RAID SYSTEM PERFORMANCE ENHANCEMENT USING COMPRESSED DATA AND BYTE ADDRESSABLE STORAGE DEVICES

• US 20170286220A1
• Filed: 03/29/2016
• Published: 10/05/2017
• Est. Priority Date: 03/29/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Gerhard, Adrian C., Moertl, Daniel F.
• Granted Patent: US 10,037,245 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 11/1056 Updating check bits on partial write, i.e. read/modify/write
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1096 Parity calculation or recalculation after configuration or reconfiguration of the system
• CPC Class Codes: G06F 2211/1004 Adaptive RAID, i.e. RAID system adapts to changing circumstances, e.g. RAID1 becomes RAID5 as disks fill up
• CPC Class Codes: G06F 2211/1014 Compression, i.e. RAID systems with parity using compression techniques
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/064 Management of blocks
• CPC Class Codes: G06F 3/0644 Management of space entities, e.g. partitions, extents, pools
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

A method for operating a RAID storage system includes configuring the RAID storage devices to receive in a read or write command a byte count, receiving a first data block to write to the storage system, compressing the received first data block to generate a first compressed data block, and then storing the first compressed data block memory. The method additionally includes executing a set of RAID operations to perform a partial stripe update, including: retrieving a second compressed data block from memory; determining a physical size of the second compressed data block; generating, based on the second compressed data block and the physical size, redundant data corresponding with the second compressed data block; and writing the second compressed data block and the redundant data by transmitting a write command including the second compressed data block, the redundant data, and the physical size to the set of RAID storage devices.

Claims

1. A method for operating a storage system, the storage system having memory and RAID storage devices, the method comprising:

configuring the RAID storage devices to receive in a read or write command a byte count, the byte count indicating an number of data bytes to read or write;

receiving, from a computing system, a first data block to write to the storage system;

compressing the received first data block to generate a first compressed data block, the first compressed data block including the first data block in compressed form;

storing the first compressed data block memory; and

executing a set of RAID operations to perform a partial stripe update to areas of the RAID storage devices, the set of operations including;

retrieving a second compressed data block from memory;

determining a physical size of the second compressed data block, the physical size indicating a byte count of the number of bytes in the second compressed data block;

generating, based on the second compressed data block and the physical size, redundant data corresponding with the second compressed data block; and

writing the second compressed data block and the redundant data to the areas of the RAID storage devices by transmitting a write command including the second compressed data block, the redundant data, and the physical size to the set of RAID storage devices.

2. The method of claim 1, wherein a ratio of the physical size of the second compressed data block in bytes to a size in bytes of a storage system sector includes a nonzero fractional portion.

3. The method of claim 1, further comprising:

transmitting a read command to the RAID storage devices to read a set of stored data blocks, the read command indicating a logical size of the set of stored data blocks as a nonzero integer multiple of a computing system block size;

receiving, from the RAID storage devices in response to transmitting the read command, the third compressed data block including the set of stored data blocks in compressed form and having a physical size that is less than the logical size of the set of stored data blocks;

generating compression statistics for the third compressed data block, the compression statistics including a compression ratio; and

storing the third compressed data block in memory.

4. The method of claim 3, further comprising:

receiving, from the RAID storage devices in response to transmitting the read command, a data structure indicating compressed sizes of each of one of the stored data blocks.

5. The method of claim 1, wherein configuring the RAID storage devices includes modifying the firmware of the RAID storage devices to enable the RAID storages devices to map at least one of a logical block address to a compressed data block, and a compressed data block to a physical block address.

6. The method of claim 1, wherein generating redundant data includes:

reading a stored data block corresponding to the second compressed data block from the RAID storage devices, wherein a stored data block corresponds with a compressed data block when the stored data block has a same physical size as the compressed data block and is located at a same physical address on a storage device that will be updated by the second compressed data block;

reading, from the RAID storage devices, a redundant data block corresponding to the stored data block; and

generating, based on the second compressed data block and the stored data block and the stored redundant data block, updated redundant data for performing at least one of an error detection and an error correction operation on the second compressed data block.

7. The method of claim 1, wherein the writing further includes transferring write command to the RAID storage devices over a serial attached small computer system interface data bus.

8. A storage system, comprising:

a set of one or more RAID storage devices configured to receive in a read or write command a byte count, the byte count indicating an number of data bytes to read or write;

a computing system interface to receive a data block from a computing system;

a storage controller having a processor and a memory, the memory having program instructions embodied therewith, the program instructions executable by the processor to cause the storage controller to;

receive, from a computing system, a first data block to write to the storage system;

compress the received first data block to generate a first compressed data block, the first compressed data block including the first data block in compressed form;

store the first compressed data block memory; and

execute a set of RAID operations to perform a partial stripe update to areas of the RAID storage devices, the set of operations to;

retrieve a second compressed data block from memory;

determine a physical size of the second compressed data block, the physical size indicating a byte count of the number of bytes in the second compressed data block;

generate, based on the second compressed data block and the physical size, redundant data corresponding with the second compressed data block; and

write the second compressed data block and the redundant data to the areas of the RAID storage devices by transmitting a write command including the second compressed data block, the redundant data, and the physical size to the set of RAID storage devices.

9. The storage system of claim 8, wherein a ratio of the physical size of the second compressed data block in bytes to a size in bytes of a storage system sector includes a nonzero fractional portion.

10. The storage system of claim 8, program instructions executable by the processor to further cause the storage controller to:

transmit a read command to the RAID storage devices to read a set of stored data blocks, the read to command indicate a logical size of the set of stored data blocks as a nonzero integer multiple of a computing system block size;

receive, from the RAID storage devices in response to transmitting the read command, the third compressed data block including the set of stored data blocks in compressed form and having a physical size that is less than the logical size of the set of stored data blocks;

generate compression statistics for the third compressed data block, the compression statistics including a compression ratio; and

store the third compressed data block in memory.

11. The storage system of claim 10, program instructions executable by the processor to further cause the storage controller to:

receive, from the RAID storage devices in response to transmitting the read command, a data structure indicating compressed sizes of each of one of the stored data blocks.

12. The storage system of claim 8, wherein configuring the RAID storage devices includes modifying the firmware of the RAID storage devices to enable the RAID storages devices to map at least one of a logical block address to a compressed data block, and a compressed data block to a physical block address.

13. The storage system of claim 8, program instructions executable by the processor to further cause the storage controller to:

read a stored data block corresponding to the second compressed data block from the RAID storage devices, wherein a stored data block corresponds with a compressed data block when the stored data block has a same physical size as the compressed data block and is located at a same physical address on a storage device that will be updated by the second compressed data block;

read, from the RAID storage devices, a redundant data block corresponding to the stored data block; and

generate, based on the second compressed data block and the stored data block and the stored redundant data block, updated redundant data for performing at least one of an error detection and an error correction operation on the second compressed data block.

14. The storage system of claim 8, program instructions executable by the processor to further cause the storage controller to transfer write command to the RAID storage devices over a serial attached small computer system interface data bus.

15. A computer program product for operating a storage system having memory and RAID storage devices, the computer program product including a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a processing circuit to cause the processing circuit to perform a method comprising:

configuring the RAID storage devices to receive in a read or write command a byte count, the byte count indicating an number of data bytes to read or write;

receiving, from a computing system, a first data block to write to the storage system;

compressing the received first data block to generate a first compressed data block, the first compressed data block including the first data block in compressed form;

storing the first compressed data block memory; and

executing a set of RAID operations to perform a partial stripe update to areas of the RAID storage devices, the set of operations including;

retrieving a second compressed data block from memory;

determining a physical size of the second compressed data block, the physical size indicating a byte count of the number of bytes in the second compressed data block;

generating, based on the second compressed data block and the physical size, redundant data corresponding with the second compressed data block; and

writing the second compressed data block and the redundant data to the areas of the RAID storage devices by transmitting a write command including the second compressed data block, the redundant data, and the physical size to the set of RAID storage devices.

16. The computer program of claim 15, wherein a ratio of the physical size of the second compressed data block in bytes to a size in bytes of a storage system sector includes a nonzero fractional portion.

17. The computer program of claim 15, the method further comprising:

transmitting a read command to the RAID storage devices to read a set of stored data blocks, the read command indicating a logical size of the set of stored data blocks as a nonzero integer multiple of a computing system block size;

receiving, from the RAID storage devices in response to transmitting the read command, the third compressed data block including the set of stored data blocks in compressed form and having a physical size that is less than the logical size of the set of stored data blocks;

generating compression statistics for the third compressed data block, the compression statistics including a compression ratio; and

storing the third compressed data block in memory.

18. The computer program of claim 17, the method further comprising:

receiving, from the RAID storage devices in response to transmitting the read command, a data structure indicating compressed sizes of each of one of the stored data blocks.

19. The computer program of claim 15, wherein configuring the RAID storage devices includes modifying the firmware of the RAID storage devices to enable the RAID storages devices to map at least one of a logical block address to a compressed data block, and a compressed data block to a physical block address.

20. The computer program of claim 15, wherein generating redundant data includes:

reading a stored data block corresponding to the second compressed data block from the RAID storage devices, wherein a stored data block corresponds with a compressed data block when the stored data block has a same physical size as the compressed data block and is located at a same physical address on a storage device that will be updated by the second compressed data block;

reading, from the RAID storage devices, a redundant data block corresponding to the stored data block; and

generating, based on the second compressed data block and the stored data block and the stored redundant data block, updated redundant data for performing at least one of an error detection and an error correction operation on the second compressed data block.