Service data node migration method, device, electronic device and storage medium

Abstract

The present disclosure provides a service data node migration method, device, electronic device and storage medium, the method comprising: obtaining a detection result of abnormal operation of a first service data node bound to the first interface node among multiple service data nodes through a first detector of a first interface node among multiple interface nodes; sending a service migration request to a service control node through the first detector of the first interface node in response to the detection result of abnormal operation of the first service data node; and releasing the binding relationship between the first interface node and the first service data node through the service control node in response to the service migration request, and migrating each service in the first interface node to a second interface node among multiple interface nodes, the second interface node having a binding relationship with one of the multiple service data nodes. Thus, the present application can automatically trigger the migration process of the service data node when the service data node of the detection interface node has abnormal operation, so as to ensure the continuity and availability of the service.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, electronic device and storage medium for migrating a service data node. Background Art

[0002] A dedicated data processing unit (DPU) is a data-centric dedicated processor that offloads the load that "CPU processing efficiency is low and GPU cannot handle" to a dedicated DPU, which can improve the efficiency of the entire computing system and reduce the total cost of ownership (TOC) of the entire system.

[0003] Specifically, DPU can build a more efficient computing platform by offloading some computing platform services. For example, with the popularity of cloud-native microservice architecture, service mesh, as a dedicated infrastructure layer for communication between microservices, is responsible for controlling data sharing between different parts of the application.

[0004] Traditional service meshes use a sidecar deployment model, that is, each microservice is configured with a sidecar. Since the sidecar will occupy a large amount of host resources, it is easy to cause microservice delays and reduce traffic processing efficiency. Therefore, a one-to-many mechanism centralized service mesh model has been developed.

[0005] However, in the centralized service mesh mode, when an abnormality occurs in the centralized proxy, if there is no service migration capability, the services will be accumulated on the abnormal node of the centralized proxy, which will still affect the forwarding and processing of traffic and reduce the continuity and availability of the service. Summary of the invention

[0006] In view of this, an embodiment of the present application provides a service data node migration solution, which can automatically trigger the migration process of the service data node when the service data node of the interface node is detected to have an operational abnormality, thereby ensuring the continuity and availability of the service.

[0007] According to a first aspect of an embodiment of the present application, a service data node migration method is provided, which is applied to a main device, wherein the main device is coupled to multiple dedicated data processors, each of which has a service data node, and the main device includes a service control node and multiple interface nodes corresponding to each service data node in each dedicated data processor, wherein the service control node controls each corresponding service data node through each interface node to provide data services for the main device, and the method includes: obtaining a detection result of an abnormal operation of a first service data node bound to the first interface node among multiple service data nodes through a first detector of a first interface node among multiple interface nodes; sending a service migration request to the service control node in response to the detection result of the abnormal operation of the first service data node through the first detector of the first interface node; and releasing the binding relationship between the first interface node and the first service data node through the service control node in response to the service migration request, and migrating each service in the first interface node to a second interface node among multiple interface nodes, wherein the second interface node has a binding relationship with one of the multiple service data nodes.

[0008] According to a second aspect of an embodiment of the present application, a service data node migration device is provided, characterized in that it is applied to a main device, the main device is coupled to multiple dedicated data processors, each dedicated data processor has a service data node, the main device includes a service control node, and multiple interface nodes corresponding to each service data node in each dedicated data processor, the service control node controls each corresponding service data node through each interface node to provide data services for the main device, and the device includes: a detection module, which is used to obtain a detection result of abnormal operation of a first service data node bound to the first interface node among multiple service data nodes through a first detector of a first interface node among multiple interface nodes; a request module, which is used to send a service migration request to the service control node in response to the detection result of abnormal operation of the first service data node through the first detector of the first interface node; and a migration module, which is used to release the binding relationship between the first interface node and the first service data node through the service control node in response to the service migration request, and migrate each service in the first interface node to a second interface node among multiple interface nodes, and the second interface node has a binding relationship with one of the multiple service data nodes.

[0009] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising: a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the service data node migration method as described in the first aspect is implemented.

[0010] According to a third aspect of an embodiment of the present application, a computer storage medium is provided, wherein the computer storage medium stores a computer program code. When the computer program code is executed by a processor, the processor executes the service data node migration method as described in the first aspect.

[0011] To sum up, the service data node migration scheme provided by various aspects of the present application detects the operating status of the data service node corresponding to the interface node, so that when an abnormality occurs in the data service node of the detected interface node, the service in the abnormally working interface node is migrated to the normally working interface node, thereby ensuring the continuity and availability of the service in the event of a data service node failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present disclosure. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0013] Figure 1 This is a diagram of the architecture of a traditional service mesh.

[0014] Figure 2 A diagram of the centralized service grid architecture.

[0015] FIG. 3A to FIG. 3B A schematic diagram of the architecture of a service data node migration method or device for implementing each embodiment of the present application.

[0016] Figure 4 This is a processing flow chart of a service data node migration method according to an exemplary embodiment of the present application.

[0017] Figure 5 It is a structural block diagram of a service data node migration device according to an exemplary embodiment of the present application.

[0018] Figure 6 It is a structural block diagram of an electronic device according to an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the embodiments of the present application should fall within the scope of protection of the embodiments of the present application.

[0020] A dedicated data processing unit (DPU) is a data-centric dedicated processor that can build a more efficient computing platform by offloading some computing platform services.

[0021] With the popularity of cloud-native microservice architecture, service mesh, as a dedicated infrastructure layer for communication between microservices, is responsible for controlling data sharing between different parts of the application. Service mesh usually consists of two components: control plane and data plane. Among them, the control plane is responsible for completing functions such as service discovery, load balancing, traffic management, and health checks, while the data plane is responsible for actual request forwarding and processing.

[0022] Figure 1 The schematic diagram of the architecture of the traditional service grid 100 is shown. As shown in the figure, the traditional service grid 100 adopts the sidecar deployment mode, that is, each microservice is configured with a sidecar (siedecar), for example, the first microservice 104A corresponds to the first sidecar 106A, the second microservice 104B corresponds to the second sidecar 106B, each sidecar (for example, the first sidecar 106A, the second sidecar 106B) as the service grid data plane and the service grid control plane 102 are located in the same container cluster (for example, K8s cluster), and the service grid control plane 102 can obtain the operation log of the grid service data plane through the interface (API) inside the cluster. Since the number of sidecars configured in the traditional service grid 100 is large, it will undoubtedly occupy a large amount of host resources, which is easy to cause microservice delay and reduced traffic processing efficiency. Based on this, the industry has developed a centralized service grid mode with a one-to-many mechanism.

[0023] Figure 2 The schematic diagram of the centralized service grid architecture is shown. As shown in the figure, the centralized service grid mode unloads the centralized service grid 200 to the dedicated data processor (DPU) 205, and sets a centralized proxy 206 in the dedicated data processor 205 that is in communication with the service grid control plane 202, so as to replace the one-to-one proxy mechanism in the traditional sidecar deployment mode with a one-to-many proxy mechanism, so that the traffic of each microservice in the node (such as the first microservice 204A and the second microservice 204B) is uniformly processed and forwarded by the centralized proxy 206 in the dedicated data processor 205, which can not only improve the forwarding efficiency of the traffic, but also effectively reduce the network delay.

[0024] However, in the centralized service grid mode, when an abnormality occurs in the centralized proxy 206, if the cluster does not have the fault migration capability of the service data node, the service will stagnate at the interface node where the abnormality occurs in the centralized proxy 205, causing the forwarding and processing of traffic to be affected when users request these services, thus affecting the continuity and availability of the service.

[0025] Based on the above technical problems, each embodiment of the present application provides a service data node migration solution, which can automatically migrate the services in the abnormally operating interface node to the normally operating interface node when the service data node corresponding to the interface node has an abnormal operating status. This not only improves the traffic forwarding efficiency and reduces network latency, but also ensures the continuity and availability of the service.

[0026] The specific implementation of each embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0027] FIG. 3A to FIG. 3B Schematic diagram of the architecture of the service data node migration method or device for implementing each embodiment of the present application. Figure 3A As shown, the system architecture 300 may include a host device 310 and a plurality of dedicated data processing units (DPUs) 320A, 320B, and 320C coupled to the host device 310 .

[0028] The main device 310 may be a container cluster architecture, including a service control node 312 and multiple interface nodes 314A, 314B, and 314C. In some embodiments, the main device 310 is, for example, a Kubernetes cluster (referred to as K8s cluster), the service control node 312 may be, for example, a K8s master, and each interface node 314A, 314B, and 314C may be, for example, a respective K8s work node.

[0029] Each dedicated data processor has a service data node, for example, dedicated data processor 320A includes service data node 322A, dedicated data processor 320B includes service data node 322B, and dedicated data processor 320C includes service data node 322C.

[0030] In some embodiments, the service data nodes 322A, 322B, 322C are as follows Figure 2 The centralized proxy 206 is shown. By way of example, the service data nodes 322A, 322B, 322C may include, but are not limited to, Envoy proxies.

[0031] By adopting a centralized proxy to replace the traditional sidecar deployment mode, the service mesh data plane can be transferred from the traditional main device 310 to the SoC side of the dedicated data processor 320 (refer to Figure 3B ), which can effectively save the system resources of the main device 310 and improve the operating efficiency of the main device 310.

[0032] In some embodiments, each service data node 322A, 322B, 322C corresponds to each interface node 314A, 314B, 314C in the main device 310, so that the service control node 312 of the main device 310 controls the corresponding service data nodes 322A, 322B, 322C through each interface node 314A, 314B, 314C to provide data services for the main device 310, that is, by using each service data node 322A, 322B, 322C to forward and process the services 330A, 330B, 330C in the corresponding interface nodes 314A, 314B, 314C, the main device 310 is provided with corresponding data request services.

[0033] For example, reference Figure 3A By binding the interface node 314A with the service data node 322A, the service control node 312 of the main device 310 can control the service data node 322A through the interface node 314A, forward and process the service 330A in the interface node 314A, and provide relevant data services for the main device 310; by binding the interface node 314B with the service data node 322B, the service control node 312 of the main device 310 can control the service data node 322B through the interface node 314B, forward and process the service 330B in the interface node 314B, and the main device 310 provides data services, and so on.

[0034] It should be noted that the number of service data nodes and the number of interface nodes in the main device can be adjusted according to the actual data service processing requirements and are not limited to one specific number. Figure 3A or Figure 3B Limited to the quantities shown.

[0035] like Figure 4 As shown, according to an embodiment of the present disclosure, a service data node migration method 400 is provided, which mainly includes the following steps:

[0036] Step 402: Obtain, through a first detector of a first interface node among multiple interface nodes, a detection result of abnormal operation of a first service data node bound to the first interface node among multiple service data nodes.

[0037] refer to Figure 3B , the operating status of the first service data node 322A having a binding relationship with the first interface node 314A can be detected through the first detector 3142A in the first interface node 314A, and the operating status of the second service data node 322B having a binding relationship with the second interface node 314B can be detected through the second detector 3142B in the second interface node 314B.

[0038] In some embodiments, a polling mechanism may be used to detect the operating status of the service data node.

[0039] Specifically, to detect Figure 3B Taking the operating status of the first service data node 322A shown as an example, the operating status detection information can be sent to the first service data node 322A of the first interface node 314A through the first detector 3142A in the first interface node 314A. If the operating status feedback information of the first service data node 322A corresponding to the operating status detection information is obtained (that is, if the first service data node 322A can respond to the operating status detection information of the first detector 3142A and return the corresponding operating status feedback information to the first detector 3142A), the detection result that the first service data node 322A is operating normally can be obtained; conversely, if the operating status feedback information of the first service data node 322A corresponding to the operating status detection information is not obtained (that is, if the first service data node 322A fails to respond to the operating status detection information of the first detector 3142A), the detection result that the first service data node 322A is operating abnormally can be obtained.

[0040] In some embodiments, a heartbeat mechanism may be used to detect the operating status of the service data node.

[0041] Specifically, the detection Figure 3B Taking the operating status of the first service data node 322A shown as an example, the first detector 3142A in the first interface node 314A can be used to obtain multiple operating status information of the first service data node 322A of the first interface node 314A within a specified detection period, that is, the first service data node 322A can actively send the first detector 3142A each operating status information of the first service data node 322A corresponding to each detection moment. The first detector 3142A can analyze the state changes of the first service data node 322A within a specified detection period based on the operating status information of the first service data node 322A. If the analysis result is that the status of the first service data node 322A is updated within the specified detection period (that is, the operating status information of the first service data node 322A is changed within the specified detection period), a detection result that the first service data node 322A is operating normally can be obtained; if the analysis result is that the status of the first service data node 322A is not updated within the specified detection period (that is, the operating status information of the first service data node 322A is not changed within the specified detection period), a detection result that the first service data node 322A is operating abnormally can be obtained.

[0042] Step 404: Send a service migration request to the service control node through the first detector of the first interface node in response to the detection result that the first service data node is operating abnormally.

[0043] In some embodiments, the service control node 312 of the master device 310 may include an update component 3122 and a scheduler 3124. Exemplarily, the update component 3122 may be an Apiserver in a K8s master controller, and the scheduler 3124 may be a Scheduler component in a K8s master controller.

[0044] In some embodiments, when the first detector 3142A obtains a detection result that the first service data node 322A is operating abnormally, it means that the first service data node 322A3 cannot normally provide forwarding and processing functions for each service 330 in the first interface node 314A. In this case, the first detector 3142A can send a service migration request of the first interface node 314A to the update component 3122 of the service control node 312.

[0045] In some embodiments, the service control node 312 also includes an alarm unit 3126 .

[0046] When the detection result of the abnormal operation of the first service data node 322A is obtained, the first detector 3142A can also send the abnormal operation detection result of the first service data node 322A bound to the first interface node 314A to the alarm unit 3126, and generate abnormal alarm information of the first service data node 314A through the alarm unit 3126.

[0047] Step 406: Through the service control node, in response to the service migration request, the binding relationship between the first interface node and the first service data node is released, and each service in the first interface node is migrated to a second interface node among the multiple interface nodes, and the second interface node has a binding relationship with one of the multiple service data nodes.

[0048] In some embodiments, the service migration request may include a node label deletion request.

[0049] The first detector 3142A may send a node label deletion request to the update component 3122, and the update component 3122 may respond to the node label deletion request and delete the bound service data node label of the first interface node 314A to release the binding relationship between the first interface node 314A and the first service data node 322A.

[0050] In this embodiment, the bound service data node label of the first interface node 314A may be determined according to the label of the first service data node 322A. Exemplarily, the label of the first service data node 322A may be determined according to the processor label (e.g., DPU identification information) of the dedicated data processor 320A of the first service data node 322A, and the bound service data node label of the first interface node 314A may be generated.

[0051] In each embodiment of the present application, when it is detected that a target interface node among the interface nodes is not currently bound to a corresponding service data node, a judgment result that the target interface node does not currently have the processing capability of the service request can be obtained. Therefore, after the binding relationship between the first interface node 314A and the first service data node 322A is released, subsequent services can be effectively prevented from being deployed on the first interface node 314A.

[0052] In some embodiments, the service 330 in the first interface node 314A can be removed through the update component 3122 in response to the service migration request of the first detector 3142A, and the service 330 in the first interface node 314A can be migrated to the second interface node 314B through the scheduler 3124 in response to the determination result that the number of services 330 in the first interface node 314 meets the first condition.

[0053] In some embodiments, the service migration request may include a service tag deletion request.

[0054] After the binding relationship between the first interface node 314A and the first service data node 322A is released, the first detector 31421A may send a service label deletion request to the update component 3124. The update component 3124 is used to respond to the service label deletion request, delete the bound service data node label of the service 330 in the first interface node 314A, and delete the Pod service process with the bound service data node label in the first interface node 314A, thereby deleting the service 330 in the first interface node 314A.

[0055] In this embodiment, the bound service data node label of the first interface node 314A is the same as the bound service data node label of the service 330 in the first interface node 314A, both of which are labels of the first service data node 314A, that is, the processor label of the dedicated data processor 320A.

[0056] In some embodiments, a service controller is also provided in the interface node. Exemplarily, the service controller may be a deplyment component in a K8s working node.

[0057] During the process of deleting the service 330 in the first interface node 314A, the number of services 330 currently remaining in the first interface node 314A can be detected (for example, the number of Pod service processes under the service 330 is detected) through the first service controller 3144A in the first interface node 314A. When it is detected that the number of services 330 in the first interface node 314A does not meet the preset number (for example, when the number of Pod service processes under the service 330 is detected, it does not meet the preset number of Pod service processes), a determination result that the number of services 330 in the first interface node 314A meets the first condition is obtained, and the determination result that the number of services 330 in the first interface node 214A meets the first condition is sent to the scheduler 3124 of the main device 310.

[0058] In some embodiments, a node manager is also provided in the interface node. Exemplarily, the node manager may be a Kubelet component in a K8s working node.

[0059] In some embodiments, the scheduler 3124 can obtain a label of a second data service node 322B having a binding relationship with the second interface node 314B in response to a determination result that the number of services 330 in the first interface node 314A satisfies the first condition, and use the label of the second data service node 322B to modify the configuration file of the removed service 330 to bind the service 330 to the second data service node 322B, and call the second node manager 3146B of the second interface node 314B bound to the second data service node 322B to create the service 330 in the second interface node 314B.

[0060] refer to Figure 3B The scheduler 3124 may search for an interface node bound with a service data node from among the interface nodes of the master device 310 according to the determination result that the number of services 330 in the first interface node 314A satisfies the first condition.

[0061] In some embodiments, if there are multiple candidate interface nodes bound to the service data node among the interface nodes of the master device 310, the operation load of each candidate interface node can be analyzed, and the candidate interface node with the lowest operation load (for example, Figure 3B The second interface node 314B shown in the figure is determined as the target interface node to migrate the service 330 in the first interface node 314A to the target interface node (for example, the second interface node 314B).

[0062] The scheduler 3124 can obtain the label of the second service data node 322B (for example, the processor label of the dedicated data processor 320B) that has a binding relationship with the second interface node 314B, and modify the configuration file of the service 330 removed from the first interface node 314A according to the label of the second service data node 322B to bind each Pod service process under the service 330 to the label of the second service data node 322B, and generate a new bound service data node label for each Pod service process under the service 330, so that the service 330 and the second data service node 314B are bound to each other.

[0063] When the new bound service data node label of each Pod service process under service 330 is the processor label of the dedicated data processor 320B, the scheduler 3124 can call the second node manager 3146B of the second interface node 314B bound to the second data service node 322B of the dedicated data processor 320B according to the new bound service data node label of each Pod service process under service 330, and create each Pod service process under service 330 in the second interface node 314B, thereby migrating service 330 from the first interface node 314A to the second interface node 314B, so that when service 330 is subsequently accessed, it will be responded by the newly created Pod service processes in the second interface node 314, and the traffic of service 330 will be processed and forwarded by the second service data node 322B in normal operating status.

[0064] In some embodiments, after completing the change of the configuration file of the service 330, the scheduler 3124 may generate service migration information of the service 330 from the first interface node 314A to the second interface node 314B, and submit it to the update component 3122, and the update component 3122 writes the service migration information of the service 330 into the log component of the service control node 312 (for example, the Etcd component of the K8s master controller).

[0065] The service data node migration method provided in this embodiment replaces the sidecar deployment mode of the traditional service grid by setting a service data node (centralized agent) in a dedicated data processor, so that the service grid data plane can be transferred from the main device side to the SoC side of the dedicated data processor, thereby effectively improving the operating efficiency of the main device.

[0066] The service data node migration method provided in this embodiment detects the operating status of the service data node (centralized agent) bound to the interface node through a detector deployed in the interface node, so that when an operating abnormality is detected in the data service node of the interface node, the service in the abnormally working interface node is migrated to the normally working interface node. In this way, the present application can automatically trigger the migration operation of the service data node when a failure of the data service node is detected to ensure the continuity and availability of the service.

[0067] The service data node migration method provided in this embodiment, when detecting that the service data node bound to the target interface node in each interface node has an abnormal operation, removes the binding relationship between the target interface node and the service data node by deleting the bound service data node label of the target interface node, thereby preventing subsequent services from being continuously scheduled to the target interface node, and clears all services to be migrated in the target interface node by deleting the bound service data node label of each service in the target interface node, and then changes the configuration file of the service to be migrated according to the label of the alternative interface node bound to the service data node in each interface node, so that the service to be migrated is re-bound to the alternative interface node, thereby migrating the service to be migrated from the target interface node with abnormal operation to the alternative interface node with normal operation. By means of the above-mentioned service data node migration scheme, the present application can improve the accuracy and success rate of service migration, ensure the continuity and availability of services, and guarantee low-latency processing of traffic.

[0068] The service data node migration method provided in this embodiment provides a detector in the interface node to detect the operating status of the service data node based on a user-defined detection mechanism (for example, a polling mechanism, a heartbeat mechanism, etc.) to meet different detection requirements and improve the flexibility of system maintenance and management.

[0069] The service data node migration method provided in this embodiment can generate corresponding abnormal alarm information based on the operation abnormality detection results of the service data node, achieve the alarm purpose of operation failure, and facilitate management personnel to perform equipment failure detection and maintenance operations in a timely manner.

[0070] Figure 5 This is a structural block diagram of a service data node migration device 500 of an exemplary embodiment of the present application. As shown in the figure, the service data node migration device 500 mainly includes:

[0071] A detection module 502 is configured to obtain, through a first detector of a first interface node among multiple interface nodes, a detection result that a first service data node bound to the first interface node among multiple service data nodes is operating abnormally;

[0072] A request module 504, configured to send a service migration request to the service control node through the first detector of the first interface node in response to a detection result that the first service data node is operating abnormally;

[0073] The migration module 506 is used to release the binding relationship between the first interface node and the first service data node through the service control node in response to the service migration request, and migrate each service in the first interface node to a second interface node among multiple interface nodes, and the second interface node has a binding relationship with one of the multiple service data nodes.

[0074] Optionally, the service control node includes an update component and a scheduler.

[0075] Optionally, the migration module 506 is also used to remove the service in the first interface node through the update component in response to the service migration request; and migrate each service in the first interface node to the second interface node through the scheduler in response to the determination result that the number of services in the first interface node satisfies the first condition.

[0076] Optionally, the migration module 506 is further configured to delete the bound service data node label of the first interface node through the update component to release the binding relationship between the first interface node and the first service data node.

[0077] Optionally, the migration module 506 is also used to obtain a label of a second data service node having a binding relationship with the second interface node in response to a determination result that the number of services in the first interface node satisfies the first condition; use the label of the second data service node to modify the configuration file of the removed service to bind the service to the second data service node; and call the node manager of the second interface node bound to the second data service node to create the service in the second interface node.

[0078] Optionally, the first interface node includes a service controller.

[0079] Optionally, the migration module 506 is also used to obtain a determination result through the service controller that the number of services in the first interface node meets a first condition when it is detected that the number of services in the first interface node does not meet a preset number, and send the determination result to the scheduler.

[0080] Optionally, the detection module 502 is also used to send running status detection information to the first service data node of the first interface node through the first detector; if running status feedback information of the first service data node corresponding to the running status detection information is obtained, a detection result that the first service data node is operating normally is obtained; if the running status feedback information of the first service data node corresponding to the running status detection information is not obtained, a detection result that the first service data node is operating abnormally is obtained; or, through the first detector, obtain multiple running status information of the first service data node of the first interface node within a specified detection period, analyze the state change of the first service data node within the specified detection period according to the multiple running status information; if the first service data node has a state update within the specified detection period, a detection result that the first service data node is operating normally is obtained; if the first service data node has no state update within the specified detection period, a detection result that the first service data node is operating abnormally is obtained.

[0081] Optionally, the service control node further includes an alarm unit.

[0082] Optionally, the request module 504 is further used to send a detection result of abnormal operation of the first service data node bound to the first interface node to the alarm unit through the first detector; the alarm unit 504 is used to generate abnormal alarm information of the first service data node.

[0083] An embodiment of the present disclosure provides a computer storage medium storing a computer program code. When the computer program code is executed by a processor, the processor executes the service data node migration method described in each embodiment of the present application.

[0084] The exemplary embodiments of the present disclosure provide an electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication. The memory stores a computer program that can be executed by the at least one processor, and when the computer program is executed by the at least one processor, the electronic device performs the service data node migration method according to each exemplary embodiment of the present disclosure.

[0085] Please refer to Figure 6, a block diagram of an electronic device 600 that can serve as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0086] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0087] A plurality of components in the electronic device 600 are connected to the I / O interface 605, including: an input unit 606, an output unit 607, a storage unit 608, and a communication unit 609. The input unit 606 may be any type of device capable of inputting information to the electronic device 600, and the input unit 606 may receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 607 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 608 may include, but is not limited to, a disk, an optical disk. The communication unit 609 allows the electronic device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0088] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above. For example, in some embodiments, the service data node migration method as described above may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 600 via the ROM 602 and / or the communication unit 609. In some embodiments, the computing unit 601 may be configured to perform the service data node migration method described above in any other appropriate manner (e.g., by means of firmware).

[0089] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0090] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0091] As used in this disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0092] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0093] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0094] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and the server relationship is generated by computer programs running on respective computers and having a client-server relationship with each other.

[0095] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present disclosure can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present disclosure.

[0096] The above implementation methods are only used to illustrate the embodiments of the present disclosure, and are not limitations of the embodiments of the present disclosure. Ordinary technicians in the relevant technical field may make various changes and modifications without departing from the spirit and scope of the embodiments of the present disclosure. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present disclosure. The scope of patent protection of the embodiments of the present disclosure should be defined by the claims.

Claims

1. A service data node migration method, characterized in that: Applied to a master device, the master device is coupled to a plurality of dedicated data processors, each of which has a service data node, the master device comprises a service control node, and a plurality of interface nodes corresponding to each service data node in each dedicated data processor, each interface node has a service controller, the service control node controls each corresponding service data node through each interface node to provide data service for the master device, the method comprises: Obtaining, by means of a first detector of a first interface node among the multiple interface nodes, a detection result of abnormal operation of a first service data node bound to the first interface node among the multiple service data nodes; Sending, by the first detector of the first interface node, a service migration request to the service control node in response to a detection result that the first service data node is operating abnormally; By means of the service control node, in response to the service migration request, deleting the bound service data node label of the first interface node, so as to release the binding relationship between the first interface node and the first service data node, and remove the service in the first interface node; By means of the service controller of the first interface node, in the process of removing the service of the first interface node, detecting the number of services currently remaining in the first interface node, and when detecting that the number of services currently remaining in the first interface node does not meet a preset number, sending a determination result that the number of services in the first interface node meets a first condition to the service control node; Through the service control node, in response to the determination result that the number of services in the first interface node meets the first condition, each service in the first interface node is migrated to a second interface node among multiple interface nodes, and the second interface node has a binding relationship with one of the multiple service data nodes.

2. The method according to claim 1, characterized in that The service control node includes an update component and a scheduler; The step of migrating each service in the first interface node to a second interface node among the plurality of interface nodes comprises: Removing, by the update component, the service in the first interface node in response to the service migration request; By the scheduler, in response to a determination result that the number of the services in the first interface node meets a first condition, each service in the first interface node is migrated to the second interface node.

3. The method according to claim 2, characterized in that The releasing the binding relationship between the first interface node and the first service data node includes: The binding service data node label of the first interface node is deleted through the update component to release the binding relationship between the first interface node and the first service data node.

4. The method according to claim 2 or 3, characterized in that: In response to a determination result that the number of services in the first interface node meets a first condition, migrating each service in the first interface node to the second interface node includes: In response to a determination result that the number of services in the first interface node meets a first condition, acquiring a label of a second data service node having a binding relationship with the second interface node; Using the label of the second data service node, modifying the configuration file of the removed service to bind the service to the second data service node; The node manager of the second interface node bound to the second data service node is called to create the service in the second interface node.

5. The method according to claim 1, characterized in that The obtaining, by using a first detector of a first interface node among the multiple interface nodes, a detection result of abnormal operation of a first service data node among the multiple service data nodes corresponding to the first interface node, includes: Sending operation status detection information to the first service data node of the first interface node through the first detector, if operation status feedback information of the first service data node corresponding to the operation status detection information is obtained, a detection result that the first service data node is operating normally is obtained; if the operation status feedback information of the first service data node corresponding to the operation status detection information is not obtained, a detection result that the first service data node is operating abnormally is obtained; or Through the first detector, multiple operating status information of the first service data node of the first interface node within a specified detection period is obtained, and the state change of the first service data node within the specified detection period is analyzed according to the multiple operating status information; if the first service data node undergoes a state update within the specified detection period, a detection result indicating that the first service data node is operating normally is obtained; if the first service data node does not undergo a state update within the specified detection period, a detection result indicating that the first service data node is operating abnormally is obtained.

6. The method according to claim 1, characterized in that The service control node also includes an alarm unit; The method further comprises: Sending, through the first detector, a detection result of abnormal operation of the first service data node bound to the first interface node to the alarm unit; Generate abnormal alarm information of the first service data node through the alarm unit.

7. A service data node migration device, characterized in that: Applied to a master device, the master device is coupled to a plurality of dedicated data processors, each of which has a service data node, the master device comprises a service control node, and a plurality of interface nodes corresponding to each service data node in each dedicated data processor, each interface node has a service controller, the service control node controls each corresponding service data node through each interface node to provide data service for the master device, the device comprises: a detection module, configured to obtain, through a first detector of a first interface node among the multiple interface nodes, a detection result of abnormal operation of a first service data node bound to the first interface node among the multiple service data nodes; a request module, configured to send a service migration request to the service control node through the first detector of the first interface node in response to a detection result that the first service data node is operating abnormally; A migration module is used to delete the bound service data node label of the first interface node in response to the service migration request through the service control node, so as to release the binding relationship between the first interface node and the first service data node, and remove the service in the first interface node, and through the service controller of the first interface node, in the process of removing the service of the first interface node, detect the number of services currently remaining in the first interface node, and when it is detected that the number of services currently remaining in the first interface node does not meet the preset number, send a determination result that the number of services in the first interface node meets the first condition to the service control node, and through the service control node, in response to the determination result that the number of services in the first interface node meets the first condition, migrate each service in the first interface node to a second interface node among the multiple interface nodes, and the second interface node has a binding relationship with one of the multiple service data nodes.

8. An electronic device, characterized in that: include: A memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the service data node migration method as described in any one of claims 1 to 6 is implemented.

9. A computer storage medium, characterized in that: The computer storage medium stores a computer program code, and when the computer program code is executed by a processor, the processor executes the service data node migration method according to any one of claims 1 to 6.

Images