Increased parallelization efficiency in tiering environments

• US 10,572,386 B1
• Filed: 09/12/2018
• Issued: 02/25/2020
• Est. Priority Date: 09/12/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Gokhale, Amey, Nair, Ranjith R., Patil, Sandeep R., Eda, Sasikanth
• Primary Examiner(s): Nguyen, Than
• Application Number:
  US16/129,410
• Publication Number:
  US 20200081843A1
• Time in Patent Office: 531 Days
• Field of Search: 711169
• CPC Class Codes: G06F 11/1448 Management of the data involved in backup or backup restore
• CPC Class Codes: G06F 11/1461 Backup scheduling policy
• CPC Class Codes: G06F 12/02 Addressing or allocation; Relocation program address sequencing G06F9/00; arrangements for selecting an address in a digital store G11C8/00
• CPC Class Codes: G06F 12/06 Addressing a physical block of locations, e.g. base addressing, module addressing, memory dedication G06F12/08 takes precedence
• CPC Class Codes: G06F 12/08 in hierarchically structured memory systems, e.g. virtual memory systems
• CPC Class Codes: G06F 12/0884 Parallel mode, e.g. in parallel with main memory or CPU
• CPC Class Codes: G06F 12/0897 with two or more cache hierarchy levels with multilevel cache hierarchies G06F12/0811
• CPC Class Codes: G06F 2201/825 the problem or solution involving locking
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/064 Management of blocks
• 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

Abstract

A computer-implemented method, according to one embodiment, includes: receiving an operation request which corresponds to a given object, identifying multiple block addresses which are associated with the given object, determining whether any one or more of the identified block addresses have a token currently issued thereon, and combining the multiple block addresses to a first set in response to determining that at least one token is currently issued on one or more of the identified block addresses. A first portion of the block addresses determined as having a token currently issued thereon is transitioned to a second set. A remaining portion of the block addresses is also divided into equal chunks. The chunks are allocated in the first set across parallelization units, and the block addresses in the second set are divided into equal chunk. Furthermore, the chunks in the second set are allocated to a dedicated parallelization unit.

Claims

1. A computer-implemented method, comprising:

receiving an operation request which corresponds to a given object;

identifying multiple block addresses which are associated with the given object;

determining whether any one or more of the identified block addresses have a token currently issued thereon;

combining the multiple block addresses to a first set in response to determining that at least one token is currently issued on one or more of the identified block addresses;

transitioning a first portion of the block addresses to a second set, wherein the first portion includes ones of the block addresses determined as having a token currently issued thereon;

dividing a second portion of the block addresses into equal chunks, wherein the second portion includes the block addresses remaining in the first set;

allocating the chunks in the first set across two or more parallelization units;

dividing the block addresses in the second set into equal chunks; and

allocating the chunks in the second set to at least one dedicated parallelization unit.

2. The computer-implemented method of claim 1, comprising:

dividing the identified block addresses into equal chunks in response to determining that tokens are not currently issued on any of the identified block addresses; and

allocating the chunks across the two or more parallelization units and the at least one dedicated parallelization unit.

3. The computer-implemented method of claim 2, wherein allocating the chunks to the two or more parallelization units and the at least one dedicated parallelization unit based on whether any one or more of the identified block addresses have a token currently issued thereon increases a number of the two or more parallelization units and the at least one dedicated parallelization unit that are in a working state, thereby reducing an amount of processing delay experienced by the operation request.

4. The computer-implemented method of claim 1, wherein the operation request is a data access request received from a remote storage location.

5. The computer-implemented method of claim 1, wherein each of the two or more parallelization units perform a portion of the operation request which corresponds to the chunks of the given object allocated thereto, in parallel.

6. The computer-implemented method of claim 1, wherein the token is a byte-range lock or a Portable Operating System Interface (POSIX) lock.

7. The computer-implemented method of claim 1, wherein the operations are performed by a processor included at a cloud storage location of a cloud tiering environment.

8. A computer program product comprising 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 readable and/or executable by a processor to cause the processor to perform a method comprising:

receiving, by the processor, an operation request which corresponds to a given object;

identifying, by the processor, multiple block addresses which are associated with the given object;

determining, by the processor, whether any one or more of the identified block addresses have a token currently issued thereon;

combining, by the processor, the multiple block addresses to a first set in response to determining that at least one token is currently issued on one or more of the identified block addresses;

transitioning, by the processor, a first portion of the block addresses to a second set, wherein the first portion includes ones of the block addresses determined as having a token currently issued thereon;

dividing, by the processor, a second portion of the block addresses into equal chunks, wherein the second portion includes the block addresses remaining in the first set;

allocating, by the processor, the chunks in the first set across two or more parallelization units;

dividing, by the processor, the block addresses in the second set into equal chunks; and

allocating, by the processor, the chunks in the second set to at least one dedicated parallelization unit.

9. The computer program product of claim 8, the program instructions readable and/or executable by the processor to cause the processor to perform the method comprising:

dividing, by the processor, the identified block addresses into equal chunks in response to determining that tokens are not currently issued on any of the identified block addresses; and

allocating, by the processor, the chunks across the two or more parallelization units and the at least one dedicated parallelization unit.

10. The computer program product of claim 9, wherein allocating the chunks to the two or more parallelization units and the at least one dedicated parallelization unit based on whether any one or more of the identified block addresses have a token currently issued thereon increases a number of the two or more parallelization units and the at least one dedicated parallelization unit that are in a working state, thereby reducing an amount of processing delay experienced by the operation request.

11. The computer program product of claim 8, wherein the operation request is a data access request received from a remote storage location.

12. The computer program product of claim 8, wherein each of the two or more parallelization units perform a portion of the operation request which corresponds to the chunks of the given object allocated thereto, in parallel.

13. The computer program product of claim 8, wherein the token is a byte-range lock or a Portable Operating System Interface (POSIX) lock.

14. The computer program product of claim 8, wherein the processor is included at a cloud storage location of a cloud tiering environment.

15. A system, comprising:

a processor; and

logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to;

receive, by the processor, an operation request which corresponds to a given file in a filesystem;

identify, by the processor, multiple block addresses which are associated with the given file;

determine, by the processor, whether any one or more of the identified block addresses have a token currently issued thereon;

combine, by the processor, the multiple block addresses to a first set in response to determining that at least one token is currently issued on one or more of the identified block addresses;

transition, by the processor, a first portion of the block addresses to a second set, wherein the first portion includes ones of the block addresses determined as having a token currently issued thereon;

divide, by the processor, a second portion of the block addresses into equal chunks, wherein the second portion includes the block addresses remaining in the first set;

allocate, by the processor, the chunks in the first set across two or more parallelization units;

divide, by the processor, the block addresses in the second set into equal chunks; and

allocate, by the processor, the chunks in the second set to at least one dedicated parallelization unit.

16. The system of claim 15, the logic being configured to:

divide, by the processor, the identified block addresses into equal chunks in response to determining that tokens are not currently issued on any of the identified block addresses; and

allocate, by the processor, the chunks across the two or more parallelization units and the at least one dedicated parallelization unit.

17. The system of claim 16, wherein allocating the chunks to the two or more parallelization units and the at least one dedicated parallelization unit based on whether any one or more of the identified block addresses have a token currently issued thereon increases a number of the two or more parallelization units and the at least one dedicated parallelization unit that are in a working state, thereby reducing an amount of processing delay experienced by the operation request.

18. The system of claim 15, wherein the operation request is a data backup request received from a cloud storage location.

19. The system of claim 15, wherein each of the two or more parallelization units perform a portion of the operation request which corresponds to the chunks of the given file allocated thereto, in parallel.

20. The system of claim 15, wherein the token is a byte-range lock or a Portable Operating System Interface (POSIX) lock.