CN117527692A - Calculation notification and routing method in calculation network, electronic equipment and storage medium - Google Patents

Abstract

The embodiment of the application discloses a method for advertising and routing a computing power in a computing power network, an electronic device and a storage medium, wherein the method comprises the following steps: acquiring computing power information of a cloud side server from a database, wherein the computing power information is acquired from a cloud network by the database; generating a calculation force routing table according to the calculation force information; according to the calculation routing table and the pre-configured IP routing table, the forwarding paths are obtained, and the forwarding operation is carried out, so that calculation notification and calculation routing can be carried out in real time, the calculation routing table is completely decoupled from the IP routing table of the calculation network, timeliness and compatibility of network communication are improved, the influence of high-frequency change of the calculation notification on the network communication is avoided, and the quality and user experience of the network communication are ensured.

Description

Calculation notification and routing method in calculation network, electronic equipment and storage medium

Technical Field

The present invention relates to the field of network communications technologies, and in particular, to a method for advertising and routing an optical power in an optical power network, an electronic device, and a storage medium.

Background

Information networks are being transformed from network infrastructure with information delivery as a core to intelligent cloud network infrastructure that fuses computing, storage, and transmission resources, and the computing network is one of the best practices and applications of cloud network fusion. Currently, in the cloud entering process of the service, an algorithm resource pool meeting requirements is comprehensively selected according to network factors (factors such as time delay, bandwidth, packet loss rate and the like) and algorithm factors (factors such as cost and the like) so as to meet the requirements of various novel applications and vertical industries.

In the prior art, a network infrastructure needs to have the sensing capability of computing resources, and perform computing notification according to network topology to generate a computing route so as to guide network equipment to perform optimal allocation of the computing resources. Thus, the perception of computing forces by the network infrastructure, the advertising of computing forces within the network, and the routing of computing forces are key technologies for achieving a convergence of computing forces network. The network infrastructure senses the calculation force, and the current common technical means is to establish connection between the network side and the operation side through some management protocols, such as file transfer protocol (File Transfer Protocol, FTP) and the like, and the operation side is responsible for actively notifying specific information of the calculation force. The notification of the calculation force information is mainly completed by expanding protocols such as an extended border gateway protocol (Border Gateway Protocol, BGP), an interior gateway protocol (Interior Gateway Protocol, IGP) and the like, and has the problems of poor compatibility and slow response speed. In addition, the computational power routing and the original traditional IP routing are coupled in the advertising and generating processes, and the computational power information has high time variability, so that the computational power advertising and the computational power routing are performed in the existing mode, and the existing load-bearing network is impacted and influenced greatly, and the quality and the user experience of network communication are influenced.

Disclosure of Invention

The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

The embodiment of the invention provides a calculation notification and routing method, electronic equipment and a storage medium in a calculation network, wherein calculation information of a cloud side server is acquired from a database, and the calculation information is acquired from the cloud network by the database; generating a calculation force routing table according to the calculation force information; the forwarding paths are obtained according to the calculation routing table and the pre-configured IP routing table, and forwarding operation is carried out, so that calculation notification and calculation routing can be carried out in real time, timeliness and compatibility of network communication are improved, influence of high-frequency change of the calculation notification on the network communication is avoided, and quality and user experience of the network communication are guaranteed.

In a first aspect, an embodiment of the present invention provides a method for advertising and routing a computing power in a computing power network, where the method is applied to an edge device, and the method includes: acquiring computing power information of a cloud side server from a database, wherein the computing power information is acquired from a cloud network by the database; generating a calculation force routing table according to the calculation force information; and acquiring a forwarding path according to the force calculation routing table and the pre-configured IP routing table, and executing forwarding operation.

In a second aspect, an embodiment of the present invention provides a method for advertising and routing a computing power in a computing power network, where the method includes: and acquiring and storing the computing power information of the cloud side server from the cloud network, so that the edge equipment can read the computing power information and generate a computing power routing table according to the computing power information.

In a third aspect, an embodiment of the present invention provides an electronic device, including: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the method for notifying and routing the computing power in the computing power network when executing the computer program.

In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium storing a computer program, where the computer program when executed by a processor implements the method for advertising and routing a computing force in a computing force network provided by the embodiment of the present invention.

According to the embodiment of the invention, the computing power information of the cloud side server is obtained from the database, wherein the computing power information is obtained from the cloud network by the database; generating a calculation force routing table according to the calculation force information; and acquiring a forwarding path according to the calculation routing table and the pre-configured IP routing table, and executing forwarding operation, so that timeliness and compatibility of network communication are improved, influence of high-frequency change of calculation notification on the network communication is avoided, and quality and user experience of the network communication are ensured.

Drawings

Fig. 1 is a schematic flow chart of a method for advertising and routing in a power network according to an embodiment of the present application;

FIG. 2 is a schematic diagram illustrating a specific implementation procedure of another embodiment of step S1000 in FIG. 1;

FIG. 3 is a schematic diagram illustrating a specific implementation procedure of another embodiment of step S2000 in FIG. 1;

FIG. 4 is a schematic diagram illustrating a specific implementation procedure of another embodiment of step S2200 in FIG. 3;

FIG. 5 is a schematic diagram illustrating a specific implementation procedure of another embodiment of step S3000 in FIG. 1;

FIG. 6 is a schematic diagram of a specific implementation process of a method for advertising and routing in a power network according to another embodiment of the present application;

FIG. 7 is a flowchart of a method for advertising and routing in a power network according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

It should be appreciated that in the description of the embodiments of the present application, if any, the descriptions of "first," "second," etc. are used for the purpose of distinguishing between technical features only, and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated. "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relation of association objects, and indicates that there may be three kinds of relations, for example, a and/or B, and may indicate that a alone exists, a and B together, and B alone exists. Wherein A, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of the following" and the like means any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c may represent: a, b, c, a and b, a and c, b and c or a and b and c, wherein a, b and c can be single or multiple.

In addition, technical features described below in the various embodiments of the present application may be combined with each other as long as they do not conflict with each other.

The method for informing and routing the power in the power computing network according to the embodiment of the application is characterized in that resources are reserved as required by whole network path calculation when the user service is required in the power computing network, so that the network needs to know the topology state, the network link state and the IP reachability information of each network device, and the functions of path planning, strategy issuing, resource routing and the like are realized on the basis of the topology state, the network link state and the IP reachability information. The computing power network is a novel information infrastructure for distributing and flexibly scheduling computing resources, storage resources and network resources among clouds, networks and edges according to service requirements. The computing power network utilizes novel network technologies such as cloud network fusion technology, software defined network (Software Defined Network, SDN), network function virtualization (Network Functions Virtualization, NFV) and the like, deeply fuses edge computing nodes, cloud computing nodes and various network resources including wide area networks together, reduces the management and control complexity of the edge computing nodes, and cooperates with computing and storage resources of the cloud computing nodes and network resources of the wide area networks through a centralized control or distributed scheduling method to form a new generation information infrastructure, provides overall computing power service comprising computing, storage and connection for clients, and provides flexible and schedulable on-demand service according to service characteristics.

In order to ensure that the network infrastructure has the perceptibility of the computing power resources, and to carry out computing power notification according to the network topology, a computing power route is generated to guide the network equipment to carry out optimal allocation of the computing power resources, in the prior art, computing power calculation is carried out through protocols such as FTP (File transfer protocol), and connection is established between an FTP client and a server, and an operation side is responsible for actively notifying computing power specific information. The notification of the calculation force information is mainly completed through the expansion of network layer protocols such as BGP, IGP and the like. Therefore, the prior art has more management protocols and network layer protocols, and long authentication time, so that the compatibility is poor and the response speed is slow; especially in the network environment with high power calculation frequency conversion, the rapid change of the power calculation route brings impact and influence to the current network service, and also brings higher performance requirements to the power calculation notification and route in the power calculation network.

Based on the above, the embodiments of the present application provide a method for advertising and routing a computing power in a computing power network, an electronic device, and a computer readable storage medium, by acquiring computing power information of a cloud side server from a database, where the computing power information is acquired from the cloud network by the database; generating a calculation force routing table according to the calculation force information; and acquiring a forwarding path according to the calculation routing table and the pre-configured IP routing table, and executing forwarding operation, so that timeliness and compatibility of network communication are improved, influence of high-frequency change of calculation notification on the network communication is avoided, and quality and user experience of the network communication are ensured.

Referring to fig. 1, fig. 1 shows a flow of a method for advertising and routing in a power network according to an embodiment of the present application. As shown in fig. 1, the method for advertising and routing the computing power in the computing power network according to the embodiment of the application includes the following steps:

s1000, computing power information of a cloud side server is obtained from a database, wherein the computing power information is obtained from a cloud network by the database.

It can be understood that the computing power information of the cloud side server is used for reflecting the performance parameters and the running conditions of the resource pool in the cloud network. And by acquiring the calculation power information of the cloud network, unified calculation power resource collaborative calling is facilitated. Exemplary computing power information of the cloud side server includes, but is not limited to, service identifier (Service ID), service Gateway (Service Gateway), and performance parameters of the network element, where the performance parameters include indicators such as CPU, IO read-write performance, memory, core number, etc., and changes in the performance parameters may cause migration and scaling of Service in the Service resource pool.

It is understood that cloud networks mainly provide services such as private network virtual path connection (Virtual Path Connection, VPC), physical network, and load balancing. The cloud Network mainly adopts the technologies of software defined Network (Software Defined Network, SDN), network function virtualization (Network Functions Virtualization, NFV), overlay Network (Overlay Network) tunnel and the like. To improve network processing performance and throughput, network load is changed from initially using Virtual switches (Virtual switches) through kernel-mode processing to using data plane development suites (DPDKs, data Plane Development Kit) based on user-mode processing. It is understood that a cloud network includes cloud devices and cloud services. The cloud equipment comprises storage equipment for data storage of a server for data calculation processing and switch equipment for data communication. The cloud service comprises cloud platform software for physical resource, virtualized scheduling management and application platform software for providing services to users.

It can be appreciated that the cloud network is a new concept that extends and develops in the concept of cloud computing (closed computing). Cloud computing is a development of distributed processing (distributed computing), parallel processing (parallel computing) and grid computing (grid computing), and is characterized in that a huge computing processing program is automatically split into a plurality of small subroutines through a network, and then the subroutines are transmitted to a user after being computed and analyzed by a huge system consisting of a plurality of servers. Through cloud computing technology, network service providers can process tens or even hundreds of millions of information within seconds to achieve the same powerful network services as supercomputers.

Specifically, step S1000 includes at least the steps of:

s1100, key value information in a key value database is read in real time, wherein the key value information is generated according to the calculation force information, and the key value database is generated by the database according to the key value information.

It will be appreciated that a key-value database is a non-relational database that uses a simple key-value method (key-value) to store data. The key-value database stores data as a set of key-value pairs, with keys as unique identifiers. Keys and values can be anything from simple objects to complex compound objects. Furthermore, key-value databases are highly partitionable and allow for horizontal expansion on a scale that other types of databases cannot achieve.

Referring to fig. 2, fig. 2 is a schematic diagram illustrating a specific implementation procedure of another embodiment of the step S1100. As shown in fig. 2, step S1100 includes at least the following steps:

s1110, acquiring computing power information of a cloud side server.

It can be understood that the edge device obtains the calculation information from the cloud network through the database, so that the running state of each resource pool of the cloud network can be mastered in real time, and the edge device can guide the service flow to the appropriate cloud network calculation resource pool. It can be appreciated that the database obtains the computing power information from the cloud network by broadcasting or in a command manner, which is not described herein.

S1120, extracting the calculation force information to generate key value information, and generating a key value database according to the key value information.

It will be appreciated that for key-value databases, the basic data model is a key-value model, the key of different key-value databases is not greatly different, and the main difference is in the value type. From the viewpoint of use, the implementation of different value types can support the data requirements of different services, and also implies the difference of different data structures in performance, space efficiency and the like, so that the difference exists between different value operations.

It can be understood that the key value database can be registered in an independent server outside the cloud network and the network domain, so that the key value database can be ensured to stably store key value information, and the condition that the key value information stored in the key value database is updated untimely due to communication faults between the cloud network and the network domain is avoided, and the timeliness of the notification of the computing power information is influenced.

It can be appreciated that, in order to fully reflect the operation state of cloud resources in the cloud network, the computing power information includes at least one of the following: service identifier, service gateway and network element performance parameters. And key information capable of reflecting the running state of the cloud resource pool is generated by extracting key information of the calculation force information.

Illustratively, the key value information is generated according to the service identifier, the service gateway, the CPU occupancy rate and the memory residual capacity in the calculation power information, wherein the service identifier and the service gateway are set as keys. In order to write key value information into the key value database, a key-value model is built as follows:

/yun service/wg prefix 2011::1

/yun service/sevice sid 3589::3

/yun service/sevice sid/cpuload 75

/yun service/sevice sid/memory remain 1G

it can be understood that in the prior art, the communication of the calculation information is established by using a management protocol such as FTP, and the cloud network providing the calculation information actively informs the network unit on one side of the network domain, so that the problem of complex notification flow exists, and the calculation information with high frequency change easily impacts the network. Therefore, a Database (Database) is introduced into the computing network for dynamically storing the key information, providing the key information for the network domain edge device to read, and providing the dynamic key information for the network domain edge device through the publish and subscribe (Publish Subscribe, pub-sub) function of the Database.

It can be appreciated that the cloud network can write the key value information into the database in real time through the database client (db-agent). The network domain edge equipment group observes the key value information through a pub-sub mechanism of the database, so that a change value of the key value information is obtained. As a plurality of edge devices observe the key value information in the database at the same time, the effect that the computing power information is perceived and announced by all the edge devices is actually achieved. It can be appreciated that by introducing database technology, the unification of the network's computing power awareness and computing power at the network's Fan Hong functionality is achieved.

It can be understood that by extracting the calculation force information into key value information and writing the key value information into the key value database, the perception of the calculation force information by the database is realized, the notification of the calculation force information on all edge devices is realized, and the perception range and response speed of the calculation force information are improved.

S1130, reading key value information in the database.

It can be understood that the cloud network writes the key value information into the key value database in real time through the db-agent, and completes writing and updating operations on the key value database so as to ensure the real-time performance of the key value information. Similarly, the edge device can dynamically read the calculation force information in the key value database through the db-agent, so as to complete the reading operation of the key value database. It can be understood that in the writing and reading process, no additional authentication of management type protocol and network layer protocol is needed, and the flow of computing power sensing and computing power notification is simplified.

S2000, generating a calculation force routing table according to the calculation force information.

It can be understood that, according to the calculation power information and the variation value thereof, a calculation power routing table which is convenient for guiding the edge equipment to execute the forwarding operation is formed, and the cloud network resources meeting the service requirements in the calculation power information can be updated and screened out efficiently. It can be appreciated that the power routing table is completely decoupled from the IP routing table of the power network, and the power routing table can be mapped onto the IP routing table to complete the forwarding operation.

Referring to fig. 3, fig. 3 is a schematic diagram illustrating a specific implementation procedure of another embodiment of the step S2000. As shown in fig. 3, step S2000 includes at least the following steps:

s2100, dynamically acquiring a change value of key value information in a database, and generating a calculation force state table.

It can be understood that, as known from the above step S1300, the cloud network writes the calculation force information thereof into the key value database in real time through the db-agent; meanwhile, the edge device can dynamically read the calculation force information in the key value database through the db-agent, so that the edge device can be ensured to dynamically acquire the change value of the calculation force information in the key value database.

It can be appreciated that after the change value and the calculation force information are acquired through the db-agent, the edge device generates a calculation force state table for representing the change of the calculation force information of the cloud network. Illustratively, in practical applications, the force state table is shown in table 1 below:

TABLE 1 force calculation State Table

S2200, generating a power calculation routing table according to the power calculation state table and SLA information of the power calculation network.

It is understood that the quality of service agreement (Service Level Agreement, SLA) information for the power network includes network SLA information and power resource SLA information. Wherein the network SLA information and the computing power resource SLA information are pre-configured on the network element by a controller of the network function domain.

It will be appreciated that SLA information of a power network is the underlying service in a communication service, i.e. the agreement by the service provider in the provided service to determine what level is to be achieved. The parameters required in the different power networks are not exactly the same. Illustratively, when the power network provides multiprotocol label switching (Multi-Protocol Label Switching, MPLS) virtual private network (Virtual Private Network, VPN) services, the SLA protocol it provides is described as follows: the SLA message of MPLS VPN provides the user with the promise of network availability (Network Availability), packet Success rate (Packet Success), delay time (Latency), jitter, fault acceptance time, etc. to provide the user with high-quality circuit and service, and to standardize the rights and obligations of both parties in the form of protocol. Illustratively, for the CPU occupancy rate of the computing resource, the network SLA information is that the message is advertised to the network element of the network domain if the CPU occupancy rate exceeds 70%; the computing resource SLA information is that in case that the CPU load exceeds 70%, the current service needs to reselect a new resource pool and index the traffic to the new resource pool.

Referring to fig. 4, fig. 4 is a schematic diagram illustrating a specific implementation procedure of another embodiment of the step S2200. As shown in fig. 4, step S2200 includes at least the steps of:

s2210, acquiring the computing power information matched with the SLA information in the computing power state table.

It can be understood that the power state table can dynamically represent the power information change of the cloud network, so in order to enable the edge device to guide forwarding of the data stream more pertinently, the power information matched with the SLA information in the power state table needs to be obtained, so as to screen the power state table, improve the success rate of guiding forwarding of the edge device, and reduce the operation time of the system. Illustratively, taking the SLA information of the power calculation network in the above steps as an example, a service gateway with a CPU load of not more than 70% in the power calculation state table is obtained.

S2220, screening the calculation force information according to the SLA information to generate a calculation force routing table.

It can be understood that after the computing power information matched with the SLA information in the computing power state table is obtained, the computing power information in the computing power state table is screened according to the index requirement on the computing power resource in the SLA information, and the computing power resource meeting the SLA information is selected so as to rapidly and accurately guide the data forwarding of the edge equipment. Taking the SLA information of the power calculation network in the above steps as an example, collecting the service gateways with the CPU load not exceeding 70% in the power calculation state table, and forming a power calculation routing table.

Illustratively, in practical application, part of the entries of the force routing table are shown in table 2 below:

TABLE 2 calculation force routing table

Service Id	Service GateWay
		Sid1	WG1(NODE SID1)
Sid2	WG2(NODE SID2)
		Sid3	WG2(NODE SID2)

It can be understood that, as can be seen from table 2, the calculation force routing table reflects the mapping relationship between the servers and the egress gateways in the cloud network, that is, characterizes the egress gateway information that satisfies the calculation force requirements of each service in the cloud network.

S3000, obtaining a forwarding path according to the calculation routing table and the pre-configured IP routing table, and executing forwarding operation.

It will be appreciated that the IP routing table includes entries for the network element to direct how the packet is forwarded and records the next hop network element to the destination IP. In order to ensure the real-time performance of the IP routing table in the computing network, the IP routing table in the computing network needs to be updated. It is understood that the characterizing items of the IP routing table include, but are not limited to, destination unit address, protocol type, priority, next hop, output interface, overhead, etc.

It will be appreciated that after the IP routing information is obtained, the IP routing table needs to be updated. The updating of the IP routing table specifically comprises the following steps: under the condition that a certain updated routing table item does not exist in the IP routing table, the routing table item is directly added in the routing table; under the condition that the routing table items of the same destination network exist in the routing table and the source ports are the same, the routing table is unconditionally updated according to the latest routing information; when the routing table has the routing table items of the same destination network but the source ports are different, the measurement values of the routing table items are compared, and the routing table item with the smaller measurement value is used as the own routing table item; under the condition that the routing table entries of the same destination network exist in the routing table and the metric values are equal, the original routing table entries are reserved. Illustratively, in practical application, a part of the table entries of the IP routing information are shown in the following table 3:

table 3 ip routing table

Prefix(Service Gateway)	Nexthop
		GW1(NODE SID1)	interface ip
GW2(NODE SID2)	sr policy(endpoint+color)

It can be appreciated that from table 3, the IP routing table reflects the mapping relationship between the egress gateway near the cloud network and the next hop device address in the computing network.

It will be appreciated that, as known from the above step S2200, the SLA information is used to normalize performance thresholds of various indicators in the computing power network, and operations that need to be performed after these performance thresholds have been exceeded. Therefore, by combining the calculation force state table and the SLA information, table items matched with the SLA information in the calculation force state table can be effectively updated and screened to form a calculation force routing table which is convenient for guiding the edge equipment to execute forwarding operation. It can be seen that the power routing table is completely decoupled from the IP routing table of the power network, and the power routing table can be mapped onto the IP routing table to complete forwarding operation.

It can be understood that the forming of the calculation power routing table is decoupled from the IP routing table, and the calculation power information of the cloud network is obtained in real time through the key value database, so that the real-time notification and the route guidance of the calculation power information in the calculation power network are realized. In addition, under the non-power network environment, the power notification and routing method in the power network can directly search the IP routing table to carry out path forwarding, thereby meeting the compatibility of the original network equipment and service.

Referring to fig. 5, fig. 5 is a schematic diagram illustrating a specific implementation procedure of another embodiment of the step S3000. As shown in fig. 5, step S3000 includes at least the following steps:

s3100, searching a computing force routing table according to computing force information, and acquiring a target exit gateway.

It can be understood that in the network operation process, the computing power information changes and triggers the matching condition in the SLA information, and the computing power state table and the computing power routing table are updated. The exit gateway meeting the service requirement and SLA information, namely the target exit gateway, can be obtained by searching the calculation force routing table.

It will be appreciated that the target egress gateway can direct traffic to a pool of cloud network resources that meet both computing power requirements and SLA information. In practical application, when the cloud network is provided with a load balancing (load balancing) unit, the target egress gateway can be set as the load balancing unit of the cloud network or a cloud-side egress network element connected with the load balancing unit of the cloud network, and the target egress gateway can also be set as an egress network element of the network domain according to requirements, which is not limited herein.

S3200, searching an IP routing table through the target exit gateway, and acquiring a next hop forwarding address corresponding to the target exit gateway.

It can be understood that the IP routing table is searched by the target egress gateway, so that the table entry of the computing power routing table can be mapped to the relevant table entry of the IP routing table, and the next hop forwarding address is obtained. Illustratively, as shown in tables 2 and 3, the egress Gateway (Service Gateway) of table 2 coincides with the egress Gateway (Prefix) of table 3 near the cloud network. Therefore, the power calculation routing table can be mapped to the IP routing table through the service gateway and the target unit address, and the next hop forwarding address meeting the power calculation requirement can be obtained.

S3300, the next hop forwarding address is advertised to the edge device.

It can be understood that, in the computing power network, the edge device is configured to perform a forwarding operation of the traffic between the network element and the cloud network, so that the edge device achieves dynamic notification of computing power and routing in the computing power network after acquiring the next hop forwarding address.

It can be understood that under the environment of a non-power network, the power notification and routing method in the power network is adopted to be consistent with the existing network, and the route forwarding is performed by directly searching the IP routing table, so that good adaptability is maintained for the existing network, and the compatibility of the power notification and routing method is ensured.

S3400, the edge device executes forwarding operation according to the next hop forwarding address.

It can be understood that after the computing power routing table is mapped to the IP routing table, the egress gateway of the resource pool meeting the service requirement can be mapped to the IP routing table, and the edge device forwards the address according to the next hop and executes the forwarding operation, so that the success rate and timeliness of the forwarding operation of the edge device are improved.

It can be understood that under the condition that the computing power routing table and the IP routing table are associated with each other, the network can perform computing power notification and computing power routing in real time by integrating computing power information, the IP routing table, network SLA information and computing power resource SLA information of the cloud network, so that timeliness and compatibility of network communication are improved, and influence of high-frequency change of computing power notification on the network communication is avoided. It can be appreciated that forwarding operation is performed according to the IP routing table, which belongs to the prior art and is not described herein.

It will be appreciated that the computational power routing table and the IP routing table obtained by the above steps are decoupled from each other in the process of directing the edge device to perform forwarding operations. The computing power routing table can represent computing power resources meeting computing power requirements and SLA information of the computing power network in real time, and conduct computing power notification and computing power routing guidance in real time. The forwarding flow is completed by mapping the computing power routing table to the IP routing table, so that the routing forwarding can be more efficiently guided, and the success rate and timeliness of forwarding information of the edge equipment are prevented from being influenced by computing power information of high-frequency change.

The method for notifying and routing the calculation power in the calculation power network comprises the following steps:

s4000, acquiring and storing computing power information of a cloud side server from a cloud network, so that edge equipment can read the computing power information and generate a computing power routing table according to the computing power information.

It can be understood that the database or the server registered by the database acquires and stores the calculation information of the cloud side server from the cloud network, so that the edge device can conveniently read the calculation information, and the edge device can be ensured to acquire the calculation information of the cloud network in real time. It can be appreciated that the database obtains and stores the computing power information from the cloud network through the management protocol, which is not described herein.

It is understood that the process of generating the computing force routing table according to the computing force information is consistent with the above step S2000, and will not be described herein.

Referring to fig. 6, fig. 6 is a schematic diagram illustrating a specific implementation procedure of another embodiment of the step S4000. As shown in fig. 7, step S4000 includes at least the following steps:

s4100, extracting the calculation force information to obtain key value information.

It can be understood that key value information capable of reflecting the running state of the cloud resource pool is generated by extracting key information of the calculation force information. Specifically, the process of extracting the key information is consistent with the above step S1120, and will not be described herein.

S4200, a key value database is built based on the key value information, so that the edge device can read the key value information in the key value database.

It can be understood that the database stores the calculation force information by establishing the key value database, so that the instantaneity and the efficiency of the calculation force information of the cloud side server stored in the database are improved, and the edge equipment can rapidly acquire the calculation force information and the change value thereof. Specifically, the process of creating the key value database according to the key value information is consistent with the above step S1120, and will not be described herein.

It can be understood that the edge device can dynamically read the calculation force information in the key value database through the db-agent, so as to complete the reading operation of the key value database. It can be understood that in the process of reading the key value information, no additional authentication of the management type protocol and the network layer protocol is needed, and the flow of the calculation sensing and the calculation notification is simplified.

Referring to fig. 7, fig. 7 shows a specific flowchart of a method for advertising and routing in a power network according to an embodiment of the present application. As shown in fig. 7, the specific flow of the method for advertising and routing the computing power in the computing power network at least includes the following steps:

it can be understood that, taking the CPU load of the cloud-side network element as an example in fig. 7, the network SLA information is that the message is advertised to the network element of the network domain if the CPU occupancy rate exceeds 70%; the computing resource SLA information is that in case that the CPU load exceeds 70%, the current service needs to reselect a new resource pool and index the traffic to the new resource pool. And consistent with the calculation force information in the step S2200, the gateway prefix of the cloud-side load balancing unit is 2011:1, and the service identifier is SID address 3589:3 of one SRV 6.

Firstly, under the condition that the CPU load of a container or a virtual machine in a computing power network exceeds 70% of a critical point, the database acquires the change value of the computing power information, and the built key-value model is written into a key value database through the db-agent to generate key value information.

And then, the edge equipment of the network domain reads the key value information in the key value database, and generates a calculation force state table by observing prefix information of the service mark in the key value information.

Then, the database actively announces to the edge device group in the event of any change in the prefix information of the class of service identification.

Then, the edge equipment group actively receives the calculation power information that the CPU load of the container or the virtual machine in the calculation power network exceeds 70%, and generates a calculation power routing table by combining the calculation power resource SLA information.

And then updating the computing power routing table, removing table entries of a computing power resource pool with the CPU load exceeding 70% in the computing power routing table, and obtaining the target export gateway meeting computing power requirements and SLA information.

And finally, mapping the target exit gateway to an IP routing table, and acquiring a next hop forwarding address corresponding to the target exit gateway. And the edge equipment performs forwarding operation according to the next hop forwarding address, and indexes the service traffic to a new resource pool. Therefore, in the process of selecting the route forwarding path, the route forwarding between the cloud network and the edge equipment group is controlled, so that the effects of dynamically carrying out calculation notification and routing are achieved. Because the formation of the calculation force routing table is decoupled from the IP routing table, the real-time notification of calculation force information is realized through the key value database; in addition, the computational power route generated by the computational power route table can be overlapped on the original IP route, so that good compatibility with the existing network is realized.

Fig. 8 shows an electronic device 600 provided by an embodiment of the present application. The electronic device 600 includes, but is not limited to:

a memory 601 for storing a program;

the processor 602 is configured to execute the program stored in the memory 601, and when the processor 602 executes the program stored in the memory 601, the processor 602 is configured to execute the method of computing power announcement and routing in the computing power network described above.

The processor 602 and the memory 601 may be connected by a bus or other means.

The memory 601 serves as a non-transitory computer readable storage medium that may be used to store non-transitory software programs and non-transitory computer-executable programs, such as the methods of computing power advertising and routing in a computing power network described in any of the embodiments of the present application. The processor 602 implements the power advertising and routing methods in the power network described above by running non-transitory software programs and instructions stored in the memory 601.

The memory 601 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store information for performing the methods of computing power advertising and routing in the computing power network described above. In addition, the memory 601 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some implementations, the memory 601 may optionally include memory located remotely from the processor 602, the remote memory being connectable to the processor 602 through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The non-transitory software programs and instructions required to implement the above-described methods of advertising and routing in a computing power network are stored in memory 601, which when executed by one or more processors 602, perform the methods of advertising and routing in a computing power network provided by any of the embodiments of the present application.

The embodiment of the application also provides a storage medium, which stores computer executable instructions for executing the method for notifying and routing the computing power in the computing power network.

In an embodiment, the storage medium stores computer-executable instructions that are executed by one or more control processors 602, for example, by one of the processors 602 in the electronic device 600, such that the one or more processors 602 perform the method of computing power advertising and routing in the computing power network provided by any embodiment of the present application.

The embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, i.e. may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Those of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically include computer readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and may include any information delivery media.

Claims (12)

1. A method of computing power advertising and routing in a computing power network, applied to an edge device, the method comprising:

acquiring computing power information of a cloud side server from a database, wherein the computing power information is acquired from a cloud network by the database;

generating a calculation force routing table according to the calculation force information;

and acquiring a forwarding path according to the calculated force routing table and a pre-configured I P routing table, and executing forwarding operation.

2. The method of claim 1, wherein the obtaining computing power information of the cloud-side server from the database comprises:

and reading key value information in a key value database in real time, wherein the key value information is generated according to the calculation force information, and the key value database is generated by the database according to the key value information.

3. The method of claim 2, wherein the generating the computing force routing table from the computing force information comprises:

dynamically acquiring a change value of the key value information in the database, and generating a calculation force state table;

and generating the power calculation routing table according to the power calculation state table and SLA information of the power calculation network.

4. A method according to claim 3, wherein said generating said power routing table from said power state table and SLA information of a power network comprises:

acquiring computing force information matched with the SLA information in the computing force state table;

and screening the calculation force information according to the SLA information to generate the calculation force routing table.

5. The method of claim 1, wherein the computing power routing table is used to characterize a mapping relationship between the cloud side server and an egress gateway; the IP routing table is used for representing the mapping relation between the exit gateway and the next hop forwarding address.

6. The method of claim 5, wherein the obtaining forwarding paths from the computing power routing table and a pre-configured IP routing table and performing forwarding operations comprises:

searching the computing force routing table according to the computing force information, and acquiring a target exit gateway;

and searching the IP routing table through the target exit gateway, and acquiring a next hop forwarding address corresponding to the target exit gateway.

7. The method of claim 6, wherein the searching the IP routing table through the target egress gateway, after obtaining the next hop forwarding address corresponding to the target egress gateway, further comprises:

advertising the next hop forwarding address to the edge device;

and the edge equipment executes forwarding operation according to the next hop forwarding address.

8. The method of any one of claims 1 to 7, wherein the computing force information comprises at least one of: service identifier, service gateway and network element performance parameters.

9. A method of computing power advertising and routing in a computing power network, the method comprising:

and acquiring and storing the computing power information of the cloud side server from the cloud network, so that the edge equipment can read the computing power information and generate a computing power routing table according to the computing power information.

10. The method according to claim 9, further comprising, after the acquiring and storing the computing power information of the cloud-side server from the cloud network:

extracting the calculation force information to obtain key value information;

and establishing a key value database based on the key value information so that the edge equipment can read the key value information in the key value database.

11. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1 to 8 when the computer program is executed; or a method as claimed in any one of claims 9 to 10.

12. A computer readable storage medium, characterized in that a computer program is stored, which computer program, when being executed by a processor, implements the method according to any of claims 1 to 8; or a method as claimed in any one of claims 9 to 10.