JP2699984B2 - Alternation area management method and apparatus - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION [Summary] For example, a method and apparatus for managing a data storage medium on an external data storage device such as a magnetic disk device, and more particularly, assigning a replacement area to a defective (defective) area on the data storage medium The present invention provides a method and apparatus for managing a spare area that can manage the state of the spare area allocation without specially preparing software for operation management on the host computer side. A host computer, an external data storage controller,
A replacement area management method for managing allocation of a replacement area provided as a replacement for a defective area in the external data storage medium in a system including an external data storage medium, wherein an event of allocation of a replacement area is determined by accessing the replacement area. The data is classified into two or more types according to the time, and a threshold value is stored in the external data storage control device for each of the classifications. Each time the event occurs during the operation of the system, the number of times is classified by the classification. Counting in the external data storage control device, comparing the number of occurrences of the event with the threshold value for each classification in the external data storage control device, and reporting any event in which the number of occurrences exceeds the threshold value. It comprises steps.

[Industrial applications]

The present invention relates to a method and apparatus for managing a data storage medium on an external data storage device such as a magnetic disk device, and more particularly to a replacement area for managing the state of assignment of a replacement area to a defective (defective) area on a data storage medium. The present invention relates to a management method and a device.

In recent years, as the performance and capacity of computer systems have increased, external data storage devices, mainly magnetic disk devices, have been required to have higher storage capacity and higher performance. Generally, in an external data storage medium such as a magnetic recording medium used in a magnetic disk drive, it is inexpensive to use a large-capacity data storage means due to the nature of its material and manufacturing process. This is a condition that must be allowed for stable supply of Therefore, a control device for controlling recording and reproduction of data on and from the storage medium requires a measure for avoiding a defective portion on the data storage medium. In addition, even if a defect occurs due to a change over time in characteristics of the data storage medium during long-term operation, the control device avoids the defective portion and enables continuous use of the data storage device. Must be provided. The present invention refers to the management of the allocation state of the alternate area which is automatically allocated to avoid such a defective portion.

[Prior Art] As a method of avoiding a defective portion on a data storage medium, various methods have been devised depending on the characteristics of data recording on the medium. To determine if there are any defects in the unit,
When a defect exists, a part of a spare storage area prepared in advance is assigned to the recording unit as a replacement area. For example, in a magnetic disk drive of the sector recording system, several sectors in a track or a cylinder, or a specific number of cylinders are reserved as spares for an alternate area, and these sectors are used for a sector having a medium defect. A normal sector is allocated as a replacement sector from the spare storage area.

On the other hand, in the magnetic disk device, it is most efficient to access data continuously on the same track as the disk medium rotates, due to its physical structure. However, the replacement sector processing generally assigns a replacement sector to a spare storage area provided at a physically non-contiguous position with respect to a sector having a defect. A rotation wait, a seek operation, and the like are required for positioning in the replacement sector, and the data access performance is significantly reduced.

Allocation of a replacement sector can be generally performed (1) when the entire surface of the data storage medium is initialized, and (2) when the replacement process of only a specific sector is performed during operation. In the former case, the existing data on the data storage medium does not need to be stored, and therefore, the control device establishes a physical positional relationship with the replacement sector so as to maintain continuity of data access as much as possible. It is permissible to perform the reassignment of the replacement sector relatively freely taking into account. But in the latter case,
Existing data on a data storage medium must be given top priority to preserve its data, except for the target sector to be subjected to alternate sector processing. Therefore, in general, maintaining continuity of access is sacrificed and data security is ensured. , A replacement sector is allocated. As a result, the replacement sector is allocated to a physically non-contiguous position from the original sector, and the subsequent access performance must be reduced.

As a result of the replacement sector allocation process, the magnetic disk device becomes apparently defect-free, and the host computer using the magnetic disk device does not need to pay special consideration to data recording and storage. But,
In particular, it should be noted that the performance of the data access is gradually degraded as described above due to the sequential addition of replacement sectors.

As the performance of the computer system has improved, it has become necessary to avoid the performance degradation. For this reason, it has been necessary for the host computer to prepare special software for monitoring and analyzing the operation status of the magnetic disk medium. This software consists of a program including an instruction to directly specify the physical address of the storage medium and read out the contents. By executing this program periodically or at any time according to a command from the console of the host computer, the allocation status of the replacement sector is determined. Can be known by the operator. As a result, for the storage medium for which the number of replacement sectors has been found to increase, the storage contents are transferred to another medium, and then the entire surface is re-initialized to reallocate the replacement sector to a physically optimal position. However, it is possible to approach the original access performance. Further, for a device in which the number of replacement sectors has abnormally increased, it is possible to avoid a fatal failure in advance by performing preventive replacement assuming that the device itself has some kind of abnormality.

[Problems to be solved by the invention]

In any case, conventionally, it is necessary to prepare special software for operation management of the data storage medium, and since the method of the defect avoidance processing is different for each model of the external data storage device, the host computer needs to prepare the software. On the computer side, it was necessary to prepare several types of operation management programs according to the model characteristics of the external data storage device connected to the computer.

Therefore, an object of the present invention is to provide a method and an apparatus for managing a replacement area, which can manage the allocation state of the replacement area without specially preparing software for operation management on the host computer side.

[Means for solving the problem]

FIG. 1 is a block diagram showing the principle of a spare area management apparatus according to the present invention, and FIG. 2 is a flowchart of a spare area management method according to the present invention.

The replacement area management method according to 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 replacement area, wherein an event of allocation of the replacement area is classified into two or more types according to the access time of the replacement area. A threshold value is stored in the external data storage control device 2 for each category (step a), and each time the event occurs during operation of the system (step b), the number of times is stored in the external data storage control device. 2 (step c), and the external data storage controller 2 compares the number of occurrences of the event with the threshold for each classification in the external data storage control device 2 (step d). It is characterized by providing each step of reporting if there is any (step e).

Further, the replacement area management device of the present invention includes an external data storage control device 2 including a host computer 1, an external data storage medium 3, and storage control means 24 for controlling writing and reading to and from the external data storage medium 3. A replacement area management device for managing allocation of a replacement area provided as a replacement for a defective area in the external data storage medium 3 in the system comprising: Threshold value storage means 21 for storing two or more threshold values for each category according to the degree of access time; counting means 22 for counting the number of times the storage control means 24 has assigned a replacement area for each category; And a comparing means 23 for comparing the count value of the counting means 22 with the threshold value stored in the threshold value storage means 21.

(Operation)

Since the number of times of replacement sector allocation is counted in the external data storage control device 2 which directly controls the external data storage medium 3, the external data storage control device 2 individually copes with defect avoidance processing which differs for each device model. can do. Since the number of times is classified according to the time required for accessing the replacement area and the number is counted and compared with the threshold value, it is possible to surely know the increase in the access time due to the allocation of the replacement area.

〔Example〕

The present invention will be specifically described by taking a magnetic disk drive as an example.

In the case of a normal magnetic disk drive, each sector belonging to the same cylinder number is sequentially accessed with the same track number, and when shifting to another track number, the next read order was used in the track before the shift. If a sector having the same sector number as the sector number is accessed, and then other sectors are sequentially accessed in the same track, access can be made with a minimum waiting time. When accessing a sector at a position out of the above order in the same cylinder, an operation of seeking the target sector is required, and usually, a time corresponding to a maximum of one rotation of the disk is required. When accessing another cylinder, more time is required for the operation of moving the head in the radial direction of the disk.

That is, the access time of a normal magnetic disk device is classified into three types: access in a predetermined order, access out of a predetermined order within the same cylinder, and access to another cylinder.

Therefore, when initializing the entire magnetic disk,
Logical addresses are assigned so as to be as close as possible to physical addresses.

FIG. 4 conceptually shows an example of the assignment of logical addresses when there is no defect in the magnetic disk at the time of the entire initialization. Each cell has one sector, T0 to T3 each track, and CYL0 to CYL0. CYL _n and CYL _{n + 1} indicate each cylinder. Within each cylinder, logical addresses are assigned in the order of the numbers shown in the cells, several sectors (represented by S in the cells) are reserved as spares, and a specific number of cylinders (represented by CYL _{n + 1} ) are further reserved. Reserved as a reserve. As long as access is made in the order of the numbers assigned in the same cylinder, the minimum access time is achieved.

FIG. 5 is a diagram for explaining replacement sector allocation when a defective sector occurs. The column (A) shows an allocation method when there is a defective sector at the location indicated by the mark x in the figure when the storage medium is entirely initialized. As shown in the figure, logical addresses are assigned in such a manner that defective sectors are skipped. In this case, since the number of defective sectors is smaller than the number of spare sectors in the cylinder, all the sectors are allocated in the same cylinder, and moreover, the physical sectors are allocated as much as possible. Therefore, in this case, even if there is a defective sector, the access time for the defective sector is slightly increased.

The (B) column shows the allocation of the replacement sector when a defect occurs in the sector at the position indicated by the number “14” during the operation in the state of the (A) column. Since there is a possibility that data has already been written in the sectors of numbers "15" to "28" since the operation is in progress, and it is dangerous to perform the operation of allocating the replacement sector as shown in FIG. Is assigned to the position of the spare sector. In this case, the number "1
When accessing 3 "," 14 "and" 15 "sectors continuously,
The time for waiting for the rotation of the disk is required, and the access time increases.

The (C) column further shows a replacement cylinder allocation method when a defect occurs in the sector at the position of the number “25”.
Since the spare sector in the same cylinder has already been used up, the replacement sector is assigned to one sector in the spare cylinder CYL _{n + 1} . In this case, the numbers “24” and “25”
When continuously accessing the "26" sectors, a time for mechanically moving and positioning the head is required in addition to a waiting time for the rotation of the disk, so that the access time is significantly increased.

As described above, in the magnetic disk drive of this type, when allocating the replacement cylinder, there are cases where the access time hardly changes and cases where the access time increases, and the latter does not require the movement of the head. And when needed.

FIG. 3 shows an embodiment of the present invention, and shows an example in which the present invention is applied to the above-described magnetic disk drive.

The illustrated system includes a host computer 10 using the magnetic disk device 30 as external data storage, a magnetic disk control device 20 connected between the host computer 10 and the magnetic disk device 30, and a magnetic disk device 30.

The magnetic disk control device 20 includes a controller unit 240, which receives a command from the host computer 10 via the control unit 241 and performs various controls in accordance with the command.Program control using a microprocessor or the like is performed. The structure is taken. 241 is the host computer 1
Reference numeral 242 denotes a control unit for controlling input / output to / from the magnetic disk device 30. Reference numeral 243 denotes a data buffer for temporarily storing read data from the magnetic disk device 30 and write data to the magnetic disk device 30, and efficiently executing data transfer with the host computer 10.

The counter 220 counts the number of occurrences of the event described in the column of FIG. 5B, that is, the number of times the controller unit 240 uses a spare sector in the same cylinder as a replacement sector. Is incremented by 1. Register 210 contains host computer 10
Is written via the controller unit 240. This constant corresponds to the allowable value of the event counted by the counter 220. The comparator 230 compares the count value of the counter 220 with a constant in the register 210, and generates a signal 232 when “count value ≧ constant”. The controller unit 240 that has received the signal 232 transmits the signal to the host computer 10, and a warning message is displayed on the console of the host computer 10.

The counter 221, the register 211, and the comparator 231 have the same configuration, and the number of occurrences of the event described in the column (B) of FIG. 5 or the number of occurrences of the event described in the column (C) of FIG. The process for the number of times 240 uses the spare sector in the spare cylinder as a replacement sector is similarly performed.

Note that the functions of the counters 220 and 221, the registers 210 and 211, and the comparators 230 and 231 can be realized by software processing of the controller unit 240, and that is more preferable.

In this example, the threshold value is set by a command from the host computer. Therefore, it is possible to set the threshold value according to the requirements required on the host system side, and it is also possible to selectively inhibit some of the events monitored on the control device side depending on how the threshold value is provided. .

〔The invention's effect〕

As described above, according to the present invention, the control device that actually executes the alternate sector process accumulates the events of the alternate sector allocation that hinders the access performance, and exceeds the predetermined threshold value depending on the number of occurrences. Can be reported to the host computer, so that the host computer does not need to prepare a means for individually managing different events depending on the attribute of the external storage device to be used,
In addition, since the number is classified according to the time required for accessing the replacement area and the number is counted and compared with the threshold value, it is possible to accurately obtain information for unintended deterioration in access performance and preventive maintenance.

[Brief description of the drawings]

FIG. 1 is a block diagram of the principle of a replacement area management apparatus of the present invention, FIG. 2 is a flowchart of a replacement area management method of the present invention, FIG. 3 is a diagram showing an embodiment of the present invention, FIG. The figure is a figure for explaining the example of allocation of a substitution field. In the drawing, 1 ... host computer, 2 ... external data storage control device, 3 ... external data storage medium, 21 ... threshold storage means, 22 ... counting means, 23 ... comparison means, 24 ... storage control means.

Claims (2)

(57) [Claims] 1. A system comprising an external data storage control device (2) and an external data storage medium (3) manages the allocation of a replacement area provided as a substitute for a defective area in the external data storage medium (3). A replacement area management method, wherein the event of replacement area allocation is classified into two or more types according to the access time of the replacement area, and a threshold value is stored in the external data storage control device (2) for each classification. Each time the event occurs during the operation of the system, the number is counted in the external data storage control device (2) for each classification, and the number is counted in the external data storage control device (2) for each classification. A method according to claim 1, further comprising the step of comparing the number of occurrences of the event with the threshold value and notifying if the number of occurrences exceeds the threshold value. 2. A system comprising an external data storage medium (3) and an external data storage control device (2) having storage control means (24) for controlling writing and reading to and from the external data storage medium (3). The external data storage medium (3)
A replacement area management device that manages the assignment of a replacement area provided as a substitute for a defective area in the external data storage control device (2), and is provided for each classification according to the access time of the replacement area. Threshold value storage means (21) for storing two or more threshold values; counting means (22) for counting the number of times the storage control means (24) has assigned the replacement area for each of the classifications; Comparing means (23) for comparing the count value of (22) with the threshold value stored in the threshold value storing means (21), and notifying means for notifying when the count value is larger than the threshold value. A replacement area management device, characterized in that: