CN117675710A

CN117675710A - Network congestion control method, system, equipment and storage medium

Info

Publication number: CN117675710A
Application number: CN202311556908.6A
Authority: CN
Inventors: 卢汉成; 黄健辉; 陈君临; 吴枫
Original assignee: University of Science and Technology of China USTC
Current assignee: University of Science and Technology of China USTC
Priority date: 2023-11-21
Filing date: 2023-11-21
Publication date: 2024-03-08

Abstract

The invention discloses a network congestion control method, a system, equipment and a storage medium, which are used for distributing transmission queues with different priorities according to the size of a data stream, and directly transmitting smaller data streams to a highest priority queue to obtain fastest processing, thereby meeting the demand of small delay of the smaller data streams; for larger data flow, dividing by proportion and distributing queues with different priorities to achieve the purpose of weighing. The medium data flow between the large and small flows is also eased by the corresponding processing mode, and good benefits are ensured between throughput and time delay. In summary, the invention respectively carries out different treatments on different types of streams and sends the streams to the transmission queues with different priorities, thus ensuring that small streams are treated in time and keeping low time delay; and high throughput of large flows can be ensured, so that network performance is improved.

Description

Network congestion control method, system, equipment and storage medium

Technical Field

The present invention relates to the field of computer networks, and in particular, to a method, a system, an apparatus, and a storage medium for controlling network congestion.

Background

The number of packets per data stream in a computer network is proportional to the size of the data stream. The network traffic at the present stage is mainly divided into two types, namely an elephant stream and a mouse stream according to the size of the stream, wherein the elephant stream is a process of transmitting data in a large quantity and continuously through a network link. The mouse flow is a small number of data transfer processes over a network link for a short period of time. The elephant flow and the mouse flow are not distinguished and enter the exchanger queue buffer together. The WRED (Weighted Random Early Detection, weighted early random drop technique) algorithm can be adjusted according to different demands of network traffic to achieve better congestion avoidance. For example, in situations where network congestion is severe, the WRED algorithm may increase the drop probability of data packets to alleviate the network congestion problem as soon as possible. And in the case of slight network congestion, the WRED algorithm can reduce the discarding probability of the data packet so as to ensure the quality and efficiency of network transmission.

However, the processing mode of not distinguishing the size flows has poor effect in practical application, can cause large throughput fluctuation, unstable delay performance, and even trigger the pause frame (a control frame for controlling the data flow to stop sending) to reverse the upstream equipment to stop sending, so that the network performance is poor.

Disclosure of Invention

The invention aims to provide a network congestion control method, a system, equipment and a storage medium, which can enable a larger data stream to keep high throughput and a smaller data stream to keep low time delay, thereby improving network performance.

The invention aims at realizing the following technical scheme:

a network congestion control method, comprising:

identifying the received data stream, and constructing a stream table to record the identified data stream information;

judging the size type of the data stream according to the data stream information recorded in the stream table, and generating a corresponding instruction according to the size type of the data stream; the size type of the data stream includes three types that increase in sequence: a first size type, a second size type, and a third size type;

if the data packet is of the first size type, directly sending the data packet in the corresponding data stream to a transmission queue with the highest priority according to the corresponding instruction;

if the second size type or the third size type, the processing manner is as follows: and carrying out dividing processing on the data stream according to different proportions according to the corresponding instruction, sending the data packet in the divided previous part of data stream to a transmission queue with the highest priority, judging the size type of the divided next part of data stream, if the size type is the first size type, sending the data packet to a transmission queue with the second priority, otherwise, continuing the dividing processing according to the corresponding proportion according to the size type of the data stream, and gradually reducing the priority of the distribution transmission queue.

A network congestion control system, comprising:

the stream identification module is used for identifying the received data stream and constructing a stream table to record the identified data stream information;

the stream processing module is used for judging the size type of the data stream according to the data stream information recorded in the stream table and generating corresponding instructions according to the size type of the data stream; the size type of the data stream includes three types that increase in sequence: a first size type, a second size and a third size type;

a flow allocation module for allocating a transmission queue according to an instruction, comprising:

A processing apparatus, comprising: one or more processors; a memory for storing one or more programs;

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the aforementioned methods.

A readable storage medium storing a computer program which, when executed by a processor, implements the method described above.

According to the technical scheme provided by the invention, the data flows are distributed to the transmission queues with different priorities for transmission according to the sizes of the data flows, and the smaller data flows are directly sent to the queue with the highest priority, so that the fastest processing is obtained, and the requirement of small delay of the smaller data flows is met; for larger data flow, dividing by proportion and distributing queues with different priorities to achieve the purpose of weighing. The medium data flow between the large and small flows is also eased by the corresponding processing mode, and good benefits are ensured between throughput and time delay. In summary, the invention respectively carries out different treatments on different types of streams and sends the streams to the transmission queues with different priorities, thus ensuring that small streams are treated in time and keeping low time delay; and high throughput of large flows can be ensured, so that network performance is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a network congestion control method according to an embodiment of the present invention;

fig. 2 is a schematic diagram of a network congestion control method according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a flow processing allocation transmit queue according to an embodiment of the present invention;

fig. 4 is a schematic diagram of a network congestion control system according to an embodiment of the present invention;

fig. 5 is a schematic diagram of a processing apparatus according to an embodiment of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.

The terms that may be used herein will first be described as follows:

the terms "comprises," "comprising," "includes," "including," "has," "having" or other similar referents are to be construed to cover a non-exclusive inclusion. For example: including a particular feature (e.g., a starting material, component, ingredient, carrier, formulation, material, dimension, part, means, mechanism, apparatus, step, procedure, method, reaction condition, processing condition, parameter, algorithm, signal, data, product or article of manufacture, etc.), should be construed as including not only a particular feature but also other features known in the art that are not explicitly recited.

The term "consisting of … …" is meant to exclude any technical feature element not explicitly listed. If such term is used in a claim, the term will cause the claim to be closed, such that it does not include technical features other than those specifically listed, except for conventional impurities associated therewith. If the term is intended to appear in only a clause of a claim, it is intended to limit only the elements explicitly recited in that clause, and the elements recited in other clauses are not excluded from the overall claim.

The following describes in detail a network congestion control method, system, device and storage medium provided by the present invention. What is not described in detail in the embodiments of the present invention belongs to the prior art known to those skilled in the art. The specific conditions are not noted in the examples of the present invention and are carried out according to the conditions conventional in the art or suggested by the manufacturer.

Example 1

An embodiment of the present invention provides a network congestion control method, as shown in fig. 1, which mainly includes:

and step 1, identifying the received data stream, and constructing a stream table to record the identified data stream information.

In one embodiment, the data flow information is counted in advance at the transmitting end and encapsulated in a data packet.

In one embodiment, the data flow information encapsulated in the data packet mainly includes: source IP and destination IP, data stream size, size type divided according to data stream size, number of data packets that the data stream needs to transmit, and sequence number of data packets in the data stream.

The preferred embodiment of this step is as follows:

(1) After receiving the data stream, splitting the data packet in the data stream, analyzing the data stream information, constructing a stream table to record the data stream information, and assigning a corresponding number to the data stream.

(2) If the analyzed data stream information has a corresponding item in the stream table, the number of the corresponding data stream is queried in the stream table, and the number is used for marking the corresponding data packet.

(3) If the analyzed data stream information has no corresponding item in the stream table, a corresponding item is newly built in the stream table, the data stream information is added to the corresponding item, a new number is sequentially assigned to the data stream, and the corresponding data packet is marked by the new number.

And step 2, judging the size type of the data stream according to the data stream information recorded in the stream table, and generating a corresponding instruction according to the size type of the data stream.

In the embodiment of the present invention, the size types of the data stream include three types that increase in sequence: a first size type (small stream), a second size type (medium stream) and a third size type (large stream).

And step 3, distributing a transmission queue according to the instruction.

In the embodiment of the invention, corresponding transmission queues are allocated to the data packets in the data stream according to the instructions corresponding to the different size types.

(1) If the data packet is of the first size type, the data packet in the corresponding data stream is directly sent to the transmission queue with the highest priority (namely, the transmission queue with the first priority) according to the corresponding instruction.

(2) If the second size type or the third size type, the processing manner is as follows: the data flow is divided according to the corresponding instruction in different proportions, the data packet in the divided previous part of data flow is sent to the transmission queue with the highest priority, the size type of the divided next part of data flow is judged, if the size type is the first size type, the data flow is sent to the second priority transmission queue, otherwise, the division processing is continuously carried out according to the size type of the data flow in corresponding proportion, the priority of the transmission queue is gradually reduced, that is, if the division exists for a plurality of times, the transmission queue with the next priority in the present division is used as the transmission queue with the highest priority in the next division, and in the first division, the transmission queue with the highest priority is the transmission queue with the first priority. Specific:

(2.1) if the second size type, the processing manner is as follows:

dividing the data stream into two parts according to a first proportion according to the corresponding instruction, sending the data packets in the first part of data stream to a transmission queue with the highest priority, taking the second part of data stream as a new data stream A1, and recording in a stream table;

judging the size type of the new data stream A1, and if the size type is the first size type, all data packets in the new data stream A1 are sent to a transmission queue with a second priority;

if the transmission queue is of the second size type, dividing the transmission queue into two parts according to the first proportion, and reducing the priority of the transmission queue, namely: the data packets in the first data stream are sent to a transmission queue with a second priority, and the second data stream is used as a new data stream A2 and recorded in a stream table; if the new data stream A2 is of the first size type, all data packets in the new data stream A2 are sent to a transmission queue of a third priority; otherwise, the new data stream A2 continues to be divided into two parts according to the first proportion, and the priority of the allocation transmission queue is gradually reduced.

(2.2) if the third size type, the processing manner is as follows:

dividing the data stream into two parts according to the corresponding instruction according to the second proportion, sending the data packets in the first part of data stream to a transmission queue with the highest priority, taking the second part of data stream as a new data stream B1, and recording in a stream table;

judging the size type of the new data flow B1, and if the size type is the first size type, all data packets in the new data flow B1 are sent to a transmission queue with a second priority; if the size is the second size type, processing according to the mode of the second size type;

if the transmission queue is of three-size type, the transmission queue is divided into two parts according to a second proportion, and the priority of the transmission queue is reduced, namely: the data packets in the first data stream are sent to a transmission queue with a second priority, and the second data stream is used as a new data stream B2 and recorded in a stream table; if the new data flow B2 is of the first size type, all data packets in the new data flow B2 are sent to a transmission queue of a third priority; if the size is the second size type, processing according to the mode of the second size type; if the data stream is of the third size type, the new data stream B2 is divided into two parts according to the second proportion, and the priority of the distribution transmission queue is gradually reduced.

In the processing of the second size type and the third size type, the first ratio is greater than the second ratio.

Through the processing of the steps, after the receiving end successfully receives all the data packets in the data stream, the related information of the corresponding data stream in the stream table is cleared.

In order to more clearly demonstrate the technical scheme and the technical effects provided by the invention, the method provided by the embodiment of the invention is described in detail below by using specific embodiments.

As shown in fig. 2, an example of the above network congestion control method is provided.

1. Firstly, a stream information statistics module is set up at a transmitting end, and data stream information to be counted comprises: the source IP and the destination IP, the data flow size, the flow small flow divided into large flow according to the data flow size, the number of data packets to be transmitted by the data flow, and the sequence number of the data packets in the flow. The information is encapsulated in packets which are then sent in turn to the link for transmission.

2. A stream identification module is set up at the exchanger end, which needs to judge the received data stream, split the arrived data packet, analyze the data stream information and construct the stream table. The flow table is to register information of the flow for the next processing. The main registration information in the flow table includes the number of the flow, the source IP and destination IP, the size of the data flow, the type of the data flow, and the number of packets the data flow needs to transmit. After receiving the data packet, two cases are classified: if the information in the data packet is found to correspond to the data packet with different sequence numbers in the flow table, the flow number of the data packet is inquired in the flow table, and the flow number is marked; if the information in the data packet is not corresponding in the flow table, indicating that the data packet is a new flow, assigning a new number to the flow by the order, adding all the information of the flow into the flow table, and marking the data packet with the flow number.

3. A stream processing module is also required to be established at the exchanger end, the outlet port of the exchanger end is generally provided with N transmission queues, the number is from N-1 to 0, the smaller the number is, the lower the priority is, namely the highest priority is for the transmission queue with the number of N-1, and the lowest priority is for the transmission queue with the number of 0; the value of N may be determined according to the actual situation. For example, n=8, the number of the 8 transmission queues may be set from 0 to 7, and the priority is the highest of the transmission queues 7, and decreases sequentially. The stream processing module processes the data packet according to the data stream information in the stream table, and then produces corresponding instructions to allocate the transmission queue. As shown in fig. 3, the following is mainly:

when new flow information appears in the flow table, the number of the flow and the type of the flow are checked.

(1) If the stream is a small stream (first size type), the corresponding stream number is recorded. The instruction issued to the flow assignment module is that all packets encountering the flow number are not processed and are directed to the highest priority transmit queue (e.g., transmit queue 7).

(2) If the stream is a middle stream (second size type), the corresponding stream number and the number of data packets of the stream are recorded. The instruction issued to the flow distribution module is to meet the data packet of the flow number and combine the set first proportion to carry out corresponding processing. The first ratio is described herein as 1/2 (i.e., after dividing the first data stream includes 1/2 packets with sequence numbers preceding the first data stream, and the second data stream includes 1/2 packets with sequence numbers following the first data stream).

When a data packet is received, checking the sequence number of the data packet in the stream when the stream type corresponding to the stream number carried by the data packet is found to be a middle stream, and sending the data packet to a highest priority queue as long as the sequence number is 1/2 in the front; if the sequence number is 1/2 later, the data packets are used as a new data stream, the new data stream is newly recorded in the stream table, new stream numbers are given, the source IP and the destination IP are unchanged, the size of the data stream is half, the number of the data packets carried by the data stream is half of the original number, and the size type of the new data stream is judged according to the new data stream size. If this new data has become small, then all packets are sent to a second priority transmission queue (e.g., transmission queue 6). If the data packets still are the middle stream, the division is continued, namely the first 1/2 data packets are reserved and sent to the transmission queue of the second priority, the last 1/2 data packets are continuously used as a new data stream and recorded in the stream table, and then whether the data packets are sent to the transmission queue of the third priority or are continuously split is judged according to the size of the data packets. And so on.

(3) If the stream is large (third size type), the corresponding stream number and the number of the data packets of the stream are recorded. The instruction issued to the flow distribution module is to meet the flow number of the data packet and combine the set second proportion to carry out corresponding processing. The second ratio is described herein as 1/3 (i.e., the first data stream after division contains 1/3 packets with sequence numbers preceding and the second data stream contains 2/3 packets with sequence numbers following).

When a data packet is received, checking the sequence number of the data packet in the stream when the stream type corresponding to the stream number carried by the data packet is found to be a large stream, and sending the data packet to a transmission queue with the highest priority as long as the sequence number is 1/3 in the front; if the sequence number is 2/3 later, the data packets are used as a new data stream, at the moment, the new data is newly recorded in the stream table, the new data stream number is given, the source IP and the destination IP are unchanged, but the size of the new data stream is changed to be 2/3 of the original size, the number of the data packets carried by the new data stream is changed to be 2/3 of the original size, and the size type of the new data stream is judged according to the new data stream size. If the new data stream has become small in size, then all data packets are sent to the second priority transmission queue. If the new data stream is of the medium-stream size type, the first 1/2 data packets are reserved and sent to the transmission queue of the second priority, the last 1/2 data packets continue to be used as a new data stream and recorded in the stream table, and then whether the new data stream is sent to the transmission queue of the third priority or is continuously split is judged according to the size of the new data stream, and the processing mode can refer to the part (2). If the size type of the new data stream is still large, the first 1/3 data packets are reserved and sent to a transmission queue of the second priority, the last 2/3 data packets continue to serve as a new data stream and are recorded in a stream table, then the new data stream is judged to be small stream, medium stream or large stream according to the size of the new data stream, if the new data stream is changed into small stream, the new data stream is sent to a transmission queue of the third priority, and if the new data stream is middle stream or large stream, the new data stream is continuously divided according to the corresponding proportion. And so on.

In the above scheme provided by the embodiment of the invention: the small flow is characterized in that the data flow is small, the required transmission time is short, the data flows generated by sending mail, looking at a webpage, chat and the like belong to the small flow, and the data flows are directly sent to the highest priority queue to be processed fastest, so that the requirement of small flow delay is met. The big stream is characterized in that the data stream is particularly big and needs longer transmission time, if the big stream is put in a high-priority queue, the long-time occupation of the high-priority queue can be caused, then the data stream in the high-priority queue and after the big stream can be normally transmitted outwards only after long-time queuing, so that the time delay is increased, but if the big stream is directly put in a low-priority queue, the long-time transmission opportunity can not be obtained, and the throughput becomes extremely low, therefore, the technical scheme adopts a mode of cutting the big stream to achieve the purpose of balancing. The middle stream between the large stream and the small stream is relaxed between the two streams by the corresponding processing mode, so that good benefits are ensured between throughput and time delay.

(4) When the last data packet of a certain data stream successfully arrives at the receiving end, the sending end receives the ACK (acknowledgement) frame of the last data packet returned by the receiving end, a message can be sent to inform the exchange end that the corresponding data stream is completely transmitted, and the related information of the corresponding data stream in the stream table can be cleared.

From the description of the above embodiments, it will be apparent to those skilled in the art that the above embodiments may be implemented in software, or may be implemented by means of software plus a necessary general hardware platform. With such understanding, the technical solutions of the foregoing embodiments may be embodied in a software product, where the software product may be stored in a nonvolatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.), and include several instructions for causing a computer device (may be a personal computer, a server, or a network device, etc.) to perform the methods of the embodiments of the present invention.

Example two

The present invention also provides a network congestion control system, which is mainly used for implementing the method provided in the foregoing embodiment, as shown in fig. 4, where the system mainly includes:

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, i.e. the internal structure of the system is divided into different functional modules to perform all or part of the functions described above.

In view of the detailed description of the embodiments of the system, the details of the embodiments are described in the previous embodiments, and thus will not be described in detail.

Example III

The present invention also provides a processing apparatus, as shown in fig. 5, which mainly includes: one or more processors; a memory for storing one or more programs; wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the methods provided by the foregoing embodiments.

Further, the processing device further comprises at least one input device and at least one output device; in the processing device, the processor, the memory, the input device and the output device are connected through buses.

In the embodiment of the invention, the specific types of the memory, the input device and the output device are not limited; for example:

the input device can be a touch screen, an image acquisition device, a physical key or a mouse and the like;

the output device may be a display terminal;

the memory may be random access memory (Random Access Memory, RAM) or non-volatile memory (non-volatile memory), such as disk memory.

Example IV

The invention also provides a readable storage medium storing a computer program which, when executed by a processor, implements the method provided by the foregoing embodiments.

The readable storage medium according to the embodiment of the present invention may be provided as a computer readable storage medium in the aforementioned processing apparatus, for example, as a memory in the processing apparatus. The readable storage medium may be any of various media capable of storing a program code, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, and an optical disk.

The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the scope of the present invention should be included in the scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A network congestion control method, comprising:

2. The network congestion control method according to claim 1, wherein the data flow information is encapsulated in a data packet, the data flow information comprising: source IP and destination IP, data stream size, size type divided according to data stream size, number of data packets that the data stream needs to transmit, and sequence number of data packets in the data stream.

3. The network congestion control method according to claim 1, wherein the data flow information is counted at the transmitting end and encapsulated in a data packet.

4. The network congestion control method according to claim 1, wherein identifying the received data flow and constructing a flow table to record the identified data flow information comprises:

after receiving the data stream, splitting the data packet in the data stream, analyzing the data stream information, constructing a stream table to record the data stream information, and assigning corresponding numbers to the data stream;

if the analyzed data stream information has a corresponding item in the stream table, the number of the corresponding data stream is queried in the stream table, and the number is used for marking the corresponding data packet;

if the analyzed data stream information has no corresponding item in the stream table, a corresponding item is newly built in the stream table, the data stream information is added to the corresponding item, a new number is sequentially assigned to the data stream, and the corresponding data packet is marked by the new number.

5. The network congestion control method according to claim 1, wherein if the second size type is the second size type, the processing manner is as follows:

6. The network congestion control method according to claim 1 or 5, wherein if the type is the third size, the processing manner is as follows:

7. The network congestion control method according to claim 1, wherein after the receiving end successfully receives all the packets in the data stream, the related information of the corresponding data stream in the stream table is cleared.

8. A network congestion control system, comprising:

9. A processing apparatus, comprising: one or more processors; a memory for storing one or more programs;

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-7.

10. A readable storage medium storing a computer program, characterized in that the method according to any one of claims 1-7 is implemented when the computer program is executed by a processor.