WO2017080273A1 - 任务管理方法和系统、计算机存储介质 - Google Patents

任务管理方法和系统、计算机存储介质 Download PDF

Info

Publication number
WO2017080273A1
WO2017080273A1 PCT/CN2016/095561 CN2016095561W WO2017080273A1 WO 2017080273 A1 WO2017080273 A1 WO 2017080273A1 CN 2016095561 W CN2016095561 W CN 2016095561W WO 2017080273 A1 WO2017080273 A1 WO 2017080273A1
Authority
WO
WIPO (PCT)
Prior art keywords
task
background
background task
time
foreground
Prior art date
Application number
PCT/CN2016/095561
Other languages
English (en)
French (fr)
Inventor
林庚佑
张文彦
Original Assignee
深圳市万普拉斯科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市万普拉斯科技有限公司 filed Critical 深圳市万普拉斯科技有限公司
Priority to US15/773,984 priority Critical patent/US10802877B2/en
Priority to EP16863451.7A priority patent/EP3376379A4/en
Publication of WO2017080273A1 publication Critical patent/WO2017080273A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234—Power saving characterised by the action undertaken
    • G06F1/329—Power saving characterised by the action undertaken by task scheduling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • G06F9/4887—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues involving deadlines, e.g. rate based, periodic
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/485—Task life-cycle, e.g. stopping, restarting, resuming execution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G06F9/5038—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate

Definitions

  • the present invention relates to the field of operating system technologies, and in particular, to a task management method and system, and a computer storage medium.
  • Multitasking generally includes foreground tasks and background tasks. Background tasks compete with foreground tasks for resources, preempting foreground task resources, and sometimes hinder the operation of foreground tasks.
  • the resources may be a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a memory, and the like.
  • CPU Central Processing Unit
  • GPU Graphics Processing Unit
  • the traditional practice is to completely suspend the background tasks, but some background tasks need to communicate with the server in real time, such as message delivery or mail service. If the background task is completely suspended, the information will not be timely feedback or other information will be generated. Expected behavior and other issues.
  • the embodiment of the present invention provides a task management method, which can not only ensure the normal operation of the background task, but also reduce the resource competition between the background task and the foreground task, and save resources.
  • the embodiment of the invention provides a task management system, which can not only ensure the normal operation of the background task, but also reduce the resource competition between the background task and the foreground task, and save resources.
  • the embodiment of the invention provides a computer storage medium, which can ensure the normal operation of the background task, and can also reduce the resource competition between the background task and the foreground task, and save resources.
  • the method further includes:
  • a specific background task is added to the background task group according to a predetermined rule.
  • the method further comprises the steps of:
  • the threshold is divided by the sum of the foreground task and the number of background tasks in the background task group.
  • the method further includes:
  • the running time allowed for each background task in the background task group is determined according to a predetermined algorithm.
  • each specific background task when each specific background task is outside the corresponding running period, the specific background tasks are respectively entered into a waiting state. After the steps, it also includes:
  • a monitoring module configured to monitor the operation of background tasks
  • Determining a module configured to determine a running time allowed for a specific background task in a unit time, and a sum of running times of the specific background tasks in a unit time is less than or equal to a preset time threshold;
  • the waiting module is configured to make each specific background task enter a waiting state when each specific background task is outside the corresponding running time period in a unit time.
  • system further comprises:
  • Establishing a module configured to establish a background task group, and setting a resource usage time quota of the background task group as a preset time threshold;
  • Adding a module configured to add a specific background task to the background task group according to a predetermined rule.
  • system further comprises:
  • Obtaining a priority module configured to obtain a priority of a foreground task being executed and a background task in the background task group;
  • the determining module is further configured to: when the foreground task has the same priority as the background task in the background task group, determine, in the unit time, that each background task in the background task group is allowed
  • the running time is the sum of the time threshold divided by the number of background tasks in the foreground task and the background task group.
  • the determining module is further configured to: when the foreground task is When the priorities of the background tasks in the background task group are different, the priority is determined based on the priority of the foreground task and the background task in the background task group in the unit time, and the background is determined according to a predetermined algorithm. The runtime allowed for each background task in the task group.
  • system further comprises:
  • the judging module is configured to determine whether a foreground task is being executed when each specific background task enters a waiting state.
  • the determining module is further configured to: when it is determined that each of the specific background tasks enters a waiting state, and the foreground task is being executed, determining that the foreground task obtains all resource usage time;
  • the hibernation module is configured to enter a sleep state when it is determined that no specific foreground task is being executed when each specific background task enters a waiting state.
  • the monitoring module, the determining module, the waiting module, the establishing module, the adding module, the obtaining priority module, and the determining module may adopt a central processing unit (CPU, Central) when performing processing.
  • CPU Central
  • Processing Unit Digital Signal Processor
  • FPGA Field-Programmable Gate Array
  • the embodiment of the present invention further provides a computer storage medium, where the computer storage medium stores computer executable instructions, and the computer executable instructions are configured to perform the task management method according to any one of the above embodiments.
  • each specific background task runs only in a corresponding running time period, and each specific background task is outside the corresponding running time period, so that each specific background task is performed outside the corresponding running time period
  • Each specific background task enters a waiting state, and the allowed running time of all the specific background tasks does not exceed a preset time threshold, which can ensure the normal operation of the background task, and the background task does not unrestrictedly
  • the front-end task preempts resources, so that the foreground tasks have better resource utilization efficiency and save resources.
  • FIG. 1 is a schematic flow chart of a task management method in an embodiment
  • FIG. 2 is a schematic diagram of time when a task is executed in an embodiment
  • FIG. 3 is a schematic flowchart of a time allocation of foreground tasks and background task resources in an embodiment
  • FIG. 4 is a schematic diagram of time when a task is executed in another embodiment
  • FIG. 5 is a schematic structural diagram of a task management system in an embodiment
  • FIG. 6 is a schematic structural diagram of a task management system in another embodiment
  • FIG. 7 is a schematic structural diagram of a task management system in another embodiment.
  • a task management method includes the following steps:
  • Step S110 monitoring the running of the background task.
  • the running of the background task is monitored, and information such as the number of background tasks, the priority, and the User Identifier (UID) are obtained.
  • information such as the number of background tasks, the priority, and the User Identifier (UID) are obtained.
  • step S120 the running time allowed for the specific background task in the unit time is determined.
  • the time is divided into consecutive multiple unit time for monitoring, and the specific background task only has the resource usage right in a part of the time in the unit time, that is, each specific background task is only in the corresponding time period corresponding thereto.
  • Running the duration of the partial period is equal to the aforementioned allowed running time.
  • the sum of the running times allowed for each specific background task in the unit time is less than or equal to the preset time threshold.
  • the time threshold is all specific backgrounds in the unit time.
  • the specific background task may be set as any one of the background tasks according to actual needs. In other embodiments, according to actual needs, the specific background task may also be set to meet all the background tasks.
  • the background task of the rule the rule.
  • the foreground task refers to the task that requires the user to participate in the interaction
  • the background task refers to the task that does not require the user to participate in the interaction.
  • the character that receives the user input is the foreground task
  • the automatic saving at a certain time is Background tasks.
  • the time threshold is less than a unit time, for example, the unit time may be 2T, and the time threshold may be T, 0.5T, 0.75T, or the like.
  • T can be a short time value of 10s (seconds), 15s, 20s, etc., which can better guarantee the execution of background tasks, and will not delay the completion of work because the waiting time is too long.
  • the method further includes:
  • the background task group is established to manage the background task, and only the background task in the background task group is limited by the resource usage time limit, that is, the background task in the background task group is allowed in the unit time.
  • the sum of the running times does not exceed the aforementioned time threshold.
  • the running time allowed for each background task in the background task group per unit time is determined according to at least the resource usage time quota and the priority of the background task in the background task group.
  • the background task in each background task group executes the background task only in a part of the time period corresponding to the unit time. And in the time outside the part of the time in the unit time, the background task is put into a waiting state.
  • the unit time and time threshold can be set according to requirements.
  • a background task that is not associated with the foreground task being executed may be added to a background task group, such as text editing software, which automatically saves as a background task at regular intervals, when receiving characters input by the user.
  • the background task is not added to the background task group during the foreground task. However, if there is still a background task of the mail service at this time, the background task If there is no association with the foreground task being executed, it will be added to the background task group, which can better guarantee the execution of the foreground task and make the foreground application have better resource utilization efficiency. Understandably, other rules can be set as needed, and then specific background tasks that match the rules are added to the background task group.
  • Step S130 in each unit time, when each specific background task is outside the corresponding running period, each specific background task is respectively entered into a waiting state.
  • FIG. 2 is a schematic diagram of a task execution in an embodiment. As shown in FIG. 2, it is assumed that the unit time is 2T and the time threshold is T. Among them, the operation of the background task 20 and the foreground task 10 is monitored. In the second 2T unit time, the running time allowed by the background tasks E, F, and G is T/4, and the tasks are executed in the respective running periods of the background tasks E, F, and G, respectively. When the running time is outside, the background tasks E, F, and G are in a waiting state.
  • Waiting state means that the background task will not use any resources.
  • the sum of the allowed running times of the background tasks E, F, G is less than the time threshold T.
  • the foreground task B can use all the resources without facing the background tasks E, F, and G competing resources.
  • the running time allowed by the background task E is T/3, and when it is outside its running time, the background task E enters the waiting state. After a period of time, enter the running period of the background task G (the duration of the period is T/3).
  • a specific background task may enter a waiting state in a unit time, and then perform, for example, 2T unit time, all specific background tasks first enter a waiting state, and after T time, according to each specific
  • the runtime allowed by the background task executes each specific background task. It can be understood that it is essentially the same as the task management method of FIG. 2.
  • each specific background task runs only in the corresponding running time period, and each specific background task enters a waiting state when each specific background task is outside the corresponding running time.
  • the sum of the allowed running times of all the specific background tasks does not exceed the preset time threshold, which can ensure the normal operation of the background tasks, and the background tasks do not preempt the resources with the foreground tasks in an unlimited manner, so that the foreground tasks are more Good resource use efficiency and resource saving.
  • the foregoing task management method further includes the following steps:
  • Step S310 obtaining the priority of the foreground task in the execution and the background task in the background task group.
  • the priority of each foreground task in the foreground task and the background task group is obtained, and the resource usage time of each task is determined according to the priority.
  • tasks with higher priority get more allowed runtime than tasks with lower priority.
  • step S320 it is determined whether the foreground task and the background task in the background task group have the same priority. If yes, step S330 is performed, and if no, step S340 is performed.
  • the time threshold is a resource usage quota of the background task in the background task group in a unit time, that is, the sum of the running times allowed by the background task in the background task group is less than or equal to the time threshold in the unit time.
  • the running time allowed for each task may be determined according to at least the time threshold and the priority of the task. If the foreground task has the same priority as the background task in the background task group, the background task group The running time allowed for each background task is the time threshold divided by the sum of the number of background tasks in the foreground task and the background task group. If the priority of the foreground task and the background task are different, the algorithm is determined according to the priority level and the predetermined algorithm. The resource usage time of each background task in the foreground task and the background task group.
  • Step S330 determining, in the unit time, the running time allowed by each background task in the background task group is the time threshold divided by the sum of the number of background tasks in the foreground task and the background task group.
  • the second 2T unit time the time threshold is T
  • the average task is divided into T/4.
  • Resource usage time The foreground task B can also be assigned to the time T outside the time threshold of the unit time. In the unit time, the foreground task B can be allocated to the resource usage time of T+T/4. If there is no foreground task B currently executed, the three background tasks E, F, and G can be equally divided into T/3 resource usage time.
  • the foreground task and the background task in the background task group may each have a half time threshold, and the background task group is in the background task group.
  • the running time allowed for each background task is half the time threshold divided by the number of background tasks in the background task group.
  • three background tasks E, F, and G are allocated a total of T/2 resource usage time, and each background task is assigned T/6 resource usage time, and the foreground task is obtained.
  • B is divided into resource usage time of T+T/2, and the allocation method is related to the task scheduler algorithm in the operating system.
  • Step S340 Determine, according to a predetermined algorithm, a running time of each background task in the background task group according to a priority level of the background task in the foreground task and the background task group in a unit time.
  • the tasks are sorted according to the priority order, and the tasks with higher priority are ranked in front of the task with lower priority, the foreground task and the background.
  • the resource usage time of each background task in the task group can be determined according to the priority of the task and according to a predetermined algorithm. For example, in 2T unit time, the time threshold is T, and the task ranked first priority can be divided into 0.5. T, the task ranked in the second priority can be divided into 0.3T, and the task ranked in the third priority can be divided into 0.2T, etc., when each background task in the background task group is not in the corresponding running time, the background task The background tasks in the group immediately enter the wait state.
  • resource allocation and scheduling may also be performed sequentially according to the request of the task.
  • each background task in the background task group is only in unit time Running in the corresponding running time period, and determining the resource usage time of the task according to the task priority, the resource scheduling can be better performed, and the work is completed.
  • the background tasks in the background task group are respectively entered into the waiting state, and the sum of the allowed running times of the background tasks in the background task group does not exceed the preset time threshold, thereby ensuring the normal operation of the background tasks and the background tasks. It does not unrestrictedly seize resources with the foreground tasks, so that the foreground tasks have better resource utilization efficiency and save resources.
  • the specific background tasks are respectively entered into the waiting state, and further includes: determining each specific background task Whether the foreground task is executing when entering the waiting state; if yes, it will determine that the foreground task obtains all resource usage time; if not, it enters the sleep state.
  • the sleep state can be entered, wherein entering the sleep state means that the computing device that performs the above task management method enters the sleep state and has achieved the purpose of power saving.
  • entering the sleep state means that the computing device that performs the above task management method enters the sleep state and has achieved the purpose of power saving.
  • the background task G After the background task G enters the waiting state, only the foreground task B is executing, and the foreground task B will obtain all the resource usage time, which can make the foreground application have better resource utilization efficiency.
  • the foreground task C In the third 2T unit time, when the background task E runs for T/3 time and before the running time of the background task G starts, only the foreground task C is being executed during this time, and the foreground task C will get all the Resource usage time.
  • the sleep state is automatically entered.
  • a task management system includes a monitoring module 510, a determining module 520, and a waiting module 530.
  • the monitoring module 510 is configured to monitor the operation of the background task.
  • the running of the background task is monitored, and information such as the number of background tasks, priority, and user identifier can be obtained.
  • a determination module 520 is configured to determine a runtime allowed for a particular background task per unit time.
  • the time is divided into consecutive multiple unit time for monitoring, and the specific background task only has the resource usage right in a part of the time in the unit time, that is, each specific background task is only in the corresponding time period corresponding thereto.
  • Running the duration of the partial period is equal to the aforementioned allowed running time.
  • the sum of the allowed running times of the specific background tasks in the unit time is less than or equal to the preset time threshold, and the time threshold is the maximum value of the sum of the times when all the specific background tasks are allowed to run in the unit time.
  • the specific background task may be set as any one of the background tasks according to actual needs. In other embodiments, according to actual needs, the specific background task may also be set to meet all the background tasks.
  • the background task of the rule is the resource usage right in a part of the time in the unit time, that is, each specific background task is only in the corresponding time period corresponding thereto.
  • Running the duration of the partial period is equal to the aforementioned allowed running time.
  • the foreground task refers to the task that requires the user to participate in the interaction
  • the background task refers to the task that does not require the user to participate in the interaction.
  • the character that receives the user input is the foreground task
  • the automatic saving at a certain time is Background tasks.
  • the time threshold is less than a unit time, for example, the unit time may be 2T, and the time threshold may be T, 0.5T, 0.75T, or the like. T can be a short time value of 10s, 15s, 20s, etc., which can better guarantee the execution of background tasks, and will not delay the completion of work because the waiting time is too long.
  • the waiting module 530 is configured to cause each specific background task to enter a waiting state when each specific background task is outside the corresponding running time period in a unit time.
  • FIG. 2 is a schematic diagram of a task execution in an embodiment. As shown in FIG. 2, it is assumed that the unit time is 2T and the time threshold is T. Among them, the operation of the background task 20 and the foreground task 10 is monitored. In the second 2T unit time, the running time allowed by the background tasks E, F, and G is T/4, and the tasks are executed in the respective running periods of the background tasks E, F, and G, respectively. When the running time is outside, the background tasks E, F, and G are in a waiting state.
  • Waiting state means that the background task will not use any resources.
  • the sum of the allowed running times of the background tasks E, F, G is less than the time threshold T.
  • the foreground task B can use all the resources without facing the background tasks E, F, and G competing resources.
  • the running time allowed by the background task E is T/3, and when it is outside its running time, the background task E enters the waiting state. After a period of time, enter the running period of the background task G (the duration of the period is T/3).
  • a specific background task may enter a waiting state in a unit time, and then perform, for example, 2T unit time, all specific background tasks first enter a waiting state, and after T time, according to each specific
  • the runtime allowed by the background task executes each specific background task. It can be understood that it is essentially the same as the task management method of FIG. 2.
  • each specific background task runs only in the corresponding running time period, and each specific background task enters a waiting state when each specific background task is outside the corresponding running time.
  • the sum of the allowed running times of all the specific background tasks does not exceed the preset time threshold, which can ensure the normal operation of the background tasks, and the background tasks do not preempt the resources with the foreground tasks in an unlimited manner, so that the foreground tasks are more Good resource use efficiency and resource saving.
  • the task management system includes a monitoring module 510, a determining module 520, and a waiting module 530, and an establishing module 512 and an adding module 514.
  • the establishing module 512 is configured to establish a background task group, and set a resource usage time limit of the background task group to a preset time threshold.
  • the background task group is established to manage the background task, and only the background task in the background task group is limited by the resource usage time limit, that is, the background task in the background task group is allowed in the unit time.
  • the sum of the running times does not exceed the aforementioned time threshold.
  • the running time allowed for each background task in the background task group per unit time is determined according to at least the resource usage time quota and the priority of the background task in the background task group.
  • the background task in each background task group executes the background task only in a part of the time period corresponding to the unit time. And in the time outside the part of the time in the unit time, the background task is put into a waiting state.
  • the unit time and time threshold can be set according to requirements.
  • the adding module 514 is configured to add a specific background task to the background task group according to a predetermined rule.
  • a background task that is not associated with the foreground task being executed may be added to a background task group, such as text editing software, which automatically saves as a background task at regular intervals, when receiving characters input by the user.
  • the background task is not added to the background task group during the foreground task.
  • adding it to the background task group can better ensure the execution of the foreground task and let the foreground application own Better resource efficiency. Understandably, other rules can be set as needed, and then specific background tasks that match the rules are added to the background task group.
  • each background task in the background task group runs only in the corresponding running time period, and each background task in the background task group is outside the corresponding running time period, so that the background task is enabled.
  • the background tasks in the group respectively enter the waiting state, and the sum of the allowed running times of the background tasks in the background task group does not exceed the preset time threshold, which can ensure the normal operation of the background tasks, and the background tasks are not Unrestricted with front desk tasks Seize resources to make the foreground tasks have better resource utilization efficiency and save resources.
  • the task management system includes an acquisition module 512, an addition module 514, a monitoring module 510, a determination module 520, and a wait module 530, and a priority acquisition module 522, a determination module 532, and a sleep module 534.
  • the get priority module 522 is configured to obtain the priority of the foreground task being executed and the background task in the background task group.
  • the priority of each foreground task in the foreground task and the background task group is obtained, and the resource usage time of each task is determined according to the priority.
  • the time threshold is the resource usage quota of the background task in the background task group in a unit time, that is, the sum of the running times allowed by the background task in the background task group in the unit time is less than or equal to the time threshold.
  • the running time allowed for each task may be determined according to at least the time threshold and the priority of the task.
  • the background task group The running time allowed for each background task is the time threshold divided by the sum of the number of background tasks in the foreground task and the background task group. If the priority of the foreground task and the background task are different, the algorithm is determined according to the priority level and the predetermined algorithm. The resource usage time of each background task in the foreground task and the background task group.
  • the determining module 520 is further configured to determine, when the current task is the same as the priority of the background task in the background task group, determine the allowed running time of each background task in the background task group as the time threshold divided by the foreground in the unit time. The sum of the number of background tasks in the task and background task groups.
  • the second 2T unit time is T
  • the average task is divided into T/4.
  • the resource usage time while the foreground task B can also be assigned to the time T outside the time threshold of the unit time, then in the unit time.
  • the foreground task B can be allocated to the resource usage time of T+T/4. If there is no front desk at present When B is executed, the three background tasks E, F, and G can be equally divided into resource usage time of T/3.
  • the foreground task and the background task in the background task group may each have a half time threshold, and the background task group is in the background task group.
  • the running time allowed for each background task is half the time threshold divided by the number of background tasks in the background task group.
  • three background tasks E, F, and G are allocated a total of T/2 resource usage time, and each background task is allocated T/6 resource usage time, and the foreground task is obtained.
  • B is divided into resource usage time of T+T/2, and the allocation method is related to the task scheduler algorithm in the operating system.
  • the determining module 520 is further configured to determine the priority of the background task in the foreground task and the background task group according to the priority of the current task and the background task in the unit time, and determine the background task group according to a predetermined algorithm. The runtime allowed for each background task.
  • the tasks are sorted according to the priority order, and the tasks with higher priority are ranked in front of the task with lower priority, the foreground task and the background.
  • the resource usage time of each background task in the task group can be determined according to the priority of the task and according to a predetermined algorithm. For example, in 2T unit time, the time threshold is T, and the task ranked first priority can be divided into 0.5. T, the task ranked in the second priority can be divided into 0.3T, and the task ranked in the third priority can be divided into 0.2T, etc., when each background task in the background task group is not in the corresponding running time, the background task The background tasks in the group immediately enter the wait state.
  • resource allocation and scheduling may also be performed sequentially according to the request of the task.
  • the determining module 532 is configured to determine whether a foreground task is being executed when each of the specific background tasks enters a waiting state.
  • the determining module 520 is further configured to determine that the foreground task obtains all resource usage time when it is determined that a foreground task is being executed when each specific background task enters a waiting state.
  • the hibernation module 534 is configured to determine that when each specific background task enters a wait state When no foreground task is executing, it goes to sleep.
  • the sleep state can be entered, wherein entering the sleep state means that the computing device that performs the above task management method enters the sleep state and has achieved the purpose of power saving.
  • entering the sleep state means that the computing device that performs the above task management method enters the sleep state and has achieved the purpose of power saving.
  • the background task G After the background task G enters the waiting state, only the foreground task B is executing, and the foreground task B will obtain all the resource usage time, which can make the foreground application have better resource utilization efficiency.
  • the foreground task C In the third 2T unit time, when the background task E runs for T/3 time and before the running time of the background task G starts, only the foreground task C is being executed during this time, and the foreground task C will get all the Resource usage time.
  • the sleep state is automatically entered.
  • each background task in the background task group runs only in the corresponding running time period, and the resource usage time of the task is determined according to the task priority, so that the resource scheduling can be better performed and the work is completed.
  • the background tasks in the background task group are respectively entered into the waiting state, and the allowed running time of the background tasks in the background task group is If the preset time threshold is not exceeded, the background task can be guaranteed to run normally.
  • the background task does not preempt the resources with the foreground task in an unlimited manner, so that the foreground task has better resource utilization efficiency and saves resources.
  • all the specific background tasks enter the waiting state, if there is no foreground task to execute, it automatically enters the sleep state, reducing the power consumption of the device.
  • the embodiment of the present invention further provides a computer storage medium, where the computer storage medium stores computer executable instructions, and the computer executable instructions are configured to perform the task management method according to any one of the above embodiments.
  • each specific background task runs only in the corresponding running time period per unit time, and when each specific background task is outside the corresponding running time period, each specific background task is separately Entering the waiting state, and the sum of the allowed running times of all the specific background tasks does not exceed the preset time threshold, which can ensure the normal operation of the background tasks, and the background tasks can not preempt the resources with the foreground tasks without restriction.
  • Front-end tasks have better resource efficiency and save resources.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Debugging And Monitoring (AREA)

Abstract

一种任务管理方法和系统、计算机存储介质。其中，所述方法包括：监视后台任务的运行（S110）；确定特定的后台任务在单位时间内所允许的运行时间（S120），全部特定的后台任务在单位时间内所允许的运行时间之和小于或等于预设的时间阈值；在单位时间内，当各个特定的后台任务在对应的运行时段之外时，使所述各个特定的后台任务分别进入等待状态（S130）。

Description

任务管理方法和系统、计算机存储介质 技术领域
本发明涉及操作系统技术领域，特别是涉及一种任务管理方法和系统、计算机存储介质。
背景技术
目前，很多计算设备(例如智能手机、平板电脑等)均支持多任务系统，即同一时间内设备可运行多个应用程序，一个应用程序中可能有一个或多个线程，每个线程上运行一个任务。而多任务中一般会包括前台任务和后台任务，后台任务会与前台任务竞争资源，抢占前台任务资源，有时会妨碍前台任务的运行。资源可以是中央处理器(CPU，Central Processing Unit)、图形处理器(GPU，Graphics Processing Unit)、内存等。为解决该问题，传统做法是将后台任务完全暂停，但有些后台任务需要实时与服务器进行沟通，例如讯息传递或邮件服务等，若是将后台任务完全暂停，会造成信息无法及时反馈或是产生其它预期外的行为等问题。
发明内容
基于此，本发明实施例提供了一种任务管理方法，既能保证后台任务的正常运行，也能减少后台任务与前台任务的资源竞争，节约资源。
此外，本发明实施例提供了一种任务管理系统，既能保证后台任务的正常运行，也能减少后台任务与前台任务的资源竞争，节约资源。
此外，本发明实施例提供了一种计算机存储介质，既能保证后台任务的正常运行，也能减少后台任务与前台任务的资源竞争，节约资源。
本发明实施例的一种任务管理方法，包括：
监视后台任务的运行；
确定特定的后台任务在单位时间内所允许的运行时间，全部特定的后台任务在单位时间内所允许的运行时间之和小于或等于预设的时间阈值；
在单位时间内，当各个特定的后台任务在对应的运行时段之外时，使所述各个特定的后台任务分别进入等待状态。
在其中一个实施例中，在所述监视后台任务的运行的步骤之后，还包括：
建立后台任务群组，并设置所述后台任务群组的资源使用时间额度为预设的时间阈值；
根据预定的规则，将特定的后台任务添加入所述后台任务群组。
在其中一个实施例中，所述方法还包括以下步骤：
获取正在执行的前台任务与所述后台任务群组中的后台任务的优先级；
当所述前台任务与所述后台任务群组中的后台任务的优先级相同时，在所述单位时间内，确定所述后台任务群组中的各个后台任务所允许的运行时间为所述时间阈值除以所述前台任务与所述后台任务群组中的后台任务的数量之和。
在其中一个实施例中，在所述获取正在执行的前台任务与所述后台任务群组中的后台任务的优先级的步骤之后，还包括：
当所述前台任务与所述后台任务群组中的后台任务的优先级不同时，在所述单位时间内，基于所述前台任务与所述后台任务群组中的后台任务的优先级高低并按照预定的算法确定所述后台任务群组中的各个后台任务所允许的运行时间。
在其中一个实施例中，在所述在单位时间内，当各个特定的后台任务在对应的运行时段之外时，使所述各个特定的后台任务分别进入等待状态 的步骤之后，还包括：
判断当各个特定的后台任务均进入等待状态时是否有前台任务正在执行；
若是，则确定所述前台任务获得全部的资源使用时间；
若否，则进入休眠状态。
本发明实施例的一种任务管理系统，包括：
监视模块，配置为监视后台任务的运行；
确定模块，配置为确定特定的后台任务在单位时间内所允许的运行时间，全部特定的后台任务在单位时间内所允许的运行时间之和小于或等于预设的时间阈值；
等待模块，配置为在单位时间内，当各个特定的后台任务在对应的运行时段之外时，使所述各个特定的后台任务分别进入等待状态。
在其中一个实施例中，所述系统还包括：
建立模块，配置为建立后台任务群组，并设置所述后台任务群组的资源使用时间额度为预设的时间阈值；
添加模块，配置为根据预定的规则，将特定的后台任务添加入所述后台任务群组。
在其中一个实施例中，所述系统还包括：
获取优先级模块，配置为获取正在执行的前台任务与所述后台任务群组中的后台任务的优先级；
所述确定模块还配置为当所述前台任务与所述后台任务群组中的后台任务的优先级相同时，在所述单位时间内，确定所述后台任务群组中的各个后台任务所允许的运行时间为所述时间阈值除以所述前台任务与所述后台任务群组中的后台任务的数量之和。
在其中一个实施例中，所述确定模块还配置为当所述前台任务与所述 后台任务群组中的后台任务的优先级不同时，在所述单位时间内，基于所述前台任务与所述后台任务群组中的后台任务的优先级高低并按照预定的算法确定所述后台任务群组中的各个后台任务所允许的运行时间。
在其中一个实施例中，所述系统还包括：
判断模块，配置为判断当各个特定的后台任务均进入等待状态时是否有前台任务正在执行。
所述确定模块还配置为当判断出当各个特定的后台任务均进入等待状态时有前台任务正在执行，则确定所述前台任务获得全部的资源使用时间；
休眠模块，配置为当判断出当各个特定的后台任务均进入等待状态时无前台任务正在执行，则进入休眠状态。
所述监视模块、所述确定模块、所述等待模块、所述建立模块、所述添加模块、所述获取优先级模块、所述判断模块在执行处理时，可以采用中央处理器(CPU，Central Processing Unit)、数字信号处理器(DSP，Digital Singnal Processor)或可编程逻辑阵列(FPGA，Field－Programmable Gate Array)实现。
本发明实施例还提供一种计算机存储介质，所述计算机存储介质中存储有计算机可执行指令，该计算机可执行指令配置为执行上述实施例中任一项所述的任务管理方法。
本发明实施例的任务管理方法和系统、计算机存储介质，每单位时间内，各个特定的后台任务只在对应的运行时段内运行，当各个特定的后台任务在对应的运行时段之外时，使各个特定的后台任务分别进入等待状态，且所有特定的后台任务的所允许的运行时间之和不超过预设的时间阈值，既能保证后台任务的正常运行，后台任务又不会无限制地与前台任务抢占资源，使前台任务有更佳的资源使用效率，节约资源。
此外，当所有后台任务均进入等待状态且无前台任务进行执行时，自 动进入休眠状态，减少设备的电力消耗。
附图说明
图1为一个实施例中任务管理方法的流程示意图；
图2为一个实施例中任务执行时的时间示意图；
图3为一个实施例中前台任务与后台任务资源使用时间分配的流程示意图；
图4为另一个实施例中任务执行时的时间示意图；
图5为一个实施例中任务管理系统的结构示意图；
图6为另一个实施例中任务管理系统的结构示意图；
图7为另一个实施例中任务管理系统的结构示意图。
具体实施方式
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。
如图1所示，一种任务管理方法，包括以下步骤：
步骤S110，监视后台任务的运行。
具体的，对后台任务的运行进行监视，可获取后台任务的数量、优先级、用户标识符(User Identifier,UID)等信息。
步骤S120，确定特定的后台任务在单位时间内所允许的运行时间。
具体的，将时间划分为连续的多个单位时间进行监测，特定的后台任务只在单位时间中的部分时段内才拥有资源使用权，即每个特定的后台任务仅在与其对应的部分时段被运行，该部分时段的时长等于前述确定的所允许的运行时间。所有特定的后台任务在单位时间内所允许的运行时间之和小于或等于预设的时间阈值，时间阈值为单位时间内所有特定的后台任 务被允许运行的时间之和的最大值。其中，根据实际需要，可设定特定的后台任务为全部后台任务中的任意一个后台任务，在其它的实施例中，根据实际需要，特定的后台任务也可设定为全部后台任务中符合预定规则的后台任务。前台任务指需要用户参与交互的任务，后台任务则指不需用户参与交互的任务，例如：文字编辑软件中，其接收用户输入的字符即为前台任务，而每隔一定时间自动进行保存则为后台任务。时间阈值小于单位时间，例如单位时间可为2T，时间阈值可为T、0.5T、0.75T等。T可以为10s(秒)、15s、20s等时间较短的数值，可以更好地保证后台任务的执行，不会因为等待时间过长而延误工作的完成。
在一个实施例中，在步骤监视后台任务的运行之后，还包括：
(1)建立后台任务群组，并设置后台任务群组的资源使用时间额度为预设的时间阈值。
具体的，建立后台任务群组对后台任务进行管理，只有在后台任务群组中的后台任务，才受资源使用时间额度的限制，即在后台任务群组中的后台任务在单位时间内被允许的运行时间之和不超过前述时间阈值。至少根据该资源使用时间额度及后台任务群组中的后台任务的优先级来确定单位时间内后台任务群组中每个后台任务所允许的运行时间。每个后台任务群组中的后台任务只有在单位时间中与之对应的部分时段，才执行该后台任务。而在单位时间中的该部分时段之外的时间内，则使该后台任务进入等待状态。该单位时间与时间阈值可根据需求进行设定。
(2)根据预定的规则，将特定的后台任务添加入后台任务群组。
具体的，可将与正在执行的前台任务无关联的后台任务添加入后台任务群组，例如文字编辑软件中，其每隔一定时间自动进行保存为后台任务，当正在执行接收用户输入的字符的前台任务时，不将该后台任务添加入后台任务群组中。但是，若此时还存在邮件服务这一后台任务，该后台任务 与正在执行的前台任务无关联，则将其添加入后台任务群组，可以更好地保证前台任务的执行，让前台应用拥有更佳的资源使用效率。可以理解地，还可以根据需要设定其他的规则，然后将符合规则的特定后台任务添加到后台任务群组。
步骤S130，在单位时间内，当各个特定的后台任务在对应的运行时段之外时，使各个特定的后台任务分别进入等待状态。
具体的，在单位时间内，只有在各个特定的后台任务对应的运行时段内时，才执行该后台任务，该运行时段的时长等于该后台任务在单位时间内所允许的运行时间。图2为一个实施例中任务执行时的示意图，如图2所示，假定单位时间为2T，时间阈值为T。其中，监视后台任务20和前台任务10的运行。在第二个2T单位时间内，后台任务E、F、G所允许的运行时间均为T/4，在后台任务E、F、G各自对应的运行时段内，执行该任务，当在各自对应的运行时段之外时，后台任务E、F、G则分别处于等待状态。等待状态指后台任务不会使用任何资源。后台任务E、F、G所允许的运行时间之和小于时间阈值T。当后台任务E、F、G均进入等待状态时，前台任务B能使用全部的资源而不必面临后台任务E、F、G竞争资源。在第三个2T单位时间内，后台任务E所允许的运行时间为T/3，当在其运行时段之外时，后台任务E进入等待状态。一段时间之后，再进入后台任务G的运行时段(该时段的时长为T/3)。只需保证在单位时间内所有特定的后台任务所允许的运行时间之和小于或等于时间阈值即可，而各个特定的后台任务在单位时间的什么时段内运行则由操作系统的任务调度器的算法决定。在其它实施例中，特定的后台任务在单位时间内，可先进入等待状态，再进行执行，例如2T单位时间内，所有特定的后台任务先进入等待状态，T时间后，再按照各个特定的后台任务所允许的运行时间执行各个特定的后台任务，可以理解，其本质上与图2的任务管理方法是一致的。
上述任务管理方法，每单位时间内，各个特定的后台任务只在对应的运行时段内运行，当各个特定的后台任务在对应的运行时段之外时，使各个特定的后台任务分别进入等待状态，且所有特定的后台任务的所允许的运行时间之和不超过预设的时间阈值，既能保证后台任务的正常运行，后台任务又不会无限制地与前台任务抢占资源，使前台任务有更佳的资源使用效率，节约资源。
如图3所示，在一个实施例中，上述任务管理方法，还包括以下步骤：
步骤S310，获取正在执行的前台任务与后台任务群组中的后台任务的优先级。
具体的，获取正在执行的前台任务及后台任务群组中的每个后台任务的优先级，并根据优先级的高低确定各个任务的资源使用时间。通常，优先级高的任务比优先级低的任务会获得更多的所允许的运行时间。
步骤S320，判断该前台任务与后台任务群组中的后台任务的优先级是否相同，若是，则执行步骤S330，若否，则执行步骤S340。
具体的，时间阈值为单位时间内后台任务群组中的后台任务的资源使用额度，即在单位时间内，后台任务群组中的后台任务所允许的运行时间之和需小于或等于该时间阈值。在单位时间内，可至少根据该时间阈值及任务的优先级确定每个任务所允许的运行时间，若前台任务与后台任务群组中的后台任务的优先级相同，则后台任务群组中的各个后台任务所允许的运行时间为时间阈值除以前台任务与后台任务群组中的后台任务的数量之和，若前台任务与后台任务的优先级不同，则按照优先级高低及预定的算法确定前台任务及后台任务群组中的各个后台任务的资源使用时间。
步骤S330，在单位时间内，确定后台任务群组中的各个后台任务所允许的运行时间为时间阈值除以前台任务与后台任务群组中的后台任务的数量之和。
具体的，例如，在图2中，第二个2T单位时间内，时间阈值为T，共有一个前台任务B和三个后台任务E、F、G，则平均每个任务分到T/4的资源使用时间。而前台任务B还能分到单位时间内时间阈值外的时间T，则在单位时间内，前台任务B共能分到T+T/4的资源使用时间。若当前没有前台任务B执行，则三个后台任务E、F、G可平均分到T/3的资源使用时间。在其它的实施例中，当前台任务与后台任务群组中的后台任务的优先级相同时，前台任务与后台任务群组中的后台任务可各分得一半的时间阈值，后台任务群组中的各个后台任务所允许的运行时间为一半的时间阈值除以后台任务群组中的后台任务数量。例如，在图2中，在单位时间内，三个后台任务E、F、G总共分得T/2的资源使用时间，每个后台任务各分得T/6的资源使用时间，而前台任务B则分得T+T/2的资源使用时间，分配方式与操作系统中的任务调度器算法相关。
步骤S340，在单位时间内，基于前台任务与后台任务群组中的后台任务的优先级高低并按照预定的算法确定后台任务群组中的各个后台任务所允许的运行时间。
具体的，若前台任务与后台任务群组中的后台任务的优先级高低不同，则将任务按照优先级高低顺序进行排序，优先级高的任务排在优先级低的任务前面，前台任务与后台任务群组中的各个后台任务的资源使用时间可根据任务优先级高低并按照预定的算法进行确定，例如在2T单位时间内，时间阈值为T，排在第一优先级的任务可分到0.5T，排在第二优先级的任务可分到0.3T，排在第三优先级的任务可分到0.2T等，当后台任务群组中的各个后台任务不在对应的运行时段时，后台任务群组中的后台任务分别立即进入等待状态。在其它的实施例中，也可根据任务的请求先后进行资源分配与调度。
上述任务管理方法，单位时间内，后台任务群组中的各个后台任务只 在对应的运行时段内运行，且根据任务优先级确定任务的资源使用时间，可以更好地进行资源调度，完成工作，当后台任务群组中的各个后台任务在对应的运行时段之外时，使后台任务群组中的后台任务分别进入等待状态，且后台任务群组中的后台任务的所允许的运行时间之和不超过预设的时间阈值，既能保证后台任务的正常运行，后台任务又不会无限制地与前台任务抢占资源，使前台任务有更佳的资源使用效率，节约资源。
在一个实施例中，在步骤在单位时间内，当各个特定的后台任务在对应的运行时段之外时，使各个特定的后台任务分别进入等待状态之后，还包括：判断当各个特定的后台任务均进入等待状态时是否有前台任务正在执行；若是，则将确定前台任务获得全部的资源使用时间；若否，则进入休眠状态。
具体的，单位时间内，当后台任务群组中的后台任务全部进入等待状态时，若有前台任务正在执行，则确定正在执行的前台任务获得全部的资源使用时间，若无前台任务正在执行，则可进入休眠状态，其中，进入休眠状态指执行上述任务管理方法的计算设备进入休眠状态已达到省电的目的。如图2所示，在第2个2T单位时间内，当后台任务G运行达T/4时间后，其进入等待状态，而在此之前，后台任务E和F已进入等待状态。在后台任务G进入等待状态后，只有前台任务B在执行，则前台任务B将获得全部的资源使用时间，可以使前台应用有更佳的资源使用效率。在第3个2T单位时间内，当后台任务E运行达T/3时间时到后台任务G的运行时段开始之前，这段时间内也只有前台任务C正在执行，将前台任务C将获得全部的资源使用时间。如图4所示，在第2个和第3个2T单位时间内无前台任务正在执行，则当所有后台任务均进入等待状态时，自动进入休眠状态。
上述任务管理方法，当所有特定的后台任务均进入等待状态时，若无前台任务进行执行时，自动进入休眠状态，减少设备的电力消耗。
如图5所示，一种任务管理系统，包括监视模块510、确定模块520和等待模块530。
监视模块510，配置为监视后台任务的运行。
具体的，对后台任务的运行进行监视，可获取后台任务的数量、优先级、用户标识符等信息。
确定模块520，配置为确定特定的后台任务在单位时间内所允许的运行时间。
具体的，将时间划分为连续的多个单位时间进行监测，特定的后台任务只在单位时间中的部分时段内才拥有资源使用权，即每个特定的后台任务仅在与其对应的部分时段被运行，该部分时段的时长等于前述确定的所允许的运行时间。所有特定的后台任务在单位时间内所允许的运行时间之和小于或等于预设的时间阈值，时间阈值为单位时间内所有特定的后台任务被允许运行的时间之和的最大值。其中，根据实际需要，可设定特定的后台任务为全部后台任务中的任意一个后台任务，在其它的实施例中，根据实际需要，特定的后台任务也可设定为全部后台任务中符合预定规则的后台任务。前台任务指需要用户参与交互的任务，后台任务则指不需用户参与交互的任务，例如：文字编辑软件中，其接收用户输入的字符即为前台任务，而每隔一定时间自动进行保存则为后台任务。时间阈值小于单位时间，例如单位时间可为2T，时间阈值可为T、0.5T、0.75T等。T可以为10s、15s、20s等时间较短的数值，可以更好地保证后台任务的执行，不会因为等待时间过长而延误工作的完成。
等待模块530，配置为在单位时间内，当各个特定的后台任务在对应的运行时段之外时，使各个特定的后台任务分别进入等待状态。
具体的，在单位时间内，只有在各个特定的后台任务对应的运行时段内时，才执行该后台任务，该运行时段的时长等于该后台任务在单位时间 内所允许的运行时间。图2为一个实施例中任务执行时的示意图，如图2所示，假定单位时间为2T，时间阈值为T。其中，监视后台任务20和前台任务10的运行。在第二个2T单位时间内，后台任务E、F、G所允许的运行时间均为T/4，在后台任务E、F、G各自对应的运行时段内，执行该任务，当在各自对应的运行时段之外时，后台任务E、F、G则分别处于等待状态。等待状态指后台任务不会使用任何资源。后台任务E、F、G所允许的运行时间之和小于时间阈值T。当后台任务E、F、G均进入等待状态时，前台任务B能使用全部的资源而不必面临后台任务E、F、G竞争资源。在第三个2T单位时间内，后台任务E所允许的运行时间为T/3，当在其运行时段之外时，后台任务E进入等待状态。一段时间之后，再进入后台任务G的运行时段(该时段的时长为T/3)。只需保证在单位时间内所有特定的后台任务所允许的运行时间之和小于或等于时间阈值即可，而各个特定的后台任务在单位时间的什么时段内运行则由操作系统的任务调度器的算法决定。在其它实施例中，特定的后台任务在单位时间内，可先进入等待状态，再进行执行，例如2T单位时间内，所有特定的后台任务先进入等待状态，T时间后，再按照各个特定的后台任务所允许的运行时间执行各个特定的后台任务，可以理解，其本质上与图2的任务管理方法是一致的。
上述任务管理系统，每单位时间内，各个特定的后台任务只在对应的运行时段内运行，当各个特定的后台任务在对应的运行时段之外时，使各个特定的后台任务分别进入等待状态，且所有特定的后台任务的所允许的运行时间之和不超过预设的时间阈值，既能保证后台任务的正常运行，后台任务又不会无限制地与前台任务抢占资源，使前台任务有更佳的资源使用效率，节约资源。
如图6所示，在一个实施例中，上述任务管理系统，除了包括监视模块510、确定模块520和等待模块530，还包括建立模块512和添加模块514。
建立模块512，配置为建立后台任务群组，并设置后台任务群组的资源使用时间额度为预设的时间阈值。
具体的，建立后台任务群组对后台任务进行管理，只有在后台任务群组中的后台任务，才受资源使用时间额度的限制，即在后台任务群组中的后台任务在单位时间内被允许的运行时间之和不超过前述时间阈值。至少根据该资源使用时间额度及后台任务群组中的后台任务的优先级来确定单位时间内后台任务群组中每个后台任务所允许的运行时间。每个后台任务群组中的后台任务只有在单位时间中与之对应的部分时段，才执行该后台任务。而在单位时间中的该部分时段之外的时间内，则使该后台任务进入等待状态。该单位时间与时间阈值可根据需求进行设定。
添加模块514，配置为根据预定的规则，将特定的后台任务添加入后台任务群组。
具体的，可将与正在执行的前台任务无关联的后台任务添加入后台任务群组，例如文字编辑软件中，其每隔一定时间自动进行保存为后台任务，当正在执行接收用户输入的字符的前台任务时，不将该后台任务添加入后台任务群组中。但是，若此时还存在邮件服务这一后台任务，该后台任务与正在执行的前台任务无关联，则将其添加入后台任务群组，可以更好地保证前台任务的执行，让前台应用拥有更佳的资源使用效率。可以理解地，还可以根据需要设定其他的规则，然后将符合规则的特定后台任务添加到后台任务群组。
上述任务管理系统，每单位时间内，后台任务群组中的各个后台任务只在对应的运行时段内运行，当后台任务群组中的各个后台任务在对应的运行时段之外时，使后台任务群组中的后台任务分别进入等待状态，且后台任务群组中的后台任务的所允许的运行时间之和不超过预设的时间阈值，既能保证后台任务的正常运行，后台任务又不会无限制地与前台任务 抢占资源，使前台任务有更佳的资源使用效率，节约资源。
如图7所示，上述任务管理系统，除了包括建立模块512、添加模块514、监视模块510、确定模块520和等待模块530，还包括获取优先级模块522、判断模块532和休眠模块534。
获取优先级模块522配置为获取正在执行的前台任务与后台任务群组中的后台任务的优先级。
具体的，获取正在执行的前台任务及后台任务群组中的每个后台任务的优先级，并根据优先级的高低确定各个任务的资源使用时间。通常，优先级高的任务比优先级低的任务会获得更多的所允许的运行时间。时间阈值为单位时间内后台任务群组中的后台任务的资源使用额度，即在单位时间内，后台任务群组中的后台任务所允许的运行时间之和需小于或等于该时间阈值。在单位时间内，可至少根据该时间阈值及任务的优先级确定每个任务所允许的运行时间，若前台任务与后台任务群组中的后台任务的优先级相同，则后台任务群组中的各个后台任务所允许的运行时间为时间阈值除以前台任务与后台任务群组中的后台任务的数量之和，若前台任务与后台任务的优先级不同，则按照优先级高低及预定的算法确定前台任务及后台任务群组中的各个后台任务的资源使用时间。
确定模块520还配置为当前台任务与后台任务群组中的后台任务的优先级相同时，在单位时间内，确定后台任务群组中的各个后台任务所允许的运行时间为时间阈值除以前台任务与后台任务群组中的后台任务的数量之和。
具体的，例如，在图2中，第二个2T单位时间内，时间阈值为T，共有一个前台任务B和三个后台任务E、F、G，则平均每个任务分到T/4的资源使用时间，而前台任务B还能分到单位时间内时间阈值外的时间T，则在单位时间内。前台任务B共能分到T+T/4的资源使用时间。若当前没有前台任 务B执行，则三个后台任务E、F、G可平均分到T/3的资源使用时间。在其它的实施例中，当前台任务与后台任务群组中的后台任务的优先级相同时，前台任务及后台任务群组中的后台任务可各分得一半的时间阈值，后台任务群组中的各个后台任务所允许的运行时间为一半的时间阈值除以后台任务群组中的后台任务数量。例如，在图2中，在单位时间内，三个后台任务E、F、G总共分得T/2的资源使用时间，每个后台任务各分得T/6的资源使用时间，而前台任务B则分得T+T/2的资源使用时间，分配方式与操作系统中的任务调度器算法相关。
确定模块520还配置为当前台任务与后台任务的优先级不同时，在单位时间内，基于前台任务与后台任务群组中的后台任务的优先级高低并按照预定的算法确定后台任务群组中的各个后台任务所允许的运行时间。
具体的，若前台任务与后台任务群组中的后台任务的优先级高低不同，则将任务按照优先级高低顺序进行排序，优先级高的任务排在优先级低的任务前面，前台任务与后台任务群组中的各个后台任务的资源使用时间可根据任务优先级高低并按照预定的算法进行确定，例如在2T单位时间内，时间阈值为T，排在第一优先级的任务可分到0.5T，排在第二优先级的任务可分到0.3T，排在第三优先级的任务可分到0.2T等，当后台任务群组中的各个后台任务不在对应的运行时段时，后台任务群组中的后台任务分别立即进入等待状态。在其它的实施例中，也可根据任务的请求先后进行资源分配与调度。
判断模块532配置为判断当各个特定的后台任务均进入等待状态时是否有前台任务正在执行。
确定模块520还配置为当判断出当各个特定的后台任务均进入等待状态时有前台任务正在执行，则确定所述前台任务获得全部的资源使用时间。
休眠模块534配置为当判断出当各个特定的后台任务均进入等待状态 时无前台任务正在执行，则进入休眠状态。
具体的，位时间内，当后台任务群组中的后台任务全部进入等待状态时，若有前台任务正在执行，则确定正在执行的前台任务获得全部的资源使用时间，若无前台任务正在执行，则可进入休眠状态，其中，进入休眠状态指执行上述任务管理方法的计算设备进入休眠状态已达到省电的目的。如图2所示，在第2个2T单位时间内，当后台任务G运行达T/4时间后，其进入等待状态，而在此之前，后台任务E和F已进入等待状态。在后台任务G进入等待状态后，只有前台任务B在执行，则前台任务B将获得全部的资源使用时间，可以使前台应用有更佳的资源使用效率。在第3个2T单位时间内，当后台任务E运行达T/3时间时到后台任务G的运行时段开始之前，这段时间内也只有前台任务C正在执行，将前台任务C将获得全部的资源使用时间。如图4所示，在第2个和第3个2T单位时间内无前台任务正在执行，则当所有后台任务均进入等待状态时，自动进入休眠状态。
上述任务管理系统，单位时间内，后台任务群组中的各个后台任务只在对应的运行时段内运行，且根据任务优先级确定任务的资源使用时间，可以更好地进行资源调度，完成工作，当后台任务群组中的各个后台任务在对应的运行时段之外时，使后台任务群组中的后台任务分别进入等待状态，且后台任务群组中的后台任务的所允许的运行时间之和不超过预设的时间阈值，既能保证后台任务的正常运行，后台任务又不会无限制地与前台任务抢占资源，使前台任务有更佳的资源使用效率，节约资源。此外，当所有特定的后台任务均进入等待状态时，若无前台任务进行执行时，自动进入休眠状态，减少设备的电力消耗。
本发明实施例还提供一种计算机存储介质，所述计算机存储介质中存储有计算机可执行指令，该计算机可执行指令配置为执行上述实施例中任一项所述的任务管理方法。
以上所述实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本发明的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变形和改进，这些都属于本发明的保护范围。因此，本发明专利的保护范围应以所附权利要求为准。
工业实用性
本发明实施例的任务管理方案，每单位时间内，各个特定的后台任务只在对应的运行时段内运行，当各个特定的后台任务在对应的运行时段之外时，使各个特定的后台任务分别进入等待状态，且所有特定的后台任务的所允许的运行时间之和不超过预设的时间阈值，既能保证后台任务的正常运行，后台任务又不会无限制地与前台任务抢占资源，使前台任务有更佳的资源使用效率，节约资源。

Claims (11)

  1. 一种任务管理方法，包括：
    监视后台任务的运行；
    确定特定的后台任务在单位时间内所允许的运行时间，全部特定的后台任务在单位时间内所允许的运行时间之和小于或等于预设的时间阈值；
    在单位时间内，当各个特定的后台任务在对应的运行时段之外时，使所述各个特定的后台任务分别进入等待状态。
  2. 根据权利要求1所述的任务管理方法，其中，在所述监视后台任务的运行的步骤之后，还包括：
    建立后台任务群组，并设置所述后台任务群组的资源使用时间额度为预设的时间阈值；
    根据预定的规则，将特定的后台任务添加入所述后台任务群组。
  3. 根据权利要求2所述的任务管理方法，其中，所述方法还包括以下步骤：
    获取正在执行的前台任务与所述后台任务群组中的后台任务的优先级；
    当所述前台任务与所述后台任务群组中的后台任务的优先级相同时，在所述单位时间内，确定所述后台任务群组中的各个后台任务所允许的运行时间为所述时间阈值除以所述前台任务与所述后台任务群组中的后台任务的数量之和。
  4. 根据权利要求3所述的任务管理方法，其中，在所述获取正在执行的前台任务与所述后台任务群组中的后台任务的优先级的步骤之后，还包括：
    当所述前台任务与所述后台任务群组中的后台任务的优先级不同时，在所述单位时间内，基于所述前台任务与所述后台任务群组中的后台任务 的优先级高低并按照预定的算法确定所述后台任务群组中的各个后台任务所允许的运行时间。
  5. 根据权利要求4所述的任务管理方法，其中，在所述在单位时间内，当各个特定的后台任务在对应的运行时段之外时，使所述各个特定的后台任务分别进入等待状态的步骤之后，还包括：
    判断当各个特定的后台任务均进入等待状态时是否有前台任务正在执行；
    若是，则确定所述前台任务获得全部的资源使用时间；
    若否，则进入休眠状态。
  6. 一种任务管理系统，包括：
    监视模块，配置为监视后台任务的运行；
    确定模块，配置为确定特定的后台任务在单位时间内所允许的运行时间，全部特定的后台任务在单位时间内所允许的运行时间之和小于或等于预设的时间阈值；
    等待模块，配置为在单位时间内，当各个特定的后台任务在对应的运行时段之外时，使所述各个特定的后台任务分别进入等待状态。
  7. 根据权利要求6所述的任务管理系统，其中，所述系统还包括：
    建立模块，配置为建立后台任务群组，并设置所述后台任务群组的资源使用时间额度为预设的时间阈值；
    添加模块，配置为根据预定的规则，将特定的后台任务添加入所述后台任务群组。
  8. 根据权利要求7所述的任务管理系统，其中，所述系统还包括：
    获取优先级模块，配置为获取正在执行的前台任务与所述后台任务群组中的后台任务的优先级；
    所述确定模块还配置为当所述前台任务与所述后台任务群组中的后台 任务的优先级相同时，在所述单位时间内，确定所述后台任务群组中的各个后台任务所允许的运行时间为所述时间阈值除以所述前台任务与所述后台任务群组中的后台任务的数量之和。
  9. 根据权利要求8所述的任务管理系统，其中，所述确定模块还配置为当所述前台任务与所述后台任务群组中的后台任务的优先级不同时，在所述单位时间内，基于所述前台任务与所述后台任务群组中的后台任务的优先级高低并按照预定的算法确定所述后台任务群组中的各个后台任务所允许的运行时间。
  10. 根据权利要求9所述的任务管理系统，其中，所述系统还包括：
    判断模块，配置为判断当各个特定的后台任务均进入等待状态时是否有前台任务正在执行。
    所述确定模块还配置为当判断出当各个特定的后台任务均进入等待状态时有前台任务正在执行，则确定所述前台任务获得全部的资源使用时间；
    休眠模块，配置为当判断出当各个特定的后台任务均进入等待状态时无前台任务正在执行，则进入休眠状态。
  11. 一种计算机存储介质，所述计算机存储介质中存储有计算机可执行指令，该计算机可执行指令配置为执行权利要求1至5任一项所述的任务管理方法。
PCT/CN2016/095561 2015-11-09 2016-08-16 任务管理方法和系统、计算机存储介质 WO2017080273A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US15/773,984 US10802877B2 (en) 2015-11-09 2016-08-16 Task management methods and system, and computer storage medium
EP16863451.7A EP3376379A4 (en) 2015-11-09 2016-08-16 Task management methods and system, and computer storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510759800.6 2015-11-09
CN201510759800.6A CN105320561B (zh) 2015-11-09 2015-11-09 任务管理方法和系统

Publications (1)

Publication Number Publication Date
WO2017080273A1 true WO2017080273A1 (zh) 2017-05-18

Family

ID=55247985

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/095561 WO2017080273A1 (zh) 2015-11-09 2016-08-16 任务管理方法和系统、计算机存储介质

Country Status (4)

Country Link
US (1) US10802877B2 (zh)
EP (1) EP3376379A4 (zh)
CN (1) CN105320561B (zh)
WO (1) WO2017080273A1 (zh)

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105320561B (zh) * 2015-11-09 2019-03-08 深圳市万普拉斯科技有限公司 任务管理方法和系统
CN105320570B (zh) 2015-11-09 2019-01-29 深圳市万普拉斯科技有限公司 资源管理方法和系统
CN107783833B (zh) * 2016-08-25 2020-04-28 华为技术有限公司 一种终端后台应用程序的管理方法及装置
CN106648856A (zh) * 2016-11-24 2017-05-10 深圳市万普拉斯科技有限公司 任务调度方法和装置
CN106843047A (zh) * 2017-01-24 2017-06-13 苏州咖博士咖啡系统科技有限公司 一种咖啡机执行器控制方法
KR20190026231A (ko) * 2017-09-04 2019-03-13 에스케이하이닉스 주식회사 메모리 시스템 및 메모리 시스템의 동작 방법
CN108834157A (zh) * 2018-04-27 2018-11-16 努比亚技术有限公司 网络带宽分配方法、移动终端及计算机可读存储介质
WO2020231196A1 (en) * 2019-05-14 2020-11-19 Samsung Electronics Co., Ltd. Method and system for predicting and optimizing resource utilization of ai applications in an embedded computing system
US11422616B2 (en) * 2020-03-26 2022-08-23 Intel Corporation System, apparatus and method for dynamically adjusting platform power and performance based on task characteristics
US11693702B2 (en) * 2020-04-01 2023-07-04 The Toronto-Dominion Bank Systems and methods for managing usage of computing resources
CN111884823B (zh) * 2020-07-20 2022-12-13 腾讯科技（深圳）有限公司 任务提示方法和装置、存储介质及电子装置
JP2022037737A (ja) * 2020-08-25 2022-03-09 レノボ・シンガポール・プライベート・リミテッド 情報処理装置及び方法
CN113626171B (zh) * 2021-08-26 2024-04-05 北京京东乾石科技有限公司 分析仓储执行设备的任务执行效率的方法、装置及系统
US11921558B1 (en) 2022-11-30 2024-03-05 Intel Corporation Using network traffic metadata to control a processor
CN117632521B (zh) * 2024-01-26 2024-05-03 中电云计算技术有限公司 后台任务的cpu利用率控制方法、装置、设备及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101452404A (zh) * 2008-12-09 2009-06-10 中兴通讯股份有限公司 一种嵌入式操作系统的任务调度装置及方法
CN103049319A (zh) * 2012-12-18 2013-04-17 广东欧珀移动通信有限公司 分时段管理后台应用程序的方法及其终端
CN103176842A (zh) * 2013-03-15 2013-06-26 广东欧珀移动通信有限公司 后台进程管理方法及其移动终端
CN103902364A (zh) * 2012-12-25 2014-07-02 腾讯科技（深圳）有限公司 一种物理资源管理方法、装置及智能终端设备
US8869154B1 (en) * 2010-03-29 2014-10-21 Crimson Corporation Controlling processor usage on a computing device
CN105320561A (zh) * 2015-11-09 2016-02-10 深圳市万普拉斯科技有限公司 任务管理方法和系统
CN105320570A (zh) * 2015-11-09 2016-02-10 深圳市万普拉斯科技有限公司 资源管理方法和系统

Family Cites Families (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6297821B1 (en) * 1998-04-23 2001-10-02 Pitney Bowes Inc. Mailing machine including an embedded control system having a screen control architecture
JP3610930B2 (ja) * 2001-07-12 2005-01-19 株式会社デンソー オペレーティングシステム、プログラム、車両用電子制御装置
US7360216B2 (en) * 2002-07-03 2008-04-15 Nvidia Corporation Method and system for real-time multitasking
JP3920818B2 (ja) * 2003-07-22 2007-05-30 株式会社東芝 スケジューリング方法および情報処理システム
US8060884B2 (en) * 2007-07-10 2011-11-15 Sharp Laboratories Of America, Inc. Deterministic task scheduling in a computing device
EP2449849A4 (en) * 2009-06-29 2013-01-16 Nokia Corp RESOURCES ALLOCATION
KR101651134B1 (ko) * 2010-06-24 2016-08-29 엘지전자 주식회사 이동 단말기 및 이것의 그룹 동작 제어 방법
US8886976B2 (en) * 2011-04-11 2014-11-11 Microsoft Corporation Management of background tasks
US8671299B2 (en) * 2011-05-26 2014-03-11 Google Inc. Delaying the initiation of transitioning to a lower power mode by placing a computer system into an intermediate power mode between a normal power mode and the lower power mode
US9602779B2 (en) * 2012-07-10 2017-03-21 Christopher DeJuliis System for passenger monitoring
US9201693B2 (en) * 2012-09-04 2015-12-01 Microsoft Technology Licensing, Llc Quota-based resource management
US20140113616A1 (en) * 2012-10-19 2014-04-24 Sony Mobile Communications Ab Network initiated terminal background activity control
CN103077086A (zh) * 2013-01-09 2013-05-01 苏州亿倍信息技术有限公司 一种任务分配控制的方法及系统
CN103077083A (zh) * 2013-01-09 2013-05-01 苏州亿倍信息技术有限公司 一种任务处理的方法及系统
US9575634B2 (en) * 2013-03-04 2017-02-21 Facebook, Inc. Techniques for asynchronous rendering
CN104035818A (zh) * 2013-03-04 2014-09-10 腾讯科技（深圳）有限公司 多任务调度的方法及装置
US9336068B2 (en) * 2013-06-07 2016-05-10 Apple Inc. Throttling of application access to resources
CN105378650B (zh) * 2013-07-09 2019-02-19 恩智浦美国有限公司 用于控制处理模块的操作模式的方法和装置
US9798629B1 (en) * 2013-12-16 2017-10-24 EMC IP Holding Company LLC Predicting backup failures due to exceeding the backup window
KR20150136345A (ko) * 2014-05-27 2015-12-07 삼성전자주식회사 태스크 그룹 전달 방법 및 이를 제공하는 전자 장치
KR101513398B1 (ko) * 2014-07-02 2015-04-17 연세대학교 산학협력단 소모전력을 감소시킬 수 있는 단말장치 및 이의 제어방법
US9766960B2 (en) * 2015-01-30 2017-09-19 Salesforce.Com, Inc. Workload-driven techniques for providing biased service level guarantees
CN104657212B (zh) * 2015-02-13 2018-02-16 北京亚信数据有限公司 一种任务调度的方法及系统
CN104820616B (zh) * 2015-04-24 2018-10-30 中国联合网络通信集团有限公司 一种任务调度的方法及装置
CN104834564B (zh) * 2015-05-20 2018-12-14 百度在线网络技术（北京）有限公司 任务调度的方法和装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101452404A (zh) * 2008-12-09 2009-06-10 中兴通讯股份有限公司 一种嵌入式操作系统的任务调度装置及方法
US8869154B1 (en) * 2010-03-29 2014-10-21 Crimson Corporation Controlling processor usage on a computing device
CN103049319A (zh) * 2012-12-18 2013-04-17 广东欧珀移动通信有限公司 分时段管理后台应用程序的方法及其终端
CN103902364A (zh) * 2012-12-25 2014-07-02 腾讯科技（深圳）有限公司 一种物理资源管理方法、装置及智能终端设备
CN103176842A (zh) * 2013-03-15 2013-06-26 广东欧珀移动通信有限公司 后台进程管理方法及其移动终端
CN105320561A (zh) * 2015-11-09 2016-02-10 深圳市万普拉斯科技有限公司 任务管理方法和系统
CN105320570A (zh) * 2015-11-09 2016-02-10 深圳市万普拉斯科技有限公司 资源管理方法和系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3376379A4 *

Also Published As

Publication number Publication date
EP3376379A1 (en) 2018-09-19
CN105320561B (zh) 2019-03-08
CN105320561A (zh) 2016-02-10
US20180321972A1 (en) 2018-11-08
EP3376379A4 (en) 2018-11-14
US10802877B2 (en) 2020-10-13

Similar Documents

Publication Publication Date Title
WO2017080273A1 (zh) 任务管理方法和系统、计算机存储介质
US10467054B2 (en) Resource management method and system, and computer storage medium
CN109582455B (zh) 多线程任务处理方法、装置及存储介质
US9875145B2 (en) Load based dynamic resource sets
JP6799947B2 (ja) スライディングタイムウィンドウを用いてタスクをスケジュール設定するためのシステムおよび方法
US8056083B2 (en) Dividing a computer job into micro-jobs for execution
CN104035818A (zh) 多任务调度的方法及装置
CN106557369A (zh) 一种多线程的管理方法及系统
CN109840149B (zh) 任务调度方法、装置、设备及存储介质
CN109491780B (zh) 多任务调度方法及装置
CN106598740B (zh) 一种限制多线程程序占用cpu利用率的系统及限制方法
CN107624181B (zh) 包括虚拟处理器的闲置和调度的虚拟机管理方法和装备
US10733022B2 (en) Method of managing dedicated processing resources, server system and computer program product
US20160291672A1 (en) Preformance state aware thread scheduling
CN108574600B (zh) 云计算服务器的功耗和资源竞争协同控制的服务质量保障方法
CN103677959A (zh) 一种基于组播的虚拟机集群迁移方法及系统
CN109739634A (zh) 一种原子任务执行方法及装置
CN112860401A (zh) 任务调度方法、装置、电子设备和存储介质
Teng et al. Scheduling real-time workflow on MapReduce-based cloud
CN109189581B (zh) 一种作业调度方法和装置
CN115309507B (zh) 一种cpu资源占用率的计算方法、装置、设备及介质
CN107885589B (zh) 一种作业调度方法及装置
JP2008225641A (ja) コンピュータシステム、割り込み制御方法及びプログラム
US9618988B2 (en) Method and apparatus for managing a thermal budget of at least a part of a processing system
CN114035926A (zh) 应用线程调度方法、装置、存储介质及电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16863451

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15773984

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2016863451

Country of ref document: EP