Production line server cluster

Abstract

The invention discloses a production line server cluster which comprises a plurality of server units, any server unit comprises a service module, a monitoring module and a storage module, and the service module collects production line data, specifies the stored server unit and sends tasks to a shared task list; the monitoring module monitors the performance of the server unit, sends the performance to the shared performance list and receives the performance of all other server units at the same time; the storage module stores equipment data corresponding to the unit and also stores production line task data; and when the performance of any server unit is surplus, the monitoring module obtains the task from the shared task list, delivers the task to the service module for processing and sends a broadcast allocated to the task, and after the task is completed, the service module for processing the task transfers task data to the storage module of the specified server unit for data storage. Server performance is fully utilized, the error-tolerant rate is improved, and the purposes of reducing cost and increasing efficiency are achieved.

Description

Technical Field

[0001] The present invention belongs to the field of SMT technology, and specifically relates to a production line server cluster. Background Art

[0002] With the rapid development of computer, storage and Internet technologies, the scale of business traffic and the complexity of business logic are also developing. In order to adapt to the increasing business traffic and increasingly complex and diverse business logic, it is often necessary to use clusters to achieve performance expansion and avoid single point failures.

[0003] The server cluster used by the company's existing workshop production lines uses one server for each production line. The applicant found that the problems with this production line server configuration are server performance redundancy and low fault tolerance. Especially when there are a large number of SMT devices on the production line, since the production line server needs to store the data of all the equipment on the production line and also store the production line business or task data, the amount of data stored in the server is large and the pressure is very high. In addition, the large amount of data stored and calculated will cause processing delays. If the server goes down, it will also delay production. In order to solve the above technical problems, the present invention is derived from this. Summary of the invention

[0004] In view of at least one of the above-mentioned technical problems, an object of the present invention is to provide a production line server cluster.

[0005] The technical solution of the present invention is: The object of the present invention is to provide a production line server cluster, comprising multiple server units, any of which includes a business module, a monitoring module and a storage module, the business module collects production line data and specifies the server unit for storage, and sends tasks to a shared task list; the monitoring module monitors the performance of this unit and sends it to a shared performance list, and simultaneously receives the performance of all other server units; the storage module is used to store the equipment data of the equipment corresponding to this unit, and also stores task data; when the performance of any of the server units is surplus, the monitoring module of the server unit obtains the task from the shared task list and hands it over to its business module for task processing and sends a broadcast of the assigned task to all other server units, and after the task is completed, the business module that processes the task transfers the task data to the storage module of the server unit specified by the task for data preservation.

[0006] Preferably, the designated storage server unit is a server unit of the same production line.

[0007] Preferably, among the server units with surplus performance, when any server unit with surplus performance receives a broadcast of task allocation sent by other server units with surplus performance, it is necessary to compare the broadcast time sent by itself to other server units with the broadcast time of task allocation sent by the server unit with surplus performance received at the first time; If the time is later, the service module of the server unit does not start task processing and deletes the task from the shared task list, and does not process it again when receiving a broadcast from other server units indicating that the task has been assigned; If the time is earlier, the server unit continues to wait according to the set timeout threshold, waiting for a broadcast of task allocation sent by other server units.

[0008] Preferably, in the step where the comparison result shows that the time is earlier and the server unit continues to wait according to the set timeout threshold, if the waiting times out, the business module of the server unit deletes the task from the shared task list and starts processing the task.

[0009] Preferably, if after waiting for a timeout, a broadcast that a task has been assigned is received from the server unit at a second time, and the second time is greater than the first time, it is necessary to determine whether the task has a pause point; If the task has no pause point, the server unit continues to process the task; If the task has a pause point, the server unit will inform the server unit corresponding to the broadcast that received the task assigned at the second time at the pause point that the task has started to be processed, and after the server unit corresponding to the broadcast that received the task assigned at the second time gives feedback on the progress of task processing, it will compare the progress of its task processing with the task processing progress of the server unit corresponding to the broadcast that received the task assigned at the second time.

[0010] Preferably, if the task processing progress of the server unit is to be faster, the task processing continues and is completed; If the task processing progress of the server unit is slower than the task processing progress of the server unit corresponding to the broadcast that the server unit receives the task assigned at the second time, or the two are the same and the server unit corresponding to the broadcast that the server unit receives the task assigned at the second time feeds back the task processing progress earlier, the server unit interrupts the task processing.

[0011] Preferably, when the designated storage server unit receives a storage notification of task processing completion, if the task data has not been stored, the storage unit of the designated storage server unit stores the task data; if the task data has been stored, no processing is required.

[0012] Preferably, the time interval between the monitoring module of any server unit performing its own performance monitoring and receiving performance monitoring of other server units is shorter than the time interval between the monitoring module obtaining a task from a shared task list and handing it over to its business module for task processing and sending a broadcast of the assigned task to all other server units.

[0013] Compared with the prior art, the advantages of the present invention are: The production line server cluster of the present invention corresponds the server cluster to the production line equipment, instead of the server unit corresponding to the production line in the prior art. Each production line corresponds to multiple server units, which can realize that one server unit corresponds to one device or multiple devices in one production line. Each server unit includes three modules: business module, monitoring module and storage module. The business module collects production line data and specifies the production tasks of the server unit and shares them with all other server units. The server unit processes the task when its performance is sufficient according to the performance status monitored by its monitoring module and stores the task data to the specified server unit after the task is processed, so as to make full use of the server performance, improve the fault tolerance rate, and achieve the purpose of reducing costs and increasing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention will be further described below in conjunction with the accompanying drawings and embodiments: Figure 1 A schematic diagram of the configuration of a production line server cluster according to an embodiment of the present invention; Figure 2 A schematic diagram of the system framework of a server unit of a production line server cluster according to an embodiment of the present invention; Figure 3 It is a structural diagram of the automatic grouping of server units and equipment of the production line server cluster according to an embodiment of the present invention; Figure 4 This is a functional schematic diagram of a monitoring module of a production line server cluster according to an embodiment of the present invention; Figure 5 It is a functional schematic diagram of a storage module of a production line server cluster according to an embodiment of the present invention.

[0015] Among them: 100, server cluster; 10, server unit; 11, business module; 12, monitoring module; 13, storage module; 200, equipment. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0017] See also Figures 1 to 5 The production line server cluster 100 provided in the embodiment of the present invention specifically includes a plurality of server units 10 (each server unit 10 is a small or mini server), and each server unit 10 includes three major functional modules, namely, a business module 11, a monitoring module 12, and a storage module 13. In the embodiment of the present invention, the server unit 10 and the production line equipment 200 are connected via a network. The purpose of the server cluster 100 in the embodiment of the present invention is to enable each server unit 10 to correspond to each equipment 200 or each server unit 10 to be connected to multiple server units 10 of a production line. This is essentially different from the storage method of connecting one server unit 10 to each production line in the prior art. More specifically, the business module 11 of any server unit 10 in the embodiment of the present invention is responsible for collecting production line data and specifying the server unit 10 to store according to the storage mapping relationship, and generating tasks and sending them to the shared task list, so that other server units 10 in the server cluster 100 can obtain tasks from the shared task list for task processing when their performance is sufficient, thereby making full use of server performance. The monitoring module 12 performs two aspects of monitoring. On the one hand, it monitors its own performance and sends the performance to the shared performance list; on the other hand, it receives the performance of other server units 10 from the shared performance list sent by other server units 10. It should be noted that the performance of the server unit 10 in the embodiment of the present invention includes memory and CPU. The storage module 13 is used to store the device 200 data (including the device 200 address, device 200 name, production line name, production line location, etc.) of the device 200 connected to this unit, and also stores the production line task data. More specifically, during the operation of the production line server cluster 100 in the embodiment of the present invention, when the performance of any server unit 10 is surplus, the monitoring module 12 of the server unit 10 obtains the task from the shared task list and hands it over to its own business module 11 for task processing and sends the assigned task broadcast to other server units 10, and after the task processing is completed, the business module 11 of the server unit 10 that processes the task transfers the task data to the storage module 13 of the aforementioned designated server unit 10 to store the task data.

[0018] More specifically, Figure 3As shown, in a preferred embodiment of the present invention, for example, the server cluster 100 is in a local area network (for the convenience of description and distinction, this local area network is described as local area network 2), and the production line equipment 200 is in another local area network (for the convenience of description and distinction, this local area network is described as local area network 1), and the network segment 2 of the local area network 2 is defined as, for example, 192.168.20.XXX (XXX is any one of 1-255), and the network segment 1 of the local area network 1 is defined as 192.168.10.XXX (XXX is any one of 1-255). The local area network 1 and the local area network 2 are connected to each other, and when accessing any server unit 10, click to realize the network connection between the server unit 10 and the device 200. More specifically, in the embodiment of the present invention, two production lines, four devices 200, and four server units 10 are used as examples for explanation. The four IP addresses of network segment 1 are 192.168.10.1, 192.168.10.2, 192.168.10.3, and 192.168.10.4, respectively. That is to say, the IP addresses of the four server units 10 are 192.168.10.1, 192.1 68.10.2, 192.168.10.3, 192.168.10.4, the four IP addresses of network segment 2 are 192.168.20.1, 192.168.20.2, 192.168.20.3, 192.168.20.4, and the corresponding information of four devices 200 (consisting of device 200 name, production line name and device 200 location) are 192.168.20.1 Line1 NPM1 1, 192.168.20.2 Line1 NPM2 2, 192.168.20.3 Line2 NPM1 1, 192.168.20.4 Line2 NPM2 2. When grouping the line, when accessing any server unit 10 through a browser or a production information management system (MES), click on the page to automatically group the line. The specific steps are as follows: Figure 3As shown, firstly, all network segments accessible to the server unit 10 and all active IPs under the network segments are automatically obtained. Then, the fixed interface is used to automatically identify whether the IP belongs to the device 200, the server unit 10, or others (i.e., it does not belong to the device 200 or the server unit 10). Finally, the lines are automatically grouped according to the production line name and the location of the device 200. For example, the server unit 192.168.10.1 and the device 192.168.20.4 Line2 NPM2 2 are networked and grouped, the server unit 192.168.10.2 and the device 192.168.20.3 Line2 NPM1 1 are networked and grouped, the server unit 192.168.10.3 and the device 192.168.20.2 Line1 NPM2 2 are networked and grouped, and the server unit 192.168.10.4 and the device 192.168.20.1 Line1 NPM1 1 are networked and grouped. As an alternative embodiment, the server unit 10 in the embodiment of the present invention may also be connected to multiple devices 200 of the same production line.

[0019] For the monitoring module 12, if Figure 4 As shown, the monitoring module 12 of any server unit 10 performs two tasks, one is to perform performance monitoring, and the other is to perform task allocation. Performance monitoring includes two aspects, one is to regularly monitor the performance of itself, that is, the server unit 10, and the other is to receive the performance of all other server units 10. As for task allocation, first add or generate tasks according to the server unit 10 specified by the data storage, and send task broadcasts at the same time, receive task broadcasts sent by other server units 10, and update the task list in time. When the monitoring module 12 of any server unit 10 monitors that its own performance is idle, it obtains tasks from the task management list, that is, the set of task lists shared by all server units 10, and specifies this server unit 10 as the server unit 10 for business processing. At the same time, it is also necessary to send task allocation broadcasts to other server units 10, and receive task allocation broadcasts sent by other server units 10, so as to facilitate subsequent comparison of which server unit 10 performs task processing. Specifically, the monitoring module 12 of the server unit 10 needs to compare the task allocation broadcast sent by the server unit 10, that is, whether the task allocation time is earlier than that of other server units 10. If yes, the business module 11 of the server unit 10 will process the task. Otherwise, the task will be cancelled.

[0020] For the storage module 13, Figure 5As shown, the main storage of the storage module 13 of the embodiment of the present invention is to write data, that is, to store the device 200 data of the corresponding device 200 (that is, the device 200 information mentioned above), and on the other hand, it is also designated to store production line task data by production line and time period. In addition, a small amount of workshop business data is also stored. The storage module 13 of the embodiment of the present invention is dynamic reading and writing. Writing data means writing the device data, production line task data and workshop data of the corresponding device 200. The process of reading data is that the monitoring module 12 of the server unit 10 first requests data from the storage module 13 of the server unit 10 and requests data from the storage module 13 of the designated storage server unit 10 according to the storage mapping relationship, and then the storage module 13 of the requested server unit 10 returns the data so that the monitoring module 12 of the requesting server unit 10 can add or generate tasks. The dynamic principle in the embodiment of the present invention is to sort all server units 10 first, and store the production line task data in different server units 10 in different time periods. If the server unit 10 of the current time period is found, the task data is assigned to the same server unit 10; otherwise, the server unit 10 of the latest time period is found, and the business data of the current time period is assigned to the next server unit 10 for storage. However, it should be noted that if it is used for the first time or the server unit 10 of the latest time period is the last server unit 10 in the sorting, the first server unit 10 is designated as the designated storage server unit 10.

[0021] Preferably, the server unit 10 designated for storage in the embodiment of the present invention and the designated server unit 10 are server units 10 of the same production line. For example, as mentioned above, when the server unit 10 that collects production line data, i.e., the designated server unit 10, is server unit 192.168.10.1 connected to the device NPM2 of production line 2, the server unit 10 designated for storage is server unit 192.168.10.2 connected to the device NPM1 of production line 2. The purpose of this setting is that there may be differences in the operation of different production lines. In order to avoid the possibility that the data may not be queried, the task data is stored in the storage module 13 of the server unit 10 of the same production line.

[0022] Preferably, among the server units 10 with surplus performance (because there may be multiple server units 10 with surplus performance in the same time period), when any server unit 10 with surplus performance receives a broadcast of task allocation sent by other server units 10 with surplus performance, it is necessary to compare the broadcast time it sends to other server units 10 with the broadcast time of task allocation sent by the server unit 10 with surplus performance received at the first time. If the time is later, the business module 11 of the server unit 10 does not start task processing and deletes the task from its own shared task list, and no longer processes it when receiving a broadcast of task allocation sent by other server units 10. If the time is earlier, the server unit 10 continues to wait according to the set timeout threshold (not specifically limited, the purpose of setting this waiting timeout threshold is to improve the fault tolerance rate), waiting for whether there is a broadcast of task allocation sent by other server units 10. More preferably, when the comparison result is an earlier time, the server unit 10 continues to wait according to the set timeout threshold. If the waiting times out, the business module 11 of the server unit 10 deletes the task from its own shared task list and starts the task processing.

[0023] Since multiple server units 10 may be in a state of surplus performance in the same time period, these server units 10 will all receive tasks and send broadcasts to other server units 10 to indicate that the tasks have been assigned. For the sake of ease of description and distinction, in the embodiment of the present invention, the time when a certain server unit 10 receives a broadcast is described as the first time, the second time, ..., the N-1th time in the order of the time when the broadcast is received, where N is the number of server units 10, and the first time is the smallest or earliest. That is, the time when a certain server unit 10 first receives a broadcast is the first time, followed by the second time, the third time, and so on. That is, the second time is greater than the first time, the third time is greater than the second time, and so on. In an embodiment of the present invention, if a server unit 10 receives a broadcast at a first time and waits for a timeout threshold and then receives a broadcast of a task being assigned from another server unit 10 (which is not the same server unit 10 as the server unit 10 corresponding to the broadcast received at the first time) at a second time, the following operations need to be performed: For ease of description and distinction and understanding, the server unit 10 that receives the broadcast from other server units 10 is described as the first server unit 10, the server unit 10 corresponding to the broadcast received by the first server unit 10 at the first time, that is, the server unit 10 that sends the broadcast to the first server unit 10 at the first time, is described as the second server unit 10, the server unit 10 corresponding to the broadcast received by the first server unit 10 at the second time is described as the third server unit 10, and so on. The specific operation is as follows: determine whether the task being processed by the first server unit 10 has a pause point; if the task has no pause point, the first server unit 10 continues to process the task; if the task has a pause point, the first server unit 10 informs the server unit 10 corresponding to the broadcast that the task has been assigned at the second time, that is, the third server unit 10, at the pause point that the task has started to be processed. After the third server unit 10 receives the notification message sent by the first server unit 10, that is, the task processing progress feedback, the first server unit 10 compares the progress of its task processing with the progress of the task processing of the server unit 10 corresponding to the broadcast that the task has been assigned at the second time, that is, the third server unit 10. If the task processing progress of the first server unit 10 is faster, the first server unit 10 continues to process the task and completes the task processing. If the task processing progress of the first server unit 10 is slower than the task processing progress of the server unit 10 corresponding to the broadcast that the task has been assigned at the second time, that is, the third server unit 10, or if the progress of the two is the same but the third server unit 10 feedbacks the task processing progress earlier, the first server unit 10 needs to interrupt the processing of the task. Further processing of the task is then performed by the third server unit 10 .

[0024] Preferably, the time interval between the monitoring module 12 of any server unit 10 monitoring its own performance and receiving the performance monitoring of other server units 10 is shorter than the time interval between the monitoring module 12 acquiring a task from the shared task list and handing it over to its business module 11 for task processing and sending a broadcast indicating that the task has been assigned to all other server units 10. The purpose of such a setting is to ensure that the performance margin viewed is the latest when tasks are distributed.

[0025] In order to more clearly understand the working principle of the server cluster 100 of the embodiment of the present invention, a more specific embodiment is as follows. In the following embodiment, two production lines (production line 1 and production line 2), four devices (two devices 200 for each production line, for example, production line 1 device 1, production line 1 device 2, production line 2 device 1 and production line 2 device 2) and four server units 10 (server unit 1-1, server unit 1-2, server unit 2-1 and server unit 2-2) are used as examples for description: The business module 11 of the server unit 1-1 collects the equipment data of the equipment 1 of the production line 1; the business module 11 of the server unit 1-2 collects the data of the equipment 2 of the production line 1; the server unit 2-1 collects the data of the equipment 1 of the production line 2; and the server unit 2-2 collects the data of the equipment 2 of the production line 2. More specifically, After collecting the data of production line 1 equipment 1, the business module 11 of server unit 1-1 designates the server unit 1-2 corresponding to the same production line, i.e., production line 1 equipment 2, as the server unit 10 for storing task data according to the storage mapping relationship, and generates a task (the earliest task is taken as an example in the embodiment of the present invention, so this task is defined as task A) and shares it with the other three server units 10, i.e., server unit 1-2, server unit 2-1 and server unit 2-2.

[0026] If the monitoring modules 12 of server unit 1-2, server unit 2-1, and server unit 2-2 each find that their own performance is surplus (that is, lower than their own performance threshold), they obtain tasks from the shared task list (here taking the earliest task, that is, task A mentioned above, as an example), and broadcast that task A has been allocated to all other server units 10, that is, server unit 1-1, server unit 2-1, and server unit 2-2.

[0027] After server unit 1-1 receives the task assigned broadcast sent by server unit 2-1, it needs to compare its own task assigned time with the task assigned broadcast time sent by server unit 2-1. If the task assigned broadcast time sent by server unit 2-1 is earlier, the business module 11 of server unit 1-1 will not start processing task A. At the same time, server unit 1-1 will also delete task A from its own shared task list. Thereafter, if server unit 1-1 receives the task assigned broadcast sent by other server unit 10, that is, server unit 2-2, no processing is required.

[0028] After receiving the broadcast that the task has been assigned from server unit 1-1, server unit 1-2 deletes task A from its own shared task list. Meanwhile, after receiving the broadcast that the task has been assigned from server unit 2-1 and server unit 2-2, server unit 1-2 does not need to process any more.

[0029] After receiving the broadcast of task A assigned by server unit 1-1, if server unit 2-1 finds that its own assignment time is earlier, it will continue to wait according to the set timeout threshold to see if there is a broadcast of task assignment sent by other server units 10. If the waiting timeout does not receive the broadcast, task A will be deleted from the shared task list and the processing of task A will be started. After the waiting timeout, if the broadcast of task assignment sent by server unit 2-2 is received, if there is no pause point in task A, server unit 2-1 will continue the task processing and complete the task processing; otherwise, it will tell server unit 2-2 that task A has been processed at the pause point, and make a judgment after receiving feedback from server unit 2-2. Specifically, if server unit 2-2 processes task A faster, or the processing progress is the same, but feedback is given earlier, server unit 2-1 will interrupt the processing of task A; otherwise, the processing of task A is completed. After the processing of task A is completed, the data of task A is stored in the designated unit, that is, sent to server unit 1-2 for data storage.

[0030] Similarly, after receiving the broadcast of the task being assigned from server unit 1-1, if server unit 2-2 finds that its own assignment time is earlier, it will continue to wait according to the set timeout threshold to see if there is a broadcast of the task being assigned sent by other server units 10. If the broadcast is not received after the waiting timeout, task A will be deleted from the shared task list and the processing of task A will be started. After the waiting timeout, if the broadcast of the task being assigned sent by server unit 2-1 is received, if there is no pause point for task A, server unit 2-2 will continue the task processing and complete the task processing; otherwise, it will tell server unit 2-1 that it has started processing task A at the pause point, and make a judgment after receiving feedback from server unit 2-1. Specifically, if server unit 2-1 processes task A faster, or the processing progress is the same, but feedback is given earlier, server unit 2-2 will interrupt the processing of task A; otherwise, the processing of task A is completed. After the processing of task A is completed, the data of task A is stored in the designated unit, that is, sent to server unit 1-2 for data storage.

[0031] After receiving the data storage notification of task A sent by server unit 2-1, server unit 1-2 will automatically start data storage processing if it finds that there is no stored data of task A. Thereafter, if it receives the data storage notification of task A sent by server unit 2-2 again, it is not necessary to perform data storage of task A. In other words, storage module 13 only stores the earliest data of a task.

[0032] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.

Claims

1. Production line server cluster, characterized by: It comprises a plurality of server units, each of which comprises a business module, a monitoring module and a storage module. The business module collects production line data and specifies a server unit for storage, and sends tasks to a shared task list; the monitoring module monitors the performance of the unit and sends it to a shared performance list, and simultaneously receives the performance of all other server units; the storage module is used to store the equipment data of the equipment corresponding to the unit, and also stores task data; when the performance of any of the server units is surplus, the monitoring module of the server unit obtains the task from the shared task list and hands it over to its business module for task processing and sends a broadcast of the assigned task to all other server units, and after the task is completed, the business module that processes the task transfers the task data to the storage module of the server unit specified by the task for data preservation.

2. The production line server cluster according to claim 1, characterized in that: The server units designated for storage are server units of the same production line.

3. The production line server cluster according to claim 1, characterized in that: When any server unit with surplus performance receives a broadcast of task allocation sent by other server units with surplus performance, it is necessary to compare the broadcast time sent by itself to other server units with the broadcast time of task allocation sent by the server unit with surplus performance received at the first time; If the time is later, the service module of the server unit does not start task processing and deletes the task from the shared task list, and does not process it again when receiving a broadcast from other server units indicating that the task has been assigned; If the time is earlier, the server unit continues to wait according to the set timeout threshold, waiting for a broadcast of task allocation sent by other server units.

4. The production line server cluster according to claim 3, characterized in that: In the step where the comparison result shows that the time is earlier, the server unit continues to wait according to the set timeout threshold. If the waiting times out, the business module of the server unit deletes the task from the shared task list and starts processing the task.

5. The production line server cluster according to claim 4, characterized in that: If after waiting for a timeout, a broadcast that a task has been assigned is received from the server unit at a second time, and the second time is greater than the first time, it is necessary to determine whether the task has a pause point; If the task has no pause point, the server unit continues to process the task; If the task has a pause point, the server unit will inform the server unit corresponding to the broadcast that received the task assigned at the second time at the pause point that the task has started to be processed, and after the server unit corresponding to the broadcast that received the task assigned at the second time gives feedback on the progress of task processing, it will compare the progress of its task processing with the task processing progress of the server unit corresponding to the broadcast that received the task assigned at the second time.

6. The production line server cluster according to claim 5, characterized in that: If the task processing progress of the server unit is faster, the task will continue to be processed and completed; If the task processing progress of the server unit is slower than the task processing progress of the server unit corresponding to the broadcast that the server unit receives the task assigned at the second time, or the two are the same and the server unit corresponding to the broadcast that the server unit receives the task assigned at the second time feeds back the task processing progress earlier, the server unit interrupts the task processing.

7. The production line server cluster according to claim 1, characterized in that: When the designated storage server unit receives the storage notification of task processing completion, if the task data has not been stored, the storage unit of the designated storage server unit stores the task data; if the task data has been stored, no processing is required.

8. The production line server cluster according to claim 1, characterized in that: The time interval between the monitoring module of any server unit monitoring its own performance and receiving performance monitoring of other server units is shorter than the time interval between the monitoring module obtaining a task from a shared task list and handing it over to its business module for task processing and sending a broadcast of the assigned task to all other server units.

Images