JPH056624A - Array disk device and control method thereof - Google Patents

Abstract

(57) [Abstract] [Purpose] Recording of tracks in an array disk device to which the disk surface is divided into a plurality of zones, and data is recorded by changing the recording density in the track direction for each zone. The OS of a general-purpose large-scale computer, which is made to have a constant density, can be used. [Structure] The disk devices 8 constituting the array disk device 1 are divided into a plurality of groups, and each group is configured to access tracks in different zones on the disk for each group based on a cylinder address designated by the host system 4. The disk device 8 is controlled. Further, the data transferred from the host system 4 is divided according to the ratio of the data capacities of the accessed tracks, and is simultaneously recorded in the respective disk devices 8.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a disk file device used in an information processing device such as a computer, and in particular, a disk surface is divided into a plurality of zones, and information is recorded by changing the data capacity per track for each zone. The present invention relates to an array disk device using a plurality of recorded disk devices.

[0002]

2. Description of the Related Art In an information processing apparatus such as a current computer, data required by a higher-order side such as a central processing unit (CPU) is stored in a secondary storage device, and the secondary storage device is requested in response to a request from the CPU. Data is written to and read from. A non-volatile storage medium is generally used for the secondary storage device. Typical examples of the secondary storage device include a magnetic disk device and an optical disk device.

In recent years, along with the advancement of advanced information, higher performance has been demanded with respect to the processing speed of the secondary storage device. For example, as one method for improving the processing capacity of a magnetic disk device, an array disk device including a large number of magnetic disk devices having a relatively small capacity as described below has been considered. The array disk device is a CPU
The data transferred from is divided and each of the divided data is simultaneously recorded in a plurality of magnetic disk devices.
On the contrary, when reading the recorded data, conversely, the data recorded in each magnetic disk device is simultaneously read, the original data is reproduced from the data read from each magnetic disk device, and the original data is transferred to the CPU. Perform parallel processing. In such parallel processing of a plurality of magnetic disk devices, the rotation of the disk, which is a recording medium, is synchronized in units of groups of magnetic disk devices that perform parallel processing, and the same address is applied to each magnetic disk device in the group. To access. As a result, the plurality of magnetic disk devices perform the same operation.

As a representative paper on the array disk device, "A Case for Redundant Arrays of Inexpensive Disks" by Patterson, Gibson, and Kurts (D. Patterson, G. Gibson, and
RHKartz: A Case for Redundant Arrays of Inexpen
sive Disks (RAID), in ACM SIGMOD Conference, Chicago,
IL, (June1988)). This paper describes the performance of an array disk device that divides data, which is a unit of processing once, and processes the data in parallel, and an array disk device that distributes individual data independently without dividing the data. And the results of reliability studies have been reported. At present, the array disk device of the method described in this paper is considered to be the most general array disk device.

In order to improve reliability in an array disk device, when data is recorded, an error correction code (hereinafter simply referred to as ECC) is calculated from divided data.
And the ECC is recorded in the magnetic disk device for storing the ECC (hereinafter referred to as ECC drive) at the same time as the recording of the data. By creating the ECC in this way, even if a failure occurs in one disk device in the group of magnetic disk devices in which the divided data is recorded and the data cannot be read, The data recorded in the failed magnetic disk device can be restored from the data recorded in the remaining magnetic disk device and the ECC.

In each disk device used in an array disk device that performs parallel processing, data is recorded in concentric tracks on a plurality of disk surfaces, as in a general disk device. Reading / writing of data from / to each disk surface is performed by read / write heads provided corresponding to each disk surface, and positioning of all read / write heads to tracks is simultaneously performed. A set of tracks that can be accessed by one-time positioning is called a cylinder. Normally, a cylinder address is assigned to each cylinder from the outer circumference to the inner circumference. The capacity of data recorded on each track is the same on all tracks. Therefore, in each magnetic disk device constituting the array disk device, the same amount of data can be handled in the same time even if any track in which cylinder is accessed. When parallel processing is performed in an array disk device using a disk device that is commonly used at present, the physical addresses of recorded data are all the same in each disk device that constitutes the array disk device. Therefore, by synchronizing the rotation of each disk device and issuing the same access command to each disk device, the read / write heads seek in the same direction so that all disk devices always access the same address at the same time. ing. In the array disk device, the plurality of disk devices are thus controlled as if one disk device is handled.

[0007]

On the disk surface, the inner track and the outer track have different lengths. Therefore, as described above, in a disk device in which all tracks on the disk surface have the same amount of data recorded in each track,
It means that the outermost track on the disk surface is used with a lower recording density.

However, in recent years, there has been an increasing demand for larger capacity of the disk device, and as shown in FIG. 5, the disk surface is divided into a plurality of zones, and the capacity of the data recorded in the track is divided in each zone. A technique has been developed in which the same data is recorded by changing the capacity of the data recorded in the track for each zone. By applying such a technique, the recording densities (linear densities) in the track directions of the tracks on the disc are made substantially the same, and the storage capacity per disc is reduced without lowering the recording density at the outer circumference. It is possible to increase. Therefore, the amount of data that can be recorded (storage capacity) in comparison with the case where the amount of data recorded on all tracks on the disk surface is constant
It is possible to realize a large disk device.

In order to further increase the storage capacity of the array disk device, as a disk device constituting an array disk, such a disk surface is divided into a plurality of zones, and the data capacity per track is changed for each zone. It is possible to apply a disk device. However, when a disk device that divides the disk surface into a plurality of zones and changes the data capacity per track for each zone to record data is applied to an array disk device, there are the following problems.

When the array disk device performs parallel processing, the plurality of disk devices constituting the array disk device are controlled as if they handle one disk device. For example, in each disk device constituting the array disk device, the same address is assigned to the cylinders physically located at the same position.
Then, at the time of recording / reproducing data, the read / write heads of the respective disk devices simultaneously access the same cylinder position. When the disc is recorded with different data capacity per track for each zone, the data capacity per track becomes smaller toward the inner zone, so each disk device accesses the same zone (cylinder) in this way. Then, the amount of data (data processing speed) that can be recorded in the same time varies depending on the zone to be accessed. That is, when processing the same amount of data, there is a problem in that the read / write time increases as the position goes to the inner circumference.

For example, assuming that the outer radius of the disk is ro, the inner radius is ri, and the linear density is c, a constant time t
The ratio of the amount of data that can be processed with is the amount of data on the outer circumference / the amount of data on the inner circumference = (2 × ro × π × c) / (2 × ri × π × c) = ro / ri. Therefore, if access is concentrated on the inner circumference side of the disk, the processing performance of the disk device will be greatly reduced.

Further, when the processing speed varies depending on the zone to be accessed, it is necessary to prepare a processing circuit corresponding to the outermost zone having the highest processing speed.

Further, since the array disk device logically handles a plurality of disk devices as one disk device, for example, when four disk devices are used, four disk devices are used.
One track for each disk unit,
A total of four tracks are processed as one track.
Therefore, when the storage capacity is changed for each zone, the capacity of the data recorded in the track differs depending on the zone being accessed. In an OS generally used in a general-purpose large-scale computer system, the amount of data recorded in each track of a disk device is
It is assumed that it is always constant. Therefore, if the capacity of the data recorded in the track differs depending on the zone to be accessed, it is necessary to take measures such as changing the OS. This OS change is a very large task and cannot be easily performed.

The present invention has the above problems when a disk device of a system in which the disk surface is divided into a plurality of zones and the recording density in the track direction is changed for each zone is applied to an array disk device. Solved, OS of general-purpose large-scale computer created with constant recording density of tracks
It is an object of the present invention to provide an array disk device that can be utilized by the.

[0015]

In order to achieve the above object, an array disk device of the present invention divides the disk surface into a plurality of zones and records data by changing the data capacity per track for each zone. A plurality of disk devices, for example, the zone in which the read / write head is located and the seek direction for moving the read / write head according to the cylinder address are made different by the disk device or by the group of disk devices. Preferably,
Each read of a disk device for storing multiple data
/ The data capacity per track is set for each zone so that the total data capacity of the tracks in the zone where the write head is located is always constant regardless of the position of the zone accessed by the read / write head.

Here, the positioning of the read / write head by the above cylinder address is performed by the disk device or the group of disk devices in the zone where the head actually accesses the same cylinder address designated from the upper side. Set differently. The read / write head access to each zone may be set by converting the cylinder address designated by the host device.

Further, the seek direction of the read / write head may have both a direction from the outer circumference to the inner circumference and a direction from the inner circumference to the outer circumference in the radial direction of the disk.

In such an array disk device,
It is preferable that the division of data for simultaneous reading and writing processing in parallel in each of the disk devices is divided into a ratio of the amount of data that can be processed at the same time in the zone where the head of each disk device is located.

Further, in the above array disk device, the ECC may be created according to the length of the longest data among the data processed by each of the disk devices. Here, when the ECC is created according to the length of the longest data among the data processed by each disk device, there is a difference in length between the data processed by each disk device and the longest data. It is preferable to fill the data with a bit pattern so that the length of each data is aligned with the longest data.

[0020]

In the method of recording data by dividing the disk surface into a plurality of zones and changing the data capacity per track for each zone, the data capacity per track in each zone is proportional to the radius. Therefore, the data capacity per track is larger in the outer peripheral zone, and the data capacity per track is smaller in the inner peripheral side. Therefore, by changing the zone in which the read / write head is located and the seek direction for moving the read / write head by the cylinder address for each disk device or for each group of disk devices, the address specified by the upper side is used. The difference in access time can be reduced. In addition, the total amount of data per track in the zones where the read / write heads of the plurality of data storage disk devices are located is constant regardless of the read / write head position. By setting the data capacity per hit, it is possible to make the amount of data processed at one time in the entire array disk device constant regardless of the position of the read / write head.

As a result, it is possible to use the OS of the conventional general-purpose large-sized computer as it is, without deteriorating the processing performance of the array disk device.

Further, in the present invention, as described above, the parallel processing of data is performed by making the zone in which the read / write head is located different depending on the disk device, for example. Therefore, data division for parallel data processing is performed by dividing the read / write head of each disk device into the ratio of the amount of data that can be processed at the same time in the zone where the read / write heads are located. / It is always constant regardless of the position of the write head, and the OS of the conventional general-purpose large-scale computer can be used as it is.

[0023]

1 is a block diagram of an array disk device according to an embodiment of the present invention.

An array disk device 1 is composed of an array disk controller 2 and an array disk unit 3. Reference numeral 4 denotes a CPU that serves as a host of the array disk device 1. Array disk controller 2
Further, the command decoding unit 12, the data dividing unit 14, and the data control unit (DCU) 5 having the ECC generating unit 15, the data buffer (DB) 6, the data restoring unit 7, and the CPU 4 input / output request and It is configured to include an interface control unit 11 that performs data communication. Further, the array disk unit 3 has a plurality of data storage disk devices (hereinafter referred to as data drives) 8 and ECC storage disk devices (hereinafter referred to as ECC drives) 9.

As shown in FIG. 2, the data transferred from the CPU 4 is divided into four, for example, a predetermined data length under the control of the data dividing section 14, such as data. The ECC generator 15 creates an ECC from the four pieces of divided data. Data divided into 4 and EC
After C is temporarily stored in the data buffer 6, under the control of the command decoding unit 12, the data drive 8 and E
It is stored in the CC drive 9. As will be described later, since only one ECC drive 9 is used in one read / write operation in this embodiment, only one ECC drive 9 is shown in FIG.

In this embodiment, as shown in FIG. 3, the ECC is a parity bit created by a group (parity group) formed by bits corresponding to mutually divided data ,. In the example of FIG. 3, the ECC is generated so that the number of 1 bits in the parity group is an odd number. That is, bit data,
,,, ECC is set to 0 when each corresponding bit has an odd number of 1's, and ECC is set to 1 when data, ... Has an even number of 1's. If the ECC is generated in this way and stored in the ECC drive 9, the data from each data drive 8 at the time of data reproduction ,.
If the number of 1's in the parity group formed by the ECC from the ECC drive 9 is not an odd number, it is known that the bit in the parity group has an error, and the data drive 8 in the array disk unit 3 Alternatively, it is possible to detect that a failure has occurred in any of the ECC drives 9.

In the case of reading data from the array disk device 1, contrary to the case of transferring data from the CPU 4, data from each data drive 8
The ECC is read from the CC drive 9 and temporarily stored in the DB 6. After that, under the control of the data division unit 14 of the DCU 5, the respective data are combined and reorganized into one data, which is transferred to the CPU 4.

In the case of reading data from the array disk device 1, contrary to the case of transferring data from the CPU 4, data from each data drive 8 ...
The ECC is read from the CC drive 9 and temporarily stored in the DB 6. After that, under the control of the data division unit 14 of the DCU 5, the respective data are combined and reorganized into one data, which is transferred to the CPU 4.

When one of the data drives 9 fails and the data in the data drive cannot be read, the data restoration unit 7 reads the data read from the normal data drive 8 and the ECC drive 9. EC read
Restore the data in the failed drive using C and DB6
It is stored in the relevant part of.

The rotation of each data drive 8 and the ECC drive 9 in the array disk unit 3 are synchronized and processed in parallel. As a result, the CPU 4 controls the timing as if processing is performed on one disk device.

In FIG. 4, the data drive 8 or EC
The internal structure of the disk device used as the C drive 9 is shown.

In the disk device, a plurality of disks 21 serving as recording media are provided so as to rotate about a single shaft 27. Data is recorded on concentric tracks 28 on each disk 21. In this embodiment,
As shown in FIG. 5, the disk 21 is divided into four zones, and the capacity of the data that can be recorded on the tracks 28 is changed for each zone so that the data recording densities on all the tracks 28 are substantially equal. .

A read / write head 22 for reading and writing data on the disk 21 is attached to the actuator 23, and at least one read / write head 22 is provided for the data recording surface of one disk 21. These read / write heads 22 use the actuators 23 to drive the disk 2
Positioned simultaneously with respect to track 28 on 1. Hereinafter, the head positioning operation is referred to as a seek operation. A set of tracks that can be accessed by one seek operation is a cylinder, and a cylinder address is assigned to each cylinder. As shown in FIG. 6, this cylinder address is recorded together with the head address and the like in the home address portion on the track where the recording information on the disk is recorded.

When writing or reading data on the disk 21, the array disk controller 2
The command decoding unit 12 analyzes the command from the CPU 4, and the disk devices 8 and 9 of the array disk unit 3 are analyzed.
Issue an access command to. Array disk unit 3
Each of the disk devices 8 and 9 in the head selector 2 selects the head corresponding to the head address specified by the access command.
The actuator 23 performs a seek operation up to the track corresponding to the cylinder address. Thereafter, the path selector 26 selects a path to the host, and the read / write circuit 25 reads / writes data.

In this embodiment, each data drive 8 in the array disk unit 3 is divided into two groups. Group 1 (data drive # 1, data drive # 2) is assigned cylinder addresses in order from the outer circumference to the inner circumference of the disk 21, and group 2 (data drive # 3, data drive # 4) is included in the disk 21. Cylinder addresses are assigned in order from the circumference to the circumference. In this embodiment, two ECC drives are provided and
A cylinder address is assigned to the CC drive # 1 similarly to the group 1 data drive, and the ECC drive # 2 is used.
Is assigned a cylinder address as in the group 2 data drive.

By doing so, even if an access command to the same cylinder address is issued from the DCU 5 to the array disk unit 3 to each data drive 8 constituting the array disk unit 3, the group 1 , 2 can access different zones. For example, as shown in FIG. 7, when group 1 accesses zone 1, group 2 accesses zone 4 (pattern 1), and when group 1 accesses zone 2, group 2 accesses zone 3. (Pattern 2). Similarly, when group 1 accesses zone 3, group 2 accesses zone 2 (pattern 3), and when group 1 accesses zone 4, group 2 accesses zone 1 (pattern 4).

When the zone to be accessed is changed depending on the group of disk devices, the data capacity in the track in each zone is shown below.

When the data capacity of each track from zones 1 to 4 is C1, C2, C3, C4, C1 + C
The track capacity of each zone is set so that 4 and C2 + C3 are equal. When the track capacity in each zone is set in this way, the amount of data that can be read / written per unit time (t) in each of zones 1 to 4 d
Between d1, d2, d3 and d4, d1 + d4 = d2 + d3
The relationship is established. Therefore, as shown in FIG. 8, the amount of data that can be read and written per unit time can be made constant between the patterns 1 to 4.

Next, a data dividing method in this embodiment will be described.

The method of data division in this embodiment is as follows.
There are two patterns as shown in FIG. Pattern 1
Is the case where either group 1 or 2 accesses tracks in zone 1 and the remaining groups access tracks in zone 4. Pattern 2 is a case where either group 1 or 2 accesses the track in zone 2 and the remaining groups access the track in zone 3.

In the data division, the command decoding unit 12 of the DCU 5 determines whether the zone to be accessed is the pattern 1 or the pattern 2 based on the cylinder address designated from the upper side. Based on this determination, the data dividing unit 14 divides the data transferred from the CPU 4.

For example, the data capacity C1, C2, C3, C4 per track in each zone is 60,
When it is set to 50, 40, 30 KB, the amount of data that can be read and written in each zone in unit time d1, d2, d
The ratio of 3, d4 is 6: 5: 4: 3. The data transferred from the CPU 4 may be divided according to this ratio. In this case, a 90 KB data write request is issued, and from the cylinder address specified by the upper side,
When it is determined that the pattern 1 is written in the zone 1 of the group 1 and the zone 4 of the group 2, the amount D1 of the data written in the zone 1 of the group 1, that is, the data drives # 1 and # 2 is 30 KB, and the group 2 is the data. The amount of data D4 written in zone 4 of drives # 3 and # 4 is 15
It becomes KB. As shown in FIG. 10A, under the control of the data division unit 14, the data transferred from the higher order is stored in the distribution DB 6 as data in byte units. At the same time, ECC generation unit 15 ECC
Is created and similarly stored in DB6.

In this way, the data is distributed byte by byte, and as shown in FIG. 10B, after the data allocated to the data become 15 KB of data respectively, the data is allocated to the data. Stop
Allocate the rest of the data only to the data.

When reading data from the array disk unit 3, conversely, the data transferred in parallel from the array disk unit 3 is temporarily stored in the DB 6, and the data dividing unit 14 stores the data in byte units.
Are assembled and transferred to the CPU 4. data,
After the data of 15 KB is supplied from each, the data is assembled only from the data.

When data is written in the zone 4 of group 1 and the zone 1 of group 2, CP is used as in the previous case.
The data transferred from U4 is distributed to the data ,,, and stored in the distribution DB 6, and after the data of 15 KB is allocated to the data, the data is distributed only to the data. Even when reading data from the array disk unit 3, the data transferred in parallel from the array disk unit 3 is assembled in the DB 6 in byte units, and after 15 KB of data is respectively supplied from the data. Builds data from data, only.

Even when the data division method is the pattern 2, the same process as the pattern 1 is performed. In this case, for example, if data is written in zone 2 of group 1 and zone 3 of group 2, the data recorded in zone 1 of group 1 or data drive # 1 and zone 2 of data drive # 2 is 25 KB and data recorded in zone 2 of group 2 or data drive # 3 and the data recorded in the zone 3 of the data drive # 4 is 20 KB.

An ECC as shown in FIG. 3 for the data divided as the pattern 1 or the pattern 2 in FIG.
9 is created, the ECC length becomes equal to the longest data among the divided data, as shown in FIG. That is, as shown in FIG. 9, the amount of ECC data is equal to the amount D1 of data written in zone 1 in pattern 1, and is equal to the amount D2 of data written in zone 2 in pattern 2.

Therefore, when creating an ECC, the difference between D1 and D4 is the difference between D1 and D4 when the data is divided into the shaded portions in FIG. 9, and the difference between D2 and D3 is the difference when the pattern is 2. A certain bit pattern, for example, as shown in FIG. 10B, is filled with a bit pattern or the like of a bit string composed of all 0s as shown in FIG. 10B to create an ECC. ECC generator 15
Generates the ECC by making the lengths of all the data thus divided equal to the length of the longest data. The ECC created in this way is stored in the ECC drive 9.

In this embodiment, since the ECC is created as described above, the amount of ECC created is equal to either the amount D1 of data recorded in zone 1 or the amount D2 of data recorded in zone 2. Will be things. So these E
To store CC at the same timing as data storage,
It is necessary to prepare two ECC drives 9.

For example, when the group 1 accesses the zone 1 and the group 2 accesses the zone 4, the amount of ECC becomes D1, and the ECC is written in the zone 1 of the ECC drive # 1. When the group 1 accesses the zone 2 and the group 2 accesses the zone 3, the amount of ECC becomes D2,
Write the ECC to zone 2 of C drive # 1. When the group 1 accesses the zone 3 and the group 2 accesses the zone 2, the ECC drive # 1 accesses the zone 3, and therefore the data capacity is insufficient to write the ECC of the data amount D2. Therefore, the drive storing the ECC is switched to the ECC drive # 2, and the zone 2 of the ECC drive # 2 is changed.
Write ECC to. Similarly, when the group 1 accesses the zone 4 and the group 2 accesses the zone 1, the ECC is written in the zone 1 of the ECC drive # 2.

As described above, by setting the track capacity of each zone and changing the zone to be accessed for each of the groups 1 and 2, as shown in FIG. It can be kept constant regardless of the zone in which it is operated.

In this embodiment, the number of data drives 9 in the array disk device 8 is set to four, but it is clear that this is feasible regardless of the number.

In this embodiment, the case where two dedicated disk devices are provided as the ECC drive is illustrated, but E
By handling the access to the CC drive independently of the access to the data drive, it is possible to have only one ECC-dedicated disk device.

In the first embodiment described above, the zones 3 and 4 of the ECC drive 9 are not used,
There is waste in the recording area of the disk device. Therefore,
A second embodiment in which the data division method is changed so that all recording areas can be effectively used will be described below.

FIG. 11 shows a block diagram of an array disk device according to the second embodiment. The array disk device of FIG. 11 has the same configuration as the array disk of FIG. 1 except that the ECC drive 9 for ECC writing is omitted from the disk devices constituting the array disk unit. In this embodiment, a part of the disk device 8a in the array disk unit 3a is used for both data and ECC, so that data (E) is stored in the disk device as in the first embodiment.
(CC) is prevented from generating a useless area where reading and writing of (CC) is not performed.

Also in this embodiment, as in the first embodiment described above, each disk device 8a in the array disk unit 3a is divided into two groups, group 1 (disk device # 1, disk device # 2). The cylinder addresses are sequentially assigned from the outer circumference to the inner circumference, and the group 2 (disk device # 3, disk device # 4) is oppositely assigned the cylinder addresses from the inner circumference to the outer circumference. In this embodiment, the data capacities of the tracks in zones 1 to 4 are C1 and C, respectively.
2, C3, C4, the data capacity of the tracks in each zone is set so as to satisfy C1 + C4 × 2 = C2 + C3 × 2. As a result, in the array disk unit 3a, the amount of data that can be processed within the same time can be made constant regardless of the position of the read / write head on the disk surface.

By setting the data capacity per track in this way, the data transferred from the CPU 4 is divided into three data in two patterns as shown in FIG.

When the ECC is created by the same method as in the first embodiment for the data divided into three in two patterns as shown in FIG. 12, the data amount of the ECC is the largest among the divided data. It is equal to the amount of data.

That is, when the data division is pattern 1, the ECC capacity is equal to D1 and when the data division is pattern 2, it is equal to D2. In the ECC generation unit 15,
The shaded portion in FIG. 10, that is, D1 in pattern 1
The difference between D4 and D4, and the difference between D2 and D3 in pattern 2 is filled with a certain bit pattern, for example, a bit pattern of a bit string consisting of all 0s, and the divided data lengths are all made equal to each other. To create.

Next, FIG. 13 and FIG. 1 show how the disk devices 8a in the array disk unit 3a are accessed.
4 shows. The data and ECC write operations in each state will be described below with reference to FIGS. 13 and 14.

In the state 1 of FIG. 13, the disk device # 1,
In # 2, the read / write head 22 is in zone 1,
In the disk devices # 3 and # 4, the read / write head 2 is in the zone 4. This state is the case where the data division is pattern 1 in FIG. Divided into 3
Of the two data, the data amount D1 is written in the zone 1 of the disk device # 1, and the data amount D4 is written in the zone 4 of the disk device # 3 and the drive # 4. At this time, the amount of ECC created is D1.
Is written to zone 1 of disk device # 2.

The state 2 in FIG. 13 is the disk devices # 1 and #.
2 shows the case where the read / write head 22 is in the zone 2 and the disk devices # 3 and # 4 have the read / write head 22 in the zone 3. In this case, the data is divided like pattern 2 in FIG. Of the divided data, the data having the data amount of D2 is written to the zone 2 of the disk device # 1, and the data having the data amount of D3 is written to the zone 3 of the disk device # 3 and the disk device # 4. At this time, since the data amount of the created ECC becomes equal to D2, it suffices to write in the zone 2 of the disk device # 2.

On the other hand, as shown in state 3 of FIG. 14, the read / write head 22 is in zone 4 in the disk devices # 1 and # 2, and the read / write head 22 is in zone 1 in the disk devices # 3 and # 4. , The data transferred from the CPU 4 is divided as shown in pattern 1 of FIG. Of the divided data, the data having the data amount of D1 is written in the zone 1 of the disk device # 4, and the data having the data amount of D4 is the disk device # 1.
And in zone 4 of disk device # 2. At this time, the amount of ECC data created by the ECC creating unit 15 is equal to D1 and is written in zone 1 of the disk device # 3. The disk device # 2 in which the ECC is written in the states 1 and 2 shown in FIG. 13 becomes the data writing disk device in the state 3 shown in FIG. 14 and the state 4 described next. Further, in the states 1 and 2 shown in FIG. 13, the disk device # 3 that was a disk device for writing data
Is a disk device for ECC writing in the states 3 and 4 shown in FIG.

The state 4 in FIG. 14 is the disk devices # 1 and #.
2 shows the case where the read / write head 22 is in the zone 3, and the disk devices # 3 and # 4 have the read / write head 22 in the zone 2. In this case, CPU4
The data from is divided like pattern 2 in FIG. Of the divided data, the data amount D2 is written in the zone 2 of the disk device # 4, and the data amount D2
The data of No. 3 is written in the zone 3 of each of the disk device # 1 and the disk device # 2. At this time, the amount of the ECC created by the ECC creating unit 15 becomes equal to D2, and the ECC is written in the zone 2 of the disk device # 3.

As described above, in the present embodiment, the disk device for writing the ECC is not fixed, but is dynamically changed with the movement of the read / write head.

In the first embodiment, the ECC drive 9 uses only the zones 1 and 2, and neither data nor ECC is recorded in the zones 3 and 4 of the ECC drive 9, which is a useless area. . However, in this embodiment, the disk device for writing the ECC is not fixed, but an area for the ECC is provided in a part of the disk device for data, and the disk device for writing the ECC is dynamically changed so that all zones can be used. There is. In addition, in the present embodiment as well, the first
It is obvious that the same effect as that of the embodiment can be expected. In addition, there is no restriction on how to divide the group or the number of disk devices constituting the array disk device.

Next, still another embodiment of the present invention will be described.

In the first and second embodiments described above, D
The CU 5 gives the same cylinder address to each disk device in the array disk unit without paying attention to the zone (cylinder) to which the disk device in the disk unit actually accesses. Different cylinders are accessed by changing the attachment method. Therefore, it can be said that the cylinder address conversion is performed in the array disk unit in the first and second embodiments. On the other hand, in this embodiment,
The address conversion is performed in the DCU 5, as shown in FIG.
As shown in FIG. 5, an address conversion unit 13 is included in the command decoding unit 12 of the DCU 5. Further, the cylinder addresses of all the disk devices 8b constituting the array disk unit 3b are attached so as to be physically the same. For example, for all disk devices, cylinder addresses are sequentially assigned from the outer circumference side to the inner circumference side of the disk.

In this embodiment, each disk device in the array disk unit 3b is divided into two groups as in the second embodiment. When accessing the array disk unit 3, the command decoding unit 12 analyzes the command from the CPU 4, and the address conversion unit 13 converts the address of the cylinder address transferred from the CPU 4 for each group of disk devices. Then, the access command is issued so as to change the zone for each group of disk devices.

The address conversion operation in the address conversion unit 13 may be performed as follows, for example. Here, 0 from the outer circumference to the inner circumference on the disk surface of each disk device.
It is assumed that cylinder addresses from 1 to 1000 are assigned.

When an access command to the cylinder address X is issued from the CPU 4 to the array disk device 1, the address conversion unit 13 in the DCU 5 performs the address conversion with the cylinder address of the group 1 as a reference. That is, the cylinder address of group 1 is set to the CPU
Address conversion is performed by matching with the cylinder address specified by 4. Therefore, the address conversion unit 13 obtains the cylinder address X as it is as the cylinder address of the group 1. On the other hand, the cylinder address of group 2 starts from the maximum value of 1000 cylinder addresses
It is obtained by subtracting the cylinder address transferred from U4. Therefore, in this case, the address conversion unit 13
1000-X is obtained as the cylinder address of group 2.

The command decoding unit 12 issues an access command to the group 1 and the group 2 using the cylinder address converted in this way. In this way
By issuing an access command to the disk device 8b belonging to the group 1 to the cylinder address X and to the disk device 8b belonging to the group 2 to the cylinder address 1000-X, different zones on the disk are allocated between the respective groups. Can be accessed.

Also in this embodiment, division of data to be written in each disk device 8b in the array disk unit 3b and generation / writing of ECC are performed in the same manner as in the second embodiment described above.

In this embodiment, the array disk unit 3
Although the number of disk drives in the inside is four and the ECC drive dedicated to the ECC is not provided, the ECC drive dedicated to the ECC writing is provided as in the first embodiment, and the disk drive for data and the ECC are provided. Obviously, it is possible to deal with the case where the disk drive is separated from the disk drive. In this case, the ECC drive may also perform address conversion and issue an access command in the same manner as the data drive.

[0075]

As described above, according to the present invention, the disk device constituting the array disk device is divided into a plurality of zones on the disk, and a disk device in which the data capacity per track is changed for each zone is provided. Even when used, the amount of data that can be processed within the same time can be made uniform in the entire array disk device. Therefore, it is possible to prevent the processing performance from being extremely changed by the cylinder address designated by the host.

[Brief description of drawings]

FIG. 1 is a diagram showing a configuration of a first exemplary embodiment of the present invention.

FIG. 2 is a diagram showing how data is transferred in the first embodiment of the present invention.

FIG. 3 is an explanatory diagram of an ECC generation method.

FIG. 4 is a structural diagram of each disk device that constitutes an array disk unit.

FIG. 5 is a diagram showing how zones are divided on a disc.

FIG. 6 is a diagram showing a configuration of tracks on a disc.

FIG. 7 is a diagram showing how a disk is accessed in the present invention.

FIG. 8 is an explanatory diagram of a data amount change according to the read / write head position of the present invention.

FIG. 9 is an explanatory diagram of a data division pattern according to the first embodiment.

FIG. 10 is an explanatory diagram of data distribution to each disk device.

FIG. 11 is a diagram showing a configuration of a second exemplary embodiment of the present invention.

FIG. 12 is an explanatory diagram of a data division pattern according to the second embodiment.

FIG. 13 is an explanatory diagram of a seek operation and data recording according to the second embodiment.

FIG. 14 is an explanatory diagram of a seek operation and data recording according to the second embodiment.

FIG. 15 is a diagram showing a configuration of a third exemplary embodiment of the present invention.

FIG. 16 is a diagram for explaining a problem when a disk drive in which a data capacity per track is changed for each disk zone is applied to an array disk device.

[Explanation of symbols]

1 ... Array disk device, 2 ... Array disk controller, 3 ... Array disk unit, 4 ... CPU, 5 ...
Data control unit, 6 ... Data buffer, 7
... data recovery unit, 8 ... data drive, 9 ... ECC drive.

Claims (17)

[Claims] 1. A recording medium is divided into a plurality of zones, and a plurality of disk devices each having a different data capacity per track are provided for each zone, and data transferred to and from a host system is transferred to the plurality of disk devices. An array disk device that simultaneously reads and writes data to and from the host system, decodes the I / O request from the host system, and, based on the cylinder address specified by the host system, changes the zone of different zones for each disk device or each group of disk devices. Means for positioning the read / write head of each disk device to a track, and dividing the data transferred from the host system into a plurality of data in response to an output request from the host system, and each of the plurality of disk devices. Means to write to both simultaneously, and input request from the host system Flip and the read plurality of the disk devices plurality of data simultaneously, the array disk apparatus characterized by comprising a means for reproducing the data to be transferred to the host system. 2. The array disk device according to claim 1, wherein said positioning means has means for converting a cylinder address designated by said host system for each said disk device or each group of said disk devices. An array disk device characterized by: 3. The array disk device according to claim 1, wherein the data capacity per track of each zone of the recording medium is the data of the track on which the read / write heads of the plurality of disk devices are located. An array disk device, wherein the sum of capacities is set to be constant regardless of a cylinder address specified by the host system. 4. The array disk device according to claim 1, wherein said dividing means divides data transferred from said host system into a data capacity per track of each zone in which said read / write head is positioned. An array disk device characterized by being divided according to a ratio. 5. The array disk device according to any one of claims 1 to 4, wherein the error correction code is created in accordance with the data length of the longest data among the divided data, and the error correction code An array disk device having a disk device for recording. 6. The array disk device according to claim 5, wherein the means for creating the error correction code comprises:
An array disk device characterized in that, for each of the divided data, a difference in data length from the data having the longest data length is filled with predetermined bits to generate the error correction code. 7. The array disk device according to claim 5, wherein the plurality of disk devices in which data is recorded include a disk device also functioning as a disk device for recording the error correction code. Disk device. 8. A plurality of disk devices in which a recording medium is divided into a plurality of zones and a data capacity per track is changed for each zone, and an input / output request from a host system is decoded and designated by the host system. Command decoding means for issuing an access command by designating the same cylinder address to each of the disk devices based on the cylinder address, and data transferred from the host system in response to an output request from the host system. Is divided into a plurality of pieces of data, and the plurality of pieces of data are simultaneously read into the plurality of disk devices, and a plurality of pieces of data are simultaneously read from the plurality of disk devices in response to an input request from the host system. An array disk device having means for reproducing data to be transferred, comprising: An array in which the disk devices are divided into a plurality of groups, and different cylinder addresses are assigned to cylinders located at the same physical location on the recording medium for each group of disk devices. Disk device. 9. The array disk device according to claim 8, wherein the group of disk devices is a group of disk devices in which the cylinder addresses are sequentially assigned from the inner circumference side to the outer circumference side of the previous recording medium. An array disk device comprising a group of disk devices in which the cylinder addresses are sequentially assigned from the outer circumference side to the inner circumference side of the disk-shaped recording medium. 10. The array disk device according to claim 8 or 9, wherein the data capacity per track of each zone of the recording medium is the data of the track on which the read / write heads of the plurality of disk devices are positioned. An array disk device, wherein the sum of capacities is set to be constant regardless of a cylinder address specified by the host system. 11. The array disk device according to claim 8, wherein said dividing means divides data transferred from said host system into data capacity per track in each zone where said read / write head is positioned. An array disk device characterized by being divided according to a ratio of. 12. A recording medium is divided into a plurality of zones, and a plurality of disk devices each having a different data capacity per track are provided for each zone, and data transferred to and from a host system is stored in the plurality of disks. In a method of controlling an array disk device that simultaneously reads and writes to a device, receives an input / output request and write data from the host system, and decodes the input / output request from the host system,
Based on the cylinder address specified by the host system, the read / write heads of each disk device are positioned on the tracks of different zones for each group of disk devices, and the data transferred from the host system is divided into a plurality of data. Then, the divided data is simultaneously written into each of the plurality of disk devices, and the array disk device control method. 13. The array disk device control method according to claim 12, wherein said positioning has a step of converting a cylinder address designated by a host system for each group of said disk devices. Control method. 14. A method of controlling an array disk device according to claim 12, wherein the division of the data is performed according to a ratio of data capacity per track of each zone in which the read / write head is positioned. A control method for a characteristic array disk device. 15. The method of controlling an array disk device according to claim 12, wherein an error correction code is generated in accordance with the longest data length of the data divided by the division of the data, A method of controlling an array disk device, wherein an error correction code is written to a part of the plurality of disk devices. 16. The method of controlling an array disk device according to claim 15, wherein in the step of generating the error correction code, a difference in data length from the longest data length is determined for each of the divided data. A method for controlling an array disk device, which comprises the step of filling with the bits of. 17. The method of controlling an array disk device according to claim 15 or 16, wherein the writing of the error correction code is performed simultaneously with the writing of the divided data.