JPH05100885A - Fault detecting system for information processing system having shared storage device - Google Patents

Abstract

PURPOSE:To perfectly separate an information processor where a fault occurs from a shared storage device by detecting the fault of the respective information processors. CONSTITUTION:The information processors 10 and 20 which have diagnostic circuits 11 and 22 diagnosing whether the fault exists or not and the storage device which has a fault detecting circuit 31 are provided. The storage device 30 is recognized to be connected with the respective information processors by connection state signals 011 and 021 and the fault detecting circuit 31 checks to recognize whether the fault exists in the respective information processors or not by recognizing signals 013 and 023 so as to diagnose by using the respective diagnostic circuits. When diagnostic result is normal, response is transmitted by response signals 012 and 013. When the fault exists, response is not transmitted and the fault detecting circuit 31 recognizes that the information processor which does not response has the fault and operates the separation of the information processor. Therefore, the fault of respective information processors can be detected and the information processor where the fault occurs is separated from the shared storage device so that the reliability is improved in the information processor system having the shared storage device.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an information processing apparatus system, and more particularly to a failure detection method in an information processing system having a shared storage device.

[0002]

2. Description of the Related Art Conventionally, there are the following failure detection methods in an information processing system having this type of shared storage device.

A notification signal indicating that another information processing apparatus is logically connected to another information processing apparatus and is operating is provided from the shared storage device to the plurality of information processing apparatuses. Is still at logic 1 even after a certain period of time, it is detected from a certain information processing device that another information processing device has a failure, and the storage device is forcibly used.

[0004]

In the fault detecting method in the above-mentioned information processing system having the shared storage device, the notification signal is monitored for a certain period of time, and the fault is effectively detected. Absent.

In addition, even in the operation of logically disconnecting the shared storage device from the information processing device in which the failure has occurred, the information processing device in which the failure has occurred uses the shared storage device, and malfunctions occur. There is a drawback that it will let you.

An object of the present invention is to provide a storage device with a storage device shared by a plurality of information processing devices and to provide a plurality of diagnostic circuits in the storage device for diagnosing whether or not a failure has occurred in each of the plurality of information processing devices. The connection status signal from each information processing device detects that the information processing device is connected to each information processing device, and outputs a confirmation signal to each diagnostic circuit of each information processing device to detect a failure that occurred in each information processing device. By having a failure detection circuit and outputting a response signal directed to a storage device that responds to the presence or absence of a failure by its confirmation signal, the above-mentioned drawbacks are eliminated, and failures in each information processing apparatus can be detected and shared. It has a shared storage device capable of completely separating the storage device and the information processing device in which a failure has occurred, and improving the reliability as an information processing device system having the shared storage device. And to provide a failure detection method in multi-address processing system.

[0007]

A failure detection method in an information processing system having a shared storage device according to the present invention is a failure detection method in an information processing apparatus system having a storage device which is connected and shared by a plurality of information processing devices. , A diagnostic circuit for diagnosing whether or not a failure has occurred in each of the plurality of information processing devices, the storage device being connected to each of the information processing devices by a connection status signal from each of the plurality of information processing devices. Has a fault detection circuit that detects a fault and outputs a confirmation signal to each diagnostic circuit of each information processing device to detect a fault occurring in each information processing device. If there is no fault, each information processing device returns a response to the fault detection circuit by a response signal. Broadcasting processing apparatus returns no response, fault detection circuit performs an operation disconnect the faulty information processing apparatus that does not response.

[0008]

Embodiments of the present invention will now be described with reference to the drawings.

FIG. 1 is a block diagram of an information processing system having a shared storage device according to an embodiment of the present invention.

In FIG. 1, an information processing system having a shared storage device according to the present embodiment comprises information processing devices 10 and 20 having diagnostic circuits 11 and 22, a storage device 30, and a failure detection circuit 31. And connection status signal 01
1,021, confirmation signals 012,022, and response signal 0
There is a signal of 13,023.

FIG. 2 is a detailed diagram of the fault detection circuit 31 of this embodiment.

Referring to FIG. 2, the fault detection circuit 3 of the present embodiment.
1 is a failure monitoring circuit 32, a timer 33, and a detection circuit 3
4 and 4.

Next, the operation will be described.

Information processing devices 10 and 20 to storage device 30
Is shared. When the information processing devices 10 and 20 and the storage device 30 are physically connected, a connection status signal 01
1,021 becomes logical 1. The connection monitoring circuit 32 in the failure detection circuit 31 of the storage device 30 outputs the connection status signals 011 and 0.
21 is detected, the information processing devices 10 and 20 detect the storage device 30.
When it is connected to the detection circuit 34, the detection circuit 34 is notified.

The detection circuit 34 includes all the information processing devices 10 connected by the timer 33 at regular intervals.
For 20, the confirmation signals 012 and 022 are set to logic 1 in order.

As an example, when the confirmation signal 012 is set to logic 1 for the information processing apparatus 10, the diagnosis circuit 11 diagnoses the inside of the information processing apparatus 10 and if there is no failure, the information processing apparatus 10 sends a response signal 013. As a logical one.

From the above, it is known that the information processing apparatus 10 has no abnormality.

Thereafter, the detection circuit 34 outputs a confirmation signal to a logic 0.
Then, the confirmation with the information processing device 10 is completed.

Next, the confirmation signal 022 is set to logic 1 to operate the diagnostic circuit 22 to check the information processing apparatus 20 for any abnormality.

This operation is periodically performed by the timer 33 for the information processing devices 10 and 20.

When the information processing apparatus 10 is diagnosed by the diagnosis circuit 12 and there is an abnormality, the response signal 013 cannot respond as logic 1 and the detection circuit 34 in the failure detection circuit 31 knows the abnormality. The detection circuit 34 detects an abnormality in the information processing device 10 and disconnects the connection state between the information processing device 10 and the storage device 30 by the instruction signal 031 so that the information processing device 10 cannot access the storage device 30.

[0022]

As described above, the failure detection method in the information processing system having the shared storage device of the present invention has a storage device shared by a plurality of information processing devices,
A diagnostic circuit that diagnoses whether or not a failure has occurred in each of the plurality of information processing devices, and detects that the storage device is connected to each information processing device by a connection status signal from each of the plurality of information processing devices. It has a fault detection circuit that outputs a confirmation signal to each diagnostic circuit of each information processing device to detect a fault occurring in each information processing device, and is suitable for a storage device that responds to the presence or absence of a fault by the confirmation signal. By outputting a response signal, a failure of each information processing apparatus can be detected, and the shared storage apparatus and the failed information processing apparatus can be completely separated, and an information processing apparatus having a shared storage apparatus This has the effect of improving the reliability of the system.

[Brief description of drawings]

FIG. 1 is a block diagram of an information processing system having a shared storage device according to an embodiment of the present invention.

FIG. 2 is a detailed diagram of a fault detection circuit 31 of this embodiment.

[Explanation of symbols]

 10, 20 Information processing device 11, 22 Diagnostic circuit 30 Storage device 31 Fault detection circuit 32 Connection monitoring circuit 33 Timer 34 Detection circuit 011 and 021 Connection state signal 012 and 022 Confirmation signal 013 and 023 Response signal 031 Indication signal

Claims (1)

[Claims] 1. A failure detection method in an information processing apparatus system having a storage device connected to and shared by a plurality of information processing apparatuses, wherein a diagnosis is made as to whether or not a failure has occurred in each of the plurality of information processing apparatuses. The diagnostic circuit detects that the storage device is connected to each of the information processing devices by a connection state signal from each of the plurality of information processing devices, and outputs a confirmation signal to each diagnostic circuit of each of the information processing devices. Each information processing device has a failure detection circuit for detecting a failure, and each diagnostic circuit diagnoses whether each information processing device has a failure by the confirmation signal, and the result of the diagnosis is normal. If so, each of the information processing devices returns a response to the failure detection circuit by a response signal, and if there is a failure, each of the information processing devices does not return a response and the failure detection is performed. A failure detection method in an information processing system having a shared storage device, characterized in that the circuit performs a disconnection operation assuming that the information processing apparatus that does not respond has a failure.