JPH0619733B2 - Tracer device - Google Patents

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a tracer device, and more particularly to a fault processing trace function provided in a fault processing device.

2. Description of the Related Art Conventionally, in a fault processing device provided for each system of an information processing system having a coupled multi-system configuration,
Since it only handles failure processing of its own system, it has only a trace function of failure processing in its own system.

That is, in the coupled multi-system configuration, the failure processing device generally has only a diagnostic interface with each device of its own system due to the limitation of the amount of hardware,
The fault handling device can only deal with faults of the device connected by the diagnostic interface.

In such a conventional tracer device, since the fault processing device has only the trace function of the fault processing in its own system, in the information processing system of the coupled multi-system configuration, the faults of its own system and other systems There is a drawback in that the mutual time relationship cannot be seen in the process of the failure processing performed by the processing device.

Therefore, when a failure occurs in a device of its own system and a failure occurs in a device of another system as well, the time relationship between them cannot be known, so traces can be made in each failure processing device. However, there is a drawback in that a large amount of time is spent in analyzing a failure performed according to the contents.

An object of the present invention is to eliminate the above-mentioned drawbacks of the conventional ones, and it is possible to trace the time relationship in the process of failure processing performed by a plurality of failure processing devices, and to spend time for failure analysis. An object of the present invention is to provide a tracer device that can shorten the time.

Another object of the present invention is to enable each of the fault processing devices of the other system and the own system to recognize each process of the fault processing performed by the fault processing devices of the own system and the other system, thereby reducing the time spent for failure analysis. It is to provide a tracer device that can be shortened.

The tracer device according to the present invention is a tracer device of an information processing system including a plurality of fault processing devices each having a tracer memory for storing fault information in the order of fault occurrence,
Sending means for sending a notification signal for notifying the occurrence of a failure in the own system to the failure processing device in another system, failure information collected when a failure occurs in the own system, and a failure indicating that a failure has occurred in another system Switching means for selectively switching the occurrence information and storing it in the tracer memory of the failure processing device of the own system, and when the failure occurs in the own system, the failure information of the own system by the own system switching means A means for storing the information in the tracer memory of the failure processing device and at the same time controlling the notification signal from the sending means of the own system to be sent to the failure processing device of the other system, and the failure processing of the other system when a failure occurs in the other system In response to the notification signal from the device, the switching means of the fault processing device of the own system is switched to control the failure occurrence information of the other system to be stored in the tracer memory of the fault processing device of the own system. Characterized in that it has a plurality of fault processing device each.

Another tracer device according to the present invention is a tracer device of an information processing system including a plurality of fault processing devices each having a tracer memory for storing fault information in order of fault occurrence, and for notifying occurrence of a fault in its own system. Notification signal and failure processing information indicating a failure processing process in the failure processing device of the own system to a failure processing device of another system, failure information collected when a failure occurs in the own system, and the failure information in the other system. Switching means for selectively switching between failure occurrence information indicating that a failure has occurred and failure processing information from a failure processing device of another system and storing it in the tracer memory of the failure processing device of the own system, and a failure in the own system When a fault occurs, the fault information of the self-system is stored in the tracer memory of the fault processing device of the self-system by the switching means of the self-system, and at the same time from the sending-out means of the self-system. Means for controlling the signal and the fault processing information to be sent to the fault processing device of the other system, and switching of its own system in response to a notification signal from the fault processing device of the other system when a fault occurs in the other system Each of the plurality of fault processing devices has means for switching the means to control so that the fault occurrence information of the other system and the fault processing information from the fault processing device of the other system are stored in the tracer memory of the fault processing device of the own system. It is characterized by

Embodiment Next, an embodiment of the present invention will be described with reference to the drawings.

FIG. 1 is a block diagram showing the configuration of an embodiment of the present invention. In the figure, the failure processing devices 1 and 2 according to an embodiment of the present invention respectively include microprogram control units 11 and 21.
, Tracer memories 12 and 22, and tracer controller 1
3 and 23 and own system trace data registers 14 and 24
And other system tracer interrupt data registers 15 and 25,
It is composed of selection circuits 16 and 26.

FIG. 2 is a block diagram showing the configuration of an information processing system to which the failure processing devices 1 and 2 of FIG. 1 are connected. In the figure, the failure processing devices 1 and 2 are diagnostic interfaces 5-i, respectively.
(i = 0, 1, ..., N-1, n), 6-i is connected to the data processing device 3-i, 4-i, and data processing is performed via this diagnostic interface 5-i, 6-i. Fault processing for the devices 3-i and 4-i is being performed. The failure processing of these data processing devices 3-i, 4-i generally means collection of failure information of the failed data processing device, retry processing and disconnection processing, or system stop processing when a serious failure occurs. and so on.

The operation of the embodiment of the present invention will be described with reference to FIGS. 1 and 2.

Here, a case where a failure occurs in the data processing device 3-i and the failure processing device 1 performs the failure processing through the diagnostic interface 5-i will be described. Here, the system composed of the failure processing device 1 and the data processing device 3-i is used as its own system, and the failure processing device 2 and the data processing device 4 are used.
-Set the system configured by and as another system.

The failure processing device 1 performs the failure processing of the data processing device 3-i by the microprogram control unit 11, and traces the process of this failure processing (contents of the failure processing described above according to the content of the failure) by the tracer control unit 13. Memory 12
To store.

At this time, at the same time, the micro program control unit 11 stores the occurrence of a fault in its own system and the process of the fault processing in the tracer memory 22 of the other system in the process of performing the fault processing. The signal 102 is output, and the tracer interrupt data 103 indicating the occurrence of a failure in the own system and the process of the failure processing is sent to the other system tracer interrupt data register 25.

In the failure processing device 2 of the other system, the micro program control unit 2
1 is a tracer interrupt instruction signal 102 from the fault processing apparatus 1.
When it receives the selection signal, it outputs a selection signal 201 for switching between the output of the own system trace data register 24 and the output of the other system tracer interrupt data register 25 to the selection circuit 26, and the selection circuit 2
6 switches to select the output of the other system tracer interrupt data register 25 from the output of the own system trace data register 24.

As a result, the tracer interrupt data 103 from the failure processing apparatus 1 is stored in the tracer memory 22 of the failure processing apparatus 2, and the tracer memory 22 shows the occurrence of a failure in the own system from the failure processing apparatus 1 and the process of the failure processing. Can be stored.

Therefore, the fault processing device 2 of the other system identifies the trace data stored in the tracer memory 22 so that the fault processing device 1 responds to the occurrence of the fault in its own system and the fault.
It is possible to recognize the process of the fault processing performed by the above, and the time relationship between the occurrence of the fault in the own system and the process of the processing of the fault can be seen in the fault processing device 2 of the other system.

Further, when a failure occurs in the data processing device 4-i and the failure processing is performed by the failure processing device 2, the micro program control unit 2 performs the same processing operation as described above.
1 to the microprogram controller 11 of the failure processing device 1
And tracer interrupt instruction signal 202 and tracer interrupt data 203 to the other system tracer interrupt data register 15, respectively.

In the fault processing device 1, when the microprogram control unit 11 receives the tracer interrupt instruction signal 202 from the fault processing device 2, it outputs the selection signal 101 to the selection circuit 16 and switches the selection circuit 16 to cause a fault in the tracer memory 12. The tracer interrupt data 203 from the processing device 2 is stored.

As a result, the tracer interrupt data 203 from the failure processing device 2 is stored in the tracer memory 12 of the failure processing device 1, and the tracer memory 12 shows the occurrence of a failure in the other system from the failure processing device 2 and the process of the failure processing. Can be stored.

Therefore, the fault processing device 1 of its own system discriminates the trace data stored in the tracer memory 12 so that the fault processing device 2 can cope with the occurrence of the fault in the other system and the fault.
It is possible to recognize the process of the fault processing performed by the system, and to see the time relationship between the fault occurrence in the other system and the process of the fault processing in the fault processing apparatus 1 of the own system.

As described above, when the failure processing device 1 or the failure processing device 2 performs the failure processing, the tracer interrupt instruction signals 102 and 202 and the tracer interrupt data 103 and 203 are sent to the failure processing device 2 or the failure processing device 1, and the tracer memory 22 or The tracer interrupt data 103, which is stored in the tracer memory 12,
By storing 203, it is possible to trace the time relationship in the process of the failure processing performed by the failure processing devices 1 and 2.

Therefore, even when a failure occurs in the data processing device 4-i due to a failure in the data processing device 3-i, the failure processing device
Because the time relationship in the process of failure processing performed by 2 is known,
The time spent analyzing the failure can be shortened.

In the embodiment of the present invention, the tracer memories 12 and 22 store the occurrence of a failure in another system and the failure processing process of the other failure processing devices 2 and 1 for the failure. It is sufficient to store either one of the occurrence of the error and the process of failure processing.

In addition, the failure processing devices 1 and 2 allow other failure processing devices 2 and
The interrupt signal is output to 1, but this informs the fault processing units 2 and 1 that a fault has occurred in another system,
Moreover, it is clear that the tracer memories 22 and 12 of the failure processing devices 2 and 1 can store the information on the process of the failure processing in the failure processing devices 1 and 2, and the invention is not limited to these.

As described above, according to the present invention, when a failure occurs in the own system, the failure information collected by the own apparatus is stored in the tracer memory of the own apparatus, and at the same time, the occurrence of the failure in the own system. By sending a notification signal for notifying the fault processing device of the other system to the fault processing device of the other system so that the occurrence of the fault in this system is stored in the tracer memory of the fault processing device of the other system. As a result, it is possible to trace the time relationship in the process of failure processing performed by a plurality of failure processing devices, and to shorten the time spent for failure analysis.

Another advantage of the present invention is that by storing the occurrence of a fault in the own system and the process of processing the fault in the tracer memory of the fault processing device of the other system, the fault processing of the own system and the other system is performed. This means that the failure processing process performed by the apparatus can be recognized by the failure processing apparatus of the other system and the own system, and the time spent for failure analysis can be shortened.

[Brief description of drawings]

FIG. 1 is a block diagram showing the configuration of an embodiment of the present invention, and FIG. 2 is a block diagram showing the configuration of an information processing system to which the failure processing device of FIG. 1 is connected. Description of symbols of main parts 1, 2 ... Fault processing device 11, 21 ... Micro program 12, 22 ... Tracer memory 13, 23 ... Tracer control unit 14, 24 ... Local trace data register 15, 25 ... ... Other system tracer interrupt data register 16, 26 ... selection circuit 102, 202 ... tracer interrupt instruction signal 103, 203 ... tracer interrupt data

Claims (2)

[Claims] 1. A tracer device of an information processing system including a plurality of fault processing devices each having a tracer memory for storing fault information in the order of fault occurrence, wherein a notification signal for notifying occurrence of a fault in its own system is provided. A failure of the own system by selectively switching between sending means for sending to a failure processing device of another system, failure information collected when a failure occurs in the own system, and failure occurrence information indicating that a failure has occurred in the other system The switching means for storing in the tracer memory of the processor and the failure information of the own system by the switching means of the own system when a failure occurs in the own system are stored in the tracer memory of the failure processing device of the own system and at the same time of the own system. Means for controlling the notification signal from the sending means to be sent to the fault processing device of another system;
When a failure occurs in another system, in response to a notification signal from the failure processing device of the other system, the switching means of the failure processing device of the own system is switched and the failure occurrence information of the other system is traced to the failure processing device of the own system. A tracer device comprising means for controlling to store in a memory in each of the plurality of fault processing devices. 2. A tracer device of an information processing system including a plurality of fault processing devices each having a tracer memory that stores fault information in the order of fault occurrence, and a notification signal for notifying occurrence of a fault in its own system. Sending means for sending the failure processing information indicating the failure processing process in the failure processing device of the own system to the failure processing device of the other system, the failure information collected when the failure occurs in the own system, and the failure occurred in the other system Switching means for selectively switching the failure occurrence information indicating that the failure processing information from the failure processing device of the other system and storing it in the tracer memory of the failure processing device of the own system, and when a failure occurs in the own system In addition, the failure information of the own system is stored in the tracer memory of the failure processing device of the own system by the switching means of the own system, and at the same time, the notification signal and the failure processing from the sending means of the own system. And a means for controlling so as to send the information to the fault processing device of the other system, and switching the switching means of the own system in response to a notification signal from the fault processing device of the other system when a fault occurs in the other system. Each of the plurality of failure processing devices has means for controlling to store the failure occurrence information of the system and the failure processing information from the failure processing device of the other system in the tracer memory of the failure processing device of the own system. Tracer device.