Congestion control method, apparatus, and system

By setting congestion detection indication information and congestion information fields in the message, the problems of inaccurate congestion control and hop-by-hop increase in the prior art are solved, and efficient congestion control in long-distance multi-hop transmission scenarios are realized.

WO2024234750A1PCT designated stage expired Publication Date: 2024-11-21HUAWEI TECH CO LTD

Patent Information

Application Number
PCT/CN2024/076402
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-18
Filing Date
2024-02-06
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

In the prior art, the TC field in the IP header can only indicate whether the packet has experienced congestion and cannot carry more congestion information, making it difficult for the end-side device to perform precise congestion control, and in a long-distance multi-hop transmission scenario, the report is The increase in text by jump affects packaging efficiency.

Method used

Set the congestion detection indication information and congestion information fields in the message, and use this information to obtain and update the congestion information to avoid hop-by-hop additions and ensure packet encapsulation efficiency.

Benefits of technology

It realizes more precise congestion control, is suitable for long-distance multi-hop transmission scenarios, and improves network transmission efficiency and bandwidth utilization.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024076402_21112024_PF_FP_ABST
    Figure CN2024076402_21112024_PF_FP_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of networks. Disclosed are a congestion control method, apparatus, and system. The method comprises: a first device obtains a first packet, the first packet comprising congestion detection indication information and a congestion information field, the congestion detection indication information being used for instructing a device to obtain congestion information corresponding to the device, and the congestion information field being used for carrying the congestion information; the first device obtains, according to the congestion detection indication information, congestion information corresponding to the first device; and the first device updates the congestion information field according to the congestion information corresponding to the first device. In the present application, the congestion information field in the first packet can carry more congestion information, which helps an end-side device to perform accurate congestion control according to the congestion information carried in the congestion information field.
Need to check novelty before this filing date? Find Prior Art

Description

Congestion control method, device and system

[0001] This application claims priority to Chinese patent application filed on May 18, 2023, with application number 202310566307.7 and application name “Congestion Control Method, Device and System”, all contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of network technology, and in particular to a congestion control method, device, and system. Background Art

[0003] Explicit congestion notification (ECN) technology uses the last two bits of the traffic class (TC) field in the Internet Protocol (IP) header to indicate network congestion. When a sending device sends a message, it sets the values ​​of these two bits to 01 or 10 to enable ECN. If congestion occurs while the network device is forwarding the message, it sets the values ​​of these two bits to 11. The receiving device determines whether the message has experienced congestion based on the values ​​of these two bits. The receiving device then sends an acknowledgment (ACK) message to the sending device via the transport layer indicating the congestion status of the received message. The sending device then adjusts its sending window, sending rate, and other parameters based on the congestion status to perform congestion control.

[0004] However, the above two bits in the message can only indicate whether the message has experienced congestion, which makes it difficult for end-side devices (including the sending end device and the receiving end device) to perform accurate congestion control based on the two bits.

[0005] Summary of the Invention

[0006] The present application provides a congestion control method, device and system. The technical solution of the present application is as follows.

[0007] In a first aspect, a congestion control method is provided. The method includes: a first device obtaining a first message, the first message including congestion detection indication information and a congestion information field, the congestion detection indication information being used to instruct the device to obtain congestion information corresponding to the device, and the congestion information field being used to carry the congestion information; the first device obtaining congestion information corresponding to the first device based on the congestion detection indication information; and the first device updating the congestion information field based on the congestion information corresponding to the first device. That is, the first device updates the congestion information in the congestion information field based on the congestion information corresponding to the first device.

[0008] The technical solution provided in the present application provides congestion detection indication information and a congestion information field in a first message. The congestion detection indication information is used to instruct a device to obtain congestion information corresponding to the device, and the congestion information field is used to carry the congestion information. This enables devices along the path of the first message to obtain the congestion information corresponding to the device based on the congestion detection indication information and update the congestion information field based on the congestion information corresponding to the device. The congestion information field can carry a large amount of congestion information, which helps the end-side device to perform accurate congestion control based on the congestion information carried by the congestion information field.

[0009] Moreover, in the technical solution provided by the present application, in the process of forwarding the first message by the devices along the route, the congestion information in the congestion information field in the first message is updated instead of adding the congestion information to the first message hop by hop. This can avoid the first message from increasing hop by hop, ensure the encapsulation efficiency of the first message, and be applicable to long-distance multi-hop transmission scenarios.

[0010] Optionally, the congestion information includes at least one of first congestion information and second congestion information; the first congestion information includes at least one of the following: utilization of a queue in a device used to buffer the first message; utilization of an interface in the device used to send the first message; and the cumulative number of congested hops on the transmission path of the first message; the second congestion information includes the cumulative processing delay of the first message, which is the cumulative value of the processing delay of the first message in the devices along the transmission path of the first message. The processing delay of the first message in any device is the queuing delay of the first message in the device (i.e., the length of time the first message stays in the queue in the device used to buffer the first message), and the cumulative processing delay of the first message is the cumulative value of the queuing delay of the first message in the devices along the transmission path of the first message, which is also the cumulative queuing delay. Alternatively, the processing delay of the first message in any device includes the queuing delay of the first message in the device and the sending delay of the first message in the device (i.e., the sending delay of the interface in the device used to send the first message).

[0011] Optionally, the utilization of the interface in the device used to send the first message includes at least one of the following: bandwidth utilization of the interface; and link utilization of the interface. The link utilization of the interface takes into account the bandwidth of the interface and the utilization of the buffer space of the interface, and is also called inflight utilization.

[0012] Optionally, the congestion detection indication information is used to instruct a device to obtain first congestion information corresponding to the device, and the congestion information field is used to carry the first congestion information. The first device obtains the congestion information corresponding to the first device based on the congestion detection indication information, including: the first device obtains the first congestion information corresponding to the first device based on the congestion detection indication information; correspondingly, the first device updates the congestion information field based on the congestion information corresponding to the first device, including: if a relationship between the first congestion information corresponding to the first device and the first congestion information in the congestion information field satisfies a preset condition, the first device updates the first congestion information in the congestion information field with the first congestion information corresponding to the first device. For example, the first device replaces the first congestion information in the congestion information field with the first congestion information corresponding to the first device.

[0013] The technical solution provided by the present application is that, during the process of forwarding the first message by a device along the path of the first message, the first congestion information corresponding to the device is used to update the first congestion information in the congestion information field, rather than adding the first congestion information to the first message hop by hop, thereby avoiding the first message from increasing hop by hop.

[0014] Optionally, the preset condition includes any one of the following: the value of the first congestion information corresponding to the first device is greater than the value of the first congestion information in the congestion information field; or the value of the first congestion information corresponding to the first device is less than or equal to the value of the first congestion information in the congestion information field.

[0015] The technical solution provided by the present application is that, when the preset condition is that the value of the first congestion information corresponding to the first device is greater than the value of the first congestion information in the congestion information field, the first device uses the first congestion information corresponding to the first device to update the first congestion information in the congestion information field when the value of the first congestion information corresponding to the first device is greater than the value of the first congestion information in the congestion information field. This can ensure that the value of the first congestion information in the congestion information field is the maximum value of the first congestion information corresponding to the devices along the path of the first message, and the first message carries the maximum value of the first congestion information corresponding to the devices along the path of the first message to the second device (for example, the receiving end device). equipment); when the preset condition is that the value of the first congestion information corresponding to the first device is less than or equal to the value of the first congestion information in the congestion information field, the first device uses the first congestion information corresponding to the first device to update the first congestion information in the congestion information field if the value of the first congestion information corresponding to the first device is less than or equal to the value of the first congestion information in the congestion information field. This can ensure that the value of the first congestion information in the congestion information field is the minimum value among the values ​​of the first congestion information corresponding to the devices along the path of the first message. The first message carries the minimum value of the first congestion information corresponding to the devices along the path of the first message to the second device (e.g., the receiving device).

[0016] Optionally, the congestion detection indication information is used to instruct a device to obtain second congestion information corresponding to the device, and the congestion information field is used to carry the second congestion information; the first device obtaining the congestion information corresponding to the first device based on the congestion detection indication information includes: the first device obtaining the second congestion information corresponding to the first device based on the congestion detection indication information; and correspondingly, the first device updating the congestion information field based on the congestion information corresponding to the first device includes: the first device updating the second congestion information in the congestion information field with the second congestion information corresponding to the first device. For example, the first device replaces the second congestion information in the congestion information field with the second congestion information corresponding to the first device.

[0017] In the technical solution provided by the present application, the value of the second congestion information corresponding to the devices along the path of the first message gradually increases, and the first device uses the second congestion information corresponding to the first device to update the second congestion information in the congestion information field. This can ensure that the value of the second congestion information in the congestion information field is the maximum value among the values ​​of the second congestion information corresponding to the devices along the path of the first message. The first message carries the maximum value of the second congestion information corresponding to the devices along the path of the first message to the receiving device.

[0018] Optionally, the first message includes an enhanced explicit congestion notification (AECN) header, where the AECN header includes the congestion detection indication information and the congestion information field. That is, the present application sets the congestion detection indication information and the congestion information in the AECN header. Compared with the ECN bit (the last two bits in the TC field in the IP header), the AECN header can carry more congestion information, which can facilitate the end-side device to perform precise congestion control.

[0019] Optionally, the first message includes an Internet Protocol version 6 (IPv6) extension header, and the AECN header is located in the IPv6 extension header. For example, the IPv6 extension header is a hop by hop (HBH) header.

[0020] Optionally, the first message includes an Internet Control Message Protocol (ICMP) header, and the AECN header is located in the ICMP header.

[0021] Optionally, the first device is a sending device, and the first device obtaining the first message includes: the first device generating the first message.

[0022] The technical solution provided by the present application is that the first message is generated by a sending end device, and the sending end device can obtain the congestion information corresponding to the sending end device based on the congestion detection indication information in the first message, and use the congestion information corresponding to the sending end device to update the congestion information field in the first message, so that the present application can detect the congestion situation of the sending end device.

[0023] Optionally, the first device is a network device (for example, the first device is any network device on a transmission path of the first message), and the first device obtains the first message, including: the first device receives the first message from the sending device.

[0024] In the technical solution provided by the present application, the first message comes from a sending device. Therefore, the sending device can obtain the congestion information corresponding to the sending device based on the congestion detection indication information in the first message, and use the congestion information corresponding to the sending device to update the congestion information field in the first message, so that the present application can detect the congestion situation of the sending device.

[0025] Optionally, the first device is a network device (for example, the first device is a network device directly connected to the sending device), and the first device obtains the first message, including: the first device receives the original message from the sending device; the first device generates the first message based on the original message.

[0026] Optionally, the first device generates a first message based on the original message, including: the first device constructs the first message based on the original message; or, the first device encapsulates the congestion detection indication information and the congestion information field in the original message to obtain the first message; or, the first device copies the original message to obtain a copied message, and the first device encapsulates the congestion detection indication information and the congestion information field in the copied message to obtain the first message.

[0027] Optionally, after the first device updates the congestion information field, the method further includes: the first device sending a first message.

[0028] Optionally, the first device is a transmitting device, and the method further includes: the first device receiving a second message from the second device, where the second message corresponds to the first message; and the first device performing congestion control on the receiving device of the first message based on the second message. The second message is generated by the second device based on a congestion information field in the first message received by the second device.

[0029] The technical solution provided by the present application is that a second device generates a second message based on the congestion information field in the first message received by the second device, and sends the second message to the sending device. The sending device performs congestion control on the receiving device of the first message based on the second message, which can improve the accuracy of the congestion control performed by the sending device.

[0030] Optionally, the second message includes at least one of the following: congestion information in the congestion information field; and a congestion control instruction, which is determined based on the congestion information in the congestion information field.

[0031] The technical solution provided by the present application is that, when the second message includes congestion information in a congestion information field but does not include a congestion control instruction, the sending device can determine the congestion control instruction based on the congestion information in the congestion information field and execute the congestion control instruction to perform congestion control on the receiving device; when the second message includes the congestion control instruction but does not include the congestion information in the congestion information field, the sending device executes the congestion control instruction to perform congestion control on the receiving device; when the second message includes congestion information and a congestion control instruction in the congestion information field, the sending device determines the congestion control instruction based on the congestion information in the congestion information field, and performs congestion control on the receiving device based on the congestion control instruction determined by the sending device and the congestion control instruction in the second message.

[0032] Optionally, the second message is a detection message or a transport layer acknowledgment (ACK) message.

[0033] Optionally, the first message is a service message, a detection message, or a copy of the service message.

[0034] Optionally, the second device is a receiving device or a network device.

[0035] In a second aspect, a congestion control method is provided, comprising: a second device receiving a first message, the first message including congestion detection indication information and a congestion information field, the congestion detection indication information being used to instruct the device to obtain congestion information corresponding to the device, and the congestion information field being used to carry the congestion information; and the second device sending a second message to a sending device based on the congestion information field, the second message being used to instruct the sending device to perform congestion control on a receiving device of the first message.

[0036] The technical solution provided by this application includes congestion detection indication information and a congestion information field in a first message. The congestion detection indication information is used to instruct a device to obtain congestion information corresponding to the device, and the congestion information field is used to carry the congestion information. This allows devices along the path of the first message to obtain the congestion information corresponding to the device based on the congestion detection indication information and update the congestion information field based on the congestion information corresponding to the device. A second device then sends a second message to the sending device based on the congestion information field, and the sending device performs congestion control on the receiving device of the first message based on the second message. The congestion information field can carry a large amount of congestion information. Therefore, the second message sent by the second device to the sending device based on the congestion information field can instruct the sending device to perform precise congestion control on the receiving device.

[0037] Optionally, the second message includes at least one of the following: congestion information in the congestion information field; and a congestion control instruction, wherein the congestion control instruction is determined according to the congestion information in the congestion information field.

[0038] Optionally, the congestion information includes at least one of first congestion information and second congestion information; the first congestion information includes at least one of the following: the utilization rate of the queue in the device used to buffer the first message; the utilization rate of the interface in the device used to send the first message; and the cumulative number of congested hops on the transmission path of the first message; the second congestion information includes the cumulative processing delay of the first message, which is the cumulative value of the processing delay of the first message in the devices along the transmission path of the first message. The processing delay of the first message in any device is the queuing delay of the first message in the device, and the cumulative processing delay of the first message is the cumulative value of the queuing delay of the first message in the devices along the transmission path of the first message, which is also the cumulative queuing delay. Alternatively, the processing delay of the first message in any device includes the queuing delay of the first message in the device and the sending delay of the first message in the device.

[0039] Optionally, the utilization of the interface in the device used to send the first message includes at least one of the following: bandwidth utilization of the interface; and link utilization of the interface. The link utilization of the interface takes into account the bandwidth of the interface and the utilization of the buffer space of the interface. This link utilization is also called inflight utilization.

[0040] Optionally, the first message includes an AECN header, and the AECN header includes congestion detection indication information and a congestion information field.

[0041] Optionally, the first message includes an IPv6 extension header, and the AECN header is located in the IPv6 extension header.

[0042] Optionally, the first message includes an ICMP header, and the AECN header is located in the ICMP header.

[0043] Optionally, the first message is a service message, a detection message, or a copy of the service message.

[0044] Optionally, the second message is a detection message or an ACK message of the transport layer.

[0045] Optionally, the second device is a receiving device or a network device.

[0046] In a third aspect, a congestion control apparatus is provided, which is applied to a first device. The congestion control apparatus includes modules for executing the method provided in the first aspect or any optional manner of the first aspect.

[0047] Optionally, the congestion control device includes:

[0048] an acquiring module, configured to acquire a first message, wherein the first message includes congestion detection indication information and a congestion information field, wherein the congestion detection indication information is used to instruct a device to acquire congestion information corresponding to the device, and the congestion information field is used to carry the congestion information;

[0049] a detection module, configured to obtain congestion information corresponding to the first device according to the congestion detection indication information;

[0050] An updating module is configured to update the congestion information field according to the congestion information corresponding to the first device.

[0051] Optionally, the congestion information includes at least one of first congestion information and second congestion information; the first congestion information includes at least one of the following: utilization of a queue in a device for caching the first message; utilization of an interface in the device for sending the first message; and the cumulative number of congested hops on the transmission path of the first message; the second congestion information includes the cumulative processing delay of the first message, where the cumulative processing delay is the cumulative value of the processing delay of the first message in devices along the transmission path of the first message. The processing delay of the first message in any device is the queuing delay of the first message in that device, and the cumulative processing delay of the first message is the cumulative value of the queuing delay of the first message in devices along the transmission path of the first message, which is also the cumulative queuing delay. Alternatively, the processing delay of the first message in any device includes the queuing delay of the first message in that device and the sending delay of the first message in that device.

[0052] Optionally, the utilization of the interface includes at least one of the following: bandwidth utilization of the interface; and link utilization of the interface.

[0053] Optionally, the congestion detection indication information is used to instruct the device to obtain first congestion information corresponding to the device, and the congestion information field is used to carry the first congestion information; the detection module is used to obtain the first congestion information corresponding to the first device according to the congestion detection indication information; correspondingly, the update module is used to update the first congestion information in the congestion information field with the first congestion information corresponding to the first device when the relationship between the first congestion information corresponding to the first device and the first congestion information in the congestion information field meets a preset condition.

[0054] Optionally, the preset condition includes any one of the following: the value of the first congestion information corresponding to the first device is greater than the value of the first congestion information in the congestion information field; or the value of the first congestion information corresponding to the first device is less than or equal to the value of the first congestion information in the congestion information field.

[0055] Optionally, the congestion detection indication information is used to instruct the device to obtain second congestion information corresponding to the device, and the congestion information field is used to carry the second congestion information; the detection module is used to obtain the second congestion information corresponding to the first device according to the congestion detection indication information; correspondingly, the update module is used to update the second congestion information in the congestion information field using the second congestion information corresponding to the first device.

[0056] Optionally, the first message includes an AECN header, and the AECN header includes the congestion detection indication information and the congestion information field.

[0057] Optionally, the first message includes an IPv6 extension header, and the AECN header is located in the IPv6 extension header.

[0058] Optionally, the first message includes an ICMP header, and the AECN header is located in the ICMP header.

[0059] Optionally, the first device is a sending device, and the acquisition module is used to generate the first message.

[0060] Optionally, the first device is a network device, and the acquisition module is used to receive the first message from a sending device.

[0061] Optionally, the first device is a network device, and the acquisition module is used to: receive an original message from a sending device; and generate the first message according to the original message.

[0062] Optionally, the acquisition module is used to: construct the first message based on the original message; or, encapsulate the congestion detection indication information and the congestion information field in the original message to obtain the first message; or, copy the original message to obtain a copied message, and encapsulate the congestion detection indication information and the congestion information field in the copied message to obtain the first message.

[0063] Optionally, the congestion control apparatus further includes: a sending module, configured to send the first message after the updating module updates the congestion information field according to the congestion information corresponding to the first device.

[0064] Optionally, the first device is a sending end device, and the congestion control apparatus further includes:

[0065] a receiving module, configured to receive a second message from a second device, where the second message corresponds to the first message;

[0066] A control module is used to perform congestion control on a receiving device of the first message according to the second message.

[0067] Optionally, the second message includes at least one of the following: congestion information in the congestion information field; a congestion control instruction, where the congestion control instruction is determined according to the congestion information in the congestion information field.

[0068] Optionally, the second message is a detection message or a confirmation message of the transport layer.

[0069] Optionally, the first message is a service message, a detection message, or a copy of the service message.

[0070] Optionally, the second device is the receiving device or a network device.

[0071] In a fourth aspect, a congestion control apparatus is provided, which is applied to a second device. The congestion control apparatus includes modules for executing the method provided in the second aspect or any optional manner of the second aspect.

[0072] Optionally, the congestion control device includes:

[0073] a receiving module, configured to receive a first message, wherein the first message includes congestion detection indication information and a congestion information field, wherein the congestion detection indication information is used to instruct a device to obtain congestion information corresponding to the device, and the congestion information field is used to carry the congestion information;

[0074] The sending module is configured to send a second message to a sending end device according to the congestion information field, wherein the second message is used to instruct the sending end device to perform congestion control on a receiving end device of the first message.

[0075] Optionally, the second message includes at least one of the following: congestion information in the congestion information field; a congestion control instruction, where the congestion control instruction is determined according to the congestion information in the congestion information field.

[0076] Optionally, the congestion information includes at least one of first congestion information and second congestion information;

[0077] The first congestion information includes at least one of the following: the utilization rate of a queue in a device used to buffer the first message; the utilization rate of an interface in the device used to send the first message; the cumulative number of congested hops on the transmission path of the first message; and the second congestion information includes the cumulative processing delay of the first message, which is the cumulative value of the processing delay of the first message in devices on the transmission path of the first message. The processing delay of the first message in any device is the queuing delay of the first message in that device, and the cumulative processing delay of the first message is the cumulative value of the queuing delay of the first message in devices on the transmission path of the first message, which is also the cumulative queuing delay. Alternatively, the processing delay of the first message in any device includes the queuing delay of the first message in that device and the sending delay of the first message in that device.

[0078] Optionally, the utilization of the interface includes at least one of the following: bandwidth utilization of the interface; link utilization of the interface.

[0079] Optionally, the first message includes an AECN header, and the AECN header includes the congestion detection indication information and the congestion information field.

[0080] Optionally, the first message includes an IPv6 extension header, and the AECN header is located in the IPv6 extension header.

[0081] Optionally, the first message includes an ICMP header, and the AECN header is located in the ICMP header.

[0082] Optionally, the first message is a service message, a detection message, or a copy of the service message.

[0083] Optionally, the second message is a detection message or a confirmation message of the transport layer.

[0084] Optionally, the second device is the receiving device or a network device.

[0085] The modules in the third and fourth aspects above may be implemented based on software, hardware, or a combination of software and hardware, and the modules may be arbitrarily combined or divided based on specific implementations.

[0086] In a fifth aspect, a congestion control device is provided, comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program stored in the memory so that the congestion control device performs the congestion control method provided in the first aspect or any optional method of the first aspect.

[0087] In a sixth aspect, a congestion control device is provided, comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program stored in the memory so that the congestion control device performs the congestion control method provided in the second aspect or any optional method of the second aspect.

[0088] In the seventh aspect, a congestion control system is provided, which includes a first device and a second device; the first device includes the congestion control device provided by the third aspect or any optional implementation of the third aspect; the second device includes the congestion control device provided by the fourth aspect; or, the first device includes the congestion control device provided by the fifth aspect; the second device includes the congestion control device provided by the sixth aspect.

[0089] In an eighth aspect, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed, the method provided in the first aspect or any optional manner of the first aspect is implemented.

[0090] In a ninth aspect, a computer program product is provided, which includes a program or code, and when the program or code is executed, it implements the method provided in the first aspect or any optional manner of the first aspect.

[0091] In a tenth aspect, a chip is provided, which includes a programmable logic circuit and / or program instructions, and when the chip is running, it is used to implement the method provided in the first aspect or any optional method of the first aspect.

[0092] The technical effects of the third to tenth aspects mentioned above can refer to the technical effects of the first to second aspects, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] FIG1 is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0094] FIG2 is a flow chart of a congestion control method provided by an embodiment of the present application;

[0095] FIG3 is a schematic diagram of an AECN head provided in an embodiment of the present application;

[0096] FIG4 is a flow chart of another congestion control method provided in an embodiment of the present application;

[0097] FIG5 is a flowchart of another congestion control method provided in an embodiment of the present application;

[0098] FIG6 is a flowchart of another congestion control method provided in an embodiment of the present application;

[0099] FIG7 is a schematic diagram of a congestion control method provided in an embodiment of the present application;

[0100] FIG8 is a flowchart of another congestion control method provided in an embodiment of the present application;

[0101] FIG9 is a schematic diagram of another congestion control method provided in an embodiment of the present application;

[0102] FIG10 is a schematic diagram of a congestion control device provided in an embodiment of the present application;

[0103] FIG11 is a schematic diagram of another congestion control device provided in an embodiment of the present application;

[0104] FIG12 is a schematic diagram of another congestion control device provided in an embodiment of the present application;

[0105] FIG13 is a schematic diagram of another congestion control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0106] The embodiments of the present application will be further described below with reference to the accompanying drawings.

[0107] This application involves ECN technology, low latency, low loss, and scalable throughput (L4S) technology, in-situ flow information telemetry (IFIT) technology, inband network telemetry (INT) technology, high precision congestion control (HPCC) technology, and bottleneck bandwidth and round-trip propagation time (BBR) congestion control technology. Before introducing the technical solution of this application, we first briefly introduce the current ECN technology, L4S technology, IFIT technology, INT technology, HPCC technology, and BBR congestion control technology.

[0108] ECN technology uses the last two bits in the TC field in the IP header to mark network congestion. When the sending device sends a message, it sets the value of these two bits in the message to 01 or 10 to enable the ECN function. During the process of forwarding the message by the network devices along the way, if the network device is congested, the network device sets the value of these two bits in the message to 11. The receiving device determines whether the message has experienced congestion based on the value of these two bits in the message. The receiving device sends the congestion status of the received message to the sending device via an ACK message at the transport layer. The sending device performs congestion control based on the congestion status. ECN technology has been widely deployed in data centers. When used in conjunction with the Data Center Transport Control Protocol (DCTCP) congestion control algorithm, ECN technology can significantly reduce network transmission delay and packet loss rate.

[0109] L4S technology reuses the architecture of ECN technology and uses the last two bits in the TC field in the IP header to mark network congestion. When the sending device sends a message, it sets the values ​​of these two bits in the message to 01 to enable the L4S function (for example, a message with the L4S function enabled is called an L4S message). The network device includes a queue dedicated to caching L4S messages. During the process of forwarding messages, if the network device is congested, the network device sets the values ​​of these two bits in at least some messages in the queue to 11. The receiving device determines whether the message has experienced congestion based on the values ​​of these two bits in the message. The receiving device sends the congestion status of the received message to the sending device via an ACK message at the transport layer. The sending device performs congestion control based on the congestion status, thereby achieving the effect of controlling delay and packet loss.

[0110] IFIT technology is a network-based in-stream detection technology. In IFIT, a head node device (e.g., a network device directly connected to a sending device) adds an IFIT header to a message. Network devices along the message's path obtain detection information based on the IFIT header and report this detection information to a network controller. The network controller then calculates network packet loss, transmission delay, and other factors based on the detection information reported by the network devices along the message's path. IFIT technology includes two detection modes: postcard mode and passport mode. The postcard mode, also known as the hop-by-hop mode, requires each network device along the message's path to report detection information to the network controller. The passport mode, also known as the end-to-end mode, requires the head node and intermediate devices to add their acquired detection information to a message and send it to the tail node device (e.g., a network device directly connected to a receiving device). The tail node device then reports all the detection information acquired by the network devices along the message's path (including the head node, intermediate devices, and tail node devices) to the network controller.

[0111] INT technology includes traffic detection technology similar to the passport mode in IFIT technology. The head node device adds an INT header to the message. The network devices along the message path obtain detection information based on the INT header, and add the detection information to the INT header and send it to the tail node device. The tail node device reports the detection information obtained by the network devices along the message path to the network controller, or the tail node device provides this detection information to the end-side device (such as the receiving device) for use.

[0112] HPCC technology utilizes the INT capabilities of network devices in the data center for network detection. For example, a head node device receives a message from a sending device and adds an INT header to the message. Network devices along the message's path obtain detection information based on the INT header and send the detection information to the receiving device by adding it to the INT header. The receiving device then sends the detection information carried in the INT header to the sending device via a transport layer ACK message. The sending device calculates the link utilization of the bottleneck link based on this detection information (the bottleneck link corresponds to the bottleneck interface in the network device, so the link utilization of the bottleneck link is also referred to as the link utilization of the bottleneck interface). Furthermore, the sending device performs congestion control based on the link utilization of the bottleneck link. For example, if the link utilization of the bottleneck link is less than a utilization threshold, the sending device increases the sending window; if the link utilization of the bottleneck link is greater than the utilization threshold, the sending device decreases the sending window.

[0113] BBR congestion control technology performs congestion control by attempting to control the sending rate of the sending device to exactly match the bottleneck bandwidth of the network. The sending rate of the sending device exactly matching the bottleneck bandwidth of the network means that when the sending device sends a message through the network at the sending rate, the amount of bandwidth occupied by the message is exactly equal to the bottleneck bandwidth of the network. Generally, if the sending device sends a message through the network at a certain sending rate, the amount of bandwidth occupied by the message is less than the bottleneck bandwidth of the network, then the bandwidth of the network is not fully utilized, which can easily lead to bandwidth waste. If the sending device sends a message through the network at a certain sending rate, the amount of bandwidth occupied by the message is greater than the bottleneck bandwidth of the network, then the message needs to be cached in the network device for a long time, which increases the queuing delay of the message. Therefore, in BBR congestion control technology, the convergence point of the sending rate of the sending device should exactly match the bottleneck bandwidth of the network. At this convergence point, the available bandwidth of the network is maximized and the round-trip time (RTT) is minimized. The sending device will periodically adjust the sending rate and determine the convergence point based on the change in the network RTT after adjusting the sending rate. For example, if the RTT of the network does not increase after the sending device increases the sending rate, it means that when the sending device sends messages at the increased sending rate, the bandwidth occupied by the messages on the network is less than the bottleneck bandwidth of the network, and the network has idle bandwidth resources. The sending device continues to increase the sending rate; if the RTT of the network decreases after the sending device decreases the sending rate, it means that when the sending device sends messages at the reduced sending rate, the bandwidth occupied by the messages on the network is greater than the bottleneck bandwidth of the network, and the network has no idle bandwidth resources. The sending device continues to decrease the sending rate.

[0114] However, in the current ECN and L4S technologies, the last two bits in the TC field in the IP header can only indicate whether the message has experienced congestion, and cannot carry more information related to congestion (actually, only one of the two bits indicates whether the message has experienced congestion, and the other bit is considered an enable bit). This makes it difficult for the end-side device to perform accurate congestion control based on these two bits. In the current IFIT technology, the detection information obtained by the network device can only be used by the network controller, without effective coordination with the end-side device. The current BBR congestion control technology cannot distinguish between the queuing delay of the message in the network device and the transmission delay of the message in the link (that is, the link delay), resulting in the need for the sending end device to continuously swing and detect near the convergence point of the sending rate. In the current INT technology and HPCC technology, during the message transmission process, the network device adds detection information to the INT header of the message hop by hop, causing the message to increase hop by hop, affecting the message encapsulation efficiency, and cannot be applied to long-distance multi-hop transmission scenarios. For example, according to the protocol, the size of a message cannot exceed the maximum transmission unit (MTU). If INT technology or HPCC technology is applied in a long-distance multi-hop transmission scenario, it is necessary to set the message to carry less application data (for example, set the payload of the message to be smaller) to ensure that the size of the message does not exceed the MTU after the message increases hop by hop. This will result in low encapsulation efficiency of the message and waste of bandwidth resources. If the message is set to carry more application data, the network device will add detection information to the INT header of the message hop by hop, which may cause the size of the message to exceed the MTU. In addition, both INT technology and HPCC technology obtain detection information at the granularity of the flow, and the end-side device performs relevant calculations based on the detection information at the flow granularity. This may cause the end-side device to perform repeated calculations, resulting in a waste of computing resources of the end-side device. For example, a sending device sends multiple streams to a receiving device, and the multiple streams share the same transmission path. The network devices on the transmission path obtain the same detection information based on the multiple streams. The end-side device (sending device or receiving device) calculates the link utilization of the bottleneck link based on the detection information of the multiple streams, which will cause the end-side device to perform repeated calculations, resulting in a waste of computing resources of the end-side device.

[0115] The embodiments of the present application provide a congestion control method, device, and system, which sets congestion detection indication information and a congestion information field in a message, uses the congestion detection indication information to instruct a device to obtain the congestion information corresponding to the device, and uses the congestion information field to carry the congestion information, so that the devices along the path of the message (including end-side devices and / or network devices) obtain the congestion information corresponding to the device according to the congestion detection indication information, and update the congestion information field according to the congestion information corresponding to the device. Compared with the current ECN technology and L4S technology, the congestion information field in the message provided by the present application can carry more congestion information, which helps the end-side device to perform accurate congestion control based on the congestion information carried by the congestion information field. Compared with the current IFIT technology, the present application can achieve effective collaboration between network devices and end-side devices. Compared to the current INT and HPCC technologies, in this application, the devices along the message path update the congestion information field based on the congestion information, rather than adding information to the message hop by hop. This does not cause the message to increase hop by hop, does not affect the message encapsulation efficiency, and is applicable to long-distance multi-hop transmission scenarios. In addition, this application allows the network device to perform hop-by-hop calculations, avoiding repeated calculations by the end-side device. Compared to the current BBR congestion control technology, in this application, the network device can calculate the cumulative processing delay of the message, which can be the cumulative queuing delay. The sending end device can quickly determine whether the sending rate of the sending end device is too high, causing additional queuing delay, based on the cumulative processing delay of the message, and the sending end device does not need to perform swing detection.

[0116] The technical solution of this application is introduced below, and the application scenario of this application is first introduced.

[0117] The application scenario of an embodiment of the present application provides a congestion control system, which includes a communication network and multiple end-side devices connected to the communication network. The communication network includes multiple network devices, and the multiple network devices are used to forward messages between different end-side devices to achieve communication between the different end-side devices. The multiple network devices include edge network devices and core network devices. The edge network devices are at the edge of the communication network and are used to connect the end-side devices to the communication network. The core network devices are connected between different edge network devices and are used to forward messages between different edge network devices. The communication network can be a data center network (DCN), a metropolitan area network, a wide area network, or a local area network. Each network device in the multiple network devices can be a switch or a router, and the types of the multiple network devices can be the same or different. For example, the multiple network devices are all switches or routers; or, some of the multiple network devices are switches, and other network devices are routers. The end-side devices can be hosts, servers, base stations, virtual machines (VMs), etc. The host can be various possible terminal devices such as smartphones, tablets, laptops, desktop computers, or Internet of Things (IoT) devices.

[0118] In an embodiment of the present application, the end-side devices accessing the communication network include a sending device and a receiving device, and the congestion control system includes a first device and a second device. The first device can be the sending device or a network device (for example, the network device is directly connected to the sending device), and the second device can be the receiving device or a network device (for example, the network device is directly connected to the receiving device). The message transmitted from the sending device to the receiving device includes a first message. During the transmission of the first message, the device along the way of the first message (for example, the first device) detects the network congestion situation based on the first message and carries the network congestion situation to the second device. The second device feeds back the network congestion situation to the sending device, and the sending device performs congestion control for the receiving device based on the network congestion situation.

[0119] Take the example where the first device is a sending device and the second device is a receiving device. As an example, Figure 1 is a schematic diagram of an application scenario provided by an embodiment of the present application. The congestion control system provided by this application scenario includes a communication network 100 and a sending device 201 and a receiving device 202 accessing the communication network 100. The communication network 100 includes network devices 101 to 103, and the network device 102 is connected between the network device 101 and the network device 103. The network device 101 and the network device 103 can both be edge network devices, and the network device 102 can be a core network device. The sending device 201 accesses the communication network 100 through the network device 101. The receiving device 202 accesses the communication network 100 through the network device 103. In an embodiment of the present application, a first message sent from a transmitting device 201 or a network device 101 to a receiving device 202 includes congestion detection indication information and a congestion information field. The congestion detection indication information is used to instruct devices along the path of the first message to obtain congestion information corresponding to the device, and the congestion information field is used to carry congestion information. In the process of sending the first message, the transmitting device 201 and each of the network devices 101 to 103 detect the congestion situation of each device according to the congestion detection indication information to obtain the congestion information of each device, and use the congestion information corresponding to each device to update the congestion information field (for example, the congestion information in the congestion information field is replaced with the congestion information corresponding to each device). After receiving the first message, the receiving device 202 sends a second message to the transmitting device 201 according to the congestion information field in the first message to instruct the transmitting device 201 to perform congestion control for the receiving device 202. The transmitting device 201 performs congestion control on the receiving device 202 based on the second message to achieve effects such as reducing network transmission delay, lowering packet loss rate, and ensuring bandwidth utilization of the communication network 100. For example, the transmitting device 201 adjusts the sending window, sending rate, etc. of the message sent by the transmitting device 201 to the receiving device 202 based on the second message to perform congestion control on the receiving device 202. The first message is a service message, a probe message, or a copy of the service message, and the second message is a probe message or an ACK message. For example, the first message is a service message or a copy of the service message, and the second message is an ACK message. For another example, the first message is a probe message and the second message is a probe message.

[0120] It should be noted that the application scenario shown in Figure 1 is for example only, and Figure 1 is not intended to limit the application scenario of the present application. The application scenario of the present application may include more or fewer devices than those shown in Figure 1, and the application scenario may also include other devices. For example, the communication network 100 may also include other devices (such as security devices) in addition to the network devices 101 to 103, and other devices may be connected between the end-side device and the communication network 100 (such as access devices for connecting the end-side device to the communication network 100). The application scenario may also include a control device for service control. Among them, the control device is connected to at least one end-side device and / or at least one network device. The control device can be a controller or a third-party network element. The control device can integrate functions such as network management, service control, and network analysis. The controller is a functional module deployed in a server, or a server, or a server cluster consisting of several servers, or a cloud computing service center, or other devices or modules with network control functions. The embodiments of the present application do not limit this.

[0121] The above is an introduction to the application scenarios of the present application. The following introduces an embodiment of the congestion control method of the present application.

[0122] Please refer to Figure 2, which shows a flowchart of a congestion control method provided in an embodiment of the present application. The congestion control method is applied to a first device in a congestion control system, where the first device is a transmitting device or a network device. For example, in the congestion control system shown in Figure 1, the first device is the transmitting device 201, or the first device is any network device from 101 to 103. As shown in Figure 2, the congestion control method includes the following steps S201 to S203.

[0123] S201. A first device obtains a first message, the first message including congestion detection indication information and a congestion information field. The congestion detection indication information is used to instruct the device to obtain congestion information corresponding to the device, and the congestion information field is used to carry the congestion information.

[0124] In an embodiment of the present application, congestion information includes at least one of first congestion information and second congestion information. The first congestion information is congestion information that the device needs to update after determining the congestion status, while the second congestion information is congestion information that the device can update without determining the congestion status. For example, the first congestion information includes at least one of the following: the utilization rate of a queue in the device used to buffer the first message; the utilization rate of an interface in the device used to send the first message; and the cumulative number of congested hops along the transmission path of the first message. The second congestion information includes the cumulative processing delay of the first message, which is the cumulative value of the processing delay of the first message in devices along the transmission path of the first message.

[0125] In which, each device on the transmission path of the first message includes a queue for caching the first message, and the utilization rate of the queue for caching the first message in any device can be the percentage of the amount of data cached in the queue to the total amount of data that the queue can cache (that is, the total capacity), or the percentage of the number of messages cached in the queue to the total number of messages that the queue can cache, or the percentage of the used space size of the queue to the total space size of the queue.

[0126] In which, each device on the transmission path of the first message includes an interface for sending the first message, and the utilization of the interface for sending the first message in any device includes at least one of the bandwidth utilization of the interface and the link utilization of the interface, and the link utilization of the interface is the utilization of the bandwidth of the interface and the cache space of the interface. The bandwidth utilization of the interface for sending the first message in any device is the percentage of the used bandwidth of the interface to the total bandwidth of the interface within a period of time (for example, the period from time t1 to time t2). The link utilization of the interface for sending the first message in any device is determined based on the amount of data sent by the interface within a period of time (for example, the period from time t1 to time t2), the used amount of the cache space of the interface at the current moment (that is, the size of the used cache space), and the bandwidth of the interface. For example, the link utilization of any interface is determined using the formula LR=Qlen / (B*T)+[(D2-D1) / (t2-t1)] / B, where LR represents the link utilization of the interface, Qlen represents the amount of cache space used by the interface at the current moment, B represents the bandwidth of the interface, T represents the ideal transmission delay of the end-to-end path (i.e., the transmission delay of the message from the sending device to the receiving device in the absence of any congestion), T is usually a constant, D2 represents the cumulative amount of data sent by the interface as of time t2, and D1 represents the cumulative amount of data sent by the interface as of time t1. Among them, D2-D1 represents the cumulative amount of data sent by the interface in the time period from time t1 to time t2, and (D2-D1) / (t2-t1) represents the average transmission rate of the interface in the time period from time t1 to time t2. In some embodiments, the link utilization of an interface is also referred to as the inflight utilization of the interface.

[0127] The cumulative congestion hop count on the transmission path of the first message is the sum of the hop counts where congestion occurs on the transmission path. Each device on the transmission path corresponds to a cumulative congestion hop count. The cumulative congestion hop count corresponding to any device on the transmission path is the cumulative congestion hop count on the transmission path up to the device.

[0128] The cumulative processing delay of the first message is the cumulative value of the processing delay of the first message in the devices on the transmission path of the first message. In one example, the processing delay of the first message in any device is the queuing delay of the first message in the device (that is, the length of time the first message stays in the queue for caching the first message in the device), and the cumulative processing delay of the first message is the cumulative value of the queuing delay of the first message in the devices on the transmission path of the first message. The cumulative processing delay is also the cumulative queuing delay. In another example, the processing delay of the first message in any device includes the queuing delay of the first message in the device and the sending delay of the first message in the device (that is, the sending delay of the interface of the device used to send the first message). Each device on the transmission path of the first message corresponds to a cumulative processing delay, and the cumulative processing delay corresponding to any device on the transmission path is the cumulative value of the processing delay of the first message in the device before the any device and the processing delay of the first message in the any device. The cumulative processing delay of the first message is accumulated hop by hop.

[0129] In an embodiment of the present application, the first message includes congestion detection indication information and a congestion information field, the congestion detection indication information is used to instruct the device to obtain the congestion information corresponding to the device, and the congestion information field is used to carry the congestion information. In one embodiment, the first message includes an enhanced explicit congestion notification (AECN) header, the AECN header includes the congestion detection indication information and the congestion information field, for example, the AECN header includes the congestion detection indication field and the congestion information field, and the congestion detection indication information is located in the congestion detection indication field. The AECN header can be an independent message header or a message header extended in other message headers. In one example, the first message includes an Internet Protocol version 6 (IPv6) extension header, the AECN header is located in the IPv6 extension header, the AECN header is a message header extended in the IPv6 extension header, for example, the AECN header is an option field extended in the IPv6 extension header. In another example, the first message includes an Internet Control Message Protocol (ICMP) header, the AECN header is located in the ICMP header, and the AECN header is a message header extended in the ICMP header, for example, the AECN header is an option field extended in the ICMP header.

[0130] In an embodiment of the present application, the AECN header includes a congestion detection indication field and a congestion information field, and may also include other fields, which are not limited in the embodiment of the present application. For example, please refer to Figure 3, which shows a schematic diagram of an AECN header provided in an embodiment of the present application. The AECN header includes a flags field, a congestion detection indication field, and a congestion information field. The length of the flag field is 8 bits, the length of the congestion detection indication field is 24 bits, and the length of the congestion information field can be an integer multiple of 32 bits. The flag field is used to indicate the type of private congestion information to support private algorithms of communication networks (such as data center networks). For example, the first bit in the flag field (for example, the first bit of the 8 bits arranged in order from low to high) is used to indicate the type of private congestion information, and the other bits are reserved. In scenarios where private congestion information does not need to be detected, the first bit is also reserved (that is, the entire flag field can be retained). The congestion detection indication field is used to carry congestion detection indication information to instruct a device along the path of the first message to obtain congestion information corresponding to the device, and the congestion information field is used to carry congestion information.

[0131] According to the foregoing description, there may be multiple types of congestion information in the embodiments of the present application (for example, the utilization rate of the queue for caching the first message in the device, the bandwidth utilization rate of the interface for sending the first message in the device, the link utilization rate of the interface for sending the first message in the device, the cumulative number of congested hops on the transmission path of the first message, and the cumulative processing delay of the first message are each a type of congestion information). Therefore, the congestion detection indication information carried by the congestion detection indication field is used to instruct the devices along the first message to obtain at least one of the multiple types of congestion information, and the congestion information field is used to carry at least one of the multiple types of congestion information. In an optional embodiment, the congestion detection indication field includes multiple detection flag subfields, the multiple detection flag subfields correspond one-to-one to the multiple types of congestion information, and each detection flag subfield is used to carry a type of congestion detection indication information, thereby instructing devices along the first message to obtain the congestion information corresponding to each detection flag subfield; the congestion information field includes at least one congestion information subfield, the at least one congestion information subfield corresponds one-to-one to at least one detection flag subfield in the multiple detection flag subfields, each congestion information subfield is used to carry the congestion information corresponding to the corresponding detection flag subfield, and the number of the multiple congestion information subfields is not greater than the number of the multiple detection flag subfields.

[0132] In one embodiment, the multiple detection flag subfields are multiple detection flag bits, and the value of each detection flag bit is 0 or 1. "1" is used to indicate that the device along the first message obtains the congestion information corresponding to each detection flag bit, and "0" is used to indicate that the device along the first message does not obtain the congestion information corresponding to each detection flag bit. The value "1" in each detection flag bit is the congestion detection indication information carried by each detection flag bit. The congestion detection indication field includes at least one congestion information subfield that corresponds one-to-one to at least one detection flag bit among the multiple detection flag bits. The at least one detection flag bit is a detection flag bit with a value of 1 among the multiple detection flag bits. In an optional embodiment, the multiple detection flags include first to fifth detection flags (i.e., a first detection flag, a second detection flag, a third detection flag, a fourth detection flag, and a fifth detection flag), the first detection flag corresponds to the utilization rate of the queue for caching the first message in the device, the second detection flag corresponds to the bandwidth utilization rate of the interface for sending the first message in the device, the third detection flag corresponds to the cumulative number of congested hops on the transmission path of the first message, the fourth detection flag corresponds to the cumulative processing delay of the first message, and the fifth detection flag corresponds to the link utilization rate of the interface for sending the first message in the device. If the value in the first detection flag is "1", the first detection flag is used to instruct the device along the first message to obtain the utilization rate of the queue for caching the first message in the device; if the value in the first detection flag is "0", the first detection flag is used to instruct the device along the first message not to obtain the utilization rate of the queue for caching the first message in the device. If the value in the second detection flag is "1," the second detection flag is used to instruct devices along the path of the first message to obtain the bandwidth utilization of the interface in the device used to send the first message; if the value in the second detection flag is "0," the second detection flag is used to instruct devices along the path of the first message not to obtain the bandwidth utilization of the interface in the device used to send the first message. If the value in the third detection flag is "1," the third detection flag is used to instruct devices along the path of the first message to obtain the cumulative number of congested hops on the transmission path of the first message; if the value in the third detection flag is "0," the third detection flag is used to instruct devices along the path of the first message not to obtain the cumulative number of congested hops on the transmission path of the first message. If the value in the fourth detection flag is "1," the fourth detection flag is used to instruct devices along the path of the first message to obtain the cumulative processing delay of the first message; if the value in the fourth detection flag is "0," the fourth detection flag is used to instruct devices along the path of the first message not to obtain the cumulative processing delay of the first message.If the value in the fifth detection flag is "1", the fifth detection flag is used to instruct the devices along the first message to obtain the link utilization of the interface in the device used to send the first message; if the value in the fifth detection flag is "0", the fifth detection flag is used to instruct the devices along the first message not to obtain the link utilization of the interface in the device used to send the first message. In one example, if the values ​​of the first to fifth detection flag bits are all 1, the congestion information field includes the first to fifth congestion information subfields (i.e., the first congestion information subfield, the second congestion information subfield, the third congestion information subfield, the fourth congestion information subfield, and the fifth congestion information subfield) that correspond one to one to the first to fifth detection flag bits. The first congestion information subfield is used to carry the utilization of the queue used to buffer the first message in the device, the second congestion information subfield is used to carry the bandwidth utilization of the interface used to send the first message in the device, the third congestion information subfield is used to carry the cumulative number of congested hops on the transmission path of the first message, the fourth congestion information subfield is used to carry the cumulative processing delay of the first message, and the fifth congestion information subfield is used to carry the link utilization of the interface used to send the first message in the device. In another example, if the values ​​of the first detection flag, the fourth detection flag, and the fifth detection flag are all 1, and the values ​​of the second detection flag and the third detection flag are all 0, the congestion information field includes a first congestion information subfield corresponding to the first detection flag, a fourth congestion information subfield corresponding to the fourth detection flag, and a fifth congestion information subfield corresponding to the fifth detection flag. The first congestion information subfield is used to carry the utilization rate of the queue used to buffer the first message in the device, the fourth congestion information subfield is used to carry the accumulated processing delay of the first message, and the fifth congestion information subfield is used to carry the link utilization rate of the interface used to send the first message in the device. For example, the multiple detection flags are arranged in order from low to high. Among the multiple detection flags arranged in order from low to high, the first detection flag is the first detection flag, the second detection flag is the second detection flag, the third detection flag is the third detection flag, the fourth detection flag is the fourth detection flag, and the fifth detection flag is the fifth detection flag.

[0133] In practical applications, the information that the AECN header can carry can be customized according to the template so that different congestion information is collected by devices along the message path in different network scenarios and different congestion control algorithms. For example, the information that the AECN header can carry can be customized by setting the values ​​of each detection flag subfield (e.g., detection flag bit) in the congestion detection indication field. For example, if the AECN header is customized to carry the utilization rate of the queue used to buffer messages in the device, the value in the first detection flag bit is set to 1. If the AECN header is customized to carry the bandwidth utilization rate of the interface used to send messages in the device, the value in the second detection flag bit is set to 1. If the AECN header is customized to carry the cumulative number of congested hops, the value in the third detection flag bit is set to 1. If the AECN header is customized to carry the cumulative processing delay, the value in the fourth detection flag bit is set to 1. If the AECN header is customized to carry the link utilization rate of the interface used to send messages in the device, the value in the fifth detection flag bit is set to 1.

[0134] This embodiment of the present application uses the example of a congestion information field including a congestion information subfield corresponding to a detection flag bit with a value of 1. In some embodiments, the number of congestion information subfields included in the congestion information field is equal to the number of detection flag subfields (e.g., detection flag bits) included in the congestion detection indication field. The congestion information field includes a congestion information subfield corresponding to a detection flag bit with a value of 1 and a congestion information subfield corresponding to a detection flag bit with a value of 0, but this embodiment of the present application is not limited thereto. In addition, in some embodiments, the congestion detection indication field is also referred to as a congestion information type field, and the congestion information field is also referred to as a congestion information data field.

[0135] In an embodiment of the present application, the first message is a business message (for example, a business message of a first business flow), a detection message, or a copy of the business message, and the copy message is a message obtained by copying the business message, and the copy message is the same as the business message. The first device is a sending end device or a network device on the transmission path of the first message. In an embodiment in which the first device is a network device, the first device may be a network device directly connected to the sending end device, or may not be a network device directly connected to the sending end device (that is, there are other network devices between the first device and the sending end device). Depending on the first device, the implementation method of the first device obtaining the first message is different. The following three embodiments introduce the implementation method of the first device obtaining the first message.

[0136] First embodiment: the first device is a sending device, and the first device generates a first message.

[0137] In the first embodiment, the first device (ie, the sending end device) may be a head node device for congestion detection.

[0138] In the first example, the first device encapsulates congestion detection indication information and congestion information field (for example, encapsulates an AECN header) in the original message A of the first service flow to obtain a first message.

[0139] In the second example, the first device constructs a probe message according to the original message A of the first service flow, and the first device encapsulates congestion detection indication information and congestion information field (for example, encapsulates an AECN header) in the probe message to obtain a first message.

[0140] In the third example, the first device copies the original message A of the first service flow to obtain a copied message A1, and the first device encapsulates congestion detection indication information and congestion information field (for example, encapsulates an AECN header) in the copied message A1 to obtain a first message.

[0141] Among them, the original message A can be a business message of the first business flow. Therefore, the first message in the above first example is a business message, the first message in the above second example is a detection message, and the first message in the above third example can be a copy message of the business message. The detection message can be an ICMP message, and the embodiment of the present application does not limit this.

[0142] Second embodiment: The first device is a network device, and the first device receives a first message from a sending device.

[0143] In this second embodiment, the first device is any network device along the path of the first message. The first device may or may not be directly connected to the sending device. The first message is generated by the sending device, which then transmits the first message, and the network device receives the first message. The implementation process of the sending device generating the first message can be referenced in the first embodiment above and will not be further described here. The sending device may be a head node device used for congestion detection.

[0144] A third embodiment: the first device is a network device, the first device receives an original message from a sending device, and the first device generates a first message according to the original message.

[0145] In this third embodiment, the first device (i.e., a network device) can be a head node device for congestion detection. The first device is a network device directly connected to the sending device (or may not be a network device directly connected to the sending device), and the original message can be a service message, a probe message, or a copy of the service message. For example, the original message is a service message of the first service flow (such as the original message A described above), or a probe message constructed by the sending device based on the service message of the first service flow, or a copy of the service message of the first service flow obtained by the sending device.

[0146] In the first example, a first device constructs a first message based on an original message from a transmitting device. For example, the original message is a service message. The first device constructs a probe message based on the original message and encapsulates congestion detection indication information and a congestion information field (e.g., an AECN header) in the probe message to obtain the first message. The first message is a probe message.

[0147] In the second example, the first device encapsulates congestion detection indication information and a congestion information field (e.g., an AECN header) in an original message from the sending device to obtain a first message. The original message is a service message or a probe message, and thus the first message can be a service message or a probe message. The probe message can be an ICMP message.

[0148] In a third example, a first device copies an original message from a sending device to obtain a copied message, and then encapsulates congestion detection indication information and a congestion information field (e.g., an AECN header) in the copied message to obtain a first message. The original message is a service message or a probe message, and the first message is a service message, a probe message, or a copied message.

[0149] S202. The first device obtains congestion information corresponding to the first device according to the congestion detection indication information in the first message.

[0150] In this embodiment of the present application, the congestion information includes at least one of first congestion information and second congestion information. Therefore, the first device obtains the first congestion information and / or second congestion information corresponding to the first device based on the congestion detection indication information in the first message. The following describes the implementation process of the first device obtaining the congestion information corresponding to the first device in two embodiments.

[0151] First embodiment: the congestion detection indication information in the first message is used to instruct a device to obtain first congestion information corresponding to the device, and the first device obtains the first congestion information corresponding to the first device according to the congestion detection indication information.

[0152] The first congestion information includes at least one of the following: utilization of a queue in the device for caching the first message, bandwidth utilization of an interface in the device for sending the first message, link utilization of an interface in the device for sending the first message, and cumulative number of congested hops on the transmission path of the first message. Therefore, in this first embodiment, the first device obtains at least one of the following congestion information corresponding to the first device based on the congestion detection indication information in the first message: utilization of a queue in the first device for caching the first message, bandwidth utilization of an interface in the first device for sending the first message, link utilization of an interface in the first device for sending the first message, and cumulative number of congested hops corresponding to the first device. The cumulative number of congested hops corresponding to the first device is the cumulative number of congested hops on the transmission path of the first message that ends at the first device.

[0153] Second embodiment: the congestion detection indication information in the first message is used to instruct the device to obtain the second congestion information corresponding to the device, and the first device obtains the second congestion information corresponding to the first device according to the congestion detection indication information.

[0154] The second congestion information includes the accumulated processing delay of the first message. Therefore, the first device obtains the accumulated processing delay corresponding to the first device based on the congestion detection indication information in the first message. The accumulated processing delay corresponding to the first device is the accumulated value of the processing delay of the first message in the first device and the processing delay of the first message in the device before the first device.

[0155] In an embodiment of the present application, there may be multiple types of congestion information (for example, a utilization rate of a queue for caching a first message in a device, a bandwidth utilization rate of an interface for sending the first message in the device, a link utilization rate of an interface for sending the first message in the device, a cumulative number of congested hops on a transmission path of the first message, and a cumulative processing delay of the first message are each a type of congestion information). The multiple types of congestion information include first congestion information and second congestion information. The congestion detection indication information in the first message is used to instruct the first device to obtain at least one type of congestion information from the multiple types of congestion information. The first device obtains the at least one type of congestion information corresponding to the first device based on the congestion detection indication information. Optionally, the first message includes an AECN header, the AECN header includes a congestion detection indication field for carrying congestion detection indication information, the congestion detection indication field includes multiple detection flag subfields, the multiple detection flag subfields correspond one to the multiple congestion information, each detection flag subfield is used to carry a type of congestion detection indication information, thereby instructing the devices along the first message to obtain the congestion information corresponding to each detection flag subfield, and the first device obtains at least one type of congestion information among the multiple congestion information based on the multiple detection flag subfields.

[0156] In one embodiment, the multiple detection flag subfields are multiple detection flag bits. The first device determines the detection flag bits with a value of 1 among the multiple detection flag bits, and the first device obtains congestion information corresponding to the detection flag bits with a value of 1. Optionally, the multiple detection flag bits include first to fifth detection flag bits, the first detection flag bit corresponding to the utilization rate of the queue used to buffer the first message in the device, the second detection flag bit corresponding to the bandwidth utilization rate of the interface used to send the first message in the device, the third detection flag bit corresponding to the cumulative number of congested hops on the transmission path of the first message, the fourth detection flag bit corresponding to the cumulative processing delay of the first message, and the fifth detection flag bit corresponding to the link utilization rate of the interface used to send the first message in the device. If the value of the first detection flag bit is "1", the first device obtains the utilization rate of the queue used to buffer the first message in the first device; if the value of the first detection flag bit is "0", the first device does not obtain the utilization rate of the queue used to buffer the first message in the first device. If the value in the second detection flag is "1," the first device obtains the bandwidth utilization of the interface on the first device used to send the first message. If the value in the second detection flag is "0," the first device does not obtain the bandwidth utilization of the interface on the first device used to send the first message. If the value in the third detection flag is "1," the first device obtains the cumulative number of congested hops on the transmission path of the first message (i.e., the cumulative number of congested hops corresponding to the first device, which is the cumulative number of congested hops on the transmission path of the first message ending at the first device). If the value in the third detection flag is "0," the first device does not obtain the cumulative number of congested hops on the transmission path of the first message. If the value in the fourth detection flag is "1," the first device obtains the cumulative processing delay of the first message (i.e., the cumulative processing delay corresponding to the first device, which is the cumulative value of the processing delay of the first message on the first device and the processing delay of the first message on the device before the first device). If the value in the fourth detection flag is "0," the first device does not obtain the cumulative processing delay of the first message. If the value in the fifth detection flag is "1", the first device obtains the link utilization of the interface in the first device used to send the first message; if the value in the fifth detection flag is "0", the first device does not obtain the link utilization of the interface in the first device used to send the first message. In one example, if the values ​​in the first to fifth detection flags are all 1, the first device obtains the following congestion information corresponding to the first device: the utilization of the queue in the first device used to buffer the first message, the bandwidth utilization of the interface in the first device used to send the first message, the cumulative number of congested hops on the transmission path of the first message (that is, the cumulative number of congested hops corresponding to the first device), the cumulative processing delay of the first message (that is, the cumulative processing delay corresponding to the first device), and the link utilization of the interface in the first device used to send the first message.In another example, the values ​​of the first detection flag, the fourth detection flag, and the fifth detection flag are all 1, and the values ​​of the second detection flag and the third detection flag are all 0, then the first device obtains the following congestion information corresponding to the first device: the utilization rate of the queue for caching the first message in the first device, the cumulative processing delay of the first message (that is, the cumulative processing delay corresponding to the first device), and the link utilization rate of the interface for sending the first message in the first device.

[0157] In one embodiment, the value in the second detection flag is "1," and the first device uses a discounted rate estimator (DRE) algorithm to obtain the bandwidth utilization of the interface in the first device used to send the first message. In another embodiment, the value in the third detection flag is "1," and the first device detects whether the interface in the first device used to send the first message is congested. If the interface in the first device used to send the first message is congested, the first device determines that congestion has occurred in the first device, and the first device adds 1 to the cumulative congestion hop count in the congestion information field in the first message to obtain the corresponding cumulative congestion hop count for the first device. In yet another embodiment, the value in the fourth detection flag is "1," and the first device obtains the processing delay of the first message in the first device. The first device adds the processing delay of the first message in the first device to the cumulative processing delay in the congestion information field in the first message to obtain the corresponding cumulative processing delay for the first device.

[0158] S203. The first device updates the congestion information field in the first message according to the congestion information corresponding to the first device.

[0159] When the first device updates the congestion information field in the first message, it means that the first device updates the congestion information in the congestion information field. In this embodiment of the present application, the congestion information includes at least one of first congestion information and second congestion information. Therefore, the first device updates the first congestion information and / or second congestion information in the congestion information field based on the congestion information corresponding to the first device. The following describes the implementation process of the first device updating the congestion information field in the first message in two embodiments.

[0160] In a first embodiment (corresponding to the first embodiment in S202), if the relationship between the first congestion information corresponding to the first device and the first congestion information in the congestion information field satisfies a preset condition, the first device updates the first congestion information in the congestion information field with the first congestion information corresponding to the first device. For example, the first device replaces the first congestion information in the congestion information field with the first congestion information corresponding to the first device. The preset condition includes any one of the following: the value of the first congestion information corresponding to the first device is greater than the value of the first congestion information in the congestion information field; or the value of the first congestion information corresponding to the first device is less than or equal to the value of the first congestion information in the congestion information field.

[0161] Optionally, the first device determines whether the first congestion information corresponding to the first device and the first congestion information in the congestion information field meet the preset condition. If the relationship between the first congestion information corresponding to the first device and the first congestion information in the congestion information field meets the preset condition, the first device uses the first congestion information corresponding to the first device to update the first congestion information in the congestion information field. If the relationship between the first congestion information corresponding to the first device and the first congestion information in the congestion information field does not meet the preset condition, the first device does not use the first congestion information corresponding to the first device to update the first congestion information in the congestion information field. It should be noted that there may be multiple types of first congestion information. When the first device determines whether the first congestion information corresponding to the first device and the first congestion information in the congestion information field meet the preset condition, the first device determines congestion information of the same type (or category). The following explanation uses the preset condition that the value of the first congestion information corresponding to the first device is greater than the value of the first congestion information in the congestion information field as an example.

[0162] In one example, the first congestion information corresponding to the first device includes the utilization of a queue in the first device for caching the first message. The congestion information field includes the queue utilization. The queue utilization in the congestion information field is an initial utilization or the utilization of a queue in a device preceding the first device on the transmission path of the first message for caching the first message. The initial queue utilization may be the initial value of the queue utilization set by the device that generates the first message, which is typically 0. The first device determines whether the utilization of the queue in the first device for caching the first message is greater than the queue utilization in the congestion information field. If the utilization of the queue in the first device for caching the first message is greater than the queue utilization in the congestion information field, the first device updates the queue utilization in the congestion information field with the utilization of the queue in the first device for caching the first message. For example, the first device replaces the queue utilization in the congestion information field with the utilization of the queue in the first device for caching the first message. If the utilization of the queue for buffering the first message in the first device is not greater than the queue utilization in the congestion information field, the first device does not use the utilization of the queue for buffering the first message in the first device to update the queue utilization in the congestion information field.

[0163] In another example, the first congestion information corresponding to the first device includes the bandwidth utilization of the interface of the first device used to send the first message. The congestion information field includes the bandwidth utilization. The bandwidth utilization in the congestion information field is the initial utilization or the bandwidth utilization of the interface of a device located before the first device on the transmission path of the first message used to send the first message. The initial utilization may be the initial value of the bandwidth utilization set by the device generating the first message, which is typically 0. The first device determines whether the bandwidth utilization of the interface of the first device used to send the first message is greater than the bandwidth utilization in the congestion information field. If the bandwidth utilization of the interface of the first device used to send the first message is greater than the bandwidth utilization in the congestion information field, the first device updates the bandwidth utilization in the congestion information field with the bandwidth utilization of the interface of the first device used to send the first message, for example, replacing the bandwidth utilization in the congestion information field with the bandwidth utilization of the interface of the first device used to send the first message. If the bandwidth utilization of the interface used for sending the first message in the first device is not greater than the bandwidth utilization in the congestion information field, the first device does not use the bandwidth utilization of the interface used for sending the first message in the first device to update the bandwidth utilization in the congestion information field.

[0164] In another example, the first congestion information corresponding to the first device includes a cumulative congestion hop count. The cumulative congestion hop count corresponding to the first device is the cumulative congestion hop count on the transmission path of the first message ending at the first device. The congestion information field includes the cumulative congestion hop count. The cumulative congestion hop count in the congestion information field is the initial congestion hop count or the cumulative congestion hop count corresponding to a device preceding the first device on the transmission path of the first message. The initial congestion hop count may be the initial value of the congestion hop count set by the device generating the first message, which is typically 0. The first device determines whether the cumulative congestion hop count corresponding to the first device is greater than the cumulative congestion hop count in the congestion information field. If the cumulative congestion hop count corresponding to the first device is greater than the cumulative congestion hop count in the congestion information field, the first device updates the cumulative congestion hop count in the congestion information field with the cumulative congestion hop count corresponding to the first device. For example, the first device replaces the cumulative congestion hop count in the congestion information field with the cumulative congestion hop count corresponding to the first device, or the first device adds 1 to the cumulative congestion hop count in the congestion information field. When the cumulative congestion hop count corresponding to the first device is not greater than the cumulative congestion hop count in the congestion information field, the first device does not use the cumulative congestion hop count corresponding to the first device to update the cumulative congestion hop count in the congestion information field.

[0165] In another example, the first congestion information corresponding to the first device includes the link utilization of the interface of the first device used to send the first message. The congestion information field includes the link utilization. The link utilization in the congestion information field is the initial utilization or the link utilization of the interface of a device located before the first device on the transmission path of the first message used to send the first message. The initial utilization may be the initial value of the link utilization set by the device generating the first message, which is typically 0. The first device determines whether the link utilization of the interface of the first device used to send the first message is greater than the link utilization in the congestion information field. If the link utilization of the interface of the first device used to send the first message is greater than the link utilization in the congestion information field, the first device updates the link utilization in the congestion information field with the link utilization of the interface of the first device used to send the first message. For example, the link utilization in the congestion information field is replaced with the link utilization of the interface of the first device used to send the first message. If the link utilization of the interface used for sending the first message in the first device is not greater than the link utilization in the congestion information field, the first device does not use the link utilization of the interface used for sending the first message in the first device to update the link utilization in the congestion information field.

[0166] In the second embodiment (corresponding to the second embodiment in S202 ), the first device updates the second congestion information in the congestion information field using the second congestion information corresponding to the first device. For example, the first device replaces the second congestion information in the congestion information field using the second congestion information corresponding to the first device.

[0167] For example, the first congestion information corresponding to the first device includes a cumulative processing delay, which is the cumulative value of the processing delay of the first message in the first device and the processing delay of the first message in devices before the first device (for example, all devices before the first device). The congestion information field includes the cumulative processing delay, which is the initial cumulative processing delay or the cumulative processing delay corresponding to the previous-hop device of the first device. The initial cumulative processing delay may be the initial value of the cumulative processing delay set by the device that generated the first message, and the initial cumulative processing delay is typically 0. The first device replaces the cumulative processing delay in the congestion information field with the cumulative processing delay corresponding to the first device to update the cumulative processing delay in the congestion information field.

[0168] In summary, the technical solution provided by the embodiment of the present application sets congestion detection indication information and a congestion information field in the first message, uses the congestion detection indication information to instruct the device to obtain congestion information corresponding to the device, and uses the congestion information field to carry the congestion information, so that the devices along the path of the first message obtain the congestion information corresponding to the device according to the congestion detection indication information, and updates the congestion information field according to the congestion information corresponding to the device. The congestion information field can carry more congestion information, which facilitates the end-side device to perform accurate congestion control according to the congestion information carried by the congestion information field.

[0169] In an optional embodiment, please continue to refer to FIG. 2 , after S203 , the method further includes the following step S204 .

[0170] S204. The first device sends a first message.

[0171] The first device sends the first message through an interface in the first device used to send the first message.

[0172] In an optional embodiment, the first device is a sending device. Please refer to Figure 4, which shows a flowchart of another congestion control method provided in an embodiment of the present application. After S204, the method also includes the following steps S205 to S206.

[0173] S205. The first device receives a second message from the second device, where the second message corresponds to the first message.

[0174] The second device is a receiving device of the first message, or the second device is a network device between the first device and the receiving device, and the network device can be directly connected to the receiving device.

[0175] In an embodiment of the present application, a device along the path of the first message obtains the congestion information corresponding to the device based on the congestion detection indication information in the first message, uses the congestion information corresponding to the device to update the congestion information in the congestion information field in the first message, and sends the first message. After the second device receives the first message, the second device sends a second message to the sending device based on the congestion information field in the first message to instruct the sending device to perform congestion control on the receiving device of the first message, and the first device, as the sending device, receives the second message from the second device. The second message is a probe message or an ACK message of the transport layer. For example, the first message is a service message or a copy of the service message, and the second message is an ACK message of the transport layer. For another example, the first message is a probe message and the second message is a probe message.

[0176] In an embodiment of the present application, the second message includes at least one of congestion information in a congestion information field and a congestion control instruction to instruct the transmitting device to perform congestion control on the receiving device of the first message. The congestion control instruction is determined by the second device based on the congestion information in the congestion information field. The congestion control instruction is used to instruct the transmitting device to perform congestion control on the receiving device. The congestion control instruction can also be used to indicate a congestion control policy (i.e., how to perform congestion control). Optionally, the second device determines whether congestion occurs in the transmission path of the first message (i.e., determines whether the first message has experienced congestion) based on the congestion information in the congestion information field of the first message received by the second device. The second device generates the congestion control instruction based on whether congestion occurs in the transmission path of the first message. For example, the second device determines whether congestion information in a congestion information field of a first message received by the second device satisfies a congestion condition. If the congestion information in the congestion information field satisfies the congestion condition, the second device determines that congestion occurs on the transmission path of the first message. If the congestion information in the congestion information field does not satisfy the congestion condition, the second device determines that congestion does not occur on the transmission path of the first message. The congestion condition includes at least one of the following: a queue utilization in the congestion information field is greater than a first threshold; a bandwidth utilization in the congestion information field (i.e., bandwidth utilization of an interface) is greater than a second threshold; a link utilization in the congestion information field (i.e., link utilization of an interface; the link utilization in the congestion information field in the first message received by the second device (e.g., a receiving device) is the link utilization of a bottleneck interface on the transmission path of the first message) is greater than a third threshold; a cumulative congestion hop count in the congestion information field is greater than a preset hop count; or a cumulative processing delay in the congestion information field is greater than a preset delay. If the second device determines that the congestion information in the congestion information field satisfies at least one of the congestion conditions, the second device determines that congestion occurs on the transmission path of the first message. The first threshold, second threshold, third threshold, preset number of hops, and preset delay are set based on actual conditions. For example, the preset number of hops is 0, and this is not limited in this embodiment of the present application.

[0177] In one embodiment, the second device determines that the transmission path of the first message is congested, and the second device generates a congestion control instruction. In one example, the congestion control instruction is used to instruct the sending end device to reduce the sending window, sending rate, etc. of the message sent by the sending end device to the receiving end device of the first message (that is, it indicates reduction but does not indicate how to reduce it). In another example, the congestion control instruction is used to instruct the sending end device to reduce the sending window of the message sent by the sending end device to the receiving end device of the first message according to subtraction (that is, it indicates reduction and indicates how to reduce it). In yet another example, the congestion control instruction is used to instruct the sending end device to reduce the sending window of the message sent by the sending end device to the receiving end device of the first message according to division (that is, it indicates reduction and indicates how to reduce it). In another example, the congestion control instruction is used to instruct the sending device to first reduce the sending window for the sending device to send messages to the receiving device of the first message according to division, and after the number of times the sending window is reduced according to division reaches a preset number, reduce the sending window for the sending device to send messages to the receiving device according to subtraction (that is, instruct to reduce and indicate how to reduce).

[0178] In another embodiment, the second device determines that the transmission path of the first message is not congested, and the second device generates a congestion control instruction. In one example, the congestion control instruction is used to instruct the sending end device to increase the sending window, sending rate, etc. of the message sent by the sending end device to the receiving end device of the first message (that is, to indicate increase but not to indicate how to increase). In another example, the congestion control instruction is used to instruct the sending end device to increase the sending window of the message sent by the sending end device to the receiving end device of the first message according to addition (that is, to indicate increase and to indicate how to increase). In yet another example, the congestion control instruction is used to instruct the sending end device to increase the sending window of the message sent by the sending end device to the receiving end device of the first message according to multiplication (that is, to indicate increase and to indicate how to increase). In another example, the congestion control instruction is used to instruct the sending device to first increase the sending window of the sending device for sending messages to the receiving device of the first message according to addition, and after the number of times the sending window is increased by addition reaches a preset number, the sending window of the sending device for sending messages to the receiving device is increased by multiplication (that is, to instruct to increase and how to increase).

[0179] In the embodiments of the present application, a second device determines whether congestion occurs on the transmission path of a first message based on congestion information in a congestion information field of a first message received by the second device. The second device may also determine the degree of congestion or congestion level of the transmission path based on the congestion information in the congestion information field. For example, the greater the value of the congestion information in the congestion information field, the greater the degree of congestion of the transmission path and the higher the congestion level. For example, the second device includes a mapping relationship between a range of congestion information values ​​and the degree of congestion (or congestion level). The second device determines the degree of congestion or congestion level of the transmission path based on the value of the congestion information in the congestion information field and the mapping relationship. Optionally, when generating a congestion control instruction, the second device may also consider the degree of congestion or congestion level of the transmission path. The greater the degree of congestion of the transmission path and the higher the congestion level of the transmission path, the greater the control force of the congestion control policy indicated by the congestion control instruction generated by the second device (for example, the faster the send window is reduced, the faster the send rate is reduced).

[0180] S206. The first device performs congestion control on the receiving device of the first message according to the second message.

[0181] In an embodiment of the present application, the second message includes congestion information and / or congestion control instructions in the congestion information field in the first message, and the first device performs congestion control on the receiving device of the first message according to the congestion information and / or the congestion control instructions.

[0182] In one embodiment, the second message includes a congestion control instruction, which is used to instruct a transmitting device (i.e., a first device) to perform congestion control on a receiving device of the first message and does not specify a congestion control policy. The first device performs congestion control on the receiving device based on the congestion control instruction in combination with a local congestion control algorithm. For example, the first device determines a congestion control policy based on the congestion control instruction in combination with a local congestion control algorithm, and the first device executes the congestion control policy on the receiving device to perform congestion control on the receiving device.

[0183] In another embodiment, the second message includes a congestion control instruction, which is used to instruct the sending device (i.e., the first device) to perform congestion control on the receiving device of the first message and indicate a congestion control strategy. The first device executes the congestion control strategy indicated by the congestion control instruction on the receiving device to perform congestion control on the receiving device.

[0184] In another embodiment, the second message includes congestion information in a congestion information field. The first device determines a congestion control instruction based on the congestion information in the second message, and performs congestion control on the receiving device of the first message based on the congestion control instruction. The implementation process of the first device determining the congestion control instruction based on the congestion information can refer to the implementation process of the second device determining the congestion control instruction based on the congestion information, and is not further described here.

[0185] In the technical solution provided by the embodiment of the present application, the devices along the first message update the congestion information in the congestion information field in the first message hop by hop, and the second device (for example, the receiving device of the first message) sends a second message to the sending device based on the congestion information in the congestion information field in the first message received by the second device. The sending device performs congestion control on the receiving device of the first message based on the second message. Since the congestion information field can carry more congestion information, the sending device can achieve accurate congestion control. In addition, the link utilization in the congestion information field in the first message received by the second device can be the link utilization of the bottleneck interface on the transmission path of the first message. Compared with the current HPCC technology, the technical solution provided by the embodiment of the present application can move the process of calculating the link utilization of the bottleneck interface from the end-side device (for example, the sending device) to the network device, avoiding repeated calculations by the end-side device and waste of resources.

[0186] The current BBR congestion control technology cannot distinguish between queuing delay and link delay, resulting in the need for the sending device to constantly swing and detect near the convergence point of the sending rate of the sending device. In the technical solution provided by the embodiment of the present application, the cumulative processing delay of the first message can be the cumulative queuing delay, and the devices along the way of the first message can obtain the cumulative queuing delay corresponding to the device. The cumulative queuing delay corresponding to each device is the cumulative value of the queuing delay of the first message in the device and the queuing delay of the first message in the device before the device. The devices along the way of the first message update the cumulative queuing delay in the congestion information field of the first message hop by hop according to the cumulative queuing delay corresponding to the device. The cumulative queuing delay in the congestion information field can be provided to the sending device by the second device. The sending device can quickly determine the convergence point of the sending rate of the message sent by the sending device to the receiving device of the first message based on the cumulative queuing delay in the congestion information field, and determine the bottleneck bandwidth on the transmission path of the first message. For example, the sending device quickly determines, based on the accumulated queuing delay of the first message, whether the sending rate of the message sent by the sending device to the receiving device is too high, causing additional queuing delay, and adjusts the sending rate of the message sent by the sending device to the receiving device to the convergence point based on the judgment result, without the need for the sending device to continuously swing and detect near the convergence point.

[0187] Please refer to Figure 5, which shows a flowchart of another congestion control method provided by an embodiment of the present application. This congestion control method is applied to a second device in a congestion control system, where the second device is a receiving device or a network device. For example, in the congestion control system shown in Figure 1, the second device is the receiving device 202, or the second device is any of the network devices 101-103. As shown in Figure 5, the congestion control method includes the following steps S501 to S502.

[0188] S501. A second device receives a first message, where the first message includes congestion detection indication information and a congestion information field. The congestion detection indication information is used to instruct the device to obtain congestion information corresponding to the device, and the congestion information field is used to carry congestion information.

[0189] The second device receives the first message from the previous hop device of the second device. For the description of the first message and congestion information, please refer to the description in S201, which will not be repeated here.

[0190] S502. The second device sends a second message to the sending device according to the congestion information field in the first message, where the second message is used to instruct the sending device to perform congestion control on the receiving device of the first message.

[0191] The second device generates a second message based on the congestion information in the congestion information field of the first message, and sends the second message to the transmitting device, instructing the transmitting device to perform congestion control on the receiving device of the first message. The second message is a probe message or a transport layer ACK message. The second message includes the congestion information in the congestion information field and / or a congestion control instruction, which is determined based on the congestion information in the congestion information field. Optionally, the second device generates the congestion control instruction based on the congestion information in the congestion information field, and the second device generates the second message including the congestion control instruction. For example, the second device determines whether the transmission path of the first message is congested, determines the degree or level of congestion on the transmission path, and generates the congestion control instruction based on the congestion information in the congestion information field. The second device generates the congestion control instruction based on whether the transmission path is congested, the degree or level of congestion on the transmission path, and the like. The implementation process for the second device generating the congestion control instruction can be found in the relevant description of S205 and is not further described here.

[0192] In summary, the technical solution provided by the embodiments of the present application provides congestion detection indication information and a congestion information field in a first message. The congestion detection indication information is used to instruct a device to obtain congestion information corresponding to the device, and the congestion information field is used to carry the congestion information. Devices along the path of the first message can obtain the congestion information corresponding to the device based on the congestion detection indication information and update the congestion information field based on the congestion information corresponding to the device. A second device sends a second message to the sending device based on the congestion information field, causing the sending device to perform congestion control for the receiving device of the first message. Because the congestion information field can carry a large amount of congestion information, the second message sent by the second device to the sending device based on the congestion information field can instruct the sending device to perform precise congestion control.

[0193] According to the above description, the first message can be generated by the sending device, or it can be generated by the network device based on the original message from the sending device. That is, the message sent by the sending device may include congestion detection indication information and congestion information field (for example, including an AECN header); or, the message sent by the sending device does not include congestion detection indication information and congestion information field (for example, does not include an AECN header), and the network device generates a message including the congestion detection indication information and the congestion information field based on the message sent by the sending device (for example, generates a message including an AECN header). In addition, the second device can be a receiving device or a network device. The congestion control method of the present application is introduced below by taking the example that the message sent by the sending device includes congestion detection indication information and congestion information field, and the second device is a receiving device.

[0194] Please refer to Figure 6, which shows a flowchart of another congestion control method provided in an embodiment of the present application. This congestion control method is applied to a congestion control system including a transmitting device, a receiving device, and a network device. For example, the congestion control system is shown in Figure 1. As shown in Figure 6, the congestion control method includes the following steps S601 to S612.

[0195] S601. The transmitting device generates a first message, which includes congestion detection indication information and a congestion information field. The congestion detection indication information is used to instruct the device to obtain congestion information corresponding to the device, and the congestion information field is used to carry congestion information.

[0196] S602. The sending end device obtains congestion information corresponding to the sending end device according to the congestion detection indication information in the first message.

[0197] S603. The sending end device updates the congestion information field in the first message according to the congestion information corresponding to the sending end device.

[0198] S604. The sending device sends a first message.

[0199] S605. The network device receives the first message.

[0200] S606. The network device obtains congestion information corresponding to the network device according to the congestion detection indication information in the first message.

[0201] S607. The network device updates the congestion information field in the first message according to the congestion information corresponding to the network device.

[0202] S608. The network device forwards the first message.

[0203] S609. The receiving device receives the first message.

[0204] S610. The receiving device sends a second message to the sending device according to the congestion information field in the first message, where the second message is used to instruct the sending device to perform congestion control on the receiving device.

[0205] S611. The transmitting device receives a second message from the receiving device.

[0206] S612. The transmitting device performs congestion control on the receiving device according to the second message.

[0207] The network device in the embodiment shown in FIG6 can be any network device on the transmission path of the first message. The implementation process of S601 can refer to the first embodiment of the first device obtaining the first message in S201. The implementation processes of S602 to S604 and the implementation processes of S606 to S608 can all refer to the implementation processes of S202 to S204. The implementation process of S605 can refer to the second embodiment of the first device obtaining the first message in S201. The implementation processes of S609 to S610 can refer to the implementation processes of S501 to S502. The implementation processes of S611 to S612 can refer to the implementation processes of S205 to S206.

[0208] As an example, please refer to Figure 7, which shows a schematic diagram of a congestion control method provided by an embodiment of the present application. Figure 7 applies the congestion control method to the congestion control system shown in Figure 1, and takes the first message generated by the sending device 201 as an example. As shown in Figure 7, the first message includes a payload and an AECN header, and the AECN header includes congestion detection indication information and a congestion information field as an example (Figure 7 does not show the congestion detection indication information and the congestion information field in the AECN header for the sake of simplicity). The transmission path of the first message is: sending device 201->network device 101->network device 102->network device 103->receiving device 202. In the process of sending the first message from the sending device 201 to the receiving device 202, the devices on the transmission path update the congestion information field in the AECN header of the first message hop by hop (that is, update the congestion information in the congestion information field). After receiving the first message, receiving device 202 sends a second message to transmitting device 201 based on the first message. The second message includes at least one of the congestion information in the congestion information field and a congestion control instruction determined based on the congestion information. The second message is used to instruct transmitting device 201 to perform congestion control on receiving device 202. Transmitting device 201 adjusts the sending window, sending rate, and other parameters for transmitting messages from transmitting device 201 to receiving device 202 based on the second message, thereby performing congestion control on receiving device 202.

[0209] The congestion control method of the present application is introduced below by taking the case where the message sent by the sending device does not include congestion detection indication information and the congestion information field, the first network device generates a message including the congestion detection indication information and the congestion information field based on the message sent by the sending device, and the second device is a receiving device as an example.

[0210] Please refer to Figure 8, which shows a flowchart of another congestion control method provided in an embodiment of the present application. This congestion control method is applied to a congestion control system including a transmitting device, a receiving device, and a network device. For example, the congestion control system is shown in Figure 1. This congestion control method includes the following steps S801 to S814.

[0211] S801. The sending device sends an original message.

[0212] S802. The first network device receives the original message from the sending device.

[0213] S803. The first network device generates a first message according to the original message. The first message includes congestion detection indication information and a congestion information field. The congestion detection indication information is used to instruct the device to obtain congestion information corresponding to the device. The congestion information field is used to carry congestion information.

[0214] S804. The first network device obtains congestion information corresponding to the first network device according to the congestion detection indication information in the first message.

[0215] S805. The first network device updates the congestion information field in the first message according to the congestion information corresponding to the first network device.

[0216] S806. The first network device forwards the first message.

[0217] S807. The second network device receives the first message.

[0218] S808. The second network device obtains congestion information corresponding to the second network device according to the congestion detection indication information in the first message.

[0219] S809. The second network device updates the congestion information field in the first message according to the congestion information corresponding to the second network device.

[0220] S810. The second network device forwards the first message.

[0221] S811. The receiving device receives the first message.

[0222] S812. The receiving device sends a second message to the sending device according to the congestion information field in the first message, where the second message is used to instruct the sending device to perform congestion control on the receiving device.

[0223] S813. The sending device receives the second message from the receiving device.

[0224] S814. The transmitting device performs congestion control on the receiving device according to the second message.

[0225] In the embodiment shown in FIG8 , the first network device can be a network device directly connected to the transmitting device, and the second network device is a network device located between the first network device and the receiving device on the transmission path of the first message. The implementation process of S801 to S803 can refer to the third embodiment of the first device obtaining the first message in S201. The implementation process of S804 to S806 and the implementation process of S808 to S810 can refer to the implementation process of S202 to S204. The implementation process of S807 can refer to the second embodiment of the first device obtaining the first message in S201. The implementation process of S811 to S812 can refer to the implementation process of S501 to S501. The implementation process of S813 to S814 can refer to the implementation process of S205 to S206.

[0226] As an example, please refer to Figure 9, which shows a schematic diagram of another congestion control method provided by an embodiment of the present application. Figure 9 takes the congestion control method applied to the congestion control system shown in Figure 1, and takes the message sent by the sending end device not including congestion detection indication information and congestion information field, and the network device generates a first message including the congestion detection indication information and the congestion information field according to the message sent by the sending end device as an example. As shown in Figure 9, the original message sent by the sending end device 201 does not include an AECN header, and the network device 101 encapsulates the AECN header in the original message to obtain a first message, and the AECN header includes congestion detection indication information and congestion information field as an example (Figure 9 does not show the congestion detection indication information and the congestion information field in the AECN header for simplicity). The transmission path of the first message is: network device 101->network device 102->network device 103->receiving end device 202. During the process of transmitting a first message from network device 101 to receiving device 202, the devices along the transmission path update the congestion information field in the AECN header of the first message hop by hop (that is, update the congestion information in the congestion information field). After receiving device 202 receives the first message, receiving device 202 sends a second message to transmitting device 201 based on the first message. The second message includes at least one of the congestion information in the congestion information field and a congestion control instruction determined based on the congestion information. The second message is used to instruct transmitting device 201 to perform congestion control on receiving device 202. Transmitting device 201 adjusts the sending window, sending rate, etc. of messages sent by transmitting device 201 to receiving device 202 based on the second message to perform congestion control on receiving device 202.

[0227] The above is an introduction to the method embodiments of the present application. The following describes the device embodiments of the present application. The device of the present application can be used to perform the method of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments.

[0228] Please refer to Figure 10, which shows a schematic diagram of a congestion control device 1000 provided in an embodiment of the present application. Congestion control device 1000 is applied to a first device. For example, congestion control device 1000 is the first device or a functional component within the first device. Congestion control device 1000 can implement the congestion control method provided in the embodiments shown in Figures 2 or 4, or implement the steps performed by the transmitting device and the network device in the congestion control method provided in the embodiments shown in Figures 6 and 8. As shown in Figure 10, congestion control device 1000 includes: an acquisition module 1010, a detection module 1020, and an update module 1030.

[0229] Acquisition module 1010 is configured to acquire a first message, the first message including congestion detection indication information and a congestion information field. The congestion detection indication information is configured to instruct a device to acquire congestion information corresponding to the device, and the congestion information field is configured to carry the congestion information. For the functional implementation of acquisition module 1010, please refer to the relevant description in S201 above.

[0230] The detection module 1020 is configured to obtain congestion information corresponding to the first device according to the congestion detection indication information. For the functional implementation of the detection module 1020, please refer to the relevant description in S202 above.

[0231] The updating module 1030 is configured to update the congestion information field according to the congestion information corresponding to the first device. For the implementation of the function of the updating module 1030, please refer to the relevant description in S203 above.

[0232] Optionally, the congestion information includes at least one of first congestion information and second congestion information; the first congestion information includes at least one of the following: utilization of a queue in a device for caching the first message; utilization of an interface in the device for sending the first message; cumulative number of congestion hops on the transmission path of the first message; the second congestion information includes cumulative processing delay of the first message, which is the cumulative value of the processing delay of the first message in the device on the transmission path of the first message.

[0233] Optionally, the utilization of the interface includes at least one of the following: bandwidth utilization of the interface; and link utilization of the interface.

[0234] Optionally, the congestion detection indication information is used to instruct the device to obtain first congestion information corresponding to the device, and the congestion information field is used to carry the first congestion information; the detection module 1020 is used to obtain the first congestion information corresponding to the first device according to the congestion detection indication information; correspondingly, the update module 1030 is used to update the first congestion information in the congestion information field with the first congestion information corresponding to the first device when the relationship between the first congestion information corresponding to the first device and the first congestion information in the congestion information field meets a preset condition.

[0235] Optionally, the preset condition includes any one of the following: the value of the first congestion information corresponding to the first device is greater than the value of the first congestion information in the congestion information field; or the value of the first congestion information corresponding to the first device is less than or equal to the value of the first congestion information in the congestion information field.

[0236] Optionally, the congestion detection indication information is used to instruct the device to obtain second congestion information corresponding to the device, and the congestion information field is used to carry the second congestion information; the detection module 1020 is used to obtain the second congestion information corresponding to the first device according to the congestion detection indication information; correspondingly, the update module 1030 is used to update the second congestion information in the congestion information field using the second congestion information corresponding to the first device.

[0237] Optionally, the first message includes an AECN header, and the AECN header includes congestion detection indication information and the congestion information field.

[0238] Optionally, the first message includes an IPv6 extension header, and the AECN header is located in the IPv6 extension header.

[0239] Optionally, the first message includes an ICMP header, and the AECN header is located in the ICMP header.

[0240] Optionally, the first device is a sending device, and the acquisition module 1010 is configured to generate a first message.

[0241] Optionally, the first device is a network device, and the acquisition module 1010 is configured to receive a first message from a sending device.

[0242] Optionally, the first device is a network device, and the acquisition module 1010 is configured to: receive an original message from a sending device; and generate a first message according to the original message.

[0243] Optionally, the acquisition module 1010 is used to: construct a first message based on the original message; or, encapsulate the congestion detection indication information and the congestion information field in the original message to obtain the first message; or, copy the original message to obtain a copied message, and encapsulate the congestion detection indication information and the congestion information field in the copied message to obtain the first message.

[0244] Optionally, referring to FIG10 , the congestion control apparatus 1000 further includes a sending module 1040 configured to send the first message after the updating module 1030 updates the congestion information field according to the congestion information corresponding to the first device. For the functional implementation of the sending module 1040 , please refer to the relevant description in S204 above.

[0245] Optionally, the first device is a transmitting device. Continuing to refer to FIG. 10 , the congestion control apparatus 1000 further includes:

[0246] The receiving module 1050 is configured to receive a second message from the second device, where the second message corresponds to the first message. For the implementation of the functions of the sending module 1040, please refer to the relevant description in S205 above.

[0247] The control module 1060 is configured to perform congestion control on the receiving device of the first message according to the second message. For the functional implementation of the control module 1060, please refer to the relevant description in S206 above.

[0248] Optionally, the second message includes at least one of the following: congestion information in the congestion information field; and a congestion control instruction, wherein the congestion control instruction is determined according to the congestion information in the congestion information field.

[0249] Optionally, the second message is a detection message or a confirmation message of the transport layer.

[0250] Optionally, the first message is a service message, a detection message, or a copy of the service message.

[0251] Optionally, the second device is a receiving device or a network device.

[0252] In summary, the technical solution provided by the embodiment of the present application sets congestion detection indication information and a congestion information field in the first message, uses the congestion detection indication information to instruct the device to obtain the congestion information corresponding to the device, and uses the congestion information field to carry the congestion information, so that the devices along the first message obtain the congestion information corresponding to the device according to the congestion detection indication information, and update the congestion information field according to the congestion information corresponding to the device. The congestion information field can carry more congestion information, which helps the end-side device to perform accurate congestion control according to the congestion information carried by the congestion information field. In addition, in the technical solution provided by the embodiment of the present application, in the process of forwarding the first message by the device along the first message, the congestion information in the congestion information field in the first message is updated, rather than adding congestion information to the first message hop by hop. This can avoid the first message from increasing hop by hop, ensure the encapsulation efficiency of the first message, and can be applied to long-distance multi-hop transmission scenarios.

[0253] Please refer to Figure 11, which shows a schematic diagram of another congestion control device 1100 provided in an embodiment of the present application. Congestion control device 1100 is applied to a second device. For example, congestion control device 1100 is the second device or a functional component within the second device. The second device can implement the congestion control method provided in the embodiment shown in Figure 5, or implement the steps performed by the receiving device in the congestion control methods provided in the embodiments shown in Figures 6 and 8. As shown in Figure 11, congestion control device 1100 includes a receiving module 1110 and a sending module 1120.

[0254] Receiving module 1110 is configured to receive a first message, the first message including congestion detection indication information and a congestion information field. The congestion detection indication information is used to instruct a device to obtain congestion information corresponding to the device, and the congestion information field is used to carry the congestion information. For the functional implementation of receiving module 1110, please refer to the relevant description in S501 above.

[0255] The sending module 1120 is configured to send a second message to the sending end device according to the congestion information field, wherein the second message is used to instruct the sending end device to perform congestion control on the receiving end device of the first message. For the functional implementation of the sending module 1120, please refer to the relevant description in S502 above.

[0256] Optionally, the second message includes at least one of the following: congestion information in the congestion information field; and a congestion control instruction, wherein the congestion control instruction is determined according to the congestion information in the congestion information field.

[0257] Optionally, the congestion information includes at least one of first congestion information and second congestion information; the first congestion information includes at least one of the following: utilization of a queue in a device for caching the first message; utilization of an interface in the device for sending the first message; cumulative number of congestion hops on the transmission path of the first message; the second congestion information includes cumulative processing delay of the first message, which is the cumulative value of the processing delay of the first message in the device on the transmission path of the first message.

[0258] Optionally, the utilization of the interface includes at least one of the following: bandwidth utilization of the interface; and link utilization of the interface.

[0259] Optionally, the first message includes an AECN header, and the AECN header includes the congestion detection indication information and the congestion information field.

[0260] Optionally, the first message includes an IPv6 extension header, and the AECN header is located in the IPv6 extension header.

[0261] Optionally, the first message includes an ICMP header, and the AECN header is located in the ICMP header.

[0262] Optionally, the first message is a service message, a detection message, or a copy of the service message.

[0263] Optionally, the second message is a detection message or a confirmation message of the transport layer.

[0264] Optionally, the second device is a receiving device or a network device.

[0265] In summary, the technical solution provided by the embodiments of the present application includes congestion detection indication information and a congestion information field in a first message. The congestion detection indication information is used to instruct a device to obtain congestion information corresponding to the device, and the congestion information field is used to carry the congestion information. This allows devices along the path of the first message to obtain the congestion information corresponding to the device based on the congestion detection indication information and update the congestion information field based on the congestion information corresponding to the device. A second device then sends a second message to the sending device based on the congestion information field, and the sending device performs congestion control on the receiving device of the first message based on the second message. The congestion information field can carry a relatively large amount of congestion information, so the second message sent by the second device to the sending device based on the congestion information field can instruct the sending device to perform precise congestion control on the receiving device.

[0266] The congestion control device provided in the embodiments of the present application can also be implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD can be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof. The methods provided in the above method embodiments can also be implemented using software. When the methods provided in the above method embodiments are implemented using software, the various modules in the congestion control device can also be software modules.

[0267] An embodiment of the present application provides a congestion control device, comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program stored in the memory so that the congestion control device performs all or part of the steps of the congestion control method provided in the above embodiment.

[0268] As an example, please refer to Figure 12, which shows a schematic diagram of another congestion control device 1200 provided in an embodiment of the present application. The congestion control device 1200 is a network device or a functional component in a network device. The congestion control device 1200 is used to execute the steps performed by the network device in the congestion control method provided in the embodiment shown in Figure 2, Figure 4, Figure 6 or Figure 8. As shown in Figure 12, the congestion control device 1200 includes: a main control board 1210, an interface board 1230 and an interface board 1240. In the case of multiple interface boards, a switching network board (not shown in Figure 12) is also included, and the switching network board is used to complete data exchange between interface boards (interface boards are also called line cards or service boards).

[0269] The main control board 1210 is used to perform functions such as system management, device maintenance, and protocol processing. The interface boards 1230 and 1240 provide various service interfaces (e.g., POS, GE, and ATM) and implement message forwarding. The main control board 1210 primarily includes three functional units: a system management and control unit, a system clock unit, and a system maintenance unit. The main control board 1210, interface boards 1230, and interface boards 1240 are interconnected via a system bus and the system backplane. The interface board 1230 includes one or more processors 1231. Processors 1231 control and manage the interface board 1230 and communicate with the central processing unit 1212 on the main control board 1210. The memory 1232 on the interface board 1230 stores AECN-related configuration information. The interface board 1230 includes one or more network interfaces 1233 for receiving and sending messages. The specific implementation process is not detailed here. As shown in FIG12 , the main control board 1210 further includes a memory 1214 , which is used to store system management information, protocols, etc., which is not limited in this embodiment of the present application.

[0270] As shown in Figure 12, this embodiment includes multiple interface boards and employs a distributed forwarding mechanism. Under this mechanism, operations on interface board 1240 are substantially similar to those on interface board 1230. For example, interface board 1240 includes one or more network interfaces 1243 for receiving and sending messages, a memory 1242 for storing AECN-related configuration information, and a processor 1241 for controlling and managing interface board 1240 and communicating with the central processing unit 1212 on the main control board 1210. For the sake of brevity, detailed description of interface board 1240 is omitted here.

[0271] In FIG12 , the processor 1231 in interface board 1230 and / or the processor 1241 in interface board 1240 can be dedicated hardware or chips, such as a network processor or an application-specific integrated circuit, to implement the aforementioned functions. This implementation is commonly referred to as utilizing dedicated hardware or chips for forwarding plane processing. In other embodiments, the processor 1231 in interface board 1230 and / or the processor 1241 in interface board 1240 can also be a general-purpose processor, such as a central processing unit (CPU).

[0272] It should also be noted that there may be one or more main control boards, including a master and backup main control board. There may also be one or more interface boards. The higher the data processing capabilities of a network device, the more interface boards it provides. With multiple interface boards, they can communicate with each other through one or more switching fabric boards (SFMs), enabling load balancing and redundant backup. In a centralized forwarding architecture, network devices may not require SFMs; the interface boards handle service data processing for the entire system. In a distributed forwarding architecture, network devices include multiple interface boards, which can exchange data between them through SFMs, providing high-capacity data exchange and processing capabilities. Therefore, network devices with distributed architectures have greater data access and processing capabilities than those with centralized architectures. The specific architecture to adopt depends on the network deployment scenario and is not defined here.

[0273] In an optional embodiment, the memory 1232 and / or the memory 1242 is a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these. The memory 1232 can be independent and connected to the processor 1231 via a communication bus, or it can be integrated with the processor 1231. The memory 1242 can be independent and connected to the processor 1241 via a communication bus, or it can be integrated with the processor 1241.

[0274] The memory 1232 is used to store program code and is controlled by the processor 1231 to execute part or all of the steps of the method provided in the above embodiment. The processor 1231 is used to execute the program code stored in the memory 1232. The program code may include one or more software modules. These one or more software modules may be functional modules provided in the embodiment shown in Figure 10. The memory 1242 may also be used to store program code and is controlled by the processor 1241 to execute part or all of the steps of the method provided in the above embodiment. Similarly, the memory 1214 may also be used to store program code and is controlled by the central processing unit 1212 to execute part or all of the steps of the method provided in the above embodiment.

[0275] In an optional implementation, the network interface 1233 and the network interface 1243 may be devices using any transceiver type for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0276] As another example, please refer to Figure 13, which shows a schematic diagram of another congestion control device 1300 provided in an embodiment of the present application. The congestion control device 1300 can be an end-side device or a functional component in an end-side device, or it can be a network device or a functional component in a network device. The congestion control device 1300 can implement the congestion control method provided in any of the embodiments shown in Figures 2, 4 to 6, and 8. Referring to Figure 13, the congestion control device 1300 includes a processor 1302, a memory 1304, a communication interface 1306, and a bus 1308. The processor 1302, the memory 1304, and the communication interface 1306 are communicatively connected via the bus 1308. The processor 1302, the memory 1304, and the communication interface 1306 can also be connected in a connection manner other than the bus 1308. The embodiment of the present application does not limit the connection manner of the processor 1302, the memory 1304, and the communication interface 1306.

[0277] Memory 1304 is used to store computer program 13042, which includes instructions and data. Memory 1304 is various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), flash memory, optical storage, and registers.

[0278] The processor 1302 may be a general-purpose processor. A general-purpose processor is a processor that performs specific steps and / or operations by reading and executing a computer program stored in a memory (e.g., memory 1304). The general-purpose processor may use data stored in the memory (e.g., memory 1304) in the process of performing the above steps and / or operations. The stored computer program is executed, for example, to implement the related functions of the aforementioned acquisition module 1010, detection module 1020, update module 1030, control module 1060, etc. The general-purpose processor may be a central processing unit (CPU). The processor 1302 may also be a dedicated processor. A dedicated processor is a processor specially designed to perform specific steps and / or operations. The dedicated processor may be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), an NP, etc. The processor 1302 may also be a combination of multiple processors, such as a multi-core processor. The processor 1302 includes at least one circuit to perform all or part of the steps of the congestion control method provided in the above embodiment.

[0279] The communication interface 1306 includes input / output (I / O) interfaces, physical interfaces, and logical interfaces, which are used to interconnect devices within the congestion control device 1300, as well as interfaces used to interconnect the congestion control device 1300 with other devices (e.g., network devices and end-side devices). The physical interface can be a Gigabit Ethernet (GE) interface, which is used to interconnect the congestion control device 1300 with other devices. The logical interface is an interface within the congestion control device 1300, which is used to interconnect devices within the congestion control device 1300. It is easy to understand that the communication interface 1306 is used for communication between the congestion control device 1300 and other devices. For example, the communication interface 1306 is used to send and receive information, messages, etc. between the congestion control device 1300 and other devices. The communication interface 1306 can implement the related functions of the aforementioned receiving module and sending module.

[0280] The bus 1308 is any type of communication bus for interconnecting the processor 1302 , the memory 1304 , and the communication interface 1306 , such as a system bus.

[0281] The above-mentioned devices can be provided on separate chips, or at least partially or entirely on the same chip. Whether to provide each device independently on different chips or to integrate them on one or more chips often depends on the product design requirements. The embodiments of this application do not limit the specific implementation of the above-mentioned devices.

[0282] The congestion control device 1300 shown in FIG13 is merely exemplary. During implementation, the congestion control device 1300 may also include other components, which are not listed here. The congestion control device 1300 shown in FIG13 performs congestion control-related operations by executing all or part of the steps of the congestion control method provided in the above method embodiment.

[0283] The embodiment of the present application provides a congestion control system, including a first device and a second device. The first device includes the congestion control apparatus shown in FIG10 , FIG12 , or FIG13 , and the second device includes the congestion control apparatus shown in any one of FIG11 to FIG13 .

[0284] The first device is a sending device or a network device, and the second device is a receiving device or a network device.

[0285] For example, the congestion control system is shown in FIG1 , where the first device is a sending device 201 or any network device among the network devices 101 - 103 , and the second device is a receiving device 202 .

[0286] An embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed (for example, by an end-side device, a network device, one or more processors, etc.), it implements all or part of the steps of the congestion control method provided in the above method embodiment.

[0287] An embodiment of the present application provides a computer program product, which includes a program or code. When the program or code is executed (for example, by an end-side device, a network device, one or more processors, etc.), it implements all or part of the steps of the congestion control method provided in the above method embodiment.

[0288] An embodiment of the present application provides a chip, which includes a programmable logic circuit and / or program instructions. When the chip is running, it is used to implement all or part of the steps of the congestion control method provided in the above method embodiment.

[0289] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product, which includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium, or a semiconductor medium (e.g., a solid-state hard disk).

[0290] It should be understood that the term "at least one" in this application refers to one or more, and "a plurality of" refers to two or more. The term "and / or" in this application is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, for the sake of clarity of description, in this application, words such as "first", "second", and "third" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that words such as "first", "second", and "third" do not limit the quantity and execution order.

[0291] The different types of embodiments, such as the method embodiments and device embodiments provided in the embodiments of this application, can refer to each other, and the embodiments of this application are not limited thereto. The order of the operations of the method embodiments provided in the embodiments of this application can be appropriately adjusted, and the operations can be increased or decreased in response to the circumstances. Any person skilled in the art who can easily think of a method of variation within the technical scope disclosed in this application should be included in the scope of protection of this application, and therefore will not be described in detail.

[0292] In the corresponding embodiments provided in this application, it should be understood that the disclosed devices, etc. can be implemented through other configurations. For example, the device embodiments described above are merely illustrative. For example, the module division is merely a logical function division. In actual implementation, other division methods may be used, such as combining or integrating multiple modules or components into another system, or ignoring or not implementing certain features.

[0293] Modules described as separate components may or may not be physically separate, and components described as modules may or may not be physical modules. They may be located in one place or distributed across multiple devices. Some or all of these modules may be selected to achieve the purpose of this embodiment based on actual needs.

[0294] The above description is merely an exemplary embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included within the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A congestion control method, characterized in that: The method comprises: The first device obtains a first message, where the first message includes congestion detection indication information and a congestion information field, where the congestion detection indication information is used to instruct the device to obtain congestion information corresponding to the device, and the congestion information field is used to carry the congestion information; The first device obtains congestion information corresponding to the first device according to the congestion detection indication information; The first device updates the congestion information field according to congestion information corresponding to the first device.

2. The method according to claim 1, characterized in that The congestion information includes at least one of first congestion information and second congestion information; The first congestion information includes at least one of the following: a utilization rate of a queue in a device for caching the first message; a utilization rate of an interface in a device for sending the first message; The accumulated number of congested hops on the transmission path of the first message; The second congestion information includes a cumulative processing delay of the first message, where the cumulative processing delay is a cumulative value of a processing delay of the first message in a device on a transmission path of the first message.

3. The method according to claim 2, characterized in that The utilization of the interface includes at least one of the following: The bandwidth utilization of the interface; the link utilization of the interface.

4. The method according to claim 2 or 3, characterized in that: The congestion detection indication information is used to instruct a device to obtain first congestion information corresponding to the device, and the congestion information field is used to carry the first congestion information; The first device acquires congestion information corresponding to the first device according to the congestion detection indication information, including: the first device acquires first congestion information corresponding to the first device according to the congestion detection indication information; The first device updates the congestion information field according to the congestion information corresponding to the first device, including: when a relationship between the first congestion information corresponding to the first device and the first congestion information in the congestion information field meets a preset condition, the first device uses the first congestion information corresponding to the first device to update the first congestion information in the congestion information field.

5. The method according to claim 4, characterized in that The preset condition includes any one of the following: the value of the first congestion information corresponding to the first device is greater than the value of the first congestion information in the congestion information field; or the value of the first congestion information corresponding to the first device is less than or equal to the value of the first congestion information in the congestion information field.

6. The method according to claim 2 or 3, characterized in that: The congestion detection indication information is used to instruct a device to obtain second congestion information corresponding to the device, and the congestion information field is used to carry the second congestion information; The first device acquires congestion information corresponding to the first device according to the congestion detection indication information, including: the first device acquires second congestion information corresponding to the first device according to the congestion detection indication information; The first device updates the congestion information field according to the congestion information corresponding to the first device, including: the first device updates the second congestion information in the congestion information field using the second congestion information corresponding to the first device.

7. The method according to any one of claims 1 to 6, characterized in that: The first message includes an Enhanced Explicit Congestion Notification (AECN) header, and the AECN header includes the congestion detection indication information and the congestion information field.

8. The method according to claim 7, characterized in that The first message includes an Internet Protocol version 6 (IPv6) extension header, and the AECN header is located in the IPv6 extension header.

9. The method according to claim 7, characterized in that: The first message includes a network control message protocol ICMP header, and the AECN header is located in the ICMP header.

10. The method according to any one of claims 1 to 9, characterized in that: The first device is a sending end device, and the first device obtains a first message, including: the first device generates the first message.

11. The method according to any one of claims 1 to 9, characterized in that: The first device is a network device, and the first device obtains a first message, including: the first device receives the first message from a sending device.

12. The method according to any one of claims 1 to 9, characterized in that: The first device is a network device, and the first device obtains a first message, including: The first device receives an original message from a sending device; The first device generates the first message according to the original message.

13. The method according to claim 12, characterized in that The first device generates the first message according to the original message, including: The first device constructs the first message according to the original message; or, The first device encapsulates the congestion detection indication information and the congestion information field in the original message to obtain the first message; or, The first device copies the original message to obtain a copied message, and the first device encapsulates the congestion detection indication information and the congestion information field in the copied message to obtain the first message.

14. The method according to any one of claims 1 to 13, characterized in that: After the first device updates the congestion information field, the method further includes: the first device sending the first message.

15. The method according to any one of claims 1 to 14, characterized in that: The first device is a transmitting end device, and the method further includes: The first device receives a second message from a second device, where the second message corresponds to the first message; The first device performs congestion control on a receiving device of the first message according to the second message.

16. The method according to claim 15, characterized in that The second message includes at least one of the following: congestion information in the congestion information field; A congestion control instruction is determined according to the congestion information in the congestion information field.

17. The method according to claim 15 or 16, characterized in that The second message is a detection message or a confirmation message of the transport layer.

18. The method according to any one of claims 15 to 17, characterized in that: The second device is the receiving end device or a network device.

19. The method according to any one of claims 1 to 18, characterized in that: The first message is a service message, a detection message, or a copy of the service message.

20. A congestion control method, characterized in that: The method comprises: The second device receives a first message, where the first message includes congestion detection indication information and a congestion information field, where the congestion detection indication information is used to instruct the device to obtain congestion information corresponding to the device, and the congestion information field is used to carry the congestion information; The second device sends a second message to the sending end device according to the congestion information field, where the second message is used to instruct the sending end device to perform congestion control on the receiving end device of the first message.

21. The method according to claim 20, characterized in that The second message includes at least one of the following: congestion information in the congestion information field; A congestion control instruction is determined according to the congestion information in the congestion information field.

22. The method according to claim 20 or 21, characterized in that The congestion information includes at least one of first congestion information and second congestion information; The first congestion information includes at least one of the following: a utilization rate of a queue in a device for caching the first message; a utilization rate of an interface in a device for sending the first message; The accumulated number of congested hops on the transmission path of the first message; The second congestion information includes a cumulative processing delay of the first message, where the cumulative processing delay is a cumulative value of a processing delay of the first message in a device on a transmission path of the first message.

23. The method according to claim 22, characterized in that The utilization of the interface includes at least one of the following: The bandwidth utilization of the interface; the link utilization of the interface.

24. The method according to any one of claims 20 to 23, characterized in that: The first message includes an Enhanced Explicit Congestion Notification (AECN) header, and the AECN header includes the congestion detection indication information and the congestion information field.

25. The method according to claim 24, characterized in that The first message includes an Internet Protocol version 6 (IPv6) extension header, and the AECN header is located in the IPv6 extension header.

26. The method according to claim 24, characterized in that The first message includes a network control message protocol ICMP header, and the AECN header is located in the ICMP header.

27. The method according to any one of claims 20 to 26, characterized in that: The first message is a service message, a detection message, or a copy of the service message.

28. The method according to any one of claims 20 to 27, characterized in that: The second message is a detection message or a confirmation message of the transport layer.

29. The method according to any one of claims 20 to 28, characterized in that: The second device is the receiving end device or a network device.

30. A congestion control device, characterized in that: including memory and processor; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory so that the congestion control device executes the congestion control method according to any one of claims 1 to 19.

31. A congestion control device, characterized in that: including memory and processor; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory so that the congestion control device performs the congestion control method according to any one of claims 20 to 29.

32. A congestion control system, characterized in that: comprising a first device and a second device; The first device comprises the congestion control apparatus as claimed in claim 30; The second device comprises a congestion control apparatus as claimed in claim 31.

33. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the congestion control method according to any one of claims 1 to 29 is implemented.

34. A computer program product, characterized in that The computer program product comprises a program or a code, and when the program or the code is executed, the congestion control method according to any one of claims 1 to 29 is implemented.

Citation Information

Patent Citations

  • Congestion control method, device and system

    CN119011475A

  • Network congestion detection method and device

    CN112383450A

  • RoCE network congestion control method and related device

    CN114143827A

  • Flow sampling method, device and system, electronic equipment and medium

    CN115002009A

  • Selective congestion notification by a network interface device

    US20220210075A1

Cited By

  • Data forwarding method, intelligent computing center, node of intelligent computing center, medium and product

    CN120567753A

  • Data management and control method and apparatus, and device, storage medium and computer program product

    WO2026113255A1