JPS63155467A - Fixed disk control system - Google Patents

Abstract

PURPOSE:To shorten the seek time by storing a data of an alternating record to be entered into an alternating area corresponding to a defective area of a fixed disk in a memory, executing an access whether its access destination is a defective area or not at the time of executing an access to the fixed disk, and executing an access to the memory in case of a defective area. CONSTITUTION:The titled system is provided with an alternating record memory 11 in which a data to be entered into an alternating record is stored. In this state, when a disk device 10 executes an access to a defective area of its fixed disk, its data is entered into the alternating record memory 11, and it is brought to an access. The contents of the alternating record memory 11 are stored in an alternating area corresponding to the defective area, for instance, when the work is ended in the end of a day. In such a way, when a defective area exists in the access destination, an access of the alternating destination on the fixed disk is not executed but its data is entered into the alternating memory 11 and an access thereto is executed, therefore, even if a defective area exists in the access destination, a seek thereto is not executed.

Description

[Detailed description of the invention] [Table of contents] Overview Industrial field of application Prior art (Figure 4) Problems to be solved by the invention Means for solving the problems (Figure 1) Working examples (Figure 1) (Figures 2 and 3) Effects of the invention [Summary] The data of the replacement record to be written in the replacement area corresponding to the defective area of the fixed disk is stored in memory in advance, and when the fixed disk is accessed, the access destination is This system aims to shorten the seek time associated with defective area access by accessing whether or not the area is a defective area and, if it is a defective area, accessing the memory.

[Industrial application field]

The present invention relates to a fixed disk control system, and more particularly to a system for quickly accessing a defective area when the access destination is a defective area.

In high-performance data processing systems that use fixed disk devices to process large-scale data, the seek time of the head with respect to the fixed disk has a significant impact on the performance of the system. Therefore, minimizing fixed disk access time is necessary to improve the performance of data processing systems. Note that the fixed disk here refers to a magnetic disk.

[Conventional technology]

In conventional fixed disk control, as shown in FIG. 4, a processor 1 such as a microprocessor outputs commands to a disk control section 2 to read/write data in a fixed disk 3. During the access to the fixed disk 3, when it is detected that the access destination is a defective area, the record address of the replacement destination of this defective area is obtained.

There are two methods for obtaining this replacement record address: a hardware method and a software method. In the hard method, the address of the record to be replaced is indicated in the defective area, that is, in the defective record. In the software method, the part where the address of the defective record and its replacement address are written,
It is transferred to the memory 4 in advance, and when accessing the fixed disk, this is accessed to check whether there is a defective record, and if a defective record exists, the replacement record that is the replacement address is accessed, and then the original address is transferred. and continue to access it. This alternate destination address is usually set in a portion of the fixed disk where the head seeks a large amount.

[Problem that the invention seeks to solve]

Therefore, conventionally, a fixed disk is accessed, and when the access destination is a defective record, the head is moved to a replacement record, and when the access to the replacement record is completed, the head is returned to its original position.

The limitation of ,:, is that the head moves twice, once to replace the record, and then to return to the original, so the access time becomes much longer than normal access, which significantly reduces the performance of the system. It was causing problems.

[Means for solving problems]

In order to solve the above problem, in the present invention, as shown in FIG. 1, a replacement record memory 11 is provided in which data to be written in the replacement record is stored. and disk mounted fIO
When accessing the defective area of the fixed disk, the data is written in the replacement record memory 11 and accessed.

The contents of this replacement record memory 11 are stored in the replacement area corresponding to the defective area, for example, at the end of work at the end of -day.

[Effect]

A comparison table indicating the existence of a defective area is stored in the memory in advance, and when the fixed disk is accessed, this comparison table is checked and if a defective area exists at the access destination, the Since the data is written in the replacement record memory 11 and accessed without accessing the replacement destination, even if a defective area exists in the access destination, no seek is performed for the defective area.

〔Example〕

An embodiment of the present invention will be described based on FIGS. 2 and 3.

FIG. 2 is a configuration diagram of an embodiment of the present invention, FIG. 3 is an explanatory diagram of its operation, and FIG. 3(A) is an explanatory diagram of the operation when the power of the disk device is turned on. Figure 3 (B)
FIG. 2 is an explanatory diagram of operations when accessing a disk.

In FIG. 2, the same symbol as the map indicates the same part.

The disk device 10 includes a disk controller 2 and a fixed disk 3.

As mentioned above, the replacement record memory 11 is a memory in which data to be written in the replacement record is stored, and can be accessed directly by the processor 1 or by the disk controller 2. The disk control unit 2 can also be configured to directly access the memory 4.

Next, the operation of the present invention will be explained.

(1) When turning on the power As shown in FIG. 3(A), when the power is turned on to the disk drive 10 to start up the system, the processor 1 transfers data from the fixed disk 3 via the disk controller 2. The area of the table indicating the replacement sector address which is a defective area and its replacement destination is read and held in the memory 4. Then, referring to the contents of this table, the data of the replacement destination address is read and held in the replacement record memory 11.

(2) During an access operation, ■When the processor 1 accesses the fixed disk 2 via the disk control unit 3, it first reads the table written in the memory 4, and if there is a defective area, that is, a replacement address in the area to be accessed. Check whether

(2) If this alternative address does not exist due to the existence of a defective area, all areas to be accessed are accessed and this access operation is terminated.

(2) However, if there is a replacement address in part, the access is first made from the beginning of the access to just before the defective area where the replacement address is indicated.

■Then, the processor 1 transfers the data to be stored for this alternate address to the alternate record memory 11 (
(for lights).

(2) After the data is transferred to the replacement record memory 11, access is again continued from the address next to the defective area indicated by the replacement address on the fixed disk 3. .

For example, when the day is over and work is finished,
The data written in this replacement record memory 11 is transferred to the replacement destination address on the fixed disk, and the data of this replacement destination address is written in the replacement record memory 11 when the next job is performed.

In addition, in the above explanation, in addition to the memory 4, there is a replacement record memory 1.
Although the example in which the alternate record memory 1 is provided has been described, the alternate record memory may be mapped on the memory 4, or the same effect can be obtained even if it is placed in the disk control unit. Of course, the disk control unit is configured to be able to read these directly in any case.

〔Effect of the invention〕

According to the present invention, even if a defective area is detected, there is no need to move the head to access a replacement area, so the time associated with moving the head is eliminated, and high-speed access is possible.

[Brief explanation of the drawing]

FIG. 1 is a diagram explaining the principle of the present invention, FIG. 2 is a configuration diagram of an embodiment of the present invention. FIG. 3 is an explanatory diagram of the operation of the present invention, FIG. 4 is an explanatory diagram of a conventional example.

Claims (1)

[Scope of Claim] A data processing device comprising a fixed disk controlled by a processor and storing a defective area of the fixed disk and a replacement area for the defective area in a memory, comprising: a replacement area in which data to be stored in the replacement area is written; A fixing device characterized in that it comprises area memory means (11), and when accessing the alternate area of the fixed disk, the alternate area memory means is accessed to read or write data to the alternate area memory means. Disk control method.