WO2024001159A1

WO2024001159A1 - Resource scheduling method and apparatus, and electronic device and storage medium

Info

Publication number: WO2024001159A1
Application number: PCT/CN2023/071687
Authority: WO
Inventors: 冯旭
Original assignee: 中兴通讯股份有限公司
Priority date: 2022-06-27
Filing date: 2023-01-10
Publication date: 2024-01-04
Also published as: CN117349002A

Abstract

The present disclosure belongs to the technical field of electronic digital data processing. Provided are a resource scheduling method and apparatus, and an electronic device and a storage medium. The method comprises: determining the interaction type of a target task; calculating a task proportion between a target task load of the interaction type and the total task load of a task pool to be subjected to processing, wherein the target task load is the total number of tasks belonging to the interaction type in said task pool; comparing the task proportion with a preset resource proportion of the interaction type; performing discrete adjustment on an initial sequence serial number of the target task according to a comparison result, wherein the sequence serial number represents an execution sequence of the target task in said task pool; and performing task resource scheduling according to the sequence serial number, which has been subjected to discrete adjustment.

Description

Resource scheduling method, device, electronic equipment and storage medium

Cross-references to related applications

This disclosure claims the priority of Chinese patent application CN202210744631.9 titled "Resource Scheduling Method, Device, Electronic Equipment and Storage Medium" submitted on June 27, 2022, the entire content of which is incorporated into this disclosure by reference.

Technical field

The present disclosure relates to the technical field of electronic digital data processing, and in particular, to a resource scheduling method, device, electronic equipment and storage medium.

Background technique

As the openness of software systems improves, users can operate the system in many different ways. Faced with this kind of random multi-interaction operation, the system often suffers from uneven resource allocation and resource waste problems such as scheduling blocking, because it is impossible to predict the user interaction mode in a certain period of time. This method often causes the system to be slow, and even the effect of continuously improving resources is not obvious, resulting in low resource utilization.

Currently, in the field of software technology, most use channel-based resource scheduling, that is, each interaction is given certain resources, which indeed plays a role in resource isolation. However, due to the random nature of interactions, one type of interaction may account for a large proportion in a certain period of time, and the resources of the other interaction cannot be utilized. Moreover, due to the fixed nature of resource allocation, resource utilization is lower for certain interactive users. .

Contents of the invention

The present disclosure provides a resource scheduling method, device, electronic equipment and storage medium to solve the technical problem of low resource utilization in related technologies.

Embodiments of the present disclosure provide a resource scheduling method, including: determining the interaction type of a target task; calculating the task ratio between the target task amount of the interaction type and the total task amount of the task pool to be processed, where the target task amount is The total number of tasks belonging to the interaction type in the task pool to be processed; compare the task proportion and the size of the preset resource proportion of the interaction type; make discrete adjustments to the initial sequence number of the target task based on the comparison result, where the sequence number represents the target task in the pending task pool. Process the execution sequence in the task pool; schedule task resources according to the discretely adjusted sequence number.

Embodiments of the present disclosure also provide a resource scheduling device, including: a judgment module configured to judge the interaction type of a target task; a calculation module configured to calculate the target task amount of the interaction type and the total task amount of the task pool to be processed. The target task amount is the total amount of tasks belonging to the interactive type in the to-be-processed task pool; the comparison module is configured to compare the task ratio and the size of the preset resource ratio of the interaction type; the discrete module is configured to compare according to As a result, the initial sequence number of the target task is discretely adjusted, where the sequence number represents the execution order of the target task in the task pool to be processed; the scheduling module is configured to schedule task resources according to the discretely adjusted sequence number.

Embodiments of the present disclosure also provide a storage medium, which includes a stored program, and performs the above steps when the program is run.

Embodiments of the present disclosure also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the resource scheduling method as described above is implemented. step.

The present disclosure also provides a computer program product containing instructions, which when run on a computer, causes the computer to perform the steps in the above method.

Description of drawings

The drawings described here are used to provide a further understanding of the present disclosure and constitute a part of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the attached picture:

Figure 1 is a hardware structural block diagram of a computer according to an embodiment of the present disclosure;

Figure 2 is a flow chart of a resource scheduling method according to an embodiment of the present disclosure;

Figure 3 is a schematic diagram of a scenario implementation in an embodiment of the present disclosure;

Figure 4 is a structural block diagram of a resource scheduling device according to an embodiment of the present disclosure.

Detailed ways

In order to enable those skilled in the art to better understand the present disclosure, the following will clearly and completely describe the technical solutions in the present disclosure embodiments in conjunction with the accompanying drawings. Obviously, the described embodiments are only These are part of the embodiments of this disclosure, not all of them. Based on the embodiments in this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts should fall within the scope of protection of this disclosure. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.

The terms "first", "second", etc. in the description and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances so that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, e.g., a process, method, product or apparatus that encompasses a series of steps or units need not be limited to those steps explicitly listed or units, but may include other steps or units not expressly listed or inherent to such processes, methods, products or devices.

The method embodiment provided in Embodiment 1 of the present disclosure can be executed on a mobile phone, computer, tablet, or similar computing device. Taking running on a computer as an example, FIG. 1 is a hardware structure block diagram of a computer according to an embodiment of the present disclosure. As shown in Figure 1, the computer may include one or more (only one is shown in Figure 1) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and A memory 104 for storing data. In an exemplary embodiment, the above-mentioned computer may also include a transmission device 106 and an input and output device 108 for communication functions. Persons of ordinary skill in the art can understand that the structure shown in Figure 1 is only illustrative and does not limit the structure of the above-mentioned computer. For example, the computer may also include more or fewer components than shown in FIG. 1 , or have a different configuration than that shown in FIG. 1 .

The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as a computer program corresponding to a resource scheduling method in an embodiment of the present disclosure. The processor 102 runs the computer program stored in the memory 104, thereby Execute various functional applications and data processing, that is, implement the above methods. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory located remotely from processor 102, and these remote memories may be connected to the computer through a network. Examples of the above-mentioned networks include but are not limited to the Internet, intranets, local area networks, mobile communication networks and combinations thereof.

Transmission device 106 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by the computer's communication provider. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC for short), which can be connected to other network devices through a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (Radio Frequency, RF for short) module, which is used to communicate with the Internet wirelessly.

This embodiment provides a resource scheduling method. Figure 2 is a flow chart of a resource scheduling method according to an embodiment of the present disclosure. As shown in Figure 2, the process includes the following steps S10 to S50.

S10, determine the interaction type of the target task.

In the embodiment of the present disclosure, the target task refers to the task currently to be entered into the pending task pool. The interaction type of a target task can refer to the source or manner of the target task. In an exemplary embodiment, for example, the 5G network management system mainly provides two external interaction methods: GUI (Graphical User Interface, graphical user interface) and API (Application Programming Interface, application program interface). Then, in the 5G network management system scenario The interaction types of target tasks can be divided into two types: GUI and API. For another example, for a certain life software system, depending on the source of the task, the interaction type of the target task can be computer access, mobile phone access, and other three-party access.

The method of determining the interaction type of the target task may be by identifying the type identifier carried by the target task, or based on the source or method of the target task, which is not specifically limited in this embodiment of the disclosure.

S20: Calculate the task ratio between the target task amount of the interactive type and the total task amount of the to-be-processed task pool, where the target task amount is the total amount of tasks of the interactive type in the to-be-processed task pool.

After determining the interaction type of the target task, this embodiment calculates the proportion of tasks of this interaction type based on the total number of tasks belonging to this interaction type in the to-be-processed task pool and the total task amount of the task pool. For example, if the target task type is GUI, the number of GUI type tasks in the pending task pool is 10, and the number of other types, that is, API type tasks, is 90, or in other words, the ratio of GUI to API tasks in the pending task pool is 1 :9, then through calculation it can be concluded that the proportion of tasks with the interaction type GUI in the pending task pool is 1/10.

S30: Compare the task proportion and the preset resource proportion of the interaction type.

In the embodiment of the present disclosure, a preset resource ratio is set for each type of task before resource scheduling is performed. The preset resource ratio can be a default initial ratio, or a custom-set ratio. When the ratio is a custom When set, this value can be adjusted at any time during the scheduling process according to the situation.

The preset resource ratio is to provide the scheduling target. Task resource scheduling is performed based on the task ratio obtained in S20 and the preset resource ratio, so that the proportion of various types of tasks in the resource scheduling process is infinitely close to the set preset resource ratio. . In an exemplary embodiment, the proportion of each task type in the task pool to be processed can be compared with the preset resource proportion. If the task proportion of the interaction type to which the target task belongs is greater than or equal to the preset resource proportion of the interaction type, It means that this interaction type accounts for a large proportion in the to-be-processed task pool. Currently, there are many tasks of this interaction type and exceeds the preset resource ratio. Then the execution of the target task will be delayed and the proportion of tasks of this interaction type will be reduced. On the contrary, if the target task belongs to The proportion of tasks of the interaction type is smaller than the preset resource proportion of the interaction type, indicating that the interaction type of the target task accounts for a small proportion in the to-be-processed task pool. Currently, there are few tasks of this interaction type, and there is still room for resource allocation of this type. Then execute the target task in advance to increase the proportion of tasks of this interaction type. By delaying the execution of interactive tasks that are larger than the preset resource ratio, and executing in advance the interactive tasks that are smaller than the preset resource ratio, the tasks are balanced to approach the set preset resource ratio.

For example, the default ratio of resources allocated to GUI tasks and API tasks in a certain network management system is 6:4, which means that during a period of time, GUI and API interact in parallel, and GUI resources occupy more resources, which means tasks that require the same resources. The GUI method is faster to complete, and the ratio of GUI to API tasks in the pending task pool is 1:9. If the target task type to be added to the task pool is GUI, the proportion of tasks of this type in the pending task pool is 1 /10, which is less than the default resource ratio of this type 6/10, indicating that there are currently few GUI interaction types, so you can execute it in advance or execute as many GUI types as possible to make the task resource scheduling close to the set default resource ratio.

S40: Discretely adjust the initial sequence number of the target task according to the comparison result, where the sequence number represents the execution order of the target task in the task pool to be processed.

S50: Schedule task resources according to the discretely adjusted sequence number.

Since repeated adjustments to tasks will reduce efficiency, in the embodiment of the present disclosure, a sequence number is added to each task. The sequence number is bound to an original target task and is used to represent the order in which the target tasks are executed after entering the task pool to be processed. Task resource scheduling is performed according to the sequence number corresponding to each task.

The initial sequence number is the original default execution order of the task without adjustment. According to the comparison result of the task proportion and the preset resource proportion, the original execution order of the target task is adjusted forward or delayed, so that the target task is added to the pending task pool. To make the resource scheduling in the task pool approach a preset resource ratio, in an exemplary embodiment, the adjustment method may be an arithmetic advance or an arithmetic delay. Considering that simply moving forward or delaying the order of target tasks will lead to the aggregation of similar interactive tasks and break the randomness of interactions, therefore, in order to avoid balanced insertion disrupting the original discreteness, in the embodiment of the present disclosure, the target tasks are The adjustment of the initial sequence number of the task is a discrete adjustment. The discrete adjustment method can be by randomizing the number of steps forward or delayed for the target task, without fixing the number of steps forward or delayed for each target task, thereby performing discrete adjustment. Adjustment.

This disclosed embodiment performs resource scheduling based on the proportion of the interaction type of the target task in the task pool and the preset resource ratio of the interaction type, so that the task ratio in the task pool to be processed is as close as possible to the preset resource ratio, and resource scheduling is more efficient. Reasonable, improve resource utilization, by adding a sequence number to each task, preventing repeated adjustments to tasks, improving the efficiency of the resource scheduling method in this embodiment, and discretizing the adjustment of the sequence number of the target task, preventing Tasks of the same type are gathered during the process, retaining the original randomness of resource scheduling as much as possible.

In one embodiment, S40, discretely adjusting the initial sequence number of the target task according to the comparison result includes steps S41 to S42.

Step S41, if the task proportion is greater than or equal to the preset resource proportion, a random backoff factor is generated, and the initial sequence number of the target task is delayed based on the random backoff factor. Step S42: If the task proportion is less than the preset resource proportion, a random forward factor is generated, and the initial sequence number of the target task is moved forward according to the random forward factor.

In order to avoid balanced insertion and disrupting the original discreteness of user behavior, embodiments of the present disclosure use random factors to discretize the forward movement and delay of the target task, and randomize the forward and backward movement of the target task, so that the proportion after adding the target task Jumps around the current proportion number, and the jump degree is evenly distributed within the interval. When the proportion of tasks corresponding to the target task type in the to-be-processed task pool is greater than or equal to the preset resource proportion, the execution sequence of the target task needs to be delayed. In this embodiment, the number of delayed steps is not fixed and directly accumulated arithmetic. The backoff factor is randomly generated, the number of delayed backoff steps is randomized, and the initial sequence number of the target task is delayed according to the backoff factor, so that each target task that needs to be delayed is randomly and discretely inserted into a later position in the to-be-processed task pool; When the proportion of tasks corresponding to the target task type in the to-be-processed task pool is less than the preset resource proportion, the execution order of the target task needs to be advanced. This embodiment randomly generates a forwarding factor to randomize the number of steps for moving the target task forward. Thus, each target task that needs to be advanced is randomly and discretely inserted into the front position of the to-be-processed task pool.

The method of generating a random forward factor or a random backward factor can be to first determine the value range of the forward factor and the backward factor, and then use a random number generator to generate a random number within the specified value range, and use the resulting random number as the random forward factor. The shift factor and the random backward factor ensure that the number of steps forward or backward is random according to the random backward factor and the random forward factor, so that the position of the target task inserted into the task pool is discretely balanced.

In one implementation, the random forwarding factor is generated by using a linear congruence method to generate a random forwarding factor in a preset interval.

In this embodiment, the method of randomly generating forward factors is implemented by using the linear congruence method, in which the range of the forward factors can be [1, the number of task processing capabilities]. The linear congruence method is a pseudo-random sequence generation algorithm. The pseudo-random numbers are realized by adding a software algorithm and a random number seed. The seed is similar to the encryption key in the cryptographic algorithm. Different seeds correspond to different random numbers. By pairing The previous number is subjected to a linear operation and modulo to obtain the next number, producing a piecewise linear equation with a pseudo-random sequence of discontinuous calculations, and the resulting random numbers present a pseudo-uniform distribution.

The embodiment of the present disclosure randomizes the forward and backward movement of target tasks to avoid task aggregation and maintain the original random characteristics.

In one embodiment, scheduling task resources according to the discretely adjusted sequence number includes: determining the first task in the current to-be-processed task pool according to the discretely-adjusted sequence number, where the first task is the first task in the current to-be-processed task pool. The task with the smallest sequence number; allocate currently available resources to the first task to execute the first task.

During the task scheduling process, each time a task is selected, the first task in the current task pool is selected to allocate currently available resources for execution. The first task is the current highest priority task, that is, the task with the smallest sequence number or the highest order.

Although resource proportions are preset for each type of task in the embodiments of the disclosed resource scheduling method, the preset resource proportion is to provide a scheduling target so that the proportion of each type of task in the resource scheduling process is infinitely close to the set preset resources. The ratio is not used to divide the allocation ratio of resources when executing tasks. Therefore, after determining the first task in the current to-be-processed task pool, this embodiment does not distinguish between task types and will allocate currently available resources to execute the first task. Understandably, when there is only one type of task during the runtime, that type of task will occupy all resources.

This embodiment implements the priority allocation of currently available resources to execute the task with the smallest sequence number in the task pool to be processed.

In one embodiment, determining the first task in the current to-be-processed task pool based on the discretely adjusted sequence number includes: constructing a minimum heap based on the sequence numbers of all tasks in the current to-be-processed task pool; The corresponding task is regarded as the first task in the current task pool.

The tasks in the task pool to be processed have corresponding sequence numbers. In the embodiment of the present disclosure, a minimum heap is constructed based on the sequence numbers of all tasks in the task pool to be processed. The method of constructing the minimum heap can be implemented through the array storage structure of a complete binary tree. , so that when fetching the top element of the heap, the smallest one is always obtained first. The sequence number on the top of the smallest heap is the current frontmost or highest priority sequence number, and the task corresponding to this sequence number is selected as the first in the current task pool. One task is executed.

In one embodiment, discretely adjusting the sequence number of the target task according to the comparison result also includes: determining whether the target task is an urgent task; if the target task is an urgent task, generating a maximum forwarding factor; and advancing the emergency according to the maximum forwarding factor. The sequence number of the task in the pending task pool.

Urgent tasks refer to important or urgent tasks that require high priority processing. The maximum forwarding factor indicates that the sequence number of the emergency task is directly forwarded to the frontmost movement parameter in the task pool. This disclosed embodiment adds top-level scheduling for redline high-risk tasks. When it is determined that the interaction type of the target task is a redline high-risk emergency task, the emergency task is directly set to a maximum forwarding factor that is much higher than other ones. The maximum forwarding factor is used to directly The sequence number of the emergency task is moved to the front of the task pool, allowing the current resources to execute the top-level task with the highest priority.

The embodiments of the present disclosure realize the highest priority processing of emergency tasks.

In one embodiment, before determining the interaction type of the target task, the method includes: receiving a user instruction; and setting a preset resource ratio for each interaction type task in response to the user instruction.

In the embodiment of the present disclosure, the preset resource ratio can be set according to user instructions, and a preset resource ratio is set for each interaction type task by receiving user instructions. For example, due to different usage scenarios of each network management system, there are many API-type tasks under minimalist calls. Users can set GUI:API=1:9 in the configuration center to allocate more resources to API tasks.

In the embodiment of the present disclosure, the preset resource ratio is set according to user instructions, making resource allocation and scheduling more reasonable and effective.

Referring to Figure 3, Figure 3 is a schematic diagram of a scenario implementation in an embodiment of the present disclosure.

As shown in Figure 3, in the embodiment of the resource scheduling method of the present disclosure, it is divided into four processes: resource proportion setting, task pre-balancing judgment, task weight discretization, and task balancing scheduling.

Resource ratio setting, used to set resource ratio. After the resource ratio is set, it can still be adjusted during the scheduling process. The subsequent resource scheduling process will make the ratio of each task in the to-be-processed task pool approach the set ratio during resource scheduling. For example, the default GUI (WEB page mode) of the network management system: API (command line mode) = 6:4, which means that the GUI and API modes interact in parallel for a period of time, and the GUI resources occupy more resources, which means that tasks that require the same resources, the GUI mode Complete faster. This method is the preset behavior of the network management system, because the usage scenarios of network management systems in various places are different. For example, under minimalist call, there are many command line methods. You can directly set the GUI: API = 1:9 in the configuration center. During the process You can also switch settings as needed. This ratio is an approximate ratio. As tasks accumulate, the scheduling process approaches this ratio infinitely.

Task pre-balancing judgment means judging the interaction type of the target task to be added to the pending task pool, and judging whether the target task needs to be moved forward or delayed based on the proportion of the interaction type in the task pool and the set resource ratio. If the proportion of this interaction type in the task pool is greater than the set resource proportion, the judgment result is that there are many tasks of the current interaction type, and the execution should be delayed to approach the proportion. On the contrary, if it is less than the set resource ratio, the judgment result is that the current interaction type is small, and it should be executed in advance or as much as possible to approach the standard ratio. For example, the network management system issues a task carrying an identifier. The system can identify whether the task type is GUI or API, and obtain the proportion of each interaction type in the current task pool. When it is greater than or equal to the preset resource proportion, the current task will be added directly. You can press etc. The difference is 1 and is accumulated. When it is less than the preset resource ratio, it can be moved forward according to the current interaction ratio of the resource to achieve a pre-balanced state. It is understandable that the above methods are used for explanation and do not constitute an advance or additional limitation of this embodiment. Other methods that are not limited to arithmetic can be used in specific implementations, and the embodiments of this disclosure are not specifically limited. This state is a relatively approximate state, which means that the current task is in a more balanced state after it is added than before it was added.

Task heavy discretization means that due to the random discreteness of the task, the task will be balanced after the pre-balanced determination of the previous task. However, the balancing process causes similar interactive tasks to aggregate, breaking the randomness of user interaction, and avoiding disruption caused by balanced insertion. Due to the original discrete nature of user behavior, this process makes a heavy discrete secondary adjustment to the location selection, making the forward and backward movements random and discretizing, so that the task distribution in the task pool maintains the original discrete random characteristics. That is, after each task is pre-balanced and judged, for scenarios that do not meet the preset resource ratio, a random factor is added to the forward or delayed point, so that the ratio jumps around the current interaction ratio, and the jump degree is evenly distributed within the interval. . For example, when the 5G network management system mainly moves tasks forward in this step, it uses the linear congruence method to generate random factors in the interval [1, number of task processing capabilities], so that the forward movement is consistent with the random factors, so that the tasks at multiple times are The proportion number jumps around the current interaction proportion number, and the degree of jump is evenly distributed within the interval. Among them, the linear congruence method is a pseudo-random number that can present a pseudo-uniform distribution. In specific embodiments, random factors can also be generated according to other methods.

Task balanced scheduling, this process mainly selects the highest priority or several of them from the task pool for execution. The task pre-balancing discrimination and task re-discretization process are all processed by the task pool to be executed, and what is maintained is a pre-state of the sequence. That is, after balancing and discretization, repeated adjustments to the original tasks will reduce the efficiency, so the task pre-balancing discrimination and task The re-discretization process simply adds a random sequence number to each task, and the sequence number is bound to an original task. During the task scheduling process, each time a task is selected, the random sequence numbers of all tasks in the task pool in this state are used to construct a minimum heap. The sequence at the top of the heap is the current top or highest priority sequence, and the task bound to this sequence number is selected. execution, the execution period is still in equilibrium. The tasks that have been through task pre-balanced discrimination and task re-dispersion processes not only follow the proportion set by the user, but also maintain the random characteristics of the task.

This implementation scenario also adds top-level scheduling for redline high-risk tasks. For some specific tasks, if it is judged to be a redline high-risk emergency task, directly set a random value much higher than other sequences, and move the emergency task to the front. Without increasing resources, let current resources perform top-level tasks with the highest priority.

The embodiments of the present disclosure balance tasks at a preset ratio through task pre-balancing and re-dispersion, which can maximize the utilization of resources in proportion to users, and maintain the random discreteness of the original tasks, thereby improving the utilization of resources to the maximum capacity, and During pre-equilibration, the heavy discretization process can also retain top-level scheduling to provide the highest priority for high-risk redline tasks.

Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is Better implementation. Based on this understanding, the technical solution of the present disclosure can be embodied in the form of a software product in essence or that contributes to the existing technology. The computer software product is stored in a storage medium (such as ROM/RAM, disk, CD), including several instructions to cause a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present disclosure.

This embodiment also provides a visualization device for the interactive process, which is used to implement the above embodiments and preferred implementations. What has already been explained will not be described again. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

Figure 4 is a structural block diagram of a resource scheduling device according to an embodiment of the present disclosure. As shown in Figure 4, the resource scheduling device includes: a judgment module 100, a calculation module 200, a comparison module 300, a discrete module 400, and a scheduling module 500 ,in,

The judgment module 100 is configured to judge the interaction type of the target task;

The calculation module 200 is configured to calculate the task ratio between the target task amount of the interaction type and the total task amount of the to-be-processed task pool, where the target task amount is the total amount of tasks belonging to the interaction type in the to-be-processed task pool;

The comparison module 300 is configured to compare the task proportion and the size of the preset resource proportion of the interaction type;

The discrete module 400 is configured to discretely adjust the initial sequence number of the target task according to the comparison result, where the sequence number represents the execution order of the target task in the task pool to be processed;

The scheduling module 500 is configured to schedule task resources according to the discretely adjusted sequence numbers.

In an exemplary embodiment, the discrete module includes: a first discrete subunit configured to generate a random backoff factor if the task ratio is greater than or equal to the preset resource ratio, and delay the initial sequence number of the target task according to the random backoff factor. ; The second discrete sub-unit, if the task proportion is less than the preset resource proportion, generates a random forwarding factor, and moves forward the initial sequence number of the target task according to the random forwarding factor.

In an exemplary embodiment, the second discrete sub-unit includes: a forwarding factor generation unit configured to generate a random forwarding factor in a preset interval using a linear congruence method.

In an exemplary embodiment, the scheduling module includes: a scheduling subunit configured to determine the first task in the current to-be-processed task pool according to the discretely adjusted sequence number, where the first task is the sequence in the current to-be-processed task pool. The task with the smallest number; allocate currently available resources to the first task to execute the first task.

In an exemplary embodiment, the scheduling subunit also includes: a first task determination unit configured to construct a minimum heap based on the sequence numbers of all tasks in the current to-be-processed task pool; and use the task corresponding to the sequence number at the top of the minimum heap as The first task in the current task pool.

In an exemplary embodiment, the comparison module further includes: an emergency task number unit configured to determine whether the target task is an emergency task; if the target task is an emergency task, generate a maximum forwarding factor; and advance the emergency task according to the maximum forwarding factor. Sequence number in the pending task pool.

In an exemplary embodiment, the resource scheduling device further includes: a preset resource ratio setting unit configured to receive user instructions; and in response to user instructions, set a preset resource ratio for each interaction type task.

Each of the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but is not limited to this: the above modules are all located in the same processor; or the above modules are located in different processors in any combination. in the processor.

The present disclosure also proposes an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

In an exemplary embodiment, the above-mentioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the above-mentioned processor, and the input-output device is connected to the above-mentioned processor.

In an exemplary embodiment, in the embodiment of the present electronic device, the above-mentioned processor may be configured to perform the following steps S1 to S5 through a computer program.

Step S1: Determine the interaction type of the target task. Step S2: Calculate the task ratio between the target task volume of the interactive type and the total task volume of the to-be-processed task pool, where the target task volume is the total number of interactive-type tasks in the to-be-processed task pool. Step S3: Compare the task proportion and the preset resource proportion of the interaction type. Step S4: Discretely adjust the initial sequence number of the target task according to the comparison result, where the sequence number represents the execution order of the target task in the task pool to be processed. Step S5: Schedule task resources according to the discretely adjusted sequence numbers.

In an exemplary embodiment, for specific examples in the embodiments of the electronic device of the present disclosure, reference may be made to the examples described in the above-mentioned embodiments and optional implementations, which will not be described again in this embodiment.

An embodiment of the present disclosure also provides a storage medium in which a computer program is stored, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

In an exemplary embodiment, in the embodiment of the present storage medium, the above-mentioned storage medium may be configured to store a computer program for performing the following steps, including steps S1 to S5.

Step S1: Determine the interaction type of the target task. Step S2: Calculate the task ratio between the target task volume of the interactive type and the total task volume in the task pool to be processed, where the target task volume is the total number of tasks belonging to the interactive type in the task pool to be processed. Step S3: Compare the task proportion and the preset resource proportion of the interaction type. Step S4: Discretely adjust the initial sequence number of the target task according to the comparison result, where the sequence number represents the execution order of the target task in the task pool to be processed. Step S5: Schedule task resources according to the discretely adjusted sequence numbers.

In an exemplary embodiment, the specific embodiments of the storage medium of the present disclosure are basically the same as the above method embodiments, and will not be described again here.

In an exemplary embodiment, in this embodiment, the above-mentioned storage medium may include but is not limited to: U disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as Various media that can store computer programs such as RAM), removable hard drives, magnetic disks or optical disks.

The above serial numbers of the embodiments of the present disclosure are only for description and do not represent the advantages and disadvantages of the embodiments.

In the above-mentioned embodiments of the present disclosure, each embodiment is described with its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

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

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

In addition, each functional unit in various embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above integrated units can be implemented in the form of hardware or software functional units.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to cause a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present disclosure. The aforementioned storage media include: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program code. .

The above are only preferred embodiments of the present disclosure. It should be pointed out that for those of ordinary skill in the art, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications can also be made. should be regarded as the scope of protection of this disclosure.

Claims

A resource scheduling method including:

Determine the interaction type of the target task;

Calculate the task ratio between the target task amount of the interaction type and the total task amount of the to-be-processed task pool, where the target task amount is the total amount of tasks belonging to the interaction type in the to-be-processed task pool;

Compare the task proportion and the preset resource proportion of the interaction type;

Discretely adjust the initial sequence number of the target task according to the comparison result, where the sequence number represents the execution order of the target task in the task pool to be processed;

Task resource scheduling is performed based on discretely adjusted sequence numbers.
The resource scheduling method according to claim 1, wherein discretely adjusting the initial sequence number of the target task according to the comparison result includes:

If the task proportion is greater than or equal to the preset resource proportion, a random backoff factor is generated, and the initial sequence number of the target task is delayed according to the random backoff factor;

If the task proportion is less than the preset resource proportion, a random forward factor is generated, and the initial sequence number of the target task is moved forward according to the random forward factor.
The resource scheduling method as claimed in claim 2, wherein generating a random forward factor includes:

Use the linear congruence method to generate random forward factors for the preset interval.
The resource scheduling method according to claim 1, wherein scheduling task resources according to the discretely adjusted sequence number includes:

Determine the first task in the current to-be-processed task pool based on the discretely adjusted sequence number, where the first task is the task with the smallest sequence number in the current to-be-processed task pool;

Allocate currently available resources to the first task to execute the first task.
The resource scheduling method according to claim 4, wherein determining the first task in the currently pending task pool according to the discretely adjusted sequence number includes:

Build a minimum heap based on the sequence numbers of all tasks in the current pending task pool;

The task corresponding to the top sequence number of the minimum heap is regarded as the first task in the current task pool.
The resource scheduling method according to claim 1, wherein discretely adjusting the sequence number of the target task according to the comparison result further includes:

Determine whether the target task is an urgent task;

If the target task is an urgent task, the maximum forward factor is generated;

Advance the sequence number of the emergency task in the pending task pool according to the maximum forwarding factor.
The resource scheduling method according to claim 1, wherein before determining the interaction type of the target task, the method includes:

receive user instructions;

In response to the user instruction, a preset resource ratio is set for each interaction type task.
A resource scheduling device, including:

The judgment module is configured to judge the interaction type of the target task;

A calculation module configured to calculate a task ratio between the target task amount of the interaction type and the total task amount of the to-be-processed task pool, wherein the target task amount is the interaction type in the to-be-processed task pool. Total amount of tasks;

A comparison module configured to compare the task proportion and the size of the preset resource proportion of the interaction type;

A discrete module configured to discretely adjust the initial sequence number of the target task according to the comparison result, wherein the sequence number represents the execution order of the target task in the task pool to be processed;

A scheduling module configured to schedule task resources based on discretely adjusted sequence numbers.
An electronic device, including a memory, a processor and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, any one of claims 1 to 7 is implemented. The steps of the resource scheduling method described in one item.
A storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the resource scheduling method according to any one of claims 1 to 7 are implemented.