A RapidIO system link fault diagnosis and isolation method

Abstract

This application provides a method for diagnosing and isolating RapidIO system link faults, belonging to the technical field of RapidIO system link fault handling. Specifically, the method includes active diagnosis, which includes: route retrieval, which searches for routes on all switch devices in the RapidIO system, using a depth-first algorithm to retrieve the system's routing tables, including the device routing table and port routing table, and obtains the device IDs of all terminal devices in the system, while proactively discovering link faults during the retrieval process; route matching, which matches the device IDs of all terminal devices in the system with the system's routing table. Based on the matching results, the method locates switch nodes with routing errors and further localizes the routing errors to the corresponding switch ports. This solution improves system reliability.

Description

Technical Field

[0001] The present application relates to the field of RapidIO system link fault processing, and in particular to a RapidIO system link fault diagnosis and isolation method. Background Art

[0002] RapidIO defines a high-performance, packet-switching interconnection technology that uses high-performance interface technology to achieve hardware-based high-performance, low-power, low-latency, and highly reliable data transmission. It has higher data transmission efficiency than 10 Gigabit Ethernet and PCIe, and is widely used in high-performance embedded systems, high-performance digital signal processing systems, 3G / 4G mobile communication base stations, military fighter aircraft electronic equipment, carrier-based aircraft electronic equipment, and industrial control fields.

[0003] In a RapidIO system consisting of one or more RapidIO switches, problems often arise, such as unconfigured or incorrectly configured RapidIO routing tables, unstable or disconnected links, or disconnected receiving RapidIO devices on one or more switches. Furthermore, the sending RapidIO devices in the RapidIO system fail to detect link and routing failures in a timely manner and continue to send RapidIO data, resulting in link congestion in the system. In severe cases, this can lead to the complete system crash.

[0004] To address the above situation, the present invention proposes a RapidIO link diagnosis and fault isolation method based on maintenance packages and the port-write mechanism. First, a maintenance package is used to retrieve the routing tables of all RapidIO switches in the system and the IDs of all RapidIO end devices in the system. Based on the routing table information and device ID information, the routing configuration between any two end devices in the system is determined to be normal, and any device nodes with abnormal configurations are isolated. During the retrieval process, the port-write function is enabled on the normally configured RapidIO switches, and the error enablement and notification mechanisms at the logic / transport layer, port layer, and channel layer are enabled. During system operation, system fault information is obtained based on the port-write information, and the fault point is isolated to prevent link faults from spreading to other units in the system.

[0005] During the initial operation of a RapidIO system, a data packet containing a response packet is often sent to a target device, such as a doorbell or Nread. The response packet is then received to determine whether the point-to-point communication link between the two devices is faulty. However, this method has the following disadvantages: It can only determine whether the link between the two devices is faulty, and cannot diagnose faults in other links in the entire system. If no response packet is received, it can only determine that the link between the two devices is faulty, and cannot accurately determine the location of the fault on the link.

[0006] During the initial operation of a RapidIO system, polling is often used to query the status of switches in the system and determine whether the link status is normal based on the switch status. However, this method has the following disadvantages: The polling method requires polling the status of every port on every switch in the system. The larger the system, the more frequent the polling, the longer the polling process takes, resulting in low system efficiency; and polling requires periodic sending of query packets, which consumes bandwidth resources on the RapidIO bus. Summary of the Invention

[0007] In view of this, the present application provides a RapidIO system link fault diagnosis and isolation method, which solves the problems in the prior art and improves system reliability.

[0008] On the one hand, the present application provides a RapidIO system link fault diagnosis method using the following technical solutions:

[0009] A RapidIO system link fault diagnosis method includes active diagnosis, wherein the active diagnosis includes:

[0010] Route retrieval: Searches routes on all switches in the RapidIO system, using a depth-first algorithm to retrieve the system's routing tables, including device routing tables and port routing tables. It also obtains the device IDs of all terminal devices in the system, proactively detecting link failures during the retrieval process.

[0011] Route matching matches the device IDs of all terminal devices in the system with the routing table in the system, and based on the matching results, locates the switch node with incorrect routing configuration, and further locates the routing error to the corresponding port of the switch.

[0012] Optionally, route retrieval specifically includes:

[0013] 1) Access the device connected to the SRIO interface of the lower computer;

[0014] 2) Determine the type of the connected device. If it is a terminal device, obtain the device information of the terminal device and the retrieval process ends;

[0015] 3) If it is a switch device, mark the switch and start from the first port of the switch to obtain the port link status and routing information. If the link is abnormal, access the next port of the switch to obtain the port link status and port routing information until the link status of the next port of the switch is normal. Then access the device connected to the port.

[0016] 4) Repeat 3) until the connected device is a terminal device or a marked switch device;

[0017] 5) If it is a terminal device, obtain the device information of the terminal device at the same time;

[0018] 6) Return to the previous level switch and obtain the port link status of the next port of the switch; if the link is abnormal, access the next port of the switch to obtain the port link status and port routing information until the link status of the next port of the switch is normal; then access the device connected to the port;

[0019] 7), repeat 3), 4), 5), and 6) until all switch ports in the system are accessed;

[0020] 8), the retrieval process ends.

[0021] It also includes system operation fault reporting. Node device faults during system operation are actively reported through port-write data packets.

[0022] On the other hand, the present application provides a RapidIO system link fault isolation method using the following technical solutions:

[0023] A RapidIO system link fault isolation method isolating the fault diagnosed as above;

[0024] When a routing failure occurs, the data packets of the routing failure are discarded;

[0025] When a link fails, the port of the failed node is closed and the data packets sent to the failed port are discarded.

[0026] When a routing failure occurs, the fault processing unit resets the port routing of the switch at the routing failure node so that the port discards the data packets of the routing failure and completes the routing failure isolation.

[0027] In summary, this application has the following beneficial technical effects:

[0028] 1. Automatically retrieve routing information and terminal device information in the RapidIO system;

[0029] 2. The link status in the system can be detected by the retrieval process, and the routing information and terminal device ID information can be used to automatically diagnose whether there is a routing fault in the system;

[0030] 3. Ability to accurately locate device nodes with routing failures;

[0031] 4. Port-write proactively notifies users of link failures during operation, avoiding the inefficiencies and excessive RapidIO bus bandwidth associated with polling the switch for link status.

[0032] 5. When a routing failure or link failure occurs, the faulty node can be automatically isolated, preventing the faulty node from affecting other devices in the system and improving system reliability.

[0033] 6. The routing information, terminal equipment information and fault information in the system are displayed on the host computer, which improves the convenience of system maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0035] Figure 1 This is a block diagram of the principle of implementing full device access in a PCIe system;

[0036] Figure 2 Retrieve the flow chart for the route. DETAILED DESCRIPTION

[0037] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0038] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the features in the following embodiments and embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative work are within the scope of protection of this application.

[0039] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on this application, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement an apparatus and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this apparatus and / or practice this method.

[0040] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. The illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0041] Additionally, in the following description, specific details are provided to provide a thorough understanding of the examples. However, one skilled in the art will appreciate that the aspects described can be practiced without these specific details.

[0042] An embodiment of the present application provides a RapidIO system link fault diagnosis method.

[0043] A RapidIO system link fault diagnosis method includes active diagnosis, wherein the active diagnosis includes:

[0044] Route retrieval searches for routes on all switch devices in the RapidIO system, using a depth-first algorithm to obtain the system's routing tables, including device routing tables and port routing tables, and obtains the device IDs of all terminal devices in the system; at the same time, link faults are proactively discovered during the retrieval process.

[0045] Route matching matches the device IDs of all terminal devices in the system with the routing table in the system, and based on the matching results, locates the switch node with incorrect routing configuration, and further locates the routing error to the corresponding port of the switch.

[0046] Route retrieval specifically includes:

[0047] 1) Access the device connected to the SRIO interface of the lower computer;

[0048] 2) Determine the type of the connected device. If it is a terminal device, obtain the device information of the terminal device and the retrieval process ends;

[0049] 3) If it is a switch device, mark the switch and start from the first port of the switch to obtain the port link status and routing information. If the link is abnormal, access the next port of the switch to obtain the port link status and port routing information until the link status of the next port of the switch is normal. Then access the device connected to the port.

[0050] 4) Repeat 3) until the connected device is a terminal device or a marked switch device.

[0051] 5) If it is a terminal device, the device information of the terminal device is also obtained.

[0052] 6) Return to the previous level switch and obtain the port link status of the next port of the switch; if the link is abnormal, access the next port of the switch to obtain the port link status and port routing information until the link status of the next port of the switch is normal; then access the device connected to the port;

[0053] 7), repeat 3), 4), 5), and 6) until all switch ports in the system are accessed.

[0054] 8), the retrieval process ends.

[0055] The RapidIO system link fault diagnosis method also includes system operation fault reporting, in which node device faults during system operation are actively reported via port-write data packets.

[0056] The present application also includes a RapidIO system link fault isolation method.

[0057] A RapidIO system link fault isolation method is used to isolate the above-diagnosed fault.

[0058] When a routing failure occurs, the data packets with the routing failure are discarded.

[0059] When a link fails, the port of the failed node is closed and the data packets sent to the failed port are discarded.

[0060] When a routing failure occurs, the fault handling unit resets the port routing of the switch at the node with the routing failure, causing the port to discard the packets caused by the routing failure, thus isolating the routing failure. This prevents the routing failure from causing link blockage and system crash.

[0061] This application can retrieve routing information in the system and obtain information about all terminal devices in the system, including device ID, manufacturer ID, etc. It uses routing matching technology to determine whether the routing between two terminal devices is correct and accurately locate the faulty node with routing errors in the system. When a link failure occurs in the system, it can locate the link fault node and isolate the fault point, ensuring the safe operation of the system, avoiding extreme situations such as link blockage caused by routing failure or link failure, and thus leading to system crash, thereby improving the reliability of the RapidIO system.

[0062] This application addresses the widespread routing and link failures in RapidIO systems, proposing a fault diagnosis and isolation method to improve system reliability. It also facilitates system maintenance by reporting routing information, terminal device information, and fault information within the system. Given RapidIO's widespread application in high-performance embedded systems, high-energy digital signal processing systems, 3G / 4G mobile communication base stations, military fighter jets, carrier-based aircraft electronics, and industrial control, this method has broad application prospects and enormous value.

[0063] like Figure 1 As shown, the principle of the implementation method of this application is mainly divided into three parts: the lower computer, the RpadiO switch network and the upper computer interface.

[0064] The lower computer is responsible for discovering, diagnosing, locating, and isolating routing and link faults in the RapidIO system, and sending routing information, terminal device information, and fault information in the system to the upper computer interface. The lower computer can be a PowerPC processor, ARM processor, or DSP processor with a RapidIO controller. The lower computer consists of five parts: routing retrieval unit, fault diagnosis unit, fault processing unit, network control unit, and RapidIO control unit. Its workflow is as follows: Figure 2 The lower computer retrieves routing information and obtains terminal device information, and locates routing fault nodes based on the routing information and terminal device information; obtains link status information during the routing retrieval process and enables the switch's fault information sending function; locates fault nodes in the system based on link status information and link fault information; and isolates routing fault and link fault nodes.

[0065] The switch network consists of one or more RapidIO switches that support the port-write mechanism and is used for high-speed communication between multiple end devices.

[0066] The host computer interface is used to display routing information, terminal equipment information and fault information in the system. Fault information includes routing faults and link faults.

[0067] In one embodiment, a RapidIO system link fault diagnosis and isolation method includes:

[0068] 1. The retrieval unit is used to retrieve routing information and terminal device information on the RapidIO system. The routing retrieval process is as follows: Figure 2 ; The specific method of using the depth-first algorithm to obtain routing information is:

[0069] 1) The lower computer accesses the switch connected to it in the switching network through the RapidIO interface unit; by configuring the error detection enable register and the port-write enable register, the switch port error information active notification function through the port-write data packet is enabled, and a unique 32-bit tag is set for the switch.

[0070] 2) Access the first port on the switch.

[0071] 3) Obtain the port routing information of the port. If there is no port routing information, obtain the device routing information on the switch as the port routing information, and obtain the status information of the port at the same time, and record the obtained routing information and port status information.

[0072] 4) If the physical link connection between the port and the peer device is unsuccessful or the port is in the Stop state, access the next port on the switch and jump to step 5); if the port status is successful and there is no error in the link with the peer device, jump to step 9).

[0073] 5) If all ports on the switch have been accessed, then access the unretrieved port of the upper-level switch and jump to step 6); otherwise, access the next port of the switch and jump to step 3).

[0074] 6) If the switch is connected to the lower computer, proceed to the next step; otherwise, jump to step 8);

[0075] 7) Check whether the last port of the switch has completed the search. If so, the search route ends; otherwise, access the next port of the switch and jump to step 3).

[0076] 8) Check whether the last port of the switch has been searched. If so, access the unsearched port of the upper-level switch and jump to step 5); otherwise, access the next port of the switch and jump to step 3).

[0077] 9) Access the performance register of the opposite device connected to the port through the maintenance package, and determine whether the device is a switch device or a terminal device.

[0078] 10) If it is a terminal device, obtain the device ID information of the terminal device, then access the switch connected to the device and jump to step 5); if it is a switch device, check the tag flag of the switch. If the tag value has not been set by the retrieval unit, it indicates that the switch device is a newly retrieved device and proceed to the next step; if the tag value has been set by the retrieval unit, it indicates that the switch device has been retrieved, record the switch tag information and the connection information of the upper-level switch connection port, query the next port of the switch, and then jump to step 3).

[0079] 11) Enable the switch port error information active notification function through port-write data packets by configuring the error detection enable register and port-write enable register, and set a unique 32-bit tag for the switch.

[0080] 12) Configure the switch's port packet counting function and initiate a maintenance read operation to the switch to check the packet counts of all ports on the switch. The port whose packet count increases by one is the port on the switch connected to the upper-level switch.

[0081] 13) Go to step 3).

[0082] The RapidIO control unit executes the processing commands from the data processing and control unit, sends the corresponding maintenance packets, and obtains the return values.

[0083] 2. The RapidIO control unit executes the processing command from the data processing and control unit, sends the corresponding maintenance packet, and obtains the return value.

[0084] 3. The fault diagnosis unit is used to detect routing faults and link faults and accurately locate the faulty node. The routing fault diagnosis process is as follows:

[0085] 1) Assume that there are M terminal devices in the system, and their device IDs are (ID1, ID2…IDm).

[0086] 2)i equals 1, j equals 2.

[0087] 3) Determine whether the routing of IDi and IDj (i is not equal to j, i, j = 2, 3...m) is normal; the judgment process is as follows:

[0088] a) Find the port of the switch connected to IDi;

[0089] b) Check whether IDj exists in the routing information on the port. If not, it indicates that the IDi->IDj routing is faulty, and the switch port is marked as a faulty node for the route from IDi to IDj, and then the query process is exited. If IDj exists in the routing information, the switch port pointed to by IDj is searched, and the device connected to the port is searched based on the device association information obtained in the retrieval unit.

[0090] c) If the device is a terminal device and the device ID is IDj, it indicates that the IDi->IDj routing is normal, and then the query process is exited; if the device is a switch device, obtain the ingress port on the switch pointed to by IDj;

[0091] d) Repeat step b.

[0092] 4) IDj points to the next ID and repeats step 3 until the routing between IDi and all other terminal devices is traversed.

[0093] 5) IDi points to the ID of the next terminal device, and steps 3 and 4 are repeated to complete the diagnosis of routing conditions between all terminal devices.

[0094] 6) When the bidirectional routing between the two terminal devices is normal, it indicates that the routing between the two devices is normal, otherwise the routing between the two devices is faulty.

[0095] 7) End.

[0096] When a C link fails, the switch at the faulty node will actively send a port-write data packet containing fault information and switch information. The fault diagnosis unit locates the switch port and path that sent the fault based on the obtained port-write data packet.

[0097] 4. The fault handling unit is used to handle link failures and routing failures. When a routing failure occurs, the fault handling unit sets the port routing of the switch at the routing failure node so that the port will discard the data packets of the routing failure to avoid link blockage caused by the routing failure, which in turn causes the system to crash. When a link fails, the fault handling unit will shut down the switch port that sent the failure and configure the switch to discard the data packets flowing to the faulty port to achieve fault isolation.

[0098] 5. The network control unit is used to receive and send network data packets to complete network communication between the upper computer and the lower computer.

[0099] 6. The host computer interface is used to display the switch interconnection information, routing information, terminal device information in the system, and display fault information at the fault node.

[0100] 7. The switch network consists of one or more RapidIO switches, and at least one switch in the network is connected to the host computer.

[0101] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A RapidIO system link fault diagnosis method, characterized in that: Including active diagnosis, active diagnosis includes: Route retrieval: Searches routes on all switches in the RapidIO system, using a depth-first algorithm to retrieve the system's routing tables, including device routing tables and port routing tables. It also obtains the device IDs of all terminal devices in the system, proactively detecting link failures during the retrieval process. Route matching: matches the device IDs of all terminal devices in the system with the routing table in the system, and locates the switch node with routing configuration errors based on the matching results, and further locates the routing error to the corresponding port of the switch; Route retrieval specifically includes: 1) Access the device connected to the SRIO interface of the lower computer; 2) Determine the type of the connected device. If it is a terminal device, obtain the device information of the terminal device and the retrieval process ends; 3) If it is a switch device, mark the switch and start from the first port of the switch to obtain the port link status and routing information. If the link is abnormal, access the next port of the switch to obtain the port link status and port routing information until the link status of the next port of the switch is normal. Then access the device connected to the port. 4) Repeat 3) until the connected device is a terminal device or a marked switch device; 5) If it is a terminal device, obtain the device information of the terminal device at the same time; 6) Return to the previous level switch and obtain the port link status of the next port of the switch; if the link is abnormal, access the next port of the switch to obtain the port link status and port routing information until the link status of the next port of the switch is normal; then access the device connected to the port; 7), repeat 3), 4), 5), and 6) until all switch ports in the system are accessed; 8), the retrieval process ends.

2. The RapidIO system link fault diagnosis method according to claim 1, wherein: It also includes system operation fault reporting. Node device faults during system operation are actively reported through port-write data packets.

3. A RapidIO system link fault isolation method, characterized in that: Isolating the fault diagnosed as claimed in any one of claims 1 or 2; When a routing failure occurs, the data packets of the routing failure are discarded; When a link fails, the port of the failed node is closed and the data packets sent to the failed port are discarded.

4. The RapidIO system link fault isolation method according to claim 3, wherein: When a routing failure occurs, the fault processing unit resets the port routing of the switch at the routing failure node so that the port discards the data packets of the routing failure and completes the routing failure isolation.

Images