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

Patent metadata

Field	Value
Publication number	US-10657101-B2
Application number	US-201815990360-A
Country	US
Kind code	B2
Filing date	May 25, 2018
Priority date	Jun 28, 2013
Publication date	May 19, 2020
Grant date	May 19, 2020

Abstract

Techniques for utilizing flash storage as an extension of hard disk (HDD) storage are provided. In one embodiment, a computer system stores a subset of blocks of a logical file in a first physical file, associated with a first data structure that represents a filesystem object, on flash storage and a subset of blocks, associated with a second data structure that represents a filesystem object comprising tiering configuration information that includes an identifier of the first physical file, in a second physical file on HDD storage. The computer system processes an I/O request directed to the logical file by directing it to either the physical file on the flash storage or the HDD storage by verifying that the tiering configuration information exists in the data structure and determining whether the one or more blocks are part of the first subset of blocks or the second subset of blocks.

First claim

What is claimed is:

1. A method for optimizing locations for storing and servicing an access request for one or more blocks of a logical file, the method comprising:
classifying, by a computer system, a plurality of blocks into a firsts subset consisting of hot blocks and a second subset consisting of cold blocks, the classifying comprising classifying frequently accessed one or more blocks of the plurality of blocks into the first subset, and remaining blocks of the plurality of blocks into the second subset;
storing by the computer system, the firsst subset of blocks in a first physical file residing on a flash storage tier, and storing the second subset of blocks in a second physical file residing on a hard disk (HDD) storge tier;
receiving, by the computer system, an input/output (I/O) request to access one or more blocks of the plurality of blocks;
accessing a pointer block cache residing on the flash storage tier, the pointer block cache indicating placement of the requested one or more blocks on the flash storage tier or the HDD storage tier;
determining, by the computer system, whether the requested one or more blocks are stored on the first physical file or the second physical file based on resolving an offset of the requested one or more blocks to a valid logical block address in the pointer block cache;
upon determining that the requested one or more blocks are stored on the first physical file, directing the I/O request to the first physical file; and
otherwise, directing the I/O request to the second physical file.

2. The method of claim 1 , wherein directing the I/O request further comprises, on condition that the I/O request is a write request:
determining the write mode;
upon the write mode being set to a first value, directing the write request to both the first physical file and the second physical file;
upon the write mode being set to a second valuel directing the write request to solely the first physical file; and
upon the write mode being set to a third value, directing the write request to the first physical file and a third physical file distinct from the first and the second physical file.

3. The method of claim 1 , further comprising:
determining whether the I/O request is directed to a hybrid file or a non-hybrid file; and
upon determining that the I/O request is directed to a hybrid file, proceeding with a determiniation of a location of the requested one or more blocks of the first physical file or the second physical file.

4. The method of claim 1 , further comprising:
detecting an invocation of a tier-up operation or a tier-down operation with respect to one or more of the logical file;
moving data associated with the one or more blocks of the logical file from the second physical file to the first physical file in response to the tier-up operation; or
moving data associated with the one or more blocks of the logical file from the first physical file to the second physical file in response to the tier-down operation.

5. The method of claim 4 , wherein upon performing the tier-up opertion, updating a tiering map to reflect a current location in the first physical file of the one or more blocks of the logical file.

6. The method of claim 4 , wherein upon performing the tier-down operation, updating a tiering map to reflect a current location in the second physical file of the one or more blocks of the logical file.

7. The method of claim 1 , further comprising:
detecting an invocation of a collapse-tier operation with respect to one or more blocks of the logical file:
moving data associated with the one or more blocks of the logical file 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 storge medium having stored thereon computer software executable by a processor, the computer software embodying a method for optimizing locations for storing and servicing an access reqeust for one or more blocks of a logical file, the method comprising:
classifying, by a computer system, a plurality of blocks into a first subset consisting of hot blocks and a second subset consisting of cold blocks, the classifying comprising classifying frequently accessed one or more blocks of the plurality of blocks into the first subset, and remaining blocks of the plurality of blocks into the second subset;
storing, by the computer system, the first subset of blocks in a first physical file residing on a flash storage tier, and storing the second subset of blocks in a second physical file residing on a hard disk (HDD) storage tier;
receiving, by the computer system, an input/output (I/O) request to access one or more blocks of the plurality of blocks;
accessing a pointer block cache residing on the flash storage tier, the pointer block cache indicating placement of the requested one or more blocks on the flash storage tier on the HDD storage tier;
determining, by the computer system, whether the requested one or more blocsk are stored on the first physical file or the second physical file based on resolving an offset of the requested one or more blocks to a valid logical block address in the pointer block cache;
upon determining that the requested one or more blocks are stored on the first physical file, directing the I/O request to the first physical file, and
otherwise, directing the I/O request to the second physical file.

9. The non-transitory computer readable storage medium of claim 8 , wherein directing the I/O request further comprises, on condition that the I/O request is a write request:
determing the write mode;
upon the write mode being set to a first value, directing the write request to both the first physical file and the second physical file;
upon the write mode being set to a second value, directing the write request to solely the first physical file; and
upon the write mode being set to a third value, directing the write request to the first physical file and a third physical file distinct from the first and the second physical file.

10. The non-transitory coputer readable storage medium of claim 8 , wherein the first physical file and the second physical file sahre a common logical address space tht includes the same file system block offsets for the first physical file and the second physical file.

11. 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 one or more blocks of the logical file;
moving data associated with the one or more blocks of the logical file from the second physical file to the first physical file in respoinse to the tier-up operation; or
moving data associated with the one or more blocsk of the logical file from the first physical file to the second physical file in response to the tier-down operation.

12. The non-transitory computer readable storage medium of claim 11 , wherein upon performing the tier-up operation, updating a tiering map to reflect a current location in the first physical file of the one or more blocks of the logical file.

13. The non-transitory computer reaadable storage medium of claim 11 , wherein upon performing the tier-down operation, upating a tiering map to reflect a current location in the second physical file of the one or more blocks of the logical file.

14. The non-transitory computer readable storage medium of claim 8 , wherein, the method further comprises:
detecting an invocation of a collapse-tier operation with respect to one or more blocks of the logical file;
moving

Assignees

• Vmware Inc

Inventors

• Liu Deng
• Uttamchandani Sandeep
• Zhou Li
• Rawat Mayank

Classifications

• G06F9/45558

  Hypervisor-specific management and integration aspects · CPC title

• G06F3/0604

  Improving or facilitating administration, e.g. storage management · CPC title

• G06F2009/45579

  I/O management, e.g. providing access to device drivers or storage · CPC title

• G06F3/0685

  Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays · CPC title

• G06F2212/217

  Hybrid disk, e.g. using both magnetic and solid state storage devices · CPC title