Ultra fast private ring network protocol and method for switches

Abstract

The application provides a super-fast private ring network protocol and method for a switch, and belongs to the technical field of communication networks, and specifically comprises: a hardware control sublayer: arranged above a MAC layer and coupled with a forwarding logic of a switching chip, the hardware control sublayer continuously samples a physical link signal state of a ring network port through a target level hardware logic, and the hardware control sublayer sends a detection frame of a special target byte to the ring network based on a fixed period, so that fault detection is realized; and a preconfigured forwarding table: all nodes update their forwarding table states through hardware logic, an original blocked port is directly switched to a forwarding state by the hardware logic, and data flow is immediately forwarded according to a preconfigured backup link, so that the reliability of data communication processing in the ring network is improved.

Description

Technical Field

[0001] This invention belongs to the field of communication network technology, and in particular relates to an ultra-fast private ring network protocol and method for switches. Background Technology

[0002] Ethernet ring network topology is widely used in fields such as industrial automation, rail transportation, and smart grids due to its high reliability. When a link in the ring network fails, the redundancy protocol needs to quickly detect the fault and perform a switchover, transferring network traffic to the backup link to ensure uninterrupted service.

[0003] Existing technical bottlenecks: Current mainstream ring network protocols, such as ITU-T G.8032 (ERPS), typically implement the protocol state machine, fault detection, and link calculation in software. Their processing flow involves CPU interrupts, operating system scheduling, and software stack processing, leading to:

[0004] Slow fault detection: Relies on Hello messages at the second or millisecond level, resulting in large detection latency and slow failover speed; Software calculation and configuration updates take a long time, with the total self-healing time usually exceeding 50ms, leading to poor determinism; Software processing is susceptible to system load, causing network jitter and high bandwidth consumption; Protocol control frames are large, consuming valuable industrial network bandwidth.

[0005] Therefore, existing technologies are insufficient to meet the extreme real-time requirements of applications such as motion control, robot collaboration, and rail transit signaling systems, which are extremely sensitive to network interruption time (requiring self-healing time <10ms). Specifically, this application provides an ultra-fast private ring network protocol and method for switches. Summary of the Invention

[0006] To achieve the objectives of this invention, the following technical solution is adopted:

[0007] Specifically, this application provides an ultra-fast private ring network protocol for switches, which includes:

[0008] Hardware-based control sublayer: Located above the MAC layer and coupled with the forwarding logic of the switching chip;

[0009] The hardware-based control sublayer continuously samples the physical link signal status of the ring network ports through target-level hardware logic;

[0010] The hardware-based control sublayer sends specially designed target byte detection frames into the ring network at a fixed period to achieve fault detection.

[0011] Pre-configured forwarding table: During ring network initialization, the management software or controller pre-calculates the network topology and forwarding information and distributes it to the hardware forwarding table of the hardware control sublayer of each node. During normal operation of the ring network, the control sublayer logic blocks a preset port to prevent broadcast storms. When a fault is detected, the fault information is broadcast within the ring via hardware signals. All nodes update their forwarding table status through hardware logic, and the originally blocked port is directly switched to forwarding status by the hardware logic. Data traffic is immediately forwarded according to the pre-configured backup link.

[0012] The beneficial effects of this invention are as follows:

[0013] This application constructs a hardware-based ring network control sublayer within the data link layer. It achieves ≤2ms fault detection through 1GHz hardware sampling and 1ms micro-detection frames, and ≤5ms self-healing switching through a pre-configured forwarding table and FPGA hardware switching. The 32-byte simplified frame ensures bandwidth utilization of ≤0.3%, and the total self-healing time is ≤10ms (1 / 5 of the standard ERPS protocol). This invention overcomes the bottlenecks of traditional protocol cross-layer and software processing, meeting the demands of extreme real-time scenarios such as motion control and rail transit. It can be integrated into mainstream Ethernet switches, exhibiting strong compatibility and scalability.

[0014] Furthermore, the hardware-based control sublayer is implemented in an FPGA or integrated into the ASIC of the switching chip.

[0015] Furthermore, the target level is the 1GHz level.

[0016] Furthermore, based on a fixed period, detection frames with specially designed target bytes are sent into the ring network to achieve fault detection, specifically including:

[0017] The hardware-based control sublayer sends specially crafted 32-byte detection frames to the ring network at a fixed period of 1ms. If a port in the ring network does not receive a valid detection frame within two consecutive detection periods and its physical link status is also disconnected, the link is immediately determined to be faulty.

[0018] Furthermore, the detection frame includes the minimum necessary information, including the ring network ID, sequence number, and port status.

[0019] Furthermore, the detection frame includes the destination MAC address (multicast address), source MAC address, Ethernet type, protocol identifier, ring network ID, sequence number, status flag, and CRC.

[0020] Furthermore, the pre-configured forwarding table specifically includes:

[0021] During network initialization, the management software or controller pre-calculates the network topology and VLAN forwarding information and distributes it to the hardware forwarding table of the hardware control sublayer of each node.

[0022] Furthermore, the forwarding table includes complete forwarding information for the primary link and the backup link.

[0023] Secondly, this application provides a data processing method for an ultra-fast private ring network protocol for switches, applied to the aforementioned ultra-fast private ring network protocol for switches, specifically including:

[0024] The switching data in different links is obtained, and the setting and processing scheme of the hardware control sublayer is determined based on the runtime in different links.

[0025] Based on the setting processing scheme, the number of settings for the hardware control sublayer is determined, and based on the number of settings and the operating data in the current link, the switching control scheme between different hardware control sublayers is determined.

[0026] Based on the aforementioned switching control scheme, different hardware control sub-layers are used for switching control processing. Based on the switching processing data of the hardware control sub-layers in different links, the switching control scheme for the link when a fault is detected is determined.

[0027] Furthermore, the switching data in the link includes the number of times the link has switched to other links in history.

[0028] Furthermore, the runtime of the link is determined based on the interval between each switch to the link and the switch from the link to another link.

[0029] Furthermore, the method for determining the configuration processing scheme of the hardware control sublayer is as follows:

[0030] Based on the handover data in different links, determine the number of handovers between different links;

[0031] Based on the runtime in different links, determine the single runtime in different links;

[0032] The configuration and processing scheme of the hardware control sublayer is determined by using the average number of switching times and the average runtime of different links in history.

[0033] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0034] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0035] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0036] Figure 1 This is a framework diagram of an ultra-fast private ring network protocol for switches;

[0037] Figure 2 This is a flowchart of a data processing method for an ultra-fast private ring network protocol used in switches;

[0038] Figure 3 This is a flowchart illustrating the method for determining the configuration and processing scheme of the hardware control sublayer.

[0039] Figure 4 A flowchart illustrating the method for determining the switching control scheme between hardware control sublayers. Detailed Implementation

[0040] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0041] Example 1

[0042] like Figure 1 As shown, this application provides an ultra-fast private ring network protocol for switches, specifically including:

[0043] Hardware-based control sublayer: Located above the MAC layer and coupled with the forwarding logic of the switching chip;

[0044] The hardware-based control sublayer continuously samples the physical link signal status of the ring network ports through target-level hardware logic;

[0045] The hardware-based control sublayer sends specially designed target byte detection frames into the ring network at a fixed period to achieve fault detection.

[0046] Pre-configured forwarding table: During ring network initialization, the management software or controller pre-calculates the network topology and forwarding information and distributes it to the hardware forwarding table of the hardware control sublayer of each node. During normal operation of the ring network, the control sublayer logic blocks a preset port to prevent broadcast storms. When a fault is detected, the fault information is broadcast within the ring via hardware signals. All nodes update their forwarding table status through hardware logic, and the originally blocked port is directly switched to forwarding status by the hardware logic. Data traffic is immediately forwarded according to the pre-configured backup link.

[0047] Furthermore, the hardware-based control sublayer is implemented in an FPGA or integrated into the ASIC of the switching chip.

[0048] Furthermore, the target level is the 1GHz level.

[0049] Furthermore, based on a fixed period, detection frames with specially designed target bytes are sent into the ring network to achieve fault detection, specifically including:

[0050] The hardware-based control sublayer sends specially crafted 32-byte detection frames to the ring network at a fixed period of 1ms. If a port in the ring network does not receive a valid detection frame within two consecutive detection periods and its physical link status is also disconnected, the link is immediately determined to be faulty.

[0051] Furthermore, the detection frame includes the minimum necessary information, including the ring network ID, sequence number, and port status.

[0052] Furthermore, the detection frame includes the destination MAC address (multicast address), source MAC address, Ethernet type, protocol identifier, ring network ID, sequence number, status flag, and CRC.

[0053] Furthermore, the pre-configured forwarding table specifically includes:

[0054] During network initialization, the management software or controller pre-calculates the network topology and VLAN forwarding information and distributes it to the hardware forwarding table of the hardware control sublayer of each node.

[0055] Furthermore, the forwarding table includes complete forwarding information for the primary link and the backup link.

[0056] Furthermore, when a fault is detected, it specifically includes:

[0057] The nodes adjacent to the fault point immediately broadcast the fault information within the ring via hardware signals. The hardware-based control sublayers of all nodes (especially the node where the original blocked port was located) update their forwarding table status in parallel through hardware logic.

[0058] The original blocked port is directly switched to forwarding state by hardware logic within ≤5ms, and the data traffic is immediately forwarded according to the pre-configured backup link without the need for CPU and software to participate in link recalculation.

[0059] Example 2

[0060] Secondly, such as Figure 2 As shown, this application provides a data processing method for an ultra-fast private ring network protocol for switches, applied to the aforementioned ultra-fast private ring network protocol for switches, specifically including:

[0061] The switching data in different links is obtained, and the setting and processing scheme of the hardware control sublayer is determined based on the runtime in different links.

[0062] Based on the setting processing scheme, the number of settings for the hardware control sublayer is determined, and based on the number of settings and the operating data in the current link, the switching control scheme between different hardware control sublayers is determined.

[0063] Based on the aforementioned switching control scheme, different hardware control sub-layers are used for switching control processing. Based on the switching processing data of the hardware control sub-layers in different links, the switching control scheme for the link when a fault is detected is determined.

[0064] Furthermore, the switching data in the link includes the number of times the link has switched to other links in history.

[0065] Furthermore, the runtime of the link is determined based on the interval between each switch to the link and the switch from the link to another link.

[0066] In the following embodiments, the method analyzes two key indicators, link switching frequency and link stable running time, to determine how many hardware control sublayers need to be set up, thereby avoiding the technical problem of frequent switching between different links when a single hardware control sublayer experiences timing disorder.

[0067] Furthermore, such as Figure 3 As shown, the method for determining the configuration processing scheme of the hardware control sublayer is as follows:

[0068] S11 determines the number of handovers between different links based on handover data in different links;

[0069] In the above steps, the number of switching times refers to the number of times the device switches from one link to another.

[0070] S12 determines the single runtime in different links based on the runtime in different links;

[0071] In the above steps, the duration of a single run is the interval from the start of switching to a certain link until the next switch away from that link.

[0072] S13 uses the average number of handovers between different links in history and the average duration of a single run to determine the configuration and processing scheme of the hardware control sublayer.

[0073] Specifically, the single runtime is the interval between each switch to the link and the switch from the link to another link.

[0074] It is understandable that the configuration and processing scheme of the hardware control sublayer is determined by utilizing the number of handovers between different links in history and the duration of a single run, specifically including:

[0075] Obtain the number of handovers between different links in history, and determine whether there are any links whose number of handovers to other links exceeds a preset handover threshold. If yes, proceed to the next step; otherwise, determine that the hardware control sublayer setting scheme is to set one hardware control sublayer.

[0076] Specifically, the above steps are essentially the initial screening (based on switching frequency): Judgment: Check if there are any links among all links that have switched to other links more than the "preset switching number threshold". Result: If not (i.e. all links are very stable and rarely switch), then the simplest solution is adopted: set only 1 hardware control sublayer.

[0077] Links that switch to other links more than a preset switching number threshold are identified as frequently switched links. It is then determined whether the number of frequently switched links is greater than a preset link number threshold. If so, the hardware control sublayer setting process is determined to set a preset number of hardware control sublayers. If not, proceed to the next step.

[0078] In the above steps, frequently switching links are identified: if links switch frequently, these links are marked as "frequently switching links." The number of hardware control sublayers is determined by identifying the frequency of switching (based on the number of frequent links): Specifically, it is checked whether the number of "frequently switching links" exceeds the "preset link number threshold." Result: If so, it indicates that the overall system switches very frequently, requiring strong hardware support. Therefore, it is decided to set a larger number of hardware control sublayers, i.e., the "preset number."

[0079] The single runtime of different links is used to determine whether there are links whose single runtime is less than a preset runtime threshold. If so, proceed to the next step; otherwise, determine that the hardware control sublayer setting scheme is to set a second preset number of hardware control sublayers.

[0080] The above steps are essentially a secondary screening (based on runtime): if the number of frequent links is not large, then further judgment is made from the perspective of operational stability: check whether there are any links among all links whose "single runtime" is lower than the "preset runtime threshold" (i.e. those unstable links that are switched in but quickly leave).

[0081] Result: If none is found, it indicates that although the link switches frequently, its runtime is relatively long once it is in use. In this case, setting a moderate number of hardware control sublayers is sufficient, i.e., the "second preset number".

[0082] The system identifies links whose single runtime is less than a preset runtime threshold. Based on the sum of the number of links with single runtimes less than the preset runtime threshold and the number of frequently switched links, it determines the total number. It then determines whether the total number is greater than a preset number threshold. If so, it determines that the hardware control sublayer setting scheme is to set a preset number of hardware control sublayers. If not, it determines that the hardware control sublayer setting scheme is to set a second preset number of hardware control sublayers.

[0083] Specifically, in the above steps, the operational status of the links is evaluated by comprehensively summarizing the links with frequent switching and those with short running times. Then, the number of hardware control sub-layers is determined accordingly. Specifically, if there are both links with frequent switching and links with short running times, these two types of links are summarized. The total number of these two types of links is calculated, and it is determined whether the total number exceeds the "preset number threshold".

[0084] Result: Total quantity exceeds threshold -> adopt aggressive approach: set "preset quantity"; Quantity does not exceed threshold -> adopt conservative approach: set "second preset quantity".

[0085] It should be noted that the preset quantity is greater than the second preset quantity, and both are greater than 1.

[0086] In a possible specific embodiment, assume a system has 5 links (Link A, B, C, D, E), and its historical data is as follows:

[0087] Switching frequency: Link A -> other links: 120 times / hour; Link B -> other links: 150 times / hour; the switching frequency for other links is less than 100 times.

[0088] Single run duration: The minimum single run duration for Link C is 20 minutes; the minimum single run duration for Link D is 40 minutes; all other links have a duration greater than 50 minutes.

[0089] Decision-making process simulation:

[0090] Identify frequently switching links: Link A (120>100) and Link B (150>100) are "frequently switching links". If they exist, proceed to the next step.

[0091] Determine the number of frequent links: There are 2 frequent links (A and B), which is no more than the threshold of 3. Proceed to the next step.

[0092] Determine short-running links: Link C (30 minutes < 50 minutes) and Link D (40 minutes < 50 minutes) are "links with a single run duration less than the threshold". If they exist, proceed to the next step.

[0093] Calculate the total quantity and determine:

[0094] The total number = frequently switched links (A, B) + short-running links (C, D) = 4. The total number of 4 is greater than the preset number threshold of 3. Therefore, the solution is to set the preset number, that is, 4 hardware control sublayers. Conclusion: Based on this historical data, the final hardware control sublayer setting scheme of this system is 4. If it is not greater than 3, the hardware control sublayer setting scheme is determined to be 3.

[0095] In the following embodiments, given that N hardware-based control sublayers need to be configured, the decision on how to switch between them is based on two factors: 1. The number of hardware-based control sublayers configured; 2. Abnormal situations such as the loss of detection frames at each port on the link, where the detection frame is a heartbeat or probe data packet used to monitor the status of a port or link; the deviation moment is the moment when a port fails to successfully receive the expected detection frame. This typically indicates that the link may experience delays, congestion, or failures; the deviation port is the port that has experienced at least one "deviation moment".

[0096] Specifically, such as Figure 4 As shown, the method for determining the switching control scheme between the hardware control sublayers is as follows:

[0097] S21 determines the acquisition data of the detection frames of the ports in the link based on the operating data in the current link;

[0098] S22 determines the times when different ports in the link fail to acquire detection frames based on the acquired data, and uses these times as the acquisition deviation times;

[0099] S23 determines the switching control scheme between the hardware control sublayers based on the acquisition deviation time data of different ports in the link and the number of hardware control sublayers set.

[0100] Furthermore, step S23 also includes the following:

[0101] Specifically, based on the acquisition deviation time data of different ports in the link and the number of settings of the hardware control sublayer, the switching control scheme between the hardware control sublayers is determined, including:

[0102] Case 1: When the number of hardware control sub-layers is 1, it is determined that there is no need to switch control processes between the hardware control sub-layers;

[0103] Specifically, the number is set to 1. The logic is: since there is only one hardware control sub-layer, there is no switching "between". The solution is to directly determine "no switching control processing is required".

[0104] Case 2: When the number of hardware control sublayers is the second preset number, the switching control scheme between the hardware control sublayers is determined to be a switching control process performed according to a preset time period, or when the number of ports with newly added acquisition deviation times in the link is greater than the preset port number threshold, switching control process is performed between different hardware control sublayers.

[0105] Specifically, the number is set to a "second preset number" (relatively small), ensuring sufficient system resources (few sub-layers) to withstand relatively frequent switching overhead, and the number of backup hardware control sub-layers is also relatively small. A fixed, relatively long switching cycle is used to balance load and performance. Furthermore, to prevent unexpected situations, when the number of ports with newly added acquisition deviations in the link exceeds a preset port number threshold, switching control processing is performed between different hardware control sub-layers.

[0106] Default behavior: Perform switching control processing according to the preset time period. Triggering behavior: When the number of ports with newly added acquisition deviation times in the link exceeds the preset port number threshold, switch control processing will be performed immediately.

[0107] Case 3: When the number of hardware control sublayers is the second preset number, the acquisition deviation time data of different ports in the link is obtained, and it is determined whether there is an acquisition deviation time for different ports in the link. If yes, proceed to the next step; if no, determine that the switching control scheme between the hardware control sublayers is to perform switching control processing between different hardware control sublayers when any port in the link adds an acquisition deviation time.

[0108] In the above steps, the quantity is set to a "preset quantity" (relatively small). System resources are limited (few sub-layers). At this point, the switching strategy needs to be determined based on the system's health. If the system is healthy, a slower switching frequency is used to save costs; if the system malfunctions, a faster switching frequency is needed to handle the fault.

[0109] Judgment 1: Check all ports to see if there is an acquisition deviation moment (i.e., whether a port has lost a detection frame). If not (the system is healthy): adopt a conservative strategy and switch at a slower frequency. That is, determine that the switching control scheme between the hardware control sublayers is to perform switching control processing between different hardware control sublayers when any port in the link adds an acquisition deviation moment.

[0110] If (system malfunction): Judgment 2: Check if the number of "obtain deviation ports" exceeds the "preset deviation port number threshold". If not (only a few ports are abnormal): still adopt the conservative "determine the switching control scheme between the hardware control sublayers. When any port in the link adds a new time to obtain deviation, then perform switching control processing between different hardware control sublayers. If (a large number of ports are abnormal, the problem may be more serious): adopt a more aggressive "preset time period" for switching to mobilize resources to deal with the problem more quickly.

[0111] The port with the acquisition deviation time is designated as the acquisition deviation port. It is determined whether the number of acquisition deviation ports in the link is greater than a preset deviation port number threshold. If so, the switching control scheme between the hardware control sublayers is determined to be switching control processing according to a preset time period. Alternatively, if the number of newly acquired deviation times in the link is greater than the preset port number threshold, switching control processing is performed between different hardware control sublayers. If not, the switching control scheme between the hardware control sublayers is determined to be switching control processing between different hardware control sublayers when any port in the link acquires a new deviation time.

[0112] It should be noted that the newly added acquisition deviation moment of a port refers to the moment when, during the operation of the system, a port changes from the state of "normal acquisition of detection frames" to "failed to acquire the expected detection frames" after the most recent acquisition deviation moment, and this single event is recorded by the monitoring system.

[0113] In one possible embodiment, case 3: the quantity is set to a "second preset quantity" (less, such as 3).

[0114] Solution: Hybrid mode (periodic switching + event-driven triggering), default behavior: switching according to a preset time period (30 minutes), trigger behavior: when the number of ports with newly added acquisition deviations in the link exceeds the preset port number threshold (2), switching will be performed immediately.

[0115] Example: Scenario: The system is configured with two hardware control sublayers (HCS-A, HCS-B). Decision: Regardless of the system's historical health status, the hybrid mode is directly adopted.

[0116] Execution: Normal operation: The system cycles between HCS-A and HCS-B every 30 minutes. Abnormal occurrence: At a certain moment, the monitoring system simultaneously detects that 3 ports have added acquisition deviation times. System response: Since the number of newly added abnormal ports (3) is greater than the threshold (2), the system immediately performs a switch (e.g., forced switch from HCS-A to HCS-B) without waiting for the current 20-minute cycle to end. Under limited resources, basic reliability is ensured through relatively slow cycle switching, and a rapid response is made to attempt recovery in the event of a serious concurrent failure.

[0117] Table 1 Scheme Patterns under Different Circumstances

[0118]

[0119] Furthermore, based on the aforementioned switching control scheme, switching control processing for different hardware-based control sub-layers is performed, specifically including:

[0120] The switching control process of different hardware control sub-layers is performed according to the switching control process cycle corresponding to the switching control scheme.

[0121] The link switching control scheme decision logic, in the following steps, describes how the system determines the strategy for switching to the current link when other links fail. The decision is based on two core metrics:

[0122] Hardware control sublayer usage time: The average working time of each sublayer on this link; Number of switching processes between hardware control sublayers: The number of times switching occurs between sublayers on this link.

[0123] The decision-making process is divided into two main branches based on the sub-layer switching control scheme adopted by the link itself.

[0124] Furthermore, the method for determining the link switching control scheme is as follows:

[0125] S41 uses the switching processing data of the hardware control sublayer in different links to determine the number of switching processes between the hardware control sublayers in different links.

[0126] S42 determines the usage duration of different hardware control sublayers in the link based on the number of switching processes between hardware control sublayers in the link.

[0127] S43 determines the link switching control scheme when the determined link fails, based on the usage time of different hardware control sublayers in different links and the number of switching processes between hardware control sublayers.

[0128] Branch 1: When the sublayer handover scheme for this link is "hybrid mode":

[0129] Furthermore, based on the usage duration of different hardware control sublayers in different links and the number of switching processes between hardware control sublayers, a link switching control scheme is determined when a link failure is detected, specifically including:

[0130] S431 If the switching control scheme between the hardware control sublayers is to perform switching control processing according to a preset time period, or if the number of ports in the link that have newly acquired deviation time is greater than a preset port number threshold, then when performing switching control processing between different hardware control sublayers, the usage time of different hardware control sublayers in the link is obtained, and it is determined whether the usage time of different hardware control sublayers in the link is greater than a preset duration threshold. If yes, proceed to the next step; if no, it is determined that when the link fails in other links, the switching processing scheme of the link is to switch to the link according to a preset period, that is, when the preset period is reached and other links fail, then switch to the link.

[0131] In the above steps, determine the usage time of the sublayer. Determine: In this link, has the usage time of all hardware control sublayers in the most recent month exceeded the preset duration threshold (150 hours)? If not (indicating that the verification reliability of different links is not good): adopt a conservative approach. The approach is to switch to this link according to the preset cycle (i.e., switch to this link only when 24 hours have been reached and other links have failed). If yes (all sublayers have been fully verified and processed): proceed to the next step.

[0132] S432 obtains the number of switching processes between different hardware control sublayers in the link, and determines whether the number of switching processes between different hardware control sublayers in the link is greater than a preset switching process threshold. If not, proceed to the next step. If yes, determine the link switching process scheme when other links fail, which is to switch to the link according to a preset period, that is, when the preset period is reached and other links fail, switch to the link.

[0133] S432. Determine the number of sublayer handovers. Determine: Does the number of handover processes between sublayers in this link exceed the preset handover process threshold (27 times / day)? If yes (the handover is too frequent, and the link may be unstable): adopt a conservative approach. If no (the handover frequency is normal and the link is stable): proceed to the next step.

[0134] Based on the usage time of different hardware control sublayers in the link, S433 uses the link with the shortest average usage time in the link as the target for link switching control when the other links fail.

[0135] In the above steps, the switching target (proactive solution) strategy is determined: this link is set as the priority switching target, all candidate links are compared, and the link with the shortest average usage time of the hardware control sublayer is selected as the preferred switching target when a failure occurs.

[0136] Furthermore, if the switching control scheme between the hardware control sublayers is to perform switching control processing between different hardware control sublayers when any port in the link adds a new acquisition deviation time, it is determined whether the number of switching processes between different hardware control sublayers in the link is greater than a preset switching process number threshold. If not, proceed to the next step. If yes, it is determined that when the link fails in other links, the switching processing scheme of the link is to switch to the link according to a preset period, that is, when the preset period is reached and other links fail, the link is switched to the link.

[0137] The link with the fewest switching processes between different hardware control sublayers in the link is used as the switching control target when the other links fail.

[0138] Branch 2: When the sublayer switching scheme of this link is "pure event-triggered mode" (i.e., when any port adds a deviation, switch immediately), determine: Does the number of switching processes between sublayers in this link exceed the preset switching process threshold (3 times / day)? If yes (too many event triggers, the link may be extremely unstable): adopt a conservative scheme: switch to this link according to the preset cycle. If no (event triggers are within a reasonable range): determine the switching target (aggressive scheme): set this link as the priority switching target. Method: compare all candidate links and use the link with the fewest hardware-controlled sublayer switching processes as the preferred switching target when a fault occurs.

[0139] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0140] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0141] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A data processing method for an ultra-fast private ring network protocol used in switches, characterized in that, Specifically, it includes: Hardware-based control sublayer: Located above the MAC layer and coupled with the forwarding logic of the switching chip; The hardware-based control sublayer continuously samples the physical link signal status of the ring network ports through target-level hardware logic; The hardware-based control sublayer sends specially designed target byte detection frames into the ring network at a fixed period to achieve fault detection. Pre-configured forwarding table: During ring network initialization, the management software or controller pre-calculates the network topology and forwarding information and distributes it to the hardware forwarding table of the hardware control sublayer of each node. During normal operation of the ring network, the control sublayer logic blocks a preset port to prevent broadcast storms. When a fault is detected, the fault information is broadcast within the ring via hardware signals. All nodes update their forwarding table status through hardware logic, and the originally blocked port is directly switched to forwarding status by the hardware logic. Data traffic is immediately forwarded according to the pre-configured backup link. The switching data in different links is obtained, and the setting and processing scheme of the hardware control sublayer is determined based on the runtime in different links. Based on the setting processing scheme, the number of settings for the hardware control sublayer is determined, and based on the number of settings and the operating data in the current link, the switching control scheme between different hardware control sublayers is determined. Based on the aforementioned switching control scheme, different hardware-based control sub-layers are used for switching control processing. Based on the switching processing data of the hardware-based control sub-layers in different links, the switching control scheme of the link is determined when other links fail.

2. The data processing method for the ultra-fast private ring network protocol for switches as described in claim 1, characterized in that, The hardware-based control sublayer is implemented in an FPGA or integrated into the ASIC of the switching chip.

3. The data processing method for the ultra-fast private ring network protocol for switches as described in claim 1, characterized in that, The target level is 1GHz.

4. The data processing method for the ultra-fast private ring network protocol for switches as described in claim 1, characterized in that, Based on a fixed period, detection frames with specially designed target bytes are sent into the ring network to achieve fault detection, specifically including: The hardware-based control sublayer sends specially crafted 32-byte detection frames to the ring network at a fixed period of 1ms. If a port in the ring network does not receive a valid detection frame within two consecutive detection periods and its physical link status is also disconnected, the link is immediately determined to be faulty.

5. The data processing method for the ultra-fast private ring network protocol for switches as described in claim 1, characterized in that, The detection frame includes the minimum necessary information, including the ring network ID, sequence number, and port status.

6. The data processing method for the ultra-fast private ring network protocol for switches as described in claim 1, characterized in that, The pre-configured forwarding table specifically includes: During network initialization, the management software or controller pre-calculates the network topology and VLAN forwarding information and distributes it to the hardware forwarding table of the hardware control sublayer of each node.

7. The data processing method for the ultra-fast private ring network protocol for switches as described in claim 6, characterized in that, The forwarding table includes complete forwarding information for both the primary and backup links.

8. The data processing method for the ultra-fast private ring network protocol for switches as described in claim 1, characterized in that, When a fault is detected, it specifically includes: The nodes adjacent to the fault point immediately broadcast the fault information within the ring via hardware signals, and the hardware-based control sublayers of all nodes update their forwarding table status in parallel through hardware logic. The original blocked port is directly switched to forwarding state by hardware logic within ≤5ms, and the data traffic is immediately forwarded according to the pre-configured backup link without the need for CPU and software to participate in link recalculation.

9. The data processing method for the ultra-fast private ring network protocol for switches as described in claim 1, characterized in that, The method for determining the handover control scheme for the link is as follows: The number of handover processes between hardware control sublayers in different links is determined by the handover processing data of the hardware control sublayers in different links. Based on the number of switching processes between hardware control sublayers in the link, the usage time of different hardware control sublayers in the link is determined. Based on the usage duration of different hardware control sublayers in different links and the number of switching processes between hardware control sublayers, the switching control scheme of the link is determined when other links fail.

Images