Fast accessible compressed thin provisioning volume

• US 8,131,927 B2
• Filed: 11/30/2007
• Issued: 03/06/2012
• Est. Priority Date: 11/30/2007
• Status: Active Grant

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Kawaguchi, Tomohiro
• Primary Examiner(s): Alsip, Michael
• Application Number:
  US11/948,948
• Publication Number:
  US 20090144496A1
• Time in Patent Office: 1,558 Days
• Field of Search: 711/4, 711/112, 711/114, 711/118, 711/203, 711/E12.002, 707/693, 708/203, 710/68
• US Class Current: 711/114
• CPC Class Codes: G06F 12/0866 for peripheral storage systems, e.g. disk cache
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/0656 Data buffering arrangements
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

A computerized data storage system includes at least one storage device including a nonvolatile writable medium; a cache memory operatively coupled to the storage port and including a data storing area and a data management controller and a storage port. The storage port is operable to connect to a host computer, receive and send I/O information required by the host computer. The storage port is also operable to receive a request to read data, and, in response to the request to read data, the storage port is operable to send the data stored in the data storing area of the cache memory. The storage port is further operable to receive a request to write data, and, in response to the request to write data, the storage port is operable to send the write data to the data storing area of the cache memory. The storage system further includes a thin provisioning controller operable to provide a virtual volume having a virtual volume page, a capacity pool having a capacity pool page and manage a mapping between the virtual volume page and the capacity pool page. The storage system further includes a data compression controller operable to perform a compression operation, and a data decompression controller operable to perform a decompression operation.

Claims

1. A computerized data storage system comprising:

a. at least one storage device;

b. a cache memory operatively coupled to a storage port and a data management controller, the cache memory comprises a data storing area storing data;

c. the storage port, wherein the storage port operable to connect to a host computer, wherein the storage port receives and sends I/O information required by the host computer, wherein the storage port is operable to receive a request to read data, and, in response to the request to read data, the storage port is operable to send the data stored in the data storing area of the cache memory and wherein the storage port is operable to receive a request to write data, and, in response to the request to write data, the storage port is operable to send write data to the data storing area of the cache memory;

d. a thin provisioning controller, the thin provisioning controller operable to manage virtual volumes to which one or more capacity pool pages from capacity pools are allocated, and to which at least one of the virtual volumes is attributed as a target of a compression;

e. a data compression controller operable to perform a compression operation on the capacity pool page, and

f. a data decompression controller operable to perform a decompression operation on the capacity pool page;

wherein the data management controller is operable to;

store a first write data, which is corresponding to a first write request targeted to a first area in a first virtual volume not attributed as the target of a compression, in the cache memory,

allocate a first capacity pool page from the capacity pool to store the first write data;

wherein the data management controller is further operable to;

store a second write data, which is corresponding to a second write request targeted to a second area in a second virtual volume attributed as the target of the compression, in the cache memory,

transfer a data corresponding to the second write data to the cache memory from a second capacity pool page in the storage device after decompressing the data if the data was compressed,

merge the data corresponding to the second write data received from the second capacity pool page in the storage device with the second write data stored in the cache memory,

compress the merged data by the data compression controller, and

allocate a third capacity pool page, other than the first or second capacity pool page, from the capacity pools to store the compressed and merged data.

2. The computerized data storage system of claim 1, wherein the data storing area has faster access parameters than the at least one storage device.

3. The computerized data storage system of claim 1, wherein the at least one storage device comprises a plurality of storage units arranged into a RAID or a JBOD composition.

4. The computerized data storage system of claim 1, wherein the data compression controller is further operable to:

i. compare an uncompressed data size and a compressed data size; and

ii. if the compressed data size is equal or larger than the uncompressed data size, skip the compression operation on the capacity pool page.

5. The computerized data storage system of claim 1, wherein the data management controller comprises a data caching controller operable to perform a data caching operation, a data staging controller operable to perform a data staging operation and a data destaging controller operable to perform a data destaging operation.

6. The computerized data storage system of claim 5, wherein the data caching controller manages the data storing area to speed up I/Os operations of the host computer by using a cache control algorithm.

7. The computerized data storage system of claim 5, wherein the data staging controller is operable to transfer data from the at least one storage device to the data storing area if the data has not been cached in the at least one storage device when the storage port attempts to send the data to the host computer.

8. The computerized data storage system of claim 5, wherein the data destaging controller is operable to transfer dirty data from the data storing area to the at least one storage device.

9. The computerized data storage system of claim 8, wherein the at least one storage device comprises a plurality of storage units arranged into a RAID5 or RAID6 configuration and wherein the destaging controller is further operable to recalculate parity data and modify the parity data before the destaging operation.

10. The computerized data storage system of claim 1, wherein a virtual volume has no or limited capacity when it is established and is allocated capacity on demand.

11. The computerized data storage system of claim 1, wherein the capacity pool comprises a group of the storage devices, and provides at least some capacity area of the group of the storage devices to a virtual volume for storing virtual volume data.

12. The computerized data storage system of claim 1, wherein a virtual volume page comprises at least a portion of a virtual volume and represents a unit of virtual volume capacity allocation management.

13. The computerized data storage system of claim 1, wherein a capacity pool page comprises at least a portion of the capacity pool and represents a unit of virtual volume capacity provisioning management.

14. The computerized data storage system of claim 1, wherein the data compression controller is operable to interrupt data destaging operation by the data destaging controller.

15. The computerized data storage system of claim 14, wherein after the interruption, the data compression controller is operable to compress data and provide the compressed data size to the thin provisioning controller.

16. The computerized data storage system of claim 15, wherein following receipt of the compressed data size, the capacity controller is operable to reallocate a new capacity pool page and free used capacity pool page.

17. The computerized data storage system of claim 15, wherein after the reallocating, the compression controller is operable to return operation to the destaging controller and the destaging controller is operable to continue the destaging operation.

18. The computerized data storage system of claim 1, wherein the data compression controller is operable to compress data to generate a compressed page comprising compression management information, the compression management information being selected from a group consisting of compression dictionary information and check sum information.

19. The computerized data storage system of claim 1, wherein the data decompression controller is operable to interrupt the data staging operation by said data staging controller.

20. The computerized data storage system of claim 19, wherein after the interruption, the data decompression controller is operable to decompress the data and return the operation to the staging controller and wherein the staging controller is operable to continue the staging operation.

27. The computerized data storage system of claim 1, wherein the data management controller allocates a new capacity pool page having a size equal to the compressed and merged data.

28. The computerized data storage system of claim 1, wherein the data management controller is operable to:

check whether the read data exists on the cache memory when the request to read data is received via the storage port,

transfer the read data to the host computer from the cache memory if the read data exists on the cache memory, and

transfer a data corresponding to the read data to the host computer via the cache memory from the storage device after decompressing the data if the read data does not exist on the cache memory.

21. A method to be performed by a computerized data storage system, the method comprising:

a. managing capacity pool page for a capacity pool;

b. providing a storing area storing data in a cache memory;

c. receiving a request to read data from a host computer, and, in response to the request to read data, sending to the host computer the data stored in the cache memory;

d. storing a first write data, which is corresponding to a first write request targeted to a first area in a first virtual volume not attributed as the target of a compression, in the cache memory;

e. allocating a first capacity pool page from the capacity pool to store the first write data;

f. storing a second write data, which is corresponding to a second write request targeted to a second area in a second virtual volume attributed as the target of the compression, in the cache memory;

g. transferring a data corresponding to the second write data to the cache memory from a second capacity pool page in the storage device after decompressing the data if the data was compressed;

h. merging the data corresponding to the second write data received from the second capacity pool page in the storage device with the second write data stored in the cache memory;

i. compressing the merged data; and

j. allocating a third capacity pool page, other than the first or second capacity pool page, from the capacity pool to store the compressed and merged data.

22. The method of claim 21, further comprising:

a. comparing an uncompressed data size and a compressed data size; and

b. if the compressed data size is equal or larger than the uncompressed data size, skipping the compression operation on a virtual volume page.

23. The method of claim 21, further comprising:

a. performing a data caching operation;

b. performing a data staging operation; and

c. performing a data destaging operation.

29. The method of claim 21 further comprising, checking whether the read data exists on the storing area when the request to read data is received,

transferring the read data to the host computer from the storing area if the read data exists on the storing area, and

transferring a data corresponding to the read data to the host computer via the storing area from the storage device after decompressing the data if the read data does not exist on the storing area.

24. A non-transitory computer-readable medium embodying a set of instructions, the set of instructions, when executed by a storage system comprising one or more processors, causes the storage system to:

a. manage one or more capacity pool page for a capacity pool;

b. provide a storing area storing data in a cache memory;

c. receive a request to read data from a host computer, and, in response to the request to read data, send to the host computer the data stored in the cache memory;

d. store a first write data, which is corresponding to a first write request targeted to a first area in a first virtual volume not attributed as the target of a compression, in the cache memory;

e. allocate a first capacity pool page from the capacity pool to store the first write data;

f. store a second write data, which is corresponding to a second write request targeted to a second area in a second virtual volume attributed as the target of the compression, in the cache memory;

g. transfer a data corresponding to the second write data to the cache memory from a second capacity pool page in a storage device after decompressing the data if the data was compressed;

h. merge the data corresponding to the second write data received from the second capacity pool page in the storage device with the second write data stored in the cache memory;

i. compress the merged data; and

j. allocate a third capacity pool page, other than the first or second capacity pool page, from the capacity pool to store the compressed and merged data.

25. The computer-readable medium of claim 24, wherein the set of instructions further causes the storage system to:

i. compare an uncompressed data size and a compressed data size; and

ii. if the compressed data size is equal or larger than the uncompressed data size, skip the compression operation on a virtual volume page.

26. The computer-readable medium of claim 24, wherein the set of instructions further causes the storage system to:

a. perform a data caching operation;

b. perform a data staging operation; and

perform a data destaging operation.

30. The computer-readable medium of claim 24, wherein the set of instructions further causes the storage system to:

check whether the read data exists on the storing area when the request to read data is received,

transfer the read data to the host computer from the storing area if the read data exists on the storing area, and

transfer a data corresponding to the read data to the host computer via the storing area from the storage device after decompressing the data if the read data does not exist on the storing area.

31. A data storage system comprising:

a controller, which includes a cache memory temporality storing data, providing a plurality of virtual volumes; and

at least one storage device providing its storing area as capacity pool including a plurality of fixed-length storing regions;

wherein at least one of the virtual volume is attributed as a target of a compression;

the controller is operable to;

store a first write data, which is corresponding to a first write request targeted to a first area in a first virtual volume not attributed as the target of the compression, in the cache memory, allocate first one or more fixed-length storing regions from the capacity pool to store the first write data;

store a second write data, which is corresponding to a second write request targeted to a second area, to which second one or more fixed-length storing regions are allocated, in a second virtual volume attributed as the target of the compression, in the cache memory, read data corresponding to the second write data to the cache memory from second one or more fixed-length storing regions,

decompress the read data if the read data was compressed, merge the decompressed read data with the second write data stored in the cache memory, compress the merged data, and allocate third one or more fixed-length storing regions from the capacity pool to store the compressed merged write data.

32. The data storage system according to the claim 31, wherein the controller is further operable to free allocation of the second one or more fixed-length storing regions which are allocated to the second area in the second virtual volume after the data read out from the second one or more fixed-length storing region.

33. The data storage system according to the claim 31, wherein the controller is further operable to round up the size of merged data to the size of multiple number of the fixed-length storing region before the compression of the merged data.

34. The data storage system according to the claim 33, wherein the controller is further operable to fill predetermined data to area except for area having merged data to round up the size of merged data.

35. The data storage system according to the claim 34, wherein the predetermined data is 0 data.

36. The data storage system according to the claim 31, wherein the controller is operable to:

receive a read request, read the requested data from the cache memory if it is stored in the cache memory, read the requested data from the storage device and decompress the read requested data if it is not stored in the cache memory.

37. A data processing method executed by a storage system comprising:

a controller, which includes a cache memory temporality storing data, providing a plurality of virtual volumes; and

at least one storage device providing its storing area as capacity pool including a plurality of fixed-length storing regions;

wherein at least one of the virtual volume is attributed as a target of a compression;

wherein the data processing method comprising steps of;

storing a first write data, which is corresponding to a first write request targeted to a first area in a first virtual volume not attributed as the target of the compression, in the cache memory, allocating first one or more fixed-length storing regions from the capacity pool to store the first write data;

storing a second write data, which is corresponding to a second write request targeted to a second area, to which second one or more fixed-length storing regions are allocated, in a second virtual volume attributed as the target of the compression, in the cache memory, reading data corresponding to the second write data to the cache memory from second one or more fixed-length storing regions, after decompressing the read data if the data was compressed, merging the decompressed read data with the second write data stored in the cache memory, compressing the merged data, and allocating third one or more fixed-length storing regions from the capacity pool to store the compressed merged write data.

38. The data processing method according to the claim 37, further comprising step of:

free allocation of the second one or more fixed-length storing regions which are allocated to the second area in the second virtual volume after the data read out from the second one or more fixed-length storing region.

39. The data processing method according to the claim 37, further comprising a step of rounding up the size of merged data to the size of multiple number of the fixed-length storing region before the compression of the merged data.

40. The data processing method according to the claim 39, further comprising a step of filling predetermined data to area except for area having merged data to round up the size of merged data.

41. The data processing method according claim 40, wherein the predetermined data is 0 data.

42. The data processing method according to the claim 37, further comprising steps of:

receiving a read request, reading the requested data from the cache memory if it is stored in the cache memory, reading the requested data from the storage device and decompress the read requested data if it is not stored in the cache memory.