CN111478814A - Anti-interference RapidIO exchanger data exchange implementation method - Google Patents

Abstract

The invention discloses an anti-interference RapidIO exchanger data exchange implementation method, and belongs to the technical field of communication. The method for realizing the data exchange of the anti-interference RapidIO exchanger comprises a normal port response exchanger report fault processing method and a normal port non-timely response exchanger report fault processing method. The invention can realize that the transmission message is not lost and reduce the number of lost packets for the port fault interruption caused by the transient interference.

Description

Anti-interference RapidIO exchanger data exchange implementation method

Technical Field

The invention relates to the technical field of communication, in particular to an anti-interference RapidIO exchanger data exchange implementation method.

Background

RapidIO is a widely used high speed, highly reliable bus capable of speeds up to several gigabytes per second. RapidIO of multiple nodes requires RapidIO switches for data interaction. When some nodes are in an environment which is easy to interfere, such as electromagnetic interference, ionization interference and the like, because of needs, link failures frequently occur; the buffer area in the switch is only several kilobytes, and the RapidIO can cause the loss of data sent to a fault node due to the overflow of the buffer area in the process of processing frequent faults, so that a mechanism for automatically recovering the data overflowed by the buffer area in the fault process is necessary for a RapidIO switching network in a working and interference environment.

In the existing solution, the switch buffers the data destined to the failed port in the transmit buffer of the failed port. When a fault port has a sending fault, the fault response message informs each normal port needing to perform message transmission with the fault port through the exchanger, and the exchanger discards the message sent to the fault port after each normal port responds, so that packet loss can be caused.

Disclosure of Invention

The invention aims to provide an anti-interference RapidIO exchanger data exchange implementation method to solve the problem that a RapidIO exchanger working in an easily interfered environment is easy to lose transmission messages due to port failure.

In order to solve the technical problem, the invention provides an anti-interference RapidIO exchanger data exchange implementation method, which comprises a normal port response exchanger report fault processing method and a normal port non-timely response exchanger report fault processing method; wherein the content of the first and second substances,

the normal port response switch report fault handling method comprises the following steps:

the exchanger responds to the failure port and marks;

the exchanger requires all the data sent by the normal port to the fault port to make fault response;

the exchanger transfers the unsent message of the fault port sending buffer area to the backup space and records the message in sequence;

the normal port responds to the fault, stops sending to the fault port and waits for the fault to be relieved;

after the failure is relieved, the exchanger takes out the unsent message of the failure port from the backup space and puts the unsent message into a sending buffer area;

after the message in the original fault port sending buffer area is sent, normal data transmission is carried out;

the method for processing the failure of the normal port which does not respond to the report of the switch in time comprises the following steps:

the normal port does not respond to the fault, and continues to send messages to the fault port;

the exchanger backups the messages continuously sent to the fault port and numbers the messages according to the sequence of the messages;

before the failure is relieved, the exchanger continuously checks whether the backup space overflows or not;

if the overflow happens, the new message covers the old message and records that the overflow happens and the fault port is disconnected;

if not, the exchanger delays to inform other ports that the original fault port is normal; the exchanger takes out the message from the backup space according to the serial number and sends the message to the original fault port; the exchanger takes out all the backup space messages to inform other ports that the original fault ports are normal; the failed port flag is cancelled.

The invention provides an anti-interference RapidIO exchanger data exchange implementation method, which comprises a normal port response exchanger report fault processing method and a normal port non-timely response exchanger report fault processing method. The invention can realize that the transmission message is not lost and reduce the number of lost packets for the port fault interruption caused by the transient interference.

Drawings

FIG. 1 is a flow diagram of a normal port response switch report failure handling method;

fig. 2 is a flow chart illustrating a method for handling a failure of a normal port not responding to a switch report in time.

Detailed Description

The following describes in detail an implementation method of data exchange of an anti-interference RapidIO switch according to the present invention with reference to the accompanying drawings and specific embodiments. Advantages and features of the present invention will become apparent from the following description and from the claims. It is to be noted that the drawings are in a very simplified form and are not to precise scale, which is merely for the purpose of facilitating and distinctly claiming the embodiments of the present invention.

Example one

The invention provides an anti-interference RapidIO exchanger data exchange implementation method, which comprises a normal port response exchanger report fault processing method and a normal port non-timely response exchanger report fault processing method; wherein the content of the first and second substances,

the normal port response exchanger report failure processing method is as shown in fig. 1, firstly the exchanger responds to a failure port, the exchanger marks the failure port, then the exchanger requires all normal ports sent to the failure port to respond to the failure, the exchanger transfers the unsent message of the failure port sending buffer area to a backup space and records the information in sequence, then the normal port responds to the failure and stops sending the message to the failure port, then the exchanger takes out the unsent message of the failure port from the backup space and puts the unsent message into the sending buffer area after the failure is removed, and finally the original failure port sends the message in the buffer area and transmits normal data after the message is sent;

the method for processing the report fault of the exchanger with the normal port not responding to the fault in time is shown in fig. 2, firstly, the normal port not responding to the fault in time and still continuously sending the message to the fault port, and then the exchanger backups the message continuously sent to the fault port and numbers the message according to the message sequence; the switch keeps checking whether the backup space overflows before the failure is resolved:

if the backup space of the exchanger overflows before the failure is relieved, the exchanger marks the failure port and then disconnects the failure port;

if the backup space of the exchanger is not overflowed when the fault is relieved, the exchanger delays and informs other ports that the original fault port is normal, the exchanger takes out the message from the backup space according to the serial number and sends the message to the original fault port, and finally the exchanger takes out all the backup space messages and informs other ports that the original fault port is normal and cancels the mark of the fault port.

The above description is only for the purpose of describing the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention, and any variations and modifications made by those skilled in the art based on the above disclosure are within the scope of the appended claims.

Claims (1)

1. An anti-interference RapidIO exchanger data exchange implementation method is characterized by comprising a normal port response exchanger report fault processing method and a normal port non-timely response exchanger report fault processing method; wherein the content of the first and second substances,

the normal port response switch report fault handling method comprises the following steps:

the exchanger responds to the failure port and marks;

the exchanger requires all the data sent by the normal port to the fault port to make fault response;

the exchanger transfers the unsent message of the fault port sending buffer area to the backup space and records the message in sequence;

the normal port responds to the fault, stops sending to the fault port and waits for the fault to be relieved;

after the failure is relieved, the exchanger takes out the unsent message of the failure port from the backup space and puts the unsent message into a sending buffer area;

after the message in the original fault port sending buffer area is sent, normal data transmission is carried out;

the method for processing the failure of the normal port which does not respond to the report of the switch in time comprises the following steps:

the normal port does not respond to the fault, and continues to send messages to the fault port;

the exchanger backups the messages continuously sent to the fault port and numbers the messages according to the sequence of the messages;

before the failure is relieved, the exchanger continuously checks whether the backup space overflows or not;

if the overflow happens, the new message covers the old message and records that the overflow happens and the fault port is disconnected;

if not, the exchanger delays to inform other ports that the original fault port is normal; the exchanger takes out the message from the backup space according to the serial number and sends the message to the original fault port; the exchanger takes out all the backup space messages to inform other ports that the original fault ports are normal; the failed port flag is cancelled.

Images