Computing power service transmission method and device, equipment and storage medium

Abstract

The invention provides a computing power service transmission method and device, equipment and a storage medium, and relates to the technical field of information transmission. The method is applied to a network system, the network system comprises a first gateway and a second gateway, the first gateway is connected with a computing power demand device, the second gateway is connected with a target computing power supply device, and the target computing power supply device is any one of a plurality of computing power supply devices. The method comprises the following steps: a first gateway receives a service request message sent by computing power demand equipment, wherein the service request message refers to a message that the computing power demand equipment requests a computing power service; and the first gateway determines a target computing power supply device based on the service request message. And the first gateway sends the service request message to the target computing power supply equipment through the second gateway.

Description

Technical Field

[0001] This application relates to the field of information transmission technology, and in particular, to a computing power service transmission method, apparatus, device, and storage medium. Background Art

[0002] Computing Power Service refers to a service that provides computing resources for users through cloud computing, distributed computing, or dedicated hardware. The computing power service supply side refers to various service providers and their infrastructure that provide computing resources, covering the entire industrial chain from hardware manufacturers to cloud service platforms, and is used to provide users with efficient, flexible, and reliable computing services to meet users' computing needs.

[0003] In the prior art, computing resources are usually allocated through a computing power router, and computing tasks are dynamically routed to the most suitable computing power node. Specifically, a user sends a computing power service request, and the computing power service request includes the destination Internet Protocol (IP) address that identifies the computing power service. After the computing power router determines the best service instance corresponding to the destination IP address, it sends the computing power service request to the best service instance, and processes the service request through the best service instance to provide computing services.

[0004] However, using the IP address as the identifier of the computing power service is prone to security risks due to the exposure of the IP address, which may lead to problems such as interruption of the computing power service and data leakage. Summary of the Invention

[0005] This application provides a computing power service transmission method, apparatus, device, and storage medium, which improves the security of computing power service transmission.

[0006] To achieve the above object, this application adopts the following technical solutions:

[0007] In a first aspect, this application provides a computing power service transmission method, which is applied to a network system. The network system includes: a first gateway and a second gateway. The first gateway is connected to a computing power demand device, and the second gateway is connected to a target computing power supply device. The method includes:

[0008] The first gateway receives a service request message sent by the computing power demand device.

[0009] The first gateway determines a target computing power supply device based on the service request message.

[0010] The first gateway sends the service request message to the target computing power supply device through the second gateway.

[0011] Among them, the service request message refers to the message sent by the computing power demand device to request computing power services, and the target computing power supply device is any one of multiple computing power supply devices.

[0012] In the solution provided by this application, by connecting the first gateway and the second gateway to the computing power demand device and the computing power supply device respectively, while realizing the message transmission between the computing power demand device and the computing power supply device, the gateway identifies the transmitted message, isolates the message transmission process into multiple segments of routing, and effectively avoids the security risk of IP address exposure.

[0013] A possible implementation manner is that the first gateway determines the target computing power supply device based on the service request message. Specifically, it can be implemented as follows: The first gateway parses the service request message to obtain the first Uniform Resource Locator (URL) in the service request message, and determines the target computing power supply device based on the first URL. Among them, the first URL is used to identify the type of computing power service in the service request message. By using the first URL to identify the type of computing power service, the identification has nothing to do with network routing, and it can realize the access of remote devices and the termination of routing while avoiding IP exposure.

[0014] Another possible implementation manner is that the first gateway determines the target computing power supply device based on the first URL. Specifically, it can be implemented as follows: The first gateway searches the computing power service type table based on the first URL to find the candidate computing power supply devices corresponding to the first URL; and determines the target computing power supply device from the candidate computing power supply devices based on the computing power scheduling policy. Among them, the computing power service type table is used to record the correspondence between the first URL and the computing power supply device, and the computing power scheduling policy is used to screen the candidate computing power supply devices. By using the first URL to screen out the candidate computing power supply devices that meet the computing power service type, and then determining the target computing power supply device from the candidate computing power supply devices according to the computing power scheduling policy, the determination of the target computing power supply device is more efficient and accurate, and at the same time, it can flexibly screen the target supply device among the candidate computing power supply devices to ensure the quality and stability of the provided computing power services.

[0015] Another possible implementation manner is that the first gateway sends the service request message to the target computing power supply device through the second gateway. Specifically, it can be implemented as follows: The first gateway sends the service request message to the second gateway through the target transmission link corresponding to the target computing power supply device, and the second gateway sends the service request message to the target computing power supply device. By using the corresponding target transmission link, the mutual interference in the message transmission process is reduced, and the security of the message transmission is guaranteed.

[0016] Another possible implementation manner is that the target transmission link is an exclusive transmission link corresponding to the target computing power supply device. By using the exclusive transmission link, the service quality of the message transmission is guaranteed, and the message transmission efficiency is improved.

[0017] In another possible implementation, the first gateway sends the service request message to the second gateway through the target transmission link corresponding to the target computing power supply device. Specifically, it can be implemented as follows: The first gateway encapsulates the service request message and the global identifier (Global ID, GID) of the target computing power supply device, and sends the encapsulated service request message and / or GID to the second gateway through the target transmission link corresponding to the target computing power supply device. By uniquely identifying the target computing power supply device with the GID, the efficiency and accuracy of determining the target computing power supply device are improved.

[0018] In another possible implementation, the second gateway sends the service request message to the target computing power supply device. Specifically, it can be implemented as follows: The second gateway parses the service request message to obtain the first URL in the service request message, modifies the first URL in the service request message to the second URL, and then sends the service request message to the target computing power supply device. Herein, the second URL includes the actual interface corresponding to the target computing power supply device. Rewriting the first URL to the second URL avoids the failure of the computing power service request caused by the difference between the actual interface of the target computing power supply device and the interface information recorded on the first gateway side.

[0019] In another possible implementation, the computing power service transmission method provided in the embodiments of the present application further includes: The second gateway sends the service response sent by the target computing power supply device to the computing power demand device through the first gateway. By feeding back the service response to the computing power demand device through the first gateway, while ensuring information security, it is convenient to determine the computing power demand device that sends the service request message.

[0020] In a second aspect, the present application provides a computing power service transmission device, which includes a receiving module, a processing module, and a sending module.

[0021] The above receiving module is used to receive the service request message sent by the computing power demand device.

[0022] The above processing module is used to determine the target computing power supply device based on the service request message.

[0023] The above sending module is used to send the service request message to the target computing power supply device through the second gateway.

[0024] Herein, the service request message refers to the message for the computing power demand device to request the computing power service.

[0025] In a possible implementation, the above processing module is further used to: Parse the service request message to obtain the first uniform resource locator URL in the service request message, and determine the target computing power supply device based on the first URL. Herein, the first URL is used to identify the type of the computing power service in the service request message.

[0026] In another possible implementation manner, the above processing module is further configured to: based on the first URL, look up a candidate computing power supply device corresponding to the first URL in the computing power service type table; and determine a target computing power supply device from the candidate computing power supply devices based on the computing power scheduling policy. The computing power service type table is used to record the correspondence between the first URL and the computing power supply device, and the computing power scheduling policy is used to screen the candidate computing power supply devices.

[0027] In another possible implementation manner, the above sending module is further configured to: send the service request message to the second gateway through the target transmission link corresponding to the target computing power supply device, and the second gateway sends the service request message to the target computing power supply device.

[0028] In another possible implementation manner, the target transmission link is an exclusive transmission link corresponding to the target computing power supply device.

[0029] In another possible implementation manner, the above processing module is further configured to: encapsulate the service request message and the global identifier GID of the target computing power supply device. The above sending module is further configured to: send the encapsulated service request message and / or GID to the second gateway through the target transmission link corresponding to the target computing power supply device.

[0030] In another possible implementation manner, the above sending module is further configured to: parse the service request message to obtain the first URL in the service request message, modify the first URL in the service request message to the second URL, and then send the service request message to the target computing power supply device. The second URL includes the actual interface corresponding to the target computing power supply device.

[0031] In another possible implementation manner, the above sending module is further configured to: send the service response sent by the target computing power supply device to the computing power demand device through the first gateway.

[0032] For the technical effects corresponding to any implementation manner in the second aspect, reference may be made to the technical effects corresponding to any implementation manner in the first aspect above, which will not be elaborated here.

[0033] In a third aspect, a computer device is provided. The computer device includes: a processor and a memory. At least one computer program is stored in the memory, and at least one computer program is loaded and executed by the processor to implement the computing power service transmission method in the above aspect.

[0034] In a fourth aspect, a computer-readable storage medium is provided. At least one computer program is stored in the computer-readable storage medium, and at least one computer program is loaded and executed by the processor to implement the computing power service transmission method in the above aspect.

[0035] Fifth aspect, a computer program product is provided, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the computing power service transmission method in the above aspect is implemented.

[0036] The solutions provided in the above third aspect to fifth aspect are used to implement the method provided in the above first aspect, and their specific implementations will not be elaborated one by one. For the technical effects corresponding to any implementation manner in the solutions provided in the above third aspect to fifth aspect, reference can be made to the technical effects corresponding to any implementation manner in the above first aspect, which will not be elaborated here.

[0037] It should be noted that, on the premise that the solutions do not conflict, all possible implementation manners in any one of the above aspects can be combined. Description of the Drawings

[0038] Figure 1 Schematic diagram of the network structure of a CFN provided for an exemplary embodiment;

[0039] Figure 2 Schematic diagram of the network structure of a proxy server provided for an exemplary embodiment;

[0040] Figure 3 Schematic diagram of the network structure of a forward proxy provided for an exemplary embodiment;

[0041] Figure 4 Schematic diagram of the network structure of a reverse proxy provided for an exemplary embodiment;

[0042] Figure 5 Schematic diagram of the structure of a network system provided for an exemplary embodiment;

[0043] Figure 6 Schematic diagram of the process of a computing power transmission method provided for an exemplary embodiment;

[0044] Figure 7 Schematic diagram of the process of another computing power transmission method provided for an exemplary embodiment;

[0045] Figure 8 Schematic diagram of the structure of a computing power service transmission system provided for an exemplary embodiment;

[0046] Figure 9 Schematic diagram of the structure of a computing power service gateway provided for an exemplary embodiment;

[0047] Figure 10 Schematic diagram of the process of a computing power service transmission provided for an exemplary embodiment;

[0048] Figure 11Schematic diagram of a computing power service transmission device provided for an exemplary embodiment;

[0049] Figure 12 Schematic diagram of a computer device provided for an exemplary embodiment. Detailed implementation manners

[0050] In the embodiments of the present application, in order to facilitate a clear description of the technical solutions of the embodiments of the present application, terms such as "first" and "second" are used to distinguish identical or similar items with basically the same functions and roles. Those skilled in the art can understand that the terms "first", "second", etc. do not limit the quantity and execution order, and the terms "first", "second", etc. do not necessarily mean different. There is no sequential or size order between the technical features described by the "first" and "second".

[0051] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner for easy understanding.

[0052] In the embodiments of the present application, at least one can also be described as one or more, and multiple can be two, three, four or more, which is not limited in the present application.

[0053] In addition, the network architectures and scenarios described in the embodiments of the present application are for a clearer illustration of the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those of ordinary skill in the art know that with the evolution of network architectures and the emergence of new service scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0054] For ease of understanding, the terms involved in the embodiments of the present application are first explained.

[0055] Computing power service: It refers to a computing power service provided on demand for users by taking computing power (such as Central Processing Unit (CPU), Graphics Processing Unit (GPU), Tensor Processing Unit (TPU) for accelerating deep learning and machine learning tasks, Field-Programmable Gate Array (FPGA), etc.) as the core resource through cloud computing, distributed computing or a dedicated hardware cluster. Computing power service transmission refers to the process of data flow between the user side and computing power resources during the use of computing power services (such as cloud computing, supercomputing centers, etc.), including input data transmission (for example: uploading task data, code, configuration, demand messages), data exchange during the computing process (for example: communication between distributed computing nodes), and output data transmission (for example: returning computing results, logs, etc.).

[0056] Computing power demand device: It refers to a terminal or system that needs external computing power to complete tasks, usually limited by local computing power, energy consumption or cost, and relying on cloud or distributed computing power resources. For example: smartphones / tablets, industrial sensors, scientific research workstations, autonomous vehicles, blockchain light nodes, etc. The computing power of the computing power demand device itself is limited, and external computing power needs to be called on demand to achieve corresponding functions.

[0057] Computing power supply device: It refers to the hardware facilities that provide computing power, usually centrally deployed in data centers or distributed networks, and output computing power in the form of services. For example: general CPU servers, GPU acceleration cards, quantum computers, FPGAs, etc. As an example, the computing power demand device initiates a computing request through the Application Programming Interface (API) / Software Development Kit (SDK), and the computing power supply device automatically allocates computing power and returns the result.

[0058] Gateway: It refers to an intermediate node in a computer network that connects different protocols, architectures, or networks, and is used to implement data format conversion, protocol translation, and network interconnection to ensure effective communication between heterogeneous networks. Specifically, the functions that a gateway can implement include protocol conversion, data format translation, network interconnection, security control, and traffic scheduling, etc. Protocol conversion means converting data between networks with different protocols. For example, the conversion from the Transmission Control Protocol / Internet Protocol (TCP / IP) to the Zigbee protocol. Data format translation means parsing and reorganizing data packets. For example, the parsing from the Hypertext Transfer Protocol (HTTP) to the Message Queuing Telemetry Transport (MQTT). Network interconnection means connecting networks with different structures. For example, the connection between a Local Area Network (LAN) and a Wide Area Network (WAN), or the connection between a 5G network and an Ethernet network. Security control means configuring functions such as firewalls, Virtual Private Networks (VPNs), and access privilege management. Traffic scheduling means load balancing and routing selection, etc.

[0059] It should be noted that the information (including but not limited to device information, object personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.), and signals involved in this application are all authorized by the object or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards. For example, the service request messages, computing power requirement type tables, Uniform Resource Locators, etc. involved in this application are all obtained under full authorization.

[0060] The commonly used computing power service transmission method in the industry is usually implemented through a computing power router or a proxy server, which is briefly described below.

[0061] Method 1: Implement through a computing power router.

[0062] Exemplarily, the computing power service is identified using an IP address. The same IP address is assigned to multiple servers or nodes, and the requests from computing power demand devices are routed to the "nearest" or "optimal" node according to the routing protocol. Specifically, in the Compute First Networking (CFN) architecture, the computing power router serves as the CFN node. The computing power service and the service instances under the computing power service are identified through a Service Identifier (SID), without the need to care about the specific service instance that processes the computing power service request. Exemplarily, a special range or encoded anycast IP address or Domain Name System (DNS) is used as the SID. Here, a service instance refers to a service process or container that runs independently in a distributed system or microservices architecture and can provide specific functions externally (such as APIs, data processing, business logic, etc.). The Border Gateway Protocol Identifier (BID) is used as the unicast IP address of a service instance. The mapping between the BID and the SID changes dynamically, depending on the network state and available resources at the time when the computing power service request is generated. When a new service instance is instantiated, destroyed, or its performance metrics change (such as load changes), the service instance needs to notify the CFN Node to which it is attached of the mapping relationship between the BID and the SID.

[0063] Such as Figure 1As shown in the figure, the CFN includes CFN node1, CFN node2, and CFN node3. There are three CFN nodes in CFN node2. The computing power services SID1 and SID2 are attached to both CFN node2 and CFN node3. The computing power service SID1 includes Service Instance1 and Service Instance3, and the computing power service SID2 includes Service Instance2 and Service Instance4. BID21 is used as the IP address of Service Instance1, BID22 is used as the IP address of Service Instance2, BID32 is used as the IP address of Service Instance3, and BID33 is used as the IP address of Service Instance4. The CFN is deployed on the edge side of the operator's access network. The CFN forwards the computing power service information flow from the client / computing power demand device to the service instance. When the client sends a computing power service request, the SID is used as the destination IP of the service request message and is sent to the "optimal" service instance attached to the CFN node. A computing power service request is usually the first packet of a data stream. After the CFN node determines the "optimal" service instance, all data packets belonging to this data stream will be processed by the same service instance.

[0064] Method 2: Implement through an HTTP proxy server.

[0065] Exemplarily, as Figure 2 shown, in the absence of a proxy server, the request message / response message is directly transmitted between the computing power demand device 200 and the computing power supply device 210. In the mode with a proxy server 220, the request message / response message is forwarded between the computing power demand device 200 and the computing power supply device 210 through the proxy server 220. Specifically, the methods for implementing computing power service transmission through a proxy server include forward proxy and reverse proxy. Forward proxy means that the proxy server proxies the browser / client to redirect the computing power service request to access the proxy service of the target server. As Figure 3 shown, the object proxied by the proxy server 300 is the browser / client 301 (computing power demand device), and the browser / client 301 is unknown to the target server (computing power supply device 302). Reverse proxy means that the browser / client directly accesses the proxy server, and the proxy server then distributes the computing power service request to the computing power supply device through reverse proxy, load balance, etc. As Figure 4As shown, the object proxied by the proxy server 400 is the computing power supply device 401, which is unknown to the browser / client 402. Load balancing means distributing computing power service requests to the computing power supply devices in the cluster mode through load balancing algorithms. Even if a certain computing power supply device fails to work properly, other computing power supply devices can still receive computing power service requests normally, and the computing power supply devices in the cluster mode support vertical scaling and can handle high-concurrency application scenarios brought about by the rapid growth of business.

[0066] However, Method 1 uses the IP address as the identifier of the computing power service request, which has the security risk of location exposure. Moreover, the IP address has both the identification function and the destination address function. The computing power demand device needs to directly send the computing power service request to the destination address, which does not have the characteristic of terminating routing, and conflicts are likely to occur when the IP information of the destination address and the computing power service identifier is different. In addition, a server with the same IP address can operate multiple computing power service software, and the corresponding relationship between the IP address and the computing power service software needs to be specially set. And the proxy server of Method 2 works at the application layer and cannot control the service quality of the computing power service transmission message during network transmission.

[0067] Based on this, the present application provides a computing power service transmission method. By connecting the first gateway and the second gateway to the computing power demand device and the computing power supply device respectively, while realizing the message transmission between the computing power demand device and the computing power supply device, the gateway identifies the transmitted message, and isolates the message transmission process into multiple segments of routing, effectively avoiding the security risk of the IP address being exposed outward.

[0068] The following specifically elaborates on the solution provided by the embodiments of the present application in conjunction with the accompanying drawings.

[0069] The solution provided by the present application can be applied to Figure 5 the network system shown in Figure 5 the architecture schematic diagram of the network system shown. The network system includes a first gateway 501, a second gateway 502, a computing power demand device 503 connected to the first gateway 501 through the demand-side network domain 506, and a computing power supply device 504 connected to the second gateway 502 through the supply-side network domain 507. Information is transmitted between the first gateway 501 and the second gateway 502 through the wide area network 505.

[0070] Exemplarily, the first gateway 501 and the second gateway 502 are devices for receiving and sending packets. The first gateway 501 and the second gateway 502 can also be devices for parsing, encapsulating, and other processing of packets. The first gateway 501 and the second gateway 502 can also be devices for scheduling computing power resources according to the computing power scheduling policy. The first gateway 501 and the second gateway 502 can also be devices for configuring routing paths, security restrictions, and computing power service information. The first gateway 501, the second gateway 502, 503, and the computing power supply device 504 can be independent physical servers, or a server cluster or distributed system composed of multiple physical servers. They can also be cloud servers, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery network (CDN), and cloud servers providing basic cloud computing services such as big data. The embodiments of the present application do not limit the implementation manner and application scenario of the computer device 100.

[0071] Figure 5 An example shows a computing power demand device, a first gateway, a second gateway, and a computing power supply device, but it is not limited thereto. The embodiments of the present application do not limit the number and connection relationship of the computing power demand device, the first gateway, the second gateway, and the computing power supply device.

[0072] Figure 6 A computing power service transmission method provided for an exemplary embodiment is implemented through a network system. The network system includes a first gateway and a second gateway. The first gateway is connected to the computing power demand device, and the second gateway is connected to the target computing power supply device. The target computing power supply device is any one of multiple computing power supply devices. The first gateway can be Figure 5 the first gateway in Figure 5 or other transit devices connected to the computing power service demand device. The second gateway can be

[0073] As Figure 6 shown, the computing power service transmission method provided by the embodiments of the present application may include:

[0074] Step S601: The first gateway receives a service request packet sent by the computing power demand device.

[0075] Among them, the service request packet refers to a packet in which the computing power demand device requests a computing power service.

[0076] Optionally, the service request packet includes the computing power service identifier requested by the computing power demand device, the purpose of the computing power service, resource configuration, operating environment, security configuration, etc.

[0077] Among them, the computing power service identifier is used to uniquely identify the computing power service, facilitating the determination and management of the computing power service. For example: The computing power service is uniquely identified by the request identifier (request_id) and the task identifier (task_id).

[0078] The purpose of the computing power service is used to indicate the type and business objectives of the computing power service. For example: The types of computing power services can include; cloud computing services, high-performance computing services (High-Performance Computing, HPC), edge computing services, etc.

[0079] Resource configuration is used to configure the computing resources of the computing power service, such as: CPU, GPU, memory, storage, etc.

[0080] The running environment is used to specify the software environment required for the computing power service to run. For example: container images, dependency libraries, etc.

[0081] Security configuration is used to configure the security protection policies during the execution of the computing power service, such as: data encryption, access control, etc.

[0082] Optionally, the styles of the service request message include the Representational State Transfer (RESTful API) style based on HTTP, the Remote Procedure Call (gRPC) style, and the GraphQL (GraphQL) style, etc.

[0083] Exemplarily, communication connection is achieved between the first gateway and the computing power demand device through the basic network to transmit messages or other information. For example: The first gateway monitors specific ports (such as HTTP 80 / 443, gRPC 50051) and receives the service request message sent by the computing power service device.

[0084] Step S602: The first gateway determines the target computing power supply device based on the service request message.

[0085] Among them, the target computing power supply device refers to the computing power supply device (service instance) that provides the computing power service required by the computing power demand device.

[0086] Exemplarily, the first gateway parses the message information in the service request message to determine the computing power service requested by the service request message, and then determines the corresponding target computing power supply device based on the computing power service.

[0087] Specifically, the first gateway initializes a parser corresponding to the protocol type according to the protocol type of the service request message (such as HTTP, gRPC, open source distributed stream processing platform (Kafka)), performs protocol parsing and decoding on the service request message, and then performs steps such as security verification, service parameter verification, resource scheduling, load balancing, and message forwarding based on the parsed service request message.

[0088] Among them, the protocol parsing methods include parsing through a lightweight data interchange format (JavaScript Object Notation, JSON) parser and a markup language (Extensible Markup Language, XML) parser, or parsing byte by byte according to a predefined format, etc.

[0089] Security verification includes identity authentication, permission control, etc. For example: performing whitelist or IP restrictions.

[0090] Service parameter verification includes field verification (such as: checking whether service_type, resources, etc. exist), parameter legality verification (such as: whether the GPU model is supported, whether the memory / storage exceeds the quota), and dependency conflict verification (such as: rejecting when requesting GPU and TPU simultaneously).

[0091] Load balancing refers to selecting a node according to the current cluster load of the computing power service providing device. For example: selecting a node through round-robin / least connections, etc.

[0092] Message forwarding includes steps such as determining the routing path and encapsulating and processing the message.

[0093] Step S603: The first gateway sends the service request message to the target computing power supply device through the second gateway.

[0094] Exemplarily, the first gateway sends the service request message to the second gateway, and the second gateway parses the service request message to determine the target computing power supply device, and forwards the service request message to the target computing power supply device to provide computing power services.

[0095] In summary, the computing power service transmission method provided by the embodiments of the present application connects the computing power demand device and the computing power supply device through the first gateway and the second gateway respectively. While realizing the message transmission between the computing power demand device and the computing power supply device, the gateway identifies the transmitted message, isolates the message transmission process into multiple segments of routing, and effectively avoids the security risk of the IP address being exposed outward.

[0096] Figure 7 Another computing power service transmission method provided for an exemplary embodiment.

[0097] Such as Figure 7As shown in the figure, the computing power service transmission method provided by the embodiment of the present application is implemented through a network system. The network system includes a first gateway and a second gateway. The first gateway is connected to the computing power demand device, and the second gateway is connected to the target computing power supply device, where the target computing power supply device is any one of multiple computing power supply devices. The first gateway can be the first gateway in Figure 5 or other transit devices connected to the computing power service demand device. The second gateway can be the second gateway in Figure 5 or other transit devices connected to the computing power service supply device.

[0098] As Figure 7 shown in the figure, the computing power service transmission method provided by the embodiment of the present application may include:

[0099] Step S701: The first gateway receives a service request message sent by the computing power demand device.

[0100] For the introduction of this step, refer to step S601, which will not be elaborated here.

[0101] Step S702: The first gateway parses the service request message to obtain the first URL in the service request message.

[0102] Among them, the URL is used to identify the type of computing power service requested by the service request message.

[0103] Optionally, the URL includes information such as the protocol used to access the resource (such as HTTP, File Transfer Protocol (FTP)), the address of the server where the resource is located, the access port (Port) of the resource on the server, the path to reach the server (Path), and the query parameters (Query Parameters) for passing additional parameters to the server.

[0104] Exemplarily, the type of computing power service is identified by the URL-Path, and the URL-Path provides a unified entry for the computing power service demand device to access a certain type of computing power service. For example: different types of computing power services are identified by / api / a, / api / b, / api / p / a, etc.

[0105] In some embodiments, after the first gateway parses the URL-Path in the service request message, the URL-Path is concatenated with the IP address and port of the first gateway to form a complete first URL.

[0106] Step S703: The first gateway determines the target computing power supply device based on the first URL.

[0107] Exemplarily, based on the first URL, the first gateway looks up the candidate computing power supply devices corresponding to the first URL in the computing power service type table, that is, all computing power supply devices that can provide the computing power service type requested by the service request message.

[0108] Among them, the computing power service type table is used to record the correspondence between the first URL and the computing power supply devices.

[0109] Exemplarily, the computing power service type table is configured in the first gateway. As shown in Table 1, it is a computing power service type table provided by an embodiment of the present application.

[0110] Table 1: Computing Power Service Type Table

[0111]

[0112] Among them, the computing power scheduling strategy is used to screen the candidate computing power supply devices.

[0113] Exemplarily, based on the computing power scheduling strategy, the first gateway determines the target computing power supply device from the candidate computing power supply devices.

[0114] Optionally, the computing power scheduling strategy includes dynamic scheduling, load balancing scheduling, weight-based traffic splitting, multi-factor scheduling algorithm selection, etc.

[0115] The dynamic scheduling strategy refers to a strategy that dynamically adjusts resource allocation according to the real-time state of the system (such as load and resource utilization rate), and is applicable to scenarios with large load fluctuations or frequent changes in task priorities (such as cloud computing).

[0116] Load balancing scheduling means evenly distributing the computing power service to all computing nodes to avoid overloading of some nodes. For example: round-robin (assigning tasks to each node in turn), least load first (selecting the node with the lowest current load), consistent hashing (reducing data migration when nodes change), etc.

[0117] Weight-based traffic splitting refers to a resource management strategy that distributes the computing tasks of the computing power service to different nodes through dynamic weight allocation. For example: allocating computing power according to task type, node capabilities, business priorities, etc., and high-priority tasks are allocated first.

[0118] Multi-factor scheduling algorithm selection refers to a resource allocation method that dynamically selects the optimal scheduling strategy by comprehensively evaluating multi-dimensional decision-making indicators (such as computing resources, network status, cost, business priorities, etc.). For example: dynamically switching or adjusting the scheduling strategy algorithm (such as switching from load balancing to energy consumption priority).

[0119] Exemplarily, the computing power service type table supports adding, deleting, modifying, and querying multiple types of computing power services, and records the key data fields corresponding to each computing power service.

[0120] Step S704: The first gateway sends the service request message to the second gateway through the target transmission link corresponding to the target computing power supply device.

[0121] Among them, the target transmission link is the exclusive transmission link corresponding to the target computing power supply device. For example: The target transmission link is a QoS flow that can guarantee the transmission quality (Quality of Service, QoS) of the computing power service.

[0122] Optionally, the embodiment of the present application does not limit the implementation method of the logical communication link of the QoS flow. For example: the SID list (sidlist) of the network architecture (srv6), VPN, etc. The receive and send bidirectional flows can be set separately, or the traffic can be received and sent simultaneously through one channel.

[0123] Exemplarily, the steps for the first gateway to determine the exclusive transmission link are as follows:

[0124] Step 1: The first gateway determines the GID corresponding to the target computing power supply device.

[0125] Among them, the GID is used to uniquely identify the target computing power supply device (P-GID) / the computing power service on the first gateway side (D-GID).

[0126] Optionally, the GID includes the gateway identifier (Gateway ID, GWID) of the first gateway, the SID indicating the type of computing power service, the target computing power supply device ID, etc.

[0127] Exemplarily, the first gateway queries the computing power supply device table and the correspondence table between the first URL and the computing power supply device, and determines the GID corresponding to the target computing power supply device based on the first URL and the computing power scheduling policy. For example: As shown in Table 2 and Table 3:

[0128] Table 2: Computing power supply device table

[0129]

[0130] Table 3: Correspondence table between the first URL and the computing power supply device

[0131]

[0132]

[0133] Exemplarily, the computing power supply device table supports adding, deleting, modifying, and querying multiple computing power supply devices (computing power service instances) on the supply side, and their corresponding key data fields.

[0134] In Table 2, fields 1 - 3 are configured during the creation, deletion, modification, and query of computing power service instances. Field 4 identifies the status information of the computing power service instances on the supply side and is updated periodically according to the real - time requirements of the computing power scheduling information. For example, it is updated through methods such as inter - gateway routing protocol announcements or periodic northbound interface transmissions.

[0135] In Table 3, fields 1 and 2 are automatically generated through Table 1, and field 3 is automatically generated through Table 2, without the need for administrator configuration, and query and debugging are supported.

[0136] Step 2: The first gateway determines the dedicated transmission link corresponding to the target computing power supply device according to the GID.

[0137] Exemplarily, the first gateway queries the correspondence table of computing power services and transmission links according to the GID to determine the dedicated transmission link. For example: as shown in Table 4:

[0138] Table 4: Correspondence table of computing power services and transmission links

[0139]

[0140]

[0141] In some embodiments, the first gateway encapsulates the service request message and the GID of the target computing power supply device, and sends the encapsulated service request message and GID to the second gateway through the target transmission link corresponding to the target computing power supply device, facilitating the second gateway to resolve the information of the target computing power supply device according to the GID.

[0142] Step S705: The second gateway sends the service request message to the target computing power supply device.

[0143] Exemplarily, the second gateway parses the service request message to obtain the first URL in the service request message.

[0144] In some embodiments, the second gateway determines the target computing power supply device as follows:

[0145] Method 1: Determine directly according to the GID.

[0146] Exemplarily, query the correspondence table of the second - gateway - side URL and the computing power supply device according to the GID.

[0147] For example: as shown in Table 5:

[0148] Table 5: Correspondence table of the second - gateway - side URL and the computing power supply device

[0149]

[0150]

[0151] Exemplarily, the correspondence table between the second gateway-side URL and the computing power supply device supports adding, deleting, modifying and checking multiple computing power supply devices (computing power service instances) and their corresponding key data fields.

[0152] For example, fields 1-5 in Table 5 are configured when adding, deleting, modifying, or checking a computing service instance. Field 8 identifies the status information of the computing service instance and is updated regularly based on the real-time nature of the information required for computing scheduling. For example, it is updated by active detection or regular reporting of computing service instances, regular delivery of northbound interfaces, and so on.

[0153] Method 2: First query the correspondence table between the computing power service and the transmission link on the second gateway side according to the dedicated transmission link, determine the GID, and then determine the target computing power supply device according to the GID.

[0154] For example, as shown in Table 6:

[0155] Table 6: Correspondence between computing power services and transmission links on the second gateway side

[0156]

[0157] In some embodiments, since the actual address of the target computing power supply device is different from the address recorded in the first gateway, the second gateway modifies the first URL in the service request message to the second URL and then sends the service request message to the target computing power supply device.

[0158] Among them, the second URL includes the actual interface corresponding to the target computing power supply device, for example: the actual IP address, port number, path, etc. of the target computing power supply device.

[0159] Step S706: The second gateway sends the service response sent by the target computing power supply device to the computing power demanding device through the first gateway.

[0160] The service response refers to a response returned by the second gateway based on the service request message.

[0161] Optionally, the service response includes a response status code (such as 200OK indicating that the request is successful and computing resources have been allocated), a timestamp (such as the time when the service response is generated), resource configuration and network configuration of the target computing power supply device (such as bandwidth limit, allocated memory size), access credentials (such as keys, remote login address), billing information (such as estimated fees), computing power service status (such as queued, executing, completed, failed), error information (such as error codes indicating insufficient resources), monitoring interfaces (such as resource usage query APIs), etc.

[0162] Exemplarily, the second gateway encapsulates the service response and sends it to the first gateway. After the first gateway de-encapsulates the service response, it forwards it to the computing power demand device.

[0163] In summary, in the computing power service transmission method provided by the embodiments of the present application, by connecting the first gateway and the second gateway to the computing power demand device and the computing power supply device respectively, while realizing the message transmission between the computing power demand device and the computing power supply device, the type of the computing power service is identified by the URL, and the message transmission process is isolated into multiple segments of routing to achieve routing termination. Combined with the API interface, the security risk of IP address exposure is effectively avoided; at the same time, the service quality of message transmission is guaranteed through the dedicated transmission link, and the transmission efficiency, flexibility and security of the message are improved. In addition, the dedicated transmission link corresponds to the target computing power supply device, improving the convenience of determining the target computing power supply device.

[0164] Figure 8 It is a schematic structural diagram of a computing power service transmission system provided for an exemplary embodiment. As Figure 8 shown, the computing power service transmission system provided by the embodiments of the present application includes a first gateway 800 and a second gateway 810. The first gateway 800 includes configuration management 801 and traffic processing 802. The configuration management 801 includes computing power service configuration 803, routing table entry 804 and QoS configuration 805. The traffic processing 802 includes a message processing module 806, a computing power service routing 807 and a QoS flow processing module 808. The second gateway 810 includes configuration management 811 and traffic processing 812. The configuration management 811 includes computing power service configuration 813 and QoS configuration 814. The traffic processing 812 includes a message processing module 815 and a QoS flow processing module 816.

[0165] Among them, since the service request message and the service response are paired, and the sending and receiving of the QoS flow also appear in pairs, the QoS flow processing module is peer in the first gateway 800 and the second gateway 810.

[0166] Specifically, in order to enable the gateway to be flexibly applied to the computing power demand device side or the computing power supply device side, the same gateway can be built-in with two processing modules so that the gateway can be used as the first gateway or the second gateway. Exemplarily, Figure 9 It is a schematic structural diagram of a computing power service gateway provided for an exemplary embodiment. As Figure 9 shown, the configuration management of the computing power service gateway includes global configuration 900, computing power service configuration 910, routing table entry 920 and QoS configuration 930. The global configuration 900 includes device address 901, gateway identifier 902 and computing power type table 903. The computing power service configuration 910 includes demand-side computing power service configuration 911 and supply-side computing power service configuration 912. The QoS configuration 930 includes QoS flow receive configuration 931 and QoS flow send configuration 932.

[0167] Traffic processing includes a packet processing module 940, a computing power service routing 950, and a QoS flow processing module 960. The packet processing module 940 includes a demand-side packet processing 941 and a supply-side packet processing 942. The QoS flow processing module 960 includes a QoS flow receive processing 961 and a QoS flow transmit processing 962.

[0168] Among them, the second gateway 810 identifies traffic through the P-GID and does not require routing.

[0169] The packet processing module 806 listens for service request packets according to Table 1. The IP address of the listened service is the local address of the first gateway, and the TCP port number can be globally specified or set for each computing power service type as needed. The service request packet is in the HTTP API request format, which includes URL information. If more information is needed to select a computing power service instance, more information can be appended in the HTTP message header of the request packet.

[0170] Figure 10 A schematic diagram of a computing power service transmission process provided for an exemplary embodiment. As Figure 10 shown, the computing power service transmission process includes:

[0171] Step S1001: The computing power demand device initiates a service request packet.

[0172] Step S1002: The packet processing module of the first gateway parses the service request packet, extracts information such as URL-Path, computing power service factors, and content, and generates a first URL.

[0173] Step S1003: The packet processing module of the first gateway sends the parsed information to the computing power service routing of the first gateway.

[0174] Step S1004: The computing power service routing of the first gateway queries the computing power supply device using the URL-Path as an index, and determines the P-GID and QoS flow of the target computing power supply device according to the computing power scheduling policy.

[0175] Step S1005: The QoS flow processing module of the first gateway obtains the corresponding QoS flow according to the QoS flow, encapsulates the service request packet according to the logical link scheme of the QoS flow, and sends it to the second gateway.

[0176] Step S1006: After receiving the service request packet, the QoS flow processing module of the second gateway parses the service request packet.

[0177] Step S1007: The QoS flow processing module of the second gateway queries the P-GID through the QoS flow.

[0178] Step S1008: The message processing module of the second gateway obtains the target computing power supply device according to the P-GID, rewrites the first URL to obtain the second URL, and sends the content requested by the service request message to the actual URL interface of the target computing power supply device.

[0179] Step S1009: The target computing power supply device provides computing services and feeds back the computing results, that is, the service response.

[0180] Step S1010: After receiving the service response, the message processing module of the second gateway sends the service response and information such as D-GID to the QoS flow processing module.

[0181] Step S1011: After encapsulating the service response, the QoS flow processing module of the second gateway sends it to the first gateway through the wide area network.

[0182] Step S1012: The QoS flow processing module of the first gateway de-encapsulates the received message to obtain the service response, and sends the service response to the message processing module.

[0183] Step S1013: The message processing module of the first gateway feeds back the service response to the computing power demand device.

[0184] Exemplarily, the present application further provides a computing power service transmission device, which is used to implement the above method embodiments.

[0185] Such as Figure 11 FIG. is a schematic structural diagram of a computing power service transmission device provided for an exemplary embodiment. The computing power service transmission device may include a receiving module 1101, a processing module 1102, and a sending module 1103. Among them, the receiving module 1101 is used to execute Figure 6 the operations in step S601 of the method shown in Figure 7 and the operations in step S701 of the method shown in Figure 6 the operations in step S602 of the method shown in Figure 7 and the operations in steps S702 and S703 of the method shown in Figure 6 the operations in step S603 of the method shown in Figure 7 and the operations in steps S704, S705, and S706 of the method shown in

[0186] In some embodiments, in order to implement the above functions, the computing power service transmission device includes the corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed in this application, this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving the hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0187] The embodiments of this application can divide the function modules of the computing power service transmission device according to the above method embodiments. For example, each function module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of a software function module. It should be noted that the division of modules in the embodiments of this application is illustrative, only a logical function division, and there can be other division methods in actual implementation.

[0188] As Figure 12 shown, the computer device provided by the embodiments of this application may include a processor 1201, a bus 1202, a communication interface 1203, and a memory 1204. The processor 1201, the memory 1204, and the communication interface 1203 communicate with each other through the bus 1202. It should be understood that this application does not limit the number of processors and memories in the network device.

[0189] The bus 1202 may be a PCI bus, an extended industry standard architecture (EISA) bus, or a UB bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 12 only one line is shown in [figure], but it does not mean that there is only one bus or one type of bus. The bus 1202 may include a path for transmitting information between various components of the network device (for example, the memory 1204, the processor 1201, and the communication interface 1203).

[0190] The processor 1201 may include any one or more of a CPU, a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP), etc.

[0191] The memory 1204 may include volatile memory, such as random access memory (RAM). The processor 1201 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0192] The communication interface 1203 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the network device and other devices or communication networks.

[0193] The executable program code is stored in the memory 1204, and the processor 1201 executes the executable program code to implement the functions of the foregoing method embodiments respectively. That is, the memory 1204 stores instructions for executing the above-mentioned computing power service transmission method.

[0194] In another aspect, a computer-readable storage medium is provided. At least one computer program is stored in the computer-readable storage medium, and the at least one computer program is loaded and executed by a processor to implement the computing power service transmission method provided in the foregoing method embodiments.

[0195] In another aspect, a computer program product is provided. The computer program product includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the computing power service transmission method provided in the foregoing method embodiments is implemented.

[0196] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the module is divided into different functional modules to complete all or part of the functions described above. The specific working processes of the systems, modules, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0197] Since the computing power service transmission module, computer-readable storage medium, and computer program product in the embodiments of the present invention can be applied to the above method, the technical effects that can be obtained therefrom can also refer to the foregoing method embodiments and will not be elaborated here.

[0198] The method steps in this embodiment can be implemented in a hardware manner or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in a random access memory (RAM), flash memory, read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), register, hard disk, removable hard disk, CD-ROM, or any other form of storage medium well-known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC. Additionally, the ASIC can be located in a network device. Of course, the processor and the storage medium can also exist as discrete components in the network device.

[0199] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions of the embodiments of the present application are executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, or other programmable modules. The computer program or instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer program or instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless manner. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; it can also be an optical medium, such as a digital video disc (DVD); it can also be a semiconductor medium, such as a solid state drive (SSD). As described above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A computing power service transmission method, characterized in that, The method is applied to a network system, which includes: a first gateway and a second gateway. The first gateway is connected to a computing power demand device, and the second gateway is connected to a target computing power supply device, where the target computing power supply device is any one of multiple computing power supply devices. The method includes: The first gateway receives a service request message sent by the computing power demand device, where the service request message is a message for the computing power demand device to request computing power services. The first gateway determines the target computing power supply device based on the service request message. The first gateway sends the service request message to the target computing power supply device through the second gateway.

2. The method according to claim 1, wherein The first gateway determines the target computing power supply device based on the service request message, including: The first gateway parses the service request message to obtain a first Uniform Resource Locator (URL) in the service request message, where the first URL is used to identify the type of computing power service in the service request message. The first gateway determines the target computing power supply device based on the first URL.

3. The method according to claim 2, wherein The first gateway determines the target computing power supply device based on the first URL, including: The first gateway looks up a candidate computing power supply device corresponding to the first URL from a computing power service type table, where the computing power service type table is used to record the correspondence between the first URL and the computing power supply device. The first gateway determines the target computing power supply device from the candidate computing power supply devices based on a computing power scheduling policy, where the computing power scheduling policy is used to screen the candidate computing power supply devices.

4. The method according to claim 1, wherein The first gateway sends the service request message to the target computing power supply device through the second gateway, including: The first gateway sends the service request message to the second gateway through a target transmission link corresponding to the target computing power supply device. The second gateway sends the service request message to the target computing power supply device.

5. The method according to claim 4, wherein The target transmission link is an exclusive transmission link corresponding to the target computing power supply device.

6. The method according to claim 4, characterized in that The first gateway sends the service request message to the second gateway through a target transmission link corresponding to the target computing power supply device, including: The first gateway encapsulates the service request message and the global identifier (GID) of the target computing power supply device. The first gateway sends the encapsulated service request message and / or the GID to the second gateway through the target transmission link corresponding to the target computing power supply device.

7. The method according to claim 4, characterized in that, The second gateway sends the service request message to the target computing power supply device, including: The second gateway parses the service request message to obtain the first URL in the service request message. The second gateway modifies the first URL in the service request message to a second URL and then sends the service request message to the target computing power supply device, where the second URL includes an actual interface corresponding to the target computing power supply device.

8. The method according to any one of claims 1-7, characterized in that, The method further includes: The second gateway sends the service response sent by the target computing power supply device to the computing power demand device through the first gateway.

9. A computing power service transmission device, characterized in that, The device includes: a receiving module, configured to receive a service request message sent by a computing power demand device, where the service request message is a message for the computing power demand device to request a computing power service; a processing module, configured to determine the target computing power supply device based on the service request message; a sending module, configured to send the service request message to the target computing power supply device through a second gateway.

10. A computer device, characterized in that, The computer device includes a processor and a memory, and at least one computer program is stored in the memory, and at least one computer program is loaded and executed by the processor to implement the computing power service transmission method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, At least one computer program is stored in the computer-readable storage medium, and at least one computer program is loaded and executed by a processor to implement the computing power service transmission method according to any one of claims 1 to 8.

12. A computer program product, characterized in that, The computer program product includes a computer program or an instruction, and when the computer program or the instruction is executed by a processor, the computing power service transmission method according to any one of claims 1 to 8 is implemented.

Images