-occupation operation, the computing resources of any SF will be stopped.
- the overload signal is a signal generated by any SF when the pre-occupied computing resources are greater than the preset computing resource threshold during the computing resource occupation period; the computing power of an SF with the same business function as any SF is The computing resources are pre-occupied until the computing resources required by the business to be processed during the computing resource occupation period are allocated and no overload signal is received, and the allocation method is determined.
- the business processing device 100 also includes: a balancing unit configured to configure remaining computing power resource indication information according to the to-be-processed service received at the interface of the business function chain SFC; the remaining computing power resource indication information is one of the indication SFC or When multiple SFs are processing pending services, the remaining computing power resources of the SFs within the computing resource occupation period are returned in real time; the computing power resource adjustment indication information is configured; wherein the computing power resource adjustment indication information is to instruct the forwarder to adjust the computing power according to one or When multiple SFs are processing pending business, the remaining computing power resources of the SF within the computing resource occupation period are returned in real time, and the instruction information of the SF processing the pending business is adjusted; the computing resource adjustment instruction information is sent to the forwarder. , and deliver the remaining computing power resource indication information to one or more SFs through the routing protocol, so that one or more SFs and forwarders can process the pending services.
- a balancing unit configured to configure remaining computing power resource indication information according to the to-be-
- the business processing device 100 further includes: a pre-occupancy balancing unit configured to configure remaining computing power resource indication information; the remaining computing power resource indication information indicates that one or more SFs in the SFC are processing When the business is to be processed, the remaining computing power resources of the SF within the computing resource occupation period are returned in real time; the computing power resource adjustment indication information is configured; wherein the computing power resource adjustment indication information is to instruct the forwarder to process according to one or more SFs.
- the business is pending, the remaining computing power resources of the SF within the computing resource occupation period are returned in real time, and the instruction information of the SF processing the pending business is adjusted; the allocation method is delivered to one or more servers through the routing protocol.
- each SF includes: delivering the computing power resource adjustment indication information to the forwarder, and delivering the allocation method and remaining computing power resource indication information to one or more SFs through the routing protocol, so that one or more SFs and forwarder to process the pending business.
- the examples and application scenarios implemented by the above-mentioned units and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned method embodiments. It should be noted that the above-mentioned modules, as part of the device, can be executed in a computer system such as a set of computer-executable instructions.
- FIG. 11 An electronic device 1100 according to this embodiment of the present disclosure is described below with reference to FIG. 11 .
- the electronic device 1100 shown in FIG. 11 is only an example and should not bring any limitations to the functions and scope of use of the embodiments of the present disclosure.
- electronic device 1100 is embodied in the form of a general computing device.
- the components of the electronic device 1100 may include, but are not limited to: the above-mentioned at least one processing unit 1110, the above-mentioned at least one storage unit 1120, and a bus 1130 connecting different system components (including the storage unit 1120 and the processing unit 1110).
- the storage unit stores program code, and the program code can be executed by the processing unit 1110, so that the processing unit 1110 performs various exemplary methods according to the present disclosure described in the "Example Method" section of this specification.
- Implementation steps for example, the processing unit 1110 can perform the following steps in the above method embodiment, for example: according to the to-be-processed service received at the interface of the service function chain SFC, determine the computing power resource parameters corresponding to the to-be-processed service; the computing power resource The parameter is at least one parameter corresponding to the computing resources that need to be used when the to-be-processed business is processed by one or more business functions SF in the SFC; according to the computing resource parameters, the computing resource occupancy period of one or more SFs is Perform pre-occupation operations on the computing resources within the computing resource occupancy period to determine the allocation method of the computing resources that need to be used by the business to be processed during the computing resource occupancy period; issue the allocation method to one or more SFs through the routing protocol, so that one Or multiple
- the storage unit 1120 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 11201 and/or a cache storage unit 11202, and may further include a read-only storage unit (ROM) 11203.
- RAM random access storage unit
- ROM read-only storage unit
- Storage unit 1120 may also include a program/utility 11204 having a set of (at least one) program modules 11205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, Each of these examples, or some combination, may include the implementation of a network environment.
- program/utility 11204 having a set of (at least one) program modules 11205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, Each of these examples, or some combination, may include the implementation of a network environment.
- Bus 1130 may be a local area representing one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or using any of a variety of bus structures. bus.
- Electronic device 1100 may also communicate with one or more external devices 1140 (e.g., keyboard, pointing device, Bluetooth device, etc.), may also communicate with one or more devices that enable a user to interact with electronic device 1100, and/or with Any device (eg, router, modem, etc.) that enables the electronic device 1100 to communicate with one or more other computing devices. This communication may occur through an input/output (I/O) interface 1150.
- the electronic device 1100 may also communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through the network adapter 1160 . As shown, network adapter 1160 communicates with other modules of electronic device 1100 via bus 1130 .
- network adapter 1160 communicates with other modules of electronic device 1100 via bus 1130 .
- the example embodiments described here can be implemented by software, or can be implemented by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or on the network , including several instructions to cause a computing device (which may be a personal computer, a server, a terminal device, a network device, etc.) to execute a method according to an embodiment of the present disclosure.
- a computing device which may be a personal computer, a server, a terminal device, a network device, etc.
- the processes described above with reference to the flowcharts may be implemented as a computer program product or computer program including computer instructions stored in a computer-readable storage medium middle.
- the processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes any of the above business processing methods.
- a computer-readable storage medium is also provided, and the computer-readable storage medium may be a readable signal medium or a readable storage medium.
- Program products capable of implementing the above methods of the present disclosure are stored thereon.
- various aspects of the present disclosure can also be implemented in the form of a program product, which includes program code.
- the program code is used to cause the The terminal device performs the steps according to various exemplary embodiments of the present disclosure described in the above "Example Method" section of this specification.
- Computer-readable storage media in this disclosure may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard drives, random access memory (RAM), read only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
- RAM random access memory
- ROM read only memory
- EPROM or flash memory Erasable programmable read-only memory
- CD-ROM portable compact disk read-only memory
- magnetic storage device or any suitable combination of the above.
- a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave carrying readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
- a readable signal medium may also be any readable medium other than a readable storage medium that can send, propagate, or transport the program for use by or in connection with an instruction execution system, apparatus, or device.
- program code embodied on a computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.
- program code for performing operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and Includes conventional procedural programming languages—such as "C” or similar programming languages.
- the program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server execute on.
- the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., provided by an Internet service). (business comes via Internet connection).
- LAN local area network
- WAN wide area network
- Internet service e.g., provided by an Internet service
- the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or on the network , including several instructions to cause a computing device (which may be a personal computer, a server, a mobile terminal, a network device, etc.) to execute a method according to an embodiment of the present disclosure.
- a computing device which may be a personal computer, a server, a mobile terminal, a network device, etc.
Landscapes
- Engineering & Computer Science (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
一种业务处理方法、装置、设备、介质及程序产品,涉及云计算业务服务链技术领域,根据在业务功能链SFC的接口处接收到的待处理业务,确定待处理业务对应的算力资源参数,根据算力资源参数,对一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,确定待处理业务在算力资源占用周期内需要使用的算力资源的分配方式,通过路由协议将分配方式下发至一个或者多个SF中,以使一个或者多个SF根据分配方式对待处理业务进行处理。在遵循现有SFC网络服务的基础上,通过路由协议引入新的机制,实现SFC对算力资源的感知,通过待处理业务的算力资源参数,对SFC中的每个SF的算力资源提前进行预占,从网络层面提高SFC的业务质量。
Description
相关申请的交叉引用
本公开要求于2022年8月24日提交的申请号为202211021129.1、名称为“业务处理方法、装置、电子设备及存储介质”的中国专利申请的优先权,该中国专利申请的全部内容通过引用全部并入本文。
本发明涉及云计算业务服务链技术领域,尤其涉及一种业务处理方法、装置、设备、介质及程序产品。
随着互联网技术的不断进步,网络运营商开始向业务功能链或业务链接转变。
在这种方法中,每个受支持的业务可以建模为一个或多个业务功能(Service Function,SF)的组合,其中,每个业务功能的作用是对网络数据包或数据包集合执行特定任务。对于给定的业务,按顺序应用业务功能,即以指定方式引导网络流量通过这些业务功能。这种技术称为业务功能链接,这些链通常称为业务功能链(Service Function Chaining,SFC)。
业务功能链(包括业务功能链所包含的业务功能)由静态配置决定。若通过业务功能链处理数据包的过程中,某个SF出现算力瓶颈或者出现故障时,则需要从头重新编排和更改链,绕过出现问题的业务功能,为降低特定的SF的负载就需调整个SFC,开销较大,缺乏灵活性。
发明内容
本公开提供一种业务处理方法、装置、设备、介质及程序产品,至少在一定程度上克服相关技术中某个SF出现算力瓶颈或者出现故障时,则需要从头重新编排和更改链,开销大,缺乏灵活性的问题。
根据本公开的第一方面,提供一种业务处理方法,包括:根据在业务功能链SFC的接口处接收到的待处理业务,确定所述待处理业务对应的算力资源参数;所述算力资源参数为表征所述待处理业务被所述SFC中的一个或者多个业务功能SF处理时,需要使用的算力资源对应的至少一个参数;根据所述算力资源参数,对所述一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,确定所述待处理业务在所述算力资源占用周期内需要使用的算力资源的分配方式;通过路由协议将所述分配方式下发至所述一个或者多个SF中,以使所述一个或者多个SF根据所述分配方式对所述待处理业务进行处理。
在一些实施例中,所述算力资源参数包括以下至少一种:算力资源占用周期、SFC业务路径标识符SPI编号、目标SF索引地址、算力资源占用周期内占用SF的内存数量和时长、中央处理器CPU处理的作业数、预估中位数、CPU时间/每次作业、内存输出量。
在一些实施例中,所述根据在业务功能链SFC的接口处接收到的待处理业务,确定所述待处理业务对应的算力资源参数,包括:根据所述路由协议扩展算力资源参数,并将所述算力资源参数下发至所述一个或者多个SF,以使所述一个或者多个SF根据所述算力资源参数,上传算力资源信息;所述算力资源参数为将处理业务时,所需要使用的算力资源通过参数的形式表述的表述方式;所述算力资源信息为所述一个或者
多个SF处理业务时,根据所述算力资源参数,返回的算力资源的使用情况/剩余可用算力资源的情况;根据所述待处理业务,以及所述算力资源信息,确定所述待处理业务对应的算力资源参数。
在一些实施例中,所述扩展算力资源参数的方式包括:所述路由协议通过协议消息体TLV或探测请求option进行扩展。
在一些实施例中,所述根据所述算力资源参数,对所述一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,确定所述待处理业务在所述算力资源占用周期内需要使用的算力资源的分配方式,包括:若将所述待处理业务对应的算力资源参数全部分配至所述一个或者多个SF,且未收到过载信号,则所述待处理业务在所述算力资源占用周期内需要使用的算力资源分配完成,确定所述分配方式;或者,若在所述预先占用操作的过程中,接收到任意一个SF反馈的过载信号,则停止对所述任意一个SF的算力资源进行占用;其中,所述过载信号为所述任意一个SF在所述算力资源占用周期中,被预先占用的算力资源大于预设算力资源阈值生成的信号;对与所述任意一个SF具备相同业务功能的SF的算力资源进行预先占用操作,直至所述待处理业务在所述算力资源占用周期内需要使用的算力资源分配完成,且未收到过载信号,确定所述分配方式。
在一些实施例中,所述方法还包括:根据在业务功能链SFC的接口处接收到的待处理业务,配置剩余算力资源指示信息;所述剩余算力资源指示信息为指示所述SFC中的一个或者多个SF在处理所述待处理业务时,实时返回的在所述算力资源占用周期内SF的剩余算力资源;配置算力资源调整指示信息;其中,所述算力资源调整指示信息为指示转发器根据所述一个或者多个SF在处理所述待处理业务时,实时返回的在所述算力资源占用周期内SF的剩余算力资源,调整处理所述待处理业务的SF的指示信息;将所述算力资源调整指示信息下发至所述转发器,以及通过路由协议将所述剩余算力资源指示信息下发至所述一个或者多个SF中,以使所述一个或者多个SF和所述转发器对所述待处理业务进行处理。
在一些实施例中,所述确定所述待处理业务在所述算力资源占用周期内需要使用的算力资源的分配方式之后,所述方法还包括:配置剩余算力资源指示信息;所述剩余算力资源指示信息为指示所述SFC中的一个或者多个SF在处理所述待处理业务时,实时返回的在所述算力资源占用周期内SF的剩余算力资源;配置算力资源调整指示信息;其中,所述算力资源调整指示信息为指示转发器根据所述一个或者多个SF在处理所述待处理业务时,实时返回的在所述算力资源占用周期内SF的剩余算力资源,调整处理所述待处理业务的SF的指示信息;通过路由协议将所述分配方式下发至所述一个或者多个SF中,包括:将所述算力资源调整指示信息下发至所述转发器,以及通过路由协议将所述分配方式和所述剩余算力资源指示信息下发至所述一个或者多个SF中,以使所述一个或者多个SF和所述转发器对所述待处理业务进行处理。
根据本公开的第二方面,本公开中的实施例提供一种业务处理装置,包括:确定单元,设置为根据在业务功能链SFC的接口处接收到的待处理业务,确定所述待处理业务对应的算力资源参数;所述算力资源参数为表征所述待处理业务被所述SFC中的一个或者多个业务功能SF处理时,需要使用的算力资源对应的至少一个参数;预占单元,设置为根据所述算力资源参数,对所述一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,确定所述待处理业务在所述算力资源占用周期内需要使用的算力资源的分配方式;下发单元,设置为通过路由协议将所述分配方式下发至所述一个或者多个SF中,以使所述一个或者多个SF根据所述分配方式对所述待处理业务进行处理。
根据本公开的第三方面,本公开实施例提供一种电子设备,包括:处理器;以及
存储器,设置为存储所述处理器的可执行指令;其中,所述处理器配置为经由执行所述可执行指令来执行如上所述的方法。
根据本公开的第四方面,提供一种计算机可读存储介质,所述计算机可读存储介质存储有计算机指令,所述指令被处理器执行如上所述的方法。
根据本公开的第五方面,还提供了一种计算机程序产品,包括计算机程序,所述计算机程序被处理器执行时实现如上所述的方法。
本公开的实施例所提供的一种业务处理方法、装置、设备、介质及程序产品,根据在业务功能链SFC的接口处接收到的待处理业务,确定待处理业务对应的算力资源参数;算力资源参数为表征待处理业务被SFC中的一个或者多个业务功能SF处理时,需要使用的算力资源对应的至少一个参数,根据算力资源参数,对一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,确定待处理业务在算力资源占用周期内需要使用的算力资源的分配方式,通过路由协议将分配方式下发至一个或者多个SF中,以使一个或者多个SF根据分配方式对待处理业务进行处理。通过预占的方式,在SFC中的一个或者多个SF处理待处理业务时,提前将每个SF的算力资源分配好,在控制器上引入新的机制,不仅可以实现SFC对算力资源的感知,确定接入的待处理业务的算力资源参数,可以在对算力资源感知的基础上根据SFC所需的算力资源对SF进行约束,通过资源标识符对现有的业务路径标识符(Service Path Identifier,SPI)处理管线进行局部灵活调整,适应算力性能差异化需求,提高业务链SF整体利用效率。在遵循现有SFC网络服务报头(Network Service Header,NSH)等格式和基本转发方式基础上,有效利用SFC处理资源,从网络层面提高SFC的业务质量,业务可用性,提高业务链扩展性和SF算力利用率。
进一步地,本公开中还根据在业务功能链SFC的接口处接收到的待处理业务,配置剩余算力资源指示信息;剩余算力资源指示信息为指示SFC中的一个或者多个SF在处理待处理业务时,实时返回的在算力资源占用周期内SF的剩余算力资源,配置算力资源调整指示信息;其中,算力资源调整指示信息为指示转发器根据一个或者多个SF在处理待处理业务时,实时返回的在算力资源占用周期内SF的剩余算力资源,调整处理待处理业务的SF的指示信息,将算力资源调整指示信息下发至转发器,以及通过路由协议将剩余算力资源指示信息下发至一个或者多个SF中,以使一个或者多个SF和转发器对待处理业务进行处理。通过算力资源指示信息,和指示转发器对算力资源调整,使得每个SF在处理待处理业务的过程中实时反馈给转发器的方式,自主刷新局部SFC的分支处理逻辑,而无需重新频繁重编排SFC,就可以将高算力开销的SF的负载进行卸载到其他SF中,可以降低重新编排SFC路径的开销。
还可以同时通过算力资源预占和实时反馈的方式,指示每个SF和转发器对待处理业务进行处理,有效的提高SFC技术的应用效率和场景适应性。
为了更清楚地说明本公开实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图仅仅是本公开的一些实施例,对于本领域普通技术人员来讲,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示出本公开实施例中一种业务处理方法的应用场景之一;
图2示出本公开实施例中一种业务处理方法的应用场景之二;
图3示出本公开实施例中一种业务处理方法的流程示意图之一;
图4示出本公开实施例中一种业务处理方法的应用场景之三;
图5示出本公开实施例中一种周期性算力资源表述示意图;
图6示出本公开实施例中一种业务处理方法的流程示意图之二;
图7示出本公开实施例中一种业务处理方法的应用场景之四;
图8示出本公开实施例中一种SFC算力网络的结构示意图;
图9示出本公开实施例中一种业务处理方法的流程示意图之三;
图10示出本公开实施例中一种业务处理装置的结构示意图;
图11示出本公开实施例中一种电子设备的结构示意图。
现在将参考附图更全面地描述示例实施方式。然而,示例实施方式能够以多种形式实施,且不应被理解为限于在此阐述的范例;相反,提供这些实施方式使得本公开将更加全面和完整,并将示例实施方式的构思全面地传达给本领域的技术人员。所描述的特征、结构或特性可以以任何合适的方式结合在一个或更多实施方式中。
此外,附图仅为本公开的示意性图解,并非一定是按比例绘制。图中相同的附图标记表示相同或类似的部分,因而将省略对它们的重复描述。附图中所示的一些方框图是功能实体,不一定必须与物理或逻辑上独立的实体相对应。可以采用软件形式来实现这些功能实体,或在一个或多个硬件模块或集成电路中实现这些功能实体,或在不同网络和/或处理器装置和/或微控制器装置中实现这些功能实体。
由于目前SFC中所有报文均是按照固定顺序遍历所有SF,为考虑到算力资源的因素,所以可能会带来以下问题:
当某一个SF出现算力瓶颈时,SFC编排的路径固定,无法感知出现问题的SF,引起负反馈。当某一个SF出现算力瓶颈时,控制器需频繁从头端重新编排业务功能路径(Service Functionpath,SFP),以达到绕过出现问题的SF,为降低某一个SF的负载就需调整个SFC管线,开销较大,缺乏灵活性。SFC缺乏直接感知算力资源的能力造成SF资源利用率较低。SFC感知对象主要为流量带宽,但是引起SFC对待处理业务处理质量下降的因素却是多方面的,具体因素SFC无法有效的感知到。
本公开提供了一种业务处理方法,根据在业务功能链SFC的接口处接收到的待处理业务,确定待处理业务对应的算力资源参数;算力资源参数为表征待处理业务被SFC中的一个或者多个业务功能SF处理时,需要使用的算力资源对应的至少一个参数,根据算力资源参数,对一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,确定待处理业务在算力资源占用周期内需要使用的算力资源的分配方式,通过路由协议将分配方式下发至一个或者多个SF中,以使一个或者多个SF根据分配方式对待处理业务进行处理。在遵循现有SFC网络服务的基础上,引入新的机制,不仅可以实现SFC对算力资源的感知,确定接入的待处理业务的算力资源参数,还可以通过对算力资源的感知,对SFC中的每个SF的算力资源提前进行预占,确定待处理业务的算力资源的分配方式,有效利用SFC处理资源,从网络层面提高SFC的业务质量,业务可用性,提高业务链扩展性和SF算力利用率。
图1为本公开实施例提供的一种业务处理方法的应用场景。
在如图1所示的SFC算力网络100中,包括:控制器101、转发器(Service Function Forwarder,SFF)102,分类器103,以及一系列SF。
通常,SFC包括驻留在各个网络节点上的一系列业务功能(或业务功能实例),也就是说,SFC是定义了经过业务分类后报文所需处理的一系列SF及处理次序,可支持IPv4,IPv6,SFC,mpls,vxlan等多样的路由协议(Underlay)。SFC可以包括沿SFC的一个或多个业务功能路径(Service Function Path,SFP)。当流量通过SFC从用户或用户设备(如用户设备112)转发时,流量中的数据包按顺序遍历SFP并由各种业务功能处理,其中,每个业务功能应用一个特定的功能,如防火墙、网络访问转换
(Network Access Translation,NAT)、深度报文检测(Deep Packet Inspection,DPI)等,之后将数据包转发到下一个网络节点。
其中,控制器101可以设置为确定处理待处理业务的路径。例如,业务功能路径(Service Function Path,SFP)。还可以设置为监测分类器103,转发器102以及一系列的SF的状态信息。还可以设置为将所确定的路径建立到分类器103和转发器102中。还可以设置为根据各种策略或者约定服务管理待处理业务的处理方式。
分类器103设置为为待处理业务对应的报文增加网络业务报头NSH,标注的业务功能路径SFP信息中包括的业务路径标识符SPI和业务索引(Service Index,SI)信息,并转交给转发器102。
转发器102在SFC中负责根据封装的SFC新消息引导流量按定义好的顺序进出一系列业务功能SF或者其他转发器102处理的网元。
SF可以是物理或虚拟网元,具备有限的处理能力,处理能力可以理解为算力,IO,存储,带宽等。SF在处理业务的处理能力不足的情况下,是可以进行扩展的。
其中,对于不支持SFC的SF节点,需通过代理设备(Proxy)处理NSH报文头。
需要说明的是,SPI唯一标记一条业务链路径。当SPI确定之后,转发器102根据业务索引判断需要将数据转发到哪个SF上,并根据查询到的具体的下一跳地址进行转发,遍历预定的、固定顺序的串联SF业务功能编组进行处理,难以根据SF的实际算力负载情况进行灵活调整。
如图1中所示的SFC算力网络,当SFC中的控制器101通过接口接收到待处理业务之后,对用户流量入口的分类器103下发3组报文分类策略,分别对应SPI1,SPI2,SPI3业务功能链处理。其中,图1中的1表示SPI1,2表示SPI2,3表示SPI3。根据SPI编号对应的SI数值降序遍历所对应的一组SF。
从图1中可以看出3条SFC均经过SF3.1,在建立SFC时SF 3.1算力充足,可满足3条SFC业务的并行处理流。但是经过长期的使用,SF3.1可能会出现算力瞬时或者长期的过载现象,可能是CPU处理时间满负荷,内存满载,内存IO超过载等。
当SF 3.1的算力过载影响到SPI1,SPI2,SPI3的业务质量,3条SPI均可能发生丢包,无响应,延迟增加等拖尾现象。
想要解决上述问题,需要通过控制器101通过虚拟化基础设施管理器或者主机性能监测***获得SF 3.1性能过载信号,并确认SF3.1无扩容资源。然后,控制器101发现SF3.2与SF3.1功能一致并可用。控制器101根据各SFC负载情况,选择撤销经过SF3.1的业务链SPI1,并重编排SPI1路径经过SF3.2。调整之后的SPI1如图2所示。
经过调整之后的SFC算力网络,可以看出经过SF3.1的SPI减少为2个,SPI1经过SF3.2。但是,由于SFC无法感知到待处理业务的算力信息,一般当部分算力资源出现瓶颈或重载现象发生后,才会通过监控***测量到业务质量劣化,并需要排除网络,算力等多方因素。SFC无法根据算力自主调整SPI管线,需通过头端拆除重建的方式,重建业务功能链,将SF3.1过载的业务卸载到SF3.2中。
上述是本公开中提供的一种业务处理方法的应用场景,本公开还提供了其他的业务处理方法的应用场景,下面结合附图及实施例对本示例实施方式进行详细说明。
首先,本公开实施例中提供了一种业务处理方法,该方法可以由任意具备计算处理能力的电子设备执行,下述过程中以电子设备为服务器为例。
图3示出本公开实施例中一种业务处理方法的流程图,如图3所示,本公开实施例中提供的业务处理方法包括如下步骤:
S302:根据在业务功能链SFC的接口处接收到的待处理业务,确定待处理业务对应的算力资源参数。
其中,算力资源参数为表征待处理业务被SFC中的一个或者多个业务功能SF处理时,需要使用的算力资源对应的至少一个参数。
需要说明的是,算力资源占用周期为控制器在配置策略的过程中,对SF的算力资源占用的预设周期。例如,待处理业务在5:30开始处理,控制器对于SF的算力资源进行占用的周期可以为5:30-5:31这段时间,这段时间即可以表示为算力资源占用周期。
在SFC算力网络中,由于SFC无法感知到SF的算力资源信息,并且也无法具体确定接收到的待处理业务在处理的过程中具体需要多少算力资源才可以将待处理业务处理完成,往往是通过监控***测量到对待处理业务的处理过程中处理质量劣化,才能够发现问题,基于此,本公开提供了一种可行的实施例,具体如下:
在一种可能的实施例中,算力资源参数的确定方式如下:
根据路由协议扩展算力资源参数,并将算力资源参数下发至一个或者多个SF,以使一个或者多个SF根据算力资源参数,上传算力资源信息;算力资源信息为一个或者多个SF处理业务时,根据算力资源参数,返回的算力资源的使用情况/剩余可用算力资源的情况,根据待处理业务,以及算力资源信息,确定待处理业务对应的算力资源参数。
其中,算力资源参数为将处理业务时,所需要使用的算力资源通过参数的形式表述的表述方式。
扩展算力资源参数的方式包括:路由协议通过协议消息体TLV或探测请求option进行扩展。SFC的路由协议通过TLV或option扩展算力资源参数。
通过路由协议扩展算力资源参数,向每个SF发送算力资源参数,使得具备发布/接收能力的SF定期向SFC路由协议提供与SFC无关的算力资源信息。可以理解为,是一种将SF处理待处理业务时,将算力资源通过算力资源参数的形式上传到SFC路由协议中,通过大量的SF上传的算力资源信息,可以使得SFC的控制器在后续接收到到处理业务时,可以根据算力资源信息,将接收到的待处理业务通过算力资源参数的方式表示出来,以此可以使SFC算力网络做到对算力的具体感知。
其中,SF向SFC路由协议注入该SF的算力资源信息,可以包括:该SF所在VNF,VM或主机的可用资源数据。
具体地,上述算力资源信息可以通过SFC路由协议分发至控制器、转发器或者分类器等,控制器也可以通过BGP LS或restful接口接收。
需要说明的是,上述通过路由协议下发算力资源参数,以及SF上传算力资源信息,其中涉及到的网元均需要时钟同步。
S304:根据算力资源参数,对一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,确定待处理业务在算力资源占用周期内需要使用的算力资源的分配方式。
在一种可能的实施例中,确定算力资源参数之后,如图4所示,以图1中存在的SPI1,SPI2,SPI3为例对本公开实施例提供的业务处理方法进行说明。均是SPI1,SPI2,SPI3对待处理业务进行处理的情况,但是图4中示出了另一种SFC算力网络200。其中,SFC算力网络200包括控制器201、转发器202、分类器203、以及一系列的SF。
上述内容中的算力资源参数可以包括:算力资源占用周期、SFC业务路径标识符SPI编号、目标SF索引地址、算力资源占用周期内占用SF的内存数量和时长、中央处理器CPU处理的作业数、预估中位数、CPU时间/每次作业、内存输出量。图5示出了一种周期性算力资源表述示意图。其中包括内存数量-时长,中位数CPU时间,请求数等。
其中,在SFC算力网络中接收待处理业务之后,具体的处理包括:
SFC算力网络中的控制器确定了待处理业务的算力资源参数,控制器可以标记一条SFC在固定周期内预计占用一个或者多个SF的算力资源,可以对一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,在对SF的算力资源进行预占的过程中,是直接由控制器通过路由协议向SF发布算力资源参数,来进行预先占用操作。通过控制器向每个SF发送该算力资源参数对SF的算力资源进行预占。此处以对SPI1涉及到的SF的算力资源进行预占。
在进行预先占用的过程中,可能包括以下两种情况,分别如下:
(1)若将待处理业务对应的算力资源参数全部分配至一个或者多个SF,且未收到过载信号,则待处理业务在算力资源占用周期内需要使用的算力资源分配完成,确定分配方式。
示例性地,在控制器向SF的算力资源进行预先占用的过程中,将SPI1所要处理的待处理业务对应的算力资源全部分配完成之后,也没有接收到任何一个SF的过载信号。那么,说明SPI1中涉及到的SF,算力资源不会出现过载的情况,可以满足此算力资源占用周期内对待处理业务的处理。
(2)若在预先占用操作的过程中,接收到任意一个SF反馈的过载信号,则停止对任意一个SF的算力资源进行占用,对与任意一个SF具备相同业务功能的SF的算力资源进行预先占用操作,直至待处理业务在算力资源占用周期内需要使用的算力资源分配完成,且未收到过载信号,确定分配方式。
其中,过载信号为任意一个SF在算力资源占用周期中,被预先占用的算力资源大于预设算力资源阈值生成的信号。过载信号中包括对哪一个算力资源占用周期的算力资源不足的信息。
示例性地,若在预先占用的过程中,以SF3.1为例,由于上述SPI1,SPI2,SPI3均经过SF3.1,所以,在对SPI1涉及到的SF的算力资源的预先占用过程中,SF3.1很可能会由于算力资源已经被SPI2和SPI3在算力资源占用周期已经占用了,会出现算力资源不足的情况,所以,控制器可以接收到SF3.1发送回来的过载信号。
SF在算力资源占用周期内的算力资源占用完毕之后,SF可以发出过载的周期或者过载的信号,控制器接收到该过载信号之后,则不会在该SF继续进行占用或者新增业务,可以理解为控制器不会在想该SF分配新的业务功能路径SFP。
进一步地,SFC算力网络的控制器在接收到过载信号之后,可以将原本占用在SF3.1中的待处理业务的算力资源,分配到SF3.2中去。并确定好具体的算力资源分配方式,由于控制器标记了业务路径标识符为SPI1的业务功能链,则可以确定SPI1的分配方式由于SF3.1的过载,已经发生变化。
需要说明的是,以SF3.1为例,若控制器标记了SPI1,并对SF3.1进行预先占用的过程中,SF3.1发出过载信号,但是控制器没有发现与SF3.1具备相同业务功能的SF,那么,可以直接限制SPI1在SF3.1所能使用的的算力资源开销,此种方式限制SPI1的算力资源开销到预占用阀值,SPI2,SPI3业务不受影响,SF 3.1算力资源正常。
S306:通过路由协议将分配方式下发至一个或者多个SF中,以使一个或者多个SF根据分配方式对待处理业务进行处理。
在一种可能的实施例中,控制器可以将确定好的分配方式通过路由协议发至转发器、分类器以及SPI1涉及到的每个SF中去,通知每个SF具体的算力资源占用周期,以及待处理业务具体的算力资源参数,使得每个SF在算力资源占用周期中预留出已经被控制器预先占用的算力资源,来处理待处理业务。整个预先占用过程对SPI2和SPI3没有任何影响。
上述图4中示出的S1、S2、S3等步骤均为控制器执行的步骤,S4为SF3.1向控
制器返回的过载信号,控制器响应于此过载信号,则确定与SF3.1具备相同业务功能的SF3.2,并向SF3.2进行预先占用操作,将待处理业务所需要的算力资源预先分配给SF3.2,最终确定分配方式,将确定好的分配方式发送至分类器和转发器以及每个SF,以对待处理业务进行处理。图4中对各种不同的情况不在进行多余的赘述。
需要说明的是,当该SF在算力资源占用周期内具备额外算力资源时,允许算力资源以相邻周期为单位的超限占用和赤字偿还。也就是可以理解为:若某个算力资源占用周期中的算力资源有富余,则可以在提前对此算力资源占用周期的算力资源进行占用,以及对后面的算力资源占用周期中的待处理业务进行提前处理。
上述业务处理方法中,通过SFC算力网络对算力资源的感知,有效的确定出算力资源参数,并对每个SF的算力资源进行预先占用,在时钟同步的前提下,可以有效的保证SF对待处理业务进行处理的过程中,SF的算力资源不会过载,保证业务链可以正常工作完成对待处理业务的处理。此种方式可以称为显式SFC算力策略,通过SFC算力网络中的控制器进行建立,并通过路由协议下发至业务功能链涉及到的每个SF、转发器和分类器中。并且,此种显式SFC算力策略是通过路由协议进行下发,整个过程是通过通信的方式对每个SF进行通知,不会改变原有的SFC机制,没有改变控制器以及分类器对待处理业务所位于的数据包或者数据包集合的处理。
需要说明的是,针对任意一个SF,当在SFC算力网络中,控制器需要将多个业务功能链对SF进行预先占用操作,每个业务功能链分别对应一种分配方式时,所有的业务功能链涉及到的SF根据均是可以识别出对应的业务功能链的,SF可以识别出哪条业务功能链在那个算力资源占用周期对该SF进行了占用,其他的业务功能链在哪个算力资源占用周期对该SF进行了占用,任意一个SF都是可以对业务功能链进行识别的。
需要说明的是,在SFC算力网络中,控制器与SF之间的通信,需要SF为具备发布能力、接收能力和识别能力。其中,发布能力为SF根据路由协议发布算力资源信息,以及发布过载信号的能力。接收能力为通过路由协议接收信息的能力。识别能力为针对任意一个SF,可以识别出此时经过该SF的业务功能链是哪一条,并且确定出此条业务功能链在该SF进行的业务以及预先占用的算力资源等。针对非算力感知网元透传信息即可。
具备上述能力的SF可以向OVS/vswitch路由等网元注册,根据算力策略指定的模式,定期向域内路由协议发布SFC无关的算力信息。
在一种可能的实施方式中,本公开提供了上述业务处理方法中的显式SFC算力策略之外,还提供了一种隐式SFC算力策略,如图6所示,图6包括以下步骤:
S602:根据在业务功能链SFC的接口处接收到的待处理业务,配置剩余算力资源指示信息。
其中,剩余算力资源指示信息为指示SFC中的一个或者多个SF在处理待处理业务时,实时返回的在算力资源占用周期内SF的剩余算力资源。
S604:配置算力资源调整指示信息。
其中,算力资源调整指示信息为指示转发器根据一个或者多个SF在处理待处理业务时,实时返回的在算力资源占用周期内SF的剩余算力资源,调整处理待处理业务的SF的指示信息。
S606:将算力资源调整指示信息下发至转发器,以及通过路由协议将剩余算力资源指示信息下发至一个或者多个SF中,以使一个或者多个SF和转发器对待处理业务进行处理。
在一种可能的实施例中,通过隐式SFC算力策略对SPI1路径进行算力调整的过程如图7所示,在控制器在接口处接收到待处理业务时,在正常配置业务功能链的基
础上,配置剩余算力资源指示信息,指示SFC中的一个或者多个SF在处理待处理业务时,实时返回的在算力资源占用周期内SF的剩余算力资源到控制器或者转发器。即,可以理解为使得SF发布算力资源占用周期内的剩余算力资源百分比信息。也可以指示每个SF实时返回算力资源占用周期的已被占用的算力资源百分比信息。
需要说明的是,算力资源调整指示信息为指示转发器,在接收到SF发送的剩余算力资源满足算力资源约束条件时,则按照正常逻辑执行即可,若接收到SF发送的剩余算力资源不满足算力资源约束条件时,则需要上报或者停止向该SF继续发送新的待处理业务,或者,根据该SF的地址检索是否存在有与该SF具备相同业务功能的SF,可以将原本转发至该SF的新的待处理业务,发送至与该SF具备相同业务功能的SF。上述算力资源约束条件可以为SF的剩余算力资源大于或者等于15%等,此设定算力资源可以根据不同周期,设置不同的阈值,以满足业务功能链对待处理业务的处理需求。
控制器配置算力资源调整指示信息发送至转发器,使得转发器在接收到SF的剩余算力资源之后,可以根据剩余算力资源对SF的算力资源进行均衡调节。例如,在SF3.1在某个周期时,处理待处理业务,并实时返回剩余算力资源给转发器,若转发器接收到SF3.1发送的剩余算力资源已经为5%,则可以自主进行均衡。
如图7中的图7b所示,其中,每个SF指转发器的虚线表示向转发器上传剩余算力资源,转发器接收到每个SF的剩余算力资源之后,即可以根据剩余算力资源,进行下一步的处理。
进一步地,出现上述SF3.1的剩余算力资源已经为5%,但是控制器又分配给SF3.1新的待处理业务时,则SPI1中的SF3.1处理开销增加,此时,若SF3.1,SF3.2采用等价地址,根据转发器接收到的算力资源调整指示信息,转发器在SF3.1发布的剩余算力资源不足以满足算力资源约束条件时,不将后续控制器分配给SF3.1的其他待处理业务分发给SF3.1,并且将SF3.1已经在处理的业务逐步调整至SF3.2进行处理。
通过调整路由协议算力权重将SPI1中SF3.1的待处理业务(其中,此处的待处理业务可以是流量、作业或者请求)逐步卸载到SF3.2,直到SF3.1在某个周期内向转发器发送的剩余算力资源满足算力资源约束条件。在上述过程中,实质上控制器并没有发出调整SPI1路径的指示信息,也没有重新配置新的SPI路径,并且由于SF3.1和SF3.2使用的是等价地址。所以,对于整个SFC算力网络而言,SPI1路径并没有进行实际的调整,仅是转发器在SF3.1的算力资源不足时,利用SF3.2的算力资源进行了增量部署,SPI1,SPI2,SPI3均不受影响,SF3.1,3.2算力资源均正常。
如图7中的图7c所示,SPI1路径经过SF3.1调整为经过SF3.2,通过SF3.2对待处理业务进行处理。虚线1表示原有的SPI1路径,实线1表示经过转发器调整之后的SPI1路径。
在上述方式中,控制器在接收到待处理业务之后,通过现有的方式对待处理业务的SPI路径进行配置,并发送至分类器,以使SPI路径中涉及到的SF对待处理业务进行处理,隐式SFC算力策略实质上可以理解为在对待处理业务正常处理的过程中,通过路由协议对转发器和每个SF进行了特殊的指示,以使转发器可以对SPI的流量等进行管理和对每个SF进行负载均衡。
本公开中的此种实施方式,通过上述隐式SFC算力策略的方式可以在转发器处将SFC算力网络中存在的SF算力过载的情况处理完成,无需额外的调整SPI路径,降低了SF算力资源瞬时/长期波动引起SFC质量劣化和端到端重建SPI需求,提高了业务链稳定性,增强了算力与SFC网络的亲和性。
本公开示出的SFC算力网络200,其具体的结构示意图如图8所示,其中包括的控制器201、转发器202、分类器203、以及一系列的SF。SFC算力网络200可以对
待处理业务进行代理。
具体可以分为如下结构:SFC算力网络200可以分为控制面和转发面。其中,控制面包括控制器201、转发面包括转发器202、分类器203、以及一系列的SF。
具体地,控制器201包括拓扑信息模块2011、路径计算模块2012、算力策略配置模块2013和路由算力拓展模块2014。
其中,路径计算模块2012主要设置为配置对待处理业务进行处理的路径,路径中包括多个SF。
算力策略配置模块2013设置为配置上述内容中提到的显式SFC算力策略和隐式SFC算力策略。
路由算力拓展模块2014设置为接收SF通过路由协议分发的算力资源信息,将算力策略配置模块2013配置的显式SFC算力策略和隐式SFC算力策略通过路由协议进行发布。以及设置为发布算力资源参数以及隐式SFC算力策略中的算力资源约束条件等。
本公开中的SFC算力网络200中的转发器202除基本的转发功能外,还可以设置为根据控制器201发送的算力资源调整指示信息,在SF的剩余算力资源不足以满足算力资源约束条件时,通过调整路由协议算力权重将流量(或作业,请求)按可用算力比例卸载到其他相同功能SF。
在一种可能的实施方式中,图9示出了一种共同使用上述显式SFC算力策略和隐式SFC算力策略的业务处理方法,如图9所示,包括以下步骤:
S902:根据在业务功能链SFC的接口处接收到的待处理业务,确定待处理业务对应的算力资源参数。
S904:根据算力资源参数,对一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,确定待处理业务在算力资源占用周期内需要使用的算力资源的分配方式。
S906:配置剩余算力资源指示信息。
S908:配置算力资源调整指示信息。
S910:通过路由协议将算力资源调整指示信息下发至转发器,以及通过路由协议将分配方式和剩余算力资源指示信息下发至一个或者多个SF中,以使一个或者多个SF和转发器对待处理业务进行处理。
本公开中的基于业务功能链的业务处理方法,在现有的SFC算力网络构架中引入业务功能链算力感知,发布和算力策略执行,算力路由等能力,新增了算力资源参数。在保持业务功能链转发器兼容性的基础上,解决了现有SFC算力灵活性不足的问题,同时提高了SF的利用率。
基于时间周期提供了显式和隐式两种SF算力资源占用策略和机制,降低了SF算力资源瞬时/长期波动引起SFC质量劣化和端到端重建SPI需求,提高了业务链稳定性,增强了算力与SFC网络的亲和性。
通过本公开中的业务处理方法,可以根据隐式SFC算力策略,以及针对SF的算力资源约束条件,局部调整SFC的业务处理管线,而不改变整个SFC转发路径。
还可以通过显式SFC算力策略,通过预先占用的方式,在处理待处理业务之前就锁定每个SF的算力资源,提高SFC算力网络中每个SF算力资源分配的合理性以及业务功能链的健壮性。
本公开中涉及到的算力资源感知方式,接收SF发送的算力资源信息,确定算力资源参数等方式,以及发布显式SFC算力策略,隐式SFC算力策略,发布算力资源约束条件等,均是通过路由协议进行发布,是通过通信的方式进行处理,没有改变现有SFC基本转发处理,代理机制。
可增量部署,可以通过将多个SF部署为同一个地址的方式,在某一个SF出现过载问题时,检索相同地址的SF,通过转发器将过载的SF的算力资源卸载至相同地址的SF中去,也可以理解为将算力资源卸载至相与出现问题的SF具备相同的业务功能的SF中去,仅需部分SF和转发器等关键网元支持算力感知。
通过上述方式,还可以减少算力因素引起的SFC路径重编排需求和业务质量降级,加快算力驱动的SFC业务升级。
基于同一发明构思,本公开实施例中还提供了一种业务处理装置,如下面的实施例。由于该装置实施例解决问题的原理与上述方法实施例相似,因此该装置实施例的实施可以参见上述方法实施例的实施,重复之处不再赘述。
图10示出本公开实施例中一种业务处理装置的结构示意图,如图10所示,该业务处理装置100包括:确定单元1001,设置为根据在业务功能链SFC的接口处接收到的待处理业务,确定待处理业务对应的算力资源参数;算力资源参数为表征待处理业务被SFC中的一个或者多个业务功能SF处理时,需要使用的算力资源对应的至少一个参数;预占单元1002,设置为根据算力资源参数,对一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,确定待处理业务在算力资源占用周期内需要使用的算力资源的分配方式;下发单元1003,设置为通过路由协议将分配方式下发至一个或者多个SF中,以使一个或者多个SF根据分配方式对待处理业务进行处理。
在本公开的一个实施例中,确定单元1001,还设置为:根据路由协议扩展算力资源参数,并将算力资源参数下发至一个或者多个SF,以使一个或者多个SF根据算力资源参数,上传算力资源信息;算力资源参数为将处理业务时,所需要使用的算力资源通过参数的形式表述的表述方式;算力资源信息为一个或者多个SF处理业务时,根据算力资源参数,返回的算力资源的使用情况/剩余可用算力资源的情况;根据待处理业务,以及算力资源信息,确定待处理业务对应的算力资源参数。
在本公开的一个实施例中,预占单元1002,还设置为:若将待处理业务对应的算力资源参数全部分配至一个或者多个SF,且未收到过载信号,则待处理业务在算力资源占用周期内需要使用的算力资源分配完成,确定分配方式;或者,若在预先占用操作的过程中,接收到任意一个SF反馈的过载信号,则停止对任意一个SF的算力资源进行占用;其中,过载信号为任意一个SF在算力资源占用周期中,被预先占用的算力资源大于预设算力资源阈值生成的信号;对与任意一个SF具备相同业务功能的SF的算力资源进行预先占用操作,直至待处理业务在算力资源占用周期内需要使用的算力资源分配完成,且未收到过载信号,确定分配方式。
业务处理装置100,还包括:均衡单元,设置为根据在业务功能链SFC的接口处接收到的待处理业务,配置剩余算力资源指示信息;剩余算力资源指示信息为指示SFC中的一个或者多个SF在处理待处理业务时,实时返回的在算力资源占用周期内SF的剩余算力资源;配置算力资源调整指示信息;其中,算力资源调整指示信息为指示转发器根据一个或者多个SF在处理待处理业务时,实时返回的在算力资源占用周期内SF的剩余算力资源,调整处理待处理业务的SF的指示信息;将算力资源调整指示信息下发至转发器,以及通过路由协议将剩余算力资源指示信息下发至一个或者多个SF中,以使一个或者多个SF和转发器对待处理业务进行处理。
在本公开的一个实施例中,业务处理装置100,还包括:预占均衡单元,设置为配置剩余算力资源指示信息;剩余算力资源指示信息为指示SFC中的一个或者多个SF在处理待处理业务时,实时返回的在算力资源占用周期内SF的剩余算力资源;配置算力资源调整指示信息;其中,算力资源调整指示信息为指示转发器根据一个或者多个SF在处理待处理业务时,实时返回的在算力资源占用周期内SF的剩余算力资源,调整处理待处理业务的SF的指示信息;通过路由协议将分配方式下发至一个或者多
个SF中,包括:将算力资源调整指示信息下发至转发器,以及通过路由协议将分配方式和剩余算力资源指示信息下发至一个或者多个SF中,以使一个或者多个SF和转发器对待处理业务进行处理。
在本公开实施例中,上述单元与对应的步骤所实现的示例和应用场景相同,但不限于上述方法实施例所公开的内容。需要说明的是,上述模块作为装置的一部分可以在诸如一组计算机可执行指令的计算机***中执行。
所属技术领域的技术人员能够理解,本公开的各个方面可以实现为***、方法或程序产品。因此,本公开的各个方面可以具体实现为以下形式,即:完全的硬件实施方式、完全的软件实施方式(包括固件、微代码等),或硬件和软件方面结合的实施方式,这里可以统称为“电路”、“模块”或“***”。
下面参照图11来描述根据本公开的这种实施方式的电子设备1100。图11显示的电子设备1100仅仅是一个示例,不应对本公开实施例的功能和使用范围带来任何限制。
如图11所示,电子设备1100以通用计算设备的形式表现。电子设备1100的组件可以包括但不限于:上述至少一个处理单元1110、上述至少一个存储单元1120、连接不同***组件(包括存储单元1120和处理单元1110)的总线1130。
其中,所述存储单元存储有程序代码,所述程序代码可以被所述处理单元1110执行,使得所述处理单元1110执行本说明书上述“示例性方法”部分中描述的根据本公开各种示例性实施方式的步骤。例如,所述处理单元1110可以执行上述方法实施例中的如下步骤,例如:根据在业务功能链SFC的接口处接收到的待处理业务,确定待处理业务对应的算力资源参数;算力资源参数为表征待处理业务被SFC中的一个或者多个业务功能SF处理时,需要使用的算力资源对应的至少一个参数;根据算力资源参数,对一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,确定待处理业务在算力资源占用周期内需要使用的算力资源的分配方式;通过路由协议将分配方式下发至一个或者多个SF中,以使一个或者多个SF根据分配方式对待处理业务进行处理。
存储单元1120可以包括易失性存储单元形式的可读介质,例如随机存取存储单元(RAM)11201和/或高速缓存存储单元11202,还可以进一步包括只读存储单元(ROM)11203。
存储单元1120还可以包括具有一组(至少一个)程序模块11205的程序/实用工具11204,这样的程序模块11205包括但不限于:操作***、一个或者多个应用程序、其它程序模块以及程序数据,这些示例中的每一个或某种组合中可能包括网络环境的实现。
总线1130可以为表示几类总线结构中的一种或多种,包括存储单元总线或者存储单元控制器、***总线、图形加速端口、处理单元或者使用多种总线结构中的任意总线结构的局域总线。
电子设备1100也可以与一个或多个外部设备1140(例如键盘、指向设备、蓝牙设备等)通信,还可与一个或者多个使得用户能与该电子设备1100交互的设备通信,和/或与使得该电子设备1100能与一个或多个其它计算设备进行通信的任何设备(例如路由器、调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口1150进行。并且,电子设备1100还可以通过网络适配器1160与一个或者多个网络(例如局域网(LAN),广域网(WAN)和/或公共网络,例如因特网)通信。如图所示,网络适配器1160通过总线1130与电子设备1100的其它模块通信。应当明白,尽管图中未示出,可以结合电子设备1100使用其它硬件和/或软件模块,包括但不限于:微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID***、磁带驱动器以及数
据备份存储***等。
通过以上的实施方式的描述,本领域的技术人员易于理解,这里描述的示例实施方式可以通过软件实现,也可以通过软件结合必要的硬件的方式来实现。因此,根据本公开实施方式的技术方案可以以软件产品的形式体现出来,该软件产品可以存储在一个非易失性存储介质(可以是CD-ROM,U盘,移动硬盘等)中或网络上,包括若干指令以使得一台计算设备(可以是个人计算机、服务器、终端装置、或者网络设备等)执行根据本公开实施方式的方法。
特别地,根据本公开的实施例,上文参考流程图描述的过程可以被实现为计算机程序产品或计算机程序,该计算机程序产品或计算机程序包括计算机指令,该计算机指令存储在计算机可读存储介质中。计算机设备的处理器从计算机可读存储介质读取该计算机指令,处理器执行该计算机指令,使得该计算机设备执行上述任一项的业务处理方法。
在本公开的示例性实施例中,还提供了一种计算机可读存储介质,该计算机可读存储介质可以是可读信号介质或者可读存储介质。其上存储有能够实现本公开上述方法的程序产品。在一些可能的实施方式中,本公开的各个方面还可以实现为一种程序产品的形式,其包括程序代码,当所述程序产品在终端设备上运行时,所述程序代码用于使所述终端设备执行本说明书上述“示例性方法”部分中描述的根据本公开各种示例性实施方式的步骤。
本公开中的计算机可读存储介质的更具体的例子可以包括但不限于:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。
在本公开中,计算机可读存储介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了可读程序代码。这种传播的数据信号可以采用多种形式,包括但不限于电磁信号、光信号或上述的任意合适的组合。可读信号介质还可以是可读存储介质以外的任何可读介质,该可读介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。
可选地,计算机可读存储介质上包含的程序代码可以用任何适当的介质传输,包括但不限于无线、有线、光缆、RF等等,或者上述的任意合适的组合。
在具体实施时,可以以一种或多种程序设计语言的任意组合来编写用于执行本公开操作的程序代码,所述程序设计语言包括面向对象的程序设计语言—诸如Java、C++等,还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户计算设备上部分在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。在涉及远程计算设备的情形中,远程计算设备可以通过任意种类的网络,包括局域网(LAN)或广域网(WAN),连接到用户计算设备,或者,可以连接到外部计算设备(例如利用因特网服务提供商来通过因特网连接)。
应当注意,尽管在上文详细描述中提及了用于动作执行的设备的若干模块或者单元,但是这种划分并非强制性的。实际上,根据本公开的实施方式,上文描述的两个或更多模块或者单元的特征和功能可以在一个模块或者单元中具体化。反之,上文描述的一个模块或者单元的特征和功能可以进一步划分为由多个模块或者单元来具体化。
此外,尽管在附图中以特定顺序描述了本公开中方法的各个步骤,但是,这并非要求或者暗示必须按照该特定顺序来执行这些步骤,或是必须执行全部所示的步骤才能实现期望的结果。附加的或备选的,可以省略某些步骤,将多个步骤合并为一个步
骤执行,以及/或者将一个步骤分解为多个步骤执行等。
通过以上实施方式的描述,本领域的技术人员易于理解,这里描述的示例实施方式可以通过软件实现,也可以通过软件结合必要的硬件的方式来实现。因此,根据本公开实施方式的技术方案可以以软件产品的形式体现出来,该软件产品可以存储在一个非易失性存储介质(可以是CD-ROM,U盘,移动硬盘等)中或网络上,包括若干指令以使得一台计算设备(可以是个人计算机、服务器、移动终端、或者网络设备等)执行根据本公开实施方式的方法。
本领域技术人员在考虑说明书及实践这里公开的发明后,将容易想到本公开的其它实施方案。本公开旨在涵盖本公开的任何变型、用途或者适应性变化,这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的,本公开的真正范围和精神由所附的权利要求指出。
Claims (11)
- 一种业务处理方法,所述方法包括:根据在业务功能链SFC的接口处接收到的待处理业务,确定所述待处理业务对应的算力资源参数;所述算力资源参数为表征所述待处理业务被所述SFC中的一个或者多个业务功能SF处理时,需要使用的算力资源对应的至少一个参数;根据所述算力资源参数,对所述一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,确定所述待处理业务在所述算力资源占用周期内需要使用的算力资源的分配方式;通过路由协议将所述分配方式下发至所述一个或者多个SF中,以使所述一个或者多个SF根据所述分配方式对所述待处理业务进行处理。
- 根据权利要求1所述的业务处理方法,其中,所述算力资源参数包括以下至少一种:算力资源占用周期、SFC业务路径标识符SPI编号、目标SF索引地址、算力资源占用周期内占用SF的内存数量和时长、中央处理器CPU处理的作业数、预估中位数、CPU时间/每次作业、内存输出量。
- 根据权利要求1所述的业务处理方法,其中,所述根据在业务功能链SFC的接口处接收到的待处理业务,确定所述待处理业务对应的算力资源参数,包括:根据路由协议扩展所述算力资源参数,并将所述算力资源参数下发至所述一个或者多个SF,以使所述一个或者多个SF根据所述算力资源参数,上传算力资源信息;所述算力资源参数为将处理业务时,所需要使用的算力资源通过参数的形式表述的表述方式;所述算力资源信息为所述一个或者多个SF处理业务时,根据所述算力资源参数,返回的算力资源的使用情况/剩余可用算力资源的情况;根据所述待处理业务,以及所述算力资源信息,确定所述待处理业务对应的算力资源参数。
- 根据权利要求3所述的业务处理方法,其中,扩展算力资源参数的方式包括:所述路由协议通过协议消息体TLV或探测请求option进行扩展。
- 根据权利要求1所述的业务处理方法,其中,所述根据所述算力资源参数,对所述一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,确定所述待处理业务在所述算力资源占用周期内需要使用的算力资源的分配方式,包括:若将所述待处理业务对应的算力资源参数全部分配至所述一个或者多个SF,且未收到过载信号,则所述待处理业务在所述算力资源占用周期内需要使用的算力资源分配完成,确定所述分配方式;或者,若在所述预先占用操作的过程中,接收到任意一个SF反馈的过载信号,则停止对所述任意一个SF的算力资源进行占用;其中,所述过载信号为所述任意一个SF在所述算力资源占用周期中,被预先占用的算力资源大于预设算力资源阈值生成的信号;对与所述任意一个SF具备相同业务功能的SF的算力资源进行预先占用操作,直至所述待处理业务在所述算力资源占用周期内需要使用的算力资源分配完成,且未收到过载信号,确定所述分配方式。
- 根据权利要求1所述的业务处理方法,其中,所述方法还包括:根据在业务功能链SFC的接口处接收到的待处理业务,配置剩余算力资源指示信息;所述剩余算力资源指示信息为指示所述SFC中的一个或者多个SF在处理所述待处理业务时,实时返回的在所述算力资源占用周期内SF的剩余算力资源;配置算力资源调整指示信息;其中,所述算力资源调整指示信息为指示转发器根据所述一个或者多个SF在处理所述待处理业务时,实时返回的在所述算力资源占用 周期内SF的剩余算力资源,调整处理所述待处理业务的SF的指示信息;将所述算力资源调整指示信息下发至所述转发器,以及通过路由协议将所述剩余算力资源指示信息下发至所述一个或者多个SF中,以使所述一个或者多个SF和所述转发器对所述待处理业务进行处理。
- 根据权利要求1所述的业务处理方法,其中,所述确定所述待处理业务在所述算力资源占用周期内需要使用的算力资源的分配方式之后,所述方法还包括:配置剩余算力资源指示信息;所述剩余算力资源指示信息为指示所述SFC中的一个或者多个SF在处理所述待处理业务时,实时返回的在所述算力资源占用周期内SF的剩余算力资源;配置算力资源调整指示信息;其中,所述算力资源调整指示信息为指示转发器根据所述一个或者多个SF在处理所述待处理业务时,实时返回的在所述算力资源占用周期内SF的剩余算力资源,调整处理所述待处理业务的SF的指示信息;通过路由协议将所述分配方式下发至所述一个或者多个SF中,包括:将所述算力资源调整指示信息下发至所述转发器,以及通过路由协议将所述分配方式和所述剩余算力资源指示信息下发至所述一个或者多个SF中,以使所述一个或者多个SF和所述转发器对所述待处理业务进行处理。
- 一种业务处理装置,所述装置包括:确定单元,用于根据在业务功能链SFC的接口处接收到的待处理业务,确定所述待处理业务对应的算力资源参数;所述算力资源参数为表征所述待处理业务被所述SFC中的一个或者多个业务功能SF处理时,需要使用的算力资源对应的至少一个参数;预占单元,用于根据所述算力资源参数,对所述一个或者多个SF在算力资源占用周期内的算力资源进行预先占用操作,确定所述待处理业务在所述算力资源占用周期内需要使用的算力资源的分配方式;下发单元,用于通过路由协议将所述分配方式下发至所述一个或者多个SF中,以使所述一个或者多个SF根据所述分配方式对所述待处理业务进行处理。
- 一种电子设备,包括:处理器;以及存储器,设置为存储所述处理器的可执行指令;其中,所述处理器配置为经由执行所述可执行指令来执行权利要求1~7中任意一项所述的方法。
- 一种计算机可读存储介质,其上存储有计算机程序,所述计算机程序被处理器执行时实现权利要求1~7中任意一项所述的方法。
- 一种计算机程序产品,包括计算机程序,所述计算机程序被处理器执行时实现权利要求1至7中任一项所述的方法。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211021129.1A CN117667366A (zh) | 2022-08-24 | 2022-08-24 | 业务处理方法、装置、电子设备及存储介质 |
CN202211021129.1 | 2022-08-24 |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2024041572A1 true WO2024041572A1 (zh) | 2024-02-29 |
WO2024041572A9 WO2024041572A9 (zh) | 2024-04-11 |
Family
ID=90012571
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2023/114474 WO2024041572A1 (zh) | 2022-08-24 | 2023-08-23 | 业务处理方法、装置、设备、介质及程序产品 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN117667366A (zh) |
WO (1) | WO2024041572A1 (zh) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180263039A1 (en) * | 2017-03-08 | 2018-09-13 | Zte Corporation | Traffic path change detection mechanism for mobile edge computing |
CN112491739A (zh) * | 2020-07-10 | 2021-03-12 | 中兴通讯股份有限公司 | 一种业务流量处理方法及装置 |
CN112751826A (zh) * | 2020-12-07 | 2021-05-04 | 中兴通讯股份有限公司 | 算力应用流量转发方法及装置 |
CN113434294A (zh) * | 2021-06-29 | 2021-09-24 | 腾讯科技(深圳)有限公司 | 一种数据处理方法、计算机设备以及可读存储介质 |
WO2021190482A1 (zh) * | 2020-03-27 | 2021-09-30 | ***通信有限公司研究院 | 算力处理的网络***及算力处理方法 |
-
2022
- 2022-08-24 CN CN202211021129.1A patent/CN117667366A/zh active Pending
-
2023
- 2023-08-23 WO PCT/CN2023/114474 patent/WO2024041572A1/zh unknown
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180263039A1 (en) * | 2017-03-08 | 2018-09-13 | Zte Corporation | Traffic path change detection mechanism for mobile edge computing |
WO2021190482A1 (zh) * | 2020-03-27 | 2021-09-30 | ***通信有限公司研究院 | 算力处理的网络***及算力处理方法 |
CN112491739A (zh) * | 2020-07-10 | 2021-03-12 | 中兴通讯股份有限公司 | 一种业务流量处理方法及装置 |
CN112751826A (zh) * | 2020-12-07 | 2021-05-04 | 中兴通讯股份有限公司 | 算力应用流量转发方法及装置 |
CN113434294A (zh) * | 2021-06-29 | 2021-09-24 | 腾讯科技(深圳)有限公司 | 一种数据处理方法、计算机设备以及可读存储介质 |
Also Published As
Publication number | Publication date |
---|---|
CN117667366A (zh) | 2024-03-08 |
WO2024041572A9 (zh) | 2024-04-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11218537B2 (en) | Load balancing in distributed computing systems | |
US11463511B2 (en) | Model-based load balancing for network data plane | |
US8386825B2 (en) | Method and system for power management in a virtual machine environment without disrupting network connectivity | |
EP4298776A1 (en) | Service mesh offload to network devices | |
CN103476062B (zh) | 一种数据流调度的方法、设备和*** | |
CN108471629A (zh) | 传输网络中业务服务质量的控制方法、设备及*** | |
CN107770085B (zh) | 一种网络负载均衡方法、设备及*** | |
JP7092813B2 (ja) | パケット伝送方法及び装置 | |
CN111371694B (zh) | 一种分流方法、装置和***、处理设备和存储介质 | |
US11991083B2 (en) | Systems and methods for enhanced autonegotiation | |
CN115514651B (zh) | 基于软件定义层叠网的云边数据传输路径规划方法及*** | |
CN104639415A (zh) | 一种虚拟机的迁移方法和软件定义网络sdn控制器 | |
US9143580B2 (en) | Brokering and provisioning in high-speed networks | |
CN108092787B (zh) | 一种缓存调整方法、网络控制器及*** | |
WO2024041572A1 (zh) | 业务处理方法、装置、设备、介质及程序产品 | |
US8832266B2 (en) | System and method for aggregating bandwidth of multiple active physical interfaces on application layer | |
US20150138979A1 (en) | Network management control device, network management control system, and network management control method | |
US11522762B2 (en) | Coordination device and method for providing control applications via a communication network for transmitting time-critical data | |
US20240171504A1 (en) | Multi-path architecture for hardware offloading | |
Luo et al. | Design and implementation of a scalable sdn-of controller cluster | |
JP2001007862A (ja) | 通信負荷分散方法 | |
CN117608848A (zh) | 一种异构计算资源控制方法、装置及设备 | |
CN118018488A (zh) | 网络集群***、报文传输方法及网络设备 |
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: 23856660 Country of ref document: EP Kind code of ref document: A1 |