JPH06139715A - Controller for rotary type storage device - Google Patents

Abstract

PURPOSE:To improve the throughput of a system by providing a register for holding an address on an error generation position and a register for holding an address to be accesed next. CONSTITUTION:A desired code is set on a control register by a CPU 1 via a bus 5. When a reading error is generated at a register 25, the address of its sector is stored in registers EAR 1 and 2. For example, when the reading error is generated on two sectors within the same track [for example, the sectors of logical addresses (n) and (n+1)] during a reading, the logical addresses(n, n+1) of the sectors where the errors are generated for the EARs 1 and 2 synchronized with an error detection signal ATTENTION to be supplied to a hard disk controller 2 from a disk driving controlling device 3 are respectively stored. Then, a rereading is carried out when the disk comes to the addresses (n, n+1) after one rotation and thus, the waiting period of time for rotation is greatly reduced and the effectiveness of restoring the device from the error is improved.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an error processing technique in a rotary storage device, and more particularly to a technique which is particularly effective when applied to a rereading processing system when a read error occurs. And effective technology.

[0002]

2. Description of the Related Art Memory devices used in microcomputer systems include small-capacity but high-speed semiconductor memories and low-speed but large-capacity magnetic memory devices. Data that is frequently used by combining two types of storage devices is read from a magnetic storage device and stored in a semiconductor memory to speed up the processing. The magnetic storage device includes a magnetic tape device, a floppy disk device, a hard disk device, and the like, but in recent years, a hard disk device is often used as an auxiliary storage device because of its high speed and high storage density. Further, a system using an optical disk device as an auxiliary storage device in addition to the magnetic storage device has been put into practical use.

[0003]

Generally, in a magnetic disk device, when a read error occurs, error processing is performed to read data again. In the conventional error recovery processing, each time an error occurs, the data in the sector in which the error occurred is read again. However, in the error recovery process in the conventional magnetic disk device, when an error is detected, the disk rotation is not stopped and the data reading is immediately stopped, and the data is read again after the head moves to the sector in which the error occurred. The method was adopted. Therefore, when a read error occurs, the disk is put into a rotation waiting state for almost one rotation, and it takes 10 to 15 ms to wait for this rotation, so that the data reading time is extended and the system throughput is lowered. It was

An object of the present invention is to improve the efficiency of error recovery processing when a read error occurs and improve the system throughput. The above and other objects and novel features of the present invention will be apparent from the description of this specification and the accompanying drawings.

[0005]

The typical ones of the inventions disclosed in the present application will be outlined below. That is, in the control device of the rotary storage device, a register holding an address indicating a data position when a read error occurs and a register holding an address to be accessed next are provided, and even if a read error occurs, The data reading is continued as it is, and the data is read again when the head comes to the sector where the error occurs.

More specifically, a control device for a rotary storage device includes a device called a magnetic disk driver, which includes a read / write head, a rotary drive motor, and a drive control circuit for driving and controlling the read / write head and the rotary drive motor. It is composed of a control LSI called a disk controller, which is interposed between a disk driver and a CPU (microprocessor) to transfer data, generate an ECC (error collecting code), and check it. In this case, the error address holding register and the next address holding register are provided in the disk controller.

[0007]

According to the above-mentioned means, when two or more read errors occur in the same track, the address of each sector in which the error occurred is held in the register, so that the disk rotates once. By re-reading the data when the head comes to the sector position where the error occurred, the rotation waiting time can be greatly reduced, which improves the efficiency of error recovery processing and improves the system throughput. The above object is achieved.

[0008]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT A preferred embodiment of the present invention will be described below with reference to the drawings. FIG. 1 illustrates the present invention as an example of ESDI (E
enhanced Small Device Inte
An example when applied to a control device of a hard disk device conforming to the r.f. In FIG.
1 is a microprocessor (or microcomputer unit), 2 is a hard disk controller, 3
Is a drive control device for a hard disk device, and 4 is a main memory device such as a semiconductor memory,
And hard disk controller 2 and main memory 4
Are connected via the system bus 5. Although not shown, a DMA (Direct Memory Access) is used to transfer data between the microprocessor 1 and the hard disk controller 2 on the system bus 5.
A peripheral control LSI such as a controller may be connected.

The hard disk controller 2 and the disk drive control device 3 are connected by an ESDI interface, and A / D for performing A / D conversion or D / A conversion of write data and read data.
The converter 6 is interposed. Disk drive controller 3
Is a signal (read clock and write data) to the read / write IC 7 that drives the magnetic head based on a signal (read clock RCK and read gate signal RGT) from the hard disk controller 2, a stepping motor 8 that rotates the disk, A drive signal (pulse) is formed and output to the stepping motor 9 that relatively moves the head in a direction orthogonal to the rotation direction of the disk.

Further, the disk drive controller 3 comprises means for judging whether or not there is a read error based on the read signal from the read / write IC 7, and when an error occurs, an error detection signal is sent to the hard disk controller 2. Send ATTENTION. In addition to the read data signal, the disk drive control device 3 also supplies a signal INDEX indicating a reference position (index) and a signal SECTOR indicating the head position of each sector to the hard disk controller 2. On the other hand, the interrupt signal IRQ can be directly input from the disk drive control device 3 to the CPU 1 as well. For example, when a disk rotation abnormality or the like is detected by a signal from a rotation position detector of a hard disk (not shown), the CPU 1 Is configured to be interrupted to stop the system.

The hard disk controller 2 is
CPU interface circuit 21 on the system bus 5 side,
Further, the disk drive controller 3 has an ESDI interface circuit 22. Further, the hard disk controller 2 adds an ECC code to the write data received from the CPU 1, checks the ECC code in the read data received from the disk drive control device 3 to restore the data, and restores the logical address to the physical address ( The operation control unit 23 for converting the head address, the sector address and the cylinder address), and the disk drive control device 3 for converting the physical address into a serial signal.
A parallel / serial conversion circuit 24 for supplying
A register unit 25 including various registers such as a control register for designating a data transfer rate and an operation mode
And the read data and write data are temporarily stored and C
It has a buffer memory unit 26 and the like for absorbing the difference in data transfer speed between the PU side and the hard disk side.

The control register in the register unit 25 is configured so that the CPU 1 can set a desired code via the system bus 5. In this embodiment, when a read error occurs in the register unit 25, two registers EAR1 for storing the address (logical address or physical address) of the sector.
And EAR2 are provided. In the disk controller of this embodiment, for example, when there is a read error in two sectors (for example, sectors of logical addresses n and n + 1) in the same track during the read processing, the disk drive controller 3 causes the hard disk controller 2 to read. The logical addresses (n and n + 1) of the sector in which the error occurred are stored in the registers EAR1 and EAR2 in synchronization with the error detection signal ATTENTION supplied thereto. Then, the disk makes one revolution and the head moves to the logical addresses n and n.
The data reading is executed again when the +1 sector position is reached.

FIG. 2 shows the difference between the error recovery process according to the present embodiment and the error recovery process according to the conventional method when a read error occurs in two sectors (sectors having logical addresses n and n + 1) in the same track during the read process. Show. As shown in FIG. 2, in the conventional method, every time a read error occurs, the re-reading of the sector in which the error occurred is performed, and therefore, waiting for rotation is required twice, whereas the method of this embodiment is used. It can be seen that, since the re-reading of the two sectors in which an error has occurred is continuously executed, only one rotation wait is required and the error recovery processing time is shortened.

In the above embodiment, the case where two registers for storing the address of the sector when two read errors occur in the same track has been described, but the present invention is not limited thereto. Instead, three or more registers may be provided to store three or more addresses of the sector in which the read error has occurred.
However, in a hard disk device, the probability that three or more errors will occur in the same track is very small, so it is usually sufficient to provide two error address holding registers.

When a read error occurs, the sector address (logical address or physical address)
In addition to the register that stores the address, one or more registers that store the address of the sector to be read next are provided, and for example, the address of the sector that started the read first is stored in that register. If there are more errors than the number of address registers or if the same sector has read errors twice in a row, read again from the first sector, or if multiple errors occur, remove them. It may be divided into several groups and used for executing the error recovery process.

Further, in the above embodiment, the hard disk controller is provided with the function of converting a logical address into a physical address, but the microprocessor 1 may have the address converting function. . In that case, the contents of the error address storage registers provided in the hard disk controller 2 are configured so that the microprocessor 1 can read them, or the error address storage registers EAR1 and EAR2 themselves are set in the microprocessor. It should be built in. Further, in the above embodiment, the case where the disk control device is configured by the hard disk controller 2 and the disk drive control device 3 has been described, but a device having both the function of the hard disk controller 2 and the function of the disk drive control device 3. Can also be configured as. Further, it is possible to form the hard disk controller 2 having the above-mentioned configuration on the same semiconductor chip as the microprocessor 1.

As described above, the above embodiment is provided with the register holding the address indicating the data position when the read error occurs and the register holding the address to be accessed next, and the read error occurs. Also, the data reading is continued as it is, and the data is read again when the head comes to the sector in which an error has occurred. Therefore, if two or more read errors occur in the same track, an error occurs. Since the address of each sector is held in the register, the disk is 1
By re-reading the data when the head comes to the sector position that caused the error by rotating, the rotation waiting time can be greatly reduced, which makes the error recovery process more efficient and increases the system throughput. Has the effect of being improved.

Although the invention made by the present inventor has been specifically described based on the embodiments, the present invention is not limited to the above embodiments, and various modifications can be made without departing from the scope of the invention. Needless to say. For example, in the above-described embodiment, the system in which the hard disk controller 2 and the disk drive control device 3 are connected by the ESDI interface has been described as an example, but it is needless to say that the system can be applied to a system using another interface. In the above description, the case where the invention made by the present inventor is mainly applied to the control device of the hard disk device which is the field of application which is the background has been described. However, the present invention is not limited to this, and a floppy disk device or The drum type storage device, the optical disk device, and other rotary storage device control devices can be widely used.

[0019]

The effects obtained by the representative one of the inventions disclosed in the present application will be briefly described as follows. That is, in the control device of the rotary storage device, the efficiency of error recovery processing when a read error occurs can be improved, and the throughput of the system can be improved.

[Brief description of drawings]

FIG. 1 is a block diagram showing an embodiment when the present invention is applied to a control device for a hard disk device conforming to the ESDI standard.

FIG. 2 is a timing chart showing the difference between the error recovery process of the method of the present embodiment and the error recovery process of the conventional method when a read error occurs in two sectors in the same track during the read process.

[Explanation of symbols]

 1 Microprocessor 2 Hard Disk Controller 3 Disk Drive Controller 4 Main Memory 5 System Bus 6 A / D Converter 8, 9 Motor

Claims (3)

[Claims] 1. A rotary drive source for a disc-shaped or drum-shaped storage medium, head moving means for relatively moving a head for reading stored information of the storage medium in a direction orthogonal to the rotation direction of the storage medium, A first register for holding an address indicating a data position when a read error occurs in a control device of a rotary storage device including a head drive means for electrically driving a head to read and write stored information. And a second register for holding the address to be accessed next are provided so that even if a read error occurs, the data reading is continued and the data is read again when the head reaches the sector in which the error occurred. A control device for a rotary storage device characterized in that 2. The first register and the second register hold address information in the form of a logical address,
2. The control device for the rotary storage device according to claim 1, wherein the control device has a function of converting a logical address into a physical address corresponding to the configuration of the rotary storage device. 3. The control device for the rotary memory device according to claim 1, wherein the second register stores an address of a memory area in the same track where a second read error has occurred. .