Techniques for implementing hybrid flash/HDD-based virtual disk files

• US 9,182,927 B2
• Filed: 06/28/2013
• Issued: 11/10/2015
• Est. Priority Date: 06/28/2013
• Status: Active Grant

• Current Assignee: Vmware LLC (Broadcom, Inc.)
• Original Assignee: VMware, Inc. (Broadcom, Inc.)
• Inventors: Liu, Deng, Uttamchandani, Sandeep, Zhou, Li, Rawat, Mayank
• Primary Examiner(s): Shah, Sanjiv
• Assistant Examiner(s): GOLDSCHMIDT, CRAIG S
• Application Number:
  US13/931,409
• Publication Number:
  US 20150006788A1
• Time in Patent Office: 865 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 2009/45579 I/O management, e.g. providing access to device drivers or storage
• CPC Class Codes: G06F 2212/217 Hybrid disk, e.g. using both magnetic and solid state storage devices
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0611 in relation to response time
• CPC Class Codes: G06F 3/0655 Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects

Abstract

Techniques for utilizing flash storage as an extension of hard disk (HDD) based storage are provided. In one embodiment, a computer system can store a first subset of blocks of a logical file in a first physical file residing on a flash storage tier, and a second subset of blocks of the logical file in a second physical file residing on an HDD storage tier. The computer system can then receive an I/O request directed to one or more blocks of the logical file and process the I/O request by accessing the flash storage tier or the HDD storage tier, the accessing being based on whether the one or more blocks are part of the first subset of blocks stored in the first physical file.

Claims

1. A method for utilizing flash storage as an extension of hard disk (HDD) based storage, the method comprising:

storing, by a computer system, a first subset of blocks of a logical file in a first physical file residing on a flash storage tier, the first physical file being associated with a first inode data structure;

storing, by the computer system, a second subset of blocks of the logical file in a second physical file residing on an HDD storage tier, the second physical file being associated with a second inode data structure distinct from the first inode data structure, the second inode data structure comprising tiering configuration information that includes an identifier of the first physical file;

receiving, by the computer system, an I/O request directed to one or more blocks of the logical file; and

processing, by the computer system, the I/O request by directing the I/O request to the first physical file on the flash storage tier or to the second physical file on the HDD storage tier, the directing comprising;

verifying the tiering configuration information in the second inode data structure; and

in response to the verifying, determining whether the one or more blocks are part of the first subset of blocks in the first physical file or the second subset of blocks in the second physical file.

2. The method of claim 1 wherein the tiering configuration information further includes a write mode for the logical file.

3. The method of claim 2 wherein directing the I/O request further comprises, if the I/O request is a write request:

determining the write mode;

if the write mode is set to a first value, directing the write request to both the first physical file and the second physical file;

if the write mode is set to a second value, directing the write request to solely the first physical file; and

if the write mode is set to a third value, directing the write request to the first physical file and a third physical file distinct from the first and second physical files.

4. The method of claim 1 wherein the first physical file and the second physical file share a common file address space, such that each block of the logical file maps to the same file block offset in the first physical file and the second physical file.

5. The method of claim 4 wherein the first inode data structure includes a pointer block cache, the pointer block cache comprising mappings between file block offsets of the first physical file and logical block addresses (LBAs) of the flash storage tier, and

wherein determining whether the one or more blocks are part of the first subset of blocks or the second subset of blocks comprises:

accessing, from the pointer block cache of the first inode data structure, one or more LBAs mapped to the one or more blocks;

if the one or more LBAs are not null, determining that the one or more blocks are part of the first subset of blocks; and

if the one or more LBAs are null, determining that the one or more blocks are part of the second subset of blocks.

6. The method of claim 1 further comprising:

detecting an invocation of a tier-up operation or a tier-down operation with respect to a block of the logical file;

moving data associated with the block from the second physical file to the first physical file in response to the tier-up operation or from the first physical file to the second physical file in response to the tier-down operation.

7. The method of claim 1 further comprising:

detecting an invocation of a collapse-tier operation with respect to the logical file;

moving data associated with the first subset of blocks from the first physical file to the second physical file; and

deleting the first physical file from the flash storage tier.

8. A non-transitory computer readable storage medium having stored thereon computer software executable by a processor, the computer software embodying a method for utilizing flash storage as an extension of HDD-based storage, the method comprising:

storing a first subset of blocks of a logical file in a first physical file residing on a flash storage tier, the first physical file being associated with a first inode data structure;

storing a second subset of blocks of the logical file in a second physical file residing on an HDD storage tier, the second physical file being associated with a second inode data structure distinct from the first inode data structure, the second inode data structure comprising tiering configuration information that includes an identifier of the first physical file;

receiving an I/O request directed to one or more blocks of the logical file; and

processing the I/O request by directing the I/O request to the first physical file on the flash storage tier or to the second physical file on the HDD storage tier, the directing comprising;

verifying the tiering configuration information in the second inode data structure; and

in response to the verifying, determining whether the one or more blocks are part of the first subset of blocks in the first physical file or the second subset of blocks in the second physical file.

9. The non-transitory computer readable storage medium of claim 8 wherein the tiering configuration information further includes a write mode for the logical file.

10. The non-transitory computer readable storage medium of claim 9 wherein directing the I/O request further comprises, if the I/O request is a write request:

determining the write mode;

if the write mode is set to a first value, directing the write request to both the first physical file and the second physical file;

if the write mode is set to a second value, directing the write request to solely the first physical file; and

if the write mode is set to a third value, directing the write request to the first physical file and a third physical file distinct from the first and second physical files.

11. The non-transitory computer readable storage medium of claim 8 wherein the first physical file and the second physical file share a common file address space, such that each block of the logical file maps to the same file block offset in the first physical file and the second physical file.

12. The non-transitory computer readable storage medium of claim 11 wherein the first inode data structure includes a pointer block cache, the pointer block cache comprising mappings between file block offsets of the first physical file and logical block addresses (LBAs) of the flash storage tier, and

wherein determining whether the one or more blocks are part of the first subset of blocks or the second subset of blocks comprises:

accessing, from the pointer block cache of the first inode data structure, one or more LBAs mapped to the one or more blocks;

if the one or more LBAs are not null, determining that the one or more blocks are part of the first subset of blocks; and

if the one or more LBAs are null, determining that the one or more blocks are part of the second subset of blocks.

13. The non-transitory computer readable storage medium of claim 8 wherein the method further comprises:

detecting an invocation of a tier-up operation or a tier-down operation with respect to a block of the logical file;

moving data associated with the block from the second physical file to the first physical file in response to the tier-up operation or from the first physical file to the second physical file in response to the tier-down operation.

14. The non-transitory computer readable storage medium of claim 13 wherein the method further comprises:

detecting an invocation of a collapse-tier operation with respect to the logical file;

moving data associated with the first subset of blocks from the first physical file to the second physical file; and

deleting the first physical file from the flash storage tier.

15. A system for utilizing flash storage as an extension of HDD-based storage, the system comprising:

a processor; and

a non-transitory computer readable medium having stored thereon program code that, when executed by the processor, causes the processor to;

store a first subset of blocks of a logical file in a first physical file residing on a flash storage tier, the first physical file being associated with a first inode data structure;

store a second subset of blocks of the logical file in a second physical file residing on an HDD storage tier, the second physical file being associated with a second inode data structure distinct from the first inode data structure, the second inode data structure comprising tiering configuration information that includes an identifier of the first physical file;

receive an I/O request directed to one or more blocks of the logical file; and

process the I/O request by directing the I/O request to the first physical file on the flash storage tier or to the second physical file on the HDD storage tier, the directing comprising;

verifying the tiering configuration information in the second inode data structure; and

in response to the verifying, determining whether the one or more blocks are part of the first subset of blocks in the first physical file or the second subset of blocks in the second physical file.

16. The system of claim 15 wherein the tiering configuration information further includes a write mode for the logical file.

17. The system of claim 16 wherein directing the I/O request further comprises, if the I/O request is a write request:

determining the write mode;

if the write mode is set to a first value, directing the write request to both the first physical file and the second physical file;

if the write mode is set to a second value, directing the write request to solely the first physical file; and

if the write mode is set to a third value, directing the write request to the first physical file and a third physical file distinct from the first and second physical files.

18. The system of claim 15 wherein the first physical file and the second physical file share a common file address space, such that each block of the logical file maps to the same file block offset in the first physical file and the second physical file.

19. The system of claim 18 wherein the first inode data structure includes a pointer block cache, the pointer block cache comprising mappings between file block offsets of the first physical file and logical block addresses (LBAs) of the flash storage tier, and

wherein determining whether the one or more blocks are part of the first subset of blocks or the second subset of blocks comprises:

accessing, from the pointer block cache of the first inode data structure, one or more LBAs mapped to the one or more blocks;

if the one or more LBAs are not null, determining that the one or more blocks are part of the first subset of blocks; and

if the one or more LBAs are null, determining that the one or more blocks are part of the second subset of blocks.

20. The system of claim 15 wherein the program code further causes the processor to:

detect an invocation of a tier-up operation or a tier-down operation with respect to a block of the logical file;

move data associated with the block from the second physical file to the first physical file in response to the tier-up operation or from the first physical file to the second physical file in response to the tier-down operation.

21. The system of claim 15 wherein the program code further causes the processor to:

detect an invocation of a collapse-tier operation with respect to the logical file;

move data associated with the first subset of blocks from the first physical file to the second physical file; and

delete the first physical file from the flash storage tier.