WO2023122891A1

WO2023122891A1 - Task scheduling method and multi-core processor system

Info

Publication number: WO2023122891A1
Application number: PCT/CN2021/141693
Authority: WO
Inventors: 段贵江; 吴成鼎
Original assignee: 宁德时代新能源科技股份有限公司
Priority date: 2021-12-27
Filing date: 2021-12-27
Publication date: 2023-07-06
Also published as: CN117751351A

Abstract

A task scheduling method, a multi-core processor system, and a computer-readable storage medium. The task scheduling method comprises: when a first task is in an execution abnormal state, determining whether the first task can be forcibly terminated; when the first task cannot be forcibly terminated, reporting, to a second task associated with the first task, that the first task is in the execution abnormal state; and when the duration in which the first task is in the execution abnormal state reaches a predetermined waiting time and a termination instruction for the first task has not been received, forcibly terminating the execution of the first task or stopping task scheduling performed on a processing core that executes the first task.

Description

Task scheduling method and multi-core processor system

technical field

The present application relates to the field of computer technology, in particular to a task scheduling method and a multi-core processor system.

Background technique

In the emerging field of vehicle controllers, especially domain controllers that meet the needs of autonomous driving, the use of Service-Oriented Architecture (SOA) has gradually become the mainstream understanding. With the continuous advancement of automobile intelligence, the functions that the on-board controller needs to handle are becoming more and more complex, and the scenarios are becoming more and more diverse. However, it is often difficult for a single developer to complete all application development independently. In addition, unlike mobile phone software, the control of vehicle-mounted systems is more complex. While loading various personalized application functions, security and real-time performance are becoming increasingly important.

For the on-board controller, it is necessary to introduce functions developed by third parties to create a digital ecosystem to meet consumers' diverse driving/riding scene experience, but also to ensure driving safety. Because, reasonable scheduling is required for a large number of tasks that need to be handled by the on-board controller.

Contents of the invention

In view of the above problems, the present application proposes a task scheduling method, a multi-core processor system, and a computer-readable storage medium.

For this reason, the first aspect of the present invention provides a kind of task scheduling method, and this task scheduling method comprises:

When the first task is in an abnormal execution state, judging whether the first task can be forcibly terminated;

When the first task cannot be forcibly terminated, report the execution exception status of the first task to a second task associated with the first task; and

When the duration of the first task in the execution abnormal state reaches the predetermined waiting time and the termination instruction of the first task is not received, the execution of the first task is forcibly terminated or the task scheduling for the processing core executing the first task is stopped. .

In the embodiment of this application, tasks have different priorities. When abnormal tasks occur, low-level tasks can be forcibly terminated immediately, middle-level tasks can be forcibly terminated after receiving instructions or delays, and high-level tasks cannot If it can be terminated forcibly, the task scheduling of the processing core executing the abnormal task is stopped. In the implementation plan of this application, according to the characteristics of the task itself, the abnormal task is terminated after a delay, neither the abnormal program will be forcibly terminated, nor will the abnormal program be left alone, which avoids further damage caused by the abnormal program expanding the scope of the fault, and avoids Abnormalities such as system crashes, flashbacks, restarts, and logic conflicts provide technical support for the system to enter a safe state.

In some embodiments of the present application, when the first task is in an execution abnormal state, the abnormal state of the first task is recorded. By recording abnormal tasks, it provides data assurance for problem analysis of third-party applications and whether new applications can be deployed.

In some embodiments of the present application, when the first task cannot be forcibly terminated, the abnormal state of the first task is sent to the system application, and the system application judges whether to execute the second task based on the abnormal state. A processing core of a task issues a termination command of the first task. In some embodiments, the system application includes a health management module.

In some embodiments, the execution exception state includes one or more of the following states: task execution timeout state, memory used by the task exceeds the limit, and stack used by the task exceeds the limit.

In some embodiments, the predetermined waiting time is determined based on the priority of the first task.

In some embodiments, the task scheduling method includes: when the first task can be forcibly terminated, forcibly terminating the first task.

In the embodiment of this application, when an abnormal task occurs, a choice is made between terminating the task and delaying the termination according to the characteristics of the task itself, which meets the requirements of high-safety scenarios such as automatic driving.

In some embodiments, the task scheduling method includes: when the first task that is forcibly terminated is the last task in the processing core executing the first task, assigning a new task to the processing core executing the first task .

In some embodiments, the task scheduling method includes: when the first task that is forcibly terminated is not the last task in the processing core executing the first task, ordering the processing core executing the first task to execute sequentially as The next task assigned.

In the embodiment of the present application, by terminating or delaying the termination of the abnormal task, the processing core executing the abnormal task is released, and the system crash is avoided.

In some embodiments, the task scheduling method is applicable to a multi-core processor system, and the multi-core processor system includes multiple processing cores.

In some embodiments, the task scheduling method is executed by a processing core in the plurality of processing cores, the task scheduling method includes:

Obtaining status information of the plurality of processing cores in real time; and

When the processing core executing the task scheduling method fails, another processing core among the plurality of processing cores executes the task scheduling method.

In the embodiment of the present application, the task scheduling method is temporarily fixed to be executed by one processing core, and then the task scheduling method is moved to another processing core for execution when the processing core fails, so as to avoid the processing core failure of the execution task scheduling method The problem that tasks cannot be scheduled continuously; at the same time, in the case of multiple processing cores, the scheduling algorithm itself is not dynamically executed by multiple processing cores, eliminating the need for stacking and stacking in different processing cores. , which saves execution time and improves the overall efficiency of the system.

In the embodiment of the present application, the processing core executing the task scheduling method plays the role of monitoring task triggering, task waiting, task scheduling, and task execution, and can record abnormalities when tasks are abnormal.

In some implementations, the task scheduling method includes: allocating the pending tasks in the pending task queue to processing cores other than the processing core executing the task scheduling method among the plurality of processing cores.

In some embodiments, when one or more processing cores in the above-mentioned plurality of processing cores fail or the above-mentioned multi-core processing system is in a low power consumption working state, the tasks to be processed in the task queue to be processed are allocated to available specified processing core. In the embodiment of the present application, not only are the processing cores searched for indiscriminate scheduling according to the dynamic execution parameters of the tasks, but also the task scheduling of the processing cores is dynamically adjusted according to the status of the processing cores and the processing system itself, making the task scheduling more reasonable.

In the embodiment of this application, in the pending task queue, the priority of some tasks cannot be changed, while the priority of some tasks can be changed; considering that the relative priority of tasks will change dynamically based on the scene, this application The implementation scheme realizes the flexible adjustment of the priority.

In some implementations, the task scheduling method includes: adjusting the priority of the pending tasks based on the allocated waiting time of the pending tasks in the pending task queue.

In some implementations of the present application, the scheduling order of the tasks to be processed in the task queue to be processed is adjusted based on the first-in-first-out and priority criteria.

In a specific embodiment of the present application, adjusting the priority of the above-mentioned tasks to be processed based on the assigned waiting time of the tasks to be processed in the task queue to be processed includes:

When the original priority of the above-mentioned pending task plus the priority adjustment value of the above-mentioned pending task is less than or equal to the maximum allowed priority of the above-mentioned pending task, set the priority of the above-mentioned pending task to the original priority of the above-mentioned pending task The priority is added to the priority adjustment value, wherein the priority adjustment value is obtained by rounding the product of the allocation waiting time of the pending task and the adjustment coefficient; and

When the original priority of the task to be processed plus the priority adjustment value is greater than the maximum allowable priority of the task to be processed, the priority of the task to be processed is set to the maximum allowable priority of the task to be processed.

In some embodiments, when a new task to be processed is received, the attribute parameters of the new task to be processed are obtained, and the above attribute parameters include one or more of the following items: the maximum allowable waiting time of the task, the scheduled time of the task The estimated execution time, the original priority of the task, the priority adjustment factor of the task, and whether the task is allowed to be forced to terminate.

In some embodiments, the task scheduling method includes: assigning tasks in the pending task queue to different idle processing cores according to the estimated execution time of the tasks in the pending task queue, so that different processing cores execute tasks Completion times are staggered.

In the embodiment of the present application, by staggering the completion time of different processing cores to execute tasks, the waiting time of idle processing cores is reduced, and the overall efficiency of the system is improved.

In some embodiments, the difference between the sum of the estimated execution times of one or more tasks assigned to one idle processing core and the sum of the estimated execution times of one or more tasks successively assigned to another idle processing core greater than or equal to the preset time interval. In an exemplary embodiment of the present application, the preset time interval is 2ms.

In the embodiment of the present application, neither tasks are allocated individually one by one, nor tasks are allocated to multiple idle processing cores in batches at the same time, but one or more tasks are allocated to each idle processing core sequentially according to the possible execution time of the task, The waiting time of the idle processing core is reduced, the system efficiency is improved, and the coordination difficulty of tasks during the waiting time and the problem of being unable to control the processing core load are avoided at the same time.

In some embodiments, allocating tasks based on estimated execution times of tasks in the queue of pending tasks includes:

assigning the first task to be processed to the first idle processing core;

When the difference between the estimated execution time of the second to-be-processed task and the estimated execution time of the first to-be-processed task is greater than or equal to a preset time interval, assign the second to-be-processed task to a second idle processing core ;

When the difference between the estimated execution time of the second to-be-processed task and the estimated execution time of the first to-be-processed task is less than a preset time interval, determine the estimated execution time of the second to-be-processed task and the third to-be-processed task Whether the difference between the sum of the estimated execution time and the estimated execution time of the first task to be processed is greater than or equal to a preset time interval;

When the difference between the sum of the estimated execution time of the second pending task and the third pending task and the estimated execution time of the first pending task is greater than or equal to the preset time interval, the second pending task The processing task and the third task to be processed are allocated to the second idle processing core; and

When the difference between the sum of the estimated execution time of the second pending task and the third pending task and the estimated execution time of the first pending task is less than a preset time interval, the second pending task The task, the third task to be processed and the fourth task to be processed are allocated to the second idle processing core.

In the above embodiments of the present application, "first", "second", "third" and " "Fourth" indicates the allocation order of tasks to be processed, and "first" and "second" in the first idle processing core and the second idle processing core indicate the allocation order of idle processing cores that are equally allocated tasks. In the embodiment of the present application, one or more tasks are assigned to a certain processing core according to the possible execution time of the task, so that each processing core is not assigned a task at an approximate time, thereby ensuring that each processing core does not frequently Entering the idle time can effectively reduce the probability that multiple processing cores enter the idle time at the same time, and improve the processing efficiency of the system.

In the embodiment of the present application, when the sum of the estimated execution time of the second pending task, the third pending task, and the fourth pending task is equal to the difference between the estimated execution time of the first pending task When the value is less than the preset time interval, assign the second task to be processed, the third task to be processed and the fourth task to be processed to the second idle processing core. In this embodiment, although the sum of the estimated execution times of the tasks assigned to the second idle processing core is less than the estimated execution time of the tasks assigned to the first idle processing core, three pending tasks are still assigned to the first idle processing core. Two idle processing cores, so that a maximum of three tasks to be processed are allocated to the second idle processing core. The reason for this is to avoid assigning too many tasks to a processing core. The more tasks assigned to a processing core, the more error-prone it is. If the execution of the second pending task is abnormal, it will affect the allocation to the second idle task. Handles the execution of other tasks for the core.

In some implementations, according to the priorities of the tasks to be processed in the task queue to be processed, the assignment order of the tasks to be processed is arranged in order from high to low.

In some embodiments, according to the idle time of the idle processing cores, the allocation order of the above idle processing cores is arranged in descending order.

The second aspect of the present application provides a computer-readable storage medium, the computer-readable storage medium stores instructions, and when the above-mentioned instructions are executed by a processor, the above-mentioned instructions cause the processor to implement the method according to the above-mentioned first aspect. Task scheduling method.

A third aspect of the present application provides a multi-core processor system, the multi-core processor system includes a plurality of processing cores, one of the processing cores in the plurality of processing cores is configured as a management core for executing task scheduling;

The management core is configured to execute the task scheduling method according to the first aspect above.

The fourth aspect of the present application provides a task scheduling method, the task scheduling method includes: assigning tasks in the pending task queue to different idle processing cores according to the estimated execution time of the tasks in the pending task queue, The completion time of tasks performed by different processing cores is staggered.

The fifth aspect of the present application provides a task scheduling method, the task scheduling method is suitable for a multi-core processor system, the multi-core processor system includes a plurality of processing cores; and

The task scheduling method is executed by one processing core in the plurality of processing cores, and the task scheduling method includes:

Description of drawings

In order to illustrate the technical solution of the present application more clearly, the accompanying drawings that need to be used in the embodiments of the present application will be briefly introduced below. Obviously, the accompanying drawings described below are only some implementations of the present application. Ordinary technicians can also obtain other drawings based on the drawings without creative labor. In the attached picture:

FIG. 1 illustrates a flowchart of a task scheduling method 100 according to an embodiment of the present application;

Figure 1a illustrates a flowchart of a task scheduling method 100a according to another embodiment of the present application;

FIG. 2 illustrates a block diagram of a multi-core processor system 200 according to one embodiment of the present application;

FIG. 3 illustrates a flowchart of a task scheduling method 300 according to an embodiment of the present application;

FIG. 4 illustrates a flowchart of a task scheduling method 400 according to an embodiment of the present application;

FIG. 5 illustrates a flowchart of a task scheduling method 500 according to an embodiment of the present application;

Figure 6 illustrates a flow chart of a task scheduling method 600 according to an embodiment of the present application; and

Fig. 6a illustrates a flowchart of a task scheduling method 600a according to another embodiment of the present application.

Detailed ways

Embodiments of the present application will be described in detail below with reference to the accompanying drawings. The following embodiments are only used to illustrate the technical solution of the present application more clearly, and therefore are only examples, and should not be used to limit the protection scope of the present application.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the application; the terms used herein are only for the purpose of describing specific embodiments, and are not intended to be To limit this application; the terms "comprising" and "having" and any variations thereof in the specification and claims of this application and the description of the above drawings are intended to cover a non-exclusive inclusion.

In the description of the embodiments of the present application, the technical terms "first" and "second" are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features , in a particular order or in a primary or secondary relationship, unless otherwise indicated.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiments.

In the description of the embodiments of the present application, the term "and/or" is only an association relationship describing associated objects, which means that there may be three relationships, such as A and/or B, which may mean: there is A, and there is A at the same time and B, there are three cases of B. In addition, the character "/" in this article generally indicates that the contextual objects are an "or" relationship. In the description of the embodiments of the present application, the term "plurality" refers to two or more (including two), unless otherwise clearly and specifically defined.

If steps are recited in order in the specification or claims, this does not necessarily mean that the embodiments or aspects are limited to the recited order. Rather, it is conceivable that the steps are also carried out in a different order or in parallel to each other, unless one step builds on another, which absolutely requires that the built-in steps be carried out subsequently (however this will become clear in individual cases) . Therefore, the stated order may be a preferred embodiment.

The inventors found that conventional scheduling algorithms classify tasks at different levels into different scheduling classes using different algorithms, resulting in overly complex algorithms for task allocation and poor program maintainability. In addition, conventional scheduling algorithms do not take into account the impact of scene changes on scheduling; conventional scheduling algorithms only use the dynamic execution parameters of tasks to find processing cores and perform undifferentiated scheduling. state, tasks may be assigned to invalid processing cores.

The inventor also found that when the scheduling algorithm is dynamically executed by multiple processing cores, it is often necessary to stack and push the data in different processing cores, resulting in a long execution time of the scheduling algorithm itself; while the scheduling algorithm is fixed by a When the main core is executing, if the main core fails, the scheduling algorithm cannot continue to be executed. In addition, when the task processing times out, the conventional scheduling algorithm often directly terminates the task, which can easily lead to system crashes, flashbacks, restarts, logic conflicts and other abnormalities.

In addition, the inventor also realized that the conventional scheduling algorithm either assigns individual tasks to idle processing cores one by one, which easily leads to too much waiting time for idle processing cores, or assigns multiple tasks to multiple idle processing cores in batches, which easily leads to task Coordination difficulties during waiting times and the inability to manage nuclear loads.

Based on the above findings, in order to overcome the problems of conventional scheduling algorithms, the inventors designed a task scheduling method and a multi-core processor system to adapt to the requirements of applications such as automatic driving for functional complexity, scene diversification, functional individualization, and system security. and real-time requirements.

Fig. 1 illustrates a flowchart of a task scheduling method 100 according to an embodiment of the present application. As shown in FIG. 1 , in step 102 , it is judged whether the executed task is in an abnormal execution state; if yes, it is judged whether the task can be forcibly terminated, step 104 . If the task cannot be forcibly terminated, then report the execution exception status of the task to other tasks associated with the task, step 108 . Then, wait to receive processing instructions for the task from other tasks, and determine whether waiting to receive processing instructions for the task times out, step 110 . If the duration of the task being in the execution abnormal state reaches the predetermined waiting time and the termination instruction of the task is not received, that is, waiting for the processing instruction of the task to be received is timed out, the execution of the task is forcibly terminated or the processing core for executing the task is stopped. Task scheduling, step 114. If a processing instruction of the task is received within the predetermined waiting time, the task is processed according to the received processing instruction (step 112 ).

In some embodiments of the present application, the execution exception state includes one or more of the following states: task execution timeout state, memory used by the task exceeds the limit, and stack used by the task exceeds the limit. In some embodiments of the present application, the predetermined waiting time is determined according to the priority of the task.

In addition, in some embodiments of the present application, when the task is in an abnormal execution state, the abnormal state of the task is recorded. By recording abnormal tasks, it provides data assurance for problem analysis of third-party applications and whether new applications can be deployed.

In some embodiments of the present application, especially in the scenario of the on-board controller, when the program process fails (for example, the memory exceeds the limit), instead of simply forcibly terminating the program process, the operating system reports the failure of the program process, And provide a certain response time for other related processes. If the operating system instructs to close the program process after receiving the fault alarm, it directly closes the program process. If the operating system does not give or receive processing instructions for the process for a long time, the operating system closes the faulty process after a timeout. In one embodiment of the present application, during automatic parking, if the taillight program fails, the operating system will set the failure and wait for other application programs to process, such as slowing down, parking, exiting the automatic driving mode, etc.; If there is no indication feedback, the operating system forcibly shuts down the process in order to prevent the process from expanding the fault range and causing further harm.

Fig. 1a illustrates a flowchart of a task scheduling method 100a according to another embodiment of the present application. Figure 1a is similar to Figure 1, so the same steps will not be repeated. As shown in FIG. 1 a , in step 101 , monitor the execution status of the task; then, judge whether the task is in an abnormal state according to the execution status of the task, step 102 . If the task is not in an abnormal state, it is judged whether the execution of the task is completed, step 103 . If the task is not completed, return to step 101 to continue monitoring the execution of the task.

In addition, if the task can be forcibly terminated, the task is terminated directly (step 106 ). In some embodiments of the present application, when the task to be forcibly terminated is the last task in the processing core executing the task, assign a new task to the processing core executing the task; When the last task in the processing core of the task is executed, the processing core executing the task is ordered to execute the next task assigned to it in sequence.

In the embodiment of this application, when an abnormal task occurs, a choice is made between terminating the task and delaying the termination according to the characteristics of the task itself, neither forcibly terminating the abnormal program nor letting the abnormal program go, avoiding the abnormal The program expands the fault range and causes further harm, avoids system crashes, flashbacks, restarts, logic conflicts and other abnormalities, provides technical support for the system to enter a safe state, and meets the needs of high-security scenarios such as automatic driving.

FIG. 2 illustrates a block diagram of a multi-core processor system 200 according to one embodiment of the present application. As shown in FIG. 2 , the multi-core processor system 200 includes a plurality of

processing cores

202A, 202B, 202C, . . . , 202N. Among the multiple processing cores, processing core 0 202A is a management core, and the remaining processing cores 1-

n

202B, 202C, ..., 202N are processing cores for executing tasks to be processed.

In some embodiments of the present application, the management core 202A plays a role of monitoring task triggering, task waiting, task scheduling, and task execution, and can record abnormalities when tasks are abnormal.

In some embodiments of the present application, when a new task is received, the attribute parameters of the new task are obtained, and the attribute parameters include one or more of the following items: the maximum allowable waiting time of the task, the estimated execution time of the task, The original priority of the task, the priority adjustment factor of the task, and whether the task allows forced termination, etc. In addition, in some embodiments of the present application, when a new task is received, the new task is inserted into the task queue to be executed according to the priority of the new task.

FIG. 3 illustrates a flowchart of a task scheduling method 300 according to an embodiment of the present application. As shown in FIG. 3 , in step 302 , the state information of the above-mentioned

multiple processing cores

202A, 202B, 202C, . . . , 202N is obtained in real time. Then, in step 304, it is determined whether the management core 202A is faulty. If the management core 202A is normal, the management core 202A continues to execute the task scheduling algorithm. If the management core 202A fails, another processing core other than the processing core 202A in the

multiple processing cores

202A, 202B, 202C, ..., 202N is used as a new management core, that is, the new management core executes the task scheduling algorithm, Step 306. In some embodiments of the present application, when the processing core 0 202A fails, the scheduling algorithm is shifted to be executed by the processing core 1 202B, and the tasks to be processed are assigned to the remaining processing cores 2-n 202C, ..., 202N for execution.

FIG. 4 illustrates a flowchart of a task scheduling method 400 according to an embodiment of the present application. As shown in FIG. 4 , in step 402 , the state information of the above-mentioned

multiple processing cores

202A, 202B, 202C, . . . , 202N is obtained in real time. Then, in step 404, it is determined whether there is a processing core failure, and in step 406, it is determined whether the system is in a low power consumption state. If there is a processing core failure or the system is in a low power consumption state, the pending tasks in the pending task queue are assigned to available designated processing cores, step 408 . In the embodiment of the present application, not only are the processing cores searched for indiscriminate scheduling according to the dynamic execution parameters of the tasks, but also the task scheduling of the processing cores is dynamically adjusted according to the status of the processing cores and the processing system itself, making the task scheduling more reasonable.

FIG. 5 illustrates a flowchart of a task scheduling method 500 according to an embodiment of the present application. As shown in FIG. 5 , in step 502 , whether the original priority of the pending task plus the priority adjustment value of the pending task is less than or equal to the maximum allowable priority of the pending task. If yes, then the new priority of the task to be processed is set to the original priority of the task to be processed plus the priority adjustment value of the task to be processed, step 504; if no, the new priority of the task to be processed will be set to Maximum allowed priority of pending tasks, step 506 . In some implementations of the present application, the priority adjustment value of the task to be processed is equal to the rounded integer of the product of the assigned waiting time of the task to be processed and the adjustment coefficient.

In some embodiments of the present application, the priorities of some tasks can be changed, but the priorities of tasks are limited within a certain range according to their own attributes. In an embodiment of the present application, especially in the scenario of the on-board controller, the priority range of the air-conditioning switching task will not exceed the priority range of the braking task.

In the implementation of the present application, the priority of the pending tasks is adjusted based on the assigned waiting time of the pending tasks in the pending task queue. Considering that the relative priority of the tasks will change dynamically based on the scene, the priority of the tasks is realized. Flexible adjustment.

FIG. 6 illustrates a flowchart of a task scheduling method 600 according to an embodiment of the present application. As shown in Figure 6, in step 602, the estimated execution time of the task is acquired; then, in step 604, the tasks in the pending task queue are allocated to different idle tasks according to the estimated execution time of the tasks in the pending task queue The processing cores enable different processing cores to stagger the completion time of tasks. In the embodiment of the present application, by staggering the completion time of different processing cores to execute tasks, the waiting time of idle processing cores is reduced, and the overall efficiency of the system is improved.

In some embodiments, the difference between the sum of the estimated execution times of one or more tasks assigned to one idle processing core and the sum of the estimated execution times of one or more tasks successively assigned to another idle processing core greater than or equal to the preset time interval. In an exemplary embodiment of the present application, the preset time interval is 2ms. In the embodiment of the present application, neither tasks are allocated individually one by one, nor tasks are allocated to multiple idle processing cores in batches at the same time, but one or more tasks are allocated to each idle processing core sequentially according to the possible execution time of the task, The waiting time of the idle processing core is reduced, the system efficiency is improved, and the coordination difficulty of tasks during the waiting time and the problem of being unable to control the processing core load are avoided at the same time.

Fig. 6a illustrates a flowchart of a task scheduling method 600a according to another embodiment of the present application. As shown in Figure 6a, in step 605, the first task to be processed is assigned to the first idle processing core; then, in step 606, it is judged that the estimated execution time of the second task to be processed is different from the estimated execution time of the first task to be processed Whether the absolute value of the execution time difference is greater than or equal to the preset time interval. If yes, then assign the second task to be processed to the second idle processing core, step 607; if not, judge the sum of the estimated execution time of the second task to be processed and the third task to be processed and the first task to be processed Whether the absolute value of the difference of the estimated execution time is greater than or equal to the preset time interval, step 608 . If yes, assign the second task to be processed and the third task to be processed to the second idle processing core, step 609; if not, assign the second task to be processed, the third task to be processed and the fourth task to be processed To the second idle processing core, step 610.

In the embodiment of Fig. 6a, the "first", "second", "third" and "second" in the first pending task, the second pending task, the third pending task and the fourth pending task Four" indicates the allocation order of tasks to be processed, and "first" and "second" in the first idle processing core and the second idle processing core indicate the allocation order of idle processing cores that are equally allocated tasks. In the embodiment of the present application, one or more tasks are assigned to a certain processing core according to the possible execution time of the task, so that each processing core is not assigned a task at an approximate time, thereby ensuring that each processing core does not frequently Entering the idle time can effectively reduce the probability that multiple processing cores enter the idle time at the same time, and improve the processing efficiency of the system.

In some embodiments of the present application, when the difference between the sum of the estimated execution time of the second pending task, the third pending task, and the fourth pending task and the estimated execution time of the first pending task is less than the estimated When the time interval is set, the second task to be processed, the third task to be processed and the fourth task to be processed are allocated to the second idle processing core. In this embodiment, although the sum of the estimated execution times of the tasks assigned to the second idle processing core is less than the estimated execution time of the tasks assigned to the first idle processing core, three pending tasks are still assigned to the first idle processing core. Two idle processing cores, so that a maximum of three tasks to be processed are allocated to the second idle processing core. In addition, in some embodiments of the present application, when assigning tasks to the third idle processing core, the estimated execution time of one or more tasks pre-allocated to the third idle processing core is also compared with the estimated execution time of one or more tasks assigned to the second idle processing core. Compare the estimated execution times of one or more tasks of a core.

In some implementations, according to the priorities of the tasks to be processed in the task queue to be processed, the assignment order of the tasks to be processed is arranged in order from high to low. In addition, in some implementations, according to the idle time of the idle processing cores, the allocation order of the above idle processing cores is arranged in descending order.

While the invention has been described with reference to a preferred embodiment, various modifications may be made and equivalents may be substituted for parts thereof without departing from the scope of the invention. In particular, as long as there is no structural conflict, the technical features mentioned in the various embodiments can be combined in any manner. The present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

A task scheduling method, characterized in that the task scheduling method comprises:

When the first task is in an abnormal execution state, judging whether the first task can be forcibly terminated;

when the first task cannot be forcibly terminated, reporting the execution exception status of the first task to a second task associated with the first task; and

When the duration of the first task being in the execution abnormal state reaches a predetermined waiting time and no termination instruction of the first task is received, forcibly terminate the execution of the first task or stop the processing of the execution of the first task The core performs task scheduling.
The task scheduling method according to claim 1, wherein the abnormal execution state includes one or more of the following states: task execution timeout state, memory used by the task exceeds the limit, and stack used by the task exceeds the limit.
The task scheduling method according to claim 1 or 2, wherein the predetermined waiting time is determined according to the priority of the first task.
The task scheduling method according to any one of claims 1 to 3, wherein the task scheduling method comprises:

When the first task can be forcibly terminated, the first task is forcibly terminated.
The task scheduling method according to any one of claims 1 to 4, wherein the task scheduling method comprises:

When the first task to be forcibly terminated is the last task in the processing core executing the first task, assign a new task to the processing core executing the first task.
The task scheduling method according to any one of claims 1 to 5, wherein the task scheduling method comprises:

When the first task to be forcibly terminated is not the last task in the processing core executing the first task, instructing the processing core executing the first task to sequentially execute the next assigned task.
The task scheduling method according to any one of claims 1 to 6, wherein the task scheduling method is applicable to a multi-core processor system, and the multi-core processor system includes a plurality of processing cores.
The task scheduling method according to claim 7, wherein the task scheduling method is executed by a processing core in the plurality of processing cores, and the task scheduling method comprises:

acquiring state information of the plurality of processing cores in real time; and

When a processing core executing the task scheduling method fails, another processing core among the plurality of processing cores executes the task scheduling method.
The task scheduling method according to claim 7 or 8, wherein the task scheduling method comprises:

Allocating the pending tasks in the pending task queue to processing cores other than the processing core executing the task scheduling method among the plurality of processing cores.
The task scheduling method according to any one of claims 7 to 9, wherein when one or more processing cores in the plurality of processing cores fail or the multi-core processing system is in a low power consumption working state , assign the pending tasks in the pending task queue to the available specified processing cores.
The task scheduling method according to any one of claims 1 to 10, wherein the task scheduling method comprises:

The priority of the pending tasks is adjusted based on the allocated waiting time of the pending tasks in the pending task queue.
The task scheduling method according to claim 11, wherein adjusting the priority of the task to be processed based on the assigned waiting time of the task to be processed in the task queue to be processed comprises:

When the original priority of the pending task plus the priority adjustment value of the pending task is less than or equal to the maximum allowed priority of the pending task, set the priority of the pending task to the the original priority of the task to be processed plus the priority adjustment value, wherein the priority adjustment value is obtained by rounding the product of the assigned waiting time of the task to be processed and an adjustment factor; and

When the original priority of the pending task plus the priority adjustment value is greater than the maximum allowed priority of the pending task, set the priority of the pending task to the maximum allowed priority of the pending task priority.
The task scheduling method according to any one of claims 1 to 12, wherein when a new task to be processed is received, attribute parameters of the new task to be processed are obtained, and the attribute parameters include the following items One or more of: the maximum allowable waiting time of the task, the estimated execution time of the task, the original priority of the task, the priority adjustment factor of the task, and whether the task is allowed to be forced to terminate.
The task scheduling method according to any one of claims 1 to 13, wherein the task scheduling method comprises:

According to the estimated execution time of the tasks in the task queue to be processed, the tasks in the task queue to be processed are allocated to different idle processing cores, so that the completion times of tasks executed by different processing cores are staggered.
The task scheduling method according to claim 14, wherein the sum of the estimated execution time of one or more tasks assigned to one idle processing core and the estimated execution time of one or more tasks successively assigned to another idle processing core The difference of the sum of estimated execution times is greater than or equal to a preset time interval.
The task scheduling method according to claim 14 or 15, wherein allocating tasks according to the estimated execution time of the tasks in the task queue to be processed comprises:

assigning the first task to be processed to the first idle processing core;

When the difference between the estimated execution time of the second to-be-processed task and the estimated execution time of the first to-be-processed task is greater than or equal to a preset time interval, assign the second to-be-processed task to the second idler processing core;

When the difference between the estimated execution time of the second pending task and the estimated execution time of the first pending task is less than a preset time interval, judging the second pending task and the third pending task Whether the difference between the sum of the estimated execution time of tasks and the estimated execution time of the first task to be processed is greater than or equal to a preset time interval;

When the difference between the sum of the estimated execution time of the second to-be-processed task and the third to-be-processed task and the estimated execution time of the first to-be-processed task is greater than or equal to a preset time interval, the assigning the second pending task and the third pending task to the second idle processing core; and

When the difference between the sum of the estimated execution time of the second to-be-processed task and the third to-be-processed task and the estimated execution time of the first to-be-processed task is less than a preset time interval, the The second task to be processed, the third task to be processed and the fourth task to be processed are allocated to the second idle processing core.
The task allocation method according to any one of claims 1 to 16, characterized in that the allocation order of the tasks to be processed is arranged in sequence from high to low according to the priorities of the tasks to be processed in the task queue to be processed.
The method for allocating tasks according to any one of claims 1 to 17, characterized in that the allocation order of the idle processing cores is arranged in descending order according to the idle time of the idle processing cores.
A computer-readable storage medium storing instructions which, when executed by a processor, cause the processor to implement the task scheduling method.
A multi-core processor system, characterized in that the multi-core processor system includes a plurality of processing cores, and one processing core in the plurality of processing cores is configured as a management core for performing task scheduling;

The management core is configured to execute the task scheduling method according to any one of claims 1 to 18 above.