CN113918309A

CN113918309A - Task queue maintenance method, device, system and medium based on waiting duration

Info

Publication number: CN113918309A
Application number: CN202111424303.2A
Authority: CN
Inventors: 刘阳; 温文坤; 王琳; 刘贝彦
Original assignee: Jixiang Technology Zhejiang Co Ltd
Current assignee: Jixiang Technology Zhejiang Co Ltd
Priority date: 2020-12-31
Filing date: 2021-11-26
Publication date: 2022-01-11

Abstract

The embodiment of the invention discloses a task queue maintenance method and device based on waiting duration, an Internet of things system and a storage medium. The method comprises the following steps: monitoring the task state in the multi-core Internet of things system, wherein each execution core of the multi-core Internet of things system corresponds to one section of a first-in first-out cache queue, and a cache subsection for recording the processing time length of the rest task is arranged in each cache interval; when the latest task is monitored to be input, caching the latest task in a first cache interval so as to be correspondingly distributed to an execution core corresponding to the first cache interval and correspondingly update the processing duration recorded in the cache subsegment, wherein the first cache interval is the cache interval with the shortest processing duration; when it is monitored that the processing time recorded in the cache interval corresponding to the execution core reaches a first threshold value, at least one task in the cache interval is migrated to the first cache interval. According to the scheme, the data processing efficiency of multi-core processing task scheduling in the Internet of things system is improved.

Description

Task queue maintenance method, device, system and medium based on waiting duration

Technical Field

The embodiment of the invention relates to the technical field of networks, in particular to a task queue maintenance method, a task queue maintenance device, a task queue maintenance equipment and a storage medium based on waiting duration.

Background

The internet of things is regarded as a major development and transformation opportunity in the information field, and is expected to bring revolutionary transformation, which has all-round influence on various fields such as industry, agriculture, property, city management, safety fire fighting and the like in a relatively common view. However, technically, the internet of things is not only a main body for changing data transmission, but also has obvious difference from traditional communication. For example, a feature of the large-scale internet of things is that a large number of users sporadically transmit very small packets, unlike conventional cellular communications.

In order to meet the task scheduling requirements in the internet of things, a high-performance embedded node is usually designed for large-scale internet of things to perform parallel processing on data collected in the internet of things, and even a multi-core processing mode is adopted to achieve task scheduling.

The inventor finds that in the process of task scheduling in a multi-core processing mode in a large-scale internet of things, one task may be scheduled for multiple times among multiple execution cores, a large amount of useless scheduling is performed, and scheduling efficiency is low.

Disclosure of Invention

The invention provides a task queue maintenance method, a task queue maintenance device, a task queue maintenance system and a task queue maintenance storage medium based on waiting duration, and aims to solve the technical problem that the scheduling efficiency of multi-core processing task scheduling of the Internet of things is low in the prior art.

In a first aspect, an embodiment of the present invention provides a task queue maintenance method based on a waiting duration, which is used for a multi-core internet of things system, and includes:

monitoring the task state in the multi-core Internet of things system, wherein each execution core of the multi-core Internet of things system is respectively and correspondingly allocated with a cache interval, the cache interval is one section of a first-in first-out cache queue in the multi-core Internet of things system, and each cache interval is provided with a cache subsection for recording the processing time length of the rest task;

when the input of the latest task is monitored, caching the latest task to a first cache interval so as to be correspondingly distributed to an execution core corresponding to the first cache interval, and correspondingly updating the processing duration recorded in the cache subsegment, wherein the first cache interval is the cache interval with the shortest processing duration;

and when monitoring that the processing time recorded in the cache interval corresponding to the execution core reaches a first threshold value, migrating at least one task in the cache interval to the first cache interval.

Further, the method further comprises:

when an idle cache interval is monitored to appear, at least one task cache is migrated from a second cache interval to the idle cache interval so as to be correspondingly distributed to an execution core corresponding to the idle cache interval, and the processing time length recorded in the cache subsegment is correspondingly updated, wherein the idle cache interval is a cache interval with a task being emptied, and the second cache interval is a cache interval with the longest processing time length.

Further, when it is monitored that an idle buffer interval occurs, migrating at least one task buffer from a second buffer interval to the idle buffer interval, including:

when the occurrence of an idle buffer interval is monitored, second buffer intervals are confirmed successively, and task buffers are migrated from the second buffer intervals to the idle buffer intervals one by one until the processing time length in the idle buffer intervals reaches a second threshold value or the processing time lengths in all the buffer intervals are not higher than the second threshold value.

Further, when there are a plurality of second buffer intervals, a task buffer is randomly migrated from one second buffer interval to the idle buffer interval.

Further, when a plurality of first buffer intervals exist, the latest task is randomly buffered to one of the first buffer intervals.

Further, the length of the cache queue corresponding to each execution core is the same.

In a second aspect, an embodiment of the present invention further provides a task queue maintenance device based on a waiting duration, which is used in a multi-core internet of things system, and includes:

the state monitoring unit is used for monitoring the task state in the multi-core Internet of things system, each execution core of the multi-core Internet of things system is respectively and correspondingly allocated with a cache interval, the cache interval is a section of a first-in first-out cache queue in the multi-core Internet of things system, and each cache interval is provided with a cache subsection for recording the processing time length of the rest tasks;

the task caching unit is used for caching the latest task to a first caching interval when the latest task is monitored to be input, so as to correspondingly allocate the latest task to an execution core corresponding to the first caching interval and correspondingly update the processing time length recorded in the caching subsegment, wherein the first caching interval is the caching interval with the shortest processing time length;

the first migration unit is configured to migrate, when it is monitored that the processing time recorded in the cache interval corresponding to the execution core reaches a first threshold value, at least one task in the cache interval to the first cache interval.

Further, the apparatus further includes:

and the second migration unit is used for migrating at least one task cache to the idle cache interval from the second cache interval when the idle cache interval is monitored to appear, so as to be correspondingly distributed to the execution core corresponding to the idle cache interval, and correspondingly update the processing duration recorded in the cache subsegment, wherein the idle cache interval is the cache interval emptied by the task, and the second cache interval is the cache interval with the longest processing duration.

In a third aspect, an embodiment of the present invention further provides an internet of things system, including:

one or more processors;

a memory for storing one or more programs;

when executed by the one or more processors, cause the system of things to implement a latency-based task queue maintenance method as in any one of the first aspects.

In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for maintaining a task queue based on a waiting duration according to the first aspect.

The task queue maintenance method and device based on waiting time, the internet of things system and the storage medium monitor the task state in the multi-core internet of things system, each execution core of the multi-core internet of things system is respectively and correspondingly allocated with a buffer interval, the buffer interval is a section of a first-in first-out buffer queue in the multi-core internet of things system, and each buffer interval is provided with a buffer subsection for recording the processing time of the remaining task; when the input of the latest task is monitored, caching the latest task to a first cache interval so as to be correspondingly distributed to an execution core corresponding to the first cache interval, and correspondingly updating the processing duration recorded in the cache subsegment, wherein the first cache interval is the cache interval with the shortest processing duration; and when monitoring that the processing time recorded in the cache interval corresponding to the execution core reaches a first threshold value, migrating at least one task in the cache interval to the first cache interval. According to the scheme, the corresponding cache intervals are distributed to the execution cores, when the latest task is received, the latest task is distributed to the corresponding cache intervals according to the processing time length in the cache intervals, the switching process of task distribution is reduced, the task with longer waiting time is actively migrated, and the data processing efficiency of multi-core processing task scheduling in the Internet of things system is improved.

Drawings

Fig. 1 is a flowchart of a task queue maintenance method based on waiting duration according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of a task queue maintenance device based on waiting duration according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of an internet of things system according to a third embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are for purposes of illustration and not limitation. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

It should be noted that, for the sake of brevity, this description does not exhaust all alternative embodiments, and it should be understood by those skilled in the art after reading this description that any combination of features may constitute an alternative embodiment as long as the features are not mutually inconsistent.

The following examples are described in detail.

Example one

Fig. 1 is a flowchart of a task queue maintenance method based on a waiting duration according to an embodiment of the present invention. The task queue maintenance method based on the waiting time provided in the embodiment may be performed by various operation devices for task queue maintenance based on the waiting time, where the operation devices may be implemented by software and/or hardware, and the operation devices may be formed by two or more physical entities or may be formed by one physical entity.

Specifically, referring to fig. 1, the task queue maintenance method based on the waiting duration specifically includes:

step S101: and monitoring the task state in the multi-core Internet of things system, wherein each execution core of the multi-core Internet of things system is respectively and correspondingly allocated with a buffer interval, the buffer interval is one section of a first-in first-out buffer queue in the multi-core Internet of things system, and each buffer interval is provided with a buffer subsection for recording the processing time length of the rest task.

In the architecture of the internet of things system, a sink node is a key component of the architecture, in the specific implementation process, the multi-core internet of things system is designed based on an embedded multi-core processor, and a plurality of execution cores in the embedded multi-core processor can perform operation simultaneously, so that higher processing efficiency is brought to data collection in the multi-core internet of things system under the condition of limited resource configuration.

For an embedded multi-core processor, each processing core cannot process all tasks allocated to the processing core at the same time, that is, tasks allocated to one internet of things node may need to be queued, and the tasks in the queued state are temporarily cached in a first-in first-out cache queue. According to the prior art, during the queuing process, the tasks may be continuously scheduled and switched to different execution cores to wait for execution according to the actual processing progress of the execution cores, which is equivalent to performing an invalid scheduling process in the task scheduling process.

In the scheme, in order to improve the scheduling processing efficiency, the first-in first-out cache queue is segmented, each segment corresponds to one execution core, a task specifically allocated to one execution core is cached to a corresponding cache interval first, and through the corresponding allocation mode of the execution cores and the cache intervals, the association relation between the task and the execution core correspondingly processing the task is fixed in a relatively static mode, so that the invalid task allocation scheduling processing is reduced as much as possible. When the fifo buffer queue is segmented, the buffer intervals allocated to each execution core may be set to be the same, that is, the length of the buffer queue corresponding to each execution core is the same, so as to ensure that the upper limit of the task allocated to each execution core is the same, and the amount of the task allocated and scheduled to each execution core is relatively balanced. In each cache interval, besides the cache task, a special storage space is also arranged for recording the processing time length of the remaining tasks in the cache interval, in the scheme, the special storage space is defined as a cache subsection, the processing time length recorded in the cache subsection is maintained by a corresponding execution core, and when the task is processed or the task is cached to the corresponding cache interval, the processing time length of the remaining tasks is updated by the corresponding execution core. And the processing time of each task is comprehensively calculated and judged by the corresponding execution core according to task description, self processing capacity, bandwidth allocation and the like, and the processing time of all tasks in the corresponding cache interval is finally comprehensively updated to the cache subsegment.

Step S102: when the input of the latest task is monitored, caching the latest task to a first cache interval so as to be correspondingly distributed to an execution core corresponding to the first cache interval, and correspondingly updating the processing duration recorded in the cache subsegment, wherein the first cache interval is the cache interval with the shortest processing duration.

For an internet of things node, when receiving input of a latest task, the latest task needs to be allocated to a certain execution core in an embedded multi-core processor of the internet of things node, in the existing processing mode, when all tasks of the current execution cores are to be executed, a first-in first-out cache queue is taken as a whole for cache management, the allocation process of a task to a specific execution core may be continuously adjusted due to the change of task processing progress, so that the task processing states of all execution cores need to be continuously monitored when the task is cached in the first-in first-out cache queue, and further, the task allocation is continuously adjusted adaptively. In the scheme, the latest task is directly distributed to the execution core with the least current processing task, the task distributed to each execution core is relatively fixed, the initially distributed execution core is used for processing the task as a basic processing principle, and distribution variation in the task waiting processing process is reduced. The number of the current processing tasks is represented by the processing time recorded in the cache subsegment, the longer the processing time, the more the current processing tasks, the shorter the processing time, the less the current processing tasks, and for the latest task, caching the latest task to the cache interval with the shortest processing time so as to shorten the waiting time of the latest task as much as possible.

In specific allocation, in order to reduce the queuing waiting time of each task as much as possible, for the detected latest task, the current task state of each execution core is firstly judged. The current task state is confirmed from the buffer interval corresponding to the execution core, and as a whole, the task of the current buffer in the buffer interval is the least, the shorter the occupied buffer queue is, the longer the remaining buffer queue is, the buffer interval with the longest remaining buffer queue is regarded as the first buffer interval, the latest task is allocated to the first buffer interval, after the latest task is buffered in the first buffer interval, the execution core allocated by the latest task is determined according to the corresponding relation between the buffer interval and the execution core, and the processing of the corresponding execution core is waited in the buffer interval.

In the actual processing process, there may be a plurality of buffer intervals in which the remaining tasks are the same, that is, there may be a plurality of buffer intervals that are all first buffer intervals, and when there are a plurality of first buffer intervals, the latest task is randomly buffered in one of the first buffer intervals.

Step S103: and when monitoring that the processing time recorded in the cache interval corresponding to the execution core reaches a first threshold value, migrating at least one task in the cache interval to the first cache interval.

For an actual task processing process, due to reasons of task complexity, data transmission speed, bandwidth allocation and the like, an execution core may need a longer processing time for a certain task, so as to cause a waiting time process of a subsequent task, in order to avoid that the task is in a waiting state for a long time, in the scheme, when the processing time recorded in a certain cache interval reaches a preset first threshold value, at least one task in the cache interval is migrated to a first cache interval, namely to other cache intervals with the shortest processing time, so as to quickly process the task at other execution cores, and reduce the congestion of the task at the certain execution core.

In addition to the basic scheduling, more balanced scheduling can be performed on the tasks through step S104.

Step S104: when an idle cache interval is monitored to appear, at least one task cache is migrated from a second cache interval to the idle cache interval so as to be correspondingly distributed to an execution core corresponding to the idle cache interval, and the processing time length recorded in the cache subsegment is correspondingly updated, wherein the idle cache interval is a cache interval with a task being emptied, and the second cache interval is a cache interval with the longest processing time length.

In the process of processing the task by each execution core, due to reasons such as task complexity, data transmission speed, bandwidth allocation and the like, the speed of task processing may not be completely the same, and finally, the task queuing conditions in the buffer interval are different. For example, some execution cores may have processed all tasks, i.e., have emptied the tasks in the corresponding buffer interval; and a plurality of tasks are queued in the buffer intervals corresponding to other execution cores. At this time, one or more tasks can be migrated from the queued buffer interval to the idle buffer interval, so that the processing speed of the tasks is improved as a whole, and the situation that the execution core is in an idle state is avoided.

When the task is specifically migrated, instead of migrating a plurality of tasks from other buffer intervals to an idle buffer interval at a time, the tasks are migrated one by one, and the processing time length states in all the buffer intervals are judged. Overall, when it is monitored that an idle buffer interval appears, second buffer intervals are confirmed one by one, and task buffers are migrated one by one from the second buffer intervals to the idle buffer intervals until the processing time length in the idle buffer intervals reaches a second threshold value or the processing time lengths in all the buffer intervals are not higher than the second threshold value. In the process of migrating tasks one by one, whether the previously confirmed idle buffer interval reaches a second threshold value or not is judged, if the previously confirmed idle buffer interval reaches the second threshold value, the fact that the idle buffer interval has a certain number of tasks to be processed means that the tasks are not migrated to the idle buffer interval any more, and the task is not migrated to the idle buffer interval until the latest task is allocated to the buffer interval. Meanwhile, in order to avoid too few tasks in other buffer intervals, when the outward migration is performed to a certain extent so that the processing time length in other buffer intervals is not large, namely the remaining processing time length in other buffer intervals is not higher than the second threshold value, the migration is stopped.

In a specific processing process, the processing time of the remaining tasks in the multiple buffer intervals may be longest in parallel, that is, there are multiple second buffer intervals, at this time, instead of directly migrating one task from each second buffer interval to an idle buffer interval, one task buffer is randomly migrated from one second buffer interval to the idle buffer interval, and a successive migration confirmation mode is still adopted, and after one task is migrated, the remaining tasks in the idle buffer intervals and the tasks in other buffer intervals are judged until the set processing time is reached, and the migration is stopped. The task migrated to the idle buffer interval may be the task of the latest buffer or the task of the earliest buffer.

The judgment basis of stopping migration of other buffer intervals can be based on comparison with tasks in the idle buffer intervals besides the second threshold value, and if the number of the remaining tasks in other buffer intervals is not more than one than the number of the tasks in the idle buffer intervals, task migration is not performed.

It should be noted that, in this embodiment, the first buffer interval and the second buffer interval are not one or more fixed buffer intervals, which are only defined differently according to the state of the buffer interval at a certain time, and are special marks for convenience in description of the embodiment, and the functions of the special marks are not different from those of other buffer intervals, and after a current latest task is buffered in a certain first buffer interval, the first buffer interval may not be the first buffer interval when the next latest task is buffered. And the idle buffer interval is defined as the idle buffer interval in the whole migration process, but not defined as the idle buffer interval only if no task exists, and the state definition of the idle buffer interval is finished after the task migration of a certain buffer interval is finished in terms of the task queuing state.

Meanwhile, in the present solution, it should be understood that steps S101 to S103 exist as a whole, which are not sequentially executed in the strict order described above, when the multi-core internet of things system processes the tasks, the assignment of the latest task and the migration of the task may be executed according to the actual monitoring result, and when the latest task is monitored, the latest task is cached; and when the idle buffer interval is monitored, migrating the task to the idle buffer interval, if the latest task is continuously monitored, continuously executing the step S102, and if the idle buffer interval is continuously monitored, continuously executing the step S103.

Monitoring the task state in the multi-core internet of things system, wherein each execution core of the multi-core internet of things system is respectively and correspondingly allocated with a buffer interval, the buffer interval is a section of a first-in first-out buffer queue in the multi-core internet of things system, and each buffer interval is provided with a buffer subsection for recording the processing duration of the remaining tasks; when the input of the latest task is monitored, caching the latest task to a first cache interval so as to be correspondingly distributed to an execution core corresponding to the first cache interval, and correspondingly updating the processing duration recorded in the cache subsegment, wherein the first cache interval is the cache interval with the shortest processing duration; and when monitoring that the processing time recorded in the cache interval corresponding to the execution core reaches a first threshold value, migrating at least one task in the cache interval to the first cache interval. According to the scheme, the corresponding cache intervals are distributed to the execution cores, when the latest task is received, the latest task is distributed to the corresponding cache intervals according to the processing time length in the cache intervals, the switching process of task distribution is reduced, the task with longer waiting time is actively migrated, and the data processing efficiency of multi-core processing task scheduling in the Internet of things system is improved.

Example two

Fig. 2 is a schematic structural diagram of a task queue maintenance device based on waiting duration according to a second embodiment of the present invention. Referring to fig. 2, the waiting time-based task queue maintaining apparatus includes: a status listening unit 210, a task caching unit 220, and a first migration unit 230.

The state monitoring unit 210 is configured to monitor a task state in the multi-core internet of things system, where each execution core of the multi-core internet of things system is respectively and correspondingly allocated with a buffer interval, the buffer interval is a segment of a first-in first-out buffer queue in the multi-core internet of things system, and each buffer interval is provided with a buffer sub-segment for recording processing time of a remaining task; the task caching unit 220 is configured to cache the latest task in a first caching interval when it is monitored that the latest task is input, so as to be correspondingly allocated to an execution core corresponding to the first caching interval, and correspondingly update the processing duration recorded in the caching sub-segment, where the first caching interval is a caching interval with the shortest processing duration; the first migration unit 230 is configured to, when it is monitored that the processing time recorded in the cache interval corresponding to the execution core reaches a first threshold value, migrate at least one task in the cache interval to the first cache interval.

On the basis of the above embodiment, the apparatus further includes:

On the basis of the foregoing embodiment, when it is monitored that an idle buffer interval occurs, migrating at least one task buffer from a second buffer interval to the idle buffer interval includes:

On the basis of the above embodiment, when there are a plurality of second buffer intervals, a task buffer is randomly migrated from one second buffer interval to the idle buffer interval.

On the basis of the above embodiment, when there are a plurality of first buffer intervals, the latest task is randomly buffered to one of the first buffer intervals.

On the basis of the above embodiment, the length of the buffer queue corresponding to each execution core is the same.

The task queue maintenance device based on the waiting time provided by the embodiment of the invention is included in the task queue maintenance equipment based on the waiting time, can be used for executing any task queue maintenance method based on the waiting time provided by the first embodiment, and has corresponding functions and beneficial effects.

EXAMPLE III

Fig. 3 is a schematic structural diagram of node devices of the internet of things according to a third embodiment of the present invention, where the node devices of the internet of things are used to form a system of the internet of things, so as to comprehensively implement task scheduling in this scheme. As shown in fig. 3, the node apparatus of the internet of things includes a processor 310, a memory 320, an input device 330, an output device 340, and a communication device 350; the number of the processors 310 in the node device of the internet of things may be one or more, and one processor 310 is taken as an example in fig. 3; the processor 310, the memory 320, the input device 330, the output device 340 and the communication device 350 in the node device of the internet of things may be connected through a bus or other manners, and fig. 3 illustrates the connection through the bus as an example.

The memory 320 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the task queue maintenance method based on waiting duration in the embodiment of the present invention (for example, the status snooping unit 210, the task caching unit 220, and the first migration unit 230 in the task queue maintenance device based on waiting duration). The processor 310 executes various functional applications and data processing of the node device of the internet of things by running software programs, instructions and modules stored in the memory 320, that is, the task queue maintenance method based on the waiting time is implemented.

The memory 320 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the node device of the internet of things, and the like. Further, the memory 320 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 320 may further include memory located remotely from the processor 310, which may be connected to the internet of things node device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 330 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the internet of things node device. The output device 340 may include a display device such as a display screen.

The node equipment of the Internet of things comprises the task queue maintenance device based on the waiting time, can be used for executing any task queue maintenance method based on the waiting time, and has corresponding functions and beneficial effects.

Example four

Embodiments of the present invention further provide a storage medium containing computer-executable instructions, where the computer-executable instructions are used to perform relevant operations in the task queue maintenance method based on waiting duration provided in any embodiment of the present application when executed by a computer processor, and have corresponding functions and beneficial effects.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product.

Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A task queue maintenance method based on waiting duration is used for a multi-core Internet of things system and is characterized by comprising the following steps:

when the task is processed, updating the processing time of the rest tasks;

2. The method of claim 1, further comprising:

3. The method of claim 2, wherein when it is monitored that a free buffer interval occurs, migrating at least one task buffer from a second buffer interval to the free buffer interval, comprises:

4. The method of claim 3, wherein when there are multiple second buffer intervals, a task buffer is randomly migrated from one of the second buffer intervals to the free buffer interval.

5. The method of claim 1, wherein when there are multiple first buffer intervals, the latest task is randomly buffered into one of the first buffer intervals.

6. The method of claim 1, wherein the length of the buffer queue corresponding to each execution core is the same.

7. A task queue maintenance device based on latency, comprising:

the task caching unit is used for caching the latest task to a first caching interval when the latest task is monitored to be input, so as to correspondingly allocate the latest task to an execution core corresponding to the first caching interval and correspondingly update the processing time length recorded in the caching subsegment, wherein the first caching interval is the caching interval with the shortest processing time length; the system is also used for updating the processing duration of the rest tasks after the tasks are processed;

8. The apparatus of claim 7, further comprising:

9. An internet of things system, comprising:

one or more processors;

a memory for storing one or more programs;

when executed by the one or more processors, cause the system of things to implement the latency-based task queue maintenance method of any of claims 1-6.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for maintaining a task queue based on latency periods according to any one of claims 1 to 6.