JPH0261866A - Magnetic disk controller - Google Patents

Abstract

PURPOSE:To enable the trouble shoot in a short time by making a data read diagnosis on a different track when a read error generating frequency exceeds a specified frequency and judging a faulty part based on the obtained result. CONSTITUTION:When the occurrence of a read error is detected during the read operation of data from a magnetic disk, the specified read error frequency of the track, stored in a storage circuit 120 is read out by a microprogram control circuit 130 to make a comparison between the read error generating frequency and the specified read error frequency. As a result of the comparison, when the read error generating frequency exceeds the specified frequency, a data transfer circuit 110 is driven by the circuit 130 to make the data read diagnosis on a different track from the track where the read error has arisen. In the case of execution of the normal data read operation, a circuit in which the read error is generated is judged as a fault by the circuit 130. On the other hand, in the case of nonexecution of the normal data read operation, a magnetic disk device, etc., are judged by the circuit 130 to be faulty.

Description

DETAILED DESCRIPTION OF THE INVENTION (Field of Application) The present invention relates to a magnetic disk control device, and particularly to processing of read errors that occur during data read operations.

(Prior Art) Conventionally, in this type of magnetic disk control device, the following processing method has been used when a read error occurs during a data read operation for a magnetic disk device. In other words, when a read error occurs during a data read operation to a magnetic disk device, the magnetic disk control device only sends a report to the central processing unit that a read error has occurred in the relevant track of the magnetic disk device. Ta.

7, it was not possible to distinguish whether the cause of the read error was a defect in the relevant track of the magnetic disk device or a failure of the magnetic disk device or magnetic disk control device.

(Problem to be Solved by the Invention) In the above-described conventional magnetic disk control device, when a read error 2- occurs during a data read operation to the magnetic disk device, a read error occurs in the corresponding track of the magnetic disk device. Only this report was sent to the central processing unit. Therefore, it is difficult to determine whether the read error is caused by a defective track in the magnetic disk drive.
Another drawback is that it takes a very long time to find the cause of the failure because it cannot be determined whether the failure is in the magnetic disk device or the magnetic disk control device.

An object of the present invention is to detect a read error during a data read operation for any track of a magnetic disk device after sending a specified number of read errors per track for starting data read diagnosis from a central processing unit. If a read error occurs, compare the number of read errors with the specified number of read errors, and if the number of read errors exceeds the specified number, read data to a different track than the one where the read error occurred. If the diagnosis is executed and the data read operation is successfully executed, a report is sent to the central processing unit stating that the read error occurred due to a defective track in which the read error occurred.

If the data read operation cannot be executed normally, the above drawback is eliminated by sending a report to the central processing unit that a read error has occurred due to a failure of the magnetic disk unit or this magnetic disk control device. However, it is an object of the present invention to provide a magnetic disk control device configured so that the cause of a failure can be investigated in a short time.

(Means for Solving the Problems) A magnetic disk control device according to the present invention is connected to a central processing unit, operates according to instructions from the central processing unit, and is configured to be able to control a plurality of magnetic disk devices. A data transfer circuit, a storage circuit,
This configuration includes a microprogram control circuit.

The data transfer circuit is for transferring write/read data between the central processing unit and the magnetic disk device.

The storage circuit determines the predetermined number of read errors per track in order to start reading and diagnosing data sent from the central processing unit, and the number of read errors per track that occur during data read operations from the magnetic disk drive. It is used to store.

When the microprogram control circuit first receives a write/continue instruction from the central processing unit, the data write/read operation to the magnetic disk device is performed by driving the data transfer circuit, and the data is sent from the central processing unit. A predetermined number of read errors per track is stored in a storage circuit for starting a read diagnosis of the recorded data.

Thereafter, if a read error occurs in any track during a data read operation to the magnetic disk device, the microprogram control circuit updates the number of times a read error has occurred in that track stored in the storage circuit.

The number of occurrences of read errors on the track is compared with the prescribed number of read errors. In the comparison results, lead 2
When the number of occurrences of - exceeds a predetermined number, the microprogram control circuit drives the data transfer circuit to perform data read diagnosis on a track other than the one where the read error occurred. On the other hand, if the data read operation for the track is successfully executed, the microprogram control circuit sends a report to the central processing unit that the read error has occurred due to a defect in the track in which the read error has occurred. On the other hand, if the data read operation for the track cannot be executed normally, the microprogram control circuit sends a report to the central processing unit that a read error has occurred due to a failure in the magnetic disk device (1+). Send out for the amount.

(Example) Next, one embodiment of the present invention will be explained in detail with reference to the drawings.

In FIG. 1 showing an embodiment of the present invention, a magnetic disk control device 100 of the present invention is comprised of a data transfer circuit 110, a storage circuit 120, and a microprogram control circuit 130.

When receiving an instruction to write data to the magnetic disk device from the central processing unit through the signal line 202, the microprogram control circuit 130 drives the data transfer circuit 110 through the signal line 203, and transfers the entire signal line 200 from the central processing unit to the data transfer circuit 110. The entered write data is written to the magnetic disk device through the signal line 201. Further, when receiving an instruction to read data from the magnetic disk device from the central processing unit through the signal line 202, the microprogram control circuit 130
drives the data transfer circuit 110 through the signal line 203, and sends the data read from the magnetic disk device through the signal line 201 to the central processing unit through the signal line 200.

Upon receiving the predetermined number of read errors per track for starting data read diagnosis from the central processing unit through the signal line 202, the microprogram control circuit 130
stores the specified number of read errors in the memory circuit 120 through the signal line 204.

When the microprogram control circuit 130 first detects the occurrence of a read error in any track during the data read operation from the magnetic disk device based on the data read instruction from the central processing unit, The stored number of read errors for the track is read out and updated.

After that, the predetermined number of read errors of the track stored in the storage circuit 120 is further output through the signal line 204, and the number of occurrences of read errors is compared with the predetermined number of read errors.

When the number of read errors does not exceed the specified number of read errors, the signal is sent to the memory circuit 120 through the signal line 204.
Stores the number of read error occurrences updated for.

When the number of occurrences of read errors exceeds the specified number of read errors, the microprogram control circuit 130 drives the data transfer circuit 110 through the signal line 203, and transfers data to a track other than the one where the read error occurred through the signal line 201. Execute data read diagnostics for the data.

If the data successive operation is successfully executed, the microprogram control circuit 130 sends a report to the central processing unit via the signal line 202 that the read error occurred because the track where the read error occurred is defective. Send. On the other hand, if the data read operation cannot be executed normally, the microprogram control circuit 1
30 is a magnetic disk device or magnetic disk control device 1
00 is out of order and a lead error 2- occurs and a report indicating 9 is sent to the central processing unit through the signal line 202.

(Effects of the Invention) As explained above, after the central processing unit sends out the specified number of read errors per track to start data read diagnosis, If a read error occurs while reading data, compare the number of read error occurrences with the specified number of read errors, and if the number of read errors exceeds the specified number, a read error has occurred. Execute data read diagnostics on a track other than the track, and if the data read operation is successfully executed, a read error will occur.The trunk will be defective.A report will be issued indicating that a read error has occurred. However, if the data read operation cannot be executed normally, a report stating that a read error has occurred due to a failure of the magnetic disk v device or this magnetic disk control device is sent to the central processing unit. By sending it to the processing device, it is determined whether the cause of the read error is a defective track in the magnetic disk storage.

Alternatively, it is possible to distinguish whether the failure is in the magnetic disk device fft or the magnetic disk control device.

This has the advantage that it is possible to shorten the time it takes to find the cause of a failure, and it is also possible to freely select the timing for reading and diagnosing data.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing an embodiment of a magnetic disk control device according to the present invention. ]00...Magnetic disk control device 110...Data transfer circuit 120...Storage circuit 130...Microprogram control circuit Patent applicant
NEC

Claims (1)

[Claims] A magnetic disk control device configured to be connected to a central processing unit, operate according to instructions from the central processing unit, and control a plurality of magnetic disk devices, the central processing unit and the A data transfer circuit for transferring write/read data to and from a magnetic disk device, and a predetermined number of read errors per track and a magnetic field for starting read diagnosis of data sent from the central processing unit. a storage circuit for storing the number of read errors per track that occurred during a data read operation to the disk device; Write/read operations are performed by driving the data transfer circuit, and after storing in the storage circuit a predetermined number of read errors per track for starting read diagnosis of data sent from the central processing unit. If a read error occurs in any track during data read operation to the magnetic disk device, the number of occurrences of read errors in the track stored in the storage circuit is updated, and the read error in the track is updated. The number of error occurrences is compared with the specified number of read errors, and if the comparison result shows that the number of read errors has occurred exceeds the specified number, the data transfer circuit is driven to perform a process other than the one in which the read error occurred. A data read diagnosis is executed for the track, and if the data read operation for the track is successfully executed, the central processing unit reports that the read error has occurred due to a defective track. If the data read operation for the track cannot be executed normally, a report indicating that a read error has occurred due to a failure of the magnetic disk device or this magnetic disk control device is sent to the device. 1. A magnetic disk control device comprising: a microprogram control circuit for sending data to a central processing unit;