CN115720180A

CN115720180A - Communication network fault real-time monitoring and recovery method and system based on SRIO bus

Info

Publication number: CN115720180A
Application number: CN202211371299.2A
Authority: CN
Inventors: 杜怀超; 卢娥; 孙俊格; 张剑; 丁小芩; 刘溙涞
Original assignee: Shanghai Institute of Electromechanical Engineering
Current assignee: Shanghai Institute of Electromechanical Engineering
Priority date: 2022-11-03
Filing date: 2022-11-03
Publication date: 2023-02-28

Abstract

The invention provides a method and a system for monitoring and recovering SRIO (serial peripheral input/output) faults in real time based on an SRIO (serial peripheral input/output) bus communication network. The invention mainly meets the application requirements of real-time fault monitoring and recovery of an SRIO high-speed communication network, and the improvement thereof comprises the following steps: fault monitoring and recovery are completed through the auxiliary bus, and fault isolation with the SRIO high-speed network is realized; and (3) monitoring the real-time fault and rapidly recovering the network fault, and not influencing the communication function of the SRIO switching network as much as possible.

Description

Communication network fault real-time monitoring and recovery method and system based on SRIO bus

Technical Field

The invention relates to the technical field of computer network communication, in particular to a method and a system for monitoring and recovering communication network faults in real time based on an SRIO bus.

Background

With the Rapid development of embedded technology, the application has increased the demand for bus speed and bandwidth, and a Serial Rapid I/O (SRIO) technology has been applied to the fields of embedded network communication, aerospace equipment communication, and the like due to its characteristics of high speed, low delay, and high reliability.

The SRIO bus interconnection architecture is a point-to-point packet switching technology, supports interconnection and communication between chips and between boards, and has a data transmission rate of over 60 Gbps. The SRIO communication topology is divided into an endpoint and an endpoint direct connection or a communication network structure formed by switching nodes. The SRIO interconnection system structure is divided into three layers, namely a logic layer, a transmission layer and a physical layer. The logic layer specification is positioned at the highest layer, defines all operation protocols and packet formats and provides necessary information for the end node device to initiate and complete transactions; the transport layer specification is in the middle layer of the protocol layer, and the transport layer defines the address space of the SRIO, an addressing mechanism and routing information for packet switching; the physical layer specification is at the bottom, containing details of the device-level interface, such as packet transport mechanisms, flow control, electrical parameters, and low-level error management.

The fault monitoring and recovery technology of the SRIO communication interconnection network has practical application requirements. The failure of any node in the network is not processed, which may cause the failure to spread to other nodes through the switching node, so a method is needed to monitor the communication state between the nodes in real time, and take quick and effective recovery measures to realize the real-time recovery of the failure without affecting the normal communication function of the whole network.

Patent document CN109194497A discloses a dual SRIO network backup system for software radio system, which comprises two GSIM modules and several functional modules, where the GSIM modules and the functional modules both contain SRIO switches, one end of the SRIO switch inside the functional module is connected to the SRIO switches of the two GSIM modules, and the other end is connected to each computing node of the functional module, and the GSIM module that has a failure and backup replaces the main GSIM. The invention realizes that the software radio system can be switched to the backup network in time when the main network fails, thereby preventing the function from failing.

However, patent document CN109194497A needs to construct two SRIO networks as backup to each other, which increases redundancy and network construction cost.

Disclosure of Invention

Aiming at the defects in the prior art, the invention aims to provide a method and a system for monitoring and recovering communication network faults in real time based on an SRIO bus.

According to the method for monitoring and recovering the SRIO bus communication network fault in real time, provided by the invention, the SRIO fault is monitored and recovered through the auxiliary bus, wherein end nodes of the SRIO bus communication network are respectively connected with the auxiliary bus.

Preferably, one end node is used as a main node, the main node receives the respective SRIO states sent by the other end nodes through the auxiliary bus, and the main node detects the SRIO states of the main node.

Preferably, the master node sends SRIO initiation frames to other end nodes over the auxiliary bus.

Preferably, the method comprises the following steps:

step S0: the end node serving as the main node performs data interaction with other end nodes through SRIO;

step S1: the end node periodically monitors the SRIO state and the communication state; if the SRIO communication fault is detected, triggering a step S2; if the SRIO communication fault is not detected, returning to the triggering step S0; the monitored SRIO states include: a port _ error state, a link _ initialized state, and an SRIO receive communication continuity state;

step S2: the end node sends a reset request and the current state of the SRIO to the main node in real time through the auxiliary bus;

and step S3: the main node judges according to the received reset request and the current state of the SRIO or the current state of the SRIO detected by the main node; if judging that the fault is effective or an SRIO fault is detected, entering a triggering step S4; if the fault is judged to be not valid and not SRIO fault, returning to the triggering step S0;

and step S4: the main node sends a reset instruction through auxiliary bus broadcasting, and the reset instruction instructs the end node to carry out SRIO port reset operation; respectively triggering the step S5 and the step S6;

step S5: the main node completes self reset recovery, performs reset recovery on the switching node, reconfigures the switching node and triggers the step S7;

step S7: the main node judges that reconnection is successful after resetting, namely after the main node monitors that SRIO reconnection is normal in real time, triggering step S9;

step S9: the main node sends an SRIO start frame to other end nodes through the auxiliary bus, and normal communication of an SRIO network is recovered;

step S6: each end node receives the reset command to reset the SRIO port, and step S8 is triggered, wherein after the main node completes the reset process, the main node monitors the link establishment state with each other end node in real time, and after the connection is reestablished successfully, the main node sends an SRIO start frame to each end node to recover the normal communication and complete the network fault recovery;

step S8: after the reconnection is successful, triggering the step S10;

step S10: the other end nodes receive SRIO initiation frames.

Preferably, the auxiliary bus is a CAN-FD bus.

The invention provides a system for monitoring and recovering communication network faults in real time based on an SRIO bus, which comprises an auxiliary bus and an end node;

and carrying out SRIO fault monitoring and recovery through an auxiliary bus, wherein end nodes of an SRIO bus communication network are respectively connected with the auxiliary bus.

Preferably, the method comprises the following steps:

a module M0: enabling an end node serving as a main node to perform data interaction with other end nodes through SRIO;

a module M1: enabling the end node to periodically monitor the SRIO state and the communication state; if the SRIO communication fault is detected, triggering a module M2; if the SRIO communication fault is not detected, returning to the trigger module M0; the monitored SRIO states include: a port _ error state, a link _ initialized state, and an SRIO receive communication continuity state;

a module M2: enabling the end node to send a reset request and the current state of the SRIO to the main node in real time through the auxiliary bus;

a module M3: the main node judges according to the received reset request and the current state of the SRIO or the current state of the SRIO detected by the main node; if judging that the fault is effective or the SRIO fault is detected, entering a trigger module M4; if the judgment result shows that the fault is not valid and not an SRIO fault, returning to the trigger module M0;

a module M4: the main node is enabled to broadcast and send a reset instruction through the auxiliary bus, and the reset instruction instructs the end node to carry out SRIO port reset operation; respectively triggering a module M5 and a module M6;

a module M5: the main node completes self reset recovery, resets and recovers the switching node, reconfigures the switching node and triggers a module M7;

a module M7: the master node is judged to be reconnected successfully after reset, namely the master node triggers the module M9 after monitoring that the SRIO reconnection is normal in real time;

a module M9: the main node sends an SRIO start frame to other end nodes through the auxiliary bus to recover the normal communication of an SRIO network;

a module M6: each end node receives a reset command to reset the SRIO port, and a module M8 is triggered, wherein after the main node completes the reset process, the main node monitors the link establishment state of each other end node in real time, and after the connection is reestablished successfully, the main node sends an SRIO start frame to each end node to recover the normal communication and complete the network fault recovery;

a module M8: after the reconnection is successful, triggering a module M10;

a module M10: having the other end node receive the SRIO initiation frame.

Preferably, the auxiliary bus is a CAN-FD bus.

Compared with the prior art, the invention has the following beneficial effects:

1. the invention mainly meets the application requirements of real-time fault monitoring and recovery of an SRIO high-speed communication network, and the improvement thereof comprises the following steps: fault monitoring and recovery are completed through the auxiliary bus, and fault isolation with the SRIO high-speed network is realized; and (3) monitoring the real-time fault and rapidly recovering the network fault, and not influencing the communication function of the SRIO switching network as much as possible.

2. The method can be applied to fault recovery of embedded high-speed SRIO communication networks which are connected among modules of a central control processor and are linked with radars and the like through optical fiber links, and can be popularized to fault real-time monitoring and recovery of various other SRIO-based network links.

3. The invention judges the SRIO state reported by other end nodes through the auxiliary bus by the main node execution period, judges whether the SRIO network needs to be reset and recovered, and starts the step of recovering reconnection when the SRIO network is reset and recovered as required, thereby realizing the network link reset to try to recover the normal communication of the whole SRIO communication network.

Drawings

Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:

fig. 1 is a schematic diagram of a high-speed SRIO bus communication network topology according to the present invention.

Fig. 2 is a schematic diagram of the mutual cooperation of the jobs in the master node and the end nodes in the present invention.

Fig. 3 is a schematic diagram of a SRIO network failure monitoring and recovery processing flow in the present invention.

Detailed Description

The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the concept of the invention. All falling within the scope of the present invention.

The invention monitors the communication state of each node in the SRIO high-speed communication network in real time through the auxiliary bus. When a communication fault or a node fault occurs in an SRIO network, reporting an error state to a main node through an auxiliary bus, and requesting network fault recovery; and the main node monitors the SRIO network state and the auxiliary bus information, and controls all nodes of the SRIO communication system to carry out fault recovery through the auxiliary bus when judging that the bus is abnormal. By the scheme, the method and the device can monitor the condition of the SRIO high-speed communication bus in real time and realize quick recovery of network faults. That is, the present invention aims to monitor the fault of SRIO network communication in real time by means of the auxiliary bus, and to perform network communication through the auxiliary bus to recover to normal regardless of the link disconnection or communication fault caused by any reason.

Fig. 1 shows a topology structure diagram of a high-speed SRIO bus communication network according to the present invention. In the field of embedded control systems, a main control processor is an end node A in a graph, serves as a main node, is interconnected with processing modules, namely an end node B and an end node C, in other equipment through a switching node and a remote equipment end node R through optical fiber connection to form a communication network, and performs high-speed data interaction with high reliability and low time delay.

In this embodiment, the CAN-FD bus is used as an auxiliary bus, all end nodes in the SRIO bus network are connected to the CAN-FD bus, each end node CAN communicate with the master node through the auxiliary bus, and the master node CAN send broadcast frames to all the end nodes of the device through the auxiliary bus.

The data frame transmitted by the CAN-FD bus sets the priority, the data frame sent by the main node has higher priority, the reset command sent by the main node is sent to each end node in a high-priority broadcast mode, and the reset command is repeatedly sent for more than 3 times to ensure that the reset command is correctly received by each end node.

Fig. 2 is a diagram showing the interaction between the node a as the master node a and the other nodes B, C, R in the present invention, and fig. 3 is a flowchart showing the SRIO network failure monitoring and recovery processing in the present invention. The method comprises the following steps that a main node and an end node in the network cooperate with each other through an auxiliary bus to complete the processing flow of real-time fault monitoring and recovery, and specifically comprises the following steps:

step S0: and the end node serving as the main node normally performs data interaction with other end nodes through SRIO.

Step S1: the end node periodically monitors the SRIO state and the communication state; if the SRIO communication fault is detected, triggering a step S2; if the SRIO communication fault is not detected, returning to the triggering step S0; wherein the period is determined according to the node execution period, preferably in the order of milliseconds. Specifically, the monitored SRIO states include: port _ error state, link _ initialized state, etc., and SRIO receive communication continuity state.

Step S2: the end nodes send reset requests and SRIO current status to the master node in real time over a secondary bus, e.g., a CAN-FD bus. Specifically, each end node in the SRIO network is connected to the auxiliary bus, and the end nodes periodically send monitoring state information to the end nodes serving as main nodes through the auxiliary bus.

And step S3: the main node judges according to the received reset request and the SRIO current state or the SRIO current state detected by the main node; if judging that the fault is effective or an SRIO fault is detected, entering a triggering step S4; if the judgment result shows that the fault is not valid and not an SRIO fault, the step S0 is returned to be triggered. Specifically, the master node periodically monitors the node state and the communication state of the master node; meanwhile, state monitoring data and recovery operation requests sent by each end node through the auxiliary bus are received periodically, and a fault recovery command is sent according to the severity of the fault.

And step S4: the main node sends a reset instruction through CAN-FD broadcast, and the reset instruction indicates the end node to carry out SRIO port reset operation; triggering step S5 and step S6. Specifically, each end node receives and executes a recovery command sent by the main node through the auxiliary bus in real time, and performs SRIO port reset or fault state clearing operation according to the recovery command.

Step S5: the main node completes self reset recovery, performs reset recovery on the switching node, reconfigures the switching node, and triggers step S7. Specifically, if the master node sends a reset recovery command, all nodes of the SRIO perform a network reset recovery procedure.

Step S7: and (4) the main node judges that the reconnection is successful after the reset, namely the main node monitors that the SRIO reconnection is normal in real time, and then the step S9 is triggered.

Step S9: and the master node sends SRIO starting frames to other end nodes through the CAN-FD bus to recover the normal communication of the SRIO network.

Step S6: and (4) each end node receives the reset command to reset the SRIO port, and step S8 is triggered. Specifically, after the master node completes the reset process, the state of link establishment with each end node is monitored in real time, after connection is reestablished successfully, an SRIO start frame is sent to each end node, normal communication is recovered, and network fault recovery is completed.

Step S8: after the reconnection is successful, step S10 is triggered.

Step S10: an SRIO initiation frame is received.

In particular, reset recovery of an SRIO communication network operates according to a specific timing sequence:

1) The end node resets immediately after receiving the reset command and resets after 50 ms.

2) And the master node immediately resets after sending a 3-time reset order, resets and reconfigures the switch serving as the switching node.

3) And after the end node is reset, the end node starts to monitor the link in real time and reestablish the state. If the link is monitored to be normal for n times continuously, judging that the link is established again stably, and waiting for a master node SRIO starting message; otherwise, judging that the link establishment fails, and resetting again until the connection establishment is stabilized again or the total reset recovery time is overtime. Wherein n >3.

4) After the main node completes the configuration of the switch, the state of the link with each end node is periodically monitored and reestablished, and if the link is judged to be reestablished stably, an SRIO starting message is sent to the end node. The failure recovery is completed.

In summary, the invention monitors the fault of the SRIO network communication in real time by means of the auxiliary bus based on the scheme of monitoring and recovering the fault of the SRIO bus communication network in real time, and can realize the recovery of the network communication through the auxiliary bus regardless of the link disconnection or the communication fault caused by any reason.

The invention also provides a system for monitoring and recovering the fault of the communication network in real time based on the SRIO bus, and a person skilled in the art can realize the system for monitoring and recovering the fault of the communication network in real time based on the SRIO bus by executing the step flow of the method for monitoring and recovering the fault of the communication network in real time based on the SRIO bus, namely, the method for monitoring and recovering the fault of the communication network in real time based on the SRIO bus can be understood as the preferred embodiment of the system for monitoring and recovering the fault of the communication network in real time based on the SRIO bus.

And one end node is used as a main node, the main node receives the respective SRIO state sent by other end nodes through the auxiliary bus, and the main node detects the SRIO state of the main node.

And the main node sends an SRIO starting frame to other end nodes through the auxiliary bus.

The system for monitoring and recovering the communication network fault in real time based on the SRIO bus comprises:

a module M3: the main node judges according to the received reset request and the current state of the SRIO or the current state of the SRIO detected by the main node; if the fault is judged to be valid or the SRIO fault is detected, the method enters a trigger module M4; if the fault is judged to be not valid and not SRIO fault, returning to the trigger module M0;

a module M7: the main node is judged to be reconnected successfully after reset, namely the main node triggers a module M9 after monitoring that SRIO reconnection is normal in real time;

a module M9: the master node sends SRIO starting frames to other end nodes through the auxiliary bus, and normal communication of the SRIO network is recovered;

a module M6: enabling each end node to receive a reset command to reset an SRIO port, and triggering a module M8, wherein after the main node completes a reset process, the main node monitors the link establishment state of each other end node in real time, and sends an SRIO start frame to each end node after connection is reestablished successfully, so that normal communication is recovered, and network fault recovery is completed;

a module M8: after the reconnection is successful, triggering the module M10;

a module M10: the other end node is caused to receive an SRIO initiation frame.

The auxiliary bus is a CAN-FD bus.

Those skilled in the art will appreciate that in addition to the system, apparatus, and various modules thereof which implement portions of the programs provided by the present invention in the form of purely computer readable program code, the system, apparatus, and various modules thereof provided by the present invention can be implemented with the same programs in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like, all by logically programming the method steps. Therefore, the system, the device and the modules thereof provided by the present invention can be considered as a hardware component, and the modules included in the system, the device and the modules thereof for implementing various programs can also be considered as structures in the hardware component; modules for performing various functions may also be considered to be both software programs for performing the methods and structures within hardware components.

The foregoing description has described specific embodiments of the present invention. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.

Claims

1. A real-time monitoring and recovery method for SRIO (serial input/output) bus communication network faults is characterized in that the SRIO fault monitoring and recovery are carried out through an auxiliary bus, wherein end nodes of an SRIO bus communication network are respectively connected with the auxiliary bus.

2. The method according to claim 1, wherein one end node is used as a master node, the master node receives respective SRIO statuses sent by other end nodes through the auxiliary bus, and the master node detects the SRIO status of itself.

3. The method of real-time monitoring and recovery from SRIO bus communication network failures of claim 2 wherein the master node sends SRIO start frames to other end nodes via the auxiliary bus.

4. The method for real-time monitoring and recovery of SRIO bus communication network fault according to claim 1, comprising:

step S2: the end node sends a reset request and the SRIO current state to the main node in real time through the auxiliary bus;

and step S3: the main node judges according to the received reset request and the SRIO current state or the SRIO current state detected by the main node; if judging that the fault is effective or an SRIO fault is detected, entering a triggering step S4; if the judgment result shows that the fault is not valid and not an SRIO fault, returning to the triggering step S0;

step S5: the main node completes self reset recovery, resets and recovers the switching node, reconfigures and triggers the step S7;

step S8: after the reconnection is successful, triggering a step S10;

step S10: the other end nodes receive SRIO initiation frames.

5. The method for real-time monitoring and recovery of communication network faults based on the SRIO bus as claimed in claim 1, wherein the auxiliary bus is a CAN-FD bus.

6. A system for monitoring and recovering communication network fault in real time based on SRIO bus is characterized by comprising an auxiliary bus and an end node;

7. The system according to claim 6, wherein one end node is used as a master node, the master node receives respective SRIO statuses sent by other end nodes through the auxiliary bus, and the master node detects the SRIO status of itself.

8. The system according to claim 7, wherein the master node sends SRIO start frames to other end nodes via the auxiliary bus.

9. The system for real-time monitoring and recovery of SRIO bus communication network fault according to claim 6, comprising:

a module M4: the main node is enabled to broadcast and send a reset instruction through the auxiliary bus, and the reset instruction indicates the end node to carry out SRIO port reset operation; respectively triggering a module M5 and a module M6;

a module M8: after the reconnection is successful, triggering a module M10;

a module M10: having the other end node receive the SRIO initiation frame.

10. The system for real-time monitoring and recovery of communication network failures based on SRIO bus of claim 6, wherein the auxiliary bus is a CAN-FD bus.