Network parameter automatic updating method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a network parameter automatic updating method and device, electronic equipment and storage medium, which can be applied to the fields of communication technology and financial technology. The network parameter automatic updating method comprises: obtaining, by a network controller, a parameter initial value of a network device and used caches of the network device at each time within a preset time period; determining, according to the parameter initial value and the used caches, a first frequency at which the network device performs congestion adjustment on network traffic and a second frequency at which the network device performs suspension adjustment on the network traffic within the preset time period; and updating the parameter initial value according to a preset frequency threshold, the first frequency, the second frequency and an output rate of an output end of the network device to obtain an updated parameter value.

Description

Technical Field

[0001] This disclosure relates to the fields of communication technology and financial technology, and in particular to a method, apparatus, electronic device, storage medium and program product for automatic network parameter updating. Background Technology

[0002] RDMA networks are widely used in financial institution data centers due to their high bandwidth, low latency, and low CPU utilization. However, RDMA networks are highly sensitive to packet loss; even a small packet loss rate can cause a sharp decline in transmission performance.

[0003] To ensure stable transmission performance in RDMA networks, related technologies, assuming switches support PFC (Priority Flow Control) and ECN (Explicit Congestion Notification) technologies, address the issue of data packet loss in RDMA networks by setting the PFC and ECN thresholds in the switches to static empirical values.

[0004] In realizing the concept disclosed herein, the inventors discovered at least the following problems in the related technology: different business scenarios of financial institutions have different requirements for RDMA networks, and uniform experience values ​​cannot be adapted to all business scenarios. How to configure different network parameters for switches according to different business scenarios has become an urgent problem for financial institutions to solve. Summary of the Invention

[0005] In view of the above problems, this disclosure provides a method, apparatus, electronic device, storage medium and program product for automatically updating network parameters.

[0006] According to a first aspect of this disclosure, a method for automatically updating network parameters is provided, comprising:

[0007] The network controller is used to obtain the initial values ​​of the network device parameters and the used cache of the network device at various times within a preset time period;

[0008] Based on the initial parameter values ​​and the used cache, determine the first frequency of network device congestion regulation and the second frequency of network traffic pause regulation within a preset time period.

[0009] The initial parameter values ​​are updated based on the preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal to obtain the updated parameter values.

[0010] According to embodiments of this disclosure, the initial parameter values ​​include initial values ​​for a trigger threshold and a recovery threshold corresponding to congestion regulation, and initial values ​​for a backpressure threshold and a backpressure stop threshold corresponding to pause regulation. Based on the initial parameter values ​​and the used buffer, determining a first frequency for network device to perform congestion regulation on network traffic and a second frequency for pausing network traffic regulation within a preset time period includes:

[0011] Based on the used cache at each moment within a preset time period, M cache extreme points are obtained, where M is a positive integer greater than or equal to 1;

[0012] The first frequency is determined based on the M cache extreme points, the initial value of the trigger threshold, and the initial value of the back pressure stop threshold;

[0013] The second frequency is determined based on the M cache extreme points and the initial value of the backpressure threshold.

[0014] According to embodiments of this disclosure, the preset frequency threshold includes a first frequency threshold. The initial parameter value is updated based on the preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal to obtain the updated parameter value, which includes:

[0015] If the first frequency is greater than the first frequency threshold, the initial value of the trigger threshold is reduced according to the first preset rule to obtain the reduced trigger threshold value;

[0016] If the output rate at the output end of the network device remains stable within the first preset rate threshold, the initial value of the trigger threshold is updated according to the reduced trigger threshold value.

[0017] According to embodiments of this disclosure, updating the initial parameter values ​​based on a preset frequency threshold, a first frequency, a second frequency, and the output rate of the network device's output terminal to obtain updated parameter values ​​further includes:

[0018] If the first frequency is less than the first frequency threshold, the initial value of the trigger threshold is increased according to the second preset rule to obtain the increased trigger threshold value.

[0019] If, within a preset time period, the third frequency at which the network device adjusts network traffic congestion is less than the first frequency, the initial value of the trigger threshold is updated based on the increased trigger threshold value.

[0020] According to embodiments of this disclosure, the preset frequency threshold includes a second frequency threshold. The initial parameter value is updated based on the preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal to obtain the updated parameter value, which includes:

[0021] When the second frequency is less than the second frequency threshold, the initial value of the back pressure stop threshold is reduced according to the third preset rule to obtain the reduced back pressure stop threshold value;

[0022] If, within a preset time period, the fourth frequency at which the network device pauses and adjusts network traffic is less than the second frequency, the initial value of the back pressure stop threshold is updated based on the reduced back pressure stop threshold value.

[0023] According to embodiments of this disclosure, updating the initial parameter values ​​based on a preset frequency threshold, a first frequency, a second frequency, and the output rate of the network device's output terminal to obtain updated parameter values ​​further includes:

[0024] When the second frequency is greater than the second frequency threshold, the network controller is used to obtain packet loss information of the network device.

[0025] If packet loss is determined to occur in the network device based on the packet loss information, the initial value of the remaining buffer is increased according to the fourth preset rule to obtain the increased value of the remaining buffer. The initial value of the remaining buffer is the initial value of the parameter corresponding to the pause adjustment.

[0026] If it is determined that the network device will not lose packets within a preset time period, the initial value of the remaining cache is updated based on the increased remaining cache value.

[0027] According to embodiments of this disclosure, updating the initial parameter values ​​based on a preset frequency threshold, a first frequency, a second frequency, and the output rate of the network device's output terminal to obtain updated parameter values ​​further includes:

[0028] If, based on the packet loss information, it is determined that there is no packet loss in the network device, the initial value of the back pressure threshold is increased according to the fifth preset rule to obtain the increased back pressure threshold value. The initial value of the back pressure threshold is the parameter initial value corresponding to the pause adjustment.

[0029] If the output rate at the output end of the network device remains stable within the second preset rate threshold, the initial value of the back pressure threshold is updated according to the increased back pressure threshold value.

[0030] According to embodiments of this disclosure, updating the initial parameter values ​​based on a preset frequency threshold, a first frequency, a second frequency, and the output rate of the network device's output terminal to obtain updated parameter values ​​further includes:

[0031] If the output rate at the output end of the network device cannot remain stable within the second preset rate threshold, the initial value of the recovery threshold is reduced according to the sixth preset rule and the initial value of the labeling probability is increased according to the seventh preset rule, so as to obtain the reduced recovery threshold value and the increased labeling probability value. The initial value of the recovery threshold and the initial value of the labeling probability are both parameter initial values ​​corresponding to congestion regulation.

[0032] When the output rate at the output end of the network device remains stable within the third preset rate threshold, the initial value of the recovery threshold is updated according to the reduced recovery threshold value and the initial value of the marking probability is updated according to the increased marking probability value.

[0033] A second aspect of this disclosure provides a network parameter automatic update device, comprising:

[0034] The acquisition module is used to acquire the initial values ​​of the network device parameters and the used cache of the network device at various times within a preset time period using the network controller;

[0035] The determination module is used to determine, based on the initial values ​​of the parameters and the used cache, the first frequency of network device congestion regulation and the second frequency of network traffic pause regulation within a preset time period.

[0036] The module is used to update the initial values ​​of parameters based on a preset frequency threshold, a first frequency, a second frequency, and the output rate of the network device's output terminal, thereby obtaining the updated parameter values.

[0037] A third aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the methods described above.

[0038] A fourth aspect of this disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the methods described above.

[0039] The fifth aspect of this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0040] According to the automatic network parameter update method provided in this disclosure embodiment, for a predetermined service scenario, the method utilizes the network controller to obtain the initial parameter values ​​of the network device corresponding to the predetermined service scenario and the used cache of the network device at various times within a preset time period; based on the initial parameter values ​​and the used cache, it determines a first frequency for the network device to perform congestion regulation on network traffic and a second frequency for pausing network traffic regulation within the preset time period; and updates the initial parameter values ​​based on a preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal to obtain updated parameter values. This method enables timely determination of the network congestion state based solely on the preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal, and then automatically determines network parameter values ​​suitable for the predetermined service scenario based on the network congestion state, thereby improving the efficiency and accuracy of configuring network parameters related to the predetermined service scenario. Attached Figure Description

[0041] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0042] Figure 1 This diagram illustrates an application scenario of the automatic network parameter update method according to an embodiment of the present disclosure.

[0043] Figure 2 A flowchart illustrating an automatic network parameter update method according to an embodiment of the present disclosure is shown schematically.

[0044] Figure 3 A flowchart illustrating an automatic network parameter update method according to another embodiment of the present disclosure is shown schematically.

[0045] Figure 4 A flowchart illustrating an automatic network parameter update method according to another embodiment of the present disclosure is shown schematically.

[0046] Figure 5 This schematic diagram illustrates a structural block diagram of an automatic network parameter update apparatus according to an embodiment of the present disclosure;

[0047] Figure 6 A block diagram schematically illustrates an electronic device suitable for implementing an automatic network parameter update method according to an embodiment of the present disclosure. Detailed Implementation

[0048] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0049] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0050] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0051] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0052] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure, and application of data (including but not limited to user personal information) comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and they do not violate public order and good morals.

[0053] According to embodiments of this disclosure, PFC technology is typically used for flow control. When it is determined that the switch is congested based on the PFC threshold parameter in the PFC technology, the switch will send a PAUSE frame to the upstream device to briefly block the upstream device from sending data packets.

[0054] According to embodiments of this disclosure, ECN technology is typically used for congestion control. When congestion is determined to occur in a switch based on the ECN threshold parameters in the ECN technology, the switch can mark data packets at its egress end with ECN according to the marking probability. When the receiver receives a packet with an ECN mark, the receiver can send a control message back to the source end that sent the data packet to adjust the rate at which the source end sends data packets. The marking probability increases linearly with the length of the switch's queue. The maximum value of the marking probability can be defined based on the maximum value in the ECN threshold parameters, and the starting value of the marking probability can be defined based on the minimum value in the ECN threshold parameters.

[0055] According to embodiments of this disclosure, ECN technology can dynamically adjust the transmission rate of data packets sent from the source end based on the congestion level of the switch, while PFC technology can cause the upstream device of the switch to suspend the transmission of data packets based on the congestion level of the switch. Therefore, when designing the network parameters of the switch, the effective time of the PFC threshold parameter is usually made later than that of the ECN threshold parameter to ensure that the RDMA network has a high throughput with no packet loss and low latency.

[0056] Related technologies address data packet loss issues in RDMA networks by setting PFC and ECN thresholds in switches to static empirical values. However, different business scenarios within financial institutions have varying requirements for RDMA networks, and uniform empirical values ​​cannot be adapted to all business scenarios.

[0057] Financial institutions' data center business scenarios are complex. Configuring different PFC threshold parameters and ECN parameters for switches for different business scenarios presents the following challenges: 1) Setting the switch's PFC threshold parameter too low will trigger PFC flow control prematurely, leading to a decrease in RDMA network throughput and thus reducing RDMA network bandwidth utilization; 2) Setting the switch's PFC threshold parameter too high will prevent timely flow control, easily causing data packet loss; 3) Setting the switch's ECN threshold parameter too high will give the RDMA network a strong ability to absorb burst traffic, which is beneficial to throughput, but will also bring excessive latency, which is detrimental to latency-sensitive services; 4) Setting the switch's ECN threshold parameter too low will result in lower latency in the RDMA network, which is beneficial to latency-sensitive service flows, but the RDMA network's ability to absorb burst traffic is weak, which is detrimental to throughput-sensitive services.

[0058] Given the numerous challenges in configuring different PFC threshold parameters and ECN parameters for switches to suit different business scenarios, how to configure different network parameters for switches according to different business scenarios has become an urgent problem for financial institutions.

[0059] In order to at least partially solve the technical problems existing in the related technologies, embodiments of this disclosure provide a method for automatic network parameter updating, which can be applied to the fields of communication technology and financial technology.

[0060] The embodiments of this disclosure provide a method for automatically updating network parameters, including: using a network controller to obtain initial parameter values ​​of a network device and the used cache of the network device at various times within a preset time period; determining, based on the initial parameter values ​​and the used cache, a first frequency for the network device to perform congestion regulation on network traffic and a second frequency for pausing network traffic regulation within the preset time period; and updating the initial parameter values ​​based on a preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal to obtain updated parameter values.

[0061] Figure 1 The diagram illustrates an application scenario of the automatic network parameter update method according to an embodiment of the present disclosure.

[0062] like Figure 1 As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0063] Users can interact with server 105 via network 104 using at least one of the first terminal device 101, second terminal device 102, and third terminal device 103 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, second terminal device 102, and third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0064] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0065] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0066] It should be noted that the automatic network parameter update method provided in this disclosure embodiment can generally be executed by server 105. Correspondingly, the automatic network parameter update device provided in this disclosure embodiment can generally be located in server 105. The automatic network parameter update method provided in this disclosure embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the automatic network parameter update device provided in this disclosure embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0067] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0068] The following will be based on Figure 1 The described scene, through Figures 2-4 The method for automatically updating network parameters according to the disclosed embodiments will be described in detail.

[0069] Figure 2 A flowchart illustrating an automatic network parameter update method according to an embodiment of the present disclosure is shown.

[0070] like Figure 2 As shown, the automatic network parameter update method of this embodiment includes operations S210 to S230.

[0071] In operation S210, the network controller is used to obtain the initial values ​​of the network device parameters and the used cache of the network device at various times within a preset time period.

[0072] According to embodiments of this disclosure, a network device represents a relay device that can forward data packets sent by a source device to a receiving device. The network device can be a relay device supporting PFC and ECN technologies. For example, the network device can be a switch supporting PFC and ECN technologies.

[0073] According to embodiments of this disclosure, both the source device and the receiving device communicating with a network device, such as a switch, can be configured with an RDMA network interface card (NIC). The source device, network device, and destination device can communicate based on the RoCE (RDMA over Converged Ethernet) network protocol.

[0074] According to embodiments of this disclosure, the parameters of a network device characterize parameters that can control the traffic of the network device. These network device parameters can be used to improve the congestion control efficiency of an RDMA network.

[0075] According to embodiments of this disclosure, when the network device is a switch that supports PFC and ECN technologies, the initial values ​​of the switch parameters can be, for example, the initial values ​​of the PFC threshold parameters corresponding to PFC technology and the initial values ​​of the ECN threshold parameters corresponding to ECN technology.

[0076] According to embodiments of this disclosure, a network controller represents a server or server cluster capable of real-time monitoring of the network status and network parameters of network devices. Information corresponding to the network status may include the network device's used cache, input rate at the input end, and output rate at the output end, etc.

[0077] According to embodiments of this disclosure, a network controller can send message requests related to the network status and network parameters of a network device, such as a switch, at a preset frequency in order to obtain the real-time network status and network parameters of the network device.

[0078] According to embodiments of this disclosure, network devices, such as switches, can also automatically send the real-time network status and network parameters of the network devices to the network controller at a preset frequency, so that the network controller can obtain the real-time network status and network parameters of the network devices.

[0079] According to embodiments of this disclosure, the preset time period can be selected based on actual business conditions. Embodiments of this disclosure do not limit the preset time period; for example, it can be 1 second, 2 seconds, 3 seconds, 5 seconds, or 10 seconds. The preset frequency can be, for example, once every 5 milliseconds, once every 10 milliseconds, once every 15 milliseconds, once every 20 milliseconds, or once every second.

[0080] In operation S220, based on the initial parameter values ​​and the used cache, the first frequency for the network device to perform congestion regulation on network traffic and the second frequency for pausing network traffic regulation are determined within a preset time period.

[0081] According to embodiments of this disclosure, congestion regulation represents traffic adjustment achieved by suspending the transmission of data packets by upstream devices of a network device based on the congestion status of the network device. Congestion regulation can be, for example, PFC regulation corresponding to PFC technology.

[0082] According to embodiments of this disclosure, pause adjustment represents traffic regulation achieved by adjusting the rate at which the source sends data packets based on the congestion status of network devices. Pause adjustment can be, for example, ECN adjustment corresponding to ECN technology.

[0083] According to embodiments of this disclosure, for example, it can be determined that the network device has performed congestion regulation on network traffic when the used cache is greater than the initial value of the parameter corresponding to congestion regulation, and it can be determined that the network device has suspended regulation on network traffic when the used cache is greater than the initial value of the parameter corresponding to pausing regulation.

[0084] In operation S230, the initial values ​​of the parameters are updated based on the preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal, resulting in updated parameter values.

[0085] According to embodiments of this disclosure, the preset frequency threshold can be selected based on actual business conditions, and the embodiments of this disclosure do not limit the preset frequency threshold. For example, the preset frequency threshold can be 4 times per second, 5 times per second, or 6 times per second, etc.

[0086] According to embodiments of this disclosure, the output rate of a network device can be obtained in real time using a network controller. After obtaining updated parameter values, the network controller can configure the network parameters of the network device based on these updated values.

[0087] According to embodiments of this disclosure, the output rate of the network device's output terminal characterizes the actual output rate of the network device's output terminal at each moment.

[0088] According to embodiments of this disclosure, for example, when the first frequency is greater than a preset frequency threshold corresponding to the first frequency, the initial value of the parameter corresponding to congestion regulation can be adjusted. When the output rate at the network device's output end is stable, the final parameter value corresponding to congestion regulation is determined, and the initial parameter value is updated based on the final parameter value corresponding to congestion regulation. Similarly, the parameter corresponding to pause regulation can be updated based on the second frequency, the preset frequency threshold corresponding to the second frequency, and the output rate of the network device.

[0089] According to the automatic network parameter update method provided in this disclosure embodiment, for a predetermined service scenario, the method utilizes the network controller to obtain the initial parameter values ​​of the network device corresponding to the predetermined service scenario and the used cache of the network device at various times within a preset time period; based on the initial parameter values ​​and the used cache, it determines a first frequency for the network device to perform congestion regulation on network traffic and a second frequency for pausing network traffic regulation within the preset time period; and updates the initial parameter values ​​based on a preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal to obtain updated parameter values. This method enables timely determination of the network congestion state based solely on the preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal, and then automatically determines network parameter values ​​suitable for the predetermined service scenario based on the network congestion state, thereby improving the efficiency and accuracy of configuring network parameters related to the predetermined service scenario.

[0090] According to embodiments of this disclosure, when the network device is a switch supporting PFC and ECN technologies and the network is RDMA, the automatic network parameter update method provided in this disclosure can determine the congestion state of the RDMA network based on a preset frequency threshold, a first frequency, a second frequency, and the output rate of the switch's output terminal. Then, based on the congestion state of the RDMA network, it can automatically determine network parameter values ​​suitable for a predetermined service scenario, thereby improving the efficiency and accuracy of configuring RDMA network parameters related to the predetermined service scenario.

[0091] According to embodiments of this disclosure, there can be multiple network devices. The network controller can be used to obtain the initial parameter values ​​of multiple network devices and the used cache of each network device at various times within a preset time period. This enables unified management of the network status and network parameters of multiple network devices by the network controller, further accelerating the efficiency of managing the network status of network devices.

[0092] According to embodiments of this disclosure, when there are multiple network devices, the network controller can obtain the initial parameter values ​​of multiple network devices and the used cache of each network device at various times within a preset time period. Then, for each of the multiple network devices, the network parameters of the network device are automatically updated according to the automatic network parameter update method provided in the embodiments of this disclosure, thereby realizing batch management of the network parameters of the network devices and further improving the efficiency of automatically updating the network parameters of the network devices.

[0093] According to embodiments of this disclosure, the initial parameter values ​​include initial values ​​for a trigger threshold and a recovery threshold corresponding to congestion regulation, and initial values ​​for a backpressure threshold and a backpressure stop threshold corresponding to pause regulation. Based on the initial parameter values ​​and the used buffer, determining a first frequency for network device to perform congestion regulation on network traffic and a second frequency for pausing network traffic regulation within a preset time period includes:

[0094] Based on the used cache at each moment within a preset time period, M cache extreme points are obtained, where M is a positive integer greater than or equal to 1;

[0095] The first frequency is determined based on the M cache extreme points, the initial value of the trigger threshold, and the initial value of the back pressure stop threshold;

[0096] The second frequency is determined based on the M cache extreme points and the initial value of the backpressure threshold.

[0097] According to embodiments of this disclosure, when congestion regulation is ECN regulation, the initial value of the trigger threshold corresponding to congestion regulation can be the initial value of the trigger threshold kmin in ECN regulation, and the initial value of the recovery threshold corresponding to congestion regulation can be the initial value of the recovery threshold kma in ECN regulation.

[0098] According to embodiments of this disclosure, the trigger threshold kmin in ECN regulation is the minimum value among the ECN threshold parameters, and the initial value of the recovery threshold kmax in ECN regulation is the maximum value among the ECN threshold parameters.

[0099] According to embodiments of this disclosure, during ECN adjustment of a network device switch, if the used buffer of the network device switch is less than the trigger threshold kmin, the data packets output by the network device switch will not be marked with ECN; if the used buffer of the network device switch is greater than the recovery threshold kma, the data packets output by the switch will be marked with ECN with the maximum marking probability; if the used buffer of the network device switch is between the trigger threshold kmin and the recovery threshold kma, the data packets output by the switch will be marked with ECN according to the marking probability. The marking probability, between the trigger threshold kmin and the recovery threshold kma, increases linearly with the increase of the used buffer of the switch.

[0100] According to embodiments of this disclosure, when the pause adjustment is PFC adjustment, the initial value of the back pressure threshold corresponding to the pause adjustment can be the initial value of the back pressure threshold pfcxoff in PFC adjustment, and the initial value of the back pressure stop threshold corresponding to the pause adjustment can be the initial value of the back pressure stop threshold pfcxon in PFC adjustment.

[0101] According to embodiments of this disclosure, during PFC adjustment of a network device switch, if the used buffer of the network device switch is greater than the backpressure threshold pfcxoff, the network device switch will send a PAUSE frame to the upstream device to briefly block the upstream device from sending data packets; if the used buffer of the network device switch is less than the backpressure stop threshold pfcxon, the network device switch will stop sending PAUSE frames to the upstream device and resume the upstream device from sending data packets to the network device switch.

[0102] According to embodiments of this disclosure, when a cached extreme point is greater than the initial value of the trigger threshold kmin and less than the initial value of the backpressure stop threshold pfcxon, it can be determined that the network device has performed ECN regulation on network traffic. Therefore, after obtaining the number of M cached extreme points between the initial values ​​of the trigger threshold kmin and the initial values ​​of the backpressure stop threshold pfcxon, a first frequency can be determined based on this number and a preset time period.

[0103] According to embodiments of this disclosure, when the cache extreme point is greater than the initial value of the backpressure threshold pfcxoff, it can be determined that the network device has performed PFC regulation on network traffic. Therefore, after obtaining the number of M cache extreme points where the cache extreme points are greater than the backpressure threshold pfcxoff, a second frequency can be determined based on this number and a preset time period.

[0104] According to embodiments of this disclosure, M cache extreme points are obtained based on the used cache at various times within a preset time period. A first frequency is determined based on these M cache extreme points, the initial value of the trigger threshold, and the initial value of the backpressure stop threshold. This enables rapid determination of the frequency at which the network device performs congestion regulation (ECN) within the preset time period, allowing for timely detection of congestion at the network device's output ports. A second frequency is then determined based on these M cache extreme points and the initial value of the backpressure threshold. This enables rapid determination of the frequency at which the network device performs pause regulation (PFC) within the preset time period, allowing for timely detection of blockage at the network device's input ports. This allows for timely adjustment of network parameters based on the first and second frequencies, resulting in rapid recovery and stability of network traffic and improved efficiency in adjusting network parameters.

[0105] According to embodiments of this disclosure, the preset frequency threshold includes a first frequency threshold. The initial parameter value is updated based on the preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal to obtain the updated parameter value, which includes:

[0106] If the first frequency is greater than the first frequency threshold, the initial value of the trigger threshold is reduced according to the first preset rule to obtain the reduced trigger threshold value;

[0107] If the output rate at the output end of the network device remains stable within the first preset rate threshold, the initial value of the trigger threshold is updated according to the reduced trigger threshold value.

[0108] According to embodiments of this disclosure, the first frequency threshold can be selected based on actual business conditions, and embodiments of this disclosure do not limit the first frequency threshold. For example, the first frequency threshold can be 4 times per second, 5 times per second, or 6 times per second, etc.

[0109] According to embodiments of this disclosure, the first preset rule may be, for example, a linearly decreasing adjustment of the trigger threshold kmin based on an initial value of kmin. For example, after each feedback adjustment cycle, the initial value of the trigger threshold kmin may be subtracted by a preset value equal to the number of feedback cycles. The preset value may be, for example, 1, 2, 5, or 10.

[0110] According to embodiments of this disclosure, the first preset rate threshold can be selected based on actual service conditions, and embodiments of this disclosure do not limit the first preset rate threshold. When the network device is a gigabit switch, the first preset rate threshold can be, for example, 5MB, 10MB, 20MB, or 30MB, etc.

[0111] According to embodiments of this disclosure, the stable output rate of the output terminal of the network device within a first preset rate threshold indicates that the difference between the output rates within a preset time period is within the first preset rate threshold.

[0112] According to embodiments of this disclosure, if the output rate remains stable within a first preset rate threshold during the nth preset time period from the current time, the reduced trigger threshold value is considered to have reached its optimal value, and the initial trigger threshold value is updated based on the reduced trigger threshold value. n can be, for example, 3, 4, or 6.

[0113] According to embodiments of this disclosure, when the first frequency is greater than a first frequency threshold, the initial value of the trigger threshold is reduced according to a first preset rule to obtain a reduced trigger threshold value. When the output rate at the output end of the network device remains stable within a first preset rate threshold, the initial value of the trigger threshold is updated according to the reduced trigger threshold value. This can achieve earlier triggering of congestion regulation (ECN) by reducing the initial value of the trigger threshold, enabling network devices such as switches to control network traffic in a timely manner and ensuring that the output rate at the output end of the network device remains stable.

[0114] According to embodiments of this disclosure, updating the initial parameter values ​​based on a preset frequency threshold, a first frequency, a second frequency, and the output rate of the network device's output terminal to obtain updated parameter values ​​further includes:

[0115] If the first frequency is less than the first frequency threshold, the initial value of the trigger threshold is increased according to the second preset rule to obtain the increased trigger threshold value.

[0116] If, within a preset time period, the third frequency at which the network device adjusts network traffic congestion is less than the first frequency, the initial value of the trigger threshold is updated based on the increased trigger threshold value.

[0117] According to embodiments of this disclosure, the second preset rule can, for example, adjust the trigger threshold kmin linearly based on the initial value of the trigger threshold kmin. For example, after each feedback adjustment cycle, the initial value of the trigger threshold kmin can be increased by a preset value equal to the number of feedback cycles. The preset value can be, for example, 1, 2, 5, or 10.

[0118] According to embodiments of this disclosure, the third frequency represents the frequency at which network devices, such as switches, perform congestion regulation on network traffic based on an increased trigger threshold value within a preset time period.

[0119] According to embodiments of this disclosure, a third frequency at which the network device performs congestion regulation on network traffic within a preset time period is less than the first frequency indicates that, within the nth preset time period from the current time, the third frequency at which the network device performs congestion regulation on network traffic based on an increased trigger threshold value is less than the first frequency. n can be, for example, 3, 4, or 6.

[0120] According to embodiments of this disclosure, when the first frequency is less than the first frequency threshold, the initial value of the trigger threshold is increased according to the second preset rule to obtain the increased trigger threshold value. When the third frequency at which the network device performs congestion regulation on network traffic is less than the first frequency within a preset time period, the initial value of the trigger threshold is updated according to the increased trigger threshold value. By increasing the initial value of the trigger threshold, the output efficiency of the network device can be increased while ensuring that the output rate of the network device remains stable, thereby improving the throughput of the RDMA network.

[0121] According to embodiments of this disclosure, the preset frequency threshold includes a second frequency threshold. The initial parameter value is updated based on the preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal to obtain the updated parameter value, which includes:

[0122] When the second frequency is less than the second frequency threshold, the initial value of the back pressure stop threshold is reduced according to the third preset rule to obtain the reduced back pressure stop threshold value.

[0123] If, within a preset time period, the fourth frequency at which the network device pauses and adjusts network traffic is less than the second frequency, the initial value of the back pressure stop threshold is updated based on the reduced back pressure stop threshold value.

[0124] According to embodiments of this disclosure, the second frequency threshold can be selected based on actual business conditions, and embodiments of this disclosure do not limit the second frequency threshold. For example, the second frequency threshold can be 3 times per second, 4 times per second, or 5 times per second, etc.

[0125] According to embodiments of this disclosure, the third preset rule can be, for example, a linearly decreasing adjustment of the back pressure stop threshold pfcxon based on the initial value of the back pressure stop threshold pfcxon. For example, after each feedback adjustment cycle, the initial value of the back pressure stop threshold pfcxon can be subtracted by the number of preset values ​​for the feedback cycle, such as 1, 2, 5, or 10.

[0126] According to embodiments of this disclosure, the fourth frequency represents the frequency at which network devices, such as switches, suspend and adjust network traffic based on a reduced backpressure stop threshold value within a preset time period.

[0127] According to embodiments of this disclosure, the fourth frequency at which the network device pauses and adjusts network traffic within a preset time period is less than the second frequency indicates that within the nth preset time period from the current time, the fourth frequency at which the network device pauses and adjusts network traffic according to the reduced back pressure stop threshold is less than the second frequency.

[0128] According to embodiments of this disclosure, when the second frequency is less than the second frequency threshold, it indicates that the input end of the network device has been blocked. Therefore, when the second frequency is less than the second frequency threshold, the initial value of the backpressure stop threshold is reduced according to the third preset rule to obtain the reduced backpressure stop threshold value. When the fourth frequency during which the network device pauses and adjusts network traffic is less than the second frequency within a preset time period, the initial value of the backpressure stop threshold is updated according to the reduced backpressure stop threshold value. This enables earlier triggering of pause adjustment and PFC adjustment, allowing the network device, such as a switch, to control the traffic at the input end in a timely manner and ensure that the input rate at the network device input end remains stable.

[0129] According to embodiments of this disclosure, updating the initial parameter values ​​based on a preset frequency threshold, a first frequency, a second frequency, and the output rate of the network device's output terminal to obtain updated parameter values ​​further includes:

[0130] When the second frequency is greater than the second frequency threshold, the network controller is used to obtain packet loss information of the network device.

[0131] If packet loss is determined to occur in the network device based on the packet loss information, the initial value of the remaining buffer is increased according to the fourth preset rule to obtain the increased value of the remaining buffer. The initial value of the remaining buffer is the initial value of the parameter corresponding to the pause adjustment.

[0132] If it is determined that the network device will not lose packets within a preset time period, the initial value of the remaining cache is updated based on the increased remaining cache value.

[0133] According to embodiments of this disclosure, the remaining cache represents the cache that can still be used in the network device from the time the network device performs PFC regulation until the upstream device responds with a rate reduction.

[0134] According to embodiments of this disclosure, when the network device is a switch supporting PFC and ECN technologies, the remaining buffer can be, for example, the switch's remaining buffer headroom. According to embodiments of this disclosure, the remaining buffer headroom can be used to ensure that the switch does not lose packets during the period when PFC regulation is in effect.

[0135] According to embodiments of this disclosure, the fourth preset rule may be, for example, to linearly increase the remaining headroom based on the initial value of the remaining headroom. For example, after each feedback adjustment cycle, the initial value of the remaining headroom may be subtracted by the number of preset values ​​for the number of feedback cycles, such as 1, 2, 5, or 10.

[0136] According to embodiments of this disclosure, when the second frequency is greater than the second frequency threshold, the network controller obtains packet loss information of the network device. If packet loss is determined based on the packet loss information, it indicates that the remaining buffer cannot guarantee that the network device, such as the switch, will not lose packets during the effective period of PFC adjustment. Therefore, the initial value of the remaining buffer is increased according to the fourth preset rule to obtain the increased remaining buffer value. If it is determined that the network device will not lose packets within the preset time period, the initial value of the remaining buffer is updated according to the increased remaining buffer value. This achieves timely adjustment of the remaining buffer, ensuring that the network device, such as the switch, will not lose packets during the effective period of PFC adjustment, thus ensuring stable network traffic and network performance.

[0137] According to embodiments of this disclosure, updating the initial parameter values ​​based on a preset frequency threshold, a first frequency, a second frequency, and the output rate of the network device's output terminal to obtain updated parameter values ​​further includes:

[0138] If, based on the packet loss information, it is determined that there is no packet loss in the network device, the initial value of the back pressure threshold is increased according to the fifth preset rule to obtain the increased back pressure threshold value. The initial value of the back pressure threshold is the parameter initial value corresponding to the pause adjustment.

[0139] If the output rate at the output end of the network device remains stable within the second preset rate threshold, the initial value of the back pressure threshold is updated according to the increased back pressure threshold value.

[0140] According to embodiments of this disclosure, the fifth preset rule can be, for example, a linearly increasing adjustment of the back pressure threshold pfcxoff based on the initial value of the back pressure threshold pfcxoff. For example, after each feedback adjustment cycle, the initial value of the back pressure threshold pfcxoff can be increased by a preset value equal to the number of feedback cycles. The preset value can be, for example, 1, 2, 5, or 10.

[0141] According to embodiments of this disclosure, the second preset rate threshold can be selected based on actual service conditions, and embodiments of this disclosure do not limit the second preset rate threshold. When the network device is a gigabit switch, the second preset rate threshold can be, for example, 5MB, 10MB, 20MB, or 30MB, etc.

[0142] According to embodiments of this disclosure, the stable output rate of the network device's output end within a second preset rate threshold indicates that the difference between the output rates within a preset time period is within the first preset rate threshold.

[0143] According to embodiments of this disclosure, if the output rate remains stable within a second preset rate threshold during the nth preset time period from the current time, the increased back pressure threshold value is considered to have reached its optimal value, and the initial value of the back pressure threshold is updated based on the increased back pressure threshold value. n can be, for example, 3, 4, or 6.

[0144] According to the embodiments of this disclosure, when it is determined that there is no packet loss in the network device based on packet loss information, the initial value of the backpressure threshold is increased according to the fifth preset rule to obtain the increased backpressure threshold value. When the output rate of the network device's output end remains stable within the second preset rate threshold, the initial value of the backpressure threshold is updated according to the increased backpressure threshold value. By increasing the backpressure threshold value, the output efficiency of the network device's output end can be increased while maintaining network stability and preventing packet loss, thereby improving the throughput of the RDMA network.

[0145] According to embodiments of this disclosure, updating the initial parameter values ​​based on a preset frequency threshold, a first frequency, a second frequency, and the output rate of the network device's output terminal to obtain updated parameter values ​​further includes:

[0146] If the output rate at the output end of the network device cannot remain stable within the second preset rate threshold, the initial value of the recovery threshold is reduced according to the sixth preset rule and the initial value of the labeling probability is increased according to the seventh preset rule, so as to obtain the reduced recovery threshold value and the increased labeling probability value. The initial value of the recovery threshold and the initial value of the labeling probability are both parameter initial values ​​corresponding to congestion regulation.

[0147] When the output rate at the output end of the network device remains stable within the third preset rate threshold, the initial value of the recovery threshold is updated according to the reduced recovery threshold value and the initial value of the marking probability is updated according to the increased marking probability value.

[0148] According to embodiments of this disclosure, the initial value of the labeling probability can be, for example, the initial value of the maximum labeling probability P in ECN regulation. The initial value of the recovery threshold can be, for example, the initial value of the recovery threshold pfcxon in ECN regulation.

[0149] According to embodiments of this disclosure, since the marking probability in ECN regulation increases linearly with the increase of the switch's used buffer between the trigger threshold kmin and the recovery threshold kma, increasing the maximum marking probability P in ECN regulation will correspondingly increase other marking probabilities. Increasing the marking probability will increase the control over the traffic at the output ports of network devices.

[0150] According to embodiments of this disclosure, the sixth preset rule may be, for example, a linearly decreasing adjustment of the recovery threshold pfcxon based on the initial value of the recovery threshold pfcxon. For example, after each feedback adjustment cycle, the initial value of the recovery threshold pfcxon may be set to a preset value that is a number of smaller feedback cycles. The preset value may be, for example, 1, 2, 5, or 10.

[0151] According to embodiments of this disclosure, the seventh preset rule can be, for example, a linearly increasing adjustment of the initial maximum marking probability P based on the initial maximum marking probability P. For example, after each feedback adjustment cycle, the initial maximum marking probability P can be increased by a preset value equal to the number of feedback cycles, such as 1%, 2%, 5%, or 10%.

[0152] According to embodiments of this disclosure, the third preset rate threshold can be selected based on actual service conditions, and embodiments of this disclosure do not limit the third preset rate threshold. When the network device is a gigabit switch, the third preset rate threshold can be, for example, 5MB, 10MB, 20MB, or 30MB, etc.

[0153] According to embodiments of this disclosure, the stable output rate of the network device's output terminal within a third preset rate threshold indicates that the difference between the output rates within a preset time period is within the third preset rate threshold.

[0154] According to embodiments of this disclosure, if the output rate remains stable within a third preset rate threshold during the nth preset time period from the current time, it can be considered that both the reduced recovery threshold and the increased label probability have reached their optimal values. The initial recovery threshold value is then updated based on the reduced recovery threshold value, and the initial label probability value is updated based on the increased label probability value. n can be, for example, 3, 4, or 6.

[0155] According to embodiments of this disclosure, if the output rate of the network device cannot be kept stable after adjusting the initial value of the recovery threshold pfcxon multiple times (e.g., 3 or 5 times), it indicates that the output rate of the network device can no longer be kept stable by adjusting the initial value of the recovery threshold pfcxon.

[0156] According to embodiments of this disclosure, when the output rate at the output end of the network device cannot remain stable within a second preset rate threshold, the initial value of the recovery threshold is reduced according to a sixth preset rule and the initial value of the marking probability is increased according to a seventh preset rule, resulting in a reduced recovery threshold value and an increased marking probability value. When the output rate at the output end of the network device remains stable within a third preset rate threshold, the initial value of the recovery threshold is updated according to the reduced recovery threshold value and the initial value of the marking probability is updated according to the increased marking probability value. This increases the congestion regulation intensity based on the reduced recovery threshold value and the increased marking probability value, ensuring that the remaining buffer of the network device does not reach the recovery threshold parameter pfcxon for pausing regulation, thereby enabling network traffic to recover to a stable state in a timely manner and increasing the rate at which network traffic is regulated to a stable state.

[0157] Figure 3 A flowchart illustrating an automatic network parameter update method according to another embodiment of the present disclosure is shown.

[0158] like Figure 3 As shown, the default parameters of network devices, such as switches, are used as the base values ​​for the parameters used for PFC tuning (PFC parameters) and the parameters used for ECN tuning (ECN parameters). In step 310, the switch sends the used buffer X, PFC parameters, ECN parameters, and output rate to the network controller in real time. In step 320, the network controller monitors the X, PFC, and ECN parameters of the network devices in real time, monitoring the fluctuations of X within a preset time period. In step 330, the extreme value Y of X within the preset time period is recorded.

[0159] In step 340, it is determined whether Y is greater than the trigger threshold kmin and less than the back pressure stop threshold pfcxon. In step 341, if Y is greater than kmin and less than pfcxon, the network device is triggered to perform ECN regulation on network traffic, but not PFC regulation. The frequency 'a' of triggering ECN regulation is recorded within a preset time period. In step 342, it is determined whether 'a' is continuous, i.e., whether 'a' is greater than the first frequency threshold.

[0160] If it is determined that 'a' is greater than the first frequency threshold, in step 3421, kmin is reduced according to the first preset rule to obtain the reduced kmin. In step 3422, it is determined that the I / O of the network device is stable, that is, that the output rate of the network device's output terminal remains stable within the first preset rate threshold. In step 343, the optimal kmin is obtained based on the reduced kmin.

[0161] If it is determined that 'a' is less than the first frequency threshold, in step 3423, kmin is increased according to the second preset rule to obtain the increased kmin. In step 3424, it is determined that 'a' no longer occurs, that is, it is determined that within the preset time period, the third frequency for network device congestion regulation of network traffic is less than the first frequency. In step 343, the optimal kmin is obtained based on the increased kmin.

[0162] In step 350, it is determined whether Y is greater than pfcxon and less than the back pressure threshold pfcxoff, or whether Y is less than kmin. In step 351, if Y is determined to be greater than pfcxon and less than pfcxoff, or if Y is determined to be less than kmin, the parameters of the network device are not modified.

[0163] In step 360, it is determined whether Y is greater than pfcxoff. In step 361, if Y is determined to be greater than pfcxoff, the network device is triggered to pause and adjust network traffic, i.e., PFC adjustment, and the frequency b of triggering PFC adjustment within a preset time period is recorded. In step 362, it is determined whether b is continuous, i.e., whether b is greater than the second frequency threshold.

[0164] If it is determined that b is less than the second frequency threshold, in step 3621, pfcxon is reduced according to the third preset rule to obtain the reduced pfcxon. In step 3622, it is determined that b no longer occurs, that is, it is determined that the fourth frequency for which the network device pauses network traffic adjustment within the preset time period is less than the second frequency. In step 3623, based on the determination that b no longer occurs, the optimal pfcxon is obtained.

[0165] If b is determined to be greater than the second frequency threshold, in step 3624, it is determined whether there is packet loss at the switch input port.

[0166] If packet loss is determined to exist at the switch input port, in step 3624_1, the remaining headroom of the network device is increased according to the fourth preset rule. In step 3624_2, it is determined that there is no packet loss at the switch input port. In step 3624_3, assuming there is no packet loss at the switch input port, the optimal remaining headroom is obtained.

[0167] If it is determined that there is no packet loss at the switch input port, in step 3624_4, pfcxoff is increased according to the fifth preset rule to obtain the increased pfcxoff. In step 3624_5, it is determined whether the I / O of the network device is stable.

[0168] In step 3624_6, it is determined that the output rate of the network device's output end remains stable within the second preset rate threshold, thus obtaining the optimal pfcxoff.

[0169] In step 3624_7, it is determined that the output rate of the network device cannot remain stable within the second preset rate threshold. Therefore, the initial value of the recovery threshold kmax is decreased according to the sixth preset rule, and the initial value of the labeling probability P is increased according to the seventh preset rule. In step 3624_8, it is determined whether the network device's I / O is stable. In step 3624_9, the network device's I / O is determined to be stable, and the optimal kmax and optimal P are obtained.

[0170] Figure 4 A flowchart illustrating an automatic network parameter update method according to another embodiment of the present disclosure is shown.

[0171] like Figure 4 As shown, network device 410 stores initial values ​​for parameters used in PFC regulation (PFC parameters), initial values ​​for parameters used in ECN regulation (ECN parameters), and initial values ​​for remaining cache. Network controller 420 can monitor and update the status of the parameters in network device 410 in real time. After updating the parameters according to the automatic network parameter update method provided in this embodiment, network controller 420 adjusts the parameters and uses the updated parameters to update the parameters in network device 410. After receiving the adjusted optimal parameters, network device 410 stores the optimal parameters.

[0172] It should be noted that, unless it is explicitly stated that there is a sequential order of execution between different operations, or that there is a sequential order of execution between different operations in terms of technical implementation, the execution order between multiple operations may not be significant, and multiple operations may be executed simultaneously.

[0173] Based on the above-described automatic network parameter update method, this disclosure also provides an automatic network parameter update device. The following will be combined with... Figure 5 The device is described in detail.

[0174] Figure 5 A schematic block diagram of a network parameter automatic update apparatus according to an embodiment of the present disclosure is shown.

[0175] like Figure 5 As shown, the network parameter automatic update device 500 of this embodiment includes an acquisition module 510, a determination module 520 and an acquisition module 530.

[0176] The acquisition module 510 is used to acquire the initial parameter values ​​of the network device and the used cache of the network device at various times within a preset time period using the network controller. In one embodiment, the acquisition module 510 can be used to perform the operation S210 described above, which will not be repeated here.

[0177] The determining module 520 is used to determine, based on the initial parameter values ​​and the used cache, a first frequency for the network device to perform congestion regulation on network traffic and a second frequency for pausing network traffic regulation within a preset time period. In one embodiment, the determining module 520 can be used to perform the operation S220 described above, which will not be repeated here.

[0178] The obtaining module 530 is used to update the initial parameter values ​​based on a preset frequency threshold, a first frequency, a second frequency, and the output rate of the network device's output terminal, thereby obtaining updated parameter values. In one embodiment, the obtaining module 530 can be used to perform the operation S230 described above, which will not be repeated here.

[0179] According to embodiments of this disclosure, the initial parameter values ​​include initial values ​​for the trigger threshold and recovery threshold corresponding to congestion regulation, and initial values ​​for the back pressure threshold and back pressure stop threshold corresponding to pause regulation. The determination module includes an extreme point acquisition submodule, a first frequency determination submodule, and a second frequency determination submodule.

[0180] The extreme point acquisition submodule is used to obtain M cache extreme points based on the used cache at each moment within a preset time period, where M is a positive integer greater than or equal to 1.

[0181] The first frequency determination submodule is used to determine the first frequency based on M cache extreme points, the initial value of the trigger threshold, and the initial value of the back pressure stop threshold.

[0182] The second frequency determination submodule is used to determine the second frequency based on the M cache extreme points and the initial value of the backpressure threshold.

[0183] According to embodiments of this disclosure, the preset frequency threshold includes a first frequency threshold, and the obtaining module includes a first obtaining submodule and a first updating submodule.

[0184] The first submodule is used to reduce the initial value of the trigger threshold according to a first preset rule when the first frequency is greater than the first frequency threshold, so as to obtain the reduced trigger threshold value.

[0185] The first update submodule is used to update the initial value of the trigger threshold according to the reduced trigger threshold value, provided that the output rate at the output end of the network device remains stable within the first preset rate threshold.

[0186] According to embodiments of this disclosure, the obtaining module further includes a second obtaining submodule and a second updating submodule.

[0187] The second submodule is used to increase the initial value of the trigger threshold according to a second preset rule when the first frequency is less than the first frequency threshold, so as to obtain the increased trigger threshold value.

[0188] The second update submodule is used to update the initial value of the trigger threshold based on the increased trigger threshold value when the third frequency of network device congestion regulation of network traffic is less than the first frequency within a preset time period.

[0189] According to embodiments of this disclosure, the preset frequency threshold includes a second frequency threshold, and the obtaining module includes a third obtaining submodule and a third updating submodule.

[0190] The third submodule is used to reduce the initial value of the back pressure stop threshold according to the third preset rule when the second frequency is less than the second frequency threshold, so as to obtain the reduced back pressure stop threshold value.

[0191] The third update submodule is used to update the initial value of the back pressure stop threshold based on the reduced back pressure stop threshold value when the fourth frequency of the network device pausing and adjusting network traffic is less than the second frequency within a preset time period.

[0192] According to embodiments of this disclosure, the module further includes a packet loss information acquisition submodule, a fourth acquisition submodule, and a fourth update submodule.

[0193] The packet loss information acquisition submodule is used to acquire packet loss information of network devices using the network controller when the second frequency is greater than the second frequency threshold.

[0194] The fourth submodule is used to increase the initial value of the remaining buffer according to the fourth preset rule when it is determined that there is packet loss in the network device based on the packet loss information. The increased value of the remaining buffer is obtained, where the initial value of the remaining buffer is the parameter initial value corresponding to the pause adjustment.

[0195] The fourth update submodule is used to update the initial value of the remaining cache based on the increased remaining cache value, provided that the network device does not lose packets within a preset time period.

[0196] According to embodiments of this disclosure, the obtaining module further includes a fifth obtaining submodule and a fifth updating submodule.

[0197] The fifth submodule is used to increase the initial value of the back pressure threshold according to the fifth preset rule when it is determined that there is no packet loss in the network device based on the packet loss information. The increased back pressure threshold value is obtained, where the initial value of the back pressure threshold is the parameter initial value corresponding to the pause adjustment.

[0198] The fifth update submodule is used to update the initial value of the back pressure threshold according to the increased back pressure threshold value, provided that the output rate at the output end of the network device remains stable within the second preset rate threshold.

[0199] According to embodiments of this disclosure, the obtaining module further includes a sixth obtaining submodule and a sixth updating submodule.

[0200] The sixth submodule is used to reduce the initial value of the recovery threshold and increase the initial value of the marking probability according to the sixth preset rule when the output rate at the output end of the network device cannot remain stable within the second preset rate threshold. The reduced recovery threshold value and the increased marking probability value are obtained according to the seventh preset rule. The initial value of the recovery threshold and the initial value of the marking probability are both parameter initial values ​​corresponding to congestion regulation.

[0201] The sixth update submodule is used to update the initial value of the recovery threshold according to the reduced recovery threshold value and the initial value of the tag probability according to the increased tag probability value when the output rate at the output end of the network device remains stable within the third preset rate threshold.

[0202] According to embodiments of this disclosure, any plurality of modules among the acquisition module 510, determination module 520, and obtaining module 530 may be combined into one module, or any one of these modules may be split into multiple modules. Alternatively, at least a portion of the functionality of one or more of these modules may be combined with at least a portion of the functionality of other modules and implemented in one module. According to embodiments of this disclosure, at least one of the acquisition module 510, determination module 520, and obtaining module 530 may be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging circuitry, or implemented in any one of software, hardware, and firmware methods, or in a suitable combination of any of these. Alternatively, at least one of the acquisition module 510, determination module 520, and obtaining module 530 may be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0203] Figure 6 A block diagram schematically illustrates an electronic device suitable for implementing an automatic network parameter update method according to an embodiment of the present disclosure.

[0204] like Figure 6 As shown, an electronic device 600 according to an embodiment of this disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage portion 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this disclosure.

[0205] RAM 603 stores various programs and data required for the operation of electronic device 600. Processor 601, ROM 602, and RAM 603 are interconnected via bus 604. Processor 601 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 602 and / or RAM 603. It should be noted that the programs may also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0206] According to embodiments of this disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to a bus 604. The electronic device 600 may also include one or more of the following components connected to the input / output (I / O) interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 610 as needed so that computer programs read from it can be installed into the storage section 608 as needed.

[0207] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the automatic network parameter update method according to the embodiments of this disclosure.

[0208] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 602 and / or RAM 603 and / or one or more memories other than ROM 602 and RAM 603 described above.

[0209] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to enable the computer system to implement the automatic network parameter update method provided in embodiments of this disclosure.

[0210] When the computer program is executed by the processor 601, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0211] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via the communication section 609, and / or installed from the removable medium 611. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0212] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0213] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0214] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0215] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0216] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method for automatically updating network parameters, comprising: The network controller is used to obtain the initial values ​​of the network device parameters and the used cache of the network device at various times within a preset time period; Based on the initial values ​​of the parameters and the used cache, a first frequency for the network device to perform congestion regulation on network traffic and a second frequency for pausing regulation of network traffic are determined within the preset time period. The initial value of the parameter is updated based on the preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal to obtain the updated parameter value.

2. The method according to claim 1, wherein, The initial parameter values ​​include initial values ​​for the trigger threshold and recovery threshold corresponding to the congestion regulation, and initial values ​​for the backpressure threshold and backpressure stop threshold corresponding to the pause regulation. The step of determining, based on the initial parameter values ​​and the used buffer, the first frequency of the network device performing congestion regulation on network traffic and the second frequency of pausing network traffic regulation within the preset time period includes: Based on the used cache at each moment within a preset time period, M cache extreme points are obtained, where M is a positive integer greater than or equal to 1; The first frequency is determined based on the M cache extreme points, the initial value of the trigger threshold, and the initial value of the backpressure stop threshold; The second frequency is determined based on the M cache extreme points and the initial value of the backpressure threshold.

3. The method according to claim 2, wherein, The preset frequency threshold includes a first frequency threshold. The updated parameter value is obtained by updating the initial parameter value based on the preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal. When the first frequency is greater than the first frequency threshold, the initial value of the trigger threshold is reduced according to the first preset rule to obtain the reduced trigger threshold value; If the output rate at the output end of the network device remains stable within a first preset rate threshold, the initial value of the trigger threshold is updated according to the reduced trigger threshold value.

4. The method according to claim 3, wherein, The step of updating the initial parameter value based on a preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal to obtain the updated parameter value further includes: When the first frequency is less than the first frequency threshold, the initial value of the trigger threshold is increased according to the second preset rule to obtain the increased trigger threshold value; If, within a preset time period, the third frequency at which the network device performs congestion regulation on the network traffic is less than the first frequency, the initial value of the trigger threshold is updated according to the increased trigger threshold value.

5. The method according to claim 2, wherein, The preset frequency threshold includes a second frequency threshold. The updated parameter value is obtained by updating the initial parameter value based on the preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal. When the second frequency is less than the second frequency threshold, the initial value of the back voltage stop threshold is reduced according to the third preset rule to obtain the reduced back voltage stop threshold value; If, within a preset time period, the fourth frequency at which the network device pauses and adjusts network traffic is less than the second frequency, the initial value of the backpressure stop threshold is updated based on the reduced backpressure stop threshold value.

6. The method according to claim 5, wherein, The step of updating the initial parameter value based on a preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal to obtain the updated parameter value further includes: When the second frequency is greater than the second frequency threshold, the network controller is used to obtain the packet loss information of the network device; If, based on the packet loss information, it is determined that the network device has packet loss, the initial value of the remaining cache is increased according to the fourth preset rule to obtain the increased remaining cache value, wherein the initial value of the remaining cache is the parameter initial value corresponding to the pause adjustment; If it is determined that the network device does not lose packets within the preset time period, the initial value of the remaining cache is updated according to the increased remaining cache value.

7. The method according to claim 6, wherein, The step of updating the initial parameter value based on a preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal to obtain the updated parameter value further includes: If, based on the packet loss information, it is determined that there is no packet loss in the network device, the initial value of the back pressure threshold is increased according to the fifth preset rule to obtain the increased back pressure threshold value, wherein the initial value of the back pressure threshold is the parameter initial value corresponding to the pause adjustment; If the output rate at the output end of the network device remains stable within the second preset rate threshold, the initial value of the back pressure threshold is updated according to the increased back pressure threshold value.

8. The method according to claim 7, wherein, The step of updating the initial parameter value based on a preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal to obtain the updated parameter value further includes: If the output rate at the output end of the network device cannot remain stable within the second preset rate threshold, the initial value of the recovery threshold is reduced according to the sixth preset rule and the initial value of the marking probability is increased according to the seventh preset rule to obtain the reduced recovery threshold value and the increased marking probability value. The initial value of the recovery threshold and the initial value of the marking probability are both parameter initial values ​​corresponding to the congestion regulation. When the output rate at the output end of the network device remains stable within a third preset rate threshold, the initial value of the recovery threshold is updated according to the reduced recovery threshold value and the initial value of the labeling probability is updated according to the increased labeling probability value.

9. A network parameter automatic update device, comprising: The acquisition module is used to acquire the initial values ​​of the parameters of the network device and the used cache of the network device at various times within a preset time period using the network controller; The determination module is used to determine, based on the initial values ​​of the parameters and the used cache, a first frequency for the network device to perform congestion regulation on network traffic and a second frequency for pausing regulation on network traffic within the preset time period; The module is used to update the initial value of the parameter based on a preset frequency threshold, the first frequency, the second frequency, and the output rate of the network device's output terminal, to obtain the updated parameter value.

10. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors perform the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 8.

12. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images