JPS583103A - Magnetic disc device - Google Patents

Abstract

(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

Description

DETAILED DESCRIPTION OF THE INVENTION The present invention solves the problem of defects (
The present invention relates to a magnetic disk device that automatically accesses an alternative storage area when a defective spot exists.

2. Description of the Related Art Disks used to store information in magnetic disk devices more or less have some sort of defect (defective spot). In a disk having such a defect, there is a risk that a storage area, that is, a sector to which one disk address is assigned, or even some of the tracks that are the result of a certain number of sectors, may become unusable. However, the host computer side recognizes the available and unusable areas within the disk,
It is impossible to read/write the disk based on this knowledge. Therefore, when a spare area (spare sector, or even a spare track) is provided on the disk, and an unusable sector (defective sector) or a sector within an unusable track (defective track) is accessed, the magnetic disk drive A method is generally adopted in which a corresponding sector of the spare area is used as an alternative sector under internal control.

FIGS. 1 and 2 illustrate a conventional disk format with a spare area for replacing defective tracks (or sectors). First, control operations in a conventional magnetic disk device will be explained with reference to FIG. In the figure, TO~T6. TEIPO~TBP 3 indicates the physical track position of the disk, among which T8PO
~T8P3 is a spare track. 80 to S8 indicate the physical positions of sectors, and in the example of FIG. 1, one track is divided into nine sectors. Also, each track (TO, T4
, T5, TSPO to TSP3) The two-digit numerical value 4-column written for each sector position indicates the disk address written on the disk, where the upper digit is the track number and the lower digit is the sector location. are shown respectively. For example, "01" is track 0
1 indicates sector 1, and "40" indicates track 4, sector 0.

Also, Tl, T2. TSPO to 'I'SP3 written for each sector position of TJ and TO indicate an alternative track position (track address of an alternative track). This is Tl,'I'2. Because defects (defective spots) exist in T3° and P6, they are reserved as spare tracks TSPO.

TSPI, 'I'SP2. This is an instruction to use TSPa as an alternative track. For example, when accessing the disk address rioJ'i, the disk control device in the magnetic disk drive first reads the sector at the corresponding physical position on the disk, that is, Tl, the header section of 80 sectors, and then selects the alternative track T8PO.
Know the address of. Next, the disk control device accesses TSPo, 8Q sectors as if the track T8PO specified by the above address were track T1.

Oh, T1. If a defective spot exists in the header of the SO sector, a read error will occur and the address of the alternative track TSPO cannot be known, so the disk control device
Read the head of one sector. This operation continues until the header section is read without error. As is clear from FIG. 1 and the above explanation, the address of the spare track TSPO is written in each sector of the track T1, and even if one sector among 8B, TI, BO to TI, the header is completed without error. If the club can lead, it will be track T8.
PO can be used as an alternate track. T.S.
P.O.

Disk address [10] has been written to the SO sector, and the target sector has been accessed. That is, when track T1 is a defective track, its replacement track TSPO is accessed apparently as track T1.

However, in the above-mentioned method, even if a defective spot exists in only one sector of a group of sectors constituting one track, an alternative track is used in place of that track, so a large number of alternative tracks are required. There was a drawback that the actual storage capacity of the disk was significantly reduced. Furthermore, the above-mentioned method requires a seek operation in most cases to access an alternative track, and has the disadvantage that the processing speed is significantly reduced.

Next, a control operation in a conventional magnetic disk device to which the format shown in FIG. 2 is applied will be explained. 8 pages in the diagram
indicates a spare track, and X indicates a defective sector. Here, when the presence of a defective spot is considered in sector units, the relevant sector is referred to as a defective sector. In the example of FIG. 2, for tracks TO to T6, sector S8 is set as a spare sector, and track 'I'8P is set as a spare sector.
Regarding O-TSP3, all sectors are reserved sectors. Then, as shown in FIG. 7-2, sector 83 (Tl
, 83 sector) is a defective sector, then
The alternative sector for this sector is located at TI, 88 sector. Also, 1 like sector 82.85 of track T2.
For the existence of more than one defective sector per track, an alternative sector for one defective sector, e.g. T2, 82 sector, is placed in the spare sector (TI, 88 sector) of the same track T1, and the remaining defective For example, the alternative sector for the T2.85 sector is sector B O (TSPO
, PfO sector). That is, the disk address "13" is in the header part of Tl, 88 sector, and the disk address "22" is in the header part of T2°S8 sector.
A disk address "25" is written in the header portion of TSPo and 80 sectors, respectively. In this method,
It is necessary to indicate an alternative address in the header section of the defective sector. However, if a defective spot exists in the header, a read error will occur and the alternative address will not be known. Therefore, a special The disadvantage was that it required control. However, if there is a defective sector that does not have an error part to indicate an alternative address, the above method cannot be applied, and replacement must be performed on a track-by-track basis as in the case of Figure 1. There wasn't. Therefore, when the number of defective sectors is one sector per track, the number of spare tracks can be reduced compared to the case shown in FIG. 1, but when there are two or more sectors, the number of spare tracks required is This was almost the same as in the case of Figure 1, and a reduction in the actual storage capacity of the disk was unavoidable.

Incidentally, disk access is generally performed not only to one specific sector but to a large number of consecutive sectors. In the above method, for example, when all setters of track T2 are sequentially accessed, the (
(to the data part) access order is T2, SO→T2
゜81→T2.88→T2,83→T2.84→TSP
0.80->T2.86→T2.87. Here, T
2,81→T2,88. T2,88→T2,83. T2
, 84 → T8PO, S O.

Regarding TBPo, 8 Q→T2.86, since the access is no longer to an adjacent sector, the access speed is significantly lower than when there is no defective sector like track TO. Moreover, in the above-mentioned column, the track movement occurs twice, resulting in even more delay. Further, even in the case of track T1, for example, where there is only one defective sector, the above method yields TI, 82→Tl, 88, TI.

There are two cases in which access to adjacent sectors is no longer available, such as S8→Tl, 84, which again has the disadvantage of lowering the access speed.

The present invention has been made in view of the above circumstances, and its purpose is to:
An object of the present invention is to provide a magnetic disk device capable of increasing the substantial storage capacity of a defective disk and increasing the access speed.

Hereinafter, one embodiment of the present invention will be described with reference to the drawings. FIG. 3 shows the configuration of the magnetic disk device IO.

The magnetic disk device 10 has a disk device Jfi, 101 and a disk controller 102. Disk device 1
01 is a disk drive mechanism that drives and stops the disk 103, an access (seek) mechanism that moves the magnetic head and positions it to a desired track, and a write/read mechanism that writes and reads data to and from the disk 103 (all are not shown in the figure). It has a well-known configuration such as (not shown).

FIG. 4 shows an example of the format of the disk 103, with tracks TO, TI, ) racks T3 to T5 each having 88
The sector is used as a spare sector and the track TSPO
~TSP3 is used as a spare track. Track TO is the case where there is no defective sector, and the S8 sector is left as a spare sector. Truck T
I is a case where there is one defective sector (TI, S3 sector) as in the example of FIG. 2. However, this is different from the example shown in FIG. 2 in which a preliminary sector is directly allocated instead of a defective sector. Here, the disk addresses "13" to "17" that should originally be written in the header part of the T1°S3 sector to Tl and 87 sectors are
'' is the head of the next sector, ie, '[' 1.84 sector to T 1 r 88 sector.

Part v1! It's included. In other words, in this embodiment, the disk addresses "13" to "17" of each sector from the TI, which is the active sector, the 83rd sector to the subsequent TI, the 84th sector to Tl, and the 87th sector are stored one sector at a time. By staggered allocation to sectors of
The disk is formatted to replace defective sectors. Therefore, as is clear from the figure, the spare sector ('r 1 t
88 sector) is a normal sector.

S7 sector ((disk address to be assigned)
17" is given away. In this case, Tl is the defective sector, and TI is the normal sector.

This is the S4 sector.

Track T2 has a large number of defective sectors, and alternative address information designating spare track T8PO as an alternative track is written in the header portion of each sector.

Note that a track such as track T2 that is replaced on a track-by-track basis is referred to as a defective track.

Track T3 has two defective sectors (T
3.82 sector, T3.85 sector) exists, and the disk addresses "32" to "3" that should originally be written in the header part of the T3.82 sector to T3°S7 sector.
7" is the next sector, or if the next sector is a defective sector, the next sector,
Or, in the case of overflow because the next sector does not exist, the next track's first sector (so sector), that is, T3.83 sector, 'l''3, T4 sector, T
It is written in the 3.86th sector to the T3°S8 sector and the 1st part of the T4.80 sector. Track P4 has no defective sector, but due to overflow from the preceding track T3, T4.
Since disk address "37" is assigned to sector 80, the destination of disk address "40" to "47" is changed to the original destination of T4.80 sector to T.
4. Starting from the 87th sector, shift backward one sector at a time, and
It was changed from 4°81 sector to T4.88 sector.

In this case, the two defective sectors existing in track T3 are replaced by track T3 and track T
It will be converged in 2 tracks of 4.

Track T5 is the same as track TO, and if there is no defective sector, track T6 is track T2.
This is a case where there are a large number of defective sectors in the same manner as in , and each of them is disk formatted in the same manner as the tracks TO and T2 described above.

Although not shown in the disk format of Figure 4, the header of each sector includes a defective sector flag for distinguishing between a defective sector and a normal sector, and a defective sector flag for distinguishing between a defective track and a normal track. Defective track flag and CRC (CyclicRe
Information such as dundancy check) is also written.

Referring again to FIG. 3, 104 is the disk controller 10.
This is the control unit that forms the center of 1. The control unit 104 has a function of reading wI commands given from the arithmetic control unit 20 and controlling access to the disk device 101 . Control unit 104
A flag register 105 is provided on the target track (a sector consisting of) and held therein. The control unit 104 refers to the flag register 105, and if the defective sector flag is set, it determines that the corresponding sector is a defective sector, and the control unit 104 determines that the corresponding sector is a defective sector. If the sector is the last sector, it has a function of reading the header part of the first sector of the next track. Further, when the defective track flag is set, the control unit 104 determines that the track to which the corresponding sector belongs is a defective track, and performs seek to the spare (alternative) track specified in the header section. It is designed to generate commands. Further, the control unit 104 has a function of performing a read operation on the header portion of the next sector when the contents of the header portion cannot be read correctly (read error). Furthermore, the control unit 104 has a function of performing the same read operation as when detecting a defective sector even if the disk address indicated in the header section does not match the target disk address. . In this embodiment, when accessing a sector after a seek, the control unit 104 performs a header read operation starting from a sector whose physical position disk address is smaller than or equal to the target disk address. 106 is a control line between the control section 104 and the arithmetic control unit #20, and 107 is a control line between the control section 104 and the disk device 101.

108 is a driver/receiver as an interface for the control unit 104; 109 is a processor/receiver 109 that connects to a computing device 'f1.20' and a disk device tz o x;
are the data lines connected to each.

Next, the operation of one embodiment of the present invention will be described with full reference to the flowchart shown in FIG. For example, assume that a disk access command is given from the arithmetic control unit 20 to the control unit 104 of the disk control device 102 via the data line 109 and the control line 106, and that the command is an access command to disk address "13". .

The control unit 104 decodes the command and reads 83 of the track T1.
It is determined that the access is to a sector, and a corresponding seek command is given to the disk device 1o1 via the data line 109 and control line 107. The disk device 101 positions the magnetic head on the designated track (cylinder position corresponding to track T1) in response to this seek command. When the seek operation is completed, the control unit 202 issues a disk address read command to the disk device 101 as shown in step SPI in FIG.
give to In this embodiment, the disk address (header portion) is read from the physical sector position corresponding to the target disk address (r13J) or from a sector position further preceding the sector position. For example, now, the content of the header section of the 83rd sector of track T1 on disk 103 is
01, data line IO9, driver/
10 - It is assumed that the signal is transferred to the control unit 104 via the receiver XOa.

The control unit 104 determines whether the contents of the header section have been read normally, that is, whether a read error has occurred.
Judgment is made by RC check (step 8P2).

If the reading is performed normally, the control unit 104
refers to the flag register 105 and determines whether either the defective sector flag or the defective track flag is set (step 8).
P3). When the hook is upright, the control unit 10
Step 4 determines whether the flag is a defective sector flag (step BP4). Since sector TI, 83 is a defective sector, the defective sector flag is set, and the control unit 104 specifies the next sector (sector TI, 84) in step SP5.
)/S, gives the disk address read command to the disk device 101 again. In the above example, there is no defective spot in the header of the TI and E13 sectors, which are the defective sectors, and the contents of the header section can be read correctly, but there is no defective spot in the header of the sector. Step 8P for the spot to exist
Even if an error is detected in step 2, the control unit 104 reads the disk address of the next sector (TI, 84 sector). Then, if the contents of the header section are read normally from the TI and 84 disks, and neither the defective sector flag nor the defective track flag is set, the control unit 104 reads the Tl read from the disk device 101.

A comparison is made to determine whether the disk address indicated in the contents of the header portion of the S4 sector matches the target disk address "13" (step 5P6). In this case, as is clear from the disk format in Figure 4,
The disk address "13" is assigned to the TI, 84 sector, and the control unit 104 determines a match.

20-Next, the control unit 104 responds to the match determination and (the relevant Tl 18
4 sector) data section access command to disk device 1.
01 (step 5P7). Disk device 10
1 is Tl in response to an access command from the control unit 104, and 8
Reads the 4-sector data portion. This read data is then transferred to the arithmetic control unit @20 via the data line 109.

On the other hand, in the case of disk access to the sector comprising track T2, since a defective track flag is written in the header part of each sector, if the header part of at least one sector out of nine sectors is read normally, then , the determination in step SP4 is made, and in accordance with the determination result of the existence of a defective track, the control unit 104 issues a seek command to the spare track TSPO specified in the header section to the disk device 101 (step 8P8). . The following access is the track T mentioned above.
This is similar to the case of disk access to 1.

By the way, if a read error is detected in step SP2, the control unit 104 continues to read the disk address from the same track while sequentially changing the target sector (step 5P9) until the header section is successfully read.

Further, if it is determined in step SP6 that the addresses do not match, the control unit 104 determines whether the read disk address is smaller than the target disk address or the resultant (step 8P10). And if the read disk address is smaller than the destination disk address,
The control unit 104 reads the disk address of the next sector, and in the reverse case, notifies the s-nose control device 20 of an error.

In addition, although the case where each track T1-T6 was provided with one spare sector was explained in the said Example, the number of spare sectors is not limited to the said Example, and the number of defective sectors and It is preferable to provide an appropriate number of spare sectors depending on the distribution.

As is clear from the above description, according to the present invention, various effects as listed below can be obtained.

(111) If the number of defective sectors existing on the 9th track is less than or equal to the number of spare sectors provided on the track, it is sufficient to use the spare sectors. is redundant.

(2) Defective sectors are replaced not directly to spare sectors, but by sequentially shifting one sector at a time, including normal sectors, and converging on the spare sector of the final track. Since the direct replacement sector for the defective sector is located much closer to the defective sector than in the conventional examples shown in FIGS. 1 and 2, the access speed by replacing the defective sector is improved. The decrease in is small.

+311 If the number of defective sectors existing on a track exceeds the number of spare sectors provided on that track, the allocated sectors are sequentially shifted so that the precautionary sectors provided on each track are used in order. Therefore, the same effect as when a large number of spare sectors are provided can be obtained with a small number of spare sectors.

(4) In a magnetic disk device using a plurality of disks, track numbers (head numbers) are generally assigned to the front and back surfaces of each disk that corresponds to the same cylinder. For example, track the front side of cylinder 0 of the first disk, track 1 on the os'Wt side, track 2 on the front side of cylinder O of the second disk, and track the back side! ,... are allocated as follows.

This is because the access speed is increased by focusing on the fact that seek operations are not required within the same cylinder. By the way, the existence of a large defective spot inevitably affects the direction of adjacent cylinders of the relevant disk, but it also has an effect on the head direction (opposite surface within the same cylinder of the relevant disk, within the same cylinder of other disks). There is no necessity for it to have any influence. Therefore, in a magnetic disk device with track (head) allocation as described above, even if alternative sector allocation does not converge on the relevant track, it is possible to converge on other disk tracks in the same cylinder. Therefore, the spare sector can be used efficiently, and a seek operation is not required, so that the decrease in access speed due to replacement of the defective sector can be minimized.

(5) T41 above, (as shown in 51,
Even if the allocation of alternative sectors does not converge on the corresponding track due to the presence of a large number of defective sectors,
Since convergence is possible by using spare sectors of several tracks, which will be described later, the number of spare trunks can be kept to a minimum.

(6) If allocation of alternative sectors does not converge even if tracks from other disks in the same cylinder are used, by allocating a spare track as an alternative track, the spare sector can be used to create an alternative sector on multiple tracks. The reduction in access speed is much smaller than when staggered allocation is performed.

(7) Since there is no need to indicate an alternative address in a defective sector, there is no need for any error-free part in the sector, and in a defective track, at least one sector can be correctly read in the header (alternative address). Since it is only necessary to be able to read, the yield of disks is improved.

In summary, according to the magnetic disk device of the present invention, it is possible to increase the substantial storage capacity of a defective disk and to increase the access speed.

[Brief explanation of the drawing]

1 and 2 are diagrams showing a disk format applied to a conventional magnetic disk device, FIG. 3 is a block diagram showing an embodiment of the magnetic disk device of the present invention, and FIG.
The figure shows the format of the disc in the above embodiment, and FIG. 5 is a flowchart for explaining the operation. 10-... Magnetic disk device, 1oz... Disk device, 102... Disk control device, 1o3... Disk, 104... Control unit, 1o5... Flag register.

Claims (3)

[Claims] (1) One or more first storage areas consisting of a set of minimum storage areas to which one disk address is allocated and a predetermined number of spare minimum storage areas, or a set of '0 first storage areas, and a set of spare minimum storage areas. a second storage area, and a set of minimum storage areas, and each of the minimum storage areas includes one or more third storage areas formatted so that the common second storage area is used as an alternative storage area. , in the first storage area, the disk address corresponding to each minimum storage area from the defective minimum storage area to immediately before the corresponding first storage area or the spare minimum storage area of the subsequent first storage area is A disk device in which a disk formatted in such a way that it is sequentially shifted to a defect-free minimum storage area including the spare minimum storage area following the defective minimum storage area and a disk device that matches the target address information given from the outside. and a disk control device that controls access to a minimum storage area to which a disk address is assigned, and the disk control device reads and accesses the header portion of the minimum storage area of the disk in response to an access command given from the outside. If the header part is not read normally, the header part of the following minimum storage area is read accessed, while if the header part is read normally, the corresponding minimum storage area is accessed according to the contents of the header part. It is determined whether there is a defect in the storage area or the storage area, and if it is determined that there is a defect, the second storage area specified as the alternative storage area in the header section is sought, or the subsequent minimum While reading the header section of the storage area, if it is determined that there is no defect, it is detected whether the disk address indicated in the header section matches the above target address information, and when a mismatch is detected, the subsequent minimum storage A magnetic disk device whose characteristic is to repeatedly read access the header portion of an area until the desired minimum storage area is confirmed. (2) In the header section of each minimum storage area of the above disk,
Type 1 defect flag information determined for each minimum storage area to indicate whether the corresponding minimum storage area has a defect, and information common to each minimum storage area of the 36th female area. 2. The magnetic disk device according to claim 1, wherein type 2 defect flag information indicating whether or not the second storage area is to be used as an alternative storage area is written therein. (3) The disk control device includes a flag register that holds the first defect flag information and the second defect flag information of the header section l of the minimum storage area of the disk, and the contents of the flag register are the minimum defective flag. When indicating a storage area, the header section of the following minimum storage area is read accessed, and when the contents of the flag register indicate that the second storage area is an alternative storage area, the corresponding header section is accessed. 3. The magnetic disk device according to claim 2, wherein said second storage area is sought.