Cloud computing service system, cloud computing service providing method, storage medium and product

Abstract

Embodiments of the present application provide a cloud computing service system, a cloud computing service providing method, a storage medium and a product. The system comprises a computing cluster, a first network switch system and a plurality of control clusters. The computing cluster comprises a plurality of servers. The first network provided by the first network switch system is divided into a plurality of first network domains. The first network switch system is configured to connect the plurality of control clusters to different first network domains based on first network domain configuration information, and connect at least one server corresponding to each control cluster to a first network domain corresponding to the control cluster, and provide data forwarding services between the control clusters and the servers connected to the same first network domain. The technical solution provided by the embodiments of the present application reduces the complexity and deployment cost of the cloud computing server system deployment mode.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of computer, and particularly relate to a cloud computing service system, a cloud computing service providing method, a storage medium and a product. BACKGROUND

[0002] With the development of computer technology, the demand of users for data processing speed and computing power is also increasing, and the traditional single server has been difficult to meet the demand. Therefore, building a computing cluster composed of one or more high-performance servers has become a solution to meet the demand. However, due to the high cost and complex wiring of building such a computing cluster, for general users, renting a set of cloud service system (for example, a cloud computing service system) to perform complex task processing has become an efficient and economical solution.

[0003] Currently, a set of cloud computing service system usually includes a computing cluster for performing complex task processing and a control cluster for managing and accessing the computing cluster. Different users can be provided with cloud computing services by building multiple sets of such cloud computing service systems, but this deployment method is relatively complex and has high cost, which needs to be improved. SUMMARY

[0004] Embodiments of the present application provide a cloud computing service system and method, a storage medium and a product to solve the problem of complex deployment and high cost of existing cloud computing service systems.

[0005] In a first aspect, a cloud computing service system is provided in embodiments of the present application, comprising: a computing cluster, a first network switch system and a plurality of control clusters; the computing cluster comprises a plurality of servers; the first network provided by the first network switch system is divided into a plurality of first network domains;

[0006] The first network switch system is configured to access the plurality of control clusters in different first network domains based on first network domain configuration information, and access at least one server corresponding to each control cluster in the corresponding first network domain, and provide data forwarding services between the control clusters and the servers in the same first network domain.

[0007] In a second aspect, a cloud computing service providing method is provided in embodiments of the present application, applied to a first network switch system of a cloud computing service system, the cloud computing service system further comprising a computing cluster and a plurality of control clusters; the computing cluster comprises a plurality of servers; the first network provided by the first network switch system is divided into a plurality of first network domains; the method comprises:

[0008] access the multiple control clusters into different first network domains based on the first network domain configuration information, and access at least one server corresponding to each of the multiple control clusters into a first network domain corresponding to the at least one server respectively;

[0009] provide data forwarding service between the control cluster and the server accessing the same first network domain.

[0010] In a third aspect, an embodiment of the present application provides a cloud computing service providing method, applied to a second network switch system of a cloud computing service system, the cloud computing service system further comprising a computing cluster, a first network switch system and multiple control clusters; the computing cluster comprises multiple servers; the first network provided by the first network switch system is divided into multiple first network domains; the multiple control clusters access different first network domains, and at least one server corresponding to each of the multiple control clusters accesses a first network domain corresponding to the at least one server respectively; and data forwarding is supported between the control cluster and the server accessing the same first network domain; the method comprises:

[0011] access at least one server corresponding to the same control cluster or the same user into a second network domain corresponding to the at least one server based on second network domain configuration information; the second network domain is obtained by dividing a second network provided by the second network switch system;

[0012] provide data forwarding service between different servers accessing the same second network domain.

[0013] In a fourth aspect, an embodiment of the present application provides a cloud computing service providing method, applied to a scheduling system of a cloud computing service system, the cloud computing service system further comprising a computing cluster, a first network switch system and multiple control clusters; the computing cluster comprises multiple servers; the first network provided by the first network switch system is divided into multiple first network domains; the multiple control clusters access different first network domains, and at least one server corresponding to each of the multiple control clusters accesses a first network domain corresponding to the at least one server respectively; data forwarding is supported between the control cluster and the server accessing the same first network domain; the method comprises:

[0014] detect a switching operation for a target server, and determine a target control cluster requesting switching;

[0015] based on the target control cluster, send a switching request to the first network switch system, so that the first network switch system determines a target control cluster in response to the switching request, and switches the target server from an original control cluster to a first network domain corresponding to the target control cluster.

[0016] In a fifth aspect, the present application provides a computer readable storage medium storing a computer program, wherein the computer program is executed by a computer to implement the cloud computing service providing method according to any one of the second aspect to the fourth aspect.

[0017] In a sixth aspect, the present application provides a computer program product storing a computer program, wherein the computer program is executed by a computer to implement the cloud computing service providing method according to any one of the second aspect to the fourth aspect.

[0018] In the cloud computing service system provided by the scheme of the present application, the cloud computing service system comprises a computing cluster composed of a plurality of servers, a first network switch system and a plurality of control clusters; the first network provided by the first network switch system is divided into a plurality of first network domains; the first network switch system is configured to connect the plurality of control clusters into different first network domains based on first network domain configuration information, and connect at least one server corresponding to each control cluster into a first network domain corresponding to the control cluster, thereby providing data forwarding services between the control clusters and the servers connected into the same first network domain. The present application can provide cloud computing services for the plurality of control clusters simultaneously by deploying only one computing cluster, which greatly reduces the complexity and cost of deployment. Moreover, the cloud service provider deploys a limited number of servers in one computing cluster, and allows the plurality of control clusters to share the same computing cluster through network domain isolation, which can provide cloud computing services for the plurality of control clusters by dispersing server resources, and can also provide large-scale, high-complexity and high-data-volume computing services for users by allowing one control cluster to exclusively use all servers in the computing cluster, thereby avoiding the problem that the system cannot form a scale due to dispersion, and thus cannot meet the increasing demand for task processing. In addition, when a new user or processing task appears, the present scheme only needs to redeploy a control cluster, and then configure the control cluster into a new network domain of the existing cloud computing service system. Since the construction cost and environmental construction difficulty of the control cluster are much lower than those of the computing cluster, the scheme of the present application greatly reduces the construction cost and difficulty compared with the current cloud computing service system which comprises a computing cluster and a control cluster. In addition, when the complexity or data volume of a user corresponding to any control cluster increases, the number of servers connected into the network domain corresponding to the control cluster only needs to be adjusted, and this process does not need to expand the computing cluster, thereby reducing the adjustment cost and difficulty.

[0019] In addition, the scheme can also configure the idle server to other control cluster through the configuration of network domain to avoid the waste of resources in the case of any control cluster failure or upgrade leading to the corresponding server idle. And the process does not need to move the server position, rewire and other operations, under the premise of low cost and high efficiency, further improves the availability of server resources and the flexibility of resource allocation.

[0020] These and other aspects of the present application will become more fully understood from the following detailed description, given by way of example only. BRIEF DESCRIPTION OF DRAWINGS

[0021] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0022] Figure 1 Fig. 1 shows a structural schematic diagram of one embodiment of a cloud computing service system provided by the present application.

[0023] Figure 2 Fig. 2 shows a structural schematic diagram of another embodiment of a cloud computing service system provided by the present application.

[0024] Figure 3 Fig. 3 shows an effect schematic diagram of one embodiment of a display interface of a scheduling system provided by the present application.

[0025] Figure 4 Fig. 4 shows a structural schematic diagram of another embodiment of a cloud computing service system provided by the present application.

[0026] Figure 5 Fig. 5 shows a flow chart of one embodiment of a cloud computing service providing method provided by the present application.

[0027] Figure 6 Fig. 6 shows a flow chart of another embodiment of a cloud computing service providing method provided by the present application.

[0028] Figure 7 Fig. 7 shows a flow chart of another embodiment of a cloud computing service providing method provided by the present application.

[0029] Figure 8 Fig. 8 shows a structural diagram of a cloud computing service system in an actual scene.

[0030] Figure 9 Fig. 9 shows a structural schematic diagram of one embodiment of a cloud computing service device provided by the present application.

[0031] Figure 10Fig. 1 shows a structural schematic diagram of another embodiment of a cloud computing service device provided by the present application.

[0032] Figure 11 Fig. 1 shows a structural schematic diagram of another embodiment of a cloud computing service device provided by the present application.

[0033] Figure 12 Fig. 1 shows a structural schematic diagram of another embodiment of a cloud computing service device provided by the present application. DETAILED DESCRIPTION

[0034] For the purpose, technical solutions and advantages of the present application to be clearer, the technical solutions of the present application will be described clearly and completely below in conjunction with the embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative work, shall fall within the scope of protection of the present application.

[0035] In some of the processes described in the specification and the claims of the present application and the above drawings, a plurality of operations appearing in a specific order, but it should be clear that these operations can be executed or in parallel without the order in which they appear in this text, the serial number of the operation such as 501, 502, etc., is only used to distinguish different operations, and the serial number itself does not represent any execution order. In addition, these processes can include more or less operations, and these operations can be executed in sequence or in parallel. It should be noted that the "first", "second" and the like described herein are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence. Also, "first" and "second" are different types.

[0036] The technical solutions of the embodiments of the present application can be applied to the scenario of providing complex cloud computing services for users, especially the scenario of providing cloud computing services based on tasks of different complexity. For example, based on a cloud computing service system, it can be realized to provide cloud computing services for multiple users by dispersing server resources, or to provide powerful cloud computing services for a single user by integrating all server resources.

[0037] At present, a set of cloud computing service system provided by a cloud service provider to users usually includes a computing cluster for processing complex tasks and a control cluster for managing and accessing the computing cluster. That is, a control cluster corresponds to a fixed computing cluster, and the two together constitute a set of cloud computing service system. In order to meet the rental needs of more users, it is necessary to build multiple such cloud computing service systems. Therefore, the following problems exist:

[0038] First, the system is dispersed. Because this way needs to deploy a set of independent cloud computing service system for each user's each processing task. Therefore, it needs to build multiple independent cloud computing service systems for the number of users or processing tasks. At this time, the cloud service provider needs to disperse its limited number of high-performance servers into multiple small-scale computing clusters. This will lead to the over-dispersion of computing resources when providing cloud computing services, making it difficult to form scale.

[0039] Second, the construction cost is high. When there are new users or processing tasks, all hardware devices in the computing cluster and the control cluster need to be purchased again, and the environment needs to be built, which increases the initial investment cost and subsequent operation and maintenance cost.

[0040] Third, it is difficult to expand. As the complexity of user tasks and the amount of data increase, small-scale computing clusters after dispersion are difficult to meet the needs of users. At this time, the expansion of the computing cluster in the cloud computing service system also has the problems of high construction cost and great difficulty.

[0041] To solve the above three problems, the inventors thought that the server resource dispersion problem can be solved by having multiple control clusters share the same computing cluster. However, this approach still has the problem of possible interaction conflicts between servers corresponding to multiple control clusters, and the communication security cannot be guaranteed. To solve this problem, the inventors, through a series of innovative thinking, proposed the technical solution of the present application. The cloud computing service system includes a computing cluster composed of multiple servers, a first network switch system, and multiple control clusters. The first network provided by the first network switch system is divided into multiple first network domains. The first network switch system is configured to access multiple control clusters in different first network domains based on first network domain configuration information, and access at least one server corresponding to each control cluster in the corresponding first network domain, thereby providing data forwarding services between control clusters and servers in the same first network domain. The embodiment of the present application can provide cloud computing services for multiple control clusters by deploying only one computing cluster, which greatly reduces the complexity and deployment cost of the deployment method. By deploying limited servers in a computing cluster and using network domain isolation to allow multiple control clusters to share the same computing cluster, the cloud service provider can provide cloud computing services for multiple control clusters while dispersing server resources. In addition, when a new user or processing task appears, the present solution only needs to redeploy a control cluster and then configure it in a new network domain of the existing cloud computing service system. Since the construction cost and environmental setup difficulty of the control cluster are much lower than those of the computing cluster, the present application greatly reduces the construction cost and difficulty compared to redeploying a cloud computing service system including a computing cluster and a control cluster. In addition, when the complexity or data volume of a user corresponding to any control cluster increases, the number of servers in the network domain corresponding to the control cluster only needs to be adjusted. This process does not require the expansion of the computing cluster, reducing the adjustment cost and difficulty.

[0042] In addition, the present embodiment can also configure idle servers to other control clusters to avoid resource waste when any control cluster fails or upgrades, resulting in idle servers. In this process, there is no need to move the server to a new location or rewire, which further improves the availability of server resources and the flexibility of resource allocation at low cost and high efficiency.

[0043] With reference to the drawings and the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work fall within the scope of the present application.

[0044] It should be noted that the embodiments of the present application can involve the use of user data. In actual applications, user-specific personal data can be used in the schemes described herein in a range permitted by applicable laws and regulations, for example, with explicit consent of the user, with actual notification to the user, and the like.

[0045] It should be noted that the user information (including but not limited to user equipment information, user personal information, and the like) and data (including but not limited to data for analysis, stored data, displayed data, and the like) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use, and processing of the relevant data need to comply with relevant laws, regulations, and standards of relevant countries and regions, and provide corresponding operation portals for the user to select authorization or rejection.

[0046] It should be noted that the technical solutions of the embodiments of the present application are applicable to a network virtual environment, and the described user generally refers to a "virtual user". A real user can register a user account in the service end by a registration method to obtain a user identity in the network environment. The same user account can be logged into the service end through different types of user terminals, so that the service end can identify the same user.

[0047] The interaction operation between the service end and the user can be realized based on the user account, and the corresponding data received or sent by the service end to the user is also realized based on the user account. In fact, the corresponding data is received or sent by the user terminal corresponding to the user account to the service end. In addition, communication and the like can also be realized between users through user accounts. The user can refer to an individual or an institution such as an enterprise, and the present application does not make specific limitations.

[0048] It should be noted that in the case that the embodiments of the present application involve user interaction operations or triggering operations, the user interaction operations or triggering operations involved in the embodiments of the present application include but are not limited to: touch operations, gesture operations, voice operations, head movement operations, eye movement operations, and various modes of interaction operations. The touch operation includes but is not limited to: click operation, double-click operation, long-press operation, sliding operation, pinch operation, or mouse hovering operation, and the like. The sliding operation includes but is not limited to: straight-line sliding, curve sliding, and the like.

[0049] The implementation details of the technical solutions of the embodiments of the present application are described in detail below.

[0050] As shown in Figure 1 Fig. 1 is a structural schematic diagram of an embodiment of a cloud computing service system provided by the present application. The system 10 can include a computing cluster 101, a first network switch system 102, and a plurality of control clusters 103. The computing cluster 101 includes a plurality of servers. The first network provided by the first network switch system 102 is divided into a plurality of first network domains.

[0051] The computing cluster 101 can be a server cluster for providing high complexity or high data volume operations. For example, it can be a server cluster that focuses on providing necessary hardware support and technical support for artificial intelligence application programs. The servers contained therein are all high-performance servers, for example, they can include but are not limited to: graphics processing unit (GPU) servers and high-performance memories, etc. GPU servers are mainly used for processing high complexity or high data volume tasks, for example, performing large model training tasks. High-performance memories are mainly used for storing high data volume data. For example, storing training samples and their training labels required for large model training tasks. It should be noted that one cloud computing service system of the present embodiment only contains one computing cluster, but the computing cluster can deploy all the limited high-performance servers available to the cloud service provider in the cloud computing cluster to ensure that a large-scale server cluster is formed to meet the task processing needs as the data processing speed and computing power continue to improve in the future.

[0052] The first network switch system 102 can be a switch device for establishing network connections between each control cluster 103 and its corresponding servers in the computing cluster 101. The switch devices contained in the first network switch system 102 can further include at least one access switch and at least one out-of-band switch. The first network provided by the first network switch system 102 can be a network connected by switch ports, for example, it can be a fiber network. The plurality of first network domains divided by the first network can be a plurality of virtual local area networks (VLANs), for example, VLAN1-VLANn. Optionally, the first network switch system 102 can also be deployed within the computing cluster 101, which is not limited.

[0053] The first network switch system 102 is configured to access the plurality of control clusters 103 into different first network domains based on first network domain configuration information, and access at least one server corresponding to each control cluster 103 into a first network domain corresponding to the control cluster 103, and provide data forwarding services between the control clusters 103 and the servers in the same first network domain.

[0054] The first network domain configuration information can be preconfigured information indicating how to divide the plurality of control clusters and the plurality of servers into different first network domains. For example, the first network domain configuration information can include the server corresponding to each control cluster 103 and the first network domain identifier corresponding to each control cluster 103. It should be noted that in the embodiment, the first network domain identifiers corresponding to different control clusters 103 are different. The server corresponding to each control cluster 103 can be a server that the control cluster 103 needs to access and call to perform a to-be-processed task. In the embodiment, the server corresponding to each control cluster 103 can be set according to the hardware resources required by the to-be-processed task of the control cluster 103.

[0055] Optionally, the first network domain configuration information can be preconfigured and loaded into the first network switch system 102 by a developer when the cloud computing service system 10 is built. Alternatively, a scheduling system can be built inside or outside the cloud computing service system, and the scheduling system is configured to issue the first network domain configuration information to the first network switch system 102. For example, the scheduling system can be a visual unified scheduling platform. When the user needs to access the control cluster 103 and the server into the first network domain, the user can configure the scheduling platform according to actual needs, and the scheduling platform generates the first network domain configuration information and issues the first network domain configuration information to the first network switch system 102. Compared with directly loading the first network domain configuration information into the first network switch system 102, the scheduling platform is used to issue the first network domain configuration information, which facilitates subsequent adjustment of devices added in different first network domains according to user needs.

[0056] Optionally, in the embodiment, the first network switch system 102 can find the first network domain identifier corresponding to each control cluster 103 from the first network domain configuration information, and configure the first network domain identifier for the port of the first network switch system 102 accessed by the control cluster 103. Then, the first network switch system 102 finds one or more servers corresponding to the control cluster 103 from the first network domain configuration information, and configures the first network domain identifier for the port of the first network switch system 102 accessed by the one or more servers. At this time, since the control cluster 103 and the corresponding servers are configured with the same first network domain identifier on the port of the first network switch system 102, the control cluster 103 and the corresponding servers are accessed into the same first network domain.

[0057] As an example, as shown in Figure 1 As shown, the first network domain configuration information can be: control cluster 1 corresponds to the first network domain 1, and the corresponding servers are server 1 and server 2; control cluster 2 corresponds to the first network domain 2, and the corresponding servers are server 3 and server 4; control cluster 3 corresponds to the first network domain 3, and the corresponding servers are server 5 and server 6; at this time, based on the first network domain configuration information, the first network domain 1 can be configured for the access of control cluster 1, server 1 and server 2 to the ports of the first network switch system 102; the first network domain 2 can be configured for the access of control cluster 2, server 3 and server 4 to the ports of the first network switch system 102; the first network domain 3 can be configured for the access of control cluster 3, server 5 and server 6 to the ports of the first network switch system 102; thereby realizing the access of control cluster 1, server 1 and server 2 to the first network domain 1; the access of control cluster 2, server 3 and server 4 to the first network domain 2; and the access of control cluster 3, server 5 and server 6 to the first network domain 3.

[0058] It should be noted that, since different first network domain identifiers are configured for different control clusters 103 in the embodiment, the isolation of the first network domains where different control clusters are located is realized, that is, the first network provided by the first network switch system 102 is finely planned and isolated, and through this network isolation strategy, the situation that multiple control clusters 103 simultaneously occupy the same server when multiple control clusters 103 share the same computing cluster 101 is avoided, and the independence and security of server resource allocation are ensured.

[0059] In some embodiments, in order to ensure the reliability and security of network isolation of the first network, the embodiment can divide the first network based on virtual local area networks, that is, the multiple first network domains divided by the first network in the above-mentioned embodiments can be multiple virtual local area networks. Specifically, the computing cluster and the multiple control clusters of the embodiment are respectively connected to ports in the first network switch system; the first network provided by the first network switch system is divided into multiple virtual local area networks; the first network switch system accesses the multiple control clusters into different first network domains and accesses at least one server corresponding to each control cluster into a first network domain corresponding to the control cluster based on the first network domain configuration information, including: determining the virtual local area network identifier corresponding to each control cluster based on the first network domain configuration information; for any control cluster, configuring the virtual local area network identifier corresponding to the control cluster for the first port connected to the control cluster and the second port connected to at least one server corresponding to the first port. It should be noted that the specific implementation of dividing the virtual local area network and configuring the virtual local area network identifier in the embodiment is similar to the way of dividing the first network domain and configuring the first network domain identifier introduced in the above-mentioned embodiments. Only the first network domain in the above-mentioned embodiments is replaced by the virtual local area network and the first network domain identifier is replaced by the virtual network domain identifier, and the rest is not described here.

[0060] Optionally, in the embodiment, after the first network switch system completes the first network domain configuration for the multiple control clusters and the servers in the computing cluster, the control cluster can communicate with the server corresponding to the control cluster, for example, send data to the server corresponding to the control cluster for the server to perform a complex task based on the received data. At this time, the first network switch system needs to provide data forwarding service between the control cluster and the server accessing the same first network domain. In some embodiments, the first data requested by any control cluster to be sent to any server can be obtained, and the first data is forwarded to the server under the condition that the server and the control cluster access the same first network domain. Wherein, the first data of the embodiment can be data that the control service cluster wants to send to any server currently accessed by the control service cluster.

[0061] Specifically, when any control cluster needs to interact with any server, it sends a request to the first network switch system, which can include the first data to be sent, the port identifier of the server receiving the first data connected to the first network switch system 102, and the address of the server, such as the Internet Protocol (IP) address of the server. After receiving the request, the first network switch system can locate the port (i.e., the first port) receiving the request, i.e., the port connected to the first network switch system by the control cluster sending the request, and then obtain the first network domain identifier configured for the port. Then, based on the port identifier included in the request, the server's port (i.e., the second port) connected to the first network switch system is located, and then the first network domain identifiers configured for the first port and the second port in the first network switch system are compared. If they are the same, it means that the control cluster sending the request and the server receiving the first data access the same first network domain, at which point the first data can be further forwarded to the server based on the server's address included in the request. Optionally, in this embodiment, the request sent by the control cluster can not include the port identifier of the server receiving the first data connected to the first network switch system 102, at which point the first network switch system 102 can further locate the second port based on the pre-configured relationship between the server's address and the connection port. Or it can be located by other means, which is not limited.

[0062] When providing data exchange services for control clusters and servers, this embodiment ensures that the control cluster sending data and the server receiving data are in the same first network domain configured by the access port on the first network switch system, thereby providing data forwarding services, and ensuring the security of data transmission.

[0063] In some embodiments, if the computing cluster and the plurality of control clusters of the embodiments are respectively connected to ports in the first network switch system, and the first network provided by the first network switch system is divided into a plurality of virtual local area networks, the implementation of the first network switch system 102 providing data forwarding service between the control clusters 103 and the servers in the same first network domain can be: obtaining first data requested by any control cluster to be sent to any server through the first port, determining the second port connected to the server, and forwarding the first data to the server through the second port when the virtual local area network identifiers configured on the first port and the second port are the same. It should be noted that the specific implementation of the embodiments is similar to the implementation described in the above embodiments, and only needs to replace the first network domain in the above embodiments with a virtual local area network and replace the first network domain identifier with a virtual network domain identifier. Therefore, the specific implementation of the embodiments will not be described here. The embodiments provide first data forwarding service only when the control clusters and the servers access the ports of the first network switch with the same virtual local area network identifier, thereby ensuring the reliability and security of data transmission.

[0064] Optionally, in the research and development test stage, the control cluster needs to be updated or adjusted due to demand changes or frequent technical iterations. The current common cloud computing service system is constructed by a control cluster and a computing cluster in a one-to-one ratio. Therefore, when the control cluster fails or upgrades, the computing cluster in the cloud computing service system will be idle due to the lack of management and scheduling support. That is, although the servers in the computing cluster are still available, they cannot be directly used due to the lack of effective access points or management interfaces, resulting in resource waste. Especially for users who rely on continuous operation, such interruptions not only reduce production efficiency, but also affect user experience and cause serious losses. The current solution to this problem is to pre-deploy a backup control cluster and its corresponding backup computing cluster. The backup control cluster is the same as the conventional control cluster in the cloud computing service system, but the backup computing cluster does not deploy servers compared to the conventional computing cluster deployed in the cloud computing service system, only reserving space for deploying servers. When a control cluster fails or upgrades, the servers in the corresponding computing cluster are moved to the reserved space in the backup computing cluster corresponding to the backup computing cluster. Thus, the problem of wasting server resources due to the unavailability of the control cluster is avoided. However, this solution still has the following problems:

[0065] First, cluster redundancy construction: in order to ensure that the backup control cluster can normally access the standby control cluster after the server is moved, in addition to not deploying servers, other hardware facilities in the standby control cluster also need to be normally deployed, for example, high-performance networks required for interaction between servers. Therefore, the redundancy construction of the control cluster and other facilities in the standby control cluster except servers is caused.

[0066] Second, frequent relocation risk. The scheme designs the position movement of physical devices, and since the servers in the computing cluster are usually expensive and sensitive server devices such as GPU servers. Any improper operation may cause damage to the device, and frequent relocation will inevitably have a high risk.

[0067] Third, high relocation cost. The relocation process of the server usually needs to involve professional technicians to ensure safe and correct operation, in addition, the relocation process will still cause the server resources to be unavailable for a period of time, which still affects the continuity of task processing.

[0068] In some embodiments, in order to solve the above problems, the first network switch system of the embodiment is also used to determine a target control cluster in response to a switching request for a target server, and switch the target server from an original control cluster to a first network domain corresponding to the target control cluster.

[0069] The target server can be a server that needs to be switched to another control cluster. For example, if the control cluster 1 in the first network domain 1 needs to be upgraded, the server 1 and / or the server 2 in the first network domain 1 can be used as the target server. The target control cluster can be a new control cluster to which the target server needs to be switched at this time. Figure 1

[0070] Optionally, one implementation manner of the embodiment can be that if a user needs to expand the server corresponding to himself due to the increase of the complexity of the task to be processed, the control cluster in which he is located can be used as the target control cluster, and one or more servers in the computing cluster in an idle state are selected as the target server according to the demand of the user, and then a switching request for the target server is triggered by a scheduling system inside or outside the cloud computing service system and sent to the first network switch system. At this time, the first network switch system determines the target server and the target control cluster from the switching request in response to the switching request for the target server. Another implementation manner can be that when the first network switch system detects that a certain server connected by it is in an idle state, in order to prevent resource waste, it is automatically used as the target server, and a switching request is triggered, and then the target control cluster is determined from a plurality of control clusters according to a preset strategy (such as using the control cluster with the highest current operation demand as the target control cluster).

[0071] ​After determining the target server and the target control cluster, the first network switch system can switch the first network domain identifier configured for the target server to access the port (i.e., the second port) of the first network switch system to the first network domain identifier corresponding to the target control cluster, so as to complete the switching of the target server from the original control cluster to the first network domain corresponding to the target control cluster.

[0072] The embodiment supports switching the idle server from the current control cluster to the target control cluster with use demand, and can well solve the problem of idle server resources due to control cluster failure or upgrade. In addition, in the process of implementing the server switching, the embodiment also does not need to build multiple groups of backup control clusters and backup computing clusters, avoiding the problems of cluster redundancy construction, frequent relocation risks, and high relocation costs.

[0073] In some embodiments, as shown in Figure 2 To facilitate the management of the servers in the computing cluster by the cloud service provider or the user, the embodiment can further deploy a scheduling system 104 connected with the first network switch system 102 in the cloud computing service system 10; the scheduling system 104 is configured to detect the switching operation on the target server, determine the target control cluster requested to be switched, and send a switching request to the first network switch system based on the target control cluster.

[0074] The scheduling system 104 can be a unified scheduling platform for the cloud service provider or the user to view the device information of the servers in the computing cluster and initiate the switching of the target server from the current control cluster to the target control cluster.

[0075] Optionally, the scheduling system 104 can provide a display interface for the cloud service provider or the user to trigger the server switching control cluster, and the cloud service provider or the user can select the target server to be switched and the target control cluster to which the server needs to be switched through the display interface, and then trigger the switching operation. At this time, the scheduling system 104 can obtain the target server and the target control cluster selected by the cloud service provider or the user, and then send a switching request to the first network switch system 102 based on the target server and the target control cluster, to request the first network switch system 102 to switch the target server from the original control cluster to the first network domain corresponding to the target control cluster. The details of how to perform the switching process of the first network domain where the target server is located have been described in the above embodiment, and will not be repeated here. The introduction of the scheduling system in the embodiment facilitates the cloud service provider or the user to initiate the switching request of the target server according to the demand, and improves the convenience and flexibility of the switching of the target server control cluster.

[0076] In some embodiments, the scheduling system of this embodiment is further configured to provide a display interface, and display device information of multiple servers and switching prompts corresponding to each of the multiple servers on the display interface. For example, Figure 3 A schematic diagram of the display interface provided by the adjustment system is shown, such as... Figure 3 As shown, this display interface can show device information for each server in the computing cluster, including device type, device identifier, hostname, current cluster, and user. The device type indicates whether the server is a GPU or memory. The device identifier is a unique identifier for the device, such as a device number. The hostname is the name created for the server by its respective control cluster; it should be noted that in this embodiment, different control clusters may assign the same hostname to the same server. The current cluster is the control cluster to which each server currently belongs; to ensure data security, in this embodiment, a server typically belongs to only one control cluster. The user is the user currently using the server. The display interface also includes an operation page, where operations include at least the migration operation of switching a server from one control cluster to another. For example, cloud service providers or users can select the target server from among the servers by checking the box before the device type, and then trigger the migration button on the interface. At this time, a prompt box will pop up on the interface to fill in the target control cluster. The cloud service provider or user can fill in the new control cluster they want to migrate to in the prompt box, i.e., the target control cluster, and then trigger the confirmation instruction. At this point, the cloud service provider or user has completed the operation of triggering the switch to the target server.

[0077] Accordingly, the scheduling system detects a handover operation targeting the target server and determines the target control cluster for the requested handover, including detecting a handover operation triggered by a handover prompt message corresponding to the target server and determining the target control cluster for the requested handover. Specifically, this could involve the cloud service provider or user... Figure 3 The selected server in the interface shown is the target server, and the control cluster entered in the prompt box after triggering the migration button is the target control cluster.

[0078] The scheduling system in this embodiment provides a display interface to show device information for multiple servers, enabling cloud service providers or users to understand the server status and details in real time, thereby assisting in server maintenance. In addition, this display interface can also trigger the switching operation of the control cluster to which the server belongs, improving the flexibility and convenience of server switching.

[0079] In some embodiments, since the server involves multiple complex steps when switching between different first network domains, for example, including address planning, in-band and out-of-band switch configuration, address segment negotiation, and network connection switching, etc. These operations are prone to errors if completed manually. Therefore, the embodiment can be a scheduling system that controls the target server to exit the original control cluster, sends a switching request to the first network switch system to switch the target server from the original control cluster to the first network domain corresponding to the target control cluster, and controls the target server to join the target control cluster based on the target control cluster. Specifically, the scheduling system can track and record the control cluster to which each server currently belongs, the port of the first network switch system, and other information. After the scheduling system detects the switching operation for the target server, based on the connection port (i.e., the first port) of the target server in the first network switch system, the control cluster to which the target server currently belongs, and the target control cluster that needs to be switched, the relevant scripts are automatically called and executed to automatically complete the operation of controlling the target server to exit the original control cluster, sending a switching request to the first network switch system to switch the target server from the original control cluster to the first network domain corresponding to the target control cluster, and controlling the target server to join the target control cluster.

[0080] The embodiment replaces manual operation of the scheduling system to switch the target server from the original control cluster to the target control cluster, avoiding errors caused by manual configuration and improving the reliability of the target server switching process.

[0081] In some embodiments, the application scenario of switching the target server from one control cluster to another control cluster in this embodiment is not limited to the scenario of upgrading or failure of the control cluster introduced in the above embodiment. It can also be applied to the scenario where any cloud service provider or user needs to expand the corresponding server due to the increase in task complexity or data volume, finds a target server that meets its needs from the computing cluster, and requests to switch it to the control cluster where it is located. For example, a user currently wants to perform a large model training task, but the server it can access and schedule cannot meet the requirements due to the high hardware requirements of the task. It needs to add other servers in the computing cluster to its control cluster to expand the scale of the accessible servers and complete the large model training task. At this time, the user can also select the target server through the display interface provided by the scheduling system and trigger the switching request to switch the target server to the control cluster where it is located.

[0082] For this scenario, it can occur that the target server currently being used by user 2 is switched by user 1. In order to avoid triggering the switching operation of the target server directly, causing user 2 to be unable to continue using the target server and thus causing the interruption of its task, the scheduling system can specifically be configured to: send an approval request to the client of the current user of the target server, the approval request being used to inquire the current user through the client whether to confirm switching the target server; and correspondingly, if a confirmation indication is received from the client of the current user, the scheduling system sends a switching request to the first network switch system based on the target control cluster.

[0083] Specifically, the scheduling system can find the client identifier of the current user of the target server based on the display interface, and generate an approval request according to the relevant information of the target server (for example, the identifier of the target server), the switching time, etc. The generated approval request is sent to the client of the current user of the target server based on the found client identifier. The approval request can be used to request the current user to evaluate the impact of switching the target server on itself through the client, and thus give a feedback indication of whether to agree to switch. For example, if the current user does not need to use the target server anymore, switching the target server will not affect itself, and at this time the current user can feed back a confirmation indication to the scheduling system through the client; if the current user is using the target server and the switching will affect the execution of the current task, at this time the current user can feed back a rejection indication to the scheduling system through the client. If the scheduling system receives a confirmation indication from the client of the current user, it will send a switching request to the first network switch system based on the target control cluster. If a rejection indication is received from the client of the user, the scheduling system will feed back a rejection message of the current user through the display interface and suggest communicating with the current user of the target server.

[0084] The embodiment scheme seeks the opinion of the current user of the target server before performing the switching of the target server, avoids the interruption of the task of the current user due to the switching of the target server, and thus guarantees the stability and reliability of the service provided by the entire cloud computing service system.

[0085] In some embodiments, when a server is switched to a new control cluster, the new control cluster usually needs to reinstall and configure it, which not only consumes time but also has a high risk. Once an error occurs, it may cause data loss and even threaten the stability and security of the entire system. In order to solve this problem, as shown in FIG. 10, the scheduling system can be configured to: when a server is switched to a new control cluster, the scheduling system can be configured to: send a reinstallation and configuration request to the new control cluster, the reinstallation and configuration request being used to request the new control cluster to perform reinstallation and configuration on the server. Figure 2As shown, the scheduling system of the embodiment can also have a connection relationship with multiple control clusters; the scheduling system is also used to obtain the host name of the target server from the target control cluster, and establish a corresponding relationship between the host name and the target server, generate initialization data based on the corresponding relationship, and send the initialization data to the target control cluster; the target control cluster is also used to perform initialization operation on the target server based on the initialization data.

[0086] Specifically, after the target server switches to the target control cluster, the target control cluster will uniformly manage the target server that has just switched in, including but not limited to: reinstallation, installation of drivers, setting of host name (hostname), and a series of operations, thereby preparing resources for the subsequent target control cluster scheduling target server. Among them, the initialization operations such as reinstallation, installation of drivers, and verification of whether the software configuration of the target server is consistent with the hardware need to rely on the topology mapping relationship between the hostname and the network in the computing cluster (i.e., the second network provided by the subsequent second network switch) (such as which second network domain the target server belongs to after the second network division). Since the scheduling system of the embodiment has established a communication connection with multiple control clusters, the scheduling system can interact with the target control cluster after the target control cluster sets a new hostname for the target server, and then establish a corresponding relationship between the hostname and the unique identifier of the target server. This corresponding relationship is used to locate the corresponding target server based on the hostname when performing the initialization operation subsequently. The scheduling system will generate initialization data based on the generated corresponding relationship, which can be a configuration file automatically generated and updated, and then send the initialization data to the target control cluster. The target control cluster will automatically complete the related operations of initializing the target server based on the initialization data, for example, including but not limited to: reinstallation, installation of drivers, verification of whether the software configuration of the target server is consistent with the hardware, etc.

[0087] The embodiment breaks through the communication connection between the scheduling system and the control cluster, obtains the hostname set by the control cluster for the target server, and then generates initialization data for the target control cluster to automatically complete the initialization operation on the target server. Compared with manual operation, the present scheme automatically completes the initialization operation, reduces the time consumption and risk of the initialization operation.

[0088] In some embodiments, as Figure 4As shown, the computing cluster of the embodiment further includes a second network switch system; the plurality of servers are connected through a second network provided by the second network switch system; the second network switch system is configured to, based on second network domain configuration information, access at least one server corresponding to a same control cluster or a same user into a second network domain corresponding to the at least one server, and provide data forwarding service between different servers accessed into a same second network domain; and the second network domain is obtained by dividing the second network provided by the second network switch system.

[0089] Optionally, since the servers in the computing cluster are all high-performance servers, and the tasks processed by the servers are all data with high complexity or large data volume, in order to ensure that the servers can work normally, the second network switch system is usually a high-performance network switch. Correspondingly, the second network provided by the high-performance network switch is also usually a high-performance network (i.e., a high-performance network). The second network domain configuration information can be preconfigured, and is indicative information for indicating how to divide the plurality of servers into different second network domains. The second network switch system of the embodiment can divide the second network based on the second network domain configuration information, in combination with the number of control clusters or the number of users corresponding to each control cluster, to obtain a plurality of second network domains, and access the servers corresponding to each control cluster or the servers corresponding to each user of each control cluster into a same second network domain, so as to isolate the one or more servers corresponding to different control clusters or different users from each other in the second network. For example, Figure 4 As shown, if the second network is divided according to the number of control clusters, at this time, based on the second network domain configuration information, server 1 and server 2 can be accessed into second network domain 1 corresponding to control cluster 1, server 3 and server 4 can be accessed into second network domain 2 corresponding to control cluster 2, and server 5 and server 6 can be accessed into second network domain 3 corresponding to control cluster 3.

[0090] Optionally, after the second network switch system in this embodiment divides the at least one server corresponding to the same control cluster or the same user into the at least one network segment, the servers in the same second network domain can communicate with each other. For example, a memory type server can transmit data to a GPU processor type server. Specifically, when any server needs to transmit data to other servers, the server can generate a data transmission request based on the data to be transmitted and a destination address (which can be the address of the server receiving the data to be transmitted) and send the data transmission request to the second network switch system. The second network switch system responds to the data transmission request, determines the source address of the server sending the request and the destination address of receiving the data, and then determines whether the source address and the destination address meet the transmission rule based on the access control list (Access Control List, ACL), that is, whether they belong to the same second network domain. If so, it means that it meets the transmission rule, and at this time, the data to be transmitted is forwarded to the server corresponding to the destination address. The access control list can be a rule for data forwarding or discarding based on the second network, which is usually defined based on the source address, destination address, port number, protocol type and other information allowed for data forwarding.

[0091] The scheme of this embodiment can avoid configuration conflicts of the second network switch system. In addition, in order to ensure the network independence between different control clusters, this scheme not only needs to divide the network domain of the first network provided by the first network switch system to realize network isolation, but also needs to divide the network domain of the second network provided by the second network switch system to realize network partition isolation. This double isolation mechanism significantly increases the complexity and security of network management of the cloud computing service system.

[0092] In some embodiments, in order to further improve the security of the second network isolation, this embodiment can use EVPC (Express Virtual Private Cloud) as an isolation means. Specifically, the second network switch system is specifically configured to: based on the second network domain configuration information, divide the at least one server corresponding to the same control cluster or the same user into the at least one network segment corresponding to the different servers, and provide data forwarding services between the different servers in the same network segment; it should be noted that the second network domain in the above embodiment can be a network segment obtained by dividing the address range corresponding to the second network; different control clusters or different users correspond to different network segments.

[0093] Specifically, the embodiment can divide the address corresponding to the second network into multiple network segments based on the number of control clusters or the number of users in the cloud computing service system; the embodiment can also reserve several network segments in advance on the basis of meeting the number of control clusters or the number of users, so as to allocate a corresponding network segment to a new control cluster when the cloud computing server system is increased in the future. Then, based on the second configuration, one or more servers corresponding to each control cluster are divided into the network segment corresponding to the control cluster, so as to isolate the second network between the servers of the same control cluster.

[0094] Correspondingly, when providing data forwarding services between different servers divided into the same network segment, the first server can request to send second data to the second server, and based on the access control list, it is determined that the destination address of the second server and the source address of the first server belong to the same network segment, and the second data is forwarded to the second server.

[0095] In the embodiment, the first server is a server that needs to send data, the second server is the receiver of the data, and the second data is the data transmitted this time. The access control list at this time can be a rule that defines the judgment of the source address and the destination address belonging to the same network segment. When the first server needs to transmit the second data to the second server in the embodiment, a data transmission request can be generated based on the second data and the target address of the second server and sent to the second network switch system. The second network switch system responds to the data transmission request, determines the source address of the first server sending the request and the destination address of the second server receiving the data, and then determines whether the source address and the destination address meet the transmission rule, i.e., whether they belong to the same network segment, based on the access control list (Access Control List, ACL). If yes, it means that the transmission rule is met, and at this time, the data to be transmitted is forwarded to the server corresponding to the destination address.

[0096] Optionally, based on the above-mentioned embodiments, since the servers in the computing cluster interact with each other based on the second network domain in which they are located, in order to ensure that the target server can normally interact with other servers of the target control cluster after being switched to the target control cluster, the control machine system is not only used to control the first network switch system to switch the target server from the original control cluster to the first network domain corresponding to the target control cluster. The scheduling system is also used to control the second network switch system to switch the target server from the original control cluster to the second network domain corresponding to the target control cluster in response to the switching request for the target server. Wherein, the process of the second network switch system determining the target control cluster in response to the switching request for the target server is similar to the process of the first network switch system determining the target control cluster in response to the switching request for the target server, which will not be described here. When the target server is switched from the original control cluster to the second network domain corresponding to the target control cluster, the second network domain corresponding to the target control cluster or the usage side of the target server can be determined, and the rules in the access control list are adjusted, and the address of the target server is taken as the address allowed to interact in the second network domain, so as to realize the switching of the target server from the original control cluster to the second network domain corresponding to the target control cluster. It should be noted that the second network domain can be a network segment obtained by dividing the second network.

[0097] It should be noted that the embodiments of the present application Figures 1 to 4 The number of servers contained in the computing cluster 101, the number of control clusters 103, the number of first network domains into which the first network is divided, and the number of second network domains into which the second network is divided are only examples. For example, the number of servers contained in the computing cluster 101 and the specific types of servers can be set according to actual needs. The number of control clusters 103 can be set according to the number of usage sides or the needs of users renting the cloud computing service system; the number of first network domains and second network domains can be determined according to the number of control clusters. None of them are limited.

[0098] Figure 5 A flowchart of an embodiment of a cloud computing service providing method provided by the present application, the technical solution of the embodiment can be executed by the first network switch system of the cloud computing service system, wherein the cloud computing service system further includes a computing cluster and multiple control clusters; the computing cluster includes multiple servers; the first network provided by the first network switch system is divided into multiple first network domains; the structure and working principle of the cloud computing service system are described in Figure 1 The related embodiments shown in the above-mentioned embodiments have been described, which will not be described here.

[0099] Figure 5 The cloud computing service providing method shown in the above-mentioned embodiments can include the following steps:

[0100] 501: access the plurality of control clusters into different first network domains based on the first network domain configuration information, and access the at least one server corresponding to each of the plurality of control clusters into the first network domain corresponding to the control cluster.

[0101] 502: provide data forwarding service between the control clusters and the servers accessing the same first network domain.

[0102] In some embodiments, the method further comprises: in response to a handover request for a target server, determining a target control cluster, and switching the target server from an original control cluster to the first network domain corresponding to the target control cluster.

[0103] Optionally, the computing cluster and the plurality of control clusters are connected to ports in a first network switch system; the first network provided by the first network switch system is divided into a plurality of virtual local area networks; that is, the plurality of first network domains in the above embodiments are a plurality of virtual local area networks. Accordingly, based on the first network domain configuration information, the plurality of control clusters are accessed into different first network domains, and the at least one server corresponding to each of the plurality of control clusters is accessed into the first network domain corresponding to the control cluster, comprises: based on the first network domain configuration information, determining the virtual local area network identifier corresponding to each of the plurality of control clusters; for any control cluster, configuring the virtual local area network identifier corresponding to the control cluster for the first port connected to the control cluster and the second port connected to the at least one server corresponding to the control cluster.

[0104] In some embodiments, providing data forwarding service between the control clusters and the servers accessing the same first network domain comprises: obtaining first data requested by any control cluster to be sent to any server, and forwarding the first data to the server if the server and the control cluster access the same first network domain.

[0105] In some embodiments, if the first network domain is a virtual local area network, obtaining first data requested by any control cluster to be sent to any server, and forwarding the first data to the server if the server and the control cluster access the same first network domain comprises: obtaining first data requested by any control cluster to be sent to any server through a first port, determining a second port connected to the server, and forwarding the first data to the server through the second port if the virtual local area network identifiers configured on the first port and the second port are the same.

[0106] Figure 5 The specific implementation and technical effects of the cloud computing service providing method are described in the above related embodiments of the cloud computing service system, and will not be repeated here.

[0107] Figure 6 For the flow chart of an embodiment of the cloud computing service providing method provided in the present application, the technical solution of the embodiment can be executed by the second network switch system of the cloud computing service system, wherein the cloud computing service system further includes a computing cluster, a first network switch system and a plurality of control clusters; the computing cluster includes a plurality of servers; the first network switch system provides a first network which is divided into a plurality of first network domains; the plurality of control clusters access different first network domains, and the plurality of control clusters respectively correspond to at least one server which accesses a corresponding first network domain; and the control clusters and the servers in the same first network domain support data forwarding; the structure and working principle of the cloud computing service system have been described in the related embodiments shown in Figure 3 , and will not be described here in detail.

[0108] Figure 6 The cloud computing service providing method shown in the figure can include the following steps:

[0109] 601: Based on the second network domain configuration information, at least one server corresponding to the same control cluster or the same user is accessed in the second network domain corresponding to the at least one server; the second network domain is obtained by dividing the second network provided by the second network switch system.

[0110] 602: Provide data forwarding service between different servers accessing the same second network domain.

[0111] In some embodiments, the specific implementation of 601 and 602 can be: based on the second network domain configuration information, at least one server corresponding to the same control cluster or the same user is divided into a network segment corresponding to the at least one server, and data forwarding service is provided between different servers divided into the same network segment; the network segment is obtained by dividing the address range corresponding to the second network; different control clusters or different users correspond to different network segments.

[0112] In some embodiments, different second network domains correspond to different network segments, and correspondingly, the data forwarding service between different servers accessing the same second network domain includes: obtaining second data requested by a first server to send to a second server, and based on the access control list, determining that the destination address of the second server and the source address of the first server belong to the same network segment, and forwarding the second data to the second server.

[0113] In some embodiments, the method is further used to determine a target control cluster in response to a switching request for a target server, and switch the target server from an original control cluster to a second network domain corresponding to the target control cluster.

[0114] Figure 6 The specific implementation and technical effects of the cloud computing service providing method shown are described in the related embodiments of the cloud computing service system above, and will not be repeated here.

[0115] Figure 7 For the flowchart of an embodiment of the cloud computing service providing method provided in the present application, the technical solution of the present embodiment can be executed by the scheduling system of the cloud computing service system, wherein the cloud computing service system further includes a computing cluster, a first network switch system, and a plurality of control clusters; the computing cluster includes a plurality of servers; the first network provided by the first network switch system is divided into a plurality of first network domains; the plurality of control clusters access different first network domains, and the at least one server corresponding to each control cluster accesses the first network domain corresponding thereto; data forwarding is supported between the control clusters and the servers accessing the same first network domain; the structure and working principle of the cloud computing service system are described in the related embodiments shown above, and will not be repeated here. Figure 2

[0116] Figure 7 The cloud computing service providing method shown can include the following steps:

[0117] 701: Detecting a switching operation for a target server, and determining a target control cluster requesting switching.

[0118] 702: Based on the target control cluster, sending a switching request to the first network switch system, so that the first network switch system determines a target control cluster in response to the switching request, and switches the target server from an original control cluster to the first network domain corresponding to the target control cluster.

[0119] In some embodiments, based on the target control cluster, sending a switching request to the first network switch system includes: based on the target control cluster, controlling the target server to exit the original control cluster, sending a switching request to the first network switch system to switch the target server from the original control cluster to the first network domain corresponding to the target control cluster, and controlling the target server to join the target control cluster.

[0120] ​In some embodiments, based on the target control cluster, a switching request is sent to the first network switch system, including: sending an approval request to a client of a current user of the target server, the approval request being used to inquire the current user through the client whether to confirm switching to the target server; if a confirmation indication is received from the client of the current user, based on the target control cluster, a switching request is sent to the first network switch system.

[0121] In some embodiments, further comprising obtaining a host name of the target server from the target control cluster, and establishing a correspondence between the host name and the target server, based on the correspondence, generating initialization data, and sending the initialization data to the target control cluster for the target control cluster to perform initialization operation on the target server based on the initialization data.

[0122] In some embodiments, further comprising providing a display interface, and displaying device information of a plurality of servers and switching prompt information corresponding to the plurality of servers on the display interface.

[0123] Correspondingly, further comprising detecting a switching operation for the target server, and determining the target control cluster requesting switching, including: detecting a switching operation triggered by the switching prompt information corresponding to the target server, and determining the target control cluster requesting switching.

[0124] In some embodiments, further comprising issuing the first network domain configuration information to the first network switch system.

[0125] Figure 7 The specific implementation manners and technical effects of the cloud computing service providing method are described in the above related embodiments of the cloud computing service system, and will not be repeated here.

[0126] In some specific implementation scenarios, the computing cluster of the present application can be an artificial intelligence (AI) service cluster, including a plurality of storage servers and a plurality of computing servers configured with a graphics processing unit (GPU), i.e. GPU servers; the first network switch system is specifically used to connect at least one computing server and / or at least one storage server corresponding to each control cluster into the corresponding first network domain, and provides data forwarding services between the control clusters and the computing servers, and between the control clusters and the storage servers in the same first network domain. Optionally, the storage server can be a high-performance storage.

[0127] For ease of understanding, Figure 8 A structure diagram of a cloud computing service system in an actual scenario is shown. As shown in FIG. 1, the cloud computing service system includes a plurality of control clusters 101, a plurality of computing clusters 102, and a first network switch system 103. Figure 8As shown, cloud product cluster A 801 - cloud product cluster C 803 in the figure are multiple control clusters, centralized AI cluster 804 is a computing cluster, access switch is a first network switch system, high-performance network switch is a second network switch system; unified scheduling platform 805 is a scheduling system. Among them, the access switch can be deployed together with the high-performance network switch in the centralized AI cluster 804, and the multiple services contained in the centralized AI cluster 804 include multiple high-performance memories and GPU servers. Optionally, the high-performance network of the embodiment can be a high-speed network constructed by RoCE v2 (Remote Direct Memory Access based on Converged Ethernet) high-speed interconnection technology.

[0128] The cloud product cluster A 801 - cloud product cluster C 803, GPU server 1 - GPU server n, and high-performance memory 1 - high-performance memory n in this scenario are respectively connected to the ports of the access switch; the network provided by the access switch is divided into multiple VLANs, namely VLAN1 - VLAN3. Among them, cloud product cluster A 801 corresponds to VLAN1, cloud product cluster B 802 corresponds to VLAN2, and cloud product cluster C 803 corresponds to VLAN3. Therefore, VLAN1 is configured for the connection interface of the access switch of cloud product cluster A 801 and its corresponding GUP server 1 and high-performance memory 1, VLAN2 is configured for the connection interface of the access switch of cloud product cluster B 802 and its corresponding GUP server 2 and high-performance memory 2, and VLAN3 is configured for the connection interface of the access switch of cloud product cluster C 803 and its corresponding GUP server 3 and high-performance memory 3. Thus, each cloud product cluster and its corresponding GPU server and high-performance memory are isolated based on VLAN1 - VLAN3 to realize physical network isolation. In order to ensure that the GUP servers and high-performance memories of different cloud product clusters or different users in the centralized cluster 804 are isolated from each other in the high-performance network, the high-performance network can be divided into multiple network segments, namely high-performance network segment 1 - high-performance network segment 2, the GUP server 1 and high-performance memory 1 belonging to cloud product cluster A 801 are divided into high-performance network segment 1; the GUP server 2 and high-performance memory 2 belonging to cloud product cluster B 802 are divided into high-performance network segment 2; and the GUP server 3 and high-performance memory 3 belonging to cloud product cluster C 803 are divided into high-performance network segment 3. The double isolation mechanisms of the above two aspects significantly increase the complexity of network management.

[0129] Based on Figure 8The cloud computing service system shown can realize data transmission between the cloud product clusters 801-803 and the centralized AI cluster 804. Taking a large model training task of the cloud product cluster A 801 as an example, the cloud product cluster A 801 needs to send large model data to the GPU server 1 and training sample data required for this training to the high-performance memory 1. When the GPU server 1 performs training based on the received large model data, it also needs to obtain training samples from the high-performance memory 1. The above data transmission process can be:

[0130] The access switch obtains the large model data sent by the cloud product cluster A 801 to the GPU server 1 and the training samples sent to the high-performance memory 1 through the access port of the access switch of the cloud product cluster A 801, and then determines that the access port of the GPU server 1 on the access switch is configured with VLAN 1, the access port of the high-performance memory 1 on the access switch is also configured with VLAN 1, and the access port of the cloud product cluster A 801 on the access switch is also configured with VLAN 1. At this time, it can be determined that the cloud product cluster A 801 and the GPU server 1 and the high-performance memory 1 have the same VLAN identifier, and the large model data can be forwarded to the GPU server 1 based on the IP address of the GPU server 1 through the corresponding port, and the training samples can be forwarded to the high-performance memory 1 based on the IP address of the high-performance memory 1. When the GPU server 1 performs a training task, the high-performance memory 1 needs to transmit training samples to the GPU server 1. At this time, the high-performance memory 1 will send the training samples to the high-performance network switch and the address of the GPU server 1 receiving the training samples, i.e. the destination address. The high-performance network switch will determine whether the destination address corresponding to the GPU server 1 and the source address of the high-performance memory 1 sending the training data belong to the same network segment based on the access control list. If yes, the high-performance network switch will forward the training samples to the GPU server 1 based on the destination address.

[0131] In the cloud computing service system, if product cluster A 801 needs to be upgraded, the corresponding GPU server 1 and high-performance memory 1 will be in an idle state. If a user A of cloud product cluster B 802 wants to use GPU server 1 through the display interface of the unified scheduling platform 805, the user A can trigger the switching operation based on the switching prompt information of GPU server 1 on the display interface of the unified scheduling platform 805, and fill in the target cloud product cluster, i.e., cloud product cluster B 802, to which GPU server 1 is to be switched. At this time, the unified scheduling platform 805 detects the switching operation of GPU server 1, determines that the target server to be switched is GPU server 1, and then determines whether GPU server 1 currently has a user. If so, the unified scheduling platform 805 sends an approval request to the client of the current user of GPU server 1, so as to inquire whether the current user agrees to switch GPU server 1 through the client. If the current user agrees to switch, the current user will feed back a confirmation instruction to the unified scheduling platform 805 through the client. After receiving the confirmation instruction, the unified scheduling platform 805 determines that GPU server 1 needs to be switched to cloud product cluster B 802, and then accesses the switch to control GPU server 1 to exit cloud product cluster A 801 by automatically executing a script file, sends a switching request to the access switch to switch GPU server 1 from VLAN 1 corresponding to cloud product cluster A 801 to VLAN 2 corresponding to cloud product cluster B 802, and controls GPU server 1 to join cloud product cluster B 802. At the same time, the unified scheduling platform 805 is also used to control the high-performance network switch to switch GPU server 1 from the high-performance network segment 1 corresponding to cloud product cluster A 801 to the high-performance network segment 2 corresponding to cloud product cluster B 802. At this time, only the switching of GPU server 1 accessing the network is completed. Cloud product cluster B 802 sets a host name for the newly added GPU server 1. The unified scheduling platform 805 obtains the host name of GPU server 1 from cloud product cluster B 802, establishes a corresponding relationship between the host name and GPU server 1, generates initialization data based on the corresponding relationship, and sends the initialization data to cloud product cluster B 802. Cloud product cluster B 802 automatically performs an initialization operation based on the initialization data. Only after the initialization operation of GPU server 1 is completed, the GPU server 1 is truly switched to cloud product cluster B 802.

[0132] This example addresses situations where a cloud product's GPU server or high-performance storage becomes idle due to a failure or upgrade. By switching the VLAN and network segment of the target GPU server or high-performance storage, along with subsequent initialization operations, the idle GPU server or high-performance storage can be configured for use by other cloud product clusters, avoiding resource waste. Furthermore, for large-scale tasks such as large model training, this embodiment can use a similar method to switch all GPU servers and high-performance storage to a single cloud product cluster, thereby consolidating all server resources to provide large-scale task services to a single cloud product cluster. This embodiment eliminates the need for server relocation or rewiring during the switching process between different cloud product clusters, further improving resource availability and allocation flexibility while maintaining low cost and high efficiency.

[0133] The detailed implementation methods and beneficial effects of each step in this embodiment have been described in detail in the foregoing embodiments, and will not be elaborated here.

[0134] like Figure 9 The diagram shown is a structural schematic of an embodiment of a cloud computing service device provided in this application, which can be applied to a first network switch system of a cloud computing service system. The cloud computing service system further includes a computing cluster and multiple control clusters; the computing cluster includes multiple servers; the first network provided by the first network switch system is divided into multiple first network domains. The structure and working principle of the cloud computing service system are described below. Figure 1 The relevant embodiments shown have already been described, and will not be repeated here.

[0135] The device may include the following modules:

[0136] The first network isolation module 901 is used to connect the multiple control clusters to different first network domains based on the first network domain configuration information, and to connect at least one server corresponding to each of the multiple control clusters to their respective first network domains.

[0137] The first data forwarding module 902 is used to provide data forwarding services between control clusters and servers connected to the same first network domain.

[0138] Figure 9 The cloud computing service device shown can be used to perform Figure 5 The implementation principles and technical effects of the cloud computing service delivery method shown will not be elaborated further. Among them, Figure 9 One or more modules of the cloud computing service device shown can constitute Figure 1The first network switch system in the system architecture shown. For the specific manner in which each module of the cloud computing service device in the above embodiment performs operations has been described in detail in the embodiment relating to the method, and will not be described in detail here.

[0139] As Figure 10 shown, an embodiment of the structure of a cloud computing service device provided by the present application, which can be applied to a second network switch system of a cloud computing service system. The cloud computing service system further includes a computing cluster, a first network switch system, and a plurality of control clusters; the computing cluster includes a plurality of servers; the first network switch system provides a first network divided into a plurality of first network domains; the plurality of control clusters access different first network domains, and the plurality of control clusters respectively correspond to at least one server accessing a corresponding first network domain; and the control clusters and servers accessing the same first network domain support data forwarding. Wherein, the structure and working principle of the cloud computing service system have been described in the related embodiments shown Figure 3 , and will not be described in detail here.

[0140] The device can include the following modules:

[0141] The second network isolation module 1001 is configured to access at least one server corresponding to the same control cluster or the same user in a second network domain corresponding to the at least one server based on second network domain configuration information; the second network domain is obtained by dividing the second network provided by the second network switch system;

[0142] The second data forwarding module 1002 is configured to provide data forwarding services between different servers accessing the same second network domain.

[0143] Figure 10 The cloud computing service device shown can be used to execute Figure 6 The cloud computing service providing method shown, its implementation principle and technical effects will not be described in detail. Wherein, Figure 10 One or more modules of the cloud computing service device shown can constitute Figure 3 The second network switch system in the system architecture shown. For the specific manner in which each module of the cloud computing service device in the above embodiment performs operations has been described in detail in the embodiment relating to the method, and will not be described in detail here.

[0144] As Figure 11As shown in the structural schematic diagram of one embodiment of a cloud computing service apparatus provided by the present application, the cloud computing service apparatus can be applied to a scheduling system of a cloud computing service system. The cloud computing service system further includes a computing cluster, a first network switch system, and a plurality of control clusters. The computing cluster includes a plurality of servers. The first network switch system provides a first network which is divided into a plurality of first network domains. The plurality of control clusters access different first network domains, and the plurality of control clusters respectively correspond to at least one server which accesses a corresponding first network domain. The control clusters and the servers which access the same first network domain support data forwarding. The structure and working principle of the cloud computing service system are described in detail in the related embodiments shown in Figure 2 The related embodiments shown in the structural schematic diagram of the cloud computing service apparatus have been described above, and will not be described here again.

[0145] The apparatus can include the following modules:

[0146] The cluster determination module 1101 is configured to detect a switching operation for a target server, and determine a target control cluster which requests switching.

[0147] The sending module 1102 is configured to send a switching request to the first network switch system based on the target control cluster, so that the first network switch system determines a target control cluster in response to the switching request, and switches the target server from an original control cluster to a first network domain corresponding to the target control cluster.

[0148] Figure 11 The cloud computing service apparatus shown in the structural schematic diagram can be used to execute Figure 7 The cloud computing service providing method shown in the structural schematic diagram will not be described again in detail. The cloud computing service apparatus shown in the structural schematic diagram can be used to execute Figure 11 One or more modules of the cloud computing service apparatus shown in the structural schematic diagram can constitute Figure 2 The scheduling system in the system architecture. The specific operation modes of each module of the cloud computing service apparatus in the above embodiments have been described in detail in the embodiments related to the method, and will not be described here in detail.

[0149] Figure 12 A structural schematic diagram of one embodiment of a computing device provided by the present application. As shown in the structural schematic diagram of one embodiment of a computing device provided by the present application, the computing device can include a storage component 1201 and a processing component 1202. Figure 12

[0150] The storage component 1201 is configured to store computer programs and can be configured to store other various data to support operations on the computing device. Examples of the data include instructions of any application program or method for operating on the computing device, data structures, contact data, phonebook data, messages, pictures, videos, etc. ​

[0151] Processing component 1202, coupled to storage component 1201, is used to execute computer programs in storage component 1201 for implementing, etc. Figures 5-7 The cloud computing service provision method is shown.

[0152] Furthermore, such as Figure 12 As shown, the computing device may also include other components such as a communication component 1203, a display component 1204, a power supply component 1205, and an audio component 1206. Figure 12 The diagram only shows some components and does not mean that the device includes only these components. Figure 12 The components shown. Additionally... Figure 12 The components within the dashed box are optional, not mandatory, and their specific requirements depend on the product form of the computing device. The computing device in this embodiment can be a terminal device such as a desktop computer, laptop computer, smartphone, or IoT (Internet of Things) device, or a server-side device such as a conventional server, cloud server, or server array. If the computing device in this embodiment is implemented as a terminal device such as a desktop computer, laptop computer, or smartphone, it may include... Figure 12 The components within the dashed box; if the computing device in this embodiment is implemented as a conventional server, cloud server, or server array, etc., then it may not include... Figure 12 The component within the dashed box.

[0153] The processing component described above includes one or more processors to execute computer instructions to complete all or part of the steps in the method described above. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the method described above.

[0154] The aforementioned storage components can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0155] The communication component is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as a radio communication technology, a telecommunication technology, or a combination thereof. In an example embodiment, the communication component receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.

[0156] The display component can include a screen, which can include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense a touch, a slide, and a gesture on the touch panel. The touch sensor can not only sense a boundary of a touching or a sliding action, but also detect duration and pressure related to the touching or sliding action.

[0157] The power supply component provides power to various components of the device where the power supply component is located. The power supply component can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to the device where the power supply component is located.

[0158] The audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC) that is configured to receive an external audio signal when the device where the audio component is located in an operation mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in a memory or transmitted via the communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0159] Accordingly, the embodiments of the present application also provide a computer readable storage medium storing a computer program, which causes a processor to be able to implement each step in the above method embodiments when the computer program is executed by the processor. The computer readable storage medium includes volatile or non-volatile or a combination thereof, and can be removable or non-removable. Examples of the computer readable storage medium include, but are not limited to, phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital video disc (DVD) or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium

[0160] Accordingly, the embodiments of the present application also provide a computer program product, which includes a computer program or instructions, and causes a processor to be able to implement each step in the above method embodiments when the computer program or instructions are executed by the processor. It should be understood that each process or a combination of multiple processes in the above method flow can be implemented by the computer program or instructions. In addition, the computer program or instructions can be applied to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device, so that the processor of the general-purpose computer, the special-purpose computer, the embedded processor or other programmable data processing device can be implemented as a device for implementing the corresponding functions in the above method embodiments.

[0161] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0162] It should also be noted that the terms "comprising", "comprises" or other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0163] Finally, it should be noted that the above merely illustrates the embodiments of the present application, and is not intended to limit the present application. Various modifications and changes can be made by those skilled in the art to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A cloud computing service system, characterized by, The system comprises: a computing cluster, a first network switch system, and a plurality of control clusters; the computing cluster comprises a plurality of servers; a first network provided by the first network switch system is divided into a plurality of first network domains; the first network switch system is configured to access the plurality of control clusters into different first network domains and access at least one server corresponding to each control cluster into a corresponding first network domain based on first network domain configuration information, and provide data forwarding services between the control clusters and the servers in the same first network domain; the first network switch system is configured to access the plurality of control clusters into different first network domains and access at least one server corresponding to each control cluster into a corresponding first network domain based on first network domain configuration information, which comprises that the first network switch system is configured to find a first network domain identifier corresponding to any control cluster from the first network domain configuration information and configure the first network domain identifier for a port of the first network switch system accessed by the control cluster; find at least one server corresponding to the control cluster from the first network domain configuration information and configure the first network domain identifier for a port of the first network switch system accessed by the at least one server; and the first network domain identifiers corresponding to different control clusters are different.

2. The system of claim 1, wherein the first network switch system is further configured to determine a target control cluster in response to a switching request for a target server and switch the target server from an original control cluster to a first network domain corresponding to the target control cluster.

3. The system of claim 2, wherein, Further comprising a scheduling system having a connection relationship with the first network switch system; the scheduling system is configured to detect a switching operation for a target server, determine a target control cluster requesting switching, and send a switching request to the first network switch system based on the target control cluster.

4. The system of claim 3, wherein, the scheduling system is configured to: based on the target control cluster, control the target server to exit the original control cluster, send a switching request to the first network switch system to switch the target server from the original control cluster to a first network domain corresponding to the target control cluster, and control the target server to join the target control cluster.

5. The system of claim 3, wherein, the scheduling system is configured to: send an approval request to a client of a current user of the target server, the approval request being used to inquire whether the current user confirms switching of the target server through the client; if a confirmation indication fed back by the client of the current user is received, send a switching request to the first network switch system based on the target control cluster.

6. The system of claim 3, wherein, the scheduling system has a connection relationship with the plurality of control clusters; The scheduling system is further configured to obtain a host name of the target server from the target control cluster, establish a correspondence between the host name and the target server, generate initialization data based on the correspondence, and send the initialization data to the target control cluster; The target control cluster is further configured to perform an initialization operation on the target server based on the initialization data.

7. The system of claim 3, wherein The scheduling system is further configured to provide a display interface and display device information of a plurality of servers and switching prompt information corresponding to the plurality of servers on the display interface; When detecting a switching operation on the target server and determining the target control cluster requesting the switching, the scheduling system is specifically configured to detect a switching operation triggered by the switching prompt information corresponding to the target server and determine the target control cluster requesting the switching.

8. The system of claim 1, wherein, The computing cluster and the plurality of control clusters are respectively connected to ports in the first network switch system; and the first network domain is a virtual local area network. When connecting the plurality of control clusters to different first network domains and connecting at least one server corresponding to each control cluster to a first network domain corresponding to the control cluster based on the first network domain configuration information, the first network switch system is specifically configured to: based on the first network domain configuration information, determine a virtual local area network identifier corresponding to each control cluster; and for any control cluster, configure the virtual local area network identifier corresponding to the control cluster for a first port connected to the control cluster and a second port connected to at least one server corresponding to the control cluster.

9. The system of claim 1, wherein, When providing data forwarding services between control clusters and servers connected to the same first network domain, the first network switch system is specifically configured to: obtain first data requested by any control cluster to be sent to any server, and forward the first data to the server if the server and the control cluster are connected to the same first network domain.

10. The system of claim 9, wherein, The first network domain is a virtual local area network. When obtaining first data requested by any control cluster to be sent to any server and forwarding the first data to the server if the server and the control cluster are connected to the same first network domain, the first network switch system is specifically configured to: obtain first data requested by any control cluster to be sent to any server through a first port, determine a second port connected to the server, and forward the first data to the server through the second port if the virtual local area network identifiers configured on the first port and the second port are the same.

11. The system of claim 1, wherein, The computing cluster further comprises a second network switch system; and the plurality of servers are connected through a second network provided by the second network switch system. The second network switch system is configured to connect at least one server corresponding to the same control cluster or the same user to a second network domain corresponding to the at least one server based on second network domain configuration information, and provide data forwarding services between different servers connected to the same second network domain. The second network domain is obtained by dividing a second network provided by the second network switch system.

12. The system of claim 11, wherein, The second network domain is a network segment obtained by dividing an address range corresponding to the second network; different control clusters or different users correspond to different network segments; The second network switch system is specifically configured to: based on second network domain configuration information, divide at least one server corresponding to a same control cluster or a same user into a network segment corresponding to the at least one server, and provide data forwarding services between different servers divided into the same network segment.

13. The system of claim 12, wherein, Different second network domains correspond to different network segments, and the second network switch system is specifically configured to: Obtain second data requested by a first server to be sent to a second server, and based on an access control list, determine that a destination address of the second server and a source address of the first server belong to a same network segment, and forward the second data to the second server.

14. The system of claim 11, wherein The scheduling system is further configured to control the second network switch system to, in response to a switching request for a target server, determine a target control cluster, and switch the target server from an original control cluster to a second network domain corresponding to the target control cluster.

15. The system of any of claims 1-14, wherein, The computing cluster is an artificial intelligence service cluster, including a plurality of storage servers and a plurality of computing servers configured with graphic processing units; The first network switch system is specifically configured to connect at least one computing server and / or at least one storage server corresponding to each of the plurality of control clusters into a first network domain corresponding thereto, and provide data forwarding services between control clusters and computing servers, and between control clusters and storage servers connected into a same first network domain.

16. A cloud computing service providing method characterized by comprising: The first network switch system is applied to a cloud computing service system, and the cloud computing service system further includes a computing cluster and a plurality of control clusters; the computing cluster includes a plurality of servers; The first network provided by the first network switch system is divided into a plurality of first network domains; The method includes: Based on first network configuration information, connecting the plurality of control clusters into different first network domains, and connecting at least one server corresponding to each of the plurality of control clusters into a first network domain corresponding thereto; Providing data forwarding services between control clusters and servers connected into a same first network domain; and The first network configuration information is used to access the multiple control clusters in different first network domains and access the at least one server corresponding to each control cluster in the corresponding first network domain. For any control cluster, the first network domain identifier corresponding to the control cluster is found from the first network domain configuration information, and the first network domain identifier is configured for the port of the first network switch system accessed by the control cluster. The at least one server corresponding to the control cluster is found from the first network domain configuration information, and the first network domain identifier is configured for the port of the first network switch system accessed by the at least one server. The first network domain identifiers corresponding to different control clusters are different.

17. A cloud computing service providing method characterized by comprising: The cloud computing service system further includes a computing cluster, a first network switch system and multiple control clusters. The computing cluster includes multiple servers. The first network provided by the first network switch system is divided into multiple first network domains. The multiple control clusters are accessed in different first network domains, and the at least one server corresponding to each control cluster is accessed in the corresponding first network domain. The control clusters and the servers accessed in the same first network domain support data forwarding. The multiple control clusters are accessed in different first network domains, and the at least one server corresponding to each control cluster is accessed in the corresponding first network domain. The first network switch system finds the first network domain identifier corresponding to any control cluster from the first network domain configuration information, and configures the first network domain identifier for the port of the first network switch system accessed by the control cluster. The at least one server corresponding to the control cluster is found from the first network domain configuration information, and the first network domain identifier is configured for the port of the first network switch system accessed by the at least one server. The first network domain identifiers corresponding to different control clusters are different. The method includes: Based on the second network configuration information, the at least one server corresponding to the same control cluster or the same user is accessed in the second network domain corresponding to the at least one server. The second network domain is obtained by dividing the second network provided by the second network switch system. Data forwarding services are provided between different servers accessed in the same second network domain.

18. A cloud computing service providing method characterized by comprising: The cloud computing service system further includes a computing cluster, a first network switch system and multiple control clusters. The computing cluster includes multiple servers. The first network provided by the first network switch system is divided into multiple first network domains. The multiple control clusters are accessed in different first network domains, and the at least one server corresponding to each control cluster is accessed in the corresponding first network domain. The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises:

19. A computer-readable storage medium, characterized in that, The method comprises:

20. A computer program product, characterised in that, The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method

Images