Method and system for realizing unified computing resource management

Abstract

The invention provides a method and a system for realizing unified computing resource management. The system comprises a resource control starter (RCL), a resource controller (RCA), a Web task controller (WJCA), a resource controller (RCA), a Web offline Actor (WSA), a Web cross-domain Actor (WCDA), a job execution Actor (JERA) and a resource theme release (RRT). The resource control starter starts the resource controller to receive the resource pool configuration file and the task resource information, send the task resource information and distribute and release the task resource information; the Web task controller communicates with the resource controller and receives task resource information; the Web offline Actor receives task resource information in an offline state; the Web cross-domain Actor receives task resource information in a cross-domain state; the job execution Actor executes the task resource information in the online state; and releasing the resource theme and sending a task resource request to the resource controller. According to the method, resources are dynamically applied and released according to demands, the cluster computing resource utilization rate is improved, the maintenance cost is reduced, no resources are available when tasks are executed, and timeliness is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of resource management and computer application, and in particular to a method and system for realizing unified computing resource management. Background Art

[0002] With the rapid development of cloud computing, big data technology and artificial intelligence, unified computing resource management has become increasingly important. In order to improve resource utilization efficiency, the industry has begun to use dynamic resource management technology to dynamically apply for resources based on task size and recycle resources that complete tasks ahead of schedule, thereby reducing the waste of computing resources and improving resource utilization efficiency.

[0003] In general, unified computing resource dynamic management technology is in a stage of rapid development. In the future, with the further development of technology and in-depth application, unified computing resource dynamic management will become more intelligent and automated, providing solid technical support for the high-quality development of the digital economy.

[0004] Although the unified computing resource dynamic management technology has made some remarkable progress in the development process, there are still some shortcomings or disadvantages.

[0005] First, in a distributed system, computing resources may be unevenly distributed between different nodes due to improper task allocation strategies or long connections, causing some nodes to be overloaded while other nodes are lightly loaded, thus affecting computing performance.

[0006] Secondly, as business needs grow, existing computing resources may not be able to meet the demand, resulting in insufficient CPU and memory resources, affecting task execution and system response speed.

[0007] Furthermore, computing tasks may be abnormally interrupted during execution due to various reasons, resulting in task failure. It is necessary to use fault-tolerant strategies such as detection points and recovery mechanisms or automatic retries to solve the problem of resource occupation and non-release.

[0008] In addition, some tasks take too long to execute or are blocked, resulting in task backlogs. These tasks occupy a large amount of computing resources for a long time, which may cause other urgent tasks to have no resources available.

[0009] Finally, although unified dynamic management of computing resources can improve resource utilization, in practice, resource utilization may not be completely balanced, which has an adverse impact on the overall computing performance and may waste some resources.

[0010] In order to solve the above problems, the present invention proposes a method and system for realizing unified computing resource management. Summary of the invention

[0011] The present invention proposes the following technical solutions to address one or more technical deficiencies in the above-mentioned prior art.

[0012] Based on the first aspect of the present invention, a system for realizing unified computing resource management is proposed, comprising a resource control launcher (RCL), a resource controller (RCA), a Web initialization service (WIS), a Web task controller (WJCA), a resource controller (RCA), a Web offline actor (WSA), a Web cross-domain actor (WCDA), a job execution actor (JERA) and a release resource topic (RRT);

[0013] The resource control launcher (RCL) is used to launch the resource controller (RCA);

[0014] The Web Initialization Service (WIS) is used to start the Web Task Controller (WJCA);

[0015] The resource controller (RCA) is used to receive the resource pool configuration file (RPCF) and task resource information, send task resource information, and allocate and release task resource information;

[0016] The Web task controller (WJCA) is used to communicate with the resource controller (RCA) and receive task resource information sent by the resource controller (RCA);

[0017] The Web Offline Actor (WSA) is used to receive offline task resource information;

[0018] The Web cross-domain Actor (WCDA) is used to receive task resource information of cross-domain status;

[0019] The job execution actor (JERA) is used to execute the task resource information in the online state;

[0020] The Release Resource Topic (RRT) is used to send a task resource request to the Resource Controller (RCA).

[0021] Furthermore, when the resource controller (RCA) is started, it verifies and loads a resource pool configuration file (RPCF) containing distributed cluster resource information, and the distributed communication cluster manages the resource controller (RCA) into the distributed cluster for monitoring.

[0022] Furthermore, after the Web task controller (WJCA) is started, it sends the Web address to the resource controller (RCA), and the distributed communication cluster manages the Web task controller (WJCA) into the cluster and monitors it.

[0023] Based on the second aspect of the present invention, a method for implementing unified computing resource management according to the system described above is also proposed, comprising:

[0024] S1: Start the shell script and build a distributed communication cluster;

[0025] S2: In response to the resource controller (RCA) being started by the resource control launcher (RCL), the Web initialization service (WIS) starts the Web task controller (WJCA);

[0026] S3: In response to the job request task initiated by the third-party application, the distributed storage database returns the task resource information in the queue state to the resource controller (RCA) after receiving the job request task from the resource controller (RCA);

[0027] S4: The resource controller (RCA) comprehensively evaluates the returned task resource information, adds the job request task with the best evaluation result to the task cache and sends it to the Web task controller (WJCA), and removes the resources of the job request task from the resource pool;

[0028] S5: The Web Task Controller (WJCA) processes the task resource information of the job request task according to the task type. Specifically, if the task type is an offline task or a cross-domain task, the Web Offline Actor (WSA) or the Web Cross-Domain Actor (WCDA) is started, and the Job Execution Actor (JERA) is started at the same time to receive the task resource information; if the task type is an online task, the task resource information is sent to the Job Execution Actor (JERA) to execute the job;

[0029] S6: The job execution Actor (JERA) executes the task job and stores the result in the distributed storage database. The resource release topic (RRT) responds to the written task ID and sends the resource release request of the task ID to the resource release topic (RRT) to release the task resources.

[0030] Furthermore, the task resource information includes task information of a specific job request task and resource information for executing the job request task.

[0031] Furthermore, the task resource information is comprehensively evaluated through four dimensions: task level, task receiving time, task resource information and task type;

[0032] The task levels include the most urgent S-level tasks, urgent A-level tasks, ordinary B-level tasks and general C-level tasks, and the priority scheduling level decreases in descending order;

[0033] The task types include online tasks, offline tasks and cross-domain tasks.

[0034] The task resource information is comprehensively evaluated through four dimensions: task level, task receipt time, task resource information and task type, avoiding the dilemma of no resources available when important tasks are executed and ensuring the timeliness of the execution of important tasks.

[0035] Furthermore, after receiving the notification of confirmation of receipt sent by the Web task controller (WJCA), the resource controller (RCA) clears the job request task in the task cache.

[0036] Furthermore, if the job execution Actor (JERA) fails to start, the task ID of the failed start is written into the release resource topic (RRT), and the resource request occupied by the failed job request task is returned to the resource controller (RCA) for release.

[0037] Furthermore, if an exception occurs during the execution of a job, the corresponding exception handling method is called and the exception information is stored in the distributed storage database.

[0038] Based on the third aspect of the present invention, a computer program product is further proposed, on which one or more computer programs are stored, and when the computer program is executed by a computer processor, the computer program implements any of the methods described above.

[0039] The technical effect of the present invention is that: by allowing jobs to dynamically apply for and release resources according to demand, the present invention improves the utilization rate of cluster computing resources, effectively reduces system maintenance costs, improves the efficiency and quality of unified resource management, formulates a task classification strategy for executing jobs, and conducts a comprehensive evaluation to select the job with the best evaluation result for execution, avoiding the dilemma of no resources available when executing important tasks, and ensuring the timeliness of the execution of important jobs. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Other features, objects and advantages of the present application will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings.

[0041] Figure 1 It is a flow chart of a method for implementing unified computing resource management provided according to an embodiment of the present invention.

[0042] Figure 2 It is an overall architecture diagram of a system for implementing unified computing resource management provided according to an embodiment of the present invention.

[0043] Figure 3A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application. DETAILED DESCRIPTION

[0044] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It should also be noted that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0045] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0046] Figure 1 A flow chart of a method for implementing unified computing resource management provided by an embodiment of the present invention is shown, including:

[0047] S1: Start the shell script and build a distributed communication cluster;

[0048] S2: In response to the resource controller (RCA) being started by the resource control launcher (RCL), the Web initialization service (WIS) starts the Web task controller (WJCA);

[0049] S3: In response to the job request task initiated by the third-party application, the distributed storage database returns the task resource information in the queue state to the resource controller (RCA) after receiving the job request task from the resource controller (RCA);

[0050] S4: The resource controller (RCA) comprehensively evaluates the returned task resource information, adds the job request task with the best evaluation result to the task cache and sends it to the Web task controller (WJCA), and removes the resources of the job request task from the resource pool;

[0051] S5: The Web Task Controller (WJCA) processes the task resource information of the job request task according to the task type. Specifically, if the task type is an offline task or a cross-domain task, the Web Offline Actor (WSA) or the Web Cross-Domain Actor (WCDA) is started, and the Job Execution Actor (JERA) is started at the same time to receive the task resource information; if the task type is an online task, the task resource information is sent to the Job Execution Actor (JERA) to execute the job;

[0052] S6: The job execution Actor (JERA) executes the task job and stores the result in the distributed storage database. The resource release topic (RRT) responds to the written task ID and sends the resource release request of the task ID to the resource release topic (RRT) to release the task resources.

[0053] It should be noted that when the resource controller (RCA) is started, the resource pool configuration file (RPCF) containing the distributed cluster resource information is verified and loaded, and the distributed communication cluster manages the resource controller (RCA) into the distributed cluster for monitoring.

[0054] It should be noted that after the Web task controller (WJCA) is started, it sends the Web address to the resource controller (RCA), and the distributed communication cluster manages the Web task controller (WJCA) into the cluster and monitors it.

[0055] It should be noted that the task resource information includes task information of a specific job request task and resource information for executing the job request task.

[0056] It should be noted that the task resource information is comprehensively evaluated through four dimensions: task level, task receiving time, task resource information and task type;

[0057] The task levels include the most urgent S-level tasks, urgent A-level tasks, ordinary B-level tasks and general C-level tasks, and the priority scheduling level decreases in descending order;

[0058] The task types include online tasks, offline tasks and cross-domain tasks.

[0059] It should be noted that, after receiving the notification of confirmation sent by the Web task controller (WJCA), the resource controller (RCA) clears the job request task from the task cache.

[0060] It should be noted that if the job execution Actor (JERA) fails to start, the task ID of the failed start is written in the release resource topic (RRT), and the resource request occupied by the failed job request task is returned to the resource controller (RCA) for release.

[0061] It should be noted that if an exception occurs during the execution of a job, the corresponding exception handling method is called and the exception information is stored in the distributed storage database.

[0062] It should be noted that the present application first divides the existing computing resources and plans a virtual resource pool, which includes multiple virtual queues. The maximum storage upper limit and the maximum CPU core upper limit are specified for each virtual queue. One or more of the virtual queues depend on a physical queue, but one virtual queue cannot correspond to multiple physical queues. At the same time, the total resources of multiple virtual queues corresponding to a physical queue cannot exceed the total resources of the actual physical queue.

[0063] It should be noted that when submitting a task, a virtual queue is specified, and the tasks in a virtual queue are sorted according to priority and resources are allocated in a FI FO manner. High-priority tasks will always be placed before low-priority tasks. Even if the high-priority task requires a lot of resources and the low-priority task requires very few resources, the low-priority task will not be scheduled first when the resource pool has sufficient resources. The low-priority task can only be executed after the high-priority task is executed.

[0064] It should be noted that the tasks in the virtual queue are sorted according to their priorities: S-level tasks, A-level tasks, B-level tasks and C-level tasks;

[0065] Among them, the S-level task represents the most urgent task and has the highest scheduling priority. When the resources of the designated queue are insufficient, it will apply for resources from other virtual queues. If the resources of all virtual queues are insufficient, the C-level task will be killed to release resources.

[0066] Class A tasks represent urgent tasks and have priority scheduling rights. When the resources of a specified virtual queue are insufficient, Class C tasks in the virtual queue are killed to release resources.

[0067] Class B tasks represent ordinary tasks. According to the normal capacity scheduling mode, the virtual queue corresponding to the task is specified and the resources are obtained through FIFO queuing;

[0068] Class C tasks represent general tasks. When the resource pool has sufficient resources, they are scheduled in the same way as Class B tasks. When resources are tight, they are killed by Class S or Class A tasks.

[0069] It should be noted that the present invention solves the problems of uneven resource allocation and insufficient resource capacity in distributed systems, improves computer performance, optimizes the speed of task execution, releases resources in a timely manner when tasks accumulate and occupy computing resources, gives priority to executing tasks with high priority, improves the utilization rate of computing resources, avoids resource waste, and makes resource utilization tend to be balanced.

[0070] Reference below Figure 2, which shows an overall architecture diagram of a system for implementing unified computing resource management, in which the method described above is implemented. The system for implementing unified computing resource management includes a resource control launcher (RCL), a resource controller (RCA), a Web task controller (WJCA), a resource controller (RCA), a Web offline Actor (WSA), a Web cross-domain Actor (WCDA), a job execution Actor (JERA) and a released resource topic (RRT).

[0071] In a specific embodiment, the resource control initiator (RCL) is used to initiate a resource controller (RCA).

[0072] In a specific embodiment, the resource controller (RCA) is used to receive a resource pool configuration file (RPCF) and task resource information, send task resource information, and allocate and release task resource information.

[0073] In a specific embodiment, the Web task controller (WJCA) is used to communicate with the resource controller (RCA) and receive task resource information sent by the resource controller (RCA).

[0074] In a specific embodiment, the Web Offline Actor (WSA) is used to receive offline task resource information.

[0075] In a specific embodiment, the Web cross-domain Actor (WCDA) is used to receive task resource information of a cross-domain state.

[0076] In a specific embodiment, the job execution actor (JERA) is used to execute online task resource information.

[0077] In a specific embodiment, the Release Resource Topic (RRT) is used to send a task resource request to the Resource Controller (RCA).

[0078] It should be noted that there are two main phases when executing tasks in this system;

[0079] The first stage is the preparation stage, which starts and builds a distributed communication cluster by calling a Shell script;

[0080] The second stage is the job execution stage, in which the initialization engine method and the job preprocessing method are called through the job execution Actor (JERA), and then the job is executed and cleaned up, and the execution results are stored in the distributed storage database;

[0081] At the same time, the successfully executed task ID is written into the released resource topic (RRT). If an exception occurs during the execution of the job by the job execution Actor (JERA), the corresponding exception handling method is called and the exception information is stored in the distributed storage database.

[0082] It should be noted that the core interaction steps in the system include:

[0083] Step 1: Start the resource controller (RCA) through the resource control launcher (RCL). After the resource controller (RCA) is started, it verifies and loads the resource pool configuration file (RPCF) containing the distributed cluster resource information. At the same time, the distributed communication cluster manages the resource controller (RCA) into the distributed cluster for monitoring;

[0084] Step 2: The Web Initialization Service (WIS) starts the Web Task Controller (WJCA), and after the Web Task Controller (WJCA) starts, it sends the Web address to the Resource Controller (RCA), and at the same time, the distributed communication cluster manages the Web Task Controller (WJCA) into the cluster and monitors it;

[0085] Step 3: The third-party application initiates a job request through the Web client;

[0086] The task resource information is stored in a distributed storage database, and the resource controller (RCA) obtains the task resource information from the distributed storage database at a regular interval. When receiving an acquisition request, the distributed storage database returns the task resource information in a queued state to the resource controller (RCA);

[0087] Step 4: After receiving the task resource information, the resource controller (RCA) comprehensively evaluates the task through four dimensions: task level, task receiving time, task resource information and task type, adds the job request task with the best evaluation result to the task cache and sends it to the Web task controller (WJCA), removes the resources of the job request task from the resource pool and sends the task resource information to the resource controller (RCA);

[0088] Step 5: After receiving the task resource information, the Web task controller (WJCA) notifies the resource controller (RCA) to confirm receipt of the task resource information, and the resource controller (RCA) clears the job request task in the task cache;

[0089] Step 6: The Web task controller (WJCA) determines the task resource information according to the task type;

[0090] If the task type is an offline task or a cross-domain task, the Web Offline Actor (WSA) or the Web Cross-Domain Actor (WCDA) is started, and at the same time, the Job Execution Actor (JERA) is started to receive the task resource information;

[0091] If the job execution Actor (JERA) is successfully started, the task resource information is returned to the job execution Actor (JERA); if the job execution Actor (JERA) fails to start, the task ID of the failed start is written in the release resource topic (RRT), the resource request occupied by the failed start job request task is returned to the resource controller (RCA) for release, and the task process is terminated;

[0092] If the task type is an online task, the task resource information is sent to the job execution Actor (JERA) to execute the job.

[0093] It should be noted that the task resource information includes task information of a specific job request task and resource information for executing the job request task.

[0094] It should be noted that in the actual modeling process, by using the unified computing resource dynamic management solution implemented by this method, the utilization rate of cluster computing resources is improved by allowing jobs to dynamically apply for and release resources according to demand, effectively reducing system maintenance costs, and achieving the effects of cost reduction, quality improvement, and efficiency improvement;

[0095] At the same time, a task classification strategy is formulated for execution jobs, and a comprehensive evaluation is conducted on the execution jobs from four dimensions: task level, task receipt time, task resource information, and task type. The job with the best corresponding evaluation result is then selected for execution. This avoids the dilemma of no resources available when executing important tasks and ensures the timeliness of the execution of important tasks.

[0096] Reference below Figure 3 , which shows a schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0097] like Figure 3As shown, the computer system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage part 308 into a random access memory (RAM) 303. Various programs and data required for system operation are also stored in the RAM 303. The CPU 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0098] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed, so that a computer program read therefrom is installed into the storage section 308 as needed.

[0099] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, the above functions defined in the method of the present application are executed. It should be noted that the computer-readable storage medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more conductors, 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 above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wireless, wireline, optical cable, RF, etc., or any suitable combination of the foregoing.

[0100] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0102] The modules involved in the embodiments of the present application may be implemented by software or by hardware.

[0103] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed by the electronic device, the electronic device: starts she ll script and build a distributed communication cluster; in response to the resource controller (RCA) started by the resource control launcher (RCL), the Web initialization service (WIS) starts the Web task controller (WJCA); in response to the job request task initiated by the third-party application, the distributed storage database returns the task resource information in the queue state to the resource controller (RCA) after receiving the job request task of the resource controller (RCA); the resource controller (RCA) comprehensively evaluates the returned task resource information, adds the job request task with the best corresponding evaluation result to the task cache and sends it to the Web task controller (WJCA), and removes the resources of the job request task in the resource pool; the Web task controller (WJCA) processes the task resource information of the job request task according to the task type; the job execution Actor (JERA) executes the task job and stores the result in the distributed storage database, and the release resource topic (RRT) responds to the written task ID, and sends the resource release request of the task ID to the release resource topic (RRT) to release the task resources.

[0104] Finally, it should be noted that the above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A system for implementing unified computing resource management, characterized in that: Includes Resource Control Launcher (RCL), Resource Controller (RCA), Web Initialization Service (WIS), Web Job Controller (WJCA), Resource Controller (RCA), Web Offline Actor (WSA), Web Cross-Domain Actor (WCDA), Job Execution Actor (JERA) and Release Resource Topic (RRT); The resource control launcher (RCL) is used to launch the resource controller (RCA); The Web Initialization Service (WIS) is used to start the Web Task Controller (WJCA); The resource controller (RCA) is used to receive the resource pool configuration file (RPCF) and task resource information, send task resource information, and allocate and release task resource information; The Web task controller (WJCA) is used to communicate with the resource controller (RCA) and receive task resource information sent by the resource controller (RCA); The Web Offline Actor (WSA) is used to receive offline task resource information; The Web cross-domain Actor (WCDA) is used to receive task resource information of cross-domain status; The job execution actor (JERA) is used to execute the task resource information in the online state; The Release Resource Topic (RRT) is used to send a task resource request to the Resource Controller (RCA).

2. The system according to claim 1, characterized in that When the resource controller (RCA) is started, it verifies and loads a resource pool configuration file (RPCF) containing distributed cluster resource information, and the distributed communication cluster manages the resource controller (RCA) into the distributed cluster for monitoring.

3. The system according to claim 1, characterized in that After the Web task controller (WJCA) is started, it sends the Web address to the resource controller (RCA), and the distributed communication cluster manages the Web task controller (WJCA) into the cluster and monitors it.

4. A method for implementing unified computing resource management according to the system of claim 1, characterized in that: include: S1: Start the shell script and build a distributed communication cluster; S2: In response to the resource controller (RCA) being started by the resource control launcher (RCL), the Web initialization service (WIS) starts the Web task controller (WJCA); S3: In response to the job request task initiated by the third-party application, the distributed storage database returns the task resource information in the queue state to the resource controller (RCA) after receiving the job request task from the resource controller (RCA); S4: The resource controller (RCA) comprehensively evaluates the returned task resource information, adds the job request task with the best evaluation result to the task cache and sends it to the Web task controller (WJCA), and removes the resources of the job request task from the resource pool; S5: The Web Task Controller (WJCA) processes the task resource information of the job request task according to the task type. Specifically, if the task type is an offline task or a cross-domain task, the Web Offline Actor (WSA) or the Web Cross-Domain Actor (WCDA) is started, and the Job Execution Actor (JERA) is started at the same time to receive the task resource information; if the task type is an online task, the task resource information is sent to the Job Execution Actor (JERA) to execute the job; S6: The job execution Actor (JERA) executes the task job and stores the result in the distributed storage database. The resource release topic (RRT) responds to the written task ID and sends the resource release request of the task ID to the resource release topic (RRT) to release the task resources.

5. The method according to claim 4, characterized in that The task resource information includes task information of a specific job request task and resource information for executing the job request task.

6. The method according to claim 4, characterized in that Comprehensively evaluate the task resource information through four dimensions: task level, task receiving time, task resource information and task type; The task levels include the most urgent S-level tasks, urgent A-level tasks, ordinary B-level tasks and general C-level tasks, and the priority scheduling level decreases in descending order; The task types include online tasks, offline tasks and cross-domain tasks.

7. The method according to claim 4, characterized in that After receiving the notification of confirmation sent by the Web task controller (WJCA), the resource controller (RCA) clears the job request task in the task cache.

8. The method according to claim 4, characterized in that: If the job execution Actor (JERA) fails to start, the task ID of the failed start is written into the resource release topic (RRT), and the resource request occupied by the failed job request task is returned to the resource controller (RCA) for release.

9. The method according to claim 4, characterized in that If an exception occurs during the execution of a job, the corresponding exception handling method is called and the exception information is stored in the distributed storage database.

10. A computer program product having one or more computer programs stored thereon, characterized in that: The computer program implements the method according to any one of claims 4 to 9 when executed by a computer processor.

Images