JPH04158449A - Multicomputer system - Google Patents

Abstract

PURPOSE:To immediately discriminate a fault whether it is due to the operation abnormality of another computer system or the one of a monitoring route itself by providing communication control equipment and communication routes >=2 with different communication procedures, respectively as the monitoring route. CONSTITUTION:When the fault occurs on the communication control equipment 106 or line connected to it, software on a central processing unit 102 detects the fact that no monitoring on the communication control equipment 106 can be performed, however, another two communication routes are operated normally, therefore, it can be discriminated that a monitoring fault on the communication control equipment 106 is not the operating fault of a computer system 108. When the monitoring faults occur on the monitoring route AA of the communication control equipment 105, the monitoring route BB of the communication control equipment 106, and the monitoring route CC of the communication control equipment 107 simultaneously, the software on the central processing unit 102 discriminates the operating fault as the one of the computer system 108. Thereby, it is possible to immediately discriminate whether the fault is due to the one of another computer system or the one of the monitoring route itself.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to mutual operation monitoring between a plurality of computer systems, and particularly to monitoring paths thereof.

[Prior Art] Conventionally, in a multi-computer system consisting of a plurality of computer systems, even if multiple paths are prepared for monitoring other computer systems, the communication procedure may be a single one. , the communication control device was single.

[Problem to be solved by the invention] Conventionally, even if multiple monitoring paths are prepared for mutual monitoring of operations between multiple computer systems, it is difficult to use a single communication procedure or a single communication control device as the monitoring path. In the system, the independence of the monitoring path is lost, and when a monitoring failure occurs, it is difficult to determine whether the failure is due to a failure in another computer system or the monitoring path itself.

Means for solving ra, s] A multi-computer system composed of a plurality of computer systems of the present invention uses different communication channels as monitoring paths for one computer system to monitor the operating status of other computer systems. By using two or more communication control devices and communication routes with procedures and maintaining the independence of each other's monitoring routes, even if one of them becomes a monitoring failure, it will not affect the operation of other computer systems. It has a means that can immediately determine whether the problem is due to an abnormality or a failure in the monitoring path itself.

[Example] Next, the present invention will be explained with reference to the drawings.

FIG. 1 is a block diagram showing one embodiment of the present invention.

Peripheral input/output devices are omitted.

=! It is assumed that the software on the central processing unit 102 on the computer system 1.01 monitors the operating status of the computer system 108.

As a monitoring route at that time, Beniji A is monitored using communication procedure A between the communication control device 105 and the communication control device 112.
A, path BB monitored using communication procedure B between communication control device W106 and communication control device 113, communication control device ff1
107 and the communication control device 114, three routes are used: route CC, which is monitored using communication procedure C. These three routes maintain their independence because their communication control devices and communication procedures are different.

If a failure occurs on the communication (4) control unit 106 or the line connected to it, the central processing unit 102J
:, the software detects that monitoring is not possible on the communication control device 108, but since the other two communication paths are operating normally, the monitoring failure on the communication control device 106 is =1. It can be determined that the computer system A 108 is not an operating staff.

If a monitoring failure occurs in three paths at the same time: monitoring path AA of the communication control device 105, monitoring path BB of the communication control device 106, and monitoring path CC of the communication control device 107, the software on the central processing unit 102 The monitoring failure can be determined as an operational failure of the computer system 108.

[Effects of the Invention] As explained above, the present invention enables monitoring between a plurality of computer systems, and even if monitoring becomes impossible, it is possible to determine whether it is due to a failure in another computer system or the monitoring path itself. It becomes possible to immediately determine whether there is a failure.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing one embodiment of the present invention. 101... Computer system, 102... Central processing bag ffi, 103... Main storage device, 104... System bus, 105... Communication control device, 106... Communication control device, 107... - Communication control device, 108... Computer system, 109... Central processing unit, 110...
・Main storage device, 111...System bus, 112...
・Communication control device, 113...Communication control device, 114・
...Communication control device, AA...Monitoring route, BB...Monitoring route, CC...Monitoring route. Agent Patent Attorney Sumihei Yamashita

Claims (1)

[Claims] In a multi-computer system consisting of multiple computer systems, one computer system can use it as a monitoring path to monitor the operating status of other computer systems.
By preparing two or more communication control devices and communication routes each with different communication procedures, the independence of each monitoring route is maintained, and therefore, even if one of the routes becomes a monitoring failure, it will not be affected by the other. A multi-computer system characterized by being able to immediately determine whether the problem is due to an abnormal operation of the computer system or a failure in the monitoring path itself.