JPH0421974A - Method and device for controlling alternative sector - Google Patents

Abstract

PURPOSE:To enable individual correspondence in a controller for various detect avoiding processings for each type of a device by counting the number of times for allocating an alternative sector in the controller to directly control an external data storing medium. CONSTITUTION:This device is composed of a host computer 1, external data storage controller 2 and external data storing medium 3 and controls the allocation of the alternative sector to be provided instead of a defective sector in the storing medium 3. The event of allocating the alternative sector is classified to more than one type corresponding to the length of access time in the alternative sector, and the controller 2 stores a threshold value for each classification and counts the number of times for generating the relevant event during the operation of a system for each classification. In the controller 2, the number of times for generating the event is compared with the relevant threshold value for each classification and when there is any event which number of times for generation is larger than the threshold value, it is announced.

Description

[Detailed Description of the Invention] [Summary] A method and apparatus for managing a data storage medium on an external data storage device such as a magnetic disk device, in particular, allocation of a replacement area to a defective (defective) area on the data storage medium. The present invention relates to a replacement area management method and device that can manage the allocation and status of replacement areas without the need for special software for operation management on the host computer side. In a system comprising a host computer, an external data storage control device, and an external data storage medium, the replacement area is managed to replace a defective area in the external data storage medium. An area management method that classifies an event of allocation of a replacement area into one or more types depending on the access time of the replacement area, stores a threshold value for each classification in the external data storage control device, and Each time the event occurs during operation, the external data storage control device counts the number of times the event occurs for each classification, and the external data storage control device calculates the number of occurrences of the event and the darkness value for each classification. The system is configured to include each step of comparing the numbers of occurrences and notifying the user if there is one whose number of occurrences is greater than a threshold value.

[Industrial application field]

The present invention relates to a method and apparatus for managing data storage media on external data storage devices such as magnetic disk devices, and
In particular, the present invention relates to a replacement area management method and apparatus for managing the state of allocation of replacement areas to defective areas on a data storage medium.

2. Description of the Related Art In recent years, with the increase in performance and capacity of computer systems, external data storage devices, mainly magnetic disk drives, are required to have increased storage capacity and performance. In general, external data storage media such as magnetic recording media used in magnetic disk drives contain some minute defects due to the characteristics of their materials and manufacturing processes. This is a condition that must be tolerated in order to provide a stable supply of For this reason, it is essential for a control device that controls recording and reproduction of data on a storage medium to take measures to avoid defective portions on the data storage medium. Furthermore, even for defects that occur due to changes in characteristics of the data storage medium over time during long-term operation, the control device provides means to avoid the defective portion and enable continuous use of the data storage device. must be equipped. The present invention refers to the management of the state of allocation of replacement areas that are automatically allocated to avoid such defective parts.

[Conventional technology]

Techniques for avoiding defective parts on data storage media include:
Various methods have been devised depending on the characteristics of data recording on a medium, but in general, each recording unit on a data storage medium is checked to see if a defect exists within that unit. When this happens, a part of a spare storage area prepared in advance is allocated as a replacement area for the recording unit. For example, in a sector recording type magnetic disk drive, several sectors within a track or cylinder, or a specific number of cylinders are reserved as spare areas for replacement areas, and these sectors are reserved for sectors with media defects. Allocate a normal sector from the spare storage area as a replacement sector.

On the other hand, in a magnetic disk device, due to its physical structure, it is most efficient for data access to be processed continuously on the same track as the disk medium rotates. However, the replacement sector processing generally involves allocating the replacement sector to a spare storage area that is physically discontinuous with respect to the defective sector. Positioning to a replacement sector requires a rotational wait, a seek operation, etc., which significantly degrades data access performance.

In general, replacement sectors can be allocated when (1) the data storage medium is fully initialized, or (2) when only a specific sector is replaced during operation. In the former case, Existing data on the data storage medium does not need to be saved, and the control unit is therefore relatively free to take into account its physical location with the replacement sector in order to maintain continuity of data access as much as possible. However, in the latter case, the preservation of the existing data on the data storage medium, except for the sector subject to replacement sector processing, must be preserved as the first priority. Therefore, in general, replacement sectors are allocated in a way that ensures data integrity at the expense of maintaining access continuity.As a result, replacement sectors are allocated in locations that are physically discontinuous from the original sector. access performance is inevitably degraded.

Through the process of allocating alternate sectors, the magnetic disk device appears to be defect-free, and the host computer using the magnetic disk device does not need to pay special consideration to data storage. However, it must be noted that data access performance is gradually decreasing as described above, especially due to the sequential addition of replacement sectors.

As the performance of computer systems has improved, it has become necessary to avoid this performance degradation, and for this reason, it has become necessary for host computers to prepare special software for monitoring and analyzing the operational status of magnetic disk media. This software consists of a program that includes instructions to directly specify the physical address of a storage medium and read its contents, and by executing this program periodically or at any time based on commands from the host computer's console, it allocates alternate sectors. This allows the operator to know the status. For storage media that are found to have an increased number of replacement sectors as a result, the storage contents are transferred to another medium, and then a full reinitialization process is performed to reallocate the replacement sectors to physically optimal positions. The access performance can be brought closer to the original access performance. Further, for a device in which the number of replacement sectors has increased abnormally, it is possible to prevent a fatal failure from occurring by assuming that there is some kind of abnormality in the device itself and performing preventive replacement.

[Problem to be solved by the invention]

In any case, conventionally, it was necessary to prepare special software for operational management of data storage media, and
Since the defect avoidance processing method differs for each model of external data storage device, it is necessary to prepare several types of operation management programs on the host computer side depending on the model characteristics of the external data storage device connected to it. there were.

Therefore, it is an object of the present invention to enable the host computer to operate without the need for special software for operation management.
The object of the present invention is to provide a replacement area management method and apparatus that can manage the allocation of replacement areas.

[Means to solve the problem]

FIG. 1 is a diagram illustrating the basic configuration of a replacement area management device according to the present invention, and FIG. 2 is a flowchart of a replacement area management method according to the present invention.

The replacement area management method of the present invention includes a host computer 1, an external data storage control device 2, and an external data storage medium 3.
A replacement area management method for managing the allocation of a replacement area provided as a substitute for a defective area in the external data storage medium 3 in a system comprising: The external data storage control device 2 is classified into one or more types according to
Step a) to store a threshold value for each category within the system, and count the number of occurrences in the external data storage control device 2 for each category each time the event occurs during system operation (Step b). C) Compare the number of occurrences of the event for each category in the external data storage control device 2 with the threshold value Step d) If there is an event whose number of occurrences is greater than the threshold value, report it (Step e) This patent is characterized by comprising each step.

The alternate area management device of the present invention also includes a host computer 1, an external data storage medium 3, and an external data storage control device 2 comprising a storage control means 24 for controlling reading and writing to the external data storage medium 3. A replacement area management device that manages the allocation of a replacement area provided as a substitute for a defective area in the external data storage medium 3 in a system comprising: threshold storage means 21 for storing one or more threshold values for each classification depending on the access time; a counting means 22 for counting the number of times the storage control means 24 has allocated a replacement area for each classification; The counting means 2
The present invention is characterized by comprising a comparison means 23 for comparing the count value of 2 and the threshold value stored in the threshold value storage means 21.

[For production]

Since the external data storage control device 2 that directly controls the external data storage medium 3 counts the number of times replacement sectors are allocated, the external data storage control device 2 individually performs defect avoidance processing that differs depending on the device model. can correspond to

〔Example〕

The present invention will be specifically explained by taking a magnetic disk device as an example.

In the case of a normal magnetic disk drive, each sector belonging to the same cylinder number is accessed sequentially for the same track number, and when moving to another track number, the sector is accessed in the order in which it will be read next on the previous track. Access can be achieved with the minimum waiting time by accessing in order such as accessing the sector with the same sector number and then accessing sequential sectors within the same track. When accessing a sector at a position outside the above order within the same cylinder, a seek operation for the target sector is required, which usually requires a maximum of one rotation of the disk. When accessing another cylinder, additional time is required to move the head in the radial direction of the disk.

In other words, the access time of a normal magnetic disk device can be classified into three types: ■ When accessing in a predetermined order; ■ When accessing out of the predetermined order within the same cylinder; ■ When accessing another cylinder. Ru.

Therefore, when a magnetic disk is completely initialized, logical addresses are assigned as close to the order of (2) as possible to physical addresses.

FIG. 4 conceptually shows an example of logical address assignment when there are no defects on the magnetic disk during full-scale initialization. Each fold represents one sector, TO~T3 represents each track, and CYLO~T3 represents one sector. CYL...

CYL,,+1 indicates each cylinder. Within each cylinder, logical addresses are assigned in the order of the numbers shown in the squares, several sectors (indicated by S in the squares) are reserved as spares, and a specific number of cylinders (indicated by CY cylinder h+1) are reserved as spares. will be secured as As long as the accesses are made in the order of numbering within the same cylinder, the minimum access time is achieved.

FIG. 5 is a diagram illustrating allocation of replacement sectors when a defective sector occurs. Column (A) shows the allocation method when there is a defective sector at the location indicated by the X mark in the figure during full initialization of the storage medium. As shown in the figure, logical addresses are assigned in a manner that skips defective sectors.

In this case, since the number of defective sectors is less than the number of spare sectors in the cylinder, all sectors are allocated within the same cylinder, and in a manner that maintains as much physical continuity as possible. Therefore, in this case, even if there is a defective sector, the access time increases only slightly.

Column (B) shows the number “1” while operating in the state of column (A).
Indicates the allocation of a replacement sector when a defect occurs in the sector at the position indicated by "4".Since it is in operation, the number "1"
There is a possibility that data has already been written in sectors 5" to 28, and it is dangerous to allocate a replacement sector as in (A). Therefore, the replacement sector should be allocated to the spare sector position. In this case, the number “
When continuously accessing sectors 13'', 14'', and 15''', it is necessary to wait for the rotation of the disk, which increases the access time.

Column (C) further shows a replacement cylinder allocation method when a defect occurs in the sector at number "25".

Since the spare sectors in the same cylinder have already been used up, the replacement sector is assigned to one sector in the spare cylinders CYL,,+. In this case the number "2"
When continuously accessing 4"25" and "26" sectors, in addition to waiting for the disk to rotate, it also requires time to mechanically move and position the head, so the access time is significantly reduced. increase

As explained above, in this type of magnetic disk drive, when allocating alternate cylinders, there are cases where the access time remains almost the same and cases where the access time increases, and the latter case does not require head movement. It is classified into two types: and cases where it is necessary.

FIG. 3 shows an embodiment of the present invention, in which it is applied to the above-mentioned magnetic disk device.

The illustrated system includes a host computer 10 that uses a magnetic disk device 30 as external data storage, a magnetic disk controller 20 connected between the host computer 10 and the magnetic disk device 30, and a magnetic disk device 3.
Consists of 0.

The magnetic disk control device 20 includes a controller unit 240, which receives commands from the host computer 10 via a control unit 241 and performs various controls in accordance with the commands, including program control using a microprocessor or the like. It has the structure of 241 is a control unit that controls input/output with the host computer 10;
2 is a control unit that controls input/output with the magnetic disk device 30; 243 is a data buffer for temporarily storing data read from the magnetic disk device 30 and data written to the magnetic disk device 30, and for efficiently transferring data to and from the host combiner 10. be.

The counter 220 counts the number of occurrences of the event described in the section (B) in FIG. +1 is added. The register 210 contains constants sent from the host computer 10 to the controller section 240.
written via. This constant corresponds to the allowed value of events counted by counter 220. Comparator 230 compares the count value of counter 220 and a constant in register 210, and generates signal 232 when the condition of "count value≧constant" is satisfied. The controller unit 24 receives the signal 232
0 transmits the signal to the host computer 10, and a warning message is displayed on the console of the host computer 10.

Counter 2211 Register 2111 and comparator 23
1 has a similar configuration, and the controller unit 240 determines the number of occurrences of the event explained in column (B) of FIG. 5 or the number of occurrence of the event explained in column (C) of FIG. Processing regarding the number of times used as a replacement sector is performed in the same way.

In addition, counter 220.22L register 210, 21
1, and comparator 230. The function of 231 can also be realized by software processing of the controller unit 240, and this is rather preferable.

Further, in this example, the threshold value is set based on a command from the host computer. Therefore, it is possible to set a threshold value according to the requirements required on the host system side, and depending on how the dark value is given, it is also possible to selectively prohibit some of the events monitored on the control device side. be.

〔Effect of the invention〕

As explained above, according to the present invention, a control device that actually executes alternate sector processing accumulates alternate sector allocation events that impede access performance, and determines a predetermined threshold based on the number of occurrences 2 = 1B), the host computer does not need to prepare a means to separately manage events that differ depending on the attributes of the external storage device used, and It becomes possible to accurately obtain information for preventing unintended deterioration in access performance and for preventive maintenance.

[Brief explanation of drawings]

FIG. 1 is a diagram showing the principle configuration of the replacement area management device of the present invention, FIG. 2 is a flowchart of the replacement area management method of the invention, FIG. 3 is a diagram showing an embodiment of the invention, and FIGS. The figure is a diagram for explaining an example of allocation of replacement areas. In the figure, 1... host computer, 2... external data storage control device, 3... external data storage medium, 21... threshold storage means, 22... counting means, 2
3... Comparison means, 24... Memory control means.

Claims (1)

[Claims] 1. In a system consisting of a host computer (1), an external data storage control device (2), and an external data storage medium (3), defective areas in the external data storage medium (3) can be fixed. A replacement area management method for managing the allocation of a replacement area provided as an alternative, which classifies the event of allocation of the replacement area into one or more types depending on the access time of the replacement area, and the external data storage control device (2) stores a threshold value for each category, and counts the number of times the event occurs for each category in the external data storage control device (2) each time the event occurs during system operation; A switching system characterized by comprising steps in which the number of occurrences of the event is compared with the threshold value for each category in the storage control device (2), and if there is an event whose number of occurrences is greater than the threshold value, a notification is provided. Space management method. 2. An external data storage control device (2) comprising a host computer (1), an external data storage medium (3), and a storage control means (24) for controlling reading and writing to the external data storage medium (3). A replacement area management device that manages the allocation of a replacement area provided as a substitute for a defective area in the external data storage medium (3) in a system comprising: , a threshold storage means (21) for storing one or more threshold values for each classification depending on the access time of the replacement area; and a threshold storage means (21) for counting the number of times the replacement area is allocated by the storage control means (24) for each classification. a counting means (22) for each category, and a count value of the counting means (22) and a threshold storage means (21) for each category.
) Comparison means (23) for comparing the comparison means (23) with a threshold value stored in the replacement area management device.