JPH0227570A - Magnetic disk controller - Google Patents

Abstract

PURPOSE:To shorten the execution time of a retrial operation by storing a sector in which an overrun error is generated, and executing a data transfer operation by the execution of retrial at the time of generating the overrun error by transferring data read out of the address of an internal memory. CONSTITUTION:A microprocessor circuit 20, when completing the readout operation of one sector, checks the state of an underrun detection circuit 70, and writes a sector value generating an underrun error on a RAM 40. When the completion of a read operation is recognized, the microprocessor circuit 20 reads out the content of the RAM 40, and when the value of the sector is set, calculates a leading address where the data of the sector in which the overrun error is detected from the sector value read out from the RAM 40 is stored on the internal memory 50, and sets the value on an address register 60, and transfers the data in the internal memory 50 to a main memory device 500 via a bus control circuit 10 and a bus 300. In such a way, it is possible to shorten the execution time of the retrial operation in a magnetic disk controller at the time of generating the overrun error.

Description

DETAILED DESCRIPTION OF THE INVENTION Field of the Invention The present invention relates to a magnetic disk control device used in an information processing device.

Conventional technology Conventionally, in a magnetic disk control device, when an overrun error occurs during a read, the general retry method in a magnetic disk control device is to re-execute the read operation from the sector where the overrun error occurred. .

Problems to be Solved by the Invention However, in the retry execution method in the magnetic disk control device when an overrun error occurs in the conventional magnetic disk control device described above, in order to re-read the sector where the overrun error has occurred, , - A rotation wait occurs, and - the end of the read operation is delayed by the time required for the rotation wait.

The present invention has been made in order to eliminate the above-mentioned drawbacks inherent in the conventional technology, and therefore, an object of the present invention is to shorten the execution time of a retry operation in a magnetic disk control device when an overrun error occurs. The object of the present invention is to provide a new magnetic disk control device that enables the following.

1. A magnetic disk control device according to the present invention includes means for transferring read data read from a magnetic disk device to a main storage device, and a means for transferring read data read from a magnetic disk device to a main storage device. means for writing into the internal memory at the same time as transferring to the main memory; means for detecting an overrun error during reading; and means for storing the sector in which the overrun error has occurred.

means for calculating a memory address of an internal memory storing data of a sector in which an overrun error has occurred from the sector in which an overrun error has occurred, which is stored by the means for storing the sector in which an overrun error has occurred; and means for executing a data transfer operation by executing a retry by transferring data read from the address of the internal memory calculated by the means for calculating the memory address.

Embodiment Next, a preferred embodiment of the present invention will be specifically explained with reference to the drawings.

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

In FIG. 1, a magnetic disk control device 1()0 includes a bus control circuit 10. Microprocessor circuit 20, magnetic disk control circuit 30, RAM/lo, internal memory 50,
Address register 60 and underrun detection circuit 70
It is composed of Moreover, the magnetic disk control device 100
is connected to the magnetic disk device 200, and also connected to the central processing unit 400 and the main storage device 5 via the bus 300.
Connected to 00.

The operation of the magnetic disk control device 100 configured in this manner is as follows. Assuming that a read command for the magnetic disk device 200 is input from the central processing unit 400 to the magnetic disk control device 100 via the bus 300, the microprocessor circuit 20 reads the read command from the magnetic disk control circuit 30.
The magnetic disk device 200 is caused to perform a seek operation via the .

When the microprocessor circuit 20 recognizes the completion of the seek operation via the magnetic disk control circuit 30.

The microprocessor circuit 20 has an address register 60
and clears the contents of the RAM 40, and outputs a read command to the magnetic disk control circuit 30.

The magnetic disk control circuit 30 is a magnetic disk device 200
When the target sector is detected, the read data is written to the main storage device 500 via the bus control circuit 10 and the bus 300, and the read data is also written to the internal memory 50. In this case, The address register 60 is incremented each time one byte of data is loaded. Furthermore, the magnetic disk control circuit 30 determines whether the magnetic disk drive 2
If the amount of data read from 00 is larger, an underrun error is determined and a flag in the underrun detection circuit 70 is set.

When the read operation for one sector is completed, the microprocessor circuit 20 checks the state of the underrun detection circuit 70, and if an underrun error is detected, writes the value of the sector in which the underrun error has occurred to the RAM 40. (However, if a sector value has already been written, the write operation is not executed.) After executing the operation, the read sector is checked in the same way as when no underrun error is detected. When continuing to perform a read operation, the microprocessor circuit 20 outputs a read operation continuation command to the magnetic disk control circuit 30. Furthermore, when the microprocessor circuit 20 checks the read sector and recognizes that the read operation has ended, the microprocessor circuit 20 checks the flAM4.
0 is read, and if the value of the sector is not set, a read operation end interrupt is output to the central processing unit 400 via the bus control circuit IO and the bus 300. or,
When the contents of the RAM 40 are read and the value of the sector is set, the microprocessor circuit 20 performs R
From the sector value read from AM40.

Calculate the starting address where the data of the sector where the overrun error was detected is stored on the internal memory 50.
L, the value is set in the address register 60, and the data in the internal memory 50 is transferred to the main storage device 500 via the bus control circuit 10 and the bus 300. When all the data has been transferred to the main memory device 500, the microprocessor circuit 20 outputs a termination interrupt to the central processing unit 400 via the bus control circuit 10 and the bus 300, and ends the read operation.

As described in detail, by employing the magnetic disk control device of the present invention, it is possible to shorten the execution time of the retry operation in the magnetic disk control device when an overrun error occurs.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing one embodiment of the present invention. 10., bus control circuit, 20. ,,microprocessor circuit, 30. , , magnetic disk control circuit, 40.
,,RAM. 50. Internal memory 60. , ,address register, 70. ,.

Claims (1)

[Claims] A means for transferring read data read from a magnetic disk device to a main storage device, a means for writing the read data to an internal memory at the same time as transferring it to the main storage device, and a means for detecting an overrun error during reading. a means for storing a sector in which an overrun error has occurred; and an internal memory storing data of a sector in which an overrun error has occurred from the sector in which an overrun error has occurred, which is stored by the means for storing a sector in which an overrun error has occurred. means for calculating a memory address of the internal memory, and means for executing a data transfer operation by retrying when an overrun error occurs by transferring data read from the address of the internal memory calculated by the means for calculating the memory address; A magnetic disk control device comprising: