JP3008801B2 - Storage device system and disk array controller - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an array type storage device system used in a computer system for distributing and storing a group of data such as files in a plurality of storage devices, and a disk array control device used therefor. In particular, a storage device system capable of dynamically adding a storage device for the purpose of improving data transfer speed or capacity without stopping the system and using the same.
And a disk array control device .

[0002]

2. Description of the Related Art As an array type storage system, a disk array system is generally used. A disk array system is a computer system in which a plurality of disk devices are operated in parallel for input and output.
This is a system for realizing high data transfer speed and high reliability between the processing device and the external storage device.

As an example of the configuration of a disk array system, see, for example, a paper by Paterson (D. Paterso).
n, G. Gibson, R. Katz, ”A Case for Redundant Array
s ofInexpensive Disks (RAID) ”, ACM SIGMOD conferen
ce porcedings, 1988, pp.109-116). In this paper, RAID (Redundunt Arrayof
A form of a disk array called Inexpensive Disks (Raid) is presented. In the RAID, ordinary input / output data is dispersedly stored in a plurality of drives (disk storage devices), and redundant data is recorded. The provision of the redundant data has the purpose of enabling the missing data to be restored by using it together with the data restoring function when the data is lost.

In a disk array system, a drive is added in units of a plurality of drive groups for data distribution. In this method, the extension area can be treated as a block of continuous areas, and data is not necessarily moved just by rewriting the address mapping information, and fetching processing after the addition of the storage device is easy. That is, the added area can be taken in by adding it after the maximum address of the storage area before the addition.

[0005] In addition, as for the addition of a drive for changing the width of data distribution as an addition of one storage device, particularly for the dynamic addition without stopping the system, only the data stored before the addition of the storage device is buffered. A method has been proposed which is realized by rearrangement using the above.

[0006]

In the conventional extension system,
When an additional storage device is added, only the data stored before the addition is rearranged. That is, the relocation of data in the storage area of the added storage device is not considered. Since the relocation cannot be performed on all data at once, the storage area of the added storage device is overwritten by the relocation, and the corresponding storage area becomes unusable. Therefore, the storage area of the added storage device cannot be used immediately after the addition, and only after the data relocation processing is completed.
There is a problem that the added storage capacity cannot be used. Further, when data was originally stored in the added storage device, this data could not be used at all.

When an additional storage device is used without relocation, the performance of the data transfer speed cannot be improved, the reliability of the data in the additional portion decreases, and the continuity of logical data and physical There is a problem that the continuity of various data becomes inconsistent.

Therefore, the technical problem to be solved by the present invention is:
In order to solve the above-mentioned problems of the prior art,
The purpose is to make the added storage capacity available immediately after the addition even when the storage devices are individually added, and to realize the addition dynamically without stopping the system.

[0009]

An object of the present invention is to relocate data on an added storage device in parallel with relocation of data stored before the extension, and furthermore, to logically locate the data. This can be achieved by performing rearrangement in consideration of continuity.

That is, a cache having a function of receiving a storage device expansion request and a data access request from the processing device, a function of recording data read from the storage device and output data from the processing device, and holding the data in the cache A cache control function, a data distribution pattern setting function for setting a data distribution pattern for a storage device group including an expanded storage device, and a prescribed amount determined from the number of storage devices and the redundancy of data of n storage devices existing before the expansion. A function to read out only the old data distribution pattern, a function to read out data of the added k storage devices by a prescribed amount determined by the number of storage devices and the redundancy, and a function to create redundant data according to the new data distribution pattern And the data read from the storage device that was A new data distribution pattern, a function of writing data read from an additional storage device to an area after the output of the new data distribution pattern, a function of controlling the progress of data relocation, and a distribution of new / old data. This can be realized by a function of recording a pattern boundary and a function of swapping a data area to a proper position after data rearrangement.

In addition, dynamic data distribution pattern change requires parallel processing of normal data input / output processing and data distribution pattern change processing, and can be realized by the following means.

That is, when there is a read request from the processing device for the data recorded in the cache, the data is transferred from the cache to the processing device without being read from the storage device, and is also recorded in the cache. When there is a write request from the processing device for the data that is being written, the cache that processes the access request from the processing device by overwriting and storing the output data from the processing device in the cache without directly writing to the storage device. This can be realized by a hit function and an input / output control function of inputting / outputting data to / from a storage device by applying a specified data distribution pattern.

[0013]

The data distribution pattern setting function, when receiving a notification of the addition of a storage device from the access receiving function, determines the number of storage devices to be added (k) and the number of storage devices originally included in the system to be read out from the control memory (k). n) and information on the redundancy (r) of the system are read, a new data distribution pattern is determined, and the new data distribution pattern is recorded in the control memory. The data distribution pattern before expansion is recorded as an old data distribution pattern. After that, the data relocation function is activated.

The data relocation function uses an input / output control function to read out a specified amount (n + kr) of data from each storage device including the added storage device and record it in the cache.

Using this data and the redundant data creating function, redundant data according to the new data distribution pattern is created and recorded in the cache.

The data relocation function uses the input / output control function to output the read data and newly created redundant data from the beginning of the relocation area of the storage device in a new data distribution pattern.

The boundary management function distinguishes a relocation incomplete area, a relocation completion area, and a relocation area as data relocation progresses, and determines which data distribution pattern the input / output control accesses. Give information to you.

In the above-described relocation processing, data of a prescribed value determined from the number of storage devices and the redundancy is processed in a processing unit (relocation group).
Indicates that the processing is completed within the processing unit.

In a system with redundancy r, n storage devices
When adding more storage devices, the specified value is (n + k-
r) is set, and a set of n × (n + kr) logically continuous data blocks recorded in the n storage devices before the addition and k × (k) of the k storage devices to be added are set. n + k-
r) together with the set of consecutive data blocks,
Define as a relocation group. The relocation processing is completed within this relocation group.

In the rearrangement process of the n × (n + kr) data blocks recorded in the n storage device groups before the expansion, the width of the data distribution is changed from n to (n + k).

The old redundant data block to be deleted is (n + kr) × r blocks, the newly created redundant data block is (n−r) × r blocks, and the total number of data blocks = n × (n + kr) − ( (n + kr) × r + (n−r) × r = (n + k) · (n−r)

This data has a data distribution width of (n +
k) By distributing the number of distribution blocks per storage device equally (n−r) for each storage device, rearrangement is possible and data without redundant data set does not occur.

Next, k × (n + k−)
In the rearrangement processing of r) data blocks, the width of data distribution is changed from 1 to (n + k).

No old redundant data blocks to delete
The number of newly created redundant data blocks is k × r, and the total number of data blocks = k × (n + kr) + k × r = (n + k) × k.

This data has a data distribution width of (n +
k), the number of distribution blocks per storage device is set equal to k for each storage device, so that the data can be rearranged, and data for which redundant data is not set does not occur.

The sum of the two data blocks is the same as the setting of the relocation group set first. That is, (n + k) · (n−r) + (n + k) × k = (n + k) · (n + k−r).

A storage device having a data distribution width of (n + k);
The number of data blocks per storage device is (n + kr). That is, all data blocks can be rearranged and stored in the original area, and new redundant data can be set for all data. This is also applicable when r ≧ 2 and r = 0.

The swap function maintains a partial collapse of the logical continuity of data accompanying the relocation processing in units of a relocation group. According to the logical continuity of the data, the data is searched. If the logical continuity is broken, the data is replaced with the data at the correct position (swap). The swap function searches according to the logical continuity of the data and replaces the data with the correct position, so that the situation where the data is not corrected to the correct position or the situation where the swap function does not end does not occur.

The cache control function keeps the data input by the relocation function in the cache until the data is output by the relocation function, and the cache hit function processes the access request with the data in the cache. As a result, it is possible to prevent unauthorized data access due to direct access to the storage device in response to a data access request for the area being relocated.

With these functions, it is possible to change the data distribution pattern.

The request accepting function accepting an access request from the processing unit requests the cache hit function if there is data in the cache, and requests the input / output control function to execute the access request if there is no data in the cache. .

The input / output control function checks whether or not the data is being relocated based on the information provided by the boundary management function. When a new data distribution pattern is selected and the data position is after the area being rearranged, not during the rearrangement, the old data distribution pattern is selected and the input / output processing to the storage device is performed. Data in the area being relocated is processed by the cache hit function.

[0033]

Embodiments of the present invention will be described below in detail with reference to the drawings. FIG. 1 is a configuration diagram of an array-type storage device system according to an embodiment of the present invention applied to a computer system. 1 includes a processing device 1001 (including a CPU) that issues an input / output request, a disk array control device 1010 that receives an input / output request, and a plurality of drive devices (storage devices) 1021 to 1 that record data.
025. In this embodiment, a system having four drive devices 1021 to 1024 before adding
This is an application example in the case where one drive device 1025 is added.

The disk array controller 1010 includes a host I / F (interface) 1011 for controlling input / output with the processing device (host device) 1001 and a cache memory (cache) for temporarily storing input / output data and the like.
1012, control memory 1 for storing various control data and the like
And various drive units including a drive I / F (interface) 1014 for controlling input / output to / from each drive device. The disk array control device 1010 performs various processes such as processing of an access request from the processing device 1001, input / output processing with a drive device, generation of redundant data, and restoration of data using redundant data.

In this embodiment, data is first recorded on four drive devices 1021 to 1024. Data is distributed to each drive device in units of blocks, and one parity data block is attached to every three blocks. The parity data (redundant data) is generated from data of three target blocks, and has a redundancy that can be restored even if any one block of data is lost. P in FIG.
Are redundantly stored in a plurality of drive devices 1021 to 1024 in order to avoid concentration of accesses to a specific drive device.

FIG. 2 shows a disk array controller 1010.
FIG. 3 is a configuration diagram showing details of the configuration. As shown in the figure, the disk array control device 1010 includes a data distribution pattern setting function 2010, a data relocation function 2020, a redundant data creation function 2030, a data restoration function 2040,
Data distribution pattern boundary management function 2050, cache control function 2060, access request reception function 2070
, A cache hit function 2080, an input / output control function 2090, a swap function 2100, and a host I / F 1
001, the cache 1012, and the control memory 100
3 and a drive I / F 1014.

FIG. 6 is a diagram showing boundary control accompanying data relocation. The relocation completion pointer 6012 indicates the final address of the relocation completion area 6020 where data relocation has already been completed and data access is possible with the data mapping information 11000 (FIG. 11) after the addition of the drive device.
The relocation not-executed pointer 6011 indicates the start address of the relocation not-executed area 6040 that has not been started yet. This area 6040 can be accessed with the data mapping information 10000 (FIG. 10) before the drive device is added. These pointers are stored in the control memory 10.
Record at 13. Relocation area 603 sandwiched between the relocation completion pointer 6012 and the non-relocation execution pointer 6011
0 indicates that the relocation process is being performed, and all access requests from the processing device 1001 to the area 6030 are processed by accessing the cache 1012 and do not access the drive device. The addresses in FIG. 6 correspond to the logical addresses in the data mapping information.

FIG. 8 shows a pointer situation in the swap processing. The swap pointer 8011 indicates the address of the data to be swapped. Swap destination pointer 801
2 is a pointer indicating the swap destination address 10030 of the data mapping information 11000. In the swap processing, the data 8021 and 8022 at the addresses indicated by the swap pointer 8011 and the swap destination pointer 8012 are exchanged. The addresses in FIG. 8 correspond to the logical addresses in the data mapping information.

FIG. 10 is a diagram showing a part of data mapping information of a data distribution pattern before expansion.
FIG. 7 is a diagram showing a part of data mapping information of a data distribution pattern after expansion. These are respectively stored in the control memory 1013 by the data distribution pattern setting function 2010.
Set above. The logical address 10010 is an address that sequentially numbers data blocks stored in the disk array control device 1010. However, the parity data is numbered in a different system from that of the data other than the parity data. The physical address 10020 indicates in which part of which drive device the data block of the logical address 10010 is actually stored. The column number 10021 is a number that is numbered in ascending order from the first data block in the drive device.
2 is a number for uniquely identifying the drives 1021 to 1025 managed by the disk array controller 1010. The swap destination address 10030 is a column number 10021 of a physical address that finally stores the data in the swap processing.

Next, referring to FIG.
The data relocation in the case where 5 is added will be described.

Since data is also recorded in the added drive device 1025, the drive devices 1021 to 1024
The data already stored in the relocation groups 4010 and 4
020,... (FIG. 4).
21 to 1025 are rearranged.

The data distribution pattern setting function 2010 accepting the expansion of the drive device sets a data distribution pattern with a data distribution width of 5 drives and a redundancy of 1 and stores it in the control memory 1013. Also, the relocation group 40
11, 4021... (FIG. 4), and then passes control to the data relocation function 2020.

Hereinafter, the relocation processing of the data relocation function 2020 will be described with reference to the processing flow of FIG.

First, in step 5010, the data distribution pattern setting function 2010 acquires the data mapping information 10000 before expansion, the data mapping information 11000 after expansion, and the information on the relocation group size recorded in the control memory 1013. .

In an initialization step 5020, a relocation non-execution pointer 6011 and a relocation completion pointer 6012 are set to the head address of the drive.

Relocation group read step 5030
Then, four blocks of continuous data 3011 (FIG. 3) are read from each drive device including the additional drive device 1025 from the address indicated by the relocation non-execution pointer 6011, and recorded in the cache 1012.

In the boundary adjustment step 5040, step 5
At 030, the relocation non-execution pointer 6011 is advanced to the final address of the data read.

In the redundant data deletion step 5050, the cache 1012 based on the data read out in step 5030 based on the data mapping information 10000 before expansion.
Deletes the parity data recorded in the cache from the cache.

In the parity data creation step 5060, new parity data 3021 (FIG. 3) is obtained from the data 3031 (FIG. 3) remaining after the redundant data is deleted in the step 5050 and the data mapping information 11000 after the expansion by using the redundancy data creation function 2030. Create 3). The created parity data 3021 is stored in the cache 1012.

In the data output step 5070, the data 3031 and the parity data 3021 are output by the input / output control function 2090. After completion of output, proceed to the next step.

In the boundary adjustment step 5080, the relocation completion pointer 6012 is set to the last address of the data output in step 5070, the data mapping information 10000 is searched from the logical address of the relocated data, and the physical address 10020 and the swap destination Address 10030
Set.

If the relocation completion pointer 6012 matches the final address of the drive device in the termination determination step 5090, the relocation is completed. If they do not match, the process returns to step 5030 to repeat the above-described processing.

FIG. 4 is a diagram showing the data arrangement before and after the rearrangement in detail. The relocation is performed by the relocation group 4010,
Since it is performed in units of 4011, as shown in the leftmost column of the data arrangement before and after the rearrangement in (2) of FIG. 4, for example, the logical address "9" which should be continuous on the drive device.
The data of the logical address “a” exists between the data of “13” and “13”. Also, the data of the logical addresses “a” and “e” are not continuous. This situation is resolved by a swap process.

Next, the swap processing will be described with reference to the flow of FIG.

First, in step 7010, data mapping information 11000 after expansion is obtained.

At step 7020, the swap pointer 8
011 is set as the head address of the drive.

At decision step 7030, data mapping information 1 of the address indicated by swap pointer 8011
1000 entries and the physical address 10020
Is compared with the swap destination address 10030. If they match, the process proceeds to step 7080 because swap is unnecessary. If not, the process proceeds to step 7040 because a swap is required.

At step 7040, the data at the address indicated by the swap pointer 8011 is read out and stored in the cache 1012.

In step 7050, a swap destination address 10030 is set in the swap destination pointer 8012, and
The data at that address is read and the cache 1012
To memorize.

In step 7060, the data at the address indicated by the swap pointer 8011 is output to the address indicated by the swap destination pointer 8012, and the data at the address indicated by the swap destination pointer 8012 is output to the swap pointer 8.
Output to the address indicated by 011.

In step 7070, the physical address 10020 and the swap destination address 10030 changed by the swap are written to the data mapping information 11000.

At step 7080, the swap pointer 8011 is advanced to the next logical address.

In decision step 7090, if the swap pointer 8011 matches the last address of the drive, the swap is completed. If not, step 7
From 030, the above processing is repeated.

FIG. 9 is a diagram showing how the data position changes in accordance with the flow of the swap processing. In step 1, the data of column numbers "1" to "3"
There is no need for swap, so it remains as it is. Since the swap processing is performed in the order of the logical addresses, the data of the column number “5” is subjected to the swap processing after the column number “3”.
The data 9015 of the column number “5” moves to the position of the column number “4” that should be stored. As a result, column number "4"
Move to the position of column number "5". In step 2, data 9016 of column number "6"
And the data 9014 of the column number “5” are swapped.
In step 3, data 9017 of column number "7" and data 9014 of column number "6" are swapped. Furthermore,
The data of column numbers “7” and “8” are left as they are because there is no need for swapping.

As described above, according to the present embodiment, when one drive is added, the data existing before the addition and the data of the added drive are simultaneously relocated, and the storage location is corrected by the swap processing. By doing so, the addition of one drive unit can be dynamically realized, and the storage capacity of the added storage device can be used immediately after the addition.

Further, since the data of the relocation group is collectively read out in the cache, the number of times of input / output with the drive device accompanying the data relocation processing is reduced, and the time required for the relocation processing can be shortened.

When a drive device is added, the parity data in the data distribution pattern before the addition is also read. Therefore, when a part of the data to be read cannot be read due to a total failure or a partial failure of the drive device. By using data on the cache, the data can be recovered without requiring input / output of new data.

[0068]

As described above in detail, according to the present invention, dynamic data relocation can be performed, and one storage device can be used instead of adding a plurality of storage device groups for distributing data. Expansion can be performed in units, and costs associated with expansion of storage capacity can be reduced. In addition, by adding storage devices,
Since the number of storage devices to which data is distributed can be changed, the data transfer speed can be improved by adding storage devices.

Furthermore, the capacity of the added storage device can be used without waiting for the completion of the data relocation processing.

[Brief description of the drawings]

FIG. 1 is a configuration diagram of an array-type storage device system according to an embodiment of the present invention applied to a computer system.

FIG. 2 is a block diagram showing a configuration of a disk array control device in FIG.

FIG. 3 is an explanatory diagram schematically showing a data flow in a data rearrangement process when a drive device is added in one embodiment of the present invention.

FIG. 4 is an explanatory diagram showing an example of data arrangement before and after rearrangement in one embodiment of the present invention.

FIG. 5 is a flowchart showing a relocation processing flow in one embodiment of the present invention.

FIG. 6 is an explanatory diagram showing an example of area division by relocation processing in one embodiment of the present invention.

FIG. 7 is a flowchart illustrating a swap processing flow in one embodiment of the present invention.

FIG. 8 is an explanatory diagram showing an example of a swap pointer and a swap destination pointer in one embodiment of the present invention.

FIG. 9 is an explanatory diagram showing an example of a change in data position due to a swap process in one embodiment of the present invention.

FIG. 10 is an explanatory diagram showing an example of data mapping information before expansion in one embodiment of the present invention.

FIG. 11 is an explanatory diagram showing an example of data mapping information after expansion in one embodiment of the present invention.

[Explanation of symbols]

 1001 Processing device 1010 Disk array control device 1012 Cache memory (cache) 1013 Control memory 1021 to 1025 Drive device 2010 Data distribution pattern setting function 2020 Data relocation function 2030 Redundant data creation function 2040 Data restoration function 2050 Data distribution pattern boundary management function 2060 Cache control function 2070 Access reception function 2080 Cache hit function 2090 I / O control function 2100 Swap function 6011 Relocation non-execution pointer 6012 Relocation completion pointer 6020 Relocation completion area 6030 Relocation area 6040 Relocation non-execution area 8011 Swap pointer 8012 Swap destination pointer 10,000, 11000 Data mapping information 10010 Logical address 1 020 physical address 10021 column number 10022 drive number 10030 swap destination address

────────────────────────────────────────────────── ─── Continuation of front page (72) Inventor Akira Yamamoto 1099 Ozenji Temple, Aso-ku, Kawasaki City, Kanagawa Prefecture Hitachi, Ltd. System Development Laboratory (56) References JP-A-8-212018 (JP, A) (58) Field surveyed (Int.Cl. ⁷ , DB name) G06F 3/06

Claims (5)

(57) [Claims] 1. A host interface for receiving a data read request from a processing device, and a drive interface for distributing data and redundant data from the processing device to a plurality of storage devices and storing the data therein. When the data on the storage device cannot be accessed when the data is read out and transferred to the processing device, the disk array control device that restores the data using the redundant data may be used to add a new storage device. A disk array control device that relocates data stored in an additional storage device together with relocated data. 2. A plurality of storage devices, a processing device that issues an input / output request for data in the storage device, a host interface that receives the request from the processing device, and data and redundant data from the processing device. In a storage device system including a drive interface for distributing and storing the data in a storage device and a disk array control device including a cache for temporarily storing the data, the control device is configured such that when a new storage device is added under the control, Read data from the storage device and the plurality of storage devices to the control device, create new redundant data based on the read data, and store the read data and the new redundant data in all storage devices after expansion. A storage system that relocates data by writing. 3. A plurality of storage devices, a processing device that issues an input / output request for data in the storage device, a host interface that receives the request from the processing device, and data and redundant data from the processing device. In a storage device system including a drive interface for distributing and storing the data in a storage device and a disk array control device including a cache for temporarily storing the data, when a new storage device is added under the control device, Means for reading data from the new storage device and the plurality of storage devices to the control device, means for newly creating redundant data, and transferring the read data and the new redundant data to all the storage devices after expansion. Means for writing,
Means for rearranging data, managing the logical positional relationship of data and the position recorded in the storage device, and means for exchanging (swapping) data contents between data recorded in the storage device. Means for adjusting the logical positional relationship of data, and for an access request from the processing device, means for storing the write position, means for comparing the access position of the access request with the write position, Means for determining a data distribution pattern used for data access from the result. 4. A control device controls n (n ≧ 1) storage devices, and outputs data from a processing device and a redundancy r (n> r ≧ 1).
0) is distributed and stored in the storage device, and in response to a data read request from the processing device, necessary data is read from the storage device and transferred to the processing device. In the case of an array-type storage device system having a function of restoring data that cannot be accessed by the control device when the data cannot be directly accessed, in the array type storage device system, k (k ≧ 1) storage devices are added under the control device. A total of n × (n + kr) from (n + kr) devices from each of the n storage devices storing data from before.
Means for reading a total of k × (n + kr) data from each of the data and the added k storage devices, and a total of k × (n + kr) data, and a storage device According to the redundancy of the system, (n +
means for newly creating r redundant data from (kr) pieces of data and (n + k) storage devices after the addition
Means for writing (n + kr) pieces of data and the r pieces of new redundant data, means for rearranging the data, and managing the logical positional relationship of the data and the position recorded in the storage device. And a means for exchanging (swapping) data contents between data stored in the storage device to adjust the logical positional relationship of the data, and store the write position for an access request from the processing device. And a means for comparing the access position of the access request with the write position, and a means for determining a data distribution pattern used for data access based on the comparison result. 5. The storage device system according to claim 2, wherein reading of stored data from before the addition of the storage device is suppressed from reading redundant data.