WO2020259208A1

WO2020259208A1 - Memory scheduling method and apparatus, device and storage medium

Info

Publication number: WO2020259208A1
Application number: PCT/CN2020/093404
Authority: WO
Inventors: 王鹏
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-06-25
Filing date: 2020-05-29
Publication date: 2020-12-30
Also published as: CN110427273A

Abstract

The present application relates to the field of data storage. Disclosed are a memory scheduling method and apparatus, a device and a storage medium. The method comprises: determining an initial memory from a shared memory, and establishing, according to the initial memory, a hierarchical memory pool for use by a client, wherein the hierarchical memory pool comprises a plurality of sub-hierarchical memory pools, and the sub-hierarchical memory pool comprises a plurality of memory blocks; receiving a memory application request sent by the client, wherein the memory application request comprises the required length and required quantity of required memory blocks; determining a target sub-hierarchical memory pool from the hierarchical memory pool according to the required length; and allocating memory blocks to the client from the determined target sub-hierarchical memory pool according to the required quantity. Thus, memory utilization is improved, and memory is saved.

Description

Memory scheduling method, device, equipment and storage medium

This application claims the priority of the Chinese patent application filed with the Chinese Patent Office on June 25, 2019, the application number is 201910553419.2, and the invention title is "Memory scheduling method, device, equipment and storage medium", the entire content of which is incorporated by reference In this application.

Technical field

This application relates to the field of computer technology, and in particular to a memory scheduling method, device, device and storage medium.

Background technique

For stand-alone client and server programs, it is usually necessary for a server to correspond to multiple clients for data exchange. A common method is to use shared memory, that is, there is a server that can be shared by different clients Logical memory accessed.

For multiple clients, if each client maps a memory pool in the shared memory, in the actual use of the memory pool, due to the real-time and volatility of the client's usage of the memory pool, it may There will be an unbalanced resource allocation of the memory pool, that is, the usage rate of some memory pools in a certain period of time is too high, while the usage rate of the memory pool in other periods of time is lower. The inventor realizes that high usage of the memory pool usually causes the application process of the client to run slower. Therefore, the unbalanced resource allocation of the memory pool will not only slow down the running speed of the client, but also reduce the utilization of shared memory, resulting in a waste of memory.

Therefore, how to save memory and improve memory utilization has become an urgent problem to be solved.

technical problem

This application provides a memory scheduling method, device, equipment, and storage medium, so as to save memory and improve memory utilization.

Technical solutions

In the first aspect, this application provides a memory scheduling method, which includes:

Determining an initial memory from the shared memory, and establishing a hierarchical memory pool for use by the client according to the initial memory, the hierarchical memory pool including multiple sub-level memory pools, the sub-level memory pool including multiple memory blocks;

Receiving a memory application request sent by the client, where the memory application request includes the required length and the required quantity of the required memory block;

Determining a target sub-level memory pool from the level memory pool according to the required length;

Allocating memory blocks for the client from the determined target sub-level memory pool according to the required quantity.

In the second aspect, the present application also provides a memory scheduling device, the device including:

The determining establishment unit is configured to determine an initial memory from the shared memory, and establish a hierarchical memory pool for the client to use according to the initial memory, the hierarchical memory pool includes multiple sub-level memory pools, and the sub-level memory pool includes multiple Memory block

An application receiving unit, configured to receive a memory application request sent by the client, where the memory application request includes the required length and the required quantity of the required memory block;

A sub-level determining unit, configured to determine a target sub-level memory pool from the level memory pool according to the required length;

The memory allocation unit is configured to allocate memory blocks for the client from the determined target sub-level memory pool according to the demand quantity.

In a third aspect, the present application also provides a computer device, the computer device includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and execute the The computer program implements the above-mentioned memory scheduling method, including:

In a fourth aspect, this application also provides a computer-readable storage medium that stores a computer program that when executed by a processor causes the processor to implement the memory scheduling method described above ,include:

Beneficial effect

This application discloses a memory scheduling method, device, equipment, and storage medium. The initial memory is determined from the shared memory and a hierarchical memory pool is established for the client to use, and then a memory application request sent by the client is received, according to the memory application request The required length of the required memory block in the middle level determines the target sub-level memory pool from the level memory pool, and then allocates the memory block in the target sub-level memory pool according to the number of required memory blocks in the memory application request. Allocate memory for the client according to the memory request sent by the client, so that the server can allocate memory according to the memory usage requirements of the client, thereby improving the utilization of shared memory and saving memory.

Description of the drawings

FIG. 1 is a schematic flowchart of steps of a memory scheduling method provided by an embodiment of the present application;

2 is a schematic diagram of the framework of a hierarchical memory pool provided by an embodiment of the present application;

3 is a schematic flowchart of sub-steps of determining initial memory from shared memory provided by an embodiment of the present application;

4 is a schematic flowchart of sub-steps of the memory scheduling method in FIG. 1;

FIG. 5 is a schematic flowchart of another memory scheduling method provided by an embodiment of the present application;

FIG. 6 is a schematic flowchart of sub-steps of the memory scheduling method provided in FIG. 5;

FIG. 7 is a schematic block diagram of a memory scheduling device provided by an embodiment of the present application;

FIG. 8 is a schematic block diagram of another memory scheduling device provided by an embodiment of the present application;

FIG. 9 is a schematic block diagram of the structure of a computer device provided by an embodiment of the present application.

The best mode of the invention

The embodiments of the present application provide a memory scheduling method, device, computer equipment, and storage medium. The memory scheduling method is used to improve the utilization of shared memory and save memory when one server uses shared memory to interact with multiple clients.

Hereinafter, some embodiments of the present application will be described in detail with reference to the accompanying drawings. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of steps of a memory scheduling method provided by an embodiment of the present application. The memory scheduling method is to allocate memory according to the actual memory usage requirements of the client, so as to achieve the purpose of improving the utilization of shared memory and saving memory.

As shown in Figure 1, the memory scheduling method specifically includes the following:

S101. Determine an initial memory from the shared memory, and establish a hierarchical memory pool for use by the client according to the initial memory.

Among them, the hierarchical memory pool includes multiple sub-level memory pools, and the sub-level memory pool includes multiple memory blocks. In the specific implementation process, the number of memory blocks in each sub-level memory pool can be the same or different, and each sub-level memory pool can include memory blocks of different lengths, and of course, can also include all memory blocks of the same length. For example, one sub-level memory pool may include memory blocks with a length of 4K and 32K, respectively, and another sub-level memory pool includes memory blocks with a length of 32K.

Please refer to FIG. 2, which is a schematic diagram of the framework of a hierarchical memory pool provided by an embodiment of the present application.

Among them, the hierarchical memory pool may include n sub-level memory pools, each sub-level memory pool includes m _n memory blocks, and the length of the memory block is 4K, 32K, and 64K. Among them, n≥1, m _n ≥2, and n and m _n are both positive integers. It should be noted that the length of the memory block listed in this embodiment only illustrates the process of establishing the sub-level memory pool, and does not limit the length of the memory block in the sub-memory pool.

Specifically, as shown in Figure 2, the sub-level memory pool 1 includes m ₁ memory blocks with a length of 4K, and the sub-level memory pool 2 includes memory blocks with a length of 4K and 32K, and memory blocks with two lengths. The sum of the numbers of is m ₂ , the sub-level memory pool n includes memory blocks with lengths of 4K, 32K, and 64K, and the sum of the numbers of memory blocks with three lengths is m ₃ .

In the specific implementation process, after the client connects to the server for the first time, the server determines the initial memory allocated for the client from the shared memory, and establishes a hierarchical memory pool for the client to use in the shared memory according to the initial memory.

In one embodiment, as shown in FIG. 3, the step of determining the initial memory from the shared memory includes step S101a and step S101b.

S101a. When the configuration memory of the client is less than the maximum free memory of the shared memory, use the configuration memory of the client as the initial memory; S101b. When the configuration memory of the client is greater than or equal to the maximum free memory of the shared memory, set the shared memory The maximum free memory of the pool is used as the initial memory.

The configuration memory of the client can be configured according to actual requirements, for example, it can be preset according to the configuration of the client. Specifically, the configured memory of the client refers to the length and number of memory blocks configured for the client.

For example, the configuration memory set for the client is 16 memory blocks with a length of 32K.

When the maximum free memory of the shared memory is 50 memory blocks with a length of 32K, and the configuration memory of the client is less than the maximum free memory of the shared memory at this time, the configuration memory of the client can be used as the initial memory.

When the maximum free memory of the shared memory is 10 memory blocks with a length of 32K, and the configured memory of the client is greater than the maximum free memory of the shared memory at this time, the maximum free memory of the shared memory can be used as the initial memory.

When the maximum free memory of the shared memory is 16 memory blocks with a length of 32K, the configuration memory of the client is equal to the maximum free memory of the shared memory. The maximum free memory of the shared memory can be used as the initial memory, or the client’s Configure memory as initial memory.

By comparing the maximum free memory of the shared memory with the configured memory of the client, a smaller memory is used as the initial memory for the client to allocate memory, which can avoid the excessive initial memory allocated to the client, which causes a waste of memory Happening.

S102. Receive a memory application request sent by the client.

Wherein, the memory application request includes the required length and the required quantity of the required memory block. Specifically, the client needs to use the memory blocks in the hierarchical memory pool in the process of implementing its functions. Therefore, when the client realizes its functions, it can send a memory request request to apply for the required memory block according to the required length and the required quantity. , And the server receives the memory request sent by it.

In the specific implementation process, the client can send a memory application request to the server based on a preset memory application rule. The preset memory application rule may be a mapping relationship rule between the function to be implemented by the client and the length and number of memory blocks required to implement the function.

For example, the realization of the client's password login function requires 10 memory blocks of 4K in length, and the realization of the client's face recognition function requires 50 memory blocks of 32K in length. When the client needs to implement the function of password login, it can send a memory application request to the server based on the preset memory application rules to apply for 10 memory blocks with a length of 4K to achieve this function.

S103. Determine a target sub-level memory pool from the level memory pool according to the required length.

Specifically, when there are free memory blocks with the same length as the required length in the sub-level memory pool, the sub-level memory pool is determined as the target sub-level memory pool, so that the server can serve as the client from the target sub-level memory pool. The end allocates memory blocks.

In the specific implementation process, when there are multiple sub-level memory pools in the hierarchical memory pool that all have free memory blocks with the same length as the required length, the server can select a sub-level memory from the multiple sub-level memory pools that meet the aforementioned conditions The pool is used as the target sub-level memory pool, and multiple sub-level memory pools can also be selected as the target sub-level memory pool from multiple sub-level memory pools that meet the aforementioned conditions. The server selection of a sub-level memory pool or multiple sub-level memory pools can be determined according to the actual situation.

S104. Allocate memory blocks for the client from the determined target sub-level memory pool according to the required quantity.

Specifically, after the server determines the target sub-level memory pool, it can allocate free memory blocks equal to the required number from the target sub-level memory pool from the target sub-level memory pool for use by the client according to the number of needs of the client. Specifically, the server fulfills the needs of the client according to the allocated memory block.

In the specific implementation process, when the server selects multiple sub-level memory pools as the target sub-level memory pool, when the server allocates free memory blocks according to the required quantity, it can select multiple sub-level memory as the target sub-level memory pool. Select a sub-level memory pool for priority allocation in the pool. That is, a sub-level memory pool is selected from the multiple sub-level memory pools, and all the free memory blocks in the sub-level memory pool are allocated to the client. If there are still shortcomings, another sub-level memory pool is selected from the multiple sub-level memory pools for priority allocation.

For example, the server selects sub-level memory pool 1, sub-level memory pool 2, and sub-level memory pool 3 as the target sub-level memory pools. Among them, the sub-level memory pool 1 has 7 free memory blocks, the sub-level memory pool 2 has 5 free memory blocks, and the sub-level memory pool 3 has 6 free memory blocks. The number of free memory blocks required by the client is 10. At this time, the server can first allocate the 7 free memory blocks in the sub-level memory pool 1 to the client, and then allocate the 3 free memory blocks in the sub-level memory pool 2 to the client to complete the allocation.

In one embodiment, referring to FIG. 4, step S104 may include the following steps:

S104a: Calculate the complementary quantity of the required memory block.

In this embodiment, the supplementary quantity is the difference between the required quantity and the quantity of free memory blocks in the target sub-level memory pool.

Specifically, the calculating the complementary quantity of the required memory blocks includes: calculating the complementary quantity of the required memory blocks according to a quantity calculation formula.

The quantity calculation formula is:

Among them, Y is the number of supplements, P is the number of requirements, R ₁ is the i-th target sub-level memory pool, n is the number of target sub-level memory pools in the hierarchical memory pool, m ₁ is the i-th target sub-level memory pool The number of memory blocks required.

For example, the required number of required memory blocks is 50. And the server selects five sub-level memory pools from the level memory pool as the target sub-level memory pool. Among the five sub-level memory pools as the target sub-level memory pool, two sub-level memory pools each include 5 free memory blocks, one sub-level memory pool includes 8 free memory blocks, and the two sub-level memory pools each include 10 A free memory block. According to the above-mentioned quantity calculation formula, the supplementary quantity can be calculated as follows:

Y=50-(2×5+1×8+2×10)=12;

S104b: When the supplementary quantity is a positive integer, allocate memory blocks from the shared memory to the target sub-level memory pool according to the supplementary quantity and the required length.

Specifically, when the number of supplements is a positive integer, it means that the number of requirements of the client is more than the number of free memory blocks in the target sub-level memory pool at this time, and the memory blocks in the target sub-level memory pool cannot satisfy the client's use At this time, the server can allocate memory blocks from the shared memory for the target sub-level memory pool according to the number of supplements and the required length to meet the needs of the client. The length of the memory block allocated from the shared memory is consistent with the length of the client. The required length of the required memory block is the same.

When the number of supplements is 0 or a negative number, it means that the client's demand is less than the number of free memory blocks in the target sub-level memory pool. The server can directly allocate free memory blocks to the client from the target sub-level memory pool. To meet the needs of the client.

In the above embodiment, the client establishes a hierarchical memory pool in the shared memory. The client sends a memory application request to the server when it needs to use the memory block, and then the server allocates the required memory block from the hierarchical memory pool to the client according to the needs of the client. End-use, so that the server can allocate memory according to the client's real-time memory usage requirements, thereby increasing the usage rate of shared memory and saving memory.

Please refer to FIG. 5, which is a schematic flowchart of another memory scheduling method provided by an embodiment of the present application. The memory scheduling method can enable the server to monitor the memory usage of the client in real time after allocating the memory to the client, so as to actively allocate the memory according to the real-time memory usage of the client and increase the memory usage rate.

As shown in FIG. 5, the memory scheduling method specifically includes: step S201 to step S206.

S201. Determine an initial memory from the shared memory, and establish a hierarchical memory pool for use by the client according to the initial memory.

Specifically, the hierarchical memory pool includes multiple sub-level memory pools, and the sub-level memory pool includes multiple memory blocks. In a specific implementation process, the number of memory blocks in each sub-level memory pool may be the same or different, and each sub-level memory pool may include memory blocks of different lengths, and of course, may also include all memory blocks of the same length. For example, one sub-level memory pool may include memory blocks with a length of 4K and 32K, respectively, and another sub-level memory pool includes memory blocks with a length of 32K.

S202: Receive a memory application request sent by the client.

Wherein, the memory application request includes the required length and the required quantity of the required memory block. Specifically, the client needs to use the memory blocks in the hierarchical memory pool in the process of implementing its functions. Therefore, when the client realizes its functions, it can send a memory request request to the server to apply according to the required length and the required quantity. The memory block is required, and the memory request sent by the server is received.

S203: Determine a target sub-level memory pool from the level memory pool according to the required length.

S204. Allocate a memory block for the client from the determined target sub-level memory pool according to the required quantity.

S205. Obtain memory usage information of the target sub-level memory pool calculated by the client within a preset time period.

Specifically, after the server allocates memory blocks to the client according to the usage requirements of the client, the client monitors and counts the allocated memory blocks, and calculates the memory usage information of the memory block within a preset time period, and then The calculated memory usage information is sent to the server. In a specific implementation process, the preset time period may be a preset use time period. For example, the client uses one minute as the preset time period to count the memory usage information of the memory block within one minute.

In one embodiment, the memory usage information may include the usage rate of the memory block. The memory usage information of the target sub-level memory pool calculated by the client within a preset time period includes:

Count the number of used memory blocks in the target sub-level memory pool within a preset time period; based on the usage rate calculation formula, calculate the use rate of the memory blocks in the target sub-level memory pool according to the number of used memory blocks . In the specific implementation process, the used memory block refers to the memory block currently being used by the client.

Specifically, the usage rate calculation formula is:

Among them, U _f is the usage rate of the memory block with the length of f in the target sub-level memory pool, Q is the number of used memory blocks with the length of f in the target sub-level memory pool; S _θ is including l _e The number of target sub-level memory pools of a memory block of length f, j is the number of target sub-level memory pools with a memory block of memory block length f, and l _e is the memory block in the e-th target sub-level memory pool The number of memory blocks of length f.

For example, in the hierarchical memory pool, the number of target sub-level memory pools with a memory block length of 64K is 3, and the sum of the number of used memory blocks with a memory block length of 64K in the 3 target sub-level memory pools is 10. Among them, the number of target sub-level memory pools including 10 memory blocks with a length of 64K is two, and the number of target sub-level memory pools including 20 memory blocks with a length of 64K is one. Then the usage rate of the 64K memory block in the target sub-level memory pool can be calculated by the above formula:

S206: Allocate memory blocks of the target sub-level memory pool according to the memory usage information.

Specifically, the server allocates the memory blocks of the target sub-level memory pool according to the memory usage information sent by the client. In the specific implementation process, allocating the memory blocks of the target sub-level memory pool may include allocating memory blocks from the shared memory to the target sub-level memory pool, or releasing memory blocks in the target sub-level memory pool.

In an embodiment, in order to actively optimize the memory allocation of the client during the use of the client to improve the experience of the client, as shown in FIG. 6, step S106 may further include substeps S206a and S206b.

S206a: If the usage rate is greater than the first usage threshold, allocate a memory block from the shared memory to the target sub-level memory pool according to the length of the memory block in the target sub-level memory pool.

Specifically, the length of the memory block allocated from the shared memory is the same as the length of the memory block whose usage rate is greater than the first usage threshold in the target sub-level memory pool.

In the specific implementation process, the first usage threshold can be set according to actual needs. After obtaining the usage rate of a memory block of a certain length calculated by the client, the server compares the usage rate with the first usage threshold. If the usage rate is greater than the first usage threshold, it means that the client uses a large amount of memory block of this length at this time, and the server can allocate the memory block from the shared memory to the target sub-level memory block, where, The length of the memory block allocated by the server from the shared memory is the same as the length of the memory block whose usage rate is greater than the first usage threshold, so as to actively allocate the memory block in real time.

In an embodiment, the number of memory blocks allocated from the shared memory may be one-half of the number of memory blocks of this length in the target sub-level memory pool.

S206b: If the usage rate is less than the second usage threshold, release free memory blocks in the target sub-level memory pool.

Specifically, the length of the free memory block is the same as the length of the memory block whose usage rate is less than the second usage threshold in the target sub-level memory pool.

In the specific implementation process, the second usage threshold can be set according to actual needs. After obtaining the usage rate of a memory block of a certain length calculated by the client, the server compares the usage rate with the second usage threshold. If the usage rate is less than the second usage threshold, it means that the client's usage of the memory block of this length is small and there are more free memory blocks. In order to increase the usage rate of the memory block, the server can set the target The free memory block of this length in the sub-level memory block is released, so that the free memory block in the target sub-level memory pool will not always be occupied. After the free memory block is released, the free memory block can be used by other clients. The problem of memory waste caused by the client's continuous occupation of free memory blocks is avoided.

In the memory scheduling method provided by the foregoing embodiment, after the client is allocated memory according to the initial memory, the client can obtain the memory usage information of the target sub-level memory pool calculated by the client within a preset time period, so that the server can be based on the memory. Use the information to actively allocate the memory blocks in the target sub-level memory pool in real time to achieve real-time on-demand allocation of memory and improve memory usage.

Please refer to FIG. 7. FIG. 7 is a schematic block diagram of a memory scheduling device provided by an embodiment of the present application, and the memory scheduling device is configured to execute the foregoing memory scheduling method. Wherein, the memory scheduling device can be configured in a server or a terminal.

Among them, the server can be an independent server or a server cluster. The terminal can be an electronic device such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device.

As shown in FIG. 7, the memory scheduling device 300 includes: a determination establishment unit 301, an application receiving unit 302, a sub-level determination unit 303 and a memory allocation unit 304.

The determining establishment unit 301 is configured to determine an initial memory from the shared memory, and establish a hierarchical memory pool for the client to use according to the initial memory.

In one embodiment, the determining establishment unit 301 includes a configuration memory subunit 3011 and a free memory subunit 3012.

Specifically, the configuration memory subunit 3011 is used to use the configuration memory of the client as the initial memory when the configuration memory of the client is less than the maximum free memory of the shared memory; the free memory subunit 3012 is used for when the configuration memory of the client is greater than When it is equal to the maximum free memory of the shared memory, the maximum free memory of the shared memory pool is used as the initial memory.

The application receiving unit 302 is configured to receive a memory application request sent by the client.

The sub-level determining unit 303 is configured to determine a target sub-level memory pool from the level memory pool according to the required length.

The memory allocation unit 304 is configured to allocate a memory block for the client from the determined target sub-level memory pool according to the demand quantity.

In one embodiment, the memory allocation unit 304 includes a supplement calculation sub-unit 3041 and a supplement allocation sub-unit 3042.

Specifically, the supplement calculation sub-unit 3041 is used to calculate the supplementary quantity of the required memory block; the supplementary allocation sub-unit 3042 is used to, when the supplementary quantity is a positive integer, from the supplementary quantity and the required length from the Allocate memory blocks from the shared memory to the target sub-level memory pool.

Please refer to FIG. 8. FIG. 8 is a schematic block diagram of another memory scheduling device provided by an embodiment of the present application, and the memory scheduling device is used to execute the foregoing memory scheduling method. Wherein, the memory scheduling device can be configured in the server.

As shown in FIG. 8, the memory scheduling device 400 includes: a determination establishment unit 401, an application receiving unit 402, a sub-level determination unit 403, a memory allocation unit 404, an information acquisition unit 405 and a memory allocation unit 406.

The determining establishment unit 401 is configured to determine an initial memory from the shared memory, and establish a hierarchical memory pool for the client to use according to the initial memory.

The application receiving unit 402 is configured to receive a memory application request sent by the client.

The sub-level determining unit 403 is configured to determine a target sub-level memory pool from the level memory pool according to the required length.

The memory allocation unit 404 is configured to allocate a memory block for the client from the determined target sub-level memory pool according to the demand quantity.

The information acquiring unit 405 is configured to acquire the memory usage information of the target sub-level memory pool calculated by the client within a preset time period.

The memory allocation unit 406 is configured to allocate memory blocks of the target sub-level memory pool according to the memory usage information.

Wherein, in one embodiment, the memory allocation unit 406 includes: a memory block calling subunit 4061 and a memory block releasing subunit 4062.

Specifically, the memory block calling subunit 4061 is configured to allocate a memory block from the shared memory to the target according to the length of the memory block in the target sub-level memory pool if the usage rate is greater than the first usage threshold. Sub-level memory pool; a memory block release sub-unit 4062, if the usage rate is less than the second usage threshold, release free memory blocks in the target sub-level memory pool.

It should be noted that those skilled in the art can clearly understand that, for convenience and concise description, the specific working process of the memory scheduling device and each unit described above can refer to the corresponding process in the foregoing memory scheduling method embodiment. I will not repeat them here.

The foregoing memory scheduling device may be implemented in the form of a computer program, and the computer program may run on the computer device shown in FIG. 9.

Please refer to FIG. 9, which is a schematic block diagram of the structure of a computer device according to an embodiment of the present application. The computer device can be a server or a terminal.

Referring to FIG. 9, the computer device includes a processor, a memory, and a network interface connected by a system bus, where the memory may include a non-volatile storage medium and an internal memory.

The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any memory scheduling method.

The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any memory scheduling method.

The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art can understand that the structure shown in FIG. 9 is only a block diagram of part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. The specific computer equipment may Including more or less parts than shown in the figure, or combining some parts, or having a different part arrangement.

It should be understood that the processor may be a central processing unit (Central Processing Unit, CPU), the processor may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), and application specific integrated circuits (Application Specific Integrated Circuits). Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor.

Wherein, in an embodiment, the processor is used to run a computer program stored in a memory to implement the following steps:

Determine the initial memory from the shared memory, establish a hierarchical memory pool for the client to use according to the initial memory, the hierarchical memory pool includes a plurality of sub-level memory pools, the sub-level memory pool includes a plurality of memory blocks; receiving the A memory application request sent by the client, where the memory application request includes the required length of the required memory block and the required quantity; the target sub-level memory pool is determined from the hierarchical memory pool according to the required length; the target sub-level memory pool is determined according to the required quantity Allocate memory blocks for the client in the target sub-level memory pool of.

In an embodiment, when the processor implements the determination of the initial memory from the shared memory, it is used to implement:

When the configuration memory of the client is less than the maximum free memory of the shared memory, the configuration memory of the client is used as the initial memory; when the configuration memory of the client is greater than or equal to the maximum free memory of the shared memory, the maximum free memory of the shared memory pool is set The memory is used as the initial memory.

In an embodiment, when the processor realizes the allocation of a memory block for the client from the determined target sub-level memory pool according to the demand quantity, the processor is configured to realize:

Calculate the complementary quantity of the required memory block, the complementary quantity is the difference between the required quantity and the number of free memory blocks in the target sub-level memory pool; when the complementary quantity is a positive integer, according to the complementary quantity And the required length allocates a memory block from the shared memory to the target sub-level memory pool.

Wherein, in another embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

Determine the initial memory from the shared memory, establish a hierarchical memory pool for the client to use according to the initial memory, the hierarchical memory pool includes a plurality of sub-level memory pools, the sub-level memory pool includes a plurality of memory blocks; receiving the A memory application request sent by the client, where the memory application request includes the required length of the required memory block and the required quantity; the target sub-level memory pool is determined from the hierarchical memory pool according to the required length; the target sub-level memory pool is determined according to the required quantity Allocate memory blocks for the client in the target sub-level memory pool of the client; obtain the memory usage information of the target sub-level memory pool calculated by the client within a preset period of time; The memory blocks of the sub-level memory pool are allocated.

In one embodiment, the memory usage information includes the usage rate of the memory block in the target sub-level memory pool; the processor is implementing the comparison of the memory usage of the target sub-level memory pool according to the memory usage information. When the block is deployed, it is used to achieve:

If the usage rate is greater than the first usage threshold, allocate a memory block from the shared memory to the target sub-level memory pool according to the length of the memory block in the target sub-level memory pool, and the shared memory The length of the memory block allocated in the target sub-level memory pool is the same as the length of the memory block whose usage rate is greater than the first usage threshold.

If the usage rate is less than the second usage threshold, release free memory blocks in the target sub-level memory pool, and the length of the free memory block and the usage rate in the target sub-level memory pool are less than the second usage The threshold memory block length is the same.

The embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium may be non-volatile or volatile. The computer-readable storage medium stores a computer program, the computer program includes program instructions, and the processor executes the program instructions to implement any of the memory scheduling methods provided in the embodiments of the present application, including:

The computer-readable storage medium may be the internal storage unit of the computer device described in the foregoing embodiment, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SMC), or a secure digital (Secure Digital, SD) equipped on the computer device. ) Card, Flash Card, etc.

Claims

A memory scheduling method, which includes:

Determining an initial memory from the shared memory, and establishing a hierarchical memory pool for use by the client according to the initial memory, the hierarchical memory pool including multiple sub-level memory pools, the sub-level memory pool including multiple memory blocks;

Receiving a memory application request sent by the client, where the memory application request includes the required length and the required quantity of the required memory block;

Determining a target sub-level memory pool from the level memory pool according to the required length;

Allocating memory blocks for the client from the determined target sub-level memory pool according to the required quantity.
The memory scheduling method according to claim 1, wherein said determining the initial memory from the shared memory comprises:

When the configuration memory of the client is less than the maximum free memory of the shared memory, use the configuration memory of the client as the initial memory;

When the configured memory of the client is greater than or equal to the maximum free memory of the shared memory, the maximum free memory of the shared memory pool is used as the initial memory.
The memory scheduling method according to claim 1, wherein the allocating a memory block for the client from the determined target sub-level memory pool according to the demand quantity comprises:

Calculate the complementary quantity of required memory blocks, where the complementary quantity is the difference between the required quantity and the quantity of free memory blocks in the target sub-level memory pool;

When the supplementary quantity is a positive integer, a memory block is allocated from the shared memory to the target sub-level memory pool according to the supplementary quantity and the required length.
The memory scheduling method according to claim 3, wherein the calculating the complementary quantity of the required memory blocks comprises: calculating the complementary quantity of the required memory blocks according to a quantity calculation formula;

The quantity calculation formula is:

Wherein, Y is a complement number, P is the number of needs, R i is the i-th sub-level target memory pool, n is the number of target sub-level hierarchical memory pool memory pool, m i is the i th sub-goal level memory pool The number of memory blocks required.
The memory scheduling method according to claim 1, further comprising:

Acquiring memory usage information of the target sub-level memory pool calculated by the client within a preset time period;

Allocate memory blocks of the target sub-level memory pool according to the memory usage information.
The memory scheduling method according to claim 5, wherein the memory usage information includes the usage rate of the memory blocks in the target sub-level memory pool; and the comparison of the target sub-level memory pool based on the memory usage information The memory block is allocated, including:

If the usage rate is greater than the first usage threshold, allocate a memory block from the shared memory to the target sub-level memory pool according to the length of the memory block in the target sub-level memory pool, and the shared memory The length of the memory block allocated in the target sub-level memory pool is the same as the length of the memory block whose usage rate is greater than the first usage threshold.
The memory scheduling method according to claim 5, wherein the memory usage information includes the usage rate of the memory blocks in the target sub-level memory pool; and the comparison of the target sub-level memory pool based on the memory usage information The memory block is allocated, including:

If the usage rate is less than the second usage threshold, release free memory blocks in the target sub-level memory pool, and the length of the free memory block and the usage rate in the target sub-level memory pool are less than the second usage The threshold memory block length is the same.
A memory scheduling device, which includes:

The determining establishment unit is configured to determine an initial memory from the shared memory, and establish a hierarchical memory pool for the client to use according to the initial memory, the hierarchical memory pool includes multiple sub-level memory pools, and the sub-level memory pool includes multiple Memory block

An application receiving unit, configured to receive a memory application request sent by the client, where the memory application request includes the required length and the required quantity of the required memory block;

A sub-level determining unit, configured to determine a target sub-level memory pool from the level memory pool according to the required length;

The memory allocation unit is configured to allocate memory blocks for the client from the determined target sub-level memory pool according to the demand quantity.
A computer device, wherein the computer device includes a memory and a processor;

The memory is used to store computer programs;

The processor is configured to execute the computer program and implement a memory scheduling method when the computer program is executed, including:

Determining an initial memory from the shared memory, and establishing a hierarchical memory pool for use by the client according to the initial memory, the hierarchical memory pool including multiple sub-level memory pools, the sub-level memory pool including multiple memory blocks;

Receiving a memory application request sent by the client, where the memory application request includes the required length and the required quantity of the required memory block;

Determining a target sub-level memory pool from the level memory pool according to the required length;

Allocating memory blocks for the client from the determined target sub-level memory pool according to the required quantity.
The computer device according to claim 9, wherein said determining the initial memory from the shared memory comprises:

When the configuration memory of the client is less than the maximum free memory of the shared memory, use the configuration memory of the client as the initial memory;

When the configured memory of the client is greater than or equal to the maximum free memory of the shared memory, the maximum free memory of the shared memory pool is used as the initial memory.
9. The computer device according to claim 9, wherein the allocating a memory block for the client from the determined target sub-level memory pool according to the demand quantity comprises:

Calculate the complementary quantity of required memory blocks, where the complementary quantity is the difference between the required quantity and the quantity of free memory blocks in the target sub-level memory pool;

When the supplementary quantity is a positive integer, a memory block is allocated from the shared memory to the target sub-level memory pool according to the supplementary quantity and the required length.
11. The computer device according to claim 11, wherein the calculating the complementary quantity of the required memory blocks comprises: calculating the complementary quantity of the required memory blocks according to a quantity calculation formula;

The quantity calculation formula is:

Wherein, Y is a complement number, P is the number of needs, R i is the i-th sub-level target memory pool, n is the number of target sub-level hierarchical memory pool memory pool, m i is the i th sub-goal level memory pool The number of memory blocks required.
The computer device according to claim 9, further comprising:

Acquiring memory usage information of the target sub-level memory pool calculated by the client within a preset time period;

Allocate memory blocks of the target sub-level memory pool according to the memory usage information.
The computer device according to claim 13, wherein the memory usage information includes a usage rate of a memory block in the target sub-level memory pool; and the memory usage information of the target sub-level memory pool is calculated according to the memory usage information. The block is deployed, including:

If the usage rate is greater than the first usage threshold, allocate a memory block from the shared memory to the target sub-level memory pool according to the length of the memory block in the target sub-level memory pool, and the shared memory The length of the memory block allocated in the target sub-level memory pool is the same as the length of the memory block whose usage rate is greater than the first usage threshold.
The computer device according to claim 13, wherein the memory usage information includes a usage rate of a memory block in the target sub-level memory pool; and the memory usage information of the target sub-level memory pool is calculated according to the memory usage information. The block is deployed, including:

If the usage rate is less than the second usage threshold, release free memory blocks in the target sub-level memory pool, and the length of the free memory block and the usage rate in the target sub-level memory pool are less than the second usage The threshold memory block length is the same.
A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor realizes a memory scheduling method, including:

Determining an initial memory from the shared memory, and establishing a hierarchical memory pool for use by the client according to the initial memory, the hierarchical memory pool including multiple sub-level memory pools, the sub-level memory pool including multiple memory blocks;

Receiving a memory application request sent by the client, where the memory application request includes the required length and the required quantity of the required memory block;

Determining a target sub-level memory pool from the level memory pool according to the required length;

Allocating memory blocks for the client from the determined target sub-level memory pool according to the required quantity.
The computer-readable storage medium according to claim 16, wherein the determining the initial memory from the shared memory comprises:

When the configuration memory of the client is less than the maximum free memory of the shared memory, use the configuration memory of the client as the initial memory;

When the configured memory of the client is greater than or equal to the maximum free memory of the shared memory, the maximum free memory of the shared memory pool is used as the initial memory.
16. The computer-readable storage medium according to claim 16, wherein the allocating a memory block for the client from the determined target sub-level memory pool according to the demand quantity comprises:

Calculate the complementary quantity of required memory blocks, where the complementary quantity is the difference between the required quantity and the quantity of free memory blocks in the target sub-level memory pool;

When the supplementary quantity is a positive integer, a memory block is allocated from the shared memory to the target sub-level memory pool according to the supplementary quantity and the required length.
18. The computer-readable storage medium according to claim 18, wherein the calculating the supplementary quantity of the required memory block comprises: calculating the supplementary quantity of the required memory block according to a quantity calculation formula;

The quantity calculation formula is:

Wherein, Y is a complement number, P is the number of needs, R i is the i-th sub-level target memory pool, n is the number of target sub-level hierarchical memory pool memory pool, m i is the i th sub-goal level memory pool The number of memory blocks required.
The memory scheduling method according to claim 16, further comprising:

Acquiring memory usage information of the target sub-level memory pool calculated by the client within a preset time period;

Allocate memory blocks of the target sub-level memory pool according to the memory usage information.