Service switching method, device, equipment and readable storage medium

Abstract

A service switching method, device and equipment and readable storage medium, the service switching method comprises: in each protection period, for each machine disk, when the machine disk receives multicast traffic from the backup root node as an entry machine disk, judging whether there is a machine disk receiving multicast traffic from the main root node as an entry machine disk in the distributed device; if there is a machine disk receiving multicast traffic from the main root node as an entry machine disk, the received multicast traffic from the backup root node is discarded; if there is no machine disk receiving multicast traffic from the main root node as an entry machine disk, the received multicast traffic from the backup root node is forwarded to the switching network of the distributed device. Through the present application, compared with switching based on IGP protocol to detect link state, the service switching time can be greatly shortened, and BFD for BIER is not needed, avoiding the compatibility problem of device interconnection.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a service switching method, apparatus, device, and readable storage medium. Background Technology

[0002] Short videos, live TV, HD video-on-demand, and virtual reality are the main application scenarios of operators' bearer networks. One of the key technologies for these video services is the multicast technology of the bearer network equipment and the protection technology for multicast services. Only sufficiently efficient packet replication capabilities and sufficiently fast protection switching times can support smooth HD video playback.

[0003] BIER (Bit Index Explicit Replication) is a novel multicast technology designed to address the problems of high network traffic consumption and low processing efficiency caused by the multicast tree state in traditional multicast technologies. (See reference...) Figure 1 , Figure 1 A schematic diagram of a typical network model for BIER dual-root protection is shown below. Figure 1 As shown, multicast traffic is forwarded simultaneously along the primary and backup links. When the links are normal, leaf node PE1 will prioritize receiving primary tunnel traffic with primary root node Root1 as BFIR (Bit Forwarding Ingress Router) and discard backup tunnel traffic with backup root node Root2 as BFIR. When primary root node Root1 or the primary tunnel link fails, leaf node PE1 will switch to receiving backup tunnel traffic with backup root node Root2 as BFIR, thereby realizing the protection switchover of multicast services.

[0004] Currently, tunnel path failures are typically detected based on IGP (Internal Gateway Protocol) or BFD (Bidirectional Forwarding Detection) for BIER, and then service failover is performed when a failure is detected. However, service failover time based on IGP to detect the reachability of service paths can reach the second level, and the service failover time in the case of root node failure can even be as long as half a minute. While BFD for BIER can achieve millisecond-level fault detection, thus significantly shortening the service failover time, BFD for BIER is still in the draft stage, and there are interoperability issues between devices from different manufacturers.

[0005] In summary, current BIER dual-root protection networks exhibit low protection switching efficiency based on IGP, while protection switching based on BFD for BIER faces application obstacles. Summary of the Invention

[0006] This application provides a service switching method, apparatus, device, and readable storage medium, aiming to solve the technical problems of low efficiency of IGP-based protection switching and application obstacles of BFD-based protection switching in current BIER dual-root protection networks.

[0007] In a first aspect, embodiments of this application provide a service failover method applied to leaf nodes of a dual-root protection network, wherein the leaf node is a distributed device, the distributed device comprising multiple hard drives, and the service failover method includes:

[0008] In each protection cycle, for each disk, when the disk as the ingress disk receives multicast traffic from the backup root node, it is determined whether there is a disk in the distributed device that is the ingress disk receiving multicast traffic from the primary root node.

[0009] If there is a disk that receives multicast traffic from the primary root node as an ingress disk, then the multicast traffic received from the backup root node will be discarded.

[0010] If there is no server board that receives multicast traffic from the primary root node as the entry server board, the multicast traffic received from the backup root node will be forwarded to the switching network of the distributed devices.

[0011] Optionally, when the primary root node receives multicast traffic from the backup root node as the entry node, determining whether there is a primary root node in the distributed device that has received multicast traffic from the main root node as the entry node includes:

[0012] When a disk acts as an ingress disk and receives multicast traffic from a backup root node, the system determines whether there is a disk in the distributed device that acts as an ingress disk and receives multicast traffic from a primary root node based on the first and second traffic flags of the disk.

[0013] Specifically, the first traffic tag of each disk is marked when the disk, as the ingress disk, receives multicast traffic from the primary root node. The second traffic tag of each disk is updated according to the first traffic tag sent by other disks when the disk receives the first traffic tag sent by other disks. After sending the first traffic tag to other disks, each disk unmarks the first traffic tag and the second traffic tag of the disk.

[0014] Optionally, the protection period duration is determined based on the duration of canceling all traffic markers, the duration of setting the first traffic marker, and the duration of updating the second traffic marker.

[0015] Optionally, each chassis includes a chip, and the protection cycle duration is determined based on the duration of canceling all traffic markers, the duration of setting the first traffic marker, and the duration of updating the second traffic marker, including:

[0016] The duration for canceling all traffic tags is calculated based on the number of all traffic tags, chip processing performance, and the performance ratio allocated to canceling traffic tags.

[0017] The duration for setting the first traffic marker is calculated based on the number of first traffic markers on the server board and the peak value of multicast traffic ingress.

[0018] The time required to update the second traffic tag is calculated based on the number of first traffic tags on the chassis, the chip processing performance, and the performance ratio allocated to forwarding the first traffic tags.

[0019] The protection period duration is calculated by summing the duration of canceling all traffic markers, the duration of setting the first traffic marker, and the duration of updating the second traffic marker.

[0020] Optionally, before calculating the duration for setting the first traffic marker based on the number of first traffic markers on the server and the peak value of multicast traffic ingress, the following steps are included:

[0021] The peak value of multicast traffic ingress is calculated based on the stable bandwidth threshold of the chassis slot, the chip processing performance, and the performance ratio allocated to cancel traffic marking.

[0022] Optionally, the sum of the performance ratio allocated to canceling traffic marking and the performance ratio allocated to forwarding the first traffic marking is 1. In each protection cycle, for each disk, before determining whether there is a disk in the distributed device that has received multicast traffic from the primary root node as an ingress disk when the disk, as an ingress disk, receives multicast traffic from the backup root node, the following steps are included:

[0023] By adjusting the performance ratio allocated to canceling traffic tags and the performance ratio allocated to forwarding the first traffic tag, experiments were conducted on the dual-root protection network to obtain the corresponding relationship between different protection cycle durations and performance ratios.

[0024] Based on the correspondence between different protection cycle durations and performance ratios, the optimal range of performance ratio values ​​is determined.

[0025] Optionally, the process of each hard drive unmarking the first and second traffic markers after sending the first traffic marker to other hard drives includes:

[0026] The number of cycles in the protection period is counted. When the number of cycles is an even multiple, each disk will unmark the first and second traffic tags after sending the first traffic tag to other disks.

[0027] Secondly, embodiments of this application provide a service switching device applied to a leaf node of a dual-root protection network, wherein the leaf node is a distributed device, the distributed device comprising multiple hard drives, and the service switching device includes:

[0028] The judgment module is used to determine, in each protection cycle, for each disk, whether there is a disk in the distributed device that has received multicast traffic from the primary root node as an ingress disk when the disk as an ingress disk receives multicast traffic from the backup root node.

[0029] The discard module is used to discard multicast traffic received from the backup root node if there is a disk that receives multicast traffic from the primary root node as an ingress disk.

[0030] The switching module is used to forward the multicast traffic received from the backup root node to the switching network of the distributed devices if there is no disk that receives multicast traffic from the primary root node as the entry disk.

[0031] Thirdly, embodiments of this application provide a service switching device, which includes a processor, a memory, and a service switching program stored in the memory and executable by the processor, wherein when the service switching program is executed by the processor, it implements the steps of the service switching method as described above.

[0032] Fourthly, embodiments of this application provide a readable storage medium storing a service switching program, wherein when the service switching program is executed by a processor, it implements the steps of the service switching method as described above.

[0033] The beneficial effects of the technical solutions provided in this application include:

[0034] In this embodiment of the application, during each protection cycle, for each disk, when the disk as the ingress disk receives multicast traffic from the backup root node, it is determined whether there is a disk in the distributed device that is also an ingress disk receiving multicast traffic from the primary root node; if there is a disk as an ingress disk receiving multicast traffic from the primary root node, the received multicast traffic from the backup root node is discarded; if there is no disk as an ingress disk receiving multicast traffic from the primary root node, the received multicast traffic from the backup root node is forwarded to the switching network of the distributed device. This application embodiment addresses the scenario where the leaf nodes of a BIER dual-root protection network are distributed devices. Each disk in the distributed device can act as an ingress disk to receive multicast traffic from the primary root and / or backup root nodes. When the multicast traffic link of the primary root node is normal, primary root traffic is prioritized, and backup root traffic is discarded. When the multicast traffic link of the primary root node fails, backup root traffic is selected. Therefore, for each disk acting as an ingress disk receiving multicast traffic from the backup root node, the system determines whether there is a disk in the distributed device acting as an ingress disk receiving multicast traffic from the primary root node, and then decides whether to discard or forward the backup root traffic. Thus, for distributed devices with multiple disks, it enables rapid detection of primary root traffic failures and rapid switching of backup root traffic within the protection period. Compared to switching based on IGP protocol link status detection, this significantly shortens service switching time and eliminates the need for BFD forBIER, avoiding compatibility issues related to device interoperability. Attached Figure Description

[0035] Figure 1 A schematic diagram of a typical network model for BIER dual-root protection;

[0036] Figure 2 This is a flowchart illustrating one embodiment of the business switching method of this application;

[0037] Figure 3 This is a schematic representation of the disk traffic marking in one embodiment of the service switching method of this application;

[0038] Figure 4 This is a schematic diagram of cross-disk forwarding of the primary root traffic tag table of this application, representing an embodiment of the service failover method of this application.

[0039] Figure 5 This diagram illustrates the correspondence between different protection period durations and performance ratios in one embodiment of the service switching method of this application.

[0040] Figure 6 This is a schematic diagram of the functional modules of an embodiment of the service switching device of this application;

[0041] Figure 7This is a schematic diagram of the hardware structure of the service switching equipment involved in the embodiments of this application. Detailed Implementation

[0042] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0043] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0044] Firstly, embodiments of this application provide a service switching method.

[0045] In one embodiment, the leaf nodes applied to the dual-root protection network are distributed devices, which include multiple hard drives, as shown in the figure. Figure 2 , Figure 2 This is a flowchart illustrating an embodiment of the business switching method of this application, as shown below. Figure 2 As shown, the business failover methods include:

[0046] Step S10: In each protection cycle, for each disk, when the disk as the ingress disk receives multicast traffic from the backup root node, determine whether there is a disk in the distributed device that is the ingress disk receiving multicast traffic from the primary root node.

[0047] In this embodiment, the leaf nodes applied to the dual-root protection network are distributed devices. Under normal link conditions, upstream multicast traffic is sent to the distributed devices through the primary root node and the backup root node, respectively, corresponding to primary root traffic and backup root traffic. The distributed devices include chassis with multiple slots, one of which is a disk. Any disk can be either an ingress disk or an egress disk. The disk that receives multicast traffic is the ingress disk, and the egress disk forwards the multicast traffic to the next network node. Taking a protection period of T as an example, fault detection of primary root traffic is performed in each period of T. If a primary root traffic fault is detected, the system switches to backup root traffic; otherwise, primary root traffic is forwarded first, and backup root traffic is discarded. For each disk in the distributed device, when the disk, acting as the entry disk, receives multicast traffic, parsing the BIER header of the multicast packet yields the multicast traffic ID and determines whether the multicast traffic originates from the primary root node or the backup root node. If the multicast traffic originates from the primary root node, it indicates that the primary root traffic is functioning correctly, requiring no further detection or judgment. In this case, the primary root traffic is forwarded first, meaning the multicast traffic from the primary root node is forwarded to the distributed device's switching network. If the multicast traffic originates from the backup root node, it is necessary to further determine whether there is a disk in the distributed device that is acting as the entry disk and receiving multicast traffic from the primary root node, in order to decide whether to discard or forward the backup root traffic.

[0048] Step S20: If there is a disk that receives multicast traffic from the primary root node as an ingress disk, then the multicast traffic received from the backup root node will be discarded.

[0049] In this embodiment, if a disk in the distributed device receives multicast traffic from the backup root node as the entry disk, and another disk in the distributed device receives multicast traffic from the primary root node as the entry disk, it indicates that the primary root traffic is fault-free. In this case, the distributed device should prioritize the multicast traffic from the primary root node, i.e., the primary root traffic, and discard the multicast traffic from the backup root node, i.e., the backup root traffic.

[0050] Step S30: If there is no server board that receives multicast traffic from the primary root node as an entry server board, then forward the multicast traffic received from the backup root node to the switching network of the distributed device.

[0051] In this embodiment, when a primary root node multicast traffic is received by an input disk as the primary root node, if no other disk in the distributed device receives multicast traffic from the primary root node, it indicates a failure in the primary root traffic. In this case, the distributed device needs to switch to the secondary root traffic, forwarding the received multicast traffic from the secondary root node to the distributed device's switching network. This achieves service failover for multicast traffic, enabling rapid detection of primary root traffic failures and rapid switching of secondary root traffic within the protection period, even when the distributed device has multiple disks. The switching network of the distributed device refers to the physical connection between the disks within the distributed device, used to enable internal forwarding between disks.

[0052] In this embodiment, the leaf nodes applied to the dual-root protection network are distributed devices. Under normal link conditions, upstream multicast traffic is sent to the distributed devices via the primary root node and backup root node, corresponding to primary root traffic and backup root traffic respectively. During each protection cycle, for each disk in the distributed devices, when the disk acts as an ingress disk and receives multicast traffic, the BIER header of the multicast packet is parsed to obtain the multicast traffic ID and determine whether the multicast traffic originates from the primary root node or the backup root node. If the multicast traffic originates from the primary root node, it indicates that the primary root traffic is not faulty and no further detection or judgment is needed. If the multicast traffic originates from the backup root node, further judgment is needed to determine whether any distributed devices, acting as ingress disks, receive multicast traffic from the primary root node. If a distributed device receives multicast traffic from the primary root node, and another disk in the distributed device acts as the entry disk, it indicates that the primary root traffic is not faulty. In this case, the distributed device should prioritize the multicast traffic from the primary root node (i.e., primary root traffic) and discard the multicast traffic from the backup root node (i.e., backup root traffic). If no other disk in the distributed device acts as the entry disk and receives multicast traffic from the primary root node, it indicates that the primary root traffic has failed. In this case, the distributed device needs to switch to the backup root traffic, forwarding the received multicast traffic from the backup root node to the distributed device's switching network. This achieves service failover for multicast traffic. Therefore, for distributed devices with multiple disks, it enables rapid detection of primary root traffic failures and rapid switching of backup root traffic within the protection period. Compared to switching based on link status detection using the IGP protocol, this significantly shortens the service failover time and eliminates the need for BFD for BIER, avoiding compatibility issues related to device interoperability.

[0053] Further, in one embodiment, when the primary root node receives multicast traffic as an ingress node, determining whether there is a primary root node in the distributed device that has received multicast traffic as an ingress node includes:

[0054] When a disk acts as an ingress disk and receives multicast traffic from a backup root node, the system determines whether there is a disk in the distributed device that acts as an ingress disk and receives multicast traffic from a primary root node based on the first and second traffic flags of the disk.

[0055] Specifically, the first traffic tag of each disk is marked when the disk, as the ingress disk, receives multicast traffic from the primary root node. The second traffic tag of each disk is updated according to the first traffic tag sent by other disks when the disk receives the first traffic tag sent by other disks. After sending the first traffic tag to other disks, each disk unmarks the first traffic tag and the second traffic tag of the disk.

[0056] In this embodiment, specifically, refer to... Figure 3 , Figure 3 This is a schematic representation of the disk traffic marking in one embodiment of the service switching method of this application, such as... Figure 3 As shown, each disk stores three traffic tagging tables, such as the local primary root traffic tagging table, the local backup root traffic tagging table, and the cross-disk primary root traffic tagging table. These can be used for each multicast traffic ID (i.e.,...). Figure 3 The MCID in the table uses 1 / 0 to mark the presence or absence of traffic, with each mark occupying 1 bit. The local disk primary root traffic mark table stores the first traffic mark, used to mark multicast traffic received from the primary root node when the disk acts as the entry point, marking the multicast ID corresponding to the multicast traffic as 1. The local disk backup root traffic mark table is used to mark multicast traffic received from the backup root node when the disk acts as the entry point, marking the multicast traffic ID corresponding to the multicast traffic as 1. The cross-disk primary root traffic mark table stores the second traffic mark. When a disk receives a local root traffic flag from another disk, it updates its own cross-disk root traffic flag based on the local root traffic flag from the other disk. When using 1 / 0 to mark the presence or absence of traffic, a bitwise OR operation can be used for updating. For example, for a certain multicast traffic ID, the cross-disk root traffic flag is 0, and the local root traffic flag received from another disk is 1. After performing a bitwise OR operation on 0 and 1, we get 1, and use the obtained 1 to update the traffic flag of the corresponding multicast traffic ID in the cross-disk root traffic flag table.

[0057] Then, based on the first and second traffic markers of the disk, it is determined whether there is a disk in the distributed device that serves as the entry disk and receives multicast traffic from the main root node. For example, for a certain multicast traffic ID, if the corresponding traffic marker in both the local disk main root traffic marker table and the cross-disk main root traffic marker table is 0, it is determined that there is no disk in the distributed device that serves as the entry disk and receives multicast traffic from the main root node. If either the corresponding traffic marker in the local disk main root traffic marker table or the cross-disk main root traffic marker table is 1, it is determined that there is a disk in the distributed device that serves as the entry disk and receives multicast traffic from the main root node.

[0058] Furthermore, refer to Figure 4 , Figure 4 This is a schematic diagram of cross-disk forwarding of the primary root traffic tag table of one embodiment of the service failover method of this application, as shown below. Figure 4 As shown, in order to achieve rapid detection of primary root traffic faults and rapid switching of backup root traffic during the protection period, each disk cancels the first and second traffic flags of the disk after sending the first traffic flag to other disks. Specifically, all traffic flags in the primary root traffic flag table of this disk, the backup root traffic flag table of this disk, and the primary root traffic flag table of cross-disk can be set to 0.

[0059] Furthermore, in one embodiment, the protection period duration is determined based on the duration of canceling all traffic markers, the duration of setting the first traffic marker, and the duration of updating the second traffic marker.

[0060] In this embodiment, as can be seen from the above-mentioned traffic marking related operations and judgment logic, in order to achieve rapid detection of primary root traffic faults and rapid switching of backup root traffic, it is necessary to complete the setting of traffic markings, cross-disk forwarding of traffic markings between different disks, and cancellation of traffic markings within a protection cycle. Therefore, the protection cycle duration is determined based on the duration of canceling all traffic markings, the duration of setting the first traffic marking, and the duration of updating the second traffic marking.

[0061] Furthermore, in one embodiment, each chassis includes a chip, and the protection cycle duration is determined based on the duration of canceling all traffic markers, the duration of setting the first traffic marker, and the duration of updating the second traffic marker, including:

[0062] The duration for canceling all traffic tags is calculated based on the number of all traffic tags, chip processing performance, and the performance ratio allocated to canceling traffic tags.

[0063] The duration for setting the first traffic marker is calculated based on the number of first traffic markers on the server board and the peak value of multicast traffic ingress.

[0064] The time required to update the second traffic tag is calculated based on the number of first traffic tags on the chassis, the chip processing performance, and the performance ratio allocated to forwarding the first traffic tags.

[0065] The protection period duration is calculated by summing the duration of canceling all traffic markers, the duration of setting the first traffic marker, and the duration of updating the second traffic marker.

[0066] In this embodiment, each hard drive is equipped with a chip. The duration for canceling all traffic tags, the duration for setting the first traffic tag, and the duration for updating the second traffic tag are closely related to the chip's processing performance and the performance allocation ratio. Specifically, the protection period duration can be set to T, and the chip processing performance (considering only the processing performance involved in forwarding and tag cancellation) can be set to K pps (Packets Per Second, abbreviated as pps, representing the number of multicast packets transmitted per second). The performance ratio allocated to canceling traffic tags is X%, and the performance ratio allocated to forwarding the first traffic tag is 1-X%. The chip's rate for canceling traffic tags is K*X% entries per second. The number of data entries in the traffic tag table is set to N, then the duration for the chip to cancel all traffic tags is T1 = 3N / (K*X%). The multicast traffic is set to L. If the chip sets the first traffic tag (the primary root traffic tag table of this disk) for pps, the duration T2 = N / L. Considering the duration of setting the backup root traffic tag table of this disk, T2 can be updated to T2 = 2N / L. The duration of updating the second traffic tag involves cross-disk forwarding of the first traffic tag. Since cross-disk forwarding of traffic tags uses the internal switching network of the distributed device, the port rate is much greater than the chip performance. Therefore, the duration of updating the second traffic tag is T3 = N / K(1-X%). The protection period duration T = T1 + T2 + T3 is calculated by summing the durations of canceling all traffic tags, setting the first traffic tag, and updating the second traffic tag. Furthermore, to avoid repeated service switching caused by refreshing the traffic tag table, an empirical coefficient of 20% can be added, correcting the protection period duration to: T = (T1 + T2 + T3) * (1 + 20%).

[0067] Further, in one embodiment, before calculating the duration for setting the first traffic marker based on the number of first traffic markers on the server and the peak value of multicast traffic ingress, the following steps are included:

[0068] The peak value of multicast traffic ingress is calculated based on the stable bandwidth threshold of the chassis slot, the chip processing performance, and the performance ratio allocated to cancel traffic marking.

[0069] In this embodiment, under normal circumstances, the multicast ingress traffic of a single slot of the distributed device does not exceed 5% of the slot bandwidth, and the average number of multicast traffic replications is 8 (source: laboratory test parameters formulated by the operator based on the current network traffic data; 8 means that each multicast packet entering the system will be distributed to 8 different receiving points on average). If the stable bidirectional traffic of any port of the distributed device exceeds 45%, a bandwidth warning needs to be reported (considering that the traffic of the protection device will double when the device loses power). Therefore, based on the stable threshold of the disk slot bandwidth, the chip processing performance, and the performance ratio allocated to cancel traffic marking, the multicast traffic ingress peak value L can be calculated by the formula L = K * (1 * 5% * 45% - X%). It should be noted that the multicast traffic ingress peak value L here is the ingress packet rate calculated under the scenario where the multicast traffic packet length is at the limit of the chip processing capability.

[0070] Further, in one embodiment, the sum of the performance ratio allocated to canceling the traffic label and the performance ratio allocated to forwarding the first traffic label is 1, and before step S10, the following is included:

[0071] By adjusting the performance ratio allocated to canceling traffic tags and the performance ratio allocated to forwarding the first traffic tag, experiments were conducted on the dual-root protection network to obtain the corresponding relationship between different protection cycle durations and performance ratios.

[0072] Based on the correspondence between different protection cycle durations and performance ratios, the optimal range of performance ratio values ​​is determined.

[0073] In this embodiment, the chip processing performance (considering only the processing performance involved in forwarding and de-marking) is set to Kpps, where the performance ratio allocated to de-marking traffic is X%, and the performance ratio allocated to forwarding the first traffic mark is 1-X%. Substituting L = K * (1 * 5% * 45% - X%) into the formula T = T1 + T2 + T3, we get T = 3N / (K * X%) + 2N / K * (1 * 5% * 45% - X%) + N / K * (1-X%). Therefore, the protection cycle duration T and the performance ratio X% allocated to de-marking traffic are functionally related. When the multicast traffic quantity N and the chip processing performance K are fixed (N = 1000, K = 100Mpps), by adjusting the performance ratios allocated to de-marking traffic and forwarding the first traffic mark, experiments can be conducted on the dual-root protection network to obtain the corresponding relationship between different protection cycle durations and performance ratios. (Refer to...) Figure 5 , Figure 5 This is a schematic diagram illustrating the correspondence between different protection period durations and performance ratios in one embodiment of the service switching method of this application, as shown below. Figure 5As shown, when X is between 1 and 1.5, the protection period duration remains basically unchanged and is optimal. The smaller the value of X%, the larger the value of 1-X%, which means that the chip's performance in processing service packet forwarding is higher. Through analysis, it can be seen that the optimal value range of X is between 1 and 1.5.

[0074] Further, in one embodiment, the process of each hard drive unmarking the first traffic marker and the second traffic marker after sending the first traffic marker to other hard drives includes:

[0075] The number of cycles in the protection period is counted. When the number of cycles is an even multiple, each disk will unmark the first and second traffic tags after sending the first traffic tag to other disks.

[0076] In this embodiment, to avoid repeated service switching caused by constantly refreshing the traffic tag table during the protection period, the number of protection period cycles is counted. When the number of cycles is an even multiple, that is, during each protection period of an even multiple, each disk cancels the first traffic tag and the second traffic tag of the disk after sending the first traffic tag to other disks.

[0077] In this embodiment, considering the use case of ultra-high-definition IPTV for operators, the number of channels is set to within 1000, the traffic per slot is approximately 5Gb / s, the average packet length is approximately 1200 bytes, the chip processing performance is set to K = 100M pps, the number of multicast traffic is N = 1000, X = 1, and the peak multicast traffic ingress is calculated to be L = 5 * 10 5 Approximately pps (5Gb / s flow rate per slot = 5 * 10) 9 b / s, each message length is 1200 bytes, that is, 1200 * 8 = 9600 b, which translates to a message rate per second (pps) of (5 * 10^6). 9 b) / 9600b≈5*10 5 It should be noted that the peak value L of the multicast traffic ingress here is the ingress packet rate calculated based on the packet length and port byte rate in the actual scenario. The average length of multicast packets in the actual application scenario is uncertain, but it is generally less than the ingress packet rate calculated under the extreme scenario of chip processing capacity. According to the aforementioned formula, the following can be calculated: T1 = 3N / (K*X%) = 3ms, T2 = 2N / L = 4ms, T3 = N / K(1-X%)≈0.03ms, T = (T1+T2+T3)*(1+20%)≈9ms. The corresponding configurable protection cycle duration T is 10ms, and the service switching duration T0 = 2T can reach about 20ms (the cancellation operation is performed every even multiple of the protection cycle, that is, twice the protection cycle duration). Compared with the switching duration of the IGP protocol detection method which is in the second range, the switching duration of this method is improved by nearly 50 times (1 second / 20ms = 50 times).

[0078] Secondly, embodiments of this application also provide a service switching device.

[0079] In one embodiment, the leaf nodes applied to the dual-root protection network are distributed devices, which include multiple hard drives, as shown in the figure. Figure 6 , Figure 6 This is a functional module diagram of an embodiment of the service switching device of this application, as shown below. Figure 6 As shown, the service switching device includes:

[0080] The judgment module 10 is used to determine, in each protection cycle, for each disk, when the disk as the entry disk receives multicast traffic from the backup root node, whether there is a disk in the distributed device that receives multicast traffic from the primary root node as the entry disk.

[0081] The discard module 20 is used to discard the multicast traffic received from the backup root node if there is a disk that receives multicast traffic from the primary root node as an entry disk.

[0082] The switching module 30 is used to forward the multicast traffic received from the backup root node to the switching network of the distributed devices if there is no disk that receives multicast traffic from the primary root node as the entry disk.

[0083] Furthermore, in one embodiment, the determination module 10 is used to:

[0084] When a disk acts as an ingress disk and receives multicast traffic from a backup root node, the system determines whether there is a disk in the distributed device that acts as an ingress disk and receives multicast traffic from a primary root node based on the first and second traffic flags of the disk.

[0085] Specifically, the first traffic tag of each disk is marked when the disk, as the ingress disk, receives multicast traffic from the primary root node. The second traffic tag of each disk is updated according to the first traffic tag sent by other disks when the disk receives the first traffic tag sent by other disks. After sending the first traffic tag to other disks, each disk unmarks the first traffic tag and the second traffic tag of the disk.

[0086] Furthermore, in one embodiment, the protection period duration is determined based on the duration of canceling all traffic markers, the duration of setting the first traffic marker, and the duration of updating the second traffic marker.

[0087] Furthermore, in one embodiment, each chassis includes a chip, and the protection cycle duration is determined based on the duration of canceling all traffic markers, the duration of setting the first traffic marker, and the duration of updating the second traffic marker.

[0088] The duration for canceling all traffic tags is calculated based on the number of all traffic tags, chip processing performance, and the performance ratio allocated to canceling traffic tags.

[0089] The duration for setting the first traffic marker is calculated based on the number of first traffic markers on the server board and the peak value of multicast traffic ingress.

[0090] The time required to update the second traffic tag is calculated based on the number of first traffic tags on the chassis, the chip processing performance, and the performance ratio allocated to forwarding the first traffic tags.

[0091] The protection period duration is calculated by summing the duration of canceling all traffic markers, the duration of setting the first traffic marker, and the duration of updating the second traffic marker.

[0092] Furthermore, in one embodiment, the service switching device further includes a multicast traffic ingress peak calculation module, used for:

[0093] The peak value of multicast traffic ingress is calculated based on the stable bandwidth threshold of the chassis slot, the chip processing performance, and the performance ratio allocated to cancel traffic marking.

[0094] Furthermore, in one embodiment, the sum of the performance ratio allocated to canceling the traffic label and the performance ratio allocated to forwarding the first traffic label is 1. The service switching device further includes an optimal ratio determination module, used for:

[0095] By adjusting the performance ratio allocated to canceling traffic tags and the performance ratio allocated to forwarding the first traffic tag, experiments were conducted on the dual-root protection network to obtain the corresponding relationship between different protection cycle durations and performance ratios.

[0096] Based on the correspondence between different protection cycle durations and performance ratios, the optimal range of performance ratio values ​​is determined.

[0097] Furthermore, in one embodiment, after each hard drive sends the first traffic marker to other hard drives, it performs a demarking operation on the first and second traffic markers of the hard drive for the following purposes:

[0098] The number of cycles in the protection period is counted. When the number of cycles is an even multiple, each disk will unmark the first and second traffic tags after sending the first traffic tag to other disks.

[0099] The functions of each module in the above-mentioned service switching device correspond to the steps in the above-mentioned service switching method embodiment, and their functions and implementation processes will not be described in detail here.

[0100] Thirdly, embodiments of this application provide a service switching device.

[0101] In this embodiment, the service switching device is an NP (networking processor) chip, which integrates a microprocessor and memory. The microprocessor can call the service switching program stored in the memory and execute the service switching method provided in this embodiment. The method executed when the service switching program is called can be referred to in various embodiments of the service switching method of this application, and will not be repeated here.

[0102] Reference Figure 7 , Figure 7 This is a schematic diagram of the hardware structure of the service switching device involved in the embodiments of this application. In the embodiments of this application, the service switching device may include a processor, a memory, a communication interface, and a communication bus.

[0103] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0104] Communication interfaces include input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting devices within the service switching equipment, as well as interfaces used for interconnecting the service switching equipment with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0105] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0106] The processor can be a general-purpose processor, which can call the service switching program stored in memory and execute the service switching method provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the service switching program is called can be referred to in the various embodiments of the service switching method of this application, and will not be repeated here.

[0107] Those skilled in the art will understand that Figure 7 The hardware structure shown does not constitute a limitation of this application and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0108] Fourthly, embodiments of this application also provide a readable storage medium.

[0109] The present application has a service switching program stored on a readable storage medium, wherein when the service switching program is executed by a processor, it implements the steps of the service switching method described above.

[0110] The method implemented when the service switchover procedure is executed can be referred to in the various embodiments of the service switchover method of this application, and will not be repeated here.

[0111] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0112] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0113] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0114] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0115] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0116] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0117] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A business switching method, characterized in that, The leaf node of the dual-root protection network is a distributed device comprising multiple disks. The service failover method includes: In each protection cycle, for each disk, when the disk as the ingress disk receives multicast traffic from the backup root node, it is determined whether there is a disk in the distributed device that is the ingress disk receiving multicast traffic from the primary root node. If there is a disk that receives multicast traffic from the primary root node as an ingress disk, then the multicast traffic received from the backup root node will be discarded. If there is no server board that receives multicast traffic from the primary root node as the entry server board, then the multicast traffic received from the backup root node will be forwarded to the switching network of the distributed devices. Each board includes a chip, and the duration for canceling all traffic tags is calculated based on the number of all traffic tags, the chip's processing performance, and the performance ratio allocated to canceling traffic tags. The duration for setting the first traffic marker is calculated based on the number of first traffic markers on the server board and the peak value of multicast traffic ingress. The time required to update the second traffic tag is calculated based on the number of first traffic tags on the chassis, the chip processing performance, and the performance ratio allocated to forwarding the first traffic tags. The protection period duration is calculated by summing the duration of canceling all traffic markers, the duration of setting the first traffic marker, and the duration of updating the second traffic marker. Specifically, the first traffic tag of each disk is marked when the disk, as the ingress disk, receives multicast traffic from the primary root node. The second traffic tag of each disk is updated according to the first traffic tag sent by other disks when the disk receives the first traffic tag sent by other disks. After sending the first traffic tag to other disks, each disk unmarks the first traffic tag and the second traffic tag of the disk.

2. The service switching method as described in claim 1, characterized in that, When a server disk, acting as an entry server disk, receives multicast traffic from a backup root node, determining whether there exists a server disk in the distributed device that, acting as an entry server disk, receives multicast traffic from a primary root node includes: When a disk acts as an ingress disk and receives multicast traffic from a backup root node, the system determines whether there exists a disk in the distributed device that acts as an ingress disk and receives multicast traffic from the primary root node, based on the disk's first and second traffic flags.

3. The service switching method as described in claim 1, characterized in that, Before calculating the duration for setting the first traffic marker based on the number of first traffic markers on the server and the peak value of multicast traffic ingress, the following steps are included: The peak value of multicast traffic ingress is calculated based on the stable bandwidth threshold of the chassis slot, the chip processing performance, and the performance ratio allocated to cancel traffic marking.

4. The service switching method as described in claim 1, characterized in that, The sum of the performance ratio allocated to canceling the traffic tag and the performance ratio allocated to forwarding the first traffic tag is 1. In each protection cycle, for each disk, before determining whether there is a disk in the distributed device that has received multicast traffic from the primary root node as an ingress disk when the disk, as the ingress disk, receives multicast traffic from the backup root node, the process includes: By adjusting the performance ratio allocated to canceling traffic tags and the performance ratio allocated to forwarding the first traffic tag, experiments were conducted on the dual-root protection network to obtain the corresponding relationship between different protection cycle durations and performance ratios. Based on the correspondence between different protection cycle durations and performance ratios, the optimal range of performance ratio values ​​is determined.

5. The service switching method as described in claim 2, characterized in that, The process of each hard drive unmarking the first and second traffic markers after sending the first traffic marker to other hard drives includes: The number of cycles in the protection period is counted. When the number of cycles is an even multiple, each disk will unmark the first and second traffic tags after sending the first traffic tag to other disks.

6. A service switching device, characterized in that, The leaf node is applied to a dual-root protection network, wherein the leaf node is a distributed device comprising multiple disks, and the service switching device comprises: The judgment module is used to determine, in each protection cycle, for each disk, whether there is a disk in the distributed device that has received multicast traffic from the primary root node as an ingress disk when the disk as an ingress disk receives multicast traffic from the backup root node. The discard module is used to discard multicast traffic received from the backup root node if there is a disk that receives multicast traffic from the primary root node as an ingress disk. The switching module is used to forward the multicast traffic received from the backup root node to the switching network of the distributed devices if there is no disk that receives multicast traffic from the primary root node as the entry disk. Each board includes a chip, and the duration for canceling all traffic tags is calculated based on the number of all traffic tags, the chip's processing performance, and the performance ratio allocated to canceling traffic tags. The duration for setting the first traffic marker is calculated based on the number of first traffic markers on the server board and the peak value of multicast traffic ingress. The time required to update the second traffic tag is calculated based on the number of first traffic tags on the chassis, the chip processing performance, and the performance ratio allocated to forwarding the first traffic tags. The protection period duration is calculated by summing the duration of canceling all traffic markers, the duration of setting the first traffic marker, and the duration of updating the second traffic marker. Specifically, the first traffic tag of each disk is marked when the disk, as the ingress disk, receives multicast traffic from the primary root node. The second traffic tag of each disk is updated according to the first traffic tag sent by other disks when the disk receives the first traffic tag sent by other disks. After sending the first traffic tag to other disks, each disk unmarks the first traffic tag and the second traffic tag of the disk.

7. A service switching device, characterized in that, The service switching device includes a processor, a memory, and a service switching program stored in the memory and executable by the processor, wherein when the service switching program is executed by the processor, it implements the steps of the service switching method as described in any one of claims 1 to 5.

8. A readable storage medium, characterized in that, The readable storage medium stores a service switching program, wherein when the service switching program is executed by a processor, it implements the steps of the service switching method as described in any one of claims 1 to 5.

Images