WO2023246330A1

WO2023246330A1 - Resource adjustment method and apparatus, computing device cluster, and readable storage medium

Info

Publication number: WO2023246330A1
Application number: PCT/CN2023/092337
Authority: WO
Inventors: 李晨; 喻学春; 李刚; 丁文鹏
Original assignee: 华为云计算技术有限公司
Priority date: 2022-06-20
Filing date: 2023-05-05
Publication date: 2023-12-28
Also published as: CN117290083A

Abstract

The present application relates to the technical field of communications, and discloses a resource adjustment method and apparatus, a computing device cluster, and a readable storage medium. The method comprises: obtaining task information of each task in a plurality of tasks, the plurality of tasks comprising a target task and at least one task to be executed; determining a resource adjustment strategy of the target task according to the task information of the plurality of tasks; and when the target task meets a first resource adjustment condition or an instance running the target task meets a second resource adjustment condition, adjusting, on the basis of the resource adjustment strategy of the target task, at least one of the quantity and the specification of the instance for running the target task. According to the method, a plurality of tasks can be comprehensively perceived, and the accuracy of a resource adjustment strategy of a target task determined on the basis of task information of the plurality of tasks is high. The plurality of tasks further comprise a task to be executed. Therefore, when resource adjustment is carried out on the basis of the resource adjustment strategy of the target task, the accuracy of resource adjustment is high.

Description

Resource adjustment method, device, computing device cluster and readable storage medium

This application claims priority to the Chinese patent application with application number 202210695652.6 and the invention title "A load elastic expansion method, device and equipment" submitted on June 20, 2022, the entire content of which is incorporated into this application by reference. For example; this application also claims priority for the Chinese patent application with application number 202211013518. The entire contents of which are incorporated herein by reference.

Technical field

The present application relates to the field of communication technology, and in particular, to a resource adjustment method, device, computing device cluster and readable storage medium.

Background technique

Cloud is a technology that provides users with software and hardware resources in the form of the Internet. For example, the cloud provides users with resources that match the business needs based on the user's business needs. Since the user's business needs may change, a resource adjustment method is needed so that when the business needs change, the resources provided for the business needs can be increased or decreased accordingly to achieve re-adaptation of resources and business needs. .

In related technologies, indicators such as central processing unit (CPU) usage, memory usage, disk read and write rates, and traffic inflow/outflow rates are monitored; when a certain indicator is monitored to meet the triggering conditions, the current The resources no longer match the business needs, and the resources are increased or decreased according to a fixed value.

However, since each of the above indicators represents the current resource occupancy, when an indicator meets the trigger condition, it means that business needs have changed, and the accuracy of adjusting resources based on the current resource occupancy is low.

Contents of the invention

This application proposes a resource adjustment method, device, computing device cluster and readable storage medium to improve the accuracy of resource adjustment.

In a first aspect, a resource adjustment method is provided, which method includes: obtaining task information for each of multiple tasks, which includes a target task and at least one to-be-executed task; according to the multiple tasks The task information of the target task is determined to determine the resource adjustment strategy of the target task; when the target task satisfies the first resource adjustment condition, or the instance running the target task satisfies the second resource adjustment condition, adjust the resource adjustment strategy of the instance used to run the target task based on the resource adjustment strategy. At least one of quantity and specification. This method can comprehensively perceive the multiple tasks, and determine the resource adjustment strategy for the target task based on the task information of the multiple tasks with high accuracy. The multiple tasks also include tasks to be executed. Therefore, when resource adjustment is performed based on the resource adjustment strategy of the target task, the accuracy of resource adjustment is higher.

In a possible implementation, the method further includes: receiving a user-configured resource update limit, where the resource update limit includes at least one of a maximum cost and a maximum number of instances running the target task; adjusting the strategy based on the resource Adjusting at least one of the number and specifications of the instances used to run the target task includes: adjusting at least one of the number and specifications of the instances used to run the target task based on the resource adjustment policy and the resource update limit. . By using based on Adjust resources according to user-configured resource update restrictions to ensure that the adjusted resources meet user needs.

In a possible implementation manner, the target task satisfies the first resource adjustment condition, including: the expected execution time of the target task is greater than the reference execution time of the target task. For example, the instance running the target task satisfies the second resource adjustment condition, including: the CPU usage of the instance running the target task is higher than the usage threshold. Situations that trigger execution of at least one of adjusting the number and specifications of instances used for a target task based on a resource adjustment policy are diverse, and this method can be applicable to a variety of situations.

In a possible implementation, the target task is a task to be executed or a task being executed. The execution of tasks used by this method is relatively diverse.

In a possible implementation, the task information includes resource occupancy and resource occupancy duration. Therefore, this method can obtain more accurate resource occupancy status and improve the accuracy of determining the resource adjustment strategy for the target task.

In a possible implementation, determining the resource adjustment strategy of the target task based on the task information of multiple tasks includes: calculating the resource requirements of the target task based on the task information of the multiple tasks and the reference execution time of the multiple tasks; According to the resource requirements of the target task and the amount of available resources of the target task, the resource adjustment strategy of the target task is determined. The resource adjustment strategy is used to make the adjusted amount of available resources of the target task meet the resource requirements of the target task. By calculating the resource requirements of the target resources, this method can sense in advance the amount of resources required to complete the target task. When resource adjustment is required, the time required from sensing the need for resource adjustment to completing the resource adjustment is shorter in this method, thereby reducing the time required for resource adjustment and improving the efficiency of resource adjustment.

In a possible implementation, the method further includes: calculating the expected execution time of the target task based on the initial resource amount and task information of the multiple tasks. Therefore, when the expected execution time of the target task is greater than the reference execution time of the target task, the resource adjustment strategy based on the target task can be triggered to perform resource adjustment so that the expected execution time of the target task does not exceed the reference execution time of the target task. .

In a possible implementation, obtaining the task information of multiple tasks includes: obtaining the task type of each task in the multiple tasks; based on the task type of each task, querying the corresponding relationship between the task type and the task information, and obtaining each Task information of the task, where the correspondence between the task type and the task information is obtained based on the configuration information of the task type and task information. By querying the corresponding relationship between task types and task information based on each task type, the task information of each task is obtained. This method obtains task information in a simpler and more efficient manner.

In a possible implementation manner, obtaining task information of multiple tasks includes: obtaining the task type of each task in the multiple tasks; obtaining the task information of each task based on the historical execution information corresponding to each task type.

In a possible implementation, the task type is any one of obtaining metadata, slicing, transcoding, or merging.

In a second aspect, a resource adjustment device is provided, which device includes:

The acquisition unit is used to acquire task information of multiple tasks. The multiple tasks include a target task and at least one task to be executed. The task information includes task information of each task;

The determination unit is used to determine the resource adjustment strategy of the target task based on the task information of multiple tasks;

An adjustment unit configured to adjust at least one of the number and specifications of instances used to run the target task based on the resource adjustment policy when the target task satisfies the first resource adjustment condition, or the instance running the target task satisfies the second resource adjustment condition. kind.

In a possible implementation, the device further includes: a receiving unit configured to receive user-configured resource update limits, where the resource update limits include at least one of a maximum cost and a maximum number of instances running the target task; adjust Unit used to adjust the number and size of instances used to run target tasks based on the resource adjustment policy and the resource update limit. at least one of the grids.

In a possible implementation manner, the target task satisfies the first resource adjustment condition, including: the expected execution time of the target task is greater than the reference execution time of the target task.

In a possible implementation manner, the instance running the target task satisfies the second resource adjustment condition, including: the CPU usage of the instance running the target task is higher than the usage threshold.

In a possible implementation, the target task is a task to be executed or a task being executed.

In a possible implementation, the task information includes resource occupancy and resource occupancy duration.

In a possible implementation, the determination unit is used to calculate the resource requirements of the target task based on the task information of the multiple tasks and the reference execution time of the multiple tasks; based on the resource requirements of the target task and the amount of available resources of the target task , determine the resource adjustment strategy of the target task, which is used to make the adjusted available resource amount of the target task meet the resource requirements of the target task.

In a possible implementation, the device further includes: a calculation unit configured to calculate the expected execution time of the target task based on the initial resource amount and task information of the multiple tasks.

In a possible implementation, the acquisition unit is used to obtain the task type of each task in multiple tasks; based on the task type of each task, query the correspondence between the task type and task information to obtain the task information of each task, The correspondence between the task type and task information is obtained based on the configuration information of the task type and task information.

In a possible implementation manner, the acquisition unit is used to obtain the task type of each task in multiple tasks; and obtain the task information of each task based on the historical execution information corresponding to each task type.

In a third aspect, a computing device cluster is provided. The computing device cluster includes at least one computing device. Each computing device includes a processor and a memory; the processor of the at least one computing device is used to execute a program stored in the memory of the at least one computing device. Instructions are provided to cause the computing device cluster to execute any one of the resource adjustment methods of the first aspect.

In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium includes computer program instructions. When the computer program instructions are executed by a computing device cluster, the computing device cluster executes any of the resources of the first aspect. Adjustment method.

In a fifth aspect, a communication device is provided, which includes: a transceiver, a memory, and a processor. Wherein, the transceiver, the memory and the processor communicate with each other through an internal connection path, the memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to control the transceiver to receive signals and control the transceiver to send signals. , and when the processor executes the instruction stored in the memory, the processor is caused to execute any resource adjustment method in the first aspect.

For example, there are one or more processors and one or more memories.

For example, the memory may be integrated with the processor, or the memory may be provided separately from the processor.

In the specific implementation process, the memory can be a non-transitory memory, such as a read-only memory (ROM), which can be integrated on the same chip as the processor, or can be set in different On the chip, this application does not limit the type of memory and the arrangement of the memory and the processor.

A sixth aspect provides a computer program product containing instructions, which when executed by a computing device cluster, causes the computing device cluster to execute any of the resource adjustment methods of the first aspect.

In a seventh aspect, a chip is provided, including a processor for calling and running instructions stored in the memory, so that at least one computing device installed with the chip executes any resource adjustment method in the first aspect. .

Exemplarily, the chip also includes: an input interface, an output interface and the memory, the input interface, the output interface, a processing The processor and memory are connected through internal connection paths.

It should be understood that the beneficial effects achieved by the technical solutions of the second to seventh aspects of the present application and their corresponding possible implementations can be referred to the above-mentioned technical effects of the first aspect and their corresponding possible implementations, No further details will be given here.

Description of the drawings

Figure 1 is a schematic diagram of the implementation environment of a resource adjustment method provided by an embodiment of the present application;

Figure 2 is a schematic diagram of the implementation environment of another resource adjustment method provided by an embodiment of the present application;

Figure 3 is a flow chart of a resource adjustment method provided by an embodiment of the present application;

Figure 4 is a schematic diagram of an arrangement result provided by an embodiment of the present application;

Figure 5 is a schematic process diagram of a resource adjustment method provided by an embodiment of the present application;

Figure 6 is a schematic diagram of a resource arrangement process provided by an embodiment of the present application;

Figure 7 is a schematic diagram of the CPU usage of a container provided by an embodiment of the present application;

Figure 8 is a schematic diagram of the completion time of a transcoding task provided by an embodiment of the present application;

Figure 9 is a schematic structural diagram of a resource adjustment device provided by an embodiment of the present application;

Figure 10 is a schematic structural diagram of a computing device provided by an embodiment of the present application;

Figure 11 is a schematic structural diagram of a computing device cluster provided by an embodiment of the present application;

Figure 12 is a schematic structural diagram of another computing device cluster provided by an embodiment of the present application.

Detailed ways

The terms used in the embodiments of the present application are only used to explain the embodiments of the present application and are not intended to limit the present application. In order to make the purpose, technical solutions and advantages of the present application clearer, the embodiments of the present application are described below in conjunction with the accompanying drawings.

Cloud is a technology that provides users with software resources and virtual hardware resources in the form of the Internet by virtualizing physical hardware resources. For ease of explanation, software resources and virtual hardware resources are simply called resources. The cloud can provide users with resources that are suitable for the business based on their business needs. Specifically, resources include computing resources, network resources, storage resources, etc. Among them, taking computing resources as an example, computing resources include virtual machines, containers and bare metal servers. It should be noted that this application does not limit the specific types of resources. Since the user's business needs may change, the cloud needs to adjust the resources provided according to the changed business needs so that the adjusted resources can be re-adapted to the changed business needs. Among them, the resource adjustment method can be used to adjust the provided resources according to the changed business needs. Resource adjustment is performed by increasing or decreasing resources. The resource adjustment method can also be called the auto scaling (AS) method of resources.

In related technologies, for unplanned and irregular business needs, by configuring trigger conditions for indicators such as CPU usage, memory usage, disk read and write rates, and traffic inflow/outflow rates, the above indicators are monitored to achieve Resource adjustment. For example, when it is monitored that one of the above indicators meets the triggering condition, it is determined that the current resources are no longer suitable for the business needs, and the resources are increased or decreased according to a fixed value to realize resource adjustment. Among them, unplanned and irregular business needs may refer to business needs in scenarios characterized by large amounts of concurrent tasks, sudden tasks, and unpredictable tasks. The above scenarios include but are not limited to offline video transcoding scenarios or news service scenarios.

Each indicator monitored in the related technology indicates the current resource occupancy. In other words, the related technology is in the business Only after the tasks corresponding to the requirements have been executed by the corresponding resources can the above indicators be monitored, and then when a certain indicator meets the triggering condition, resource adjustment is triggered. However, when an indicator meets the triggering condition, it means that the business demand has changed. There will be a certain delay in the time point when the resource adjustment is triggered compared with the time point when the business demand changes. The resource adjustment is based on the current resource occupancy. Adjustments are made less accurately. Furthermore, since it takes a certain amount of time to complete resource adjustment, the time from the change in business requirements to the re-adaptation of resources and business needs in related technologies is long, and the adjustment efficiency is low.

The embodiment of the present application provides a resource adjustment method, which can improve the accuracy of resource adjustment. Illustratively, the method can be applied to the implementation environment shown in Figure 1. Referring to Figure 1, the implementation environment includes but is not limited to the first module 101, the second module 102, the third module 103, the fourth module 104, the fifth module Module 105, sixth module 106 and seventh module 107. The first module 101 is communicatively connected with the second module 102 and the sixth module 106 respectively. The second module 102 is also communicatively connected with the third module 103, the fourth module 104 and the fifth module 105. The third module 103 and the fifth module 105 Communication connection: the fourth module 104 is communicatively connected with the fifth module 105, and the sixth module 106 is also communicatively connected with the fifth module 105 and the seventh module 107. Each module of the communication connection can exchange information, and the communication connection can be implemented based on a wired network or a wireless network, which is not limited in the embodiments of the present application.

For example, the sixth module 106 is used to obtain the tasks to be executed stored in the seventh module 107, and the sixth module 106 is also used to obtain the tasks being executed in the fifth module 105 and the amount of available resources in the fifth module 105. , the resources corresponding to the amount of available resources are used to run tasks. The sixth module 106 is also configured to report the acquired task and the amount of available resources of the task to the first module 101 . The first module 101 is used to obtain the task information and reference execution duration of the task, determine the resource requirements of the task based on the obtained task information and reference execution duration, and determine the resource adjustment strategy of the task based on the task's resource requirements and the amount of available resources. The first module 101 is also used to adjust the amount of available resources for the task based on the resource adjustment policy of the task, or to send a control instruction to the second module 102 that manages resources, so that the second module 102 adjusts the amount of resources for the task based on the control instruction. The amount of available resources is adjusted. The second module 102 is also used to obtain the backup resources in the third module 103 and the configuration information stored in the fourth module 104, and configure the backup resources based on the configuration information to generate new available resources, thereby realizing the optimization of available resources. Quantity adjustment.

Figure 2 is a schematic diagram of the implementation environment of another resource adjustment method provided by an embodiment of the present application. As shown in FIG. 2 , the first module 101 may be a task resource control module, and the task resource module is used to implement the functions of the first module 101 . The second module 102 may be a control center, which is used to implement the functions of the second module 102 . The third module 103 is a node pool, which includes at least one node, and one node is a spare resource. The fourth module 104 is an image warehouse, which is used to store at least one image, and one image is the configuration information of an execution program. The fifth module 105 is a workload (deployment). The workload includes at least one node that has been configured based on the configuration information. Each configured node includes at least one instance. The resources provided by this instance are the available resources corresponding to the tasks to be executed, and the available resources are used to run the tasks to be executed. Instances of different specifications provide different resources. Exemplarily, the instance includes at least one of a physical host, a virtual machine, or a container (pod). The sixth module 106 is a cloud monitoring module. The cloud monitoring module is used to implement the functions of the sixth module 106. That is, the cloud monitoring module is used to obtain the tasks to be executed stored in the seventh module 107 and the tasks stored in the fifth module 105. The task being executed and the amount of available resources for the task in the fifth module 105. The seventh module 107 is a task queue, which is used to store tasks to be executed.

Each module shown in the above-mentioned FIG. 1 and FIG. 2 may be included in one device or multiple devices. For example, see Figure 2, the task resource control module, control center, node pool, mirror warehouse, workload and cloud monitoring are all included in the cloud container engine. This task queue is included in other devices besides the cloud container engine. Furthermore, in the implementation environment shown in Figures 1 and 2, each Each module is divided only by function and is not used to limit the implementation of each module. Each module can be merged based on needs. For example, in the implementation environment shown in FIG. 1 , the sixth module 106 can be merged with the first module 101 so that the first module 101 has the function of the sixth module 106 . That is to say, the first module 101 can obtain the tasks to be executed stored in the seventh module 107, and can also obtain the tasks being executed in the fifth module 105 and the amount of available resources for the tasks in the fifth module 105.

It can be understood that each of the above implementation environments may include multiple modules, which is not limited in the embodiments of the present application. Moreover, the number of tasks, the number of instances, the number of nodes, and the number of mirrors shown in Figure 2 are only for illustration, and the embodiments of the present application are not limited thereto.

The resource adjustment method provided by the embodiment of the present application can be shown in Figure 3. Next, the method will be described with reference to the implementation environment shown in Figure 1 or Figure 2. Exemplarily, the method is applied to at least one computing device. Each module shown in Figure 1 or Figure 2 may be included in one computing device, or may be included in multiple computing devices respectively. As shown in Figure 3, the method includes but is not limited to S301 to S303.

S301. Obtain task information of multiple tasks. The multiple tasks include a target task and at least one task to be executed. The task information includes task information of each task.

S301 may be executed by the first module. In a possible implementation, before obtaining the task information of multiple tasks, the method further includes: obtaining at least one task flow based on business requirements, and any task flow includes at least one subtask; obtaining each task included in the at least one task flow. Among the subtasks, the unexecuted subtasks and/or the subtasks that are being executed are obtained, and multiple tasks are obtained based on the obtained subtasks.

The business requirement may be a parent task issued by the user, and the first module may split the parent task issued by the user into at least one sub-task, and use the at least one sub-task as an acquired task stream. For example, splitting the parent task delivered by the user means splitting the parent task delivered by the user according to at least one execution stage of the parent task to obtain at least one subtask, and one subtask corresponds to one execution stage. When the user delivers multiple parent tasks, the first module can separate the multiple parent tasks delivered by the user to obtain multiple task streams, and any task stream includes at least one task. Furthermore, since the task flow is obtained by splitting the parent task according to at least one execution stage of the parent task, at least one sub-task belonging to the same task flow can have a logical execution sequence.

The embodiments of the present application do not limit the method of obtaining the unexecuted subtasks and/or the currently executing subtasks among the subtasks included in at least one task flow. For example, the first module is the task resource control module shown in Figure 2. The task resource control module sends a first request to obtain unexecuted tasks to the task queue through the cloud monitoring module, and receives the task queue returned in response to the first request. Subtasks that have not been executed. The task resource control module also sends a second request to obtain the executing subtask to the workload through the cloud monitoring module, and receives the executing subtask returned by the workload in response to the second request. The cloud monitoring module can also actively send unexecuted subtasks and/or subtasks that are being executed to the task resource control module. In this embodiment, the cloud monitoring module does not actively send unexecuted subtasks and/or subtasks to the task resource control module. Or limit the timing of the subtask being executed.

In one possible implementation, obtaining multiple tasks based on the obtained subtasks includes: based on the task type of each subtask, subtasks of the same task type are treated as one task to obtain multiple tasks; where, for the Any task among multiple tasks, if any task only includes subtasks to be executed, this any task is a task to be executed; if any task includes subtasks that are being executed, any task is being executed. tasks to perform. For example, when the number of subtasks of a certain task type is one, the subtask is the obtained task of the task type. The obtained target task among the multiple tasks may be a task to be executed or a task being executed among the multiple tasks. appoint Service types include but are not limited to any of obtaining metadata, slicing, transcoding, or merging.

The embodiment of the present application does not limit the task type of obtaining a subtask. For example, the task type of a subtask can be obtained through the following obtaining task type method 1 and obtaining task type method 2.

The first way to obtain the task type is to send a request to the module that stores the task type of the subtask, and receive the task type of the subtask sent by other modules in response to the request.

Taking the implementation environment shown in Figure 1 as an example, the first module may send a third request to the seventh module that stores at least one subtask to be executed. The third request is used to request to obtain the task type of each subtask to be executed. , receiving the task type of each sub-task to be executed returned by the seventh module in response to the third request. The first module may also send a fourth request to the fifth module for executing the subtask, the fourth request is used to request to obtain the task type of the subtask being executed, and receive the currently executing subtask returned by the fifth module in response to the fourth request. The task type of the subtask being executed.

The second method of obtaining the task type is to obtain the task types of multiple subtasks by receiving the task types of each subtask actively sent by the module that stores the task type.

Still taking the implementation environment shown in Figure 1 as an example, the first module can receive the task type of each sub-task to be executed actively sent by the seventh module. For example, when the seventh module sends at least one subtask to be executed to the first module, it also sends the task type of each subtask to be executed to the first module. The first module may also receive the task type of the subtask being executed actively sent by the fifth module. For example, when the fifth module sends the subtask being executed to the first module, it also sends the task type of the subtask being executed to the first module.

In a possible implementation, based on the obtained multiple tasks, the task information and reference execution time of the multiple tasks are obtained. The first module for executing S301 also obtains the amount of available resources of the target task. The embodiments of this application do not limit the order in which task information, reference execution duration, and available resources are obtained. Next, the process of obtaining task information, reference execution time, and available resources is explained respectively.

Methods of obtaining task information for multiple tasks include but are not limited to the following method 1 of obtaining task information and method 2 of obtaining task information.

The first method of obtaining task information is to obtain the task type of each task in multiple tasks; based on the historical execution information corresponding to each task type, obtain the task information of each task.

For example, for any task type, the historical execution information corresponding to the any task type includes the resource occupancy amount and resource occupancy duration for completing at least one sub-task of the any task type. For example, for any task type, obtain the resource occupancy and resource occupancy time for completing multiple subtasks of any task type, and use the average value of the resource occupancy for completing the multiple subtasks as the corresponding value for any task type. The average resource occupancy time for completing the multiple subtasks is used as the resource occupancy time corresponding to any task type. The resource occupancy and resource occupancy duration corresponding to any task type can be used as the task information of the sub-tasks of any task type, so that the task information of each sub-task can be obtained based on the task type of each sub-task. Task information, get the task information of each task.

For example, when the task information of a sub-task includes resource occupancy and resource occupancy duration, for any task, the resource occupancy of each sub-task included in the any task is added to obtain the resources of any task. Occupancy, add the resource occupancy time of each sub-task to get the resource occupancy time of any task.

That is to say, for any one of the multiple tasks, the task information of any one of the tasks includes but is not limited to the resource occupancy amount and the resource occupancy duration. The resource occupancy of any task refers to the amount of available resources required to execute the task. The resource occupancy time of any task refers to the time the available resources are occupied when executing the task. long. For example, when any task includes multiple subtasks, the task information of any task includes but is not limited to the resource occupancy amount and resource occupancy duration of each subtask included in the any task. As a result, a more accurate resource occupancy situation can be obtained, thereby achieving more accurate resource adjustment.

The second method of obtaining task information is to obtain the task type of each task in multiple tasks; based on the task type of each task, query the corresponding relationship between the task type and the task information, and obtain the task information of each task, where the relationship between the task type and the task information is The corresponding relationship is obtained based on the configuration information of task type and task information. Since each task includes subtasks of the same type, the task type of each task can be obtained by obtaining the task type of the subtask of each task. After obtaining the task type of each task, the corresponding relationship between the task type and task information can be queried based on the task type of each task, and the task information of each task can be obtained.

The corresponding relationship between the task type and the task information may be generated based on the obtained configuration information. For example, before obtaining the task information of multiple tasks, the method further includes: obtaining the task type and configuration information of the task information; and generating a correspondence between the task type and the task information based on the task type and the configuration information of the task information.

In one possible implementation, the user configures parent task information for the parent task. Parent task information includes but is not limited to the resource usage and resource usage duration of the parent task. The resource occupancy of the parent task refers to the amount of available resources required to execute the parent task, and the resource occupancy time of the parent task refers to the time the available resources are occupied when the parent task is executed. Configuration information of task type and task information is generated based on the parent task information. For example, according to at least one execution stage of the parent task, the parent task is split into at least one subtask, one subtask corresponds to one execution stage, and one execution stage corresponds to one task type; based on the parent task information and the task type of each subtask , configure task information for subtasks of each task type.

For example, when the parent task information includes the resource occupancy amount and resource occupancy duration of the parent task, based on the parent task information and the task type of each sub-task, configure task information for the sub-tasks of each task type, including: changing the parent task The resource occupancy and resource occupancy time of the task are split according to the task type, and the resource occupancy and resource occupancy time of each sub-task are obtained. The resource occupancy of a subtask refers to the amount of available resources required to execute the subtask, and the resource occupancy time of the subtask refers to the time the available resources are occupied when executing the subtask.

The embodiments of this application do not limit the method of splitting the resource occupancy and resource occupancy duration of the parent task according to the task type. For example, each task type has a weight factor, and the resource usage and resource usage duration of the parent task are split according to the weight factor of each task type. The information generated when configuring task information for subtasks of each task type is called configuration information of the task type and task information. Of course, users can also directly configure task information for subtasks of each task type. In this case, the configuration information of task type and task information is the information generated when the user configures task information for subtasks of each task type. By obtaining the configuration information of the task type and task information, the corresponding relationship between the task type and the task information can be generated.

Exemplarily, the correspondence between the task type and the task information is stored in advance in the first module for performing S301. That is to say, after the first module obtains the task type of each task, it can directly query the corresponding relationship between the stored task type and task information to obtain the task information of each task. In the method provided by the embodiment of the present application, the method of obtaining the correspondence between the task type and the task information is relatively flexible. The task information of each task is obtained by querying the corresponding relationship between the task type and the task information, and the efficiency of obtaining the task information is high.

After obtaining the task type of each task and the corresponding relationship between the task type and task information, the task type based on each task can be executed, the corresponding relationship between the task type and task information can be queried, and the task information of each task can be obtained. The process may include: for any subtask included in any task, query the correspondence between the task type and task information based on the task type of any subtask, and obtain the task information of any subtask; based on the task type of any subtask Tasks include The task information of each sub-task is obtained to obtain the task information of any task. The method of obtaining the task information of any task is the same as the related content in method 1 of obtaining the task information, and will not be described again here.

In a possible implementation, the first module for executing S301 stores the reference execution time of subtasks of each task type. The reference execution time of a subtask refers to the time from starting to execute the subtask to completing the subtask. Reference duration. For any task type, the reference execution time of subtasks of any task type can be set based on experience or actual needs, or can be obtained based on the historical execution time of subtasks of any task type. The historical execution time of the sub-task of any task type refers to the execution time of the first module to complete the sub-task of any task type under historical circumstances. For example, the first module obtains the historical execution duration of multiple subtasks of any task type, and uses the average of the multiple historical execution durations as the reference execution duration of the subtasks of any task type.

The first module may obtain the reference execution time of each task based on the reference execution time of subtasks of each task type. For example, for any acquired task, the first module obtains the reference execution time of any task based on the number of subtasks included in the any task and the reference execution time of the subtask. The reference execution time of any task refers to the reference time from the start of execution to the completion of any task.

In a possible implementation manner, the first module also obtains the amount of available resources for the target task, and the amount of available resources is the amount of available resources used to complete the target task. Obtaining the amount of resources available for the target task includes: determining the amount of unoccupied resources in the reference resource amount, and using the unoccupied resource amount as the amount of available resources for the target task. The amount of reference resources is the amount of available resources used to complete the business requirements. Resources. That is, the reference resource amount is the available resource amount used to complete the parent task issued by the user. The reference resource amount can be set by users according to their business needs. For example, in the case where the available resources are resources provided by the instance, the amount of available resources is the amount of resources provided by the instance. For example, in the implementation environment shown in Figure 2, available resources for completing business requirements include resources provided by Instance 1 to Instance 4 in Node 1, and resources provided by Instance 1 to Instance 4 in Node 2. Reference resources The amount is the amount of resources provided by 8 instances. When none of these eight instances are occupied, the resources provided by these eight instances are all available resources for the target task, and the amount of resources available for the target task is the amount of resources provided by the eight instances.

For example, if an available resource is executing a subtask, the available resource is occupied. Since the subtask being executed will be completed after a period of time, the occupied available resources can become unoccupied available resources after the subtask is completed. In other words, at different points in time, the amount of available resources for the target task can be different. For example, at the point in time when the operation of obtaining the available resource amount of the target task is performed, some available resources are being occupied, then the available resource amount of the target task is the difference between the reference resource amount and the occupied available resource amount. After a period of time, the subtasks in the occupied available resources are completed and there are no occupied available resources. In this case, the amount of available resources of the target task is equal to the amount of reference resources. In a possible implementation, when obtaining the amount of available resources of the target task, you can obtain the unused resources corresponding to each time point within the first execution duration from the time point when the operation of obtaining the amount of available resources of the target task is performed. The amount of available resources occupied is the amount of unoccupied available resources corresponding to each time point as the amount of available resources for the target task at each time point. The first execution time is greater than or equal to the reference execution time of the target task.

S302: Determine the resource adjustment strategy for the target task based on the task information of multiple tasks.

S302 may be executed by the first module. For example, determining the resource adjustment strategy of the target task based on the task information of multiple tasks includes S3021 and S3022.

S3021: Calculate the resource requirements of the target task based on the task information of multiple tasks and the reference execution time of multiple tasks.

In one possible implementation, calculating the resource requirements of the target task based on the task information of multiple tasks and the reference execution duration of the multiple tasks includes: calculating the target task based on the initial resource amount and the task information of the multiple tasks. The expected execution time of the target task; based on the relationship between the expected execution time of the target task and the reference execution time of the target task, the initial The resource amount is adjusted so that the calculated expected execution time of the target task is no longer than the reference execution time of the target task; the resource requirements of the target task are obtained based on the adjusted initial resource amount.

The initial resource amount may be the available resource amount of the target task or a preset available resource amount. For example, if the amount of available resources of the target task at each point in time during the first execution duration is different, the initial amount of resources can be the maximum value of the amount of available resources of the target task at each point in time, that is, the initial amount of resources. The resource amount can be equal to the reference resource amount. The expected execution time of a target task refers to the expected time from the start of execution to the completion of the target task.

Based on the content of S301 mentioned above, it can be seen that the task information may include resource occupancy and resource occupancy duration. In one possible implementation, the expected execution time of the target task is calculated based on the initial resource amount and the task information of multiple tasks, including: arranging resources for each task based on the resource occupancy and resource occupancy time of each task. Distribution, calculate the expected execution time of the target task based on the arrangement results; wherein the total amount of resource occupancy corresponding to each time point within the expected execution time does not exceed the initial resource amount, and the proportion of resource occupancy corresponding to each time point is greater than or equal to Threshold, the resource occupancy ratio refers to the ratio of the total amount of resource occupancy to the initial resource amount.

In one possible implementation, arranging resources for each task based on the resource occupancy and resource occupancy duration of each task means: on a two-dimensional plane with the resource amount and time as the coordinate axes, based on the resource occupancy of each task. Resource occupancy and resource occupancy duration are used to arrange resources for each task; and when arranging resources for each task, the total amount of resource occupancy corresponding to each time point does not exceed the initial resource amount, and the resource occupancy corresponding to each time point is The ratio is greater than or equal to the threshold. The threshold can be set based on experience or actual needs, which is not limited in the embodiments of this application. For example, the threshold is 0.5.

Since when arranging resources for each task, the total amount of resource occupancy corresponding to each time point does not exceed the initial resource amount, and the resource occupancy ratio is greater than or equal to the threshold. This resource arrangement method can make the resource occupancy not exceed the initial resource amount. In this case, the resource utilization rate is higher. Furthermore, by arranging resources based on the resource occupancy and resource occupancy duration of each task on a two-dimensional plane with the resource amount and time as the coordinate axes, more accurate planning of resources in the time domain can be achieved, and we get The resource requirements of the target tasks are more accurate.

For example, for any one of the multiple tasks, the any task includes one or more subtasks, and arranging resources for any one of the tasks means arranging resources for each of the subtasks included in any of the tasks. cloth. The process of arranging resources for each sub-task is the same as the above-mentioned resource arrangement for each task, and will not be described again here. For example, the multiple subtasks included in the multiple tasks have an execution order, and arranging resources for each subtask included in the multiple tasks includes: arranging resources for each subtask according to the execution order of each subtask. The execution order of each sub-task can be determined based on the order of each sub-task in the task flow, which is not limited in the embodiments of the present application.

After obtaining the expected execution time of the target task, the initial resource amount is adjusted based on the relationship between the expected execution time of the target task and the reference execution time of the target task, and then the resource requirements of the target task are obtained, including but Not limited to the following situations A and B.

In case A, the expected execution time of the target task is greater than the reference execution time of the target task.

In a possible implementation manner, if the expected execution time of the determined target task is greater than the reference execution time of the target task, it means that the initial resource amount is insufficient and the initial resource amount needs to be increased. That is to say, when the expected execution time of the target task is greater than the reference execution time of the target task, the initial resource amount is adjusted by increasing the resource amount.

Afterwards, based on the increased initial resource amount and the task information of multiple tasks, the expected execution time of the target task is calculated. If the calculated expected execution time of the target task is still greater than the reference execution time of the target task, the increased initial resource amount is increased again until the calculated based on the increased initial resource amount and task information of multiple tasks. The target Until the expected execution time of the task is no longer than the reference execution time of the target task, the increased initial resource amount at this time will be regarded as the resource requirement of the target task.

In case B, the expected execution time of the target task is not greater than the reference execution time of the target task.

For example, if the expected execution time of the target task is not greater than the reference execution time of the target task, the initial resource amount may not be adjusted, and the initial resource amount may be used as the resource requirement of the target task. Of course, in this case, the initial resource amount can also be adjusted. For example, in response to the expected execution time of the target task being no greater than the reference execution time of the target task, the initial resource amount is reduced. Based on the reduced initial resource amount and task information of multiple tasks, the expected execution time of the target task is calculated. If the expected execution time of the target task calculated based on the reduced initial resource amount and task information of multiple tasks is still not greater than the reference execution time of the target task, the reduced initial resource amount can be reduced again, Until the calculated expected execution time of the target task is greater than the reference execution time of the target task. Obtain the last resource amount that satisfies the expected execution time of the target task and is not greater than the reference execution time of the target task, and use the obtained resource amount as the resource requirement of the target task. That is to say, the amount of resources corresponding to the resource requirement is the minimum amount of resources that can satisfy the calculated expected execution time of the target task, which is not greater than the reference execution time of the target task. Therefore, when the resource amount is used as the resource requirement, the resource amount used to execute the target task can be made smaller, thereby saving resources.

In one possible implementation, it will take a certain amount of time to complete the resource adjustment. If the initial resource amount needs to be adjusted, the initial resource amount corresponding to the time point after the time period is adjusted. After completing the adjustment of the initial resource amount, perform the resource arrangement operation. The process of completing resource adjustment will be explained later and will not be introduced here. For example, the time point when it is determined that the initial resource amount needs to be adjusted is called the first time point, and the time required to complete the resource adjustment is called the scaling duration. After the initial resource amount is adjusted, resources are arranged for multiple tasks. The obtained arrangement results can be shown in Figure 4. In the arrangement result shown in Figure 4, the initial resource amount is adjusted by increasing the resource amount.

S3022: Determine a resource adjustment strategy for the target task based on the resource requirements of the target task and the amount of available resources of the target task. The resource adjustment strategy is used to make the adjusted amount of available resources of the target task meet the resource requirements of the target task.

For example, when the resource requirements of the target task are greater than the amount of available resources of the target task, the resource adjustment strategy for the target task is determined to increase the amount of available resources of the target task, so that the increased amount of available resources of the target task is not less than Resource requirements for the target task. The resource adjustment strategy may also include the difference between the resource demand and the available resource amount. That is, the resource adjustment strategy of the target task is to increase the target task according to the difference between the resource demand of the target task and the available resource amount of the target task. the amount of available resources.

For example, when the resource requirement of the target task is less than the amount of available resources of the target task, the resource adjustment strategy of the target task is determined to reduce the amount of available resources of the target task, and the reduced amount of available resources of the target task is not less than the target The resource requirements of the task. The resource adjustment strategy may also include the difference between the amount of available resources and the resource demand. That is, the resource adjustment strategy for the target task is to reduce the target task according to the difference between the amount of available resources for the target task and the resource demand for the target task. the amount of available resources. When the resource requirement of the target task is less than the available resource amount of the target task, the available resource amount of the target task can also be kept unchanged, as long as the available resource amount of the target task is not less than the available resource amount of the target task.

Of course, the resource requirements of the target task can also be equal to the amount of available resources for the target task. In this case, the resource adjustment strategy of the target task is to keep the amount of available resources of the target task unchanged.

For ease of explanation, the amount of resources provided by an instance is referred to as the amount of instance resources. In one possible implementation, if the available resources are instances, the resource requirements of the target task are the amount of instance resources required to complete the target task, and the amount of available resources for the target task is the instance used to complete the target task. Resources. When the resource requirements of the target task are greater than the target task If the amount of available resources for the task is determined, the resource adjustment strategy for the target task is to increase the amount of instance resources used to complete the target task. When the resource requirement of the target task is equal to the amount of available resources of the target task, the resource adjustment strategy of the target task is to keep the amount of instance resources used to complete the target task unchanged. When the resource requirements of the target task are less than the amount of available resources for the target task, the resource adjustment strategy for the target task is to reduce the amount of instance resources used to complete the target task, or to maintain the amount of instance resources used to complete the target task. .

By calculating the resource requirements of the target resources, this method can sense in advance the amount of resources required to complete the target task. When resource adjustment is required, the time required from sensing the need for resource adjustment to completing the resource adjustment is shorter in this method, thereby reducing the time required for resource adjustment and improving the efficiency of resource adjustment.

S303. When the target task satisfies the first resource adjustment condition, or the instance running the target task satisfies the second resource adjustment condition, adjust the number and specifications of the instances used to run the target task based on the resource adjustment policy of the target task. At least one.

S303 may be executed by the first module. In the embodiment of this application, if the target task satisfies the first resource adjustment condition, or the instance running the target task satisfies the second resource adjustment condition, it means that the amount of available resources of the target task cannot meet the resource requirements of the target task, and it is necessary to The amount of available resources for the target task is adjusted. The amount of resources available for a target task can be the amount of resources provided by the instance used to run the target task. For example, the target task satisfies the first resource adjustment condition, including: the expected execution time of the target task is greater than the reference execution time of the target task. For information about the expected execution time of the target task, please refer to S3021, which will not be described again here. For example, the instance running the target task satisfies the second resource adjustment condition, including: the CPU usage of the instance running the target task is higher than the usage threshold. The occupancy threshold can be set based on demand or actual experience, which is not limited in the embodiments of the present application.

In the embodiment of the present application, instances of different specifications provide different amounts of resources, so adjusting the amount of available resources for the target task based on the resource adjustment policy of the target task means: adjusting the amount of resources used to run the target task based on the resource adjustment policy of the target task. At least one of the number and specifications of instances of the target task. In a possible implementation, the first module executes a resource adjustment strategy based on the target task to adjust at least one of the instances, quantity, and specifications of the target task. In another possible implementation, the first module sends a control instruction to the second module, which is a module that manages the number and specifications of instances. The control instruction is used to instruct the second module to use resources based on the target task. The adjustment strategy adjusts at least one of the number and specifications of instances used to run the target task. The first module and the second module may belong to the same device or different devices.

For example, in the implementation environment shown in Figure 2, the first module is the task resource control module, and the second module is the control center. Then when the target task satisfies the first resource adjustment condition, or the instance running the target task satisfies the second resource adjustment condition, the task resource control module sends a control instruction to the control center, and the control instruction is used to instruct the control center to adjust resources based on the target task. The policy adjusts at least one of the number and specifications of instances used to run the target task.

In a possible implementation, the method further includes: receiving a resource update limit configured by the user, where the resource update limit includes at least one of a maximum cost and a maximum number of instances running the target task; adjusting the usage based on the resource adjustment policy. Adjusting at least one of the number and specifications of instances for running the target task includes: adjusting at least one of the number and specifications of the instances for running the target task based on the resource adjustment policy and the resource update limit. Resource adjustment based on user-configured resource update restrictions can ensure that the adjusted resources meet user needs.

Compared with increasing or decreasing resources according to fixed values in related technologies, in the method provided by the embodiment of the present application, the resource adjustment strategy of the target task is first determined, and then the resource adjustment is performed based on the resource adjustment strategy of the target task. The accuracy is higher and the resource adjustment method is more flexible.

Exemplarily, in the implementation environment shown in Figure 2, increasing the number of instances used to run the target task includes: Obtain a node from the point pool and copy the image from the image warehouse to the acquired node to obtain a new instance. Reduce the number of instances used to run target tasks, including deleting instances included in the workload. Adjust the specifications of the instance used to run the target task, including: obtaining a node from the node pool, copying the image from the image warehouse to the obtained node to obtain a new instance, and the new instance is used to replace the instance in the current workload, Adjust the instance specifications.

In a possible implementation, the method further includes: for any subtask included in the target task, determining a target instance corresponding to any subtask in the adjusted instance used for the target task, Execute any subtask through the target instance. By determining the target instance corresponding to the subtask, and then executing the subtask through the target instance, the instance used to execute the subtask can be controlled. Rather than sending individual subtasks to the workload, the workload determines the instance used to perform each subtask, allowing precise control over the instances used to perform each subtask. Illustratively, the operation of determining a target instance corresponding to any subtask and executing the any subtask through the target instance is performed by the first module.

In the method provided by the embodiment of the present application, task information of multiple tasks is obtained, and the resource adjustment strategy of the target task in the multiple tasks is determined based on the task information of the multiple tasks. This method can comprehensively perceive the multiple tasks, and determine the resource adjustment strategy for the target task based on the task information of the multiple tasks with high accuracy. Therefore, when resource adjustment is performed based on the resource adjustment strategy of the target task, the accuracy of resource adjustment is high.

Next, the method provided by the embodiment of the present application is applied to the implementation environment and the offline video transcoding scenario shown in Figure 2 as an example to illustrate more clearly the resource adjustment method provided by the embodiment of the present application. Figure 5 is a schematic process diagram of a resource adjustment method provided by an embodiment of the present application.

Referring to Figure 5, the business requirements include N offline video transcoding tasks, which are transcoding task 1, transcoding task 2, ..., and transcoding task N, where N is a positive integer. N task streams are obtained based on the N offline video transcoding tasks. For the i-th task stream among the N task streams, the i-th task stream includes four subtasks, namely the metadata acquisition task i and the slicing task. i, transcoding task i and merging task i, where i is an integer greater than 0 and less than or equal to N. The task types of these four subtasks are obtaining metadata, slicing, transcoding and merging respectively. The N task flows are stored in the task queue in the order of each sub-task, as shown in Figure 5. The sub-tasks stored in the task queue include: Get Metadata Task 1, Slice Task 1, Get Metadata Task 2, Get metadata task 3, transcoding task 1, slicing task 2, ..., merge task N.

For example, each sub-task in the task queue is a sub-task to be executed. The instances in the workload are containers, and each container is not occupied, that is, each container is idle. The task resource control module obtains the subtasks to be executed in the task queue, and obtains multiple tasks based on the obtained subtasks to be executed. For example, based on the task type of each subtask, subtasks of the same task type are regarded as one obtained task.

The target task can be any one of the plurality of tasks. For example, the target task in the plurality of tasks is a transcoding task. The transcoding task includes transcoding task 1 to transcoding task N. The available resources of the transcoding task include container 1, container 2, container 3, ..., and container M in Figure 5, that is, the amount of available resources for the transcoding task is M, and M is a positive integer.

After obtaining multiple tasks, the task resource control module can obtain the task information of each task in the multiple tasks. For example, the task resource control module first obtains the task type of each task, and then obtains the task information of each task based on the task type of each task. For example, the task resource control module obtains the task information of each task based on the historical execution information corresponding to each task type, or obtains the task information of each task by querying the correspondence between the task type and the task information.

In a possible implementation, the task resource control module also stores task type-metadata-task information. corresponding relationship. Metadata is the data of the execution object of business requirements. For example, for offline video transcoding tasks, metadata includes but is not limited to the resolution, duration, and bit rate of the video. The metadata of each video may be different, so that for multiple subtasks of the same type that are respectively performed on multiple videos, the task information of the multiple subtasks may be different. For example, for two videos with different resolutions, if the resource occupancy of the transcoding subtask performed on the two videos is the same, the resource occupancy of the transcoding subtask performed on the video with a higher resolution will be the same. The duration is longer. When the resource occupancy time of the transcoding subtask performed on the two videos is the same, the resource occupancy of the transcoding subtask performed on the video with a higher resolution is higher.

The correspondence between task type-metadata-task information can also be used to obtain task information of subtasks. For example, for a certain task flow, metadata can be obtained by first executing the subtask of obtaining metadata, and then for other subtasks in the task flow, the task can be queried based on the task type and the obtained metadata. Correspondence between type-metadata-task information to obtain the task information of the subtask. The correspondence between task type-metadata-task information can be obtained by executing subtasks of each task type on multiple test videos, and counting the resource occupancy and resource occupancy time of the subtasks of each task type. The multiple The test videos have different metadata.

For ease of explanation, the corresponding relationship between task type and task information is called the first query relationship, and the corresponding relationship between task type-metadata-task information is called the second query relationship. For two subtasks of the same task type, since different metadata in the second query relationship can correspond to different task information, compared with the task information of the subtask obtained based on the first query relationship, the subtasks obtained based on the second query relationship Mission information for tasks can be more accurate. Therefore, when the task information of the subtask obtained based on the first query relationship is different from the task information of the subtask obtained based on the second query relationship, the task resource control module can change the task information of the subtask obtained based on the second query relationship. Information is used as task information when arranging resources.

For example, the task information includes resource occupancy and resource occupancy duration. The task resource control module arranges resources for each task based on the resource occupancy and resource occupancy duration of each task. In a possible implementation manner, when the task resource control module arranges resources for each task, it arranges resources for each task according to the execution order of each task. Since the task resource control module can also store the corresponding relationship between task type-metadata-task information, the task resource control module can arrange the task of obtaining metadata to be executed first, so that it can further query the task type-metadata based on the obtained metadata. —The corresponding relationship between task information, and thus more accurate task information can be obtained.

Figure 6 is a schematic diagram of a resource arrangement process provided by an embodiment of the present application. As shown in Figure 6, the task resource control module obtains the resource occupancy and resource occupancy time of each sub-task; classifies each sub-task; based on the resource occupancy and resource occupancy time of each sub-task, classifies each sub-task Arrange resources.

Referring to Figure 6, the amount of available resources at each time point is used as the initial resource amount corresponding to each time point. When arranging resources for each classified sub-task, all sub-tasks for obtaining metadata are arranged first, so that each sub-task for obtaining meta-data is executed first, and the obtained meta-data can be used to obtain tasks for other sub-tasks. information. Then arrange the subtasks of the slices. If the resource occupation time of the subtasks of a certain slice is short, you can first arrange the transcoding subtasks that belong to the same task flow as the subtasks of the slice, so that the task flow can be Tasks are completed earlier. When arranging slice subtasks, you can also arrange all slice subtasks first and then arrange the transcoding subtasks, as long as the total resource usage corresponding to each time point within the expected execution time does not exceed the initial The amount of resources, and the proportion of resource occupation corresponding to each time point is greater than or equal to the threshold.

By arranging resources for multiple tasks, the expected execution time of the target task can be calculated. Therefore, when the expected execution time of the target task and the reference execution time of the target task are different, the initial resource amount can be adjusted based on the relationship between the expected execution time of the target task and the reference execution time of the target task, so that through Resource Arrangement Plan The calculated expected execution time of the target task is not greater than the reference execution time of the target task.

Figure 6 only shows the arrangement results of some tasks, and is not used to limit the task types and number of tasks for performing resource arrangement. For example, the resource requirement of the target task obtained according to the arrangement result in Figure 6 is greater than the amount of available resources of the target task. The resource requirement may be M+1 as shown in Figure 5. In this case, the task resource control module sends a control instruction to the control center, instructing the control center to adjust the amount of available resources so that the adjusted amount of available resources is not less than M+1. For example, referring to Figure 5, the control center generates container M+1 based on the received control instructions to adjust the amount of available resources.

In a possible implementation manner, the task resource control module can also determine the target instance corresponding to each sub-task included in the target task, so as to execute each sub-task through the target instance corresponding to each sub-task. For example, as shown in Figure 5, the task resource control module determines the target container corresponding to each sub-task included in the target task, sends each sub-task to the workload, and executes each sub-task through the target container corresponding to each sub-task in the workload. Subtasks.

For example, for an offline video transcoding scenario, the transcoding task includes 40 transcoding subtasks, and the available resources of the 40 subtasks are 1 container, that is, the available resources of the target task are 1. , the CPU occupancy of the container in the method of the related art and the method provided by the embodiment of the present application is shown in Figure 7.

Figure 7 is a schematic diagram of the CPU usage of a container provided by an embodiment of the present application. Among them, (1) in Figure 7 corresponds to the CPU occupancy of the container in the method of the related art, and (2) in Figure 7 corresponds to the CPU occupancy of the container in the method provided by the embodiment of the present application. Whether it is (1) in Figure 7 or (2) in Figure 7, the horizontal axis represents time, and the vertical axis represents the CPU usage of the container. It can be seen that in the method of related technologies, the time when the transcoding task is issued is around 15:21, and only about 6 minutes after it is issued, that is, around 15:27, a new container is generated and runs the transcoding task. In the method provided by the embodiment of this application, the time when the transcoding task is issued is around 15:47. About 1 minute after it is issued, that is, around 15:48, a new container generates and runs the transcoding task. The method provided by the embodiments of the present application requires a shorter time from when the resource amount needs to be adjusted to when the resource amount is adjusted.

Figure 8 is a schematic diagram of the completion time of a transcoding task provided by an embodiment of the present application. As shown in Figure 8, in the method of the related art, the polyline connecting the completion times of the 40 subtasks is the upper one of the two polylines shown in Figure 8, and the completion time of the last 25 subtasks among the 40 subtasks is Both are around 500 seconds (second, s). In the method provided by the embodiment of the present application, the polyline connecting the completion times of the 40 subtasks is the lower one of the two polylines shown in Figure 8 , and the completion time of the 40 subtasks is about 300s. As shown in Figure 8, the completion time of the transcoding task in the method provided by the embodiment of the present application is short.

Figure 9 is a schematic structural diagram of a resource adjustment device provided by an embodiment of the present application. Illustratively, the device is applied to the first module shown in Figure 1 or the task resource control module shown in Figure 2 to implement the resource adjustment method provided by the embodiment of the present application. Based on the following multiple units shown in Figure 9, the resource adjustment device shown in Figure 9 can perform all or part of the operations performed by the first module or the task resource control module. It should be understood that the device may include more additional units than those shown or omit some of the units shown, and this is not limited by the embodiments of the present application. As shown in Figure 9, the device includes:

The acquisition unit 901 is used to acquire task information of multiple tasks. The multiple tasks include a target task and at least one task to be executed. The task information includes task information of each task;

The determination unit 902 is used to determine the resource adjustment strategy of the target task based on the task information of multiple tasks;

The adjustment unit 903 is configured to adjust at least one of the number and specifications of instances used to run the target task based on the resource adjustment policy when the target task satisfies the first resource adjustment condition, or the instance running the target task satisfies the second resource adjustment condition. A sort of.

In a possible implementation, the device further includes: a receiving unit configured to receive user-configured resource update limits, where the resource update limits include at least one of a maximum cost and a maximum number of instances running the target task; adjust Unit 903 is configured to adjust at least one of the number and specifications of instances used to run the target task based on the resource adjustment policy and the resource update limit.

In a possible implementation, the determining unit 902 is configured to calculate the resource requirements of the target task based on the task information of the multiple tasks and the reference execution duration of the multiple tasks; based on the resource requirements of the target task and the available resources of the target task The resource adjustment strategy of the target task is determined, and the resource adjustment strategy is used to make the adjusted available resource amount of the target task meet the resource requirements of the target task.

In a possible implementation, the obtaining unit 901 is used to obtain the task type of each task in multiple tasks; based on the task type of each task, query the corresponding relationship between the task type and the task information, and obtain the task information of each task. The correspondence between the task type and task information is obtained based on the configuration information of the task type and task information.

In a possible implementation, the obtaining unit 901 is configured to obtain the task type of each task in multiple tasks; and obtain the task information of each task based on the historical execution information corresponding to each task type.

In the device provided by the embodiment of the present application, task information of multiple tasks is obtained, and the resource adjustment strategy of the target task in the multiple tasks is determined based on the task information of the multiple tasks. The device can comprehensively perceive the multiple tasks, and determine the resource adjustment strategy for the target task based on the task information of the multiple tasks with high accuracy. Therefore, when resource adjustment is performed based on the resource adjustment strategy of the target task, the accuracy of resource adjustment is high.

The above-mentioned obtaining unit 901, determining unit 902 and adjusting unit 903 can all be implemented by software or hardware. Next, taking the acquisition unit 901 as an example, the implementation of the acquisition unit 901 will be described. Similarly, the implementation of the determination unit 902 and the adjustment unit 903 may refer to the implementation of the acquisition unit.

In a possible implementation manner, the acquisition unit 901 is implemented by software. That is, the acquisition unit 901 is a software functional unit, and the acquisition unit 901 may include code running on the computing instance. The computing instance includes but is not limited to at least one of a physical host, a virtual machine, and a container. A physical host can be called a computing device. For example, the computing instance can be one or more. For example, the acquisition unit 901 may include code running on multiple hosts/virtual machines/containers. Multiple hosts/VMs/containers used to run the code can be distributed in the same region or in different regions. Furthermore, multiple hosts/virtual machines/containers used to run the code can be distributed in the same availability zone (AZ) or in different AZs. Each AZ includes one data center or multiple AZs. geographically close data centers. Among them, a region can include multiple AZs.

For example, multiple hosts/virtual machines/containers used to run the code can be distributed in the same virtual private cloud (virtual private cloud, VPC), or can be distributed in multiple VPCs. Among them, a VPC is set up in a region Inside. Cross-region communication between two VPCs in the same region and between VPCs in different regions is achieved by setting up a communication gateway in each VPC, and the interconnection between VPCs is realized through the communication gateway.

In another possible implementation, the acquisition unit 901 is implemented by hardware. That is, the acquisition unit 901 is a hardware functional unit, and the acquisition unit 901 may include at least one computing device, such as a server. For example, the acquisition unit 901 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). Among them, the above-mentioned PLD can be a complex programmable logical device (CPLD), a field-programmable gate array (field-programmable gate array, FPGA), a general array logic (generic array logic, GAL), or any combination thereof.

Multiple computing devices included in the acquisition unit 901 may be distributed in the same region or in different regions. Multiple computing devices included in the acquisition unit 901 may be distributed in the same AZ or in different AZs. For example, multiple computing devices included in the acquisition unit 901 may be distributed in the same VPC or in multiple VPCs. The multiple computing devices may be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

Exemplarily, in other embodiments, the obtaining unit 901 can be used to perform any step in the resource adjustment method, the determining unit 902 can be used to perform any step in the resource adjustment method, and the adjusting unit 903 can be used to perform the resource adjustment method. For any steps in the resource adjustment method, the steps that the acquisition unit 901, the determination unit 902, and the adjustment unit 903 are responsible for implementing can be specified as needed and implemented by the acquisition unit 901, the determination unit 902, and the adjustment unit 903 respectively implementing different steps in the resource adjustment method. Full functionality of the resource adjustment device.

By way of example, this application also provides a computing device 1000. As shown in Figure 10, computing device 1000 includes: bus 1002, processor 1004, memory 1006, and communication interface 1008. The processor 1004, the memory 1006 and the communication interface 1008 communicate through the bus 1002. Computing device 1000 may be a server or a terminal device. It should be understood that this application does not limit the number of processors and memories in the computing device 1000.

The bus 1002 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of presentation, only one line is used in Figure 10, but it does not mean that there is only one bus or one type of bus. Bus 1002 may include a path that carries information between various components of computing device 1000 (eg, memory 1006, processor 1004, communications interface 1008).

The processor 1004 may include any one or more of a CPU, a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP). .

Memory 1006 may include volatile memory, such as random access memory (RAM). The memory 1006 may also include non-volatile memory (non-volatile memory), such as read-only memory (ROM), flash memory, mechanical hard disk (hard disk drive, HDD) or solid state drive (solid state drive). ,SSD).

The memory 1006 stores executable program code, and the processor 1004 executes the executable program code to implement the functions of the aforementioned acquisition unit 901, determination unit 902, and adjustment unit 903 respectively, thereby implementing the resource adjustment method. That is, the memory 1006 stores instructions for executing the resource adjustment method.

Alternatively, executable code is stored in the memory 1006, and the processor 1004 executes the executable code to implement the foregoing. The resource adjustment device functions to implement the resource adjustment method. That is, the memory 1006 stores instructions for executing the resource adjustment method.

The communication interface 1008 uses transceiver modules such as, but not limited to, network interface cards and transceivers to implement communication between the computing device 1000 and other devices or communication networks.

In a possible implementation manner, embodiments of the present application also provide a computing device cluster. The computing device cluster includes at least one computing device. The computing device may be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device may also be a terminal device such as a desktop computer, a laptop computer, or a smartphone.

As shown in Figure 11, the computing device cluster includes at least one computing device 1000. The same instructions for performing the resource adjustment method may be stored in the memory 1006 of one or more computing devices 1000 in the computing device cluster.

In some possible implementations, the memory 1006 of one or more computing devices 1000 in the computing device cluster may also store part of the instructions for executing the resource adjustment method. In other words, a combination of one or more computing devices 1000 may collectively execute instructions for performing a resource adjustment method.

It should be noted that the memories 1006 in different computing devices 1000 in the computing device cluster can store different instructions, respectively used to execute part of the functions of the resource adjustment device. That is, instructions stored in the memory 1006 in different computing devices 1000 may implement the functions of one or more units among the obtaining unit 901 , the determining unit 902 and the adjusting unit 903 .

In some possible implementations, one or more computing devices in a cluster of computing devices may be connected through a network. Among them, the network can be a wide area network or a local area network, etc. Figure 12 is a schematic structural diagram of another computing device cluster provided by an embodiment of the present application. As shown in Figure 12, two computing devices 1000A and 1000B are connected through a network. Specifically, the connection to the network is made through a communication interface in each computing device. In one possible implementation, instructions for performing the functions of the acquisition unit 901 are stored in the memory 1006 of the computing device 1000A. At the same time, instructions for performing the functions of the determining unit 902 and the adjusting unit 903 are stored in the memory 1006 of the computing device 1000B.

The connection method between the computing device clusters shown in Figure 12 can be that considering that the resource adjustment method provided by this application needs to obtain task information of multiple tasks, the functions implemented by the determination unit 902 and the adjustment unit 903 are handed over to the computing device 1000B for execution. .

It should be understood that the functions of the computing device 1000A shown in FIG. 12 may also be performed by multiple computing devices 1000. Likewise, the functions of computing device 1000B may also be performed by multiple computing devices 1000 .

Exemplarily, the embodiment of the present application also provides another computing device cluster. The connection relationship between the computing devices in the computing device cluster can be similar to the connection method of the computing device cluster in FIG. 11 and FIG. 12 . The difference is that the same instructions for executing the resource adjustment method may be stored in the memory 1006 of one or more computing devices 1000 in the computing device cluster.

Embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium includes computer program instructions. When the computer program instructions are executed by a computing device cluster, the computing device cluster executes the resource adjustment method in Figure 3 .

Embodiments of the present application provide a computer program product containing instructions. When the instructions are executed by a computing device cluster, the computing device cluster can perform corresponding steps and/or processes in the above method embodiments.

Embodiments of the present application provide a chip, including a processor, which is configured to call and run instructions stored in the memory, so that at least one computing device installed with the chip executes the methods in the above aspects.

Exemplarily, the chip further includes: an input interface, an output interface and the memory, and the input interface, the output interface, the processor and the memory are connected through internal connection paths.

An embodiment of the present application also provides a device, which includes the above chip. Optionally, the device is a computing device. For example, the device is a server or a terminal device.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in this application are generated in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device. Computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, e.g., computer instructions may be transmitted from a website, computer, server or data center via a wired link (e.g. Coaxial cable, optical fiber, digital subscriber line) or wireless (such as infrared, wireless, microwave, etc.) means to transmit to another website, computer, server or data center. Computer-readable storage media can be any available media that can be accessed by a computer or a data storage device such as a server, data center, or other integrated media that contains one or more available media. The available media may be magnetic media (eg, floppy disk, hard disk, magnetic tape), optical media (eg, digital video disc (DVD)), or semiconductor media (eg, SSD), etc.

The above-mentioned specific embodiments further describe the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above-mentioned are only specific embodiments of the present application and are not intended to limit the scope of the present application. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of this application shall be included in the scope of protection of this application.

Those of ordinary skill in the art will appreciate that the method steps and modules described in conjunction with the embodiments disclosed herein can be implemented in software, hardware, firmware, or any combination thereof. In order to clearly illustrate the interoperability of hardware and software, Alternatively, the steps and compositions of each embodiment have been generally described in terms of functions in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. One of ordinary skill in the art may implement the described functionality using different methods for each specific application, but such implementations should not be considered beyond the scope of this application.

Those of ordinary skill in the art can understand that all or part of the steps to implement the above embodiments can be completed by hardware, or can be completed by instructing the relevant hardware through a program. The program can be stored in a computer-readable storage medium. As mentioned above, The storage medium can be read-only memory, magnetic disk or optical disk, etc.

When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer program instructions. By way of example, methods of embodiments of the present application may be described in the context of machine-executable instructions, such as included in a program module executing in a device on a target's real or virtual processor. Generally speaking, program modules include routines, programs, libraries, objects, classes, components, data structures, etc., which perform specific tasks or implement specific abstract data structures. In various embodiments, the functionality of program modules may be combined or split between the described program modules. Machine-executable instructions for program modules can execute locally or on a distributed device. In a distributed device, program modules can be located in both local and remote storage media.

Computer program codes for implementing the methods of embodiments of the present application may be written in one or more programming languages. These computer program codes may be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable resource adjustment device, The program code, when executed by a computer or other programmable resource adjustment device, causes the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the computer, partly on the computer, as a stand-alone software package, partly on the computer and partly on a remote computer or entirely on the remote computer or server.

In the context of the embodiments of the present application, the computer program code or related data may be carried by any appropriate carrier, so that the device, device or processor can perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, and the like.

Examples of signals may include electrical, optical, radio, acoustic, or other forms of propagated signals, such as carrier waves, infrared signals, and the like.

A machine-readable medium may be any tangible medium that contains or stores a program for or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any suitable combination thereof. More detailed examples of machine-readable storage media include an electrical connection with one or more wires, laptop computer disk, hard drive, random memory accessor (RAM), read-only memory (ROM), erasable programmable read-only memory Memory (erasable programmable ROM, EPROM) or flash memory, optical storage device, magnetic storage device, or any suitable combination thereof.

Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be described again here.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components may be combined or may be Integrated into another system, or some features can be ignored, or not implemented. In addition, the coupling or direct coupling or communication connection between each other shown or discussed may be indirect coupling or communication connection through some interfaces, devices or modules, or may be electrical, mechanical or other forms of connection.

The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software function modules.

If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

In this application, the terms "first", "second" and other words are used to distinguish the same or similar items with basically the same function and function. It should be understood that the terms "first", "second" and "nth" There is no logical or sequential dependency between them, and there is no limit on the number or execution order. It should also be understood that although the following description uses the terms first, second, etc. to describe various elements, but these elements should not be limited by the term. These terms are only used to distinguish one element from another. For example, a first module may be termed a second module, and similarly, a second module may be termed a first module, without departing from the scope of various described examples. Both the first module and the second module may be any type of computing device, and, in some cases, may be separate and distinct computing devices.

It should also be understood that in each embodiment of the present application, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not be determined by the execution order of the embodiments of the present application. The implementation process constitutes no limitation.

The term "at least one" in this application means one or more, and the term "plurality" in this application means two or more. For example, multiple tasks means two or more. Task. The terms "system" and "network" are often used interchangeably in this article.

It is to be understood that the terminology used in the description of the various examples herein is for the purpose of describing the particular example only and is not intended to be limiting. As used in the description of various described examples and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context dictates otherwise. Instruct clearly.

It will also be understood that the term "includes" (also "includes," "including," "comprises," and/or "comprising") when used in this specification specifies the presence of stated features, integers, steps, operations, elements , and/or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groupings thereof.

It should also be understood that the terms "if" and "if" may be interpreted to mean "when" or "upon" or "in response to determining" or "in response to detecting." Similarly, depending on the context, the phrase "if it is determined..." or "if [stated condition or event] is detected" may be interpreted to mean "when it is determined..." or "in response to the determination... ” or “on detection of [stated condition or event]” or “in response to detection of [stated condition or event].”

It should be understood that determining B based on A does not mean determining B only based on A, and B can also be determined based on A and/or other information.

It should also be understood that references throughout this specification to "one embodiment,""anembodiment," and "a possible implementation" mean that specific features, structures, or characteristics related to the embodiment or implementation are included herein. In at least one embodiment of the application. Therefore, “in one embodiment” or “in an embodiment” or “a possible implementation” appearing in various places throughout this specification do not necessarily refer to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments.

Claims

A resource adjustment method, characterized in that the method includes:

Obtain task information of multiple tasks, the multiple tasks include a target task and at least one task to be executed, and the task information includes task information of each task;

Determine a resource adjustment strategy for the target task according to the task information of the multiple tasks;

When the target task satisfies the first resource adjustment condition, or the instance running the target task satisfies the second resource adjustment condition, adjust the number and specifications of the instances used to run the target task based on the resource adjustment policy. At least one.
The method of claim 1, further comprising:

Receive a user-configured resource update limit, the resource update limit including at least one of a maximum cost and a maximum number of instances running the target task;

The adjusting at least one of the number and specifications of instances used to run the target task based on the resource adjustment policy includes:

Based on the resource adjustment policy and the resource update limit, at least one of the number and specifications of instances used to run the target task is adjusted.
The method according to claim 1 or 2, characterized in that the target task satisfies the first resource adjustment condition, including:

The expected execution time of the target task is greater than the reference execution time of the target task.
The method according to any one of claims 1 to 3, characterized in that the instance running the target task satisfies the second resource adjustment condition, including:

The central processor CPU usage of the instance running the target task is higher than the usage threshold.
The method according to any one of claims 1 to 4, characterized in that the target task is a task to be executed or a task being executed.
The method according to any one of claims 1 to 5, characterized in that the task information includes resource occupancy amount and resource occupancy duration.
The method according to any one of claims 1 to 6, characterized in that determining the resource adjustment strategy of the target task according to the task information of the plurality of tasks includes:

Calculate the resource requirements of the target task according to the task information of the multiple tasks and the reference execution duration of the multiple tasks;

According to the resource requirements of the target task and the amount of available resources of the target task, a resource adjustment strategy for the target task is determined, and the resource adjustment strategy is used to make the adjusted amount of available resources of the target task satisfy the Resource requirements for the target task.
The method according to claim 3, characterized in that the method further includes:

According to the initial resource amount and the task information of the multiple tasks, the expected execution time of the target task is calculated.
The method according to any one of claims 1 to 8, characterized in that the obtaining task information of multiple tasks includes:

Obtain the task type of each task in the plurality of tasks;

Based on the task type of each task, the corresponding relationship between the task type and the task information is queried to obtain the task information of each task, wherein the corresponding relationship between the task type and the task information is obtained based on the task type and the configuration information of the task information. .
The method according to claim 9, characterized in that the task type is any one of obtaining metadata, slicing, transcoding or merging.
A resource adjustment device, characterized in that the device includes:

An acquisition unit, configured to acquire task information of a plurality of tasks, the plurality of tasks including a target task and at least one task to be executed, the task information including task information of each task;

A determining unit configured to determine a resource adjustment strategy for the target task based on the task information of the multiple tasks;

An adjustment unit configured to adjust the resource adjustment rate for running the instance of the target task based on the resource adjustment policy when the target task satisfies the first resource adjustment condition or the instance running the target task satisfies the second resource adjustment condition. At least one of quantity and specification.
The device according to claim 11, characterized in that the device further includes:

A receiving unit configured to receive user-configured resource update restrictions, where the resource update restrictions include at least one of a maximum cost and a maximum number of instances running the target task;

The adjustment unit is configured to adjust at least one of the number and specifications of instances used to run the target task based on the resource adjustment policy and the resource update limit.
The apparatus according to claim 11 or 12, wherein the target task satisfies the first resource adjustment condition, including: the expected execution time of the target task is greater than the reference execution time of the target task.
The apparatus according to any one of claims 11 to 13, wherein the instance running the target task satisfies the second resource adjustment condition, including: the central processing unit (CPU) of the instance running the target task. Occupancy is above the occupancy threshold.
The device according to any one of claims 11 to 14, characterized in that the target task is a task to be executed or a task being executed.
The device according to any one of claims 11 to 15, wherein the task information includes resource occupancy amount and resource occupancy duration.
The device according to any one of claims 11 to 16, characterized in that the determining unit is configured to calculate the target task according to the task information of the multiple tasks and the reference execution duration of the multiple tasks. resource requirements; according to the resource requirements of the target task and the amount of available resources of the target task, determine the resource adjustment strategy of the target task, the resource adjustment strategy is used to make the adjusted available resources of the target task The amount of resources required to meet the target tasks.
The device according to claim 13, characterized in that the device further includes:

A calculation unit configured to calculate the expected execution time of the target task based on the initial resource amount and task information of the multiple tasks.
The device according to any one of claims 11 to 18, characterized in that the obtaining unit is used to obtain the task type of each task in the plurality of tasks; based on the task type of each task, query the task type The corresponding relationship with the task information is to obtain the task information of each task, wherein the corresponding relationship between the task type and the task information is obtained based on the configuration information of the task type and the task information.
The device according to claim 19, wherein the task type is any one of obtaining metadata, slicing, transcoding or merging.
A computing device cluster, characterized in that the computing device cluster includes at least one computing device, and each computing device includes a processor and a memory;

The processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device, so that the cluster of computing devices performs the method according to any one of claims 1 to 10.
A computer-readable storage medium, characterized in that the computer-readable storage medium includes computer program instructions, and when the computer program instructions are executed by a computing device cluster, the computing device cluster executes claims 1 to 10 any of the methods described.
A computer program product containing instructions, characterized in that, when the instructions are executed by a cluster of computing devices, they cause the cluster of computing devices to perform the method according to any one of claims 1 to 10.
A chip, characterized in that the chip includes a processor, the processor is used to call from the memory and run the instructions stored in the memory, so that at least one computing device installed with the chip executes claim 1 to any of the methods described in 10.
The chip according to claim 24, further comprising: an input interface, an output interface and the memory, and the input interface, the output interface, the processor and the memory are connected through an internal connection path connected.