Managing host data placed in a container file system on a data storage array having multiple storage tiers

• US 9,594,514 B1
• Filed: 06/27/2013
• Issued: 03/14/2017
• Est. Priority Date: 06/27/2013
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Inventors: Bono, Jean-Pierre, Davenport, William C., de Forest, Miles A., Armangau, Philippe, Forrester, Walter C., Chen, Xiangping
• Primary Examiner(s): Giardino, Jr., Mark
• Assistant Examiner(s): Woolwine, Shane
• Application Number:
  US13/929,019
• Time in Patent Office: 1,356 Days
• Field of Search: 711/102, 711/103, 711/114
• US Class Current: 1/1
• CPC Class Codes: G06F 12/00 Accessing, addressing or allocating within memory systems or architectures digital input from, or digital output to record carriers, e.g. to disk storage units, G06F3/06
• CPC Class Codes: G06F 3/0605 by facilitating the interaction with a user or administrator
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0611 in relation to response time
• CPC Class Codes: G06F 3/0613 in relation to throughput
• CPC Class Codes: G06F 3/0644 Management of space entities, e.g. partitions, extents, pools
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/0649 Lifecycle management
• 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 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/0679 Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP]
• CPC Class Codes: G06F 3/0683 Plurality of storage devices
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

A technique manages host data in a data storage array. The technique involves placing, in response to host input/output (I/O) requests from a set of host devices, host data in a container file system which is stored in a slice pool of storage slices (e.g., storage space of a standard size such as 256 MB) formed by multiple storage tiers of the data storage array. Each storage tier provides storage access at a different storage access speed. The technique further involves assigning classifications to storage slices of the slice pool which store the container file system, each classification being assigned based on storage slice access history resulting from the host I/O requests. The technique further involves relocating portions of the container file system among the multiple storage tiers according to the classifications assigned to the storage slices of the slice pool.

Claims

1. A method of managing host data in a data storage array, the method comprising:

in response to host input/output (I/O) requests from a set of host devices, placing host data in a container file system which is stored in a slice pool of storage slices formed by multiple storage tiers of the data storage array, each storage tier providing storage access at a different storage access speed;

assigning classifications to storage slices of the slice pool which store the container file system, each classification being assigned based on storage slice access history resulting from the host I/O requests; and

relocating portions of the container file system among the multiple storage tiers according to the classifications assigned to the storage slices of the slice pool,

wherein the data storage array includes (i) a first storage tier formed by a first set of storage units which provides a first storage access speed, and (ii) a second storage tier formed by a second set of storage units which provides a second storage access speed, the first storage access speed being faster than the second storage access speed,

wherein relocating the portions of the container file system among the multiple storage tiers includes moving, as the portions of the container file system, particular host data placed in the container file system from the second set of storage units to the first set of storage units to provide faster storage access speed to the particular host data, and

wherein placing the host data in the container file system includes;

performing file-based I/O operations to place, as the host data in the container file system, an upper-deck file system having hierarchically arranged host files within the container file system,

wherein placing the host data in the container file system includes placing both data and metadata of the upper-deck file system within a file in the container file system.

2. A method as in claim 1 wherein the first set of storage units includes flash drives;

wherein the second set of storage units includes magnetic disk drives; and

wherein moving the particular host data includes;

repositioning the particular host data from the magnetic disk drives to the flash drives while the data storage array performs host I/O operations in response to newly received host I/O requests.

3. A method as in claim 1 wherein placing the host data in the container file system includes:

performing block-based I/O operations to place, as the host data in the container file system, a logical unit of storage within the container file system.

4. A method as in claim 1, further comprising:

while the host data is being placed in the container file system in response to the host I/O requests, providing ongoing host access to a production file of the container file system, the production file operating as a primary object which represents a current version of production host data.

5. A method as in claim 4, further comprising:

while the host data is being placed in the container file system in response to the host I/O requests, providing ongoing host access to a snapshot file of the container file system, the snapshot file operating as a snapshot object which represents a prior version of the production host data.

6. A method as in claim 1, further comprising:

while the host data is being placed in the container file system in response to the host I/O requests, providing ongoing host access to a set of files of the container file system, the set of files being formed by non-shared blocks to enable the container file system to operate as a standalone container in which no blocks are shared within the container file system.

7. A method as in claim 1, further comprising:

while the host data is being placed in the container file system in response to the host I/O requests, providing ongoing host access to a set of files of the container file system, the set of files being formed by sharable blocks to enable the container file system to operate as a deduplication container in which at least some blocks are shared by files of the container file system.

8. A method as in claim 1 wherein relocating the portions of the container file system among the multiple storage tiers further includes moving certain host data placed in the container file system from the first set of storage units to the second set of storage units to demote less active host data.

9. A method as in claim 1, further comprising:

evicting less active portions of the container file system from the first storage tier to the second storage tier in response to operations promoting more active portions of the container file system from the second storage tier to the first storage tier.

10. A method as in claim 1 wherein the data storage array maintains a slice access history database;

and wherein assigning the classifications includes;

updating the slice access history database to identify access rates for the storage slices of the slice pool which store the container file system.

11. A method as in claim 10 wherein relocating the portions of the container file system among the multiple storage tiers includes:

moving, as the portions of the container file system, particular host data between storage tiers based on the access rates for the storage slices of the slice pool which store the container file system.

12. A method as in claim 11 wherein moving the particular host data is performed in a manner which is transparent to the set of host devices while the data storage array performs host I/O operations in response to new host I/O requests received from the set of host devices.

13. A method as in claim 1, further comprising:

in response to receiving second host I/O requests from the set of host devices, placing second host data in a second container file system which is stored in the slice pool of storage slices formed by the multiple storage tiers of the data storage array,

wherein placing the second host data in the second container file system includes performing block-based I/O operations to place, as the second host data in the second container file system, a logical unit of storage realized within a file of the second container file system.

14. A method as in claim 13, further comprising relocating portions of the second container file system among the multiple storage tiers according to the classifications assigned to the storage slices of the slice pool.

15. A method as in claim 1, wherein the data storage array implements the upper-deck file system in its entirety within a single file of the container file system, the single file being one of multiple files in the container file system, and wherein the data storage array includes a mapping layer that maps the upper-deck file system to the single file of the container file system.

16. A method as in claim 15, wherein the mapping layer is configured to update an access history database that associates upper-level slice identifiers with back-end slice identifiers and corresponding slice temperature values.

17. A data storage array, comprising:

a host interface constructed and arranged to communicate with a set of host devices;

multiple storage tiers, each storage tier providing storage access at a different storage access speed; and

control circuitry coupled to the host interface and the multiple storage tiers, the control circuitry being constructed and arranged to;

in response to host input/output (I/O) requests from the set of host devices, place host data in a container file system which is stored in a slice pool of storage slices formed by the multiple storage tiers,

assign classifications to storage slices of the slice pool which store the container file system, each classification being assigned based on storage slice access history resulting from the host I/O requests, and

relocate portions of the container file system among the multiple storage tiers according to the classifications assigned to the storage slices of the slice pool,

wherein, when constructed and arranged to place the host data in the container file system, the control circuitry is further constructed and arranged to perform file-based I/O operations to place, as the host data in the container file system, an upper-deck file system realized within a file of the container file system, the upper-deck file system having hierarchically arranged host files within the file of the container file system,

wherein the control circuitry, constructed and arranged to place the host data in the container file system, is further constructed and arranged to place both data and metadata of the upper-deck file system within a file in the container file system.

18. A data storage array as in claim 17 wherein the multiple storage tiers includes (i) a first storage tier formed by a first set of storage units which provides a first storage access speed, and (ii) a second storage tier formed by a second set of storage units which provides a second storage access speed, the first storage access speed being faster than the second storage access speed;

and

wherein the control circuitry, when relocating the portions of the container file system among the multiple storage tiers, is constructed and arranged to move, as the portions of the container file system, particular host data placed in the container file system from the second set of storage units to the first set of storage units to provide faster storage access speed to the particular host data.

19. A data storage array as in claim 17, further comprising:

a slice access history database;

wherein the control circuitry, when assigning the classifications, is constructed and arranged to update the slice access history database to identify access rates for the storage slices of the slice pool which store the container file system.

20. A computer program product having a non-transitory computer readable medium which stores a set of instructions to manage host data, the set of instructions, when carried out by computerized circuitry of a data storage array, causing the computerized circuitry to perform a method of:

in response to host input/output (I/O) requests from a set of host devices, placing host data in a container file system which is stored in a slice pool of storage slices formed by multiple storage tiers of the data storage array, each storage tier providing storage access at a different storage access speed;

assigning classifications to storage slices of the slice pool which store the container file system, each classification being assigned based on storage slice access history resulting from the host I/O requests; and

relocating portions of the container file system among the multiple storage tiers according to the classifications assigned to the storage slices of the slice pool,

wherein placing the host data in the container file system includes performing file-based I/O operations to place, as the host data in the container file system, an upper-deck file system realized within a file of the container file system, the upper-deck file system having hierarchically arranged host files within the file of the container file system,

wherein placing the host data in the container file system includes placing both data and metadata of the upper-deck file system within a file in the container file system.

21. A computer program product as in claim 20 wherein the data storage array includes (i) a first storage tier formed by a first set of storage units which provides a first storage access speed, and (ii) a second storage tier formed by a second set of storage units which provides a second storage access speed, the first storage access speed being faster than the second storage access speed;

and

wherein relocating the portions of the container file system among the multiple storage tiers includes moving, as the portions of the container file system, particular host data placed in the container file system from the second set of storage units to the first set of storage units to provide faster storage access speed to the particular host data.

22. A computer program product as in claim 20 wherein the data storage array maintains a slice access history database;

and wherein assigning the classifications includes;

updating the slice access history database to identify access rates for the storage slices of the slice pool which store the container file system.