A Fault-Tolerant Adaptive Blueprint Deployment Method, System, Device and Medium

Abstract

The present invention discloses a fault-tolerant adaptive blueprint deployment method, system, device and medium, belonging to the field of embedded digital signal processing, including the steps of: S1, after initialization, waiting for a function blueprint deployment instruction; S2-1, obtaining the status of all nodes in the current system; S2-2, obtaining all node information corresponding to the function programs to be loaded in the function deployment blueprint; S3, comparing the status of the nodes of the program to be loaded in the deployment blueprint and determining whether it is normal and corresponding processing; S4, loading the function program into the processing chip to be executed to execute the corresponding function task; S5, loading all the function programs required by the deployment blueprint one by one and determining whether it is normal and corresponding processing; S6, completing the program loading and returning the deployment result. The present invention can judge the status of the current system nodes in real time, improve the task reliability of the system, and achieve hardware fault avoidance.

Description

Technical Field

[0001] The present invention relates to the field of embedded digital signal processing, and more specifically, to a fault-tolerant adaptive blueprint deployment method, system, device, and medium. Background Art

[0002] Traditional "combined" systems are built with individual independent devices as basic units. Once such a system is built, it is very difficult to add new functions, and the system does not have the ability to expand, upgrade, or grow. The integrated system realizes the ability of system upgrade, expansion, and reconstruction by constructing an open architecture and through software or expanding hardware modules. However, the realization of this ability comes at the cost of technological advancement. Traditional design ideas and design means are difficult to meet such technical requirements, and new design concepts, new design ideas, and new design means must be adopted. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a fault-tolerant adaptive blueprint deployment method, system, device, and medium, which can judge the current system node status in real time, improve the task reliability of the system, and achieve hardware fault avoidance, etc.

[0004] The purpose of the present invention is achieved through the following solutions:

[0005] A fault-tolerant adaptive blueprint deployment method includes the steps of:

[0006] S1, after the system initialization is completed, wait for the function blueprint deployment instruction initiated by the user according to the current task requirements;

[0007] S2-1, dynamically query the initialization information of each node in the current system to obtain the status of all nodes in the current system;

[0008] S2-2, read and parse the function deployment blueprint to obtain all node information corresponding to the function programs to be loaded in the function deployment blueprint;

[0009] S3, compare the status of the nodes to be loaded with the program in the deployment blueprint one by one to judge whether it is normal. If it is found that the nodes required by the deployment blueprint are abnormal, reselect a new function deployment blueprint and return to step S2-2 until a function deployment blueprint with all nodes normal is found, and then proceed to step S4;

[0010] S4, load the function program into the processing chip to be executed to perform the corresponding function task;

[0011] S5. Load all functional programs required by the deployment blueprint one by one, and determine whether they are normal. If the program is loaded normally, continue to load the next node program. If all programs required by the deployment blueprint are loaded normally, proceed to step S6. Otherwise, record the status of this node as an abnormal node and feedback it to step S2-1 as the basis for determining whether to select the functional deployment blueprint next time. Meanwhile, re-select a new functional deployment blueprint and proceed to step S2-2;

[0012] S6. Complete the program loading and return the deployment result, and the functional blueprint deployment task ends.

[0013] Furthermore, the number of nodes of the deployment functional programs required by the functional blueprint should be less than the total number of nodes in the system.

[0014] Furthermore, for the same function, there are multiple deployment blueprints according to different deployment node positions.

[0015] A multi-type processor node system tolerant of partial node failures includes a scheduling / control center, a functional deployment blueprint file, FPGA-based general signal processing nodes, DSP-based general signal processing nodes, and CUP-based general data processing nodes. The scheduling / control center is respectively connected to the FPGA-based general signal processing nodes, DSP-based general signal processing nodes, and CUP-based general data processing nodes.

[0016] Furthermore, node status records are available on each of the FPGA-based general signal processing nodes, DSP-based general signal processing nodes, and CUP-based general data processing nodes, and the scheduling / control center can query this status record in real time.

[0017] Furthermore, the hardware status of all FPGA-based general signal processing nodes is the same and is equivalent for functional program loading, and the same applies to DSP-based general signal processing nodes and CUP-based general data processing nodes.

[0018] Furthermore, the scheduling / control center is used to parse the blueprint deployment instruction, determine whether the current node status meets the node deployment requirements of the functional blueprint, and initiate the functional program loading tasks for FPGA, DSP, and CPU nodes.

[0019] Furthermore, the functional deployment blueprints are stored in the functional deployment blueprint file system in the form of files for the scheduling / control center to select and read.

[0020] A computer device, the computer device includes a processor and a memory, and a computer program is stored in the memory. When the computer program is loaded and executed by the processor, it performs the method described in any one of the above.

[0021] A computer-readable storage medium stores a computer program, and the computer program is loaded and executed by a processor to perform the method described in any one of the above.

[0022] The beneficial effects of the present invention include:

[0023] (1) The present invention has the technical effect of realizing hardware fault avoidance: For the design of flexible deployment of functional application programs in an integrated electronic system, a set of adaptive blueprint deployment methods that can automatically select a suitable functional deployment blueprint by real-time judging the node status is provided, so as to achieve fault tolerance. It supports high-reliable operation in the integrated electronic system. When some nodes in the system fail, by using the present invention to automatically select a deployment blueprint that does not include the faulty node, the hardware modules and chips corresponding to the faulty node can be avoided.

[0024] (2) The present invention has the technical effect of improving task reliability: For the requirements of high-reliable tasks in an integrated electronic system, using the present invention to design enough functional deployment blueprints. When some nodes fail, by redeploying the functional blueprint corresponding to the function and the newly deployed blueprint, fault handling can be realized without affecting the operation of the functional task, greatly improving the task reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 It is a schematic diagram of the process of automatically selecting a functional blueprint for deployment by real-time judging the node status in an embodiment of the present invention;

[0027] Figure 2 It is a schematic diagram of the composition of the functional blueprint deployment system in an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0028] All the features disclosed in all the embodiments in this specification, or all the steps in the methods or processes implicitly disclosed, can be combined and / or extended, replaced in any way except for mutually exclusive features and / or steps.

[0029] Embodiments of the present invention relate to the field of embedded digital signal processing, and provide a highly reliable and fault-avoiding adaptive blueprint deployment method for an integrated electronic device with "software-defined functions". Specifically, the integrated electronic device can automatically select a suitable function deployment blueprint by real-time judging the node status, so as to realize the adaptive blueprint deployment method with fault tolerance. This method is applied to an integrated electronic information processing system.

[0030] The technical solution proposed by the embodiments of the present invention provides a highly reliable and fault-avoiding adaptive blueprint deployment method for constructing an open general integrated processing software and hardware architecture under complex resource scale conditions, and realizing the dynamic deployment and reconstruction of function software such as radar, electronic reconnaissance, and communication. It greatly improves the task reliability of the integrated electronic information system, and has incomparable advantages over the traditional device-level integrated system with strong coupling between functions and hardware. As Figure 1 shown, in the embodiment, the fault-tolerant adaptive blueprint deployment method provided by the embodiments of the present invention automatically selects a suitable function deployment blueprint by real-time judging the node status, and specifically includes the following steps:

[0031] S1. After the system initialization is completed, wait for the function blueprint deployment instruction initiated by the user according to the current task requirements;

[0032] S2-1. Dynamically query the initialization information of each node in the current system to obtain the status of all nodes in the current system;

[0033] S2-2. Read and parse the function deployment blueprint to obtain all node information corresponding to the function programs to be loaded in the function deployment blueprint;

[0034] S3. Compare the status of the nodes to be loaded in the deployment blueprint one by one to judge whether it is normal. If it is found that the nodes required by the deployment blueprint are abnormal during the comparison, re-select a new function deployment blueprint, and return to step S2-2 until a function deployment blueprint with all nodes normal is found, and then proceed to step S4;

[0035] S4. Load the function program into the processing chip to be executed to execute the corresponding function task;

[0036] S5. Load all function programs required by the deployment blueprint one by one to judge whether it is normal. If the program is loaded normally, continue to load the next node program. If all programs required by the deployment blueprint are loaded normally, proceed to step S6. Otherwise, record the status of this node as an abnormal node and feedback it to S2-1 as the basis for judging whether to select a function deployment blueprint next time. At the same time, re-select a new function deployment blueprint and proceed to step S2-2;

[0037] S6. Complete the program loading and return the deployment result, and the function blueprint deployment task ends.

[0038] In a further embodiment, in order to ensure the smooth execution of the functional blueprint deployment, the number of nodes of the deployment functional program required by the functional blueprint should be less than the total number of nodes in the system. Generally, assuming that the system has three types of nodes, with the number of each type of node being L, M, and N respectively, and the number of each type of node required by the functional deployment blueprint being o, p, and q respectively, then o ≤ L, p ≤ M, q ≤ N.

[0039] In a further embodiment, in order to ensure that there are sufficient deployment blueprints to choose from, the same function should have multiple deployment blueprints according to the different positions of the deployment nodes. For the system with the above general assumptions, all the deployment methods of the function in the system are in, that is, there are deployment blueprints to choose from.

[0040] As Figure 2 shown, the multi-type processor node system capable of tolerating partial node failures provided by the embodiment of the present invention includes the following:

[0041] The system consists of a scheduling / control center, a functional deployment blueprint file, FPGA-based general signal processing nodes, DSP-based general signal processing nodes, and CUP-based general data processing nodes;

[0042] In a further embodiment, on the FPGA-based general signal processing nodes, DSP-based general signal processing nodes, and CUP-based general data processing nodes, there are node status records, and the scheduling / control center can query this status in real time;

[0043] In a further embodiment, the hardware states of all FPGA-based general signal processing nodes are the same and are equivalent for the loading of functional programs. The same is true for DSP-based general signal processing nodes and CUP-based general data processing nodes;

[0044] In a further embodiment, the scheduling / control center is used to parse the blueprint deployment instruction, determine whether the current node status meets the node deployment requirements of the functional blueprint, and initiate the functional program loading tasks of nodes such as FPGA, DSP, and CPU;

[0045] In a further embodiment, all functional deployment blueprints are stored in the functional deployment blueprint file system in the form of files for the scheduling / control center to select and read.

[0046] The present invention has the following improved effects compared with the prior art:

[0047] The hardware failures of the present invention can be automatically avoided: In the existing system for handling hardware failures, if the blueprint deployment fails, manual judgment and analysis of the failure reasons are required, and then different blueprints are selected according to the failures and redeployed. It does not have the ability to automatically avoid hardware failures in real time during the blueprint deployment process, which greatly increases the timeliness of the system to execute tasks. Based on the design of the flexible deployment function application program in the integrated electronic system, the present invention has invented a set of function deployment blueprints that can automatically select a suitable one by judging the node status in real time. Among them, when it is found that a certain node involved in the deployment blueprint has a failure when the blueprint deployment reaches S3, at this time, execute S2-2, reselect a deployment blueprint that does not include this faulty node, and then sequentially execute S3, S4, S5, and S6 to complete the blueprint deployment. Thus, during the blueprint deployment process, the system automatically reselects the blueprint corresponding to this function that does not include the faulty node for deployment, realizing the automatic avoidance of hardware failures without affecting the operation conditions of the function tasks.

[0048] The present invention improves the task reliability: In the traditional combined system, failure avoidance is achieved through 1:1 redundancy design of hardware resources, which not only causes a large waste of resources, but also the redundancy value of the system is only 1. When any node in the two sets of backups fails, it will affect the execution of the system functions, and the task reliability is relatively low. To meet the requirements of high-reliability tasks in the integrated electronic system, using the method provided by the present invention, when some nodes fail, there are enough function blueprint deployment methods to avoid the faulty nodes. Suppose there are three types of nodes in the system, with 6, 4, and 2 nodes in each type respectively, and the number of nodes that need to be deployed in a certain function blueprint is 3, 2, and 1 respectively. When 1 node in the 6 nodes of the first type fails, there are 3 ways for the system to choose to avoid this faulty node. When 1 node in the 4 nodes of the second type fails, there are 2 ways for the system to choose to avoid this faulty node. When 1 node in the 2 nodes of the third type fails, there is 1 way for the system to choose to avoid this faulty node. The total redundancy value is 6. Therefore, the redundancy value of this function for any 1 node failure is 6, which is 6 times that of the traditional combined system, thus greatly improving the task reliability of the system.

[0049] Embodiment 1

[0050] A fault-tolerant adaptive blueprint deployment method, comprising the steps of:

[0051] S1, after the system initialization is completed, wait for the function blueprint deployment instruction initiated by the user according to the current task requirements;

[0052] S2-1, dynamically query the initialization information of each node in the current system to obtain the status of all nodes in the current system;

[0053] S2-2. Read and parse the function deployment blueprint, and obtain all node information corresponding to the function programs to be loaded in the function deployment blueprint;

[0054] S3. Compare the status of the program nodes to be loaded in the deployment blueprint one by one to determine whether they are normal. If it is found during the comparison that the deployment blueprint requires a node to be abnormal, reselect a new function deployment blueprint and return to step S2-2 until a function deployment blueprint with all nodes being normal is found, and then proceed to step S4;

[0055] S4. Load the function program into the processing chip to be executed to perform the corresponding function tasks;

[0056] S5. Load all function programs required by the deployment blueprint one by one and determine whether they are normal. If the program is loaded normally, continue to load the next node program. If all programs required by the deployment blueprint are loaded normally, proceed to step S6. Otherwise, record the status of this node as an abnormal node and feedback it to step S2-1 as the basis for determining whether to select a function deployment blueprint next time. At the same time, reselect a new function deployment blueprint and proceed to step S2-2;

[0057] S6. Complete the program loading and return the deployment result, and the function blueprint deployment task ends.

[0058] Embodiment 2

[0059] Based on Embodiment 1, the number of nodes of the deployment function program required by the function blueprint should satisfy being less than the total number of nodes in the system.

[0060] Embodiment 3

[0061] Based on Embodiment 1, for the same function, there are multiple deployment blueprints according to different deployment node positions.

[0062] Embodiment 4

[0063] A multi-type processor node system that tolerates partial node failures includes a scheduling / control center, a function deployment blueprint file, FPGA-based general-purpose signal processing nodes, DSP-based general-purpose signal processing nodes, and CUP-based general-purpose data processing nodes. The scheduling / control center is respectively connected to the FPGA-based general-purpose signal processing nodes, DSP-based general-purpose signal processing nodes, and CUP-based general-purpose data processing nodes.

[0064] Embodiment 5

[0065] Based on Embodiment 4, node status records are available on the FPGA-based general-purpose signal processing nodes, DSP-based general-purpose signal processing nodes, and CUP-based general-purpose data processing nodes, and the scheduling / control center can query this status record in real time.

[0066] Embodiment 6

[0067] Based on Embodiment 4, the hardware states of all general-purpose signal processing nodes of the FPGA type are the same and are equivalent for loading functional programs. The same applies to general-purpose signal processing nodes of the DSP type and general-purpose data processing nodes of the CUP type.

[0068] Embodiment 7

[0069] Based on Embodiment 4, the scheduling / control center is used to parse blueprint deployment instructions, determine whether the current node state meets the node deployment requirements of the functional blueprint, and initiate the task of loading functional programs for FPGA, DSP, and CPU nodes.

[0070] Embodiment 8

[0071] Based on Embodiment 4, functional deployment blueprints are stored in the functional deployment blueprint file system in the form of files for selection and reading by the scheduling / control center.

[0072] Embodiment 9

[0073] A computer device, the computer device includes a processor and a memory, and a computer program is stored in the memory. When the computer program is loaded and executed by the processor, the method described in any one of Embodiments 1 to 8 is performed.

[0074] Embodiment 10

[0075] A computer-readable storage medium, in which a computer program is stored. The computer program is loaded and executed by a processor to perform the method described in any one of Embodiments 1 to 8.

[0076] The units involved in the embodiments of the present invention can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not constitute a limitation to the unit itself in some cases.

[0077] According to one aspect of the present application, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the methods provided in the above various alternative implementation manners.

[0078] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or may exist alone without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiments.

[0079] Parts not involved in the present invention are the same as or can be implemented using the prior art.

[0080] The above technical solution is only one implementation manner of the present invention. For those skilled in the art, based on the disclosed application methods and principles of the present invention, various types of improvements or deformations can be easily made, not limited to the methods described in the above specific implementation manners of the present invention. Therefore, the manner described above is only preferred and does not have a restrictive meaning.

[0081] In addition to the above examples, those skilled in the art can obtain inspiration according to the above disclosure or make modifications using the knowledge or technology in related fields to obtain other embodiments. The features of each embodiment can be interchanged or replaced. As long as the modifications and changes made by those skilled in the art do not depart from the spirit and scope of the present invention, they should all be within the protection scope of the appended claims of the present invention.

Claims

1. A fault-tolerant adaptive blueprint deployment method, characterized in that, Including the steps: S1. After the system initialization is completed, wait for the function blueprint deployment instruction initiated by the user according to the current task requirements. S2-1. Dynamically query the initialization information of each node in the current system to obtain the status of all nodes in the current system. S2-2. Read and parse the function deployment blueprint to obtain all node information corresponding to the function programs to be loaded in this function deployment blueprint. S3. Compare the status of the nodes where the programs to be loaded in the deployment blueprint one by one to determine whether they are normal. If it is found that the nodes required by the deployment blueprint are abnormal during the comparison, re-select a new function deployment blueprint and return to step S2-2 until a function deployment blueprint with all nodes being normal is found, and then proceed to step S4. S4. Load the function program into the processing chip to be executed to perform the corresponding function task. S5. Load all the function programs required by the deployment blueprint one by one to determine whether they are normal. If the program is loaded normally, continue to load the next node program. If all the programs required by the deployment blueprint are loaded normally, proceed to step S6. Otherwise, record the status of this node as an abnormal node and feedback it to step S2-1 as the basis for determining whether to select a function deployment blueprint next time. At the same time, re-select a new function deployment blueprint and proceed to step S2-2. S6. Complete the program loading and return the deployment result, and the function blueprint deployment task ends.

2. The fault-tolerant adaptive blueprint deployment method according to claim 1, characterized in that The number of nodes of the deployment function program required by the function blueprint should be less than the total number of nodes in the system.

3. The fault-tolerant adaptive blueprint deployment method according to claim 1, wherein For the same function, there are multiple deployment blueprints according to different deployment node positions.

4. A multi-type processor node system that tolerates partial node failures, characterized in that, For implementing the fault-tolerant adaptive blueprint deployment method described in any one of claims 1 to 3, it further includes a scheduling / control center, a function deployment blueprint file, FPGA-based general signal processing nodes, DSP-based general signal processing nodes, and CUP-based general data processing nodes. The scheduling / control center is respectively connected to the FPGA-based general signal processing nodes, DSP-based general signal processing nodes, and CUP-based general data processing nodes.

5. The multi-type processor node system tolerant to partial node failures according to claim 4, characterized in that, There are node status records on the FPGA-based general signal processing nodes, DSP-based general signal processing nodes, and CUP-based general data processing nodes, and the scheduling / control center can query this status record in real time.

6. The multi-type processor node system capable of tolerating partial node failures according to claim 4, characterized in that The hardware status of all FPGA-based general signal processing nodes is the same and is equivalent for function program loading. The same applies to DSP-based general signal processing nodes and CUP-based general data processing nodes.

7. The multi-type processor node system tolerant to partial node failures according to claim 4, characterized in that, The scheduling / control center is used to parse the blueprint deployment instruction, determine whether the current node status meets the node deployment requirements of the function blueprint, and initiate the function program loading tasks for FPGA, DSP, and CPU nodes.

8. The multi-type processor node system tolerant to partial node failures according to claim 4, wherein The function deployment blueprints are stored in the function deployment blueprint file system in the form of files for the scheduling / control center to select and read.

9. A computer device, characterized in that, The computer device includes a processor and a memory. The memory stores a computer program, and when the computer program is loaded and executed by the processor, it performs the method described in any one of claims 1 to 3.

10. A computer-readable storage medium, characterized in that, A computer program is stored in a readable storage medium, and the computer program is loaded and executed by a processor to perform the method described in any one of claims 1 to 3.

Images