TW202119207A - Scheduling method and apparatus, electronic device and storage medium - Google Patents

Abstract

The present disclosure relates to a scheduling method and apparatus, an electronic device, and a storage medium. The method includes: obtaining task processing time of a first task within a current scheduling period; base on the task processing time and a length of a first time slice allocated for the first task within the current scheduling period, determining whether the first task times out; and based on the determined result, adjusting a time slice allocated for at least one second task within a target scheduling period, where the target scheduling period includes the current scheduling period or a scheduling period next to the current scheduling period.

Description

Scheduling method and device, electronic equipment and recording medium

The present disclosure relates to the field of computer technology, in particular to a scheduling method and device, electronic equipment and recording media.

With the rapid development of artificial intelligence technology, a large number of artificial intelligence enterprises have been established. The neural network used in artificial intelligence relies on the computing power of the graphics processing unit (GPU). Gradually develop towards large-scale, high-speed internet interconnection. In order to meet the different requirements of different tasks on the GPU, academia and industry have begun to explore GPU virtualization technology.

The present disclosure proposes a scheduling scheme.

According to an aspect of the present disclosure, there is provided a scheduling method, including: obtaining task processing time of a first task in a current scheduling period; based on the task processing time and the first task allocated to the first task in the current scheduling period A time slice to determine whether the first task has timed out; according to the determined result, the time slice allocated to at least one second task in the target scheduling period is adjusted, wherein the target scheduling period includes the current scheduling period or the State the next scheduling period of the current scheduling period.

In one or more optional embodiments, the determining whether the first task times out based on the task processing time and the first time slice allocated for the first task in the current scheduling period includes : Determine the first time difference between the deadline of the task processing time and the deadline of the first time slice; if the first time difference is greater than the first time threshold, determine the first time difference A task timed out.

In one or more optional embodiments, the first time threshold is obtained based on the length of the first time slice.

In one or more optional embodiments, the adjusting the time slice allocated to the at least one second task in the target scheduling period according to the result of the determination includes: adjusting when the first task is determined to time out The length of the current scheduling period; based on the adjusted length of the current scheduling period, adjusting the time slice allocated for at least one second task in the current scheduling period.

In one or more optional embodiments, the adjusting the time slice allocated for at least one second task in the current scheduling period based on the adjusted length of the current scheduling period includes: based on the current scheduling period The adjusted length of the period and the service quality parameter corresponding to each second task, adjust the length of the time slice allocated for each second task in the current scheduling period, so that each second task The service quality parameter of the task is maintained at the corresponding preset value and/or the proportion of the time slice of each second task in the current scheduling period is maintained at the corresponding preset value.

In one or more optional embodiments, in the case where it is determined that the first task is timed out, adjusting the length of the current scheduling period includes: obtaining the timeout of the third task in the current scheduling period The third task is a task that has been executed in the current scheduling period; according to the number of timeouts, an extension coefficient for extending the length of the current scheduling period is determined, wherein the extension coefficient is The number of timeouts is positively correlated; based on the extension coefficient, the length of the current scheduling period is extended to obtain the adjusted length of the current scheduling period.

In one or more optional embodiments, the extension coefficient is obtained based on an exponential function with the number of timeouts as a variable.

In one or more optional embodiments, the method further includes: acquiring the task processing time of a third task in the current scheduling period, wherein the at least one second task includes the third task; in response to The task processing time of the third task is less than the adjusted time slice length of the third task, and time compensation is performed on the third task in the current scheduling period.

In one or more optional embodiments, the task processing time in response to the third task is less than the adjusted time slice length of the third task, and the third task is processed in the current scheduling period. The time compensation of the task includes: determining the compensation time of the third task based on the task processing time of the third task and the adjusted time slice length of the third task; and calculating the compensation time of the third task based on the compensation time The compensation task of the third task is added to the scheduling queue of the current scheduling period.

In one or more optional embodiments, adding the compensation task of the third task to the scheduling queue of the current scheduling period based on the compensation time includes: adding the compensation task of the third task to the scheduling queue of the current scheduling period based on the compensation time. The compensation task of the third task is added to the end of the scheduling queue of the current scheduling period.

In one or more optional embodiments, the adjusting the time slice allocated for the at least one second task in the target scheduling period according to the result of the determination includes: determining that each task does not exceed the time in the current scheduling period. In the case of time, the length of the next scheduling period of the current scheduling period is adjusted; based on the adjusted length of the next scheduling period, the time slice allocated for at least one second task in the next scheduling period is determined .

In one or more optional embodiments, the adjusting the length of the next scheduling period of the current scheduling period includes: reducing the length of the next scheduling period by using a preset reduction factor.

In one or more optional embodiments, the determining a time slice allocated for at least one second task in the next scheduling period based on the adjusted length of the next scheduling period includes: based on the The adjusted length of the next scheduling period and the service quality parameter corresponding to each of the second tasks determine the length of the time slice allocated by each of the second tasks in the next scheduling period, so that each The service quality parameter of the second task is maintained at the corresponding preset value and/or the proportion of the time slice of each second task in the next scheduling period is maintained at the corresponding preset value.

In one or more optional embodiments, the method further includes: acquiring the historical task processing time of multiple tasks executing historical tasks within a preset time period; and determining the current task processing time according to the statistical information of the historical task processing time The initial length of the scheduling period.

According to an aspect of the present disclosure, there is provided a scheduling device, including: an acquisition module for acquiring the task processing time of a first task in a current scheduling period; a determination module for acquiring task processing time based on the task processing time and the current The first time slice allocated for the first task in the scheduling period determines whether the first task has timed out; the adjustment module is used to adjust the allocation of at least one second task in the target scheduling period according to the determined result Time slice, wherein the target scheduling period includes the current scheduling period or the next scheduling period of the current scheduling period.

According to another aspect of the present disclosure, there is provided an electronic device including: a processor; a memory for storing computer-readable instructions; wherein the processor is used for scheduling the computer-readable instructions stored in the memory , To perform the above scheduling method.

According to another aspect of the present disclosure, there is provided a computer-readable recording medium on which computer program instructions are stored, and the computer program instructions implement the above scheduling method when executed by a computer.

In another aspect of the present disclosure, there is provided a computer program including computer-readable instructions, wherein the computer-readable instructions implement the above scheduling method when executed by a computer.

In the embodiment of the present disclosure, the task processing time of the first task in the current scheduling period can be obtained, and then based on the task processing time and the first time slice allocated for the first task in the current scheduling period, it is determined whether the first task has timed out, According to the determined result, the time slice allocated to the at least one second task in the target scheduling period is adjusted, where the target scheduling period includes the current scheduling period or the next scheduling period of the current scheduling period. In this way, the time slice allocated for the second task in the target scheduling period can be automatically adjusted, so that the time slice allocated for each second task in the target scheduling period meets the service quality requirements, thereby improving user experience.

It should be understood that the above general description and the following detailed description are only exemplary and explanatory, rather than limiting the present disclosure.

According to the following detailed description of exemplary embodiments with reference to the accompanying drawings, other features and aspects of the present disclosure will become clear.

Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the drawings. The same reference numerals in the drawings indicate elements with the same or similar functions. Although various aspects of the embodiments are illustrated in the drawings, unless otherwise noted, the drawings are not necessarily drawn to scale.

The dedicated word "exemplary" here means "serving as an example, embodiment, or illustration." Any embodiment described here as "exemplary" need not be construed as being superior or better than other embodiments.

The term "and/or" in this article is only an association relationship that describes associated objects. It means that there can be three relationships. For example, A and/or B can mean: A alone exists, A and B exist at the same time, and B exists alone. three situations. In addition, the term "at least one" in this document means any one or any combination of at least two of the multiple, for example, including at least one of A, B, and C, and may mean including those formed from A, B, and C. Any one or more elements selected in the set.

In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. Those skilled in the art should understand that the present disclosure can also be implemented without certain specific details. In some instances, the methods, means, elements, and circuits well known to those skilled in the art have not been described in detail, so as to highlight the gist of the present disclosure.

The scheduling scheme provided by the embodiments of the present disclosure can obtain the task processing time of each task of the virtual graphics processing unit (vGPU) in the current scheduling period, and then based on the task processing time of the first task and the current scheduling period The first time slice allocated for the first task determines whether the first task times out, so that the time slice allocated for at least one second task in the target scheduling period can be adjusted according to the determined result. In this way, when the first time slice assigned to the first task is too long or too short, the time slice assigned to the second task can be automatically adjusted, so as to reasonably configure the time slice of the second task in the target scheduling period, so that While the GPU has high performance, it can flexibly set the allocated time slices, so that the resources of the GPU can be effectively used and the user experience can be improved.

Here, the GPU, that is, the physical GPU, can be divided into smaller granular units, and each unit can be called a virtual image processing unit. The virtual image processing unit can process tasks in a time-sharing multiplexing GPU manner, and each task can include multiple task units. When the virtual image processing unit is performing a task, it cannot pause the task unit being executed. Therefore, when the processing time of the virtual image processing unit to execute a task unit is long, the task processing time of the task will exceed the task assigned to the task. Time slice, thereby reducing the quality of service (QoS) of other tasks. The service quality may be an index for evaluating the service capability. The scheduling scheme provided by the embodiment of the present disclosure can match the task processing time of the task to the time slice assigned to the task, so that the service quality provided by the scheduling system is guaranteed. The task unit here can be understood as the basic unit of task processing, usually cannot be divided into smaller units, and cannot be suspended during execution. Multiple task units can be time-sharing multiplexed virtual image processing unit. For example, a task unit can correspond to a kernel function. A kernel function can include a set of instructions, and the length of each kernel function can be the same or different. When executing a kernel function, you must wait for all the instructions of the kernel function to be executed before stopping.

A device may include one or more GPUs, and a GPU may also include one or more virtual image processing units. The scheduling method provided by the present disclosure can be applied to a single virtual image processing unit, and can also be applied to multiple virtual image processing units. Wherein, the scheduling method of each of the multiple virtual image processing units is similar to the scheduling method of a single virtual image processing unit. For the sake of simplicity, a single virtual image processing unit is used as an example for description in the following. Those skilled in the art should understand that the present disclosure does not limit the number of virtual image processing units. Similarly, those skilled in the art should understand that the present disclosure does not limit the number of GPUs.

The technical solutions provided by the embodiments of the present disclosure can be applied to task processing of GPUs, scheduling of virtual image processing units, time slice adaptive expansion, etc., which are not limited in the embodiments of the present disclosure.

Fig. 1 shows a flowchart of a scheduling method according to an embodiment of the present disclosure. The scheduling method can be executed by terminal equipment, servers or other types of electronic equipment, where the terminal equipment can be User Equipment (UE), mobile equipment, user terminal, terminal, cellular mobile phone, wireless phone, personal Digital assistants (Personal Digital Assistant, PDA), handheld devices, computing devices, in-vehicle devices, wearable devices, etc. In some possible implementations, the scheduling method can be implemented by the processor invoking computer-readable instructions stored in the memory. The scheduling method can be applied to schedule multiple tasks on the same virtual image processing unit. For each task, one or more time slices can be allocated, and this can be achieved by executing at least one task unit of the task on the time slice The execution of the task. The scheduling method of the embodiment of the present disclosure will be described below by taking the electronic device as the execution subject as an example.

Step S11: Obtain the task processing time of the first task in the current scheduling period.

In the embodiment of the present disclosure, the electronic device may detect the task processing time of each of the multiple tasks in the current scheduling period, and the first task may be the task currently being processed. The current scheduling period may be the scheduling period of the task currently being processed. In the virtual image processing unit, the task queue includes multiple scheduling periods.

In some examples, in the virtual image processing unit, a scheduling period is relatively short, for example, it can be several seconds or several hundreds of milliseconds. The cycle of a task queue is relatively long, for example, it can be several hours or even several days. Since a task in the task queue may need to be executed in multiple scheduling periods to complete, correspondingly, a certain task in the scheduling period described in the present disclosure refers to the part of the task allocated to be executed in the scheduling period. It is all task units of the task, or part of the task units of the task. Multiple tasks processed by time division in two task scheduling periods may be the same or different.

Each task can be time-sharing multiplexed virtual image processing unit. Correspondingly, multiple tasks can form a scheduling queue. The task can be an image processing task or a neural network training task. The present disclosure does not limit the tasks specifically handled by the tasks. The task processing time of a task may be the total time spent to execute the task in a scheduling period, where executing the task may include executing one or more task units of the task.

Step S12: Determine whether the first task times out based on the task processing time and the first time slice allocated for the first task in the current scheduling period.

In the embodiment of the present disclosure, the task processing time of the first task may be compared with the first time slice allocated for the first task to obtain a comparison result, and according to the comparison result, it is determined whether the first task has timed out. Here, the first time slice may be the time allocated for the first task and occupying the virtual image processing unit. The length of the time slice allocated to each task can be the same or different.

For example, the first task includes multiple task units, and the first time slice is allocated to the first task in the current scheduling period, and at least two task units are used to execute the first task. In the process of using the first time slice of the current scheduling period to execute at least two task units of the first task, it is assumed that the execution starts from the nth task unit, and when the mth task unit is executed, the first time slice The time has expired, but because the task unit cannot be suspended, you must wait for the mth task unit to complete before switching to the next task. In this case, the task processing time of the first task is from the beginning of the nth task unit. The time taken to complete the execution of the mth task exceeds the length of the first time slice allocated for it, that is, the first task times out. Among them, m and n are both positive integers, and m≥n.

For example, the length of the task processing time of the first task can be compared with the length of the first time slice to determine whether the length of the task processing time of the first task is greater than the length of the first time slice. If the task processing time of the first task is If the length of the time is greater than the length of the first time slice, it can be determined that the first task has timed out. If the length of the task processing time of the first task is less than or equal to the length of the first time slice, it may be determined that the first task has not timed out.

For another example, the deadline of the task processing time of the first task can be compared with the deadline of the first time slice. If the deadline of the task processing time of the first task is greater than the deadline of the first time slice, the first task can be determined. A task timed out. If the deadline of the task processing time of the first task is less than or equal to the deadline of the first time slice, it can be determined that the first task has not timed out.

In a possible implementation, the first time difference between the deadline of the task processing time of the first task and the deadline of the first time slice can be determined, and then the first time difference is greater than the first time threshold. In this case, it is determined that the first task has timed out.

In this implementation manner, the first time difference between the deadline of the task processing time of the first task and the deadline of the first time slice may be calculated first, and then the calculated first time difference may be compared with the preset first time difference. A time threshold is compared, and if the first time difference is greater than the first time threshold, it can be determined that the first task has timed out. If the first time difference is less than or equal to the first time threshold, it can be determined that the first task has not timed out.

Still taking the above example to illustrate, when the m-th task unit is executed, the time slice has expired, but because the task unit cannot be suspended, it must wait for the m-th task unit to complete before switching to the next task. In this case Next, do not directly determine the first task timeout, but determine the deadline of the task processing time of the first task, that is, the deadline of the m-th task unit, and the first time between the deadline of the first time slice Difference. If the first time difference is greater than the first time threshold, it is determined that the first task has timed out.

In some examples, the first time threshold may be a preset fixed value, for example, the first time threshold may be set to 0.2s, 0.5s, etc.

In some examples, the first time threshold may be a preset ratio value. For example, the above-mentioned first time threshold can be obtained based on the length of the first time slice. For example, the first time threshold can be set to 1% of the length of the first time slice, so that the first time threshold can be set by the length of the first time slice. , Make the first time threshold more flexible. When the first time slice is short, the first time threshold is smaller, that is, the condition for timeout judgment is relatively harsh; when the first time slice is longer, the first time threshold is larger, which is the condition for timeout judgment Relatively loose. For another example, the first time threshold may also be obtained based on the length of the current scheduling period, for example, the first time threshold is set to 1% of the length of the current scheduling period.

Through the first time threshold, the difference between the task processing time of the first task and the first time slice of the first time slice can be allowed to be within a reasonable range, so that the process of adjusting the time slice allocated to the second task can converge instead of Adjust the time slice assigned to the second task too frequently. For example, when the first time threshold is adjusted proportionally, for example, when the first time slice is longer, the first time threshold is larger, which can reduce the possibility of the first task overtime. Thus, the process of adjusting the second task can be converged.

Step S13: Adjust the time slice allocated to at least one second task in the target scheduling period according to the determined result, where the target scheduling period includes the current scheduling period or the next scheduling period of the current scheduling period.

In the embodiment of the present disclosure, the time slice allocated to at least one second task can be adjusted according to the result of determining whether the first task has timed out. The second task may be a task in the current scheduling period, or may be a task in a scheduling period next to the current scheduling period.

When the second task is a task in the current scheduling period, the second task may include tasks that have been executed in the current scheduling period, tasks that have not been executed in the current scheduling period, and the first task. When the second task is a task in a scheduling period next to the current scheduling period, the second task may include all tasks in the next scheduling period.

For example, if the first task in the current scheduling period times out, the length of the time slice allocated to the second task can be extended to obtain the extended time slice of the second task. If all tasks have not timed out in the current scheduling period, the time slice allocated to the second task in the next scheduling period can be shortened to obtain the shortened time slice of the second task. If there is a task timeout in the current scheduling period, on the basis of adjusting the length of the scheduling period, the next scheduling period will inherit the adjusted length of the scheduling period. The scheduling method provided by the present disclosure continuously adjusts the scheduling period, such as extending the scheduling period in the case of a timeout (the length of the next scheduling period is equal to the length after the extension of the scheduling period) and reducing the next scheduling period without timeout. The scheduling cycle can achieve the relative "steady state" of the scheduling cycle, and at the same time, the time slice allocated for the task can be adjusted to a reasonable range.

Through the above scheduling scheme, the time slice allocated to the second task can be automatically adjusted, so that the time slice allocated to the second task in the target scheduling period meets the quality of service requirements.

In a possible implementation manner, when it is determined that the first task is overtime, the length of the current scheduling period can be adjusted, and then based on the adjusted length of the current scheduling period, there is at least one second task in the current scheduling period. The allocated time slice is adjusted.

In this implementation, if it is determined that the first task has timed out, the length of the current scheduling period can be adjusted first. For example, the length of the current scheduling period can be extended by a fixed period of time, or the length of the current scheduling period can be expanded to Several times the original. Then, according to the adjusted length of the current scheduling period, the length of the time slice allocated to the at least one second task in the current scheduling period can be adjusted. For example, the time slice allocated to each second task is extended by a fixed time length, or the time slice allocated to each second task can be extended according to a certain ratio. In this way, when it is determined that the first task has timed out, the length of the current scheduling period can be adjusted, and the time slice of the second task can be adjusted through the adjusted length of the current scheduling period.

In an example, the length of the time slice allocated for each second task in the current scheduling period may be adjusted based on the adjusted length of the current scheduling period and the service quality parameters of each second task, so that The service quality parameter of each second task is maintained at the corresponding preset value and/or the proportion of the time slice of each second task in the current scheduling period is maintained at the corresponding preset value.

For example, there are three second tasks A, B, and C in the current scheduling period. Assuming that before the adjustment, the ratio of the second tasks A, B, and C in the current scheduling period is 3:3:4, which is the preset value It is 3:3:4. After adjustment, the proportion of the second tasks A, B, and C in the current scheduling period is still 3:3:4.

In this example, the quality of service parameter may be a parameter that characterizes the quality of service, and the quality of service parameter may be the share of the time slice corresponding to any task in a scheduling period in the scheduling period. The higher the service quality of a task, the more time slices it occupies in the scheduling period. For example, the service quality of a task can correspond to a weight. The higher the service quality, the higher the weight. When calculating the time slice share, you can first calculate the sum of the weights of each task in the scheduling period, and then divide the weight of a task by the sum of the weights of each task. The value obtained can be the time slice corresponding to the task. The time slice share of this scheduling period. By assigning different service qualities to different tasks, it can be ensured that tasks with high service quality can be given priority. A scheduling period can include multiple tasks, and each task can correspond to a quality of service parameter. After adjusting the length of the current scheduling period, the length of the time slice allocated to each second task can be adjusted according to the service quality parameter of each second task in the current scheduling period and the adjusted length of the current scheduling period. In this way, the service quality parameter of each second task remains unchanged, and/or the proportion of the time slice of each second task in the current scheduling period remains unchanged. Therefore, the time slice length of the second task can be adjusted according to the service quality, so as to meet the service quality requirements of each task.

In an example, in order to ensure that the service quality parameter of each task in the scheduling period remains unchanged after adjustment, the duration of the first task needs to be processed as well. The duration of the first task can be processed in the same way as other second tasks. For example, the allocated time slices of the first task are extended by a fixed length of time, or the first task can be increased in a certain proportion. The allocated time slice is extended.

In an example, the number of timeouts of tasks that have been executed in the current scheduling period may be obtained, and the executed tasks may be referred to as the third task. Then, according to the number of timeouts, an extension coefficient for extending the length of the current scheduling period is determined, and then based on the extension coefficient, the length of the current scheduling period is extended to obtain the adjusted length of the current scheduling period. Here, the extension coefficient is positively correlated with the number of timeouts.

In this example, the number of timeouts of the third task in the current scheduling period can be counted. Every time a third task is executed, if the third task times out, the number of times out can be increased by one. The extension coefficient for extending the length of the current scheduling period may be determined according to the number of timeouts, and the extension coefficient is positively correlated with the number of timeouts. For example, the greater the number of timeouts, the greater the extension coefficient. Then, the length of the current scheduling period can be extended by using the determined extension coefficient. For example, the length of the current scheduling period can be obtained by multiplying the extension coefficient by the length of the current scheduling period. Among them, the extension factor is greater than 1. In this way, the length of the current scheduling period can be reasonably extended by the number of timeouts, so that the current scheduling period has a reasonable length of time.

In an example, the aforementioned extension coefficient is obtained based on an exponential function with the number of timeouts as a variable.

In this example, the extension coefficient can be obtained based on an exponential function with the number of timeouts as a variable, so that the length of the current scheduling period can be extended by multiples of the extension coefficient to obtain the extended length of the current scheduling period. Here, the extended length of the current scheduling period can be calculated according to the following formula (1):

公式（1），

Formula 1),

_Wherein, T newtimeslice may extend the length of the current scheduling _period, T oldtimeslice may be the length of the current scheduling period, count the number of timeouts can be statistical, 2 ^count coefficient may be extended.

Here, the use of a binary exponential function for the extension coefficient can prevent the length of the extended scheduling period from increasing too fast, and it can also prevent the length of the current scheduling period from being extended and not converging due to the slow increase in the later period.

For example, suppose that the current scheduling cycle includes 10 tasks, among which the second, third, and fifth tasks have timed out. When the second time-out task, since the first task does not expire, count to 1, according to the formula _(1), T newtimeslice _T oldtimeslice is twice, that is, compared to the current scheduling period is not started The length of the time, this adjustment is to extend the length by 2 times. When the third task timeout, count of 2, according to equation _(1), T newtimeslice _T oldtimeslice of four times, to be noted that, at this time _T oldtimeslice already once extended length, i.e., phase Compared with the length of the current scheduling period when the execution is not started, this adjustment is to extend the length by 4 times when the length has been extended by 2 times. Similarly, when the fifth task times out, compared to the length of the current scheduling period when the execution is not started, this adjustment is to extend the length by 8 times after it has been extended by 2*4 times.

In a possible implementation, the task processing time of the third task that has been executed in the current scheduling period can be obtained, and then in response to the task processing time of the third task being less than the adjusted time slice length of the third task, the current Time compensation is performed on the third task in the scheduling period. Wherein, the second task includes the third task.

In this implementation manner, after adjusting the time slice of at least one second task in the current scheduling period, if the task processing time of any third task included in the at least one second task is less than the adjusted third task The length of the time slice can be compensated for the third task in the current scheduling period.

Here, since the time slice of the executed third task cannot be directly extended, the service quality parameter of each second task in the current scheduling period can be kept unchanged by time compensation for the third task. Among them, time compensation for the third task can be understood as assigning a corresponding time slice to the third task.

In an example of this implementation, the compensation time of the third task may be determined based on the task processing time of the third task and the adjusted time slice length of the third task, and then based on the compensation time, the compensation time of the third task The compensation task is added to the scheduling queue of the current scheduling period.

This example provides a way of time compensation for the third task. In this example, the compensation time of the third task can be determined according to the task processing time of the third task and the adjusted time slice length of the third task. For example, the adjusted time slice length of the third task and the adjusted time slice length of the third task can be calculated. The second time difference between the task processing times of the third task is used as the compensation time of the third task. Then, the task that compensates for the third task can be added to the scheduling queue of the current scheduling period, and the calculated compensation time can be allocated to the third task when the compensation task is executed. In this way, time compensation for the executed third task can be realized, and the service quality parameters of the executed third task remain unchanged.

In one example, based on the compensation time, the compensation task of the third task may be added to the end of the scheduling queue of the current scheduling period.

In this example, according to the compensation time of the third task, the compensation task of the third task can be added to the end of the scheduling queue of the current scheduling period, and a determined compensation time can be allocated to the compensation task, so as to realize the compensation of the third task. Time compensation. Adding the compensation task to the end of the scheduling queue of the current scheduling period can not disrupt the order of the tasks in the scheduling queue of the current scheduling period, so that the tasks in the scheduling queue are scheduled in the original order.

In an example, the compensation time of the third task may be determined according to the service quality parameters of the executed third task and the length before and after the adjustment of the current scheduling period.

In this example, the third time difference between the adjusted length of the current scheduling period and the length before the adjustment can be determined. Then, the compensation time of the third task can be determined according to the third time difference and the service quality parameter of the third task. For example, by multiplying the third time difference by the service quality parameter of the third task, the compensation time of the third task can be obtained, and then the time compensation of the third task can be realized. Here, the compensation time can be calculated according to the following formula (2):

公式（2），

Formula (2),

Wherein, t _compensation may represent compensation _time, T newtimeslice length may be adjusted after the current scheduling _period, T oldtimeslice length may be adjusted before the current scheduling period, Share _vGPU may be a quality of service parameter of the third task. The compensation time of each third task can be obtained by formula (2).

Fig. 2 shows an exemplary flow chart of extending the time slice allocated to a task according to an embodiment of the present disclosure, which may include the following steps.

In step S201, it is judged whether the currently executed task has timed out.

Wherein, in the case that the current task times out, step S202 and subsequent steps can be executed. In the case that the current task has not timed out, step S205 and subsequent steps can be performed.

In step S202, the length of the current scheduling period is extended according to the number of timeouts of tasks that have been executed in the current scheduling period.

Optionally, the length of the current scheduling period can be adjusted according to the current cumulative number of timeouts in the current scheduling period, that is, the cumulative number of timeouts of tasks that have been executed in the current scheduling period.

Step S203: Adjust the time slice allocated to each task in the current scheduling period according to the extended length of the current scheduling period.

Step S204, insert the compensation task of the completed task into the end of the scheduling queue, and allocate the compensation time corresponding to the compensation task.

By extending the time slice of the task, the time slice allocated for each task in the current scheduling period can be extended when the currently executing task is overtime, so that the extended time slice can be adapted to the corresponding service quality.

Step S205: It is judged whether the current scheduling period is over.

If the current scheduling period has not ended, step S207 is executed. When the current scheduling period ends, step S206 is executed.

Step S206, the current process is terminated. Inherit the length of the current scheduling period to the next scheduling period.

In step S207, the next task is scheduled to execute the task, the next task is updated to the currently executed task, and step S201 is returned.

In a possible implementation, it is possible to adjust the length of the next scheduling period of the current scheduling period under the condition that each task in the current scheduling period has not timed out, and then adjust the length of the next scheduling period based on the adjustment of the next scheduling period. Length determines the time slice allocated for the second task in the next scheduling period.

In this example, if each task does not time out in the current scheduling period, the length of the next scheduling period of the current scheduling period can be reduced to obtain the shortened length of the next scheduling period. For example, a certain duration can be reduced on the basis of the length of the next scheduling period, or the length of the next scheduling period can be multiplied by a certain coefficient to obtain the shortened length of the next scheduling period. Then, the length of the time slice allocated for each second task in the next scheduling period can be determined according to the adjusted length of the next scheduling period. For example, the time allocated for each second task in the next scheduling period can be set The length of the slices is reduced, so that the sum of the lengths of the reduced time slices is equal to the adjusted length of the next scheduling period. According to the length of the reduced time slice of each second task, the time slice allocated for each second task can be further determined, so that when the time slice allocated to the task in the current scheduling period is too long, the next time slice can be automatically reduced The time slice of the second task in the scheduling period, so that the resources of the virtual image processing unit can be effectively used.

In an example, a preset reduction factor may be used to reduce the length of the next scheduling period.

In this example, the reduction factor can be set according to actual application scenarios, and can be set to a real number less than 1, for example, the reduction factor is set to 1/2. When using the reduction factor to reduce the length of the next scheduling period, the length of the next scheduling period can be multiplied by the reduction factor to obtain the reduced length of the next scheduling period. By using an appropriate reduction factor to reduce the length of the next scheduling period, it is possible to avoid an excessively aggressive reduction of the length of the next scheduling period, resulting in the reduced length of the next scheduling period being too small.

In an example, the length of the time slice allocated for each second task in the next scheduling period can be determined based on the adjusted length of the next scheduling period and the service quality parameter corresponding to each second task, so that each The service quality parameter of the second task is maintained at the corresponding preset value and/or the proportion of the time slice of each second task in the next scheduling period is maintained at the corresponding preset value.

In this example, after adjusting the length of the next scheduling period, it can be determined to assign each second task according to the service quality parameter corresponding to each second task in the next scheduling period and the adjusted length of the next scheduling period For example, the service quality parameter corresponding to each second task is multiplied by the adjusted length of the next scheduling period to obtain the length of the time slice allocated by the second task, which is then determined as each second task The time slice of the task allocation, in this way, the service quality parameter of each second task can be kept unchanged, and/or the proportion of the time slice of each second task in the current scheduling period remains unchanged, thereby satisfying Service quality requirements.

Fig. 3 shows an exemplary flow chart of reducing the time slice allocated to a task according to an embodiment of the present disclosure, which may include the following steps.

In step S301, it is judged whether each task in the current scheduling period has timed out.

In step S302, when each task does not time out in the current scheduling period, the length of the next scheduling period is reduced by the reduction coefficient to obtain the reduced length of the next scheduling period.

Step S303: According to the reduced length of the next scheduling period, the time slice allocated for each task in the next scheduling period is reduced.

Step S304: Perform task scheduling in the next scheduling period.

By reducing the time slice of the task, the time slice allocated for each task in the next scheduling period can be automatically reduced when the tasks in the current scheduling period have not timed out, so that the reduced time slice is the same as the one assigned to each task in the next scheduling period. Corresponding service quality is compatible.

In a possible implementation manner, the historical task processing time of multiple task units executing historical tasks within a preset time period can be obtained, and then the initial length of the current scheduling period can be determined according to the statistical information of the historical task processing time.

In this implementation manner, the initial length of the current scheduling period can be determined based on the historical task processing time within a preset time period. The preset time period can be set according to actual application scenarios. For example, the historical task processing time of multiple tasks executing historical tasks in the last 24 hours can be obtained. The statistical information of the historical task processing time may include the information of the historical task, the cumulative frequency of the historical task, etc., and then the initial length of the current scheduling period can be determined based on the statistical information of the historical task processing time. For example, a curve between the processing time of a historical task and the cumulative frequency of the historical task can be determined according to the historical task execution time of multiple tasks, and then an appropriate historical task processing time can be selected according to the curve as the initial length of the current scheduling period.

4 shows a curve of historical task processing time and cumulative frequency according to an embodiment of the present disclosure. In the figure, the abscissa corresponds to the historical task processing time, the unit of the abscissa is ms, and the ordinate corresponds to the cumulative frequency. As shown in Figure 4, the cumulative frequency of 70% corresponds to about 100 ms, which can be understood as the task processing time of 70% of the task units within 100 ms within the preset time period. For example, the historical task processing time corresponding to a cumulative frequency of 70% can be used to determine the initial length of the current scheduling period. Alternatively, the historical task processing time corresponding to a cumulative frequency of 70% can be multiplied by a multiple, for example, the historical task processing time corresponding to a cumulative frequency of 70% can be multiplied by 10 to obtain the initial length of the current scheduling period.

In an example of this implementation manner, the length of the initial time slice allocated for each task can be determined according to the initial length of the current scheduling period and the service quality parameter corresponding to each task in the current scheduling period.

In this example, the initial duration allocated to each task can be calculated according to the service quality parameters corresponding to each task in the current scheduling period and the initial length of the current scheduling period. For example, the current scheduling period includes 3 tasks, task A , Task B and Task C, where the time slice share corresponding to task A is 3, the time slice share corresponding to task B is 3, and the time slice share corresponding to task C is 4, then the initial time slice of task A can be 0.3 The initial duration, the initial time slice of task B can be 0.3 initial duration, and the initial time slice of task C can be 0.4 initial duration. In this way, the initial time slice of each task in a scheduling period can be allocated according to the corresponding service quality parameters to meet the service quality requirements.

In a possible implementation manner, the initial length of the current scheduling period can also be set according to actual application scenarios, for example, the initial length is set to 100 ms. Then the initial length of the current scheduling period and the service quality parameter corresponding to each task in the current scheduling period can determine the initial time slice allocated for each task in the current scheduling period.

The scheduling scheme provided by the embodiments of the present disclosure can automatically adjust the time slice allocated to the task when the length of the time slice allocated to the task is too long or too short, so as to achieve the effect of rationally configuring the time slice of the task .

It can be understood that the various method embodiments mentioned in the present disclosure can be combined with each other to form a combined embodiment without violating the principle and logic. The length is limited, and the details of this disclosure will not be repeated.

In addition, the present disclosure also provides devices, electronic equipment, computer-readable recording media, and programs, all of which can be used to implement any of the scheduling methods provided in the present disclosure. The corresponding technical solutions and descriptions and the corresponding records in the method section will not be repeated. .

Those skilled in the art can understand that in the above-mentioned methods of the specific implementation, the writing order of the steps does not mean a strict execution order but constitutes any limitation on the implementation process. The specific execution order of each step should be based on its function and possibility. The inner logic is determined.

FIG. 5 shows a block diagram of a scheduling device according to an embodiment of the present disclosure. As shown in FIG. 5, the device includes an acquisition module 51, a determination module 52 and an adjustment module 53.

The obtaining module 51 is used to obtain the task processing time of the first task in the current scheduling period.

The determining module 52 is configured to determine whether the first task has timed out based on the task processing time and the first time slice allocated for the first task in the current scheduling period.

The adjustment module 53 is configured to adjust the time slice allocated to at least one second task in the target scheduling period according to the determined result, wherein the target scheduling period includes the current scheduling period or the next one of the current scheduling period The scheduling period.

In one or more optional embodiments, the determining module 52 is specifically configured to determine the first time difference between the deadline of the task processing time and the deadline of the first time slice; In a case where the first time difference is greater than a first time threshold, it is determined that the first task has timed out.

In one or more optional embodiments, the first time threshold is obtained based on the length of the first time slice.

In one or more optional embodiments, the adjustment module 53 is specifically configured to adjust the length of the current scheduling period when it is determined that the first task has timed out; based on the current scheduling period Adjust the adjusted length to adjust the time slice allocated to the at least one second task in the current scheduling period.

In one or more optional embodiments, the adjustment module 53 is specifically configured to adjust the current scheduling based on the adjusted length of the current scheduling period and the service quality parameters of each second task The length of the time slice allocated for each second task in the cycle, so that the service quality parameter of each second task is maintained at the corresponding preset value and/or the time slice of each second task is within The proportion in the current scheduling period remains at the corresponding preset value.

In one or more optional embodiments, the adjustment module 53 is specifically configured to obtain the number of timeouts of the third task in the current scheduling period, where the third task is executed in the current scheduling period Completed tasks; determine an extension coefficient for extending the length of the current scheduling period according to the number of timeouts, wherein the extension coefficient is positively correlated with the number of timeouts; based on the extension coefficient, the The length of the current scheduling period is extended to obtain the adjusted length of the current scheduling period.

In one or more optional embodiments, the extension coefficient is obtained based on an exponential function with the number of timeouts as a variable.

In one or more optional embodiments, the adjustment module 53 is further configured to obtain the task processing time of the third task in the current scheduling period, wherein the at least one second task includes the third Task; in response to the task processing time of the third task being less than the adjusted time slice length of the third task, time compensation is performed on the third task within the current scheduling period.

In one or more optional embodiments, the adjustment module 53 is specifically configured to determine the third task based on the task processing time of the third task and the adjusted time slice length of the third task. The compensation time of the task; based on the compensation time, the compensation task of the third task is added to the scheduling queue of the current scheduling period.

In one or more optional embodiments, the adjustment module 53 is specifically configured to add the compensation task of the third task to the queue of the scheduling queue of the current scheduling period based on the compensation time. tail.

In one or more optional embodiments, the adjustment module 53 is specifically configured to adjust the next scheduling of the current scheduling period when it is determined that each task has not timed out in the current scheduling period. The length of the period; based on the adjusted length of the next scheduling period, determine the time slice allocated for at least one second task in the next scheduling period.

In one or more optional embodiments, the adjustment module 53 is specifically configured to use a preset reduction coefficient to reduce the length of the next scheduling period.

In one or more optional embodiments, the adjustment module 53 is specifically configured to determine the next task based on the adjusted length of the next scheduling period and the service quality parameter of each second task. The length of the time slice allocated for each second task in a scheduling period, so that the service quality parameter of each second task is maintained at the corresponding preset value and/or the time of each second task The proportion of slices in the next scheduling period remains at the corresponding preset value.

In one or more optional embodiments, the device further includes: an initial period determining module, configured to obtain historical task processing time of multiple virtual image processing units executing historical tasks within a preset time period; and The statistical information of the historical task processing time determines the initial length of the current scheduling period.

In some embodiments, the functions or modules contained in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments. For specific implementation, refer to the description of the above method embodiments. For brevity, I won't repeat it here.

An embodiment of the present disclosure also provides an electronic device, including: a processor; a memory used to store executable instructions of the processor; wherein the processor is used to call the instructions stored in the memory to execute the aforementioned scheduling method.

Electronic devices can be provided as terminals, servers, or other types of devices.

Fig. 6 is a block diagram of an electronic device 600 according to an exemplary embodiment. For example, the electronic device 600 may be provided as a server. 6, the electronic device 600 includes a processor 622, which further includes one or more processors, and a memory resource represented by a memory 632 for storing instructions executable by the processor 622, such as application programs. The application program stored in the memory 632 may include one or more modules each corresponding to a set of commands. In addition, the processor 622 is configured to execute instructions to execute the aforementioned scheduling method.

The electronic device 600 may also include a power component 626 configured to perform power management of the electronic device 600, a wired or wireless network interface 650 configured to connect the electronic device 600 to a network, and an input and output (I/O) Interface 658. The electronic device 600 can operate based on an operating system stored in the memory 632, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.

In an exemplary embodiment, a non-volatile computer-readable recording medium is also provided, such as the memory 632 including computer program instructions, which can be executed by the processor 622 of the electronic device 600 to complete the scheduling method.

The present disclosure may be a system, method, and/or computer program product. The computer program product may include a computer-readable recording medium loaded with computer-readable program instructions for enabling the processor to implement various aspects of the present disclosure.

The computer-readable recording medium may be a tangible device that can hold and store instructions used by the instruction execution device. The computer-readable recording medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable recording media (non-exhaustive list) include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable and programmable Read-only memory (EPROM or flash memory), static random access memory (SRAM), CD-ROM, digital multi-function audio-visual disc (DVD), memory card, floppy disk, machinery An encoding device, such as a punch card on which instructions are stored, or a convex structure in a groove, and any suitable combination of the above. The computer-readable recording medium used here is not interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (for example, light pulses through fiber optic cables), or through wires Transmission of electrical signals.

The computer-readable program instructions described here can be downloaded from a computer-readable recording medium to each computing/processing device, or downloaded to an external computer via a network, such as the Internet, a local area network, a wide area network, and/or a wireless network Or external storage device. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge computing servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network, and forwards the computer-readable program instructions to be readable by the computers stored in each computing/processing device In the recording medium.

The computer program instructions used to perform the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, status setting data, or any of one or more programming languages. The source code or the object code written in combination, the programming language includes object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as "C" language or similar programming languages. Computer-readable program instructions can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on the remote computer, or entirely on the remote computer or Execute on the server. In the case of a remote computer, the remote computer can be connected to the user’s computer through any kind of network-including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using the Internet). Internet service provider to connect via the Internet). In some embodiments, the electronic circuit is personalized by using the status information of the computer-readable program instructions, such as programmable logic circuit, field programmable gate array (FPGA) or programmable logic array (PLA), the electronic circuit can be The computer-readable program instructions are executed to realize various aspects of the present disclosure.

Here, various aspects of the present disclosure are described with reference to flowcharts and/or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowchart and/or block diagram and the combination of each block in the flowchart and/or block diagram can be implemented by computer-readable program instructions.

These computer-readable program instructions can be provided to the processors of general-purpose computers, dedicated computers, or other programmable data processing devices, thereby producing a machine that, when executed by the processors of the computer or other programmable data processing devices, A device that implements the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams is produced. It is also possible to store these computer-readable program instructions in a computer-readable recording medium. These instructions make the computer, the programmable data processing device, and/or other equipment work in a specific manner, so that the computer-readable recording medium storing the instructions is It includes an article of manufacture, which includes instructions for implementing various aspects of the functions/actions specified in one or more blocks in the flowchart and/or block diagram.

It is also possible to load computer-readable program instructions onto a computer, other programmable data processing device, or other equipment, so that a series of operation steps are executed on the computer, other programmable data processing device, or other equipment to produce a computer-implemented process , So that the instructions executed on the computer, other programmable data processing device, or other equipment realize the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams.

The flowcharts and block diagrams in the accompanying drawings show the possible implementation architecture, functions, and operations of the system, method, and computer program product according to multiple embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, program segment, or part of an instruction, and the module, program segment, or part of an instruction includes one or more Executable instructions for logic functions. In some alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and/or flowchart, as well as the combination of the blocks in the block diagram and/or flowchart, can use a dedicated hardware-based The system can be implemented, or it can be implemented by a combination of dedicated hardware and computer instructions.

The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Without departing from the scope and spirit of the illustrated embodiments, many modifications and changes are obvious to those of ordinary skill in the art. The choice of terms used herein is intended to best explain the principles, practical applications, or technical improvements of the technologies in the market, or to enable those of ordinary skill in the art to understand the embodiments disclosed herein.

S11~S13, S201~S207, S301~S304: steps 51: Obtain modules 52: Determine the module 53: adjustment module 600: electronic equipment 622: processor 626: Power Components 632: memory 650: network interface 658: input and output interface

Fig. 1 shows a flowchart of a scheduling method according to an embodiment of the present disclosure. Fig. 2 shows an exemplary flow chart of extending the time slice allocated to a task according to an embodiment of the present disclosure. FIG. 3 shows an exemplary flow chart of reducing the time slice allocated to a task according to an embodiment of the present disclosure. FIG. 4 illustrates a curve of historical task processing time and cumulative frequency according to an embodiment of the present disclosure. Fig. 5 shows a block diagram of a scheduling device according to an embodiment of the present disclosure. Fig. 6 shows an exemplary block diagram of an electronic device according to an embodiment of the present disclosure.

S11~S13: steps

Claims (15)

A scheduling method, including: Obtain the task processing time of the first task in the current scheduling period; Determine whether the first task times out based on the task processing time and the first time slice allocated for the first task in the current scheduling period; According to the result of the determination, the time slice allocated to the at least one second task in the target scheduling period is adjusted, where the target scheduling period includes the current scheduling period or the next scheduling period of the current scheduling period. The method according to claim 1, wherein the step of determining whether the first task has timed out based on the task processing time and the first time slice allocated for the first task in the current scheduling period includes : Determining the first time difference between the deadline of the task processing time and the deadline of the first time slice; In a case where the first time difference is greater than a first time threshold, it is determined that the first task has timed out. The method according to claim 2, wherein the first time threshold is obtained based on the length of the first time slice. The method according to any one of claim items 1 to 3, wherein according to the determined result, the step of adjusting the time slice allocated for the at least one second task in the target scheduling period includes: In a case where it is determined that the first task has timed out, adjusting the length of the current scheduling period; Based on the adjusted length of the current scheduling period, adjust the time slice allocated for the at least one second task in the current scheduling period. The method according to claim 4, wherein the step of adjusting the time slice allocated for the at least one second task in the current scheduling period based on the adjusted length of the current scheduling period includes: Based on the adjusted length of the current scheduling period and the service quality parameter of each second task, the length of the time slice allocated for each second task in the current scheduling period is adjusted so that each The service quality parameter of the second task is maintained at a corresponding preset value and/or the proportion of the time slice of each second task in the current scheduling period is maintained at the corresponding preset value. The method according to claim 4 or 5, wherein in a case where it is determined that the first task has timed out, the step of adjusting the length of the current scheduling period includes: Acquiring the number of timeouts of the third task in the current scheduling period, where the third task is a task that has been executed in the current scheduling period; Determining an extension coefficient for extending the length of the current scheduling period according to the number of timeouts, wherein the extension coefficient is positively correlated with the number of timeouts; Based on the extension coefficient, the length of the current scheduling period is extended to obtain the adjusted length of the current scheduling period. The method according to any one of claims 4 to 6, wherein the method further includes: Acquiring the task processing time of the third task in the current scheduling period, where the at least one second task includes the third task; In response to the task processing time of the third task being less than the adjusted time slice length of the third task, time compensation is performed on the third task in the current scheduling period. The method according to claim 7, wherein in response to the task processing time of the third task being less than the adjusted time slice length of the third task, time the third task is performed within the current scheduling period The compensation steps include: Determining the compensation time of the third task based on the task processing time of the third task and the adjusted time slice length of the third task; Based on the compensation time, the compensation task of the third task is added to the end of the scheduling queue of the current scheduling period. The method according to any one of claim items 1 to 3, wherein according to the determined result, the step of adjusting the time slice allocated for the at least one second task in the target scheduling period includes: Adjusting the length of the next scheduling period of the current scheduling period when it is determined that each task in the current scheduling period has not timed out; Based on the adjusted length of the next scheduling period, determine the time slice allocated for the at least one second task in the next scheduling period. The method according to claim 9, wherein the step of adjusting the length of the next scheduling period of the current scheduling period includes: The length of the next scheduling period is reduced by using a preset reduction coefficient. The method according to claim 9 or 10, wherein the step of determining the time slice allocated for the at least one second task in the next scheduling period based on the adjusted length of the next scheduling period includes: Based on the adjusted length of the next scheduling period and the service quality parameter of each second task, the length of the time slice allocated for each second task in the next scheduling period is determined so that each The service quality parameter of each of the second tasks is maintained at the corresponding preset value and/or the proportion of the time slice of each second task in the next scheduling period is maintained at the corresponding preset value. The method according to any one of claims 1 to 11, wherein the method further includes: Obtain the historical task processing time of multiple tasks executing historical tasks within a preset time period; Determine the initial length of the current scheduling period according to the statistical information of the historical task processing time. A scheduling device includes: The obtaining module is used to obtain the task processing time of the first task in the current scheduling period; A determining module, configured to determine whether the first task has timed out based on the task processing time and the first time slice allocated for the first task in the current scheduling period; The adjustment module is configured to adjust the time slice allocated to at least one second task in a target scheduling period according to the determined result, wherein the target scheduling period includes the current scheduling period or the next scheduling of the current scheduling period cycle. An electronic device including: processor; Memory used to store executable instructions of the processor; Wherein, the processor is configured to call instructions stored in the memory to execute the method described in any one of request items 1-12. A computer-readable recording medium has computer program instructions stored thereon, wherein the computer program instructions are executed by a computer to implement the method described in any one of request items 1 to 12.

Images