Remote supercomputing-oriented CFD software heterogeneous operation state monitoring method, device and equipment and medium

Abstract

The invention discloses a remote supercomputing-oriented CFD software heterogeneous operation state monitoring method, device and equipment and a medium, relates to the technical field of data processing, and is applied to a preset monitoring system which is internally provided with a plurality of different types of supercomputing scheduling system monitoring scripts. Comprising the steps that when a state monitoring instruction which is sent through an interaction page and aims at a target task job is received, a corresponding target super-computing scheduling system monitoring script is called through a super-computing scheduling system type in the state monitoring instruction, and a corresponding task monitoring thread is selected to be started according to the target super-computing scheduling system monitoring script; obtaining target task operation state information of the corresponding CFD software fed back after the task monitoring thread is executed, and performing identification processing on the target task operation state information to obtain to-be-displayed operation state information; and sending the to-be-displayed job state information to the interaction page, and displaying the job running state of the CFD software. And through separate deployment, the overall environment compatibility of the software is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and medium for monitoring heterogeneous operation status of CFD software for remote supercomputers. Background Art

[0002] Computational Fluid Dynamics (CFD) is a science and technology that uses computers and discrete numerical methods to perform numerical simulation and analysis on fluid mechanics problems. It is an emerging branch of fluid mechanics. With the rapid development of computing and computer technology, CFD technology has been applied to all aspects of national production, especially in the fields of aerospace, automobiles, ships, water conservancy, etc. It is a very important auxiliary tool in engineering applications and product design.

[0003] As an indispensable and primary link in industrial production and manufacturing, industrial simulation technology has been widely used in various fields of industry. With the rise of a new round of industrial revolutions such as intelligent manufacturing, Industry 4.0 and Industrial Internet, the demand for industrial simulation is becoming increasingly strong, and engineers and designers have higher and higher requirements for the precision of simulation. Therefore, CFD software is widely used in aerospace, transportation, energy and power, bridge construction and other fields. It is a typical computationally intensive scientific computing software that strongly relies on high-performance computers. However, when CFD software in the prior art performs simulation calculations, when there is a lack of visualization nodes in the supercomputer, the software cannot be deployed and used due to the hardware requirements for the installation environment. In addition, when performing simulation calculation scenarios, the supercomputer scheduling system job management command is directly executed to obtain the job running status. When facing different types of supercomputer scheduling systems, the code needs to be modified, debugged, and tested before it can be compiled and deployed before it can be used, which is insufficient in compatibility.

[0004] In summary, how to improve the efficiency of using CFD software, realize the real-time monitoring function of the operation status of simulation software in heterogeneous states, and meet the research and development needs of human-computer interaction of CFD software on high-performance computers are technical problems to be solved in this field. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for monitoring the heterogeneous operation status of CFD software for remote supercomputers, which can improve the efficiency of CFD software use, realize the real-time monitoring function of the operation status of simulation software in heterogeneous states, and meet the research and development needs of human-computer interaction of CFD software on high-performance computers. The specific scheme is as follows:

[0006] In the first aspect, the present application discloses a method for monitoring the heterogeneous job status of CFD software for remote supercomputers, which is applied to a preset monitoring system, wherein the preset monitoring system has built-in several different types of supercomputer scheduling system monitoring scripts, including:

[0007] When receiving a status monitoring instruction for a target task job sent through an interactive page, calling a corresponding target supercomputing scheduling system monitoring script according to the supercomputing scheduling system type in the status monitoring instruction, so as to select and start a corresponding task monitoring thread according to the target supercomputing scheduling system monitoring script;

[0008] Obtaining target task operation status information of the corresponding CFD software fed back after executing the task monitoring thread, and identifying and processing the target task operation status information to obtain the operation status information to be displayed;

[0009] The job status information to be displayed is sent to the interactive page so as to display the job running status of the CFD software.

[0010] Optionally, calling a corresponding target supercomputing scheduling system monitoring script through the supercomputing scheduling system type in the status monitoring instruction to select and start a corresponding task monitoring thread according to the target supercomputing scheduling system monitoring script includes:

[0011] Monitor the monitoring queue according to a preset polling time interval, and determine whether there is a task job to be monitored in the monitoring queue; wherein the task job to be monitored is a CFD calculation job submitted to the supercomputing environment;

[0012] If the task to be monitored does not exist, the monitoring action is stopped to release the current memory resources;

[0013] If the task job to be monitored exists, the corresponding target supercomputing scheduling system monitoring script is called through the supercomputing scheduling system type in the status monitoring instruction, so as to select and start the corresponding task monitoring thread according to the target supercomputing scheduling system monitoring script.

[0014] Optionally, the identifying and processing the target task operation status information to obtain the operation status information to be displayed includes:

[0015] Determine whether the target task operation status information is empty status information;

[0016] If the target task job status information is empty status information, the job status of the target task job is marked as stopped to obtain job status information to be displayed, and the task job to be monitored representing the target task job in the monitoring queue is removed;

[0017] If the target task operation status information is non-empty status information, determining whether the target task operation status information satisfies a completed status condition;

[0018] If the completed status condition is met, the job status of the target task job is marked as completed to obtain job status information to be displayed.

[0019] Optionally, after determining whether the target task job status information satisfies a completed status condition, the method further includes:

[0020] If the completed status condition is not met, determining whether the target task job status information meets the status conditions of the queuing status and / or the running status;

[0021] If the target task job status information satisfies the status conditions of the queuing status and / or the running status, it is determined whether the target task job status information is updated from the previous queuing status to the current running status to obtain a corresponding determination result.

[0022] Optionally, after determining whether the target task job status information is updated from the previous queuing status to the current running status to obtain a corresponding determination result, the method further includes:

[0023] If the judgment result is that the target task job status information has not been updated from the previous state to the current state, then the job status of the target task job is marked as a queue state and / or a running state to obtain the job status information to be displayed;

[0024] If the judgment result is that the target task operation status information is updated from the previous queuing status to the current running status, then checking whether the network connection between the personal computer and the preset monitoring system is disconnected;

[0025] If the network connection is disconnected, removing the target task job from the monitoring queue;

[0026] If the network connection is not disconnected, the job status of the target task job is updated to a running status to obtain job status information to be displayed.

[0027] Optionally, before monitoring the monitoring queue at a preset polling time interval and determining whether there is a task to be monitored in the monitoring queue, the method further includes:

[0028] Starts the listener and loads a preset configuration file to get a preset polling interval.

[0029] Optionally, before receiving the status monitoring instruction for the target task job sent through the interactive page, the method further includes:

[0030] The interactive page is placed on the personal computer, and the CFD software and preset monitoring system are placed on the supercomputing environment.

[0031] In the second aspect, the present application discloses a CFD software heterogeneous job status monitoring device for remote supercomputers, which is applied to a preset monitoring system, wherein the preset monitoring system has several different types of supercomputer scheduling system monitoring scripts built in, and the device includes:

[0032] A thread selection module, for, when receiving a status monitoring instruction for a target task job sent through an interactive page, calling a corresponding target supercomputing scheduling system monitoring script according to the supercomputing scheduling system type in the status monitoring instruction, so as to select and start a corresponding task monitoring thread according to the target supercomputing scheduling system monitoring script;

[0033] An information monitoring module is used to obtain the target task operation status information of the corresponding CFD software fed back after executing the task monitoring thread, and identify and process the target task operation status information to obtain the operation status information to be displayed;

[0034] The information display module is used to send the job status information to be displayed to the interactive page so as to display the job running status of the CFD software.

[0035] In a third aspect, the present application discloses an electronic device, comprising:

[0036] Memory, used to store computer programs;

[0037] A processor is used to execute the computer program to implement the steps of the aforementioned method for monitoring the heterogeneous operation status of CFD software for remote supercomputing.

[0038] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steps of the aforementioned disclosed method for monitoring heterogeneous job status of CFD software for remote supercomputing are implemented.

[0039] It can be seen that the present application discloses a CFD software heterogeneous job status monitoring method for remote supercomputers, which is applied to a preset monitoring system, wherein the preset monitoring system has several different types of supercomputer scheduling system monitoring scripts built in, including: when receiving a status monitoring instruction for a target task job sent through an interactive page, the corresponding target supercomputer scheduling system monitoring script is called through the supercomputer scheduling system type in the status monitoring instruction, so as to select and start the corresponding task monitoring thread according to the target supercomputer scheduling system monitoring script; obtain the target task job status information of the corresponding CFD software fed back after executing the task monitoring thread, and identify and process the target task job status information to obtain the job status information to be displayed; send the job status information to be displayed to the interactive page to display the job running status of the CFD software. It can be seen that the present invention deploys the software interactive interface and the job status monitoring system separately, improves the overall environmental compatibility of the software, and the built-in scheduling system monitoring script improves the ability of the software to be compatible with different clusters. The many-to-one monitoring mode greatly reduces the software job status monitoring, and indirectly improves the software job monitoring processing capability for the CPU resource overhead of the supercomputer. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention 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 embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0041] Figure 1 A flow chart of a method for monitoring heterogeneous operation status of CFD software for remote supercomputers disclosed in this application;

[0042] Figure 2 A monitoring workflow diagram of a listener disclosed in this application;

[0043] Figure 3 A schematic diagram of the interaction between a listener disclosed in this application and different scheduling systems;

[0044] Figure 4 This is a graph of the output return form of querying the running status of a supercomputing job disclosed in this application;

[0045] Figure 5 This is a schematic diagram of the structure of a CFD software heterogeneous operation status monitoring device for remote supercomputers disclosed in this application;

[0046] Figure 6 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0048] Computational fluid dynamics is a science and technology that uses computers and discrete numerical methods to perform numerical simulation and analysis on fluid mechanics problems. It is an emerging branch of fluid mechanics. With the rapid development of computing and computer technology, CFD technology has been applied to all aspects of national production, especially in the fields of aerospace, automobiles, ships, water conservancy, etc. It is a very important auxiliary tool in engineering applications and product design.

[0049] As an indispensable and primary link in industrial production and manufacturing, industrial simulation technology has been widely used in various fields of industry. With the rise of a new round of industrial revolutions such as intelligent manufacturing, Industry 4.0 and Industrial Internet, the demand for industrial simulation is becoming increasingly strong, and engineers and designers have higher and higher requirements for the precision of simulation. Therefore, CFD software is widely used in aerospace, transportation, energy and power, bridge construction and other fields. It is a typical computationally intensive scientific computing software that strongly relies on high-performance computers. However, when CFD software in the prior art performs simulation calculations, when there is a lack of visualization nodes in the supercomputer, the software cannot be deployed and used due to the hardware requirements for the installation environment. In addition, when performing simulation calculation scenarios, the supercomputer scheduling system job management command is directly executed to obtain the job running status. When facing different types of supercomputer scheduling systems, the code needs to be modified, debugged, and tested before it can be compiled and deployed before it can be used, which is insufficient in compatibility.

[0050] To this end, the present invention provides a CFD software heterogeneous operation status monitoring solution for remote supercomputers, which can improve the use efficiency of CFD software, realize the real-time monitoring function of the operation status of simulation software in a heterogeneous state, and meet the research and development needs of human-computer interaction of CFD software on high-performance computers.

[0051] Reference Figure 1 As shown, the embodiment of the present invention discloses a method for monitoring the heterogeneous job status of CFD software for remote supercomputers, which is applied to a preset monitoring system, wherein the preset monitoring system has several different types of supercomputer scheduling system monitoring scripts built in, including:

[0052] Step S11: When receiving a status monitoring instruction for a target task job sent through an interactive page, the corresponding target supercomputing scheduling system monitoring script is called through the supercomputing scheduling system type in the status monitoring instruction to select and start the corresponding task monitoring thread according to the target supercomputing scheduling system monitoring script.

[0053] In this embodiment, before receiving the status monitoring instruction for the target task job sent through the interactive page, it also includes: arranging the interactive page on the personal computer side, and arranging the CFD software and the preset monitoring system on the supercomputing environment. It can be understood that the preset monitoring system has several different types of supercomputing scheduling system monitoring scripts built in, such as Slurm (Simple Linux Utility for Resource Management, simple Linux resource management tool), LSF (Load Sharing Facility, load sharing tool), PBS (Portable Batch System, portable batch processing system), SGE (SunGrid Engine, Sun Grid Engine), etc., which can be compatible with the above multiple supercomputing scheduling systems. At the same time, the interactive page is arranged as a client on the PC (Personal Computer, personal computer) side, and the preset monitoring system is deployed as a server side on the supercomputing environment. It should be noted that the CFD software is also deployed on the supercomputing environment for executing the corresponding CFD task calculation process. Moreover, the preset monitoring system is deployed on the supercomputing, and the preset monitoring system is heterogeneously designed to enable it to simultaneously meet the job status monitoring needs of multiple clients (the interactive interface is deployed on the PC side). Specifically, the preset monitoring system writes different types of supercomputer scheduling system instruction sets into Bash (Bourne-Again SHell) scripts, which can monitor the operation status of jobs based on the pre-configured scheduling system type and execute scripts compatible with different supercomputer scheduling systems. In this way, no matter which scheduling system the supercomputer uses, the monitoring system can effectively obtain job status information, provide services for multiple interactive interfaces, and improve the monitoring efficiency of supercomputer job operation status and CPU (Central Processing Unit) utilization.

[0054] In this way, the interactive interface is decoupled from the preset monitoring system deployed on the supercomputer environment as a client. On the one hand, the preset monitoring system interacts with the supercomputer scheduling system through scripts corresponding to the internal different types of supercomputer scheduling system instruction sets, and on the other hand, it monitors the job status of the CFD software and feeds back the information to the interactive interface on the PC for users to view. This solves the problem that the user cannot start the interactive interface to monitor the running status of the simulation job due to the lack of visualization nodes in the supercomputer.

[0055] In this embodiment, the user starts the monitoring operation through the interactive interface on the PC side, and the interactive interface sends the status monitoring request / status monitoring instruction to the preset monitoring system deployed on the supercomputing environment. Then, the preset monitoring system determines and executes the target supercomputing scheduling system monitoring script from the pre-configured monitoring scripts according to the supercomputing scheduling system type to start the corresponding task monitoring thread; wherein, the supercomputing scheduling system monitoring script is a Bash script, which contains the corresponding type of supercomputing scheduling system instructions.

[0056] In this embodiment, a monitoring request in JSON (JavaScript Object Notation) format is generated in the interactive interface. The monitoring request mainly includes two attributes: the monitoring job ID (Identification) and the path of the job on the supercomputer. Then, the monitoring request is serialized and sent to the preset status monitoring system through the network. The preset status monitoring system receives the serialized monitoring request and obtains the JSON format request that needs to be submitted for monitoring through deserialization. After the status monitoring system obtains the monitoring request that needs to be submitted for monitoring, it first creates a job monitoring object and sets its corresponding attribute values, and then adds the job monitoring object to the monitoring queue.

[0057] Among them, the job monitoring object mainly includes attributes such as job code, job location, current state, previous state, connection channel, etc. The job code is the ID value returned by the supercomputing job scheduling system after submitting the job, the job location is the absolute path of the job on the supercomputing, the current state is empty when the monitoring is submitted for the first time, and the previous state is recorded as PD (queuing), and the connection channel is the network connection object established between the client and the monitoring system, which records the network connection address information, ID, heartbeat, etc.

[0058] In this embodiment, the listener is started and a preset configuration file is loaded to obtain a preset polling time interval, the monitoring queue is listened to according to the preset polling time interval, and it is determined whether there is a task job to be monitored in the monitoring queue; wherein the task job to be monitored is a CFD calculation job submitted to the supercomputing environment; if the task job to be monitored does not exist, the listening action is stopped to release the current memory resources; if the task job to be monitored exists, the corresponding target supercomputing scheduling system monitoring script is called through the supercomputing scheduling system type in the status monitoring instruction, so as to select and start the corresponding task monitoring thread according to the target supercomputing scheduling system monitoring script. It can be understood that, referring to Figure 2 As shown in the figure, after the client submits a monitoring request, the listener needs to be enabled. After the listener is enabled, it will read the job monitoring object in the monitoring queue to perform monitoring. The specific steps are as follows:

[0059] (1-1) Start the listener and read the preset parameter information such as the polling time interval, supercomputer scheduling system type, and workspace address in the configuration file. Start the asynchronous listening thread and run the listening logic in the listening thread at the polling time interval to monitor the jobs submitted to the supercomputer.

[0060] (1-2) Determine whether the monitoring queue is empty. If the monitoring queue is empty, it means there is no job to be monitored. At this time, stop the monitoring thread, close the listener, and release memory resources. It should be noted that the specific implementation of the monitoring queue can be a queue, array, collection, string, etc. There is no specific limitation on this.

[0061] (1-3) If there are jobs that need to be monitored in the monitoring queue, call the corresponding Bash script to query according to the supercomputing scheduling system type in the configuration file, such as Figure 3 As shown, the corresponding supercomputer scheduling system monitoring script is pre-configured, wherein the configured supercomputer scheduling system monitoring script specifically includes but is not limited to: Slurm scheduling system query script, LSF scheduling system query script, PBS scheduling system query script, SGE scheduling system query script. Then when the listener selects to execute the "Slurm scheduling system query script" from the pre-configured monitoring script according to the read scheduling system type, it waits for the target task job status information fed back after the execution of the "Slurm scheduling system query script" as the return result. The query result output format is as follows Figure 4 shown.

[0062] Step S12: obtaining the target task operation status information of the corresponding CFD software fed back after executing the task monitoring thread, and identifying and processing the target task operation status information to obtain the operation status information to be displayed.

[0063] In this embodiment, it is determined whether the target task job status information is empty status information; if the target task job status information is empty status information, the job status of the target task job is marked as stopped to obtain the job status information to be displayed, and the task job to be monitored representing the target task job in the monitoring queue is removed; if the target task job status information is non-empty status information, it is determined whether the target task job status information meets the completed status condition; if the completed status condition is met, the job status of the target task job is marked as completed to obtain the job status information to be displayed. If the completed status condition is not met, it is determined whether the target task job status information meets the status conditions of the queuing status and / or the running status; if the target task job status information meets the status conditions of the queuing status and / or the running status, it is determined whether the target task job status information is updated from the previous queuing status to the current running status to obtain the corresponding judgment result.

[0064] Specifically, if the judgment result is that no update operation has occurred to the target task job status information from the previous state to the current state, the job status of the target task job is marked as a queue state and / or a running state to obtain the job status information to be displayed; if the judgment result is that the target task job status information is updated from the previous queue state to the current running state, check whether the network connection between the personal computer and the preset monitoring system is disconnected; if the network connection is disconnected, remove the target task job from the monitoring queue; if the network connection is not disconnected, update the job status of the target task job to the running state to obtain the job status information to be displayed.

[0065] It is understandable that, referring to Figure 2 As shown, the target task job status information is identified and processed by executing the following steps to obtain the job status information to be displayed:

[0066] (1-4) Determine whether the query result is empty. If it is empty, it means that all jobs that need to be monitored on the cluster have stopped. The listener will mark the status of all jobs in the monitoring queue as stopped (S) and return it to the client, then remove the above jobs from the monitoring queue, and repeat steps (1-2) after the polling time interval. If it is not empty, it means that there are jobs that need to be monitored on the supercomputer. It should be noted that polling can be made single-threaded or multi-threaded according to the number of monitoring tasks, and there is no specific limitation on this. During the monitoring process, due to the differences in the job running status defined by different scheduling systems, when the interactive interface obtains different statuses, parsing errors or parsing failures often occur due to lack of definition. By uniformly defining unrecognized status as stopped (S), the error rate of the software monitoring module is reduced, and the quality of the software job status monitoring module is effectively improved.

[0067] (1-5) When there is an overload in the monitoring queue, that is, the target task job status information is non-empty, the status needs to be identified and processed. The listener reads the query results and matches the job ID to identify the running status of the job. When the running status is not PD or R (running), the listener marks the job as completed, notifies the client, and removes the job from the monitoring queue.

[0068] (1-6) When the job status in the monitoring queue is PD or R, it is necessary to determine whether the status changes from PD to R. If the status changes from PD to R, determine whether the network connection between the client and the job monitoring system is disconnected. If the connection is not disconnected, the status change of the job is returned. If the connection is disconnected, that is, the network connection port is in an abnormal state, then the job will be removed from the job monitoring queue.

[0069] After the preset polling time interval, repeat from step (1-2) until there are no jobs to be monitored in the job monitoring queue, and then close the listener.

[0070] It should be noted that removing a job from the job monitoring queue, that is, canceling the monitoring request data, is a preset state monitoring system that removes the job in the monitoring queue according to the requested job ID and position after obtaining the request data for canceling the monitoring.

[0071] In this way, the present invention writes the instruction sets of different types of supercomputer scheduling systems such as Slurm, LSF, PBS, SGE, etc. into Bash scripts. When facing different types of supercomputer scheduling systems, the present invention does not need to modify the code, debug, and test before compiling and deploying, and has stronger compatibility. It can execute scripts compatible with different supercomputer scheduling systems according to the pre-configured scheduling system type to monitor the job running status, greatly improving the compatibility.

[0072] Step S13: Sending the job status information to be displayed to the interactive page so as to display the job running status of the CFD software.

[0073] In this embodiment, the preset monitoring system feeds back the processed job status information to the interactive interface of the PC, and the user views the job running status of the CFD software on the interactive interface. For example, when the task is in the "R" state, it means that the related job of the CFD software is running normally on the supercomputer. The system can feed back the specific operating parameters and other information of the task to the interactive interface of the PC through the monitoring system, so that the user can understand the real-time progress of the job.

[0074] It can be seen that the present application discloses a CFD software heterogeneous job status monitoring method for remote supercomputers, which is applied to a preset monitoring system, wherein the preset monitoring system has several different types of supercomputer scheduling system monitoring scripts built in, including: when receiving a status monitoring instruction for a target task job sent through an interactive page, the corresponding target supercomputer scheduling system monitoring script is called through the supercomputer scheduling system type in the status monitoring instruction, so as to select and start the corresponding task monitoring thread according to the target supercomputer scheduling system monitoring script; obtain the target task job status information of the corresponding CFD software fed back after executing the task monitoring thread, and identify and process the target task job status information to obtain the job status information to be displayed; send the job status information to be displayed to the interactive page to display the job running status of the CFD software. It can be seen that the present invention deploys the software interactive interface and the job status monitoring system separately, improves the overall environmental compatibility of the software, and the built-in scheduling system monitoring script improves the ability of the software to be compatible with different clusters. The many-to-one monitoring mode greatly reduces the software job status monitoring, and indirectly improves the software job monitoring processing capability for the CPU resource overhead of the supercomputer.

[0075] Reference Figure 5 As shown, the present invention also discloses a CFD software heterogeneous job status monitoring device for remote supercomputers, which is applied to a preset monitoring system, wherein the preset monitoring system has several different types of supercomputer scheduling system monitoring scripts built in, and the device includes:

[0076] The thread selection module 11 is used for, when receiving a status monitoring instruction for a target task job sent through an interactive page, calling a corresponding target supercomputing scheduling system monitoring script according to the supercomputing scheduling system type in the status monitoring instruction, so as to select and start a corresponding task monitoring thread according to the target supercomputing scheduling system monitoring script;

[0077] The information monitoring module 12 is used to obtain the target task operation status information of the corresponding CFD software fed back after executing the task monitoring thread, and identify and process the target task operation status information to obtain the operation status information to be displayed;

[0078] The information display module 13 is used to send the job status information to be displayed to the interactive page so as to display the job running status of the CFD software.

[0079] It can be seen that the present application discloses that when receiving the status monitoring instruction for the target task job sent through the interactive page, the corresponding target supercomputing scheduling system monitoring script is called through the supercomputing scheduling system type in the status monitoring instruction, so as to select and start the corresponding task monitoring thread according to the target supercomputing scheduling system monitoring script; the target task job status information of the corresponding CFD software fed back after executing the task monitoring thread is obtained, and the target task job status information is identified and processed to obtain the job status information to be displayed; the job status information to be displayed is sent to the interactive page to display the job running status of the CFD software. It can be seen that the present invention deploys the software interactive interface and the job status monitoring system separately, improves the overall environmental compatibility of the software, the built-in scheduling system monitoring script improves the software's ability to be compatible with different clusters, and the many-to-one monitoring mode greatly reduces the software job status monitoring, and indirectly improves the software job monitoring processing capability for the CPU resource overhead of the supercomputer.

[0080] Furthermore, the present application also discloses an electronic device. Figure 6 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0081] Figure 6A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the CFD software heterogeneous job status monitoring method for remote supercomputing disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0082] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0083] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0084] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0085] Among them, the operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, so as to realize the operation and processing of the massive data 223 in the memory 22 by the processor 21, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the CFD software heterogeneous operation status monitoring method for remote supercomputing executed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks. In addition to data transmitted from an external device received by the electronic device, the data 223 can also include data collected by its own input and output interface 25, etc.

[0086] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned disclosed method for monitoring heterogeneous job status of CFD software for remote supercomputing is implemented. For the specific steps of the method, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, and no further description will be given here.

[0087] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0088] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application. The steps of the method or algorithm described in conjunction with the embodiments disclosed herein can be implemented directly with hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory RAM (Random Access Memory), memory, read-only memory ROM (Read Only Memory), electrically programmable EPROM (Electrically Programmable Read Only Memory), electrically erasable programmable EEPROM (ElectricErasable Programmable Read Only Memory), register, hard disk, removable disk, CD-ROM (CompactDisc-Read Only Memory), or any other form of storage medium known in the technical field.

[0089] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0090] The scheme provided by the present invention is introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for monitoring the heterogeneous operation status of CFD software for remote supercomputers, characterized in that: Applied to the preset monitoring system, which has several different types of supercomputing scheduling system monitoring scripts built in, including: When receiving a status monitoring instruction for a target task job sent through an interactive page, calling a corresponding target supercomputing scheduling system monitoring script according to the supercomputing scheduling system type in the status monitoring instruction, so as to select and start a corresponding task monitoring thread according to the target supercomputing scheduling system monitoring script; Obtaining target task operation status information of the corresponding CFD software fed back after executing the task monitoring thread, and identifying and processing the target task operation status information to obtain the operation status information to be displayed; The job status information to be displayed is sent to the interactive page so as to display the job running status of the CFD software.

2. The method for monitoring heterogeneous job status of CFD software for remote supercomputer according to claim 1, characterized in that: The calling of the corresponding target supercomputer scheduling system monitoring script by the supercomputer scheduling system type in the status monitoring instruction, so as to select and start the corresponding task monitoring thread according to the target supercomputer scheduling system monitoring script, includes: Monitor the monitoring queue according to a preset polling time interval, and determine whether there is a task job to be monitored in the monitoring queue; wherein the task job to be monitored is a CFD calculation job submitted to the supercomputing environment; If the task to be monitored does not exist, the monitoring action is stopped to release the current memory resources; If the task job to be monitored exists, the corresponding target supercomputing scheduling system monitoring script is called through the supercomputing scheduling system type in the status monitoring instruction, so as to select and start the corresponding task monitoring thread according to the target supercomputing scheduling system monitoring script.

3. The method for monitoring heterogeneous operation status of CFD software for remote supercomputer according to claim 2 is characterized in that: The identifying and processing the target task operation status information to obtain the operation status information to be displayed includes: Determine whether the target task operation status information is empty status information; If the target task job status information is empty status information, the job status of the target task job is marked as stopped to obtain the job status information to be displayed, and the task job to be monitored representing the target task job in the monitoring queue is removed; If the target task operation status information is non-empty status information, determining whether the target task operation status information satisfies a completed status condition; If the completed status condition is met, the job status of the target task job is marked as completed to obtain job status information to be displayed.

4. The method for monitoring heterogeneous operation status of CFD software for remote supercomputing according to claim 3 is characterized in that: After determining whether the target task operation status information satisfies the completed status condition, the method further includes: If the completed status condition is not met, determining whether the target task job status information meets the status conditions of the queuing status and / or the running status; If the target task job status information satisfies the status conditions of the queuing status and / or the running status, it is determined whether the target task job status information is updated from the previous queuing status to the current running status to obtain a corresponding determination result.

5. The method for monitoring heterogeneous operation status of CFD software for remote supercomputer according to claim 4 is characterized in that: After determining whether the target task job status information is updated from the previous queuing status to the current running status to obtain the corresponding determination result, the method further includes: If the judgment result is that the target task job status information has not been updated from the previous state to the current state, then the job status of the target task job is marked as a queue state and / or a running state to obtain the job status information to be displayed; If the judgment result is that the target task operation status information is updated from the previous queuing status to the current running status, then checking whether the network connection between the personal computer and the preset monitoring system is disconnected; If the network connection is disconnected, removing the target task job from the monitoring queue; If the network connection is not disconnected, the job status of the target task job is updated to a running status to obtain job status information to be displayed.

6. The method for monitoring heterogeneous operation status of CFD software for remote supercomputer according to claim 2, characterized in that: Before monitoring the monitoring queue according to the preset polling time interval and determining whether there is a task to be monitored in the monitoring queue, the method further includes: Starts the listener and loads a preset configuration file to get a preset polling interval.

7. The method for monitoring heterogeneous operation status of CFD software for remote supercomputer according to any one of claims 1 to 6, characterized in that: Before receiving the status monitoring instruction for the target task operation sent through the interactive page, the method further includes: The interactive page is placed on the personal computer, and the CFD software and preset monitoring system are placed on the supercomputing environment.

8. A CFD software heterogeneous operation status monitoring device for remote supercomputers, characterized in that: Applied to a preset monitoring system, the preset monitoring system has several different types of supercomputing scheduling system monitoring scripts built in, and the device includes: A thread selection module, for, when receiving a status monitoring instruction for a target task job sent through an interactive page, calling a corresponding target supercomputing scheduling system monitoring script according to the supercomputing scheduling system type in the status monitoring instruction, so as to select and start a corresponding task monitoring thread according to the target supercomputing scheduling system monitoring script; An information monitoring module is used to obtain the target task operation status information of the corresponding CFD software fed back after executing the task monitoring thread, and identify and process the target task operation status information to obtain the operation status information to be displayed; The information display module is used to send the job status information to be displayed to the interactive page so as to display the job running status of the CFD software.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of the method for monitoring the heterogeneous job status of CFD software for remote supercomputing as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, the steps of the method for monitoring the heterogeneous job status of CFD software for remote supercomputing are implemented as described in any one of claims 1 to 7.

Images