Message forwarding method and equipment

Abstract

The invention provides a message forwarding method and equipment. In one example, the method comprises the steps of selecting a fault agent node from a second cloud network service unit in the distributed decoupling machine frame cloud cluster under the condition that management network communication between a first cloud network service unit and a main cloud network control unit fails; and under the condition that the fault agent node is determined, for a to-be-forwarded management message, through a data network link between the first cloud network service unit and the fault agent node, sending the to-be-forwarded management message to the fault agent node, and forwarding the to-be-forwarded management message to the fault agent node. And the fault agent node sends the to-be-forwarded management message to target equipment. By applying the embodiment of the invention, the running stability of the DDC cloud cluster can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of network communications, and in particular to a message forwarding method and device. Background Art

[0002] DDC (Distributed Disaggregated Chassis) technology solves the upgrade and iteration problems of DCI (Data Center Interconnect) networks by distributing and decoupling large chassis devices, using box switches as forwarding line cards and switching network boards, and flexibly deploying them in multiple cabinets. Compared with traditional chassis switches, DDC can not only form a larger-scale switching capacity cluster, but also is not limited by the space of a single cabinet, breaking through the capacity bottleneck of chassis switches.

[0003] As the scale of equipment continues to expand, it becomes particularly important to ensure the stability of equipment and effective fault protection. It is necessary to reduce the impact of a single device on the operation of the entire DDC cloud cluster and avoid large-scale business anomalies caused by partial equipment failures. Summary of the invention

[0004] The present invention provides a message forwarding method and device to improve the stability of DDC cloud cluster operation.

[0005] According to a first aspect of an embodiment of the present invention, a message forwarding method is provided, which is applied to a first cloud network service unit in a distributed decoupled chassis cloud cluster, and the method includes:

[0006] In the case of a communication failure between the first cloud network service unit and the main cloud network control unit management network, selecting a fault proxy node from the second cloud network service unit in the distributed decoupled chassis cloud cluster; wherein the fault proxy node communicates normally with the main cloud network control unit; the second cloud network service unit is the other cloud network service unit in the distributed decoupled chassis cloud cluster except the first cloud network service unit;

[0007] When the faulty proxy node is determined, for the management message to be forwarded, the management message to be forwarded is sent to the faulty proxy node through the data network link between the first cloud network service unit and the faulty proxy node, and the faulty proxy node sends the management message to be forwarded to the destination device.

[0008] According to a second aspect of an embodiment of the present invention, a message forwarding device is provided, which is deployed in a first cloud network service unit in a distributed decoupled chassis cloud cluster, and the device includes:

[0009] A selection unit is configured to select a fault proxy node from a second cloud network service unit in the distributed decoupled chassis cloud cluster when the first cloud network service unit fails to communicate with the main cloud network control unit management network; wherein the fault proxy node communicates normally with the main cloud network control unit; and the second cloud network service unit is a cloud network service unit other than the first cloud network service unit in the distributed decoupled chassis cloud cluster;

[0010] A communication unit is used to, when a faulty proxy node is determined, send the management message to be forwarded to the faulty proxy node through the data network link between the first cloud network service unit and the faulty proxy node, and the faulty proxy node sends the management message to be forwarded to the destination device.

[0011] By applying the technical solution disclosed in the present invention, in the case of a management network communication failure between the first cloud network service unit and the main cloud network control unit, a second cloud network service unit that communicates normally with the main cloud network control unit is selected from the distributed decoupled chassis cloud cluster as a fault proxy node, and for management messages to be forwarded, the management messages to be forwarded are sent to the fault proxy node through the data network link between the first cloud network service unit and the fault proxy node, and the fault proxy node sends the management messages to be forwarded to the destination device. By using the data network link between the cloud network service units as an escape channel for the management messages of the cloud network service units, the stability of the operation of the DDC cloud cluster is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a flow chart of a message forwarding method provided by an embodiment of the present invention;

[0013] Figure 2A This is a schematic diagram of the management message forwarding path when the management network is normal;

[0014] Figure 2B This is a schematic diagram of a management message forwarding path in the event of a management network failure provided by an embodiment of the present invention;

[0015] Figure 3 It is a schematic diagram of the architecture of a DDC cloud cluster provided by an embodiment of the present invention;

[0016] Figure 4 This is a schematic diagram of a scenario in which a small number of NCP management networks fail, provided by an embodiment of the present invention;

[0017] Figure 5 It is a schematic diagram of a scenario of an NCF management network failure provided by an embodiment of the present invention;

[0018] Fig. 6AIt is a schematic diagram of the architecture of a DDC cloud cluster with an escape container deployed, provided by an embodiment of the present invention;

[0019] Figure 6B This is a schematic diagram of a scenario in which an escape container is deployed and an NCC management network fails, provided by an embodiment of the present invention;

[0020] Figure 7 This is a schematic diagram of a scenario in which an escape container is deployed and an MGT network fails, provided by an embodiment of the present invention;

[0021] Figure 8 It is a structural schematic diagram of a message forwarding device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, a brief description of the DDC device is given below.

[0023] The DDC device may include a network cloud control unit (Network Cloud Controller, NCC for short), a network cloud fabric (Network Cloud Fabric, NCF for short) and a network cloud service unit (Network Cloud Processor, NCP for short).

[0024] In the DDC cloud cluster architecture, in the management network between DDC devices, the DDC devices are connected through the MGT (Management) device to realize the communication between the board devices. Each DDC device establishes a forwarding path for the maintenance management network through the Router container.

[0025] In the management network, a forwarding path is usually established independently through the Router container for inter-board communication between the DDC devices in the cluster. All DDC devices are connected to the middle MGT device to form a large internal management network. Although the internal management network supports MGT devices to be interconnected through multiple devices and multiple links, and multiple equal-cost paths to reduce the probability of link failure, the possibility of failure still exists.

[0026] Therefore, in order to improve the stability of cluster equipment, in the event of a DDC equipment management network failure, a set of escape channels can be provided for management network communication between NCPs, such as completing management network data communication interaction through cross-board business traffic interaction in the data network.

[0027] In the process of data interaction between DDC devices through cross-board service traffic interaction in the data network, the destination port is not a panel port but an internal port of the destination board, such as a port of a CPU (Center Process Unit) of the destination board.

[0028] For example, see Figure 2A Taking NCP as an example, when the management network is normal, the management message sent by the business container 2011 of NCP201 ​​to NCP202 can be sent by the business container 2011 to the forwarding module of the Router container 2012 (not shown in the figure), and the forwarding module of the Router container 2012 sends the management message to the forwarding module of the Router container 2022 of NCP202 through the management channel (not shown in the figure). The forwarding module of the Router container 2022 can forward the management message to the business container 2021 of NCP202 according to the destination slot number of the management message.

[0029] See also Figure 2B In the case of a management network failure, the escape channel can be enabled. The management message sent by the service container 2011 of NCP201 ​​to NCP202 can be sent by the service container 2011 to the forwarding module (not shown in the figure) of the Router container 2012. Due to the management network failure, when the forwarding module of the Router container 2012 receives the management message, it can send the management message to the service container 2011, and the service container 2011 sends the management message to the service container 2021 of NCP202 through the cross-board service traffic interaction mode. The service container 2021 of NCP202 can send the received management message to the forwarding module of the Router container 2022 of NCP202, and the forwarding module of the Router container 2022 of NCP202 sends the management message to the service container 2021 of NCP202 according to the destination slot number of the management message.

[0030] In order to make the above-mentioned purposes, features and advantages of the embodiments of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention are further described in detail below with reference to the accompanying drawings.

[0031] See also Figure 1 , is a flow chart of a message forwarding method provided by an embodiment of the present invention, wherein the message forwarding method can be applied to any NCP (which can be called the first NCP) in the DDC cloud cluster, such as Figure 1 As shown, the message forwarding method may include the following steps:

[0032] Step 101. When there is a communication failure between the first cloud network service unit and the main cloud network control unit management network, select a fault proxy node from the second cloud network service unit in the distributed decoupled chassis cloud cluster; wherein the fault proxy node communicates normally with the main cloud network control unit; the second cloud network service unit is the other cloud network service units in the distributed decoupled chassis cluster except the first cloud network service unit.

[0033] In an embodiment of the present invention, in the event of a communication failure between the first NCP and the main NCC management network, the first NCP can select a second NCP that communicates normally with the main NCC from other NCPs in the DDC cloud cluster except the first NCP (can be from the second NCP) as a fault proxy node, and use the data network link between the first NCP and the fault proxy node as an escape channel for the first NCP message.

[0034] The communication failure between the first NCP and the main NCC management network may include a management network link failure of the first NCP or a management network failure of the main NCC.

[0035] It should be noted that, if the management network of the main NCC fails and there is a backup NCC, the backup NCC will re-elect the main NCC, and before the new main NCC is elected, each NCP cannot communicate normally with the main NCC; when the new main NCC is selected, if the first NCP still cannot communicate with the new main NCC through the management network (such as the management network of the first NCP fails), and there is a second NCP in the second NCP that can communicate normally with the main NCC, then a faulty proxy node can be selected; if the first NCP can communicate with the new main NCC through the management network (such as the management network of a single device of the original main NCC fails), then there is no need to select a faulty proxy node.

[0036] Step 102: When the faulty proxy node is determined, for the management message to be forwarded, the management message to be forwarded is sent to the faulty proxy node through the data network link between the first cloud network service unit and the faulty proxy node, and the faulty proxy node sends the management message to be forwarded to the destination device.

[0037] In the embodiment of the present invention, when the first NCP determines the faulty proxy node, the first NCP can send the management message to be forwarded to the faulty proxy node through the data network link between the first NCP and the faulty proxy node, and the faulty proxy node sends the management message to be forwarded to the destination device.

[0038] Exemplarily, when the faulty proxy node communicates normally with the main NCC management network, the faulty proxy node may forward the management message of the first NCP through the management network.

[0039] Exemplarily, when the communication between the faulty proxy node and the main NCC management network also fails, the faulty proxy node may forward the management message of the first NCP through the data network link.

[0040] It should be noted that, when the destination device of the management message of the first NCP is the faulty proxy node, the faulty proxy node does not need to forward the management message of the first NCP externally after receiving the management message.

[0041] It can be seen that in Figure 1 In the method flow shown, in the case of a management network communication failure between the first cloud network service unit and the main cloud network control unit, a second cloud network service unit that communicates normally with the main cloud network control unit is selected from the distributed decoupled chassis cloud cluster as a fault proxy node. For management messages to be forwarded, the management messages to be forwarded are sent to the fault proxy node through the data network link between the first cloud network service unit and the fault proxy node, and the fault proxy node sends the management messages to be forwarded to the destination device. By using the data network link between the cloud network service units as an escape channel for the management messages of the cloud network service units, the stability of the operation of the DDC cloud cluster is improved.

[0042] In some embodiments, the selecting of the fault proxy node from the second cloud network service unit in the distributed decoupled chassis cloud cluster includes:

[0043] Sending a fault proxy request message to the second cloud network service unit via a data network link between the second cloud network service unit and the second cloud network service unit;

[0044] Upon receiving a fault proxy request response message sent by the second cloud network service unit, a fault proxy node is selected from the second cloud network service unit that sends the fault proxy request response message; wherein, the fault proxy request response message is sent by the second cloud network service unit to the first cloud network service unit through the data network link upon receiving the fault proxy request message and determining that the communication between the current node and the main cloud network control unit is normal.

[0045] Exemplarily, in the case of a communication failure between the first NCP and the primary NCC management network, the first NCP may send a fault proxy request message to the second NCP via a data network link.

[0046] It should be noted that, in the process of the first NCP sending the fault proxy request message, it will send the fault proxy request message to all the second NCPs in the DDC cloud cluster before the failure of the first NCP; among them, for the newly added NCPs in the DDC cloud cluster after the failure of the first NCP and before the selection of the fault proxy node, the first NCP will not obtain the newly added NCPs in the DDC cloud cluster, and accordingly, will not send fault proxy request messages to these NCPs.

[0047] When the second NCP receives the fault proxy request message sent by the first NCP, it can determine whether the node can communicate normally with the main NCC.

[0048] The normal communication between the second NCP and the main NCC includes that the second NCP and the main NCC can communicate through a management network, or that the second NCP and the main NCC can communicate through a data network.

[0049] When the second NCP determines that the node can communicate normally with the main NCC, the second NCP may send a fault proxy request response message to the first NCP.

[0050] When receiving the fault proxy request response message sent by the second NCP, the first NCP selects a fault proxy node from the second NCP that sent the fault proxy request response message.

[0051] In an example, the first NCP may select the second NCP that sends the fault proxy request response message as the fault proxy node according to the received first fault proxy request response message.

[0052] It should be noted that in the embodiment of the present invention, for any NCP, after the NCP selects a proxy fault node, if it is determined that the management network communication between the device and the main NCC is restored, the forwarding of the management message can be switched back to forwarding through the management network without forwarding through the faulty proxy node.

[0053] In some embodiments, after selecting the fault proxy node from the second cloud network service unit in the distributed decoupled chassis cloud cluster, the method further includes:

[0054] A fault proxy node notification message is sent to the fault proxy node through the data network link between the first cloud network service unit and the fault proxy node, so that when the fault proxy node receives the fault proxy node notification message, it sends the fault proxy node notification message to other distributed decoupled frame devices; wherein the fault proxy node notification message is used to notify the fault proxy node selected by the first cloud network service unit, so that other distributed decoupled frame devices will forward the management message sent to the first cloud network service unit through the fault proxy node.

[0055] Exemplarily, considering that the first NCP selects a fault proxy node, management messages sent by other DDC devices in the DDC cloud cluster to the first NCP also need to be forwarded through the fault proxy node. Therefore, the fault proxy node selected by the first NCP needs to be notified to other DDC devices in the DDC cloud cluster.

[0056] Accordingly, when the first NCP selects a faulty proxy node, a faulty proxy node notification message may be sent to the faulty proxy node via a data network link between the first NCP and the faulty proxy node.

[0057] The fault proxy node notification message is used to notify the first NCP of the fault proxy node selected, that is, to notify each DDC device in the DDC cloud cluster which NCP the first NCP has selected as the fault proxy node.

[0058] The faulty proxy node notification message may carry identification information of the faulty proxy node, such as slot number information.

[0059] When receiving the fault proxy node notification message sent by the first NCP, the fault proxy node may forward the fault proxy node notification message to other DDC devices.

[0060] When other DDC devices receive the notification message of the fault proxy node, they can refresh the management network forwarding path of their own nodes. For management messages that need to be sent to the first NCP, they can first be sent to the fault proxy node, which will then forward them to the first NCP.

[0061] In some embodiments, when the escape container is started on the first cloud network service unit, the following may also be included:

[0062] In the event of a failure in the management network of the current primary cloud network control unit, the escape container is used as the virtual backup cloud network control unit to elect a new primary cloud network control unit; wherein the priority of the escape container being elected as the primary cloud network control unit is lower than the priority of the cloud network control unit being elected as the primary cloud network control unit.

[0063] For example, in order to further improve the stability of the DDC cloud cluster and reduce the impact of the failure of the main NCC management network on the operation of the DDC cloud cluster, in addition to deploying multiple NCC devices, the DDC cloud cluster can also choose to start an escape container (Escap container) on some NCPs.

[0064] For example, eight NCC devices can be deployed in a DDC cloud cluster, and escape containers can be started on two NCPs, with a 1-master-9-standby configuration. The master NCC manages the cluster, and the nine standby NCCs perform backup to ensure cluster stability.

[0065] Among them, the escape container can be used as a virtual NCC device to participate in the election of the main NCC.

[0066] Among them, the priority of the escape container being elected as the main NCC is lower than the priority of the NCC being elected as the main NCC.

[0067] In some embodiments, selecting a fault proxy node from a second cloud network service unit in a distributed decoupled chassis cloud cluster may include:

[0068] A target cloud network service unit in the second cloud network service unit is selected as a fault proxy node; wherein the target cloud network service unit starts an escape container, and the escape container is selected as a main cloud network control unit as a virtual backup cloud network control unit.

[0069] For example, when an escape container is started on an NCP in a DDC cloud cluster and the escape container on a certain NCP is elected as the main NCC, for example, when the management network of all NCC devices fails, in order to improve the interaction efficiency of management messages, the first NCP can give priority to selecting the second NCP (which can be called the target NCP) whose started escape container is elected as the main NCC as the fault proxy node during the process of selecting the fault proxy node.

[0070] In order to enable those skilled in the art to better understand the technical solution provided by the embodiment of the present invention, the technical solution provided by the embodiment of the present invention is described below in conjunction with specific application scenarios.

[0071] See also Figure 3 , is a schematic diagram of the architecture of a DDC cloud cluster provided by an embodiment of the present invention, such as Figure 3 As shown, the DDC cloud cluster may include multiple NCCs (only two NCCs are shown in the figure, namely NCC311 and NCC312), an MGT device 340, multiple NCFs (only two NCFs are shown in the figure, namely NCF321 and NCF322) and multiple NCPs (only three NCPs are shown in the figure, namely NCP331, NCP332 and NCP333).

[0072] like Figure 3 As shown in the figure, NCPs interact with each other in the data network through NCF, and NCPs, NCFs and NCCs interact with each other in the management network through MGT devices.

[0073] in, Figure 3 The solid lines in the figure are data network links, and the dotted lines are management network links.

[0074] For any DDC device, multiple links can be used for mutual backup, supporting link ECMP (Equal-Cost Multi-Path).

[0075] It should be noted that Figure 3In the example, a data network link (which can be called full connection) is used between each NCP and each NCF. However, in actual applications, considering the large number of DDC devices, full connection may not be achieved due to the number of device ports. Instead, a connection between NCP and NCF can be established according to actual needs. Under the premise of ensuring link backup and improving reliability, the limitation caused by the number of device ports can be reduced.

[0076] Based on the above scenario, the message forwarding implementation is explained below with reference to a specific example.

[0077] Example 1: A small number of NCP management networks are faulty.

[0078] When a small number of NCPs fail to communicate with the current main NCC due to a management network failure, the system will start the partial proxy escape function. The NCP with the management network failure will notify other NCPs and select one from the other NCPs as the failure proxy node. The messages of the NCP with the management network failure will be forwarded to the main NCC through the failure proxy node to ensure uninterrupted communication.

[0079] by Figure 4 Taking the scenario shown as an example, assuming that line 5 fails, the NCP332 management network fails, the NCP332 management network can no longer communicate with other DDC devices, and the management networks of other DDC devices are normal, the system will start some escape functions. Among them, it is assumed that NCC311 is the current main NCC.

[0080] exist Figure 4 In the scenario shown, NCP332 needs to select a fault proxy device first. The implementation process is as follows:

[0081] 1) NCP322 provides emergency access to all other NCPs before the failure (in Figure 4 The device (including NCP331 and NCP333) sends a fault proxy request message and sets the device to a fault election state, with the election time set to T1.

[0082] 1.1. The escape route from NCP332 to NCP331 includes:

[0083] Direction 1: via line 9 to NCF321, then via line 8 to NCP331;

[0084] Direction 2: via line 12 to NCF322, then via line 11 to NCP331.

[0085] 1.2. The escape route from NCP332 to NCP333 includes:

[0086] Direction 1: via line 9 to NCF321, then via line 10 to NCP333;

[0087] Direction 2: via line 12 to NCF322, then via line 11 to NCP331.

[0088] 2) When NCP331 or NCP333 receives the proxy request message from NCP332, if the current device (NCP331 or NCP333) communicates normally with the current main NCC (i.e., NCC311), it responds to the fault proxy request, carries the slot information of the current board, and sends the fault proxy request response message to NCP332 through the escape channel; otherwise, it does not send the fault proxy request response message.

[0089] 3) If NCP332 receives a fault proxy request response message within the election time T1, it selects the first fault proxy request response message, NCP332 releases the fault election state, and selects the NCP that sent the fault proxy request response message (assuming it is NCP331) as the proxy fault node.

[0090] NCP332 will send a fault proxy node notification message to NCP331 through the escape channel, notifying NCP331 to serve as the proxy fault node of NCP332.

[0091] 4) NCP331 is selected as the fault proxy node of NCP332, and NCP331 forwards the fault proxy node notification message to other DDC devices through the management network. The DDC device that receives the fault proxy node notification message refreshes the management network forwarding path of the device, and the management message that needs to be sent to NCP332 will first be sent to NCP331 through the management network, and NCP331 will then send it to NCP332 through the escape channel, realizing the interaction of management information between NCP332 and other DDC devices.

[0092] The comparison of management message interaction path switching between NCC311 and NCP332 is as follows:

[0093] Before the NCP332 management network fails: NCC311—Line 1—MGT340—Line 5—NCP332;

[0094] After the NCP332 management network fails, assuming that NCP331 is the fault proxy node of NCP332, the escape channels are line 8 and line 9:

[0095] NCC311—Line 1—MGT340—Line 4—NCP331 (fault proxy node)—escape channel (lines 8 and 9)—NCP332.

[0096] It should be noted that, in the case where NCP331 is the fault proxy node of NCP332, line 8 and line 9, or line 11 and line 12 can be selected as the escape channel in a load balancing manner.

[0097] Example 2: NCF management network failure.

[0098] like Figure 5 As shown in the figure, assuming that both NCF321 and NCF322 have management network failures, NCF will be split from the DDC cluster. NCF can use the default traffic forwarding function and establish a default multicast table design, and no longer respond to the dynamic changes of NCP. Since the port connection between NCP and NCF is an auto-negotiation mechanism, it will not rely on the state change of NCP. Therefore, when NCF is split and has no master, it will continue to work and will not affect the entire DDC cluster network.

[0099] In this embodiment, for ports on the NCF used to connect to the NCP (which may be referred to as target ports), message forwarding channels between the target ports may be established in advance.

[0100] For any target port, when it is detected that the target port is connected to the NCP, the state of the target port is controlled to be an open state.

[0101] Based on the above design, NCF can forward messages to NCP according to the actual connection status of NCP without the need to interact with the main NCC for management data, so that NCF can continue to work even if the NCF management network fails.

[0102] Example 3: NCC management network failure.

[0103] The DDC cloud cluster architecture introduces the escape container function to ensure the stability of the equipment. The specification design allocates 8 NCCs and 2 NCP escape containers, supporting a maximum of 8+2 master controllers, equivalent to 10 NCCs (including two virtual NCCs), with a 1 master and 9 standby configuration. The master NCC manages the cluster, and the 9 standby NCCs perform backup to ensure the stability of the cluster.

[0104] After the DDC device is started, the cloud cluster manages the container and, in addition to the regular business container and Rrouter container, starts the escape container according to the resource priority of NCP. Its role is the same as that of the master container and the standby container. It is used for the backup and management of the DDC device and is a separate container to the outside world.

[0105] When there are more than two NCPs, the escape containers can be started on at most two NCPs with higher priorities by classifying the NCP resource priorities.

[0106] like Fig. 6A As shown in the figure, when there is no fault in the management network of NCC311 and NCC312, if the escape container is allocated to NCP332 and NCP333, there are 2 NCC devices, 2 NCF devices, 3 NCP devices and 2 NCP escape containers in the network (assuming that the escape container 3321 is started on NCP332 and the escape container 3331 is started on NCP333), which is equivalent to 4 main controllers (2 NCCs, 2 NCP escape containers), 2 network boards (NCF) and 3 service boards (3 NCP) on the frame device.

[0107] If both NCC311 and NCC312 have management network failures, the NCP escape container will take over the entire cluster. Figure 6B As shown in the figure, assuming that both line 1 and line 2 fail, the escape containers of NCP332 and NCP333 will elect a master NCC, select the master NCC, take over the cluster, and ensure the stability of the cluster.

[0108] Example 4: MGT network failure.

[0109] The MGT device network fails, that is, the entire management network fails, and management data exchange between devices cannot be completed through the management network. Figure 7 As shown in the figure, the escape containers are started on NCP332 and NCP333 respectively. When the MGT340 network fails, lines 1, 2, 3, 4, 5, 6, and 7 all fail. The escape plan in this scenario is designed as follows:

[0110] 1) The escape containers of NCP332 and NCP333 elect a master NCC to take over the entire DDC cluster. For specific implementation, see Example 3. In this case, the management message is switched to the escape channel.

[0111] 2) The interaction of NCP management messages is implemented through the escape channel to ensure the normal operation of NCP equipment, refer to the scenario of Example 1.

[0112] Taking NCP331 as an example, NCP331 can trigger the fault proxy process, communicate with other NCPs through the escape channel, and complete the communication with the main NCC.

[0113] Assuming that the escape container started on NCP332 is elected as the main NCC, NCP331 and NCP333 can preferentially select NCP332 as the fault proxy node.

[0114] Assuming that the fault proxy node of NCP331 is NCP332 and the fault proxy node of NCP333 is NCP332, the management message interaction path is as follows:

[0115] NCP331 and NCP332 manage message interaction paths: NCP331—escape channel (such as line 8 and line 9)—NCP332.

[0116] NCP333 and NCP332 manage message interaction paths: NCP333—escape channel (such as line 13 and line 12)—NCP332.

[0117] NCP331 and NCP333 manage message interaction paths: NCP331—escape channel (such as line 8 and line 9)—NCP332—escape channel (such as line 12 and line 13)—NCP333.

[0118] 3) The NCF device is split from the cluster and runs independently. For specific implementation, see Example 2.

[0119] See also Figure 8 , is a structural diagram of a message forwarding device provided by an embodiment of the present invention, such as Figure 8 As shown, the message forwarding device 80 may include:

[0120] The selection unit 810 is used to select a fault proxy node from a second cloud network service unit in the distributed decoupled chassis cloud cluster when the first cloud network service unit fails to communicate with the main cloud network control unit management network; wherein the fault proxy node communicates normally with the main cloud network control unit; and the second cloud network service unit is a cloud network service unit other than the first cloud network service unit in the distributed decoupled chassis cloud cluster;

[0121] The communication unit 820 is used to send the management message to be forwarded to the faulty proxy node through the data network link between the first cloud network service unit and the faulty proxy node when the faulty proxy node is determined, and the faulty proxy node sends the management message to be forwarded to the destination device.

[0122] In some embodiments, the selection unit 810 selects a fault proxy node from a second cloud network service unit in a distributed decoupled chassis cloud cluster, including:

[0123] Sending a fault proxy request message to the second cloud network service unit via a data network link between the second cloud network service unit and the second cloud network service unit;

[0124] Upon receiving a fault proxy request response message sent by the second cloud network service unit, a fault proxy node is selected from the second cloud network service unit that sends the fault proxy request response message; wherein, the fault proxy request response message is sent by the second cloud network service unit to the first cloud network service unit through the data network link upon receiving the fault proxy request message and determining that the communication between the current node and the main cloud network control unit is normal.

[0125] In some embodiments, the communication unit 820 is also used to send a fault proxy node notification message to the fault proxy node through the data network link between the first cloud-network service unit and the fault proxy node, so that when the fault proxy node receives the fault proxy node notification message, it sends the fault proxy node notification message to other distributed decoupled chassis devices; wherein the fault proxy node notification message is used to notify the fault proxy node selected by the first cloud-network service unit, so that other distributed decoupled chassis devices will forward the management messages sent to the first cloud-network service unit through the fault proxy node.

[0126] In some embodiments, the message forwarding device may further include:

[0127] An election unit is used to start an escape container on the first cloud network service unit, and when the current main cloud network control unit management network fails, use the escape container as a virtual backup cloud network control unit to elect a new main cloud network control unit; wherein the priority of the escape container being elected as the main cloud network control unit is lower than the priority of the cloud network control unit being elected as the main cloud network control unit.

[0128] In some embodiments, the selection unit 810 selects a fault proxy node from a second cloud network service unit in a distributed decoupled chassis cloud cluster, including:

[0129] A target cloud network service unit in the second cloud network service unit is selected as a fault proxy node; wherein the target cloud network service unit starts an escape container, and the escape container is selected as a main cloud network control unit as a virtual backup cloud network control unit.

[0130] The implementation process of the functions and effects of each unit in the above-mentioned device 80 is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here. Each unit in the device 80 can be a hardware module that can include a specially designed permanent circuit or logic device (such as a dedicated processor, such as FPGA or ASIC) for completing a specific operation. The hardware module can also include a programmable logic device or circuit (such as a general-purpose processor or other programmable processor) temporarily configured by software to perform a specific operation.

[0131] The embodiment of the present invention further provides a distributed decoupled chassis cloud cluster, including: a cloud network control unit, a cloud network switching unit, a cloud network service unit and a management device; the cloud network control unit, the cloud network switching unit and the cloud network service unit realize management network interaction through the management device; the cloud network service unit realizes data network interaction through the cloud network switching unit; wherein:

[0132] A cloud network service unit is used to select a fault proxy node from a second cloud network service unit in a distributed decoupled chassis cloud cluster when it serves as a first cloud network service unit and a communication failure occurs between the first cloud network service unit and the main cloud network control unit management network; wherein the communication between the fault proxy node and the main cloud network control unit is normal; the second cloud network service unit is a cloud network service unit other than the first cloud network service unit in the distributed decoupled chassis cloud cluster; for management messages to be forwarded, the management messages to be forwarded are sent to the fault proxy node through a data network link between the first cloud network service unit and the fault proxy node, and the fault proxy node sends the management messages to be forwarded to a destination device.

[0133] In some embodiments, for the target ports on the cloud network switching unit used to connect to the cloud network service unit, a message forwarding channel between the target ports is pre-established;

[0134] For any target port, when it is detected that the target port is connected to the cloud network service unit, the state of the target port is controlled to be turned on.

[0135] Exemplarily, based on the above settings of the cloud network switching unit, in the case of a cloud network switching unit management network failure, the cloud network switching unit can adopt the default traffic forwarding function and establish a default multicast table design, and no longer respond to the dynamic changes of the cloud network service unit. And the cloud network switching unit does not need to rely on the state changes of the cloud network service unit, and can continue to work in the absence of a master (i.e., a communication failure with the main cloud network control unit management network), and will not affect the entire DDC cluster network.

[0136] The implementation process of the functions and effects of each unit in the cluster is specifically described in the implementation process of the corresponding steps in the above method, which will not be repeated here. Each unit in the cluster can be composed of a hardware module that can include a specially designed permanent circuit or logic device (such as a dedicated processor, such as FPGA or ASIC) to complete a specific operation. The hardware module can also include a programmable logic device or circuit (such as a general-purpose processor or other programmable processor) temporarily configured by software to perform a specific operation.

Claims

1. A message forwarding method, characterized in that: Applied to a first cloud network service unit in a distributed decoupled chassis cloud cluster, the method includes: In the case of a communication failure between the first cloud network service unit and the main cloud network control unit management network, selecting a fault proxy node from the second cloud network service unit in the distributed decoupled chassis cloud cluster; wherein the fault proxy node communicates normally with the main cloud network control unit; the second cloud network service unit is the other cloud network service unit in the distributed decoupled chassis cloud cluster except the first cloud network service unit; When the faulty proxy node is determined, for the management message to be forwarded, the management message to be forwarded is sent to the faulty proxy node through the data network link between the first cloud network service unit and the faulty proxy node, and the faulty proxy node sends the management message to be forwarded to the destination device.

2. The method according to claim 1, characterized in that The selecting a fault proxy node from the second cloud network service unit in the distributed decoupled chassis cloud cluster includes: Sending a fault proxy request message to the second cloud network service unit via a data network link between the second cloud network service unit and the second cloud network service unit; Upon receiving a fault proxy request response message sent by the second cloud network service unit, a fault proxy node is selected from the second cloud network service unit that sends the fault proxy request response message; wherein the fault proxy request response message is sent by the second cloud network service unit to the first cloud network service unit through a data network link upon receiving the fault proxy request message and determining that the communication between the current node and the main cloud network control unit is normal.

3. The method according to claim 1, characterized in that After selecting a fault proxy node from the second cloud network service unit in the distributed decoupled chassis cloud cluster, the method further includes: A fault proxy node notification message is sent to the fault proxy node through the data network link between the first cloud network service unit and the fault proxy node, so that when the fault proxy node receives the fault proxy node notification message, it sends the fault proxy node notification message to other distributed decoupled chassis devices; wherein the fault proxy node notification message is used to notify the fault proxy node selected by the first cloud network service unit, so that other distributed decoupled chassis devices will forward the management message sent to the first cloud network service unit through the fault proxy node.

4. The method according to claim 1, characterized in that When the escape container is started on the first cloud network service unit, the method further includes: In the event that the current primary cloud network control unit management network fails, the escape container is used as a virtual backup cloud network control unit to elect a new primary cloud network control unit; wherein the priority of the escape container being elected as the primary cloud network control unit is lower than the priority of the cloud network control unit being elected as the primary cloud network control unit.

5. The method according to claim 1, characterized in that The selecting a fault proxy node from the second cloud network service unit in the distributed decoupled chassis cloud cluster includes: A target cloud network service unit in the second cloud network service unit is selected as a fault proxy node; wherein the target cloud network service unit starts an escape container, and the escape container is selected as a main cloud network control unit as a virtual backup cloud network control unit.

6. A message forwarding device, characterized in that: A first cloud network service unit deployed in a distributed decoupled chassis cloud cluster, the device comprising: A selection unit is configured to select a fault proxy node from a second cloud network service unit in the distributed decoupled chassis cloud cluster when the first cloud network service unit fails to communicate with the main cloud network control unit management network; wherein the fault proxy node communicates normally with the main cloud network control unit; and the second cloud network service unit is a cloud network service unit other than the first cloud network service unit in the distributed decoupled chassis cloud cluster; A communication unit is used to, when a faulty proxy node is determined, send the management message to be forwarded to the faulty proxy node through the data network link between the first cloud network service unit and the faulty proxy node, and the faulty proxy node sends the management message to be forwarded to the destination device.

7. The device according to claim 6, characterized in that The selection unit selects a fault proxy node from the second cloud network service unit in the distributed decoupled chassis cloud cluster, including: Sending a fault proxy request message to the second cloud network service unit via a data network link between the second cloud network service unit and the second cloud network service unit; Upon receiving a fault proxy request response message sent by the second cloud network service unit, a fault proxy node is selected from the second cloud network service unit that sends the fault proxy request response message; wherein the fault proxy request response message is sent by the second cloud network service unit to the first cloud network service unit through a data network link upon receiving the fault proxy request message and determining that the communication between the current node and the main cloud network control unit is normal.

8. The device according to claim 6, characterized in that The communication unit is also used to send a fault proxy node notification message to the fault proxy node through the data network link between the first cloud network service unit and the fault proxy node, so that when the fault proxy node receives the fault proxy node notification message, it sends a fault proxy node notification message to other distributed decoupled chassis devices; wherein the fault proxy node notification message is used to notify the fault proxy node selected by the first cloud network service unit, so that other distributed decoupled chassis devices will forward the management message sent to the first cloud network service unit through the fault proxy node.

9. The device according to claim 6, characterized in that The device also includes: An election unit is used to start an escape container on the first cloud network service unit, and when the current main cloud network control unit management network fails, use the escape container as the virtual backup cloud network control unit to elect a new main cloud network control unit; wherein the priority of the escape container being elected as the main cloud network control unit is lower than the priority of the cloud network control unit being elected as the main cloud network control unit.

10. The device according to claim 6, characterized in that The selection unit selects a fault proxy node from the second cloud network service unit in the distributed decoupled chassis cloud cluster, including: A target cloud network service unit in the second cloud network service unit is selected as a fault proxy node; wherein the target cloud network service unit starts an escape container, and the escape container is selected as a main cloud network control unit as a virtual backup cloud network control unit.

11. A distributed decoupled chassis cloud cluster, characterized in that: include: Cloud network control unit, cloud network switching unit, cloud network service unit and management equipment; The cloud network control unit, the cloud network switching unit and the cloud network service unit realize management network interaction through the management device; the cloud network service unit realizes data network interaction through the cloud network switching unit; wherein: The cloud network service unit is used to select a fault proxy node from the second cloud network service unit in the distributed decoupled chassis cloud cluster when it serves as the first cloud network service unit and the first cloud network service unit fails to communicate with the main cloud network control unit management network; wherein the fault proxy node communicates normally with the main cloud network control unit; the second cloud network service unit is the other cloud network service unit in the distributed decoupled chassis cloud cluster except the first cloud network service unit; for the management message to be forwarded, the management message to be forwarded is sent to the fault proxy node through the data network link between the first cloud network service unit and the fault proxy node, and the fault proxy node sends the management message to be forwarded to the destination device.

12. The distributed decoupled chassis cloud cluster according to claim 11, characterized in that: For the target ports on the cloud network switching unit used to connect to the cloud network service unit, pre-establish a message forwarding channel between the target ports; For any target port, when it is detected that the target port is connected to the cloud network service unit, the state of the target port is controlled to be turned on.

Images