A communication method and related devices

Abstract

In the first aspect of the embodiment of the present application, a communication method is provided. In this method, a first node obtains a target cell and a target time, where the target time is used to indicate the time when the target cell is processed. During the process of the first node sending the target cell to a lower-level node in a switching network system, when the difference between the system time of the first node and the target time is greater than the delay sending threshold, the first node sends the target cell to the lower-level node. That is, the first node delays the sending of the target cell through the delay sending threshold, thereby enabling the upper-level node of the switching network system to share the sorting pressure of the lower-level node, avoiding the increase in transmission delay caused by the backpressure of the lower-level node, realizing the optimization of sorting resources among nodes at all levels in the switching network system, and improving the stability of the switching network system.

Description

Technical Field

[0001] This application relates to the field of communications, and in particular, to a communication method and related devices. Background Art

[0002] In a switching network system, a line card chassis (LCC) is usually composed of at least one line card (LC) and at least one fabric card (FC). Each LC in the LCC includes at least one fabric interface chip (FIC) chip, and each FC includes at least one switch element (SE).

[0003] In the prior art, multiple FICs in a switching network system can communicate with multiple SEs interconnected. Taking the single-stage single-frame networking scenario as an example, as Figure 1 shown, it includes at least one ingress FIC 101, at least one SE 102, and at least one egress FIC 103. Among them, after the packets are sliced into cells at the ingress FIC 101 side, the cells are distributed to multiple SEs 102, and then output from the multiple SEs 102 to the egress FIC 103.

[0004] Among them, in the communication process from the multiple SEs 102 to the egress FIC 103, since the instantaneous congestion degree of the output queue (OQ) of each SE is different, the delay of the cells arriving at the egress FIC through different SEs is also different. At this time, the egress FIC needs to reserve an input queue (IQ) buffer to absorb the delay difference of each path, and finally complete sorting and packet assembly, and then send it out by the egress FIC. In the current switching network system, the IQ resources of the egress FIC chip for sorting are limited. If the traffic burst in the network is large or the distribution of the ingress FIC is instantaneously uneven, it is easy to cause the exhaustion of the IQ resources of the egress FIC. At this time, the egress FIC can only passively backpressure the corresponding SE.

[0005] However, when the egress FIC backpressures the SE (for example, the FIC sends a backpressure indication to the SE), due to the time-consuming of the backpressure transmission process of the egress FIC and the relatively long round-trip time (RTT) of the SE response, the transmission delay of the cells inside the switching network system is greatly increased, which easily leads to a large performance risk in the current switching network system. Summary of the Invention

[0006] The embodiments of the present application provide a communication method and related devices, which are used to enable the upper-level nodes of the switching network system to share the sorting pressure of the lower-level nodes, avoid the increase in transmission delay caused by the backpressure of the lower-level nodes, realize the optimization of sorting resources among nodes at all levels in the switching network system, and improve the stability of the switching network system.

[0007] In a first aspect of the embodiments of the present application, a communication method is provided, which is applied to a first node in a switching network system. In this method, during the communication process of the switching network system, the first node in the switching network system obtains a target cell to be sent and a target time, where the target time is used to indicate the time when the target cell is processed; then, the first node determines a delay transmission threshold for the target cell; in addition, the first node obtains the current system time in the first node; thereafter, when the difference between the system time and the target time is greater than the delay transmission threshold, the first node sends the target cell to the lower-level node. Among them, the first node obtains the target cell and the target time. During the process of the first node sending the target cell to the lower-level node in the switching network system, when the difference between the system time and the target time is greater than the delay transmission threshold, the first node sends the target cell to the lower-level node. That is, the first node delays the transmission of the target cell through the delay transmission threshold, thereby enabling the upper-level nodes of the switching network system to share the sorting pressure of the lower-level nodes, avoiding the increase in transmission delay caused by the backpressure of the lower-level nodes, realizing the optimization of sorting resources among nodes at all levels in the switching network system, and improving the stability of the switching network system.

[0008] In a possible implementation manner of the first aspect of the embodiments of the present application, when the first node is not the initial node in the switching network system, the process of the first node determining the delay transmission threshold for the target cell may include: the first node obtains the number of hops between the first node and the initial node in the switching network system, and thereafter, the first node determines the delay transmission threshold according to the number of hops, and the number of hops is positively correlated with the size of the delay transmission threshold.

[0009] In this embodiment, when the first node is not the initial node in the switching network system, the first node can determine the delay transmission threshold for the target cell according to the number of hops between the first node and the initial node in the switching network system. Among them, the number of hops is positively correlated with the size of the delay transmission threshold, that is, the more hops between the first node and the initial node, the greater the delay transmission threshold for the target cell, and the fewer hops between the first node and the initial node, the smaller the delay transmission threshold for the target cell. That is to say, in a multi-level switching network system, the first node can determine corresponding different delay transmission thresholds according to different numbers of hops of cell transmission between the first node and the initial node, providing a specific implementation manner for the first node to determine the delay transmission threshold, improving the feasibility of the solution, and thus improving the implementation flexibility of this solution.

[0010] In a possible implementation manner of the first aspect of the embodiments of the present application, the process by which the first node determines the delay transmission threshold of the target cell may include: The first node obtains the transmission delay with the lower-level node; thereafter, the first node determines the delay transmission threshold according to the transmission delay, and the magnitude of the transmission delay is positively correlated with the magnitude of the delay transmission threshold.

[0011] In this embodiment, the first node may determine the delay transmission threshold of the target cell according to the transmission delay between the first node and the lower-level node, where the magnitude of the transmission delay is positively correlated with the magnitude of the delay transmission threshold, that is, the greater the transmission delay between the first node and the lower-level node, the greater the delay transmission threshold of the target cell, and the smaller the transmission delay between the first node and the lower-level node, the smaller the delay transmission threshold of the target cell. That is to say, when the first node has multiple lower-level nodes, the first node may determine corresponding different delay transmission thresholds according to the differences in the transmission delays with different lower-level nodes, providing a specific implementation manner for the first node to determine the delay transmission threshold, improving the feasibility of the solution, and thus enhancing the implementation flexibility of the present solution.

[0012] In a possible implementation manner of the first aspect of the embodiments of the present application, the process by which the first node determines the delay transmission threshold of the target cell may include: The first node receives first congestion feedback information from the lower-level node, and the first congestion feedback information is used to indicate the first congestion degree of the lower-level node; thereafter, the first node determines the delay transmission threshold according to the first congestion degree, and the level of the first congestion degree is positively correlated with the magnitude of the delay transmission threshold.

[0013] In this embodiment, the first node may determine the delay transmission threshold of the target cell according to the first congestion degree indicated by the first congestion feedback information from the lower-level node, where the level of the first congestion degree is positively correlated with the magnitude of the delay transmission threshold, that is, the higher the first congestion degree of the lower-level node, the greater the delay transmission threshold of the target cell, and the lower the first congestion degree of the lower-level node, the smaller the delay transmission threshold of the target cell. That is to say, the first node may determine the corresponding delay transmission threshold through the congestion degree feedback by the lower-level node, providing a specific implementation manner for the first node to determine the delay transmission threshold, improving the feasibility of the solution, and thus enhancing the implementation flexibility of the present solution.

[0014] In a possible implementation manner of the first aspect of the embodiments of the present application, after the first node determines the delay transmission threshold of the target cell, the method may further include: the first node receives second congestion feedback information from the lower-level node, where the second congestion feedback information is used to indicate the second congestion degree of the lower-level node; thereafter, the first node updates the delay transmission threshold according to the second congestion degree to obtain an updated delay transmission threshold, and the higher the second congestion degree, the larger the delay transmission threshold; meanwhile, when the difference between the system time and the target time is greater than the delay transmission threshold, the first node sending the target cell to the lower-level node includes: when the difference between the system time and the target time is greater than the updated delay transmission threshold, the first node sends the target cell to the lower-level node.

[0015] In this embodiment, after the first node determines the delay transmission threshold of the target cell, it may update the delay transmission threshold according to the second congestion degree reflected by the second congestion feedback information from the lower-level node to obtain an updated delay transmission threshold. Among them, the second congestion feedback information may specifically be used to real-time feedback the congestion degree of the lower-level node. Correspondingly, when the difference between the system time and the target time is greater than the updated delay transmission threshold, the first node sends the target cell to the lower-level node. That is to say, the first node can dynamically update the delay transmission threshold according to the congestion degree real-time feedback by the lower-level node, so that the first node can more accurately share the sorting pressure of the lower-level node, realize the further optimization of the sorting resources between the nodes at all levels in the switching network system, and further improve the stability of the switching network system.

[0016] In a possible implementation manner of the first aspect of the embodiments of the present application, the process for the first node to obtain the target cell to be sent and the target time may include: the first node obtains the message to be sent; then, the first node slices the message to be sent to obtain the target cell, and the target time is used to indicate the generation time of the target cell in the first node.

[0017] In this embodiment, the first node may be the initial node in the switching network system. At this time, after the first node obtains the message to be sent, it may slice the message to be sent to obtain the target cell. Meanwhile, the target time may indicate the time when the first node slices the message to be sent, that is, the generation time of the target cell in the first node, providing a specific implementation manner for the first node to obtain the target cell to be sent and the target time, improving the feasibility of the solution, and thus improving the implementation flexibility of the present solution.

[0018] In a possible implementation manner of the first aspect of the embodiment of the present application, the first node obtaining the target cell to be sent and the target time includes: the first node receiving the target cell and the target time sent by the upper-level node, where the target time is used to indicate the time when the upper-level node receives the target cell, or the target time is used to indicate the time when the upper-level node sends the target cell, or the target time is used to indicate the time when the initial node in the switching network system generates the target cell, or the target time is used to indicate the time when the initial node in the switching network system sends the target cell.

[0019] In this embodiment, the first node may be an intermediate node in the switching network system, that is, there is an upper-level node for the first node. At this time, the first node can obtain the target cell and the target time by receiving the target cell and the target time sent by the upper-level node; at the same time, the target time can be used to indicate the time when the upper-level node receives the target cell, or the target time can be used to indicate the time when the upper-level node sends the target cell, or the target time can be used to indicate the time when the initial node in the switching network system generates the target cell, or the target time can be used to indicate the time when the initial node in the switching network system sends the target cell, which provides a specific implementation manner for the first node to obtain the target cell to be sent and the target time, and correspondingly provides multiple implementation manners of the target time, improving the feasibility of the solution, and thus improving the implementation flexibility of this solution.

[0020] In a possible implementation manner of the first aspect of the embodiment of the present application, the first node sending the target cell to the lower-level node includes: the first node sending the target cell and the target time to the lower-level node.

[0021] In this embodiment, in the process of the first node sending the target cell to the lower-level node, the target time may specifically be sent to the lower-level node. Thus, the lower-level node can further process the target cell according to the corresponding delay sending threshold, so as to realize that the lower-level node delays sending the target cell to a more lower-level node, optimize the sorting resources between nodes at all levels in the switching network system, and further improve the stability of the switching network system.

[0022] In a possible implementation manner of the first aspect of the embodiment of the present application, the first node sending the target cell and the target time to the lower-level node includes: the first node updating the target time with the system time to obtain the updated target time; thereafter, the first node sending the target cell and the updated target time to the lower-level node.

[0023] In this embodiment, the first node can update the target time using the system time. After obtaining the updated target time, the first node then sends the target cell and the updated target time to the subordinate node, that is, indicating to the subordinate node that the target time is the time when the first node sends the target cell, so as to implement a specific implementation method for the subordinate node to delay sending the target cell to a lower-level node, improving the feasibility of the solution and thus enhancing the implementation flexibility of this solution.

[0024] In a possible implementation manner of the first aspect of the embodiments of the present application, the first node is a fabric interface chip (FIC) or a switching element (SE), and the subordinate node is an FIC or an SE.

[0025] In this embodiment, the fabric system can be a single-stage single-frame system or a multi-stage multi-frame system. Among them, the subordinate node is the upper-level node of the first node, that is, the first node can be an FIC or an SE. Correspondingly, the subordinate node can also be an FIC or an SE, so that this solution can be applied to various scenarios flexibly arranged in the fabric system, supporting a more flexible networking structure.

[0026] The second aspect of the embodiments of the present application provides a communication device, which is characterized in that the communication device is the first node in the fabric system. The first node includes: an acquisition unit for acquiring a target cell to be sent and a target time, where the target time is used to indicate the time when the target cell is processed; a determination unit for determining the delay transmission threshold of the target cell; the acquisition unit is further used to acquire the current system time in the first node; a sending unit for sending the target cell to the subordinate node when the difference between the system time and the target time is greater than the delay transmission threshold. Among them, the acquisition unit acquires the target cell to be sent and the target time, and the target time is used to indicate the time when the target cell is processed. In the process of the first node sending the target cell to the subordinate node in the fabric system, when the difference between the system time and the target time is greater than the delay transmission threshold, the sending unit sends the target cell to the subordinate node, that is, the sending unit delays the sending of the target cell through the delay transmission threshold, so that the upper-level node of the fabric system shares the sorting pressure of the subordinate node, avoiding the increase in transmission delay caused by the backpressure of the subordinate node, realizing the optimization of sorting resources among nodes at all levels in the fabric system, and enhancing the stability of the fabric system.

[0027] In the second aspect of the embodiments of the present application, the constituent modules of the communication device can also be used to execute the steps performed in various possible implementation manners of the first aspect. Specifically, reference can be made to the first aspect for details, and no further elaboration will be provided here.

[0028] In a third aspect of the embodiments of the present application, a communication device is provided. The communication device may specifically be a first node. Wherein, the communication device includes a processor, the processor is coupled to a memory, the memory is used to store computer programs or instructions, and the processor is used to execute the computer programs or instructions in the memory, so that the method described in the foregoing first aspect or any possible implementation manner of the first aspect is executed.

[0029] In a fourth aspect of the embodiments of the present application, a communication device is provided. The communication device may specifically be a first node. Wherein, the communication device includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run computer programs or instructions, so that the method described in the foregoing first aspect or any possible implementation manner of the first aspect is executed.

[0030] In a fifth aspect of the embodiments of the present application, a computer-readable storage medium storing one or more computer-executable instructions is provided. When the computer-executable instructions are executed by a processor, the processor executes the method described in the foregoing first aspect or any possible implementation manner of the first aspect.

[0031] In a sixth aspect of the embodiments of the present application, a computer program product (or computer program) storing one or more computers is provided. When the computer program product is executed by the processor, the processor executes the method described in the foregoing first aspect or any possible implementation manner of the first aspect.

[0032] In a seventh aspect of the embodiments of the present application, a chip system is provided. The chip system includes a processor, which is used to support an access network device to implement the functions involved in the foregoing first aspect or any possible implementation manner of the first aspect. In a possible design, the chip system may further include a memory, and the memory is used to store necessary program instructions and data of the access network device. The chip system may be composed of chips or may include chips and other discrete devices.

[0033] In an eighth aspect of the embodiments of the present application, a communication system is provided. The communication system includes the communication device of the foregoing first aspect and the communication device of the sixth aspect.

[0034] Wherein, for the technical effects brought by the second to eighth aspects or any possible implementation manner thereof, reference may be made to the technical effects brought by the first aspect or different possible implementation manners of the first aspect, which will not be elaborated herein.

[0035] As can be seen from the above technical solutions, the embodiments of the present application have the following advantages: During the communication process of the switching network system, the first node in the switching network system acquires the target cell to be sent and the target time, where the target time is used to indicate the time when the target cell is processed; then, the first node determines the delay transmission threshold of the target cell; in addition, the first node acquires the current system time in the first node; thereafter, when the difference between the system time and the target time is greater than the delay transmission threshold, the first node sends the target cell to the lower-level node. Among them, the first node acquires the target cell and the target time. During the process of the first node sending the target cell to the lower-level node in the switching network system, when the difference between the system time and the target time is greater than the delay transmission threshold, the first node sends the target cell to the lower-level node. That is, the first node makes the target cell be delayed in transmission through the delay transmission threshold, thereby enabling the upper-level node of the switching network system to share the sorting pressure of the lower-level node, avoiding the increase in transmission delay caused by the backpressure of the lower-level node, realizing the optimization of sorting resources among nodes at all levels in the switching network system, and improving the stability of the switching network system. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 FIG. is a schematic diagram of an application scenario in an embodiment of the present application;

[0037] Figure 2 FIG. is a schematic diagram of an embodiment of a communication method in an embodiment of the present application;

[0038] Figure 3 FIG. is another schematic diagram of an embodiment of a communication method in an embodiment of the present application;

[0039] Figure 4 FIG. is another schematic diagram of an embodiment of a communication method in an embodiment of the present application;

[0040] Figure 5 FIG. is another schematic diagram of an embodiment of a communication method in an embodiment of the present application;

[0041] Figure 6 FIG. is a schematic diagram of an embodiment of a communication device in an embodiment of the present application;

[0042] Figure 7 FIG. is another schematic diagram of an embodiment of a communication device in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.

[0044] Please refer to Figure 1, multiple FICs in the switching network system can communicate with multiple SEs interconnectedly. Taking the single-stage single-frame networking scenario as an example, the switching network system includes at least one upstream FIC 101, at least one SE 102, and at least one downstream FIC 103.

[0045] Among them, after the packets are sliced into cells at the upstream FIC 101 side, the cells are distributed to multiple SEs 102, and then output from the multiple SEs 102 to the downstream FIC 103. Specifically, during the communication process from the multiple SEs 102 to the downstream FIC 103, since the instantaneous congestion degree of the 0Q of each SE is different, the delay of the cells reaching the downstream FIC through different SEs is also different. At this time, the downstream FIC needs to reserve buffer to absorb the delay difference of each path, and finally complete sorting and packet assembly, and then send it out by the downstream FIC. In the current switching network system, the IQ resources used by the downstream FIC chip for sorting are limited. If the traffic burst in the network is large or the upstream FIC distribution is instantaneously uneven, it is easy to cause the depletion of the buffer resources of the downstream FIC. At this time, the downstream FIC can only passively backpressure the corresponding SE.

[0046] Exemplarily, during this backpressure process, the SE can set multiple 0Q queues according to different output links and / or different priority types, and the downstream FIC sets IQ queues according to the receiving link and service type. When the IQ of the downstream FIC is congested, it triggers reverse backpressure and transmits it to the SE through the cell header, and the 0Q of the SE responds to the corresponding backpressure.

[0047] However, as Figure 1 shown, when the downstream FIC backpressures the SE, due to the time-consuming of the backpressure transmission process of the downstream FIC and the relatively large RTT time-consuming of the SE response, the transmission delay of the cells inside the switching network system is greatly increased. For the downstream FIC, when the output delay difference of the data packets sent by its upper-level node (SE) is relatively large, it is easy to cause the depletion of the sorting resources of the downstream FIC. Thus, it is easy to cause relatively large performance risks in the current switching network system.

[0048] Similarly, when the switching network system is applied to scenarios such as single-stage multi-frame networking, multi-stage single-frame networking, or multi-stage multi-frame networking, the initial nodes (i.e., input nodes) and end nodes (i.e., output nodes) of the switching network system are generally FICs, and the intermediate nodes existing between the initial nodes and end nodes can be FICs or SEs. At this time, for any upper-level node in the switching network system, when sending data to the lower-level node, there may be a situation where the sorting resources of the lower-level node are insufficient, resulting in backpressure. Due to the backpressure, the transmission delay of the cells inside the switching network system is greatly increased, which is easy to cause relatively large performance risks in the current switching network system, affecting the stability of data transmission in the switching network system.

[0049] To solve the above problems, embodiments of the present application provide a communication method and related devices, which are used to enable the upper-level nodes of the switching network system to share the sorting pressure of the lower-level nodes, avoid the increase in transmission delay caused by the backpressure of the lower-level nodes, realize the optimization of sorting resources between nodes at all levels in the switching network system, and improve the stability of the switching network system.

[0050] Please refer to Figure 2 , embodiments of the present application provide a communication method, including:

[0051] S101. A first node obtains a target cell to be sent and a target time;

[0052] In this embodiment, the first node obtains the target cell to be sent and the target time, where the target time is used to indicate the time when the target cell is processed.

[0053] Among them, in the switching network system, there are multiple levels of nodes, and each level of nodes includes multiple FICs or multiple SEs. Among them, the first node is any upper-level node (i.e., FIC or SE) in the switching network system, that is, the first node has lower-level nodes in the switching network system. Specifically, this embodiment can, in a variety of application scenarios, relieve the sorting pressure of the lower-level nodes through the upper-level nodes. The supported scenarios include: single-level single-frame, CLOS multi-level multi-frame, two-frame back-to-back, Mesh multi-frame and other scenarios, as well as scenarios where the pull distances between FIC-SE or SE-SE are inconsistent, or other application scenarios of the switching network system, which are not specifically limited here.

[0054] In a specific implementation manner, in step S101, the target cell obtained by the first node may include a cell, and the target time may be carried in the cell header information of the target cell; or, in step S101, the first node may obtain two independent information blocks, which are respectively used to carry the target time and the target cell, and the identifier of the target cell may be carried in the information block where the target time is located, or the identifier of the target time may be carried in the information block where the target cell is located; or the first node obtains the target time and the target cell in other forms in step S101, which is not limited here.

[0055] In a specific implementation manner, the first node has lower-level nodes in the switching network system, that is, the first node is not the terminal node of the switching network system in the switching network system. That is to say, the first node may specifically be an initial node or an intermediate node in the switching network system. Specifically:

[0056] 1) When the first node is the initial node of the switching network system, in step S101, the process for the first node to obtain the target cell and the target time can include: the first node obtains the packet to be sent; then, the first node splits the packet to be sent to obtain the target cell, and the target time is used to indicate the generation time of the target cell in the first node. Among them, in the process of the first node obtaining the target cell and the target time, it can be obtained by splitting the received packet to be sent.

[0057] In a specific implementation manner, the local clocks can be synchronized between multiple levels of nodes (SE and FIC) in the switching network system. At this time, as the initial node of the switching network system, when the first node splits the packet to be sent to obtain the target cell, it can read the time when the first node splits the packet to be sent in the local clock and determine it as the target time, that is, use the generation time of the target cell in the first node as the target time. Exemplarily, the local clocks of multiple levels of nodes in the switching network system can be synchronized by aligning to the global time stamp (Global Time Stamp, GTS) based on the global time stamp synchronization mechanism. At this time, when the first node splits the packet to be sent to obtain the target cell, it can assign a global time stamp to each cell, that is, the time corresponding to when the first node splits the packet to be sent to obtain the target cell is used as the target time. In addition, when there are multiple FICs in the initial node (such as Figure 1 the multiple upstream FICs in), different initial nodes can maintain a global time stamp counter. When the multiple upstream FICs transfer to each other, the time stamp synchronization cells carry their own time stamp values and are globally aligned to the time stamp with the smallest FIC number to achieve the unification and synchronization of the global time stamps between different initial nodes.

[0058] In addition, in another implementation manner, when the data volume of the packet to be sent is relatively small or the number of the lower-level nodes of the first node is only one, the first node can use the packet to be sent as the target cell in step S101 and use the time when the first node obtains the packet to be sent as the target time.

[0059] 2) When the first node is not the initial node of the switching network system, in step S101, the process for the first node to obtain the target cell and the target time can include: the first node receives the target cell and the target time from the upper-level node to achieve the acquisition of the target cell and the target time. That is, when the first node is an intermediate node in the switching network system, the first node can specifically obtain the target cell and the target time by receiving the target cell and the target time sent by the upper-level node.

[0060] In a specific implementation manner, the first node may be an intermediate node in the switching network system, that is, there is a superior node for the first node. At this time, the first node can obtain the target cell and the target time by receiving the target cell and the target time sent from the superior node; at this time, there are multiple implementation manners for the target time, including any one of the following:

[0061] a. The target time can be used to indicate the time when the superior node receives the target cell, that is, when the superior node receives the target cell sent from a higher-level node, the superior node uses the reception time of the target cell as the target time and sends it to the first node. At this time, during the multi-level transmission process of the target cell in the switching network system, the target time may change;

[0062] b. The target time can be used to indicate the time when the superior node sends the target cell, that is, after the superior node receives the target cell sent from a higher-level node and sends the target cell, the superior node uses the transmission time of the target cell as the target time and sends it to the first node. At this time, during the multi-level transmission process of the target cell in the switching network system, the target time may change;

[0063] c. The target time can be used to indicate the time when the initial node in the switching network system generates the target cell, that is, the switching network system uses the generation time of the target cell as the target time, and during the multi-level transmission process of the target cell in the switching network system, the target time remains unchanged;

[0064] d. The target time can be used to indicate the time when the initial node in the switching network system sends the target cell, that is, the switching network system uses the transmission time of the target cell as the target time, and during the multi-level transmission process of the target cell in the switching network system, the target time remains unchanged.

[0065] Therefore, the target time can be achieved in various ways, which improves the implementation flexibility of this solution. In addition, generally speaking, in a switching network system, the initial node will carry corresponding routing and forwarding information in each cell after the message is segmented. This routing and forwarding information can indicate that multiple cells segmented from the same message are routed to the same end node. Subsequently, the multiple cells can be restored to the original message and output at the end node. Therefore, among the various implementation processes of the above target time, compared with the process in which the target time changes in the implementation by the above methods a and b, it is preferably implemented by the above methods c and d, that is, when the initial node obtains the target cell by segmenting the message to be sent, the segmentation time or the sending time of the initial node is determined as the target time, and during the multi-level transmission process of the target cell in the switching network system, the target time remains unchanged, which can ensure that the cells from the same message to be sent can be restored to the original message with as short a delay as possible at the end node.

[0066] In this switching network system, when applied to the scenario of a single-stage single-frame, such as Figure 1 shown, SE102 is the lower-level node of the upstream FIC101, and the downstream FIC103 is the lower-level node of SE102. At the same time, the upstream FIC101 is the upper-level node of SE102, and SE102 is the upper-level node of the downstream FIC103; when applied to the scenario of multi-level nodes (such as CLOS multi-level multi-frame, two-frame back-to-back, Mesh multi-frame, etc. scenarios), the transmission between different-level nodes can be one-hop transmission, two-hop transmission or more-hop transmission. At this time, the upper-level node and the lower-level node can be nodes between adjacent levels or nodes between every other hop of two levels.

[0067] S102, the first node determines the delay transmission threshold of the target cell;

[0068] In this embodiment, the first node can determine the delay transmission threshold corresponding to the target cell obtained in step S101 in step S102.

[0069] In a specific implementation manner, in step S102, the first node can determine the delay transmission threshold (TS_TX_THD) of the target cell according to one or more of the following conditions. The first node can determine the corresponding delay transmission threshold according to different configuration rules:

[0070] 1) The first node obtains the number of hops between it and the initial node in the switching network system. Thereafter, the first node determines the delay transmission threshold according to the number of hops, and the number of hops is positively correlated with the size of the delay transmission threshold;

[0071] Specifically, the first node can set different delay transmission thresholds for different target cells through different settings of the link between the first node and the initial node in the switching network system. Among them, the number of hops is positively correlated with the size of the delay transmission threshold, that is, the more hops between the first node and the initial node, the larger the delay transmission threshold for the target cell; the fewer hops between the first node and the initial node, the smaller the delay transmission threshold for the target cell. Exemplarily, the delay transmission threshold can be determined by multiplying the number of hops by the delay per hop, or it can be determined by other mathematical relationships between the number of hops and the delay per hop, which is not limited here. Among them, the delay per hop can be pre-configured in the first node, or carried in the target cell in step S101, or the first node can obtain the delay per hop in other ways, which is not limited here.

[0072] In addition, if applied to a single-stage single-frame scenario, TS_TX_THD can be default-configured as the average delay passing through the nodes of the first-stage switching network system (first-stage FIC or first-stage SE), that is, for the link with 1 hop between the first node and the initial node in the switching network system, configure TS_TX_THD = HopDelay, where HopDelay is the delay passing through the first-stage nodes in the switching network system, or the user-defined delay passing through the first-stage nodes in the switching network system, or defined in other ways, which is not limited here. Further, if applied to a scenario with multiple levels of nodes (such as CLOS multi-stage multi-frame, two-frame back-to-back, Mesh multi-frame, etc.), when the number of hops between the first node and the initial node in the switching network system is n (n is an integer greater than 0), the corresponding delay transmission threshold can be set according to the number of hops, that is, for the link with n hops between the first node and the initial node in the switching network system, configure it to be obtained by multiplying the number of hops n by the average delay time, that is, TS_TX_THD = n * HopDelay.

[0073] 2) The first node obtains the transmission delay between it and the lower-level node; thereafter, the first node determines the delay transmission threshold according to the transmission delay, and the size of the transmission delay is positively correlated with the size of the delay transmission threshold;

[0074] Specifically, for the first node, in the switching network system, there can be multiple lower-level nodes for the first node. The first node can pre-know the transmission delays between it and multiple lower-level nodes, and then set different threshold values according to different transmission delays, that is, the first node can determine the delay as the delay transmission threshold, or the first node can determine the product of the delay multiplied by a preset coefficient as the delay transmission threshold, where the preset coefficient can be pre-configured in the first node or carried in the target cell in step S101, or the first node determines the delay transmission threshold in other ways according to the delay, which is not limited here.

[0075] Among them, if there are transmission delays between the same-level node and multiple lower-level nodes in the switching network system, and different transmission delays exist for different lower-level nodes, different TS_TX_THDs can also be configured according to different links to compensate for the path delay on the output side in advance. The difference in the transmission delay between the first node and the multiple lower-level nodes can indicate the difference in the transmission distance between the first node and the lower-level node, can also indicate the difference in the material of the transmission optical fiber between the first node and the lower-level node, and can also indicate the difference in other transmission parameters between the first node and the lower-level node. No limitation is made here.

[0076] Exemplarily, taking the difference in the transmission distance between the first node and the lower-level node as an example, when there are multiple lower-level nodes in the first node of the switching network system, different delay transmission thresholds can be set in the first node according to the difference in the transmission distance from multiple lower-level nodes combined with a preset coefficient. Among them, the distance of the transmission distance can be positively correlated with the size of the delay transmission threshold. For example, when the preset coefficient is 0.5 milliseconds per meter, if the transmission distance is 10 meters, the delay transmission threshold is determined to be 5 milliseconds. After that, for each additional meter of the transmission distance, the delay transmission threshold is increased by 0.5 ms; or, when the preset coefficient is 20 milliseconds per kilometer, if the transmission distance is 10 kilometers, the delay transmission threshold is determined to be 200 milliseconds. After that, for each additional kilometer of the transmission distance, the delay transmission threshold is increased by 20 ms; or the delay transmission threshold is set correspondingly in combination with the actual application scenario. No specific limitation is made here.

[0077] In addition, when applied to the scenario of a single-stage and single-frame, as Figure 1 shown, SE102 is the lower-level node of the upstream FIC101. At the same time, the downstream FIC103 is the lower-level node of SE102; when applied to the scenario of multi-level nodes (such as CLOS multi-level and multi-frame, two-frame back-to-back, Mesh multi-frame, etc. scenarios), the transmission between different-level nodes can be one-hop transmission, two-hop transmission or more-hop transmission. At this time, the upper-level node and the lower-level node can be the nodes between adjacent two levels, or can be the nodes between two levels with a skipped hop.

[0078] 3) The first node receives first congestion feedback information from the lower-level node, and the first congestion feedback information is used to indicate the first congestion degree of the lower-level node; after that, the first node determines the delay transmission threshold according to the first congestion degree, and the level of the first congestion degree is positively correlated with the size of the delay transmission threshold.

[0079] Specifically, the first node can dynamically set the delay transmission threshold according to the congestion feedback of the subordinate node. Among them, the first congestion feedback information can indicate the data volume of the currently processed cells of the subordinate node, the number of currently processed cells, the rate of the currently processed cells, or other parameters indicating the congestion degree of the subordinate node, which is not limited here. The first node can set the delay transmission threshold according to the first congestion feedback information based on a preset delay transmission threshold setting rule. Taking the first congestion feedback information as the rate of the currently processed cells of the subordinate node as an example, among them, the higher the rate of the currently processed cells of the subordinate node, the lower the congestion degree of the subordinate node. Correspondingly, the smaller the delay transmission threshold determined by the first node; the lower the rate of the currently processed cells of the subordinate node, the higher the congestion degree of the subordinate node. Correspondingly, the larger the delay transmission threshold determined by the first node. Among them, in step S102, the first node can determine the delay transmission threshold through a preset mapping relationship table. Still taking the first congestion feedback information as the rate of the currently processed cells of the subordinate node as an example, the mapping relationship table can indicate the mapping relationship between the rate value of each currently processed cell and the delay transmission threshold (for example, in the mapping relationship table, the rate values are 0 / 1 / 2 / 3 / 4... / n, and the corresponding delay transmission thresholds are a1 / a2 / a3 / a4... / an, where n is a positive integer, and a1 / a2 / a3 / a4... / an are preset values), or can indicate the functional relationship between the rate value of the currently processed cells and the delay transmission threshold (for example, in the mapping relationship table, the delay transmission threshold is equal to the rate value multiplied by the coefficient b, where the coefficient b is a preset value), or other implementation methods, which are not limited here.

[0080] Thus, in step S102, the first node can determine the delay transmission threshold of the target cell through the difference in the link between the first node and the initial node in the switching network system, the difference in the link between the first node and the subordinate node, or the feedback information of the subordinate node. Multiple implementation methods for the first node to determine the delay transmission threshold are provided, improving the feasibility of the solution, and thus enhancing the implementation flexibility of this solution.

[0081] S103. The first node obtains the current system time in the first node;

[0082] In this embodiment, before step S104, the first node can first obtain the current system time in the first node.

[0083] Specifically, in the multi-level nodes (SE and FIC) of the switching network system, multiple SEs or FICs can exist in the same-level nodes, and the same-level nodes can be set with aligned global time scales. The specific implementation process can refer to the unified method of the global time scales among the aforementioned multiple different initial nodes, which will not be elaborated here.

[0084] Thereafter, the first node can use the current global time scale as the current system time of the first node. The first node can also use the global time scales sent by other nodes in the same-level nodes as the current system time of the first node, or it can also obtain the current system time in other ways, which is not limited here.

[0085] S104. When the difference between the system time and the target time is greater than the delayed transmission threshold, the first node sends the target cell to the lower-level node.

[0086] In this embodiment, when the difference between the system time obtained in step S103 and the target time obtained in step S101 is greater than the delayed transmission threshold determined in step S102, the first node sends the target cell in step S101 to the lower-level node.

[0087] In a specific implementation manner, the process of the first node sending the target cell to the lower-level node in step S104 can include: the first node sends the target cell and the target time to the lower-level node, that is, the lower-level node can obtain the target cell and the target time through step S104, and can further process the target cell according to the determined corresponding delayed transmission threshold in the lower-level node (similar to the determination process in step S102) to realize that the lower-level node delays the transmission of the target cell to a more lower-level node, so as to further optimize the sorting resources among the nodes at all levels in the switching network system and further improve the stability of the switching network system. In addition, during the process of the first node sending the target cell and the target time to the lower-level node, the first node can update the target time with the system time to obtain the updated target time. Thereafter, the first node sends the target cell and the updated target time to the lower-level node. Among them, after the first node updates the target time with the system time to obtain the updated target time, it then sends the target cell and the updated target time to the lower-level node, that is, indicates to the lower-level node that the target time is the time when the first node sends the target cell, so as to provide a specific implementation manner for the lower-level node to delay the transmission of the target cell to a more lower-level node.

[0088] In a specific implementation manner, after the first node determines the delay transmission threshold of the target cell in step S102, the first node may further receive second congestion feedback information from the lower-level node, where the second congestion feedback information is used to indicate the second congestion degree of the lower-level node; thereafter, the first node updates the delay transmission threshold according to the second congestion degree to obtain an updated delay transmission threshold, and the higher the second congestion degree, the larger the delay transmission threshold; meanwhile, in the implementation process of step S104, when the difference between the system time and the target time is greater than the updated delay transmission threshold, the first node sends the target cell to the lower-level node. That is to say, after the first node determines the delay transmission threshold of the target cell, it can update the delay transmission threshold according to the second congestion degree reflected by the second congestion feedback information from the lower-level node to obtain an updated delay transmission threshold. Among them, the second congestion feedback information can specifically be used to real-time feedback the congestion degree of the lower-level node. Correspondingly, when the difference between the system time and the target time is greater than the updated delay transmission threshold, the first node sends the target cell to the lower-level node. That is to say, the first node can dynamically update the delay transmission threshold according to the congestion degree real-time feedback by the lower-level node, so that the first node can more accurately share the sorting pressure of the lower-level node, realize the further optimization of the sorting resources between nodes at all levels in the switching network system, and further improve the stability of the switching network system.

[0089] Among them, the above Figure 2 The delay mechanism of steps S101 to S104 shown above is not limited to being used in a single-frame system (only the link on the TxToFic side), but can also be used in a multi-level multi-frame system (including the link on the TxToSe side and the link on the TxToFic side). Among them, "TxToFic" refers to the link for transmitting to a lower-level node as FIC, and "TxToSe" refers to the link for transmitting to a lower-level node as SE. Specifically:

[0090] 1) As Figure 3 shown, in the scenario of a single-level single-frame application, taking any one or a combination of multiple in SE102 as the first node and the downstream FIC103 as the lower-level node as an example, that is, all SEs receive the target cell (i.e., step S101) carrying the target time (Cell.TS) sent by the upstream FIC, align it to the global time stamp (GTS) through the global time scale synchronization mechanism to determine the system time of the SE (i.e., step S103), set the delay transmission threshold (TS_TX_THD) for TS transmission (i.e., step S102), and further send the target cell to the downstream FIC according to the system time, the target time, and the delay transmission threshold (i.e., in step S104, when the difference between the system time and the target time is greater than the delay transmission threshold, send the target cell).

[0091] 2) As Figure 4 shown, in the scenario applied to multi - level SE, taking any one or a combination of multiple SEs at the same level as the first node (i.e., uplink S0, S2, downlink S0), and taking the downlink FIC as the downlink node as an example, as shown in step S102, the method for determining the delay transmission threshold can be determined by the hop count from the initial node (i.e., uplink FIC) (which are 1, 2, 3 respectively), and the target cell is sent to the downlink FIC according to the system time, the target time, and the delay transmission threshold.

[0092] Specifically, for any uplink S0, when GTS - Cell.TS in the target cell > HopDelay, the target cell is sent to the lower - level node; for any S2, when GTS - Cell.TS in the target cell > 2 * HopDelay, the target cell is sent to the lower - level node; for any downlink S0, when GTS - Cell.TS in the target cell > 3 * HopDelay, the target cell is sent to the lower - level node.

[0093] 3) As Figure 5 shown, based on the scenario shown in Figure 3 as shown in step S102, the method for determining the delay transmission threshold can be determined by the communication delay with the lower - level node (i.e., downlink FIC), and the target cell is sent to the downlink FIC according to the system time, the target time, and the delay transmission threshold.

[0094] Specifically, for SE#0, when GTS - Cell.TS in the target cell > HopDelay + Tx_Delay_1m, the corresponding target cell is sent to the lower - level node, and when GTS - Cell.TS in the target cell > HopDelay + Tx_Delay_100m, the corresponding target cell is sent to another lower - level node; for SE#1, when GTS - Cell.TS in the target cell > HopDelay + Tx_Delay_20m, the corresponding target cell is sent to the lower - level node, and when GTS - Cell.TS in the target cell > HopDelay + Tx_Delay_80m, the corresponding target cell is sent to another lower - level node; for SE#m, when GTS - Cell.TS in the target cell > HopDelay + Tx_Delay_100m, the corresponding target cell is sent to the lower - level node, and when GTS - Cell.TS in the target cell > HopDelay + Tx_Delay_1m, the corresponding target cell is sent to another lower - level node.

[0095] Through the above-mentioned delayed transmission mechanism, the differences in the output times of each first node can be reduced. At this time, the 0Q resources of the first node can share part of the sorting pressure corresponding to the IQ resources of the subordinate nodes, facilitating the optimization of the sorting resources of FIC / SE (which is beneficial to reducing chip costs or ensuring engineering feasibility). Further, the system scalability can be improved to support a more flexible networking structure (such as asymmetric link remote extension, etc.).

[0096] In this embodiment, during the communication process of the switching network system, the first node in the switching network system acquires a target cell to be transmitted and a target time, where the target time is used to indicate the time when the target cell is processed. Then, the first node determines the delayed transmission threshold of the target cell. In addition, the first node acquires the current system time in the first node. Thereafter, when the difference between the system time and the target time is greater than the delayed transmission threshold, the first node transmits the target cell to the subordinate node. Among them, the first node acquires the target cell and the target time. During the process of the first node transmitting the target cell to the subordinate node in the switching network system, when the difference between the system time and the target time is greater than the delayed transmission threshold, the first node transmits the target cell to the subordinate node. That is, the first node delays the transmission of the target cell through the delayed transmission threshold, thereby enabling the upper-level node of the switching network system to share the sorting pressure of the lower-level node, avoiding the increase in transmission delay caused by the backpressure of the lower-level node, and realizing the optimization of the sorting resources between the nodes at all levels in the switching network system, and improving the stability of the switching network system.

[0097] The above describes the embodiments of the present application from the perspective of the method. Next, the communication device in the embodiments of the present application will be introduced from the perspective of the specific device implementation.

[0098] Please refer to Figure 6 , the embodiments of the present application provide a communication device 600. Specifically, the communication device 600 can be a first node. The communication device 600 includes: an acquisition unit 601, a determination unit 602, a transmission unit 603, a reception unit 604, and an update unit 605;

[0099] The acquisition unit 601 is configured to acquire a target cell to be transmitted and a target time, where the target time is used to indicate the time when the target cell is processed;

[0100] The determination unit 602 is configured to determine the delayed transmission threshold of the target cell;

[0101] The acquisition unit 601 is further configured to acquire the current system time in the first node;

[0102] The transmission unit 603 is configured to transmit the target cell to the subordinate node when the difference between the system time and the target time is greater than the delayed transmission threshold.

[0103] In a specific implementation manner, the determining unit 602 is specifically configured to:

[0104] Obtain the number of hops between the initial nodes in the switching network system;

[0105] Determine the delay transmission threshold according to the number of hops, and there is a positive correlation between the number of hops and the size of the delay transmission threshold.

[0106] In a specific implementation manner, the determining unit 602 is specifically configured to:

[0107] Obtain the transmission delay between the lower-level nodes;

[0108] Determine the delay transmission threshold according to the transmission delay, and there is a positive correlation between the size of the transmission delay and the size of the delay transmission threshold.

[0109] In a specific implementation manner, the determining unit 602 is specifically configured to:

[0110] Receive first congestion feedback information from the lower-level node, where the first congestion feedback information is used to indicate the first congestion degree of the lower-level node;

[0111] Determine the delay transmission threshold according to the first congestion degree, and there is a positive correlation between the level of the first congestion degree and the size of the delay transmission threshold.

[0112] In a specific implementation manner, the device further includes:

[0113] A receiving unit 604, configured to receive second congestion feedback information from the lower-level node, where the second congestion feedback information is used to indicate the second congestion degree of the lower-level node;

[0114] An updating unit 605, configured to update the delay transmission threshold according to the second congestion degree to obtain an updated delay transmission threshold, and there is a positive correlation between the level of the second congestion degree and the size of the delay transmission threshold;

[0115] The sending unit 603 is specifically configured to:

[0116] When the difference between the system time and the target time is greater than the updated delay transmission threshold, send the target cell to the lower-level node.

[0117] In a specific implementation manner, the obtaining unit 601 is specifically configured to:

[0118] Obtain the message to be sent;

[0119] The to-be-sent message is segmented to obtain the target cell, and the target time is used to indicate the generation time of the target cell in the first node.

[0120] In a specific implementation manner, the obtaining unit 601 is specifically configured to:

[0121] Receive the target cell and the target time sent by the upper-level node, where the target time is used to indicate the time when the upper-level node receives the target cell, or the target time is used to indicate the time when the upper-level node sends the target cell, or the target time is used to indicate the time when the initial node in the switching network system generates the target cell, or the target time is used to indicate the time when the initial node in the switching network system sends the target cell.

[0122] In a specific implementation manner, the sending unit 603 is specifically configured to:

[0123] Send the target cell and the target time to the lower-level node.

[0124] In a specific implementation manner, the sending unit 603 is specifically configured to:

[0125] Use the system time to update the target time to obtain the updated target time;

[0126] Send the target cell and the updated target time to the lower-level node.

[0127] It should be noted that for the information execution process and the like of the units of the communication device 600 above, specific details can be referred to the description in the method embodiment shown above in this application, and will not be elaborated here.

[0128] Please refer to Figure 7 , which is a possible logical structure diagram of the communication device 700 involved in the above embodiment provided in the embodiment of the present application. The communication device may specifically be the first node in the foregoing embodiment. The communication device 700 may include but is not limited to a processor 701, a communication port 702, a memory 703, and a bus 704. In the embodiment of the present application, the processor 701 is used to control and process the actions of the communication device 700.

[0129] In addition, the processor 701 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosure of the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, and so on. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0130] It should be noted that Figure 7 The communication device shown can specifically be used to implement Figures 2 to 5 the steps implemented by the terminal device in the corresponding method embodiment and achieve the technical effects corresponding to the first node, which will not be elaborated one by one here.

[0131] The embodiments of the present application also provide a computer-readable storage medium storing one or more computer-executable instructions. When the computer-executable instructions are executed by the processor, the processor executes the method as described in the possible implementation manners of the communication device in the foregoing embodiments, where the communication device can specifically be Figures 2 to 5 the first node in the corresponding method embodiment.

[0132] The embodiments of the present application also provide a computer program product (or computer program) storing one or more computers. When the computer program product is executed by the processor, the processor executes the method of the possible implementation manners of the above communication device, where the communication device can specifically be the foregoing Figures 2 to 5 first node in the corresponding method embodiment.

[0133] The embodiments of the present application also provide a computer program product storing one or more computers. When the computer program product is executed by the processor, the processor executes the method of the possible implementation manners of the above communication device, where the communication device can specifically be Figures 2 to 5 the first node in the corresponding method embodiment.

[0134] The embodiments of the present application also provide a chip system. The chip system includes a processor for supporting the communication device to implement the functions involved in the possible implementation manners of the above communication device. In a possible design, the chip system may further include a memory for storing the necessary program instructions and data of the communication device. The chip system may be composed of chips or may include chips and other discrete devices, where the communication device can specifically be Figures 2 to 5 the first node in the corresponding method embodiment.

[0135] The embodiment of the present application also provides a network system architecture, which includes the above-mentioned communication device. Specifically, the communication device may be Figures 2 to 5 the first node corresponding to the method embodiment, and a possible third node.

[0136] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0137] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] In addition, the functional units in each embodiment of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0139] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

Claims

1. A communication method, characterized in that, Applied to the first node in a switching network system, the method includes: The first node obtains a target cell to be sent and a target time, where the target time is used to indicate the time when the target cell is processed by the first node, the upper-level node of the first node, or the initial node of the switching network system; The first node determines a delay transmission threshold for the target cell; When the difference between the system time and the target time is greater than the delay transmission threshold, the first node sends the target cell to a lower-level node.

2. The method according to claim 1, wherein The first node determines the delay transmission threshold for the target cell, including: The first node obtains the number of hops to the initial node in the switching network system; The first node determines the delay transmission threshold according to the number of hops, and the number of hops is positively correlated with the size of the delay transmission threshold.

3. The method according to claim 1, characterized in that The first node determines the delay transmission threshold for the target cell, including: The first node obtains the transmission delay to the lower-level node; The first node determines the delay transmission threshold according to the transmission delay, and the size of the transmission delay is positively correlated with the size of the delay transmission threshold.

4. The method according to claim 1, wherein The first node determines the delay transmission threshold for the target cell, including: The first node receives first congestion feedback information from the lower-level node, where the first congestion feedback information is used to indicate the first congestion degree of the lower-level node; The first node determines the delay transmission threshold according to the first congestion degree, and the level of the first congestion degree is positively correlated with the size of the delay transmission threshold.

5. The method according to any one of claims 1 to 4, characterized in that After the first node determines the delay transmission threshold for the target cell, the method further includes: The first node receives second congestion feedback information from the lower-level node, where the second congestion feedback information is used to indicate the second congestion degree of the lower-level node; The first node updates the delay transmission threshold according to the second congestion degree to obtain an updated delay transmission threshold, and the level of the second congestion degree is positively correlated with the size of the delay transmission threshold; When the difference between the system time and the target time is greater than the delay transmission threshold, the first node sends the target cell to a lower-level node, including: When the difference between the system time and the target time is greater than the updated delay transmission threshold, the first node sends the target cell to a lower-level node.

6. The method according to any one of claims 1 to 4, characterized in that The first node obtains a target cell to be sent and a target time, including: The first node obtains a message to be sent; The first node splits the message to be sent to obtain the target cell, and the target time is used to indicate the generation time of the target cell in the first node.

7. The method according to any one of claims 1 to 4, characterized in that, The first node obtains a target cell to be sent and a target time, including: The first node receives the target cell and the target time sent by the upper-level node, where the target time is used to indicate the time when the upper-level node receives the target cell, or the target time is used to indicate the time when the upper-level node sends the target cell, or the target time is used to indicate the time when the initial node in the switching network system generates the target cell, or the target time is used to indicate the time when the initial node in the switching network system sends the target cell.

8. The method according to any one of claims 1 to 4, characterized in that, The first node sending the target cell to the lower-level node includes: The first node sends the target cell and the target time to the lower-level node.

9. The method according to claim 8, characterized in that, The first node sending the target cell and the target time to the lower-level node includes: The first node updates the target time using the system time to obtain the updated target time; The first node sends the target cell and the updated target time to the lower-level node.

10. The method according to any one of claims 1 to 4, characterized in that The first node is a switching network interface chip FIC or a switching element SE, and the lower-level node is an FIC or an SE.

11. A communication device, characterized in that, The communication device is the first node in the switching network system, and the first node includes: An obtaining unit, configured to obtain a target cell and a target time to be sent, where the target time is used to indicate the time when the target cell is processed by the first node or the upper-level node of the first node or the initial node of the switching network system; A determining unit, configured to determine a delay transmission threshold of the target cell; A sending unit, configured to send the target cell to a lower-level node when the difference between the system time and the target time is greater than the delay transmission threshold.

12. The device according to claim 11, characterized in that, The determining unit is configured to: Obtain the number of hops to the initial node in the switching network system; Determine the delay transmission threshold according to the number of hops, and the number of hops is positively correlated with the magnitude of the delay transmission threshold.

13. The device according to claim 11, characterized in that, The determining unit is configured to: Obtain the transmission delay to the lower-level node; Determine the delay transmission threshold according to the transmission delay, and the magnitude of the transmission delay is positively correlated with the magnitude of the delay transmission threshold.

14. The device according to claim 11, wherein The determining unit is configured to: Receive first congestion feedback information from the lower-level node, where the first congestion feedback information is used to indicate the first congestion degree of the lower-level node; Determine the delay transmission threshold according to the first congestion degree, and the first congestion degree is positively correlated with the magnitude of the delay transmission threshold.

15. The device according to any one of claims 11 to 14, characterized in that, The device further includes: A receiving unit, configured to receive second congestion feedback information from the lower-level node, where the second congestion feedback information is used to indicate the second congestion degree of the lower-level node; An updating unit, configured to update the delay transmission threshold according to the second congestion degree to obtain the updated delay transmission threshold, and the second congestion degree is positively correlated with the magnitude of the delay transmission threshold; The sending unit is configured to: Send the target cell to the lower-level node when the difference between the system time and the target time is greater than the updated delay transmission threshold.

16. The device according to any one of claims 11 to 14, characterized in that The obtaining unit is configured to: Obtain a message to be sent; The to-be-sent message is segmented to obtain the target cell, and the target time is used to indicate the generation time of the target cell in the first node.

17. The device according to any one of claims 11 to 14, characterized in that The obtaining unit is configured to: Receive the target cell and the target time sent by the upper-level node, where the target time is used to indicate the time when the upper-level node receives the target cell, or the target time is used to indicate the time when the upper-level node sends the target cell, or the target time is used to indicate the time when the initial node in the switching network system generates the target cell, or the target time is used to indicate the time when the initial node in the switching network system sends the target cell.

18. The device according to any one of claims 11 to 14, characterized in that The sending unit is configured to: Send the target cell and the target time to the lower-level node.

19. The device according to claim 18, wherein The sending unit is configured to: Update the target time using the system time to obtain the updated target time; Send the target cell and the updated target time to the lower-level node.

20. The device according to any one of claims 11 to 14, characterized in that The first node is a switching network interface chip FIC or a switching unit SE, and the lower-level node is an FIC or an SE.

21. A computer-readable storage medium, characterized in that, Stores a program or instruction for implementing the method according to any one of claims 1 to 10.

22. A communication device, characterized in that, Includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a computer program or instruction so that the method according to any one of claims 1 to 10 is executed.

Images