ANALYZING SUB-LUN GRANULARITY FOR DYNAMIC STORAGE TIERING

• US 20120072662A1
• Filed: 02/03/2011
• Published: 03/22/2012
• Est. Priority Date: 09/21/2010
• Status: Active Grant

• Current Assignee: Avago Technologies International Sales Pte Limited (Broadcom, Inc.)
• Original Assignee: LSI Corporation (Broadcom, Inc.)
• Inventors: Jess, Martin, McKean, Brian
• Granted Patent: US 8,341,350 B2
• Time in Patent Office: Days
• US Class Current: 711/114
• CPC Class Codes: G06F 12/0653 with centralised address assignment
• CPC Class Codes: G06F 3/0605 by facilitating the interaction with a user or administrator
• CPC Class Codes: G06F 3/0631 by allocating resources to storage systems
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• 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 method for metadata management in a storage system may include providing a metadata queue of a maximum size; determining whether the metadata for a particular sub-LUN is held in the metadata queue; updating the metadata for the particular sub-LUN when the metadata for the particular sub-LUN is held in the metadata queue; inserting the metadata for the particular sub-LUN at the head of the metadata queue when the metadata queue is not full and the metadata is not held in the metadata queue; replacing an entry in the metadata queue with the metadata for the particular sub-LUN and moving the metadata to the head of the metadata queue when the metadata queue is full and the metadata is not held in the metadata queue; and controlling the number of sub-LUNs in the storage system to manage data accessed with respect to an amount of available data storage.

Claims

1. A method for metadata management in a storage system, comprising:

using a computer or processor to perform the steps of

providing a least recently used (LRU) queue of a maximum size, the LRU queue configured for holding metadata for a maximum number of sub-LUNs;

determining whether the metadata for a particular sub-LUN is held in the LRU queue when the particular sub-LUN is being accessed;

updating the metadata for the particular sub-LUN and moving the updated metadata to the head of the LRU queue when the metadata for the particular sub-LUN is held in the LRU queue;

inserting the metadata for the particular sub-LUN to the LRU queue when the LRU queue is not full and the metadata for the particular sub-LUN is not held in the LRU queue;

replacing a last entry in the LRU queue with the metadata for the particular sub-LUN and moving that entry to the head of the LRU queue when the LRU queue is full and the metadata for the particular sub-LUN is not held in the LRU queue; and

controlling the number of sub-LUNs in the storage system to manage an amount of data accessed within a range of sub-LUNs including the particular sub-LUN with respect to an amount of available data storage within the range of sub-LUNs including the particular sub-LUN.

2. The method of claim 1, wherein the metadata for each sub-LUN comprises:

an accumulated access time to the sub-LUN;

an accumulated access measurement associated with the sub-LUN, the accumulated access measurement being at least one of;

an input/output count, and a size of data transfer; and

a time stamp for most recent access to the sub-LUN.

3. The method of claim 2, further comprising:

calculating a utilization rate for each sub-LUN having metadata held in the LRU queue, the utilization rate being calculated at least partially based on the accumulated access time and the accumulated access measurement associated with each sub-LUN; and

identifying at least one sub-LUN as frequently accessed based on the utilization rate for each sub-LUN having metadata held in the LRU queue.

4. The method of claim 1, wherein the storage system is configured for supporting sub-LUN tiering, and wherein replacing a last entry in the LRU queue further comprises:

determining whether the sub-LUN corresponding to the metadata held as the last entry in the LRU queue is in a higher performing tier in the storage system; and

initiating a process to move the sub-LUN corresponding to the metadata held as the last entry in the LRU queue to a lower performing tier in the storage system.

5. The method of claim 1, wherein the storage system is configured for supporting sub-LUN tiering, and wherein the method further comprises:

determining a utilization level of a higher performing tier in the storage system; and

increasing the size of the LRU queue to hold metadata for at least one additional sub-LUN when the utilization level of the higher performing tier is below a predetermined level.

6. The method of claim 1, further comprising:

determining a utilization level of a higher performing tier in the storage system; and

decreasing the size of the LRU queue to hold metadata for at least one less sub-LUN when the utilization level of the higher performing tier is above a predetermined level.

7. The method of claim 1, wherein the amount of data accessed within the range of sub-LUNs including the particular sub-LUN with respect to an amount of available data storage within the range of sub-LUNs including the particular sub-LUN is at least approximately 80%.

8. A method for metadata management in a storage system, comprising:

using a computer or processor to perform the steps of

providing a metadata queue of a maximum size, the metadata queue configured for holding metadata for a maximum number of sub-LUNs;

determining whether the metadata for a particular sub-LUN is held in the metadata queue when the particular sub-LUN is being accessed;

updating the metadata for the particular sub-LUN when the metadata for the particular sub-LUN is held in the metadata queue;

inserting the metadata for the particular sub-LUN to the metadata queue when the metadata queue is not full and the metadata for the particular sub-LUN is not held in the metadata queue;

replacing an entry in the metadata queue with the metadata for the particular sub-LUN when the metadata queue is full and the metadata for the particular sub-LUN is not held in the metadata queue; and

controlling the number of sub-LUNs in the storage system to manage an amount of data accessed within a range of sub-LUNs including the particular sub-LUN with respect to an amount of available data storage within the range of sub-LUNs including the particular sub-LUN.

9. The method of claim 8, wherein the metadata for each sub-LUN comprises:

an accumulated access time to the sub-LUN;

an accumulated access measurement associated with the sub-LUN, the accumulated access measurement being at least one of;

an input/output count, and a size of data transfer; and

a time stamp for most recent access to the sub-LUN.

10. The method of claim 9, further comprising:

calculating a utilization rate for each sub-LUN having metadata held in the metadata queue, the utilization rate being calculated at least partially based on the accumulated access time and the accumulated access measurement associated with each sub-LUN; and

identifying at least one frequently accessed sub-LUN based on the utilization rate for each sub-LUN having metadata held in the metadata queue.

11. The method of claim 9, wherein the storage system is configured for supporting sub-LUN tiering, and wherein replacing an entry in the metadata queue further comprises:

determining whether the sub-LUN corresponding to the metadata held in the entry to be replaced is in a higher performing tier in the storage system; and

initiating a process to move the sub-LUN corresponding to the metadata held in the entry to be replaced to a lower performing tier in the storage system.

12. The method of claim 8, wherein the storage system is configured for supporting sub-LUN tiering, and wherein the method further comprises:

determining a utilization level of a higher performing tier in the storage system; and

increasing the size of the metadata queue to hold metadata for at least one additional sub-LUN when the utilization level of the higher performing tier is below a predetermined level; and

decreasing the size of the metadata queue to hold metadata for at least one less sub-LUN when the utilization level of the higher performing tier is above a predetermined level.

13. The method of claim 12, wherein the amount of data accessed within the range of sub-LUNs including the particular sub-LUN with respect to an amount of available data storage within the range of sub-LUNs including the particular sub-LUN is at least approximately 80%.

14. The method of claim 8, wherein the metadata queue utilizes a least recently used algorithm.

15. A storage system configured for supporting sub-LUN tiering, comprising:

a higher performing tier;

a lower performing tier;

a metadata queue of a maximum size for holding metadata for a maximum number of sub-LUNs;

a metadata queue controller configured for managing the metadata held in the metadata queue and identifying at least one frequently accessed sub-LUN for moving to the higher performing tier, wherein the at least one frequently accessed sub-LUN is identified based on the metadata held in the metadata queue;

a metadata queue adjustment module configured for determining a utilization level of the higher performing tier and adjusting the size of the metadata queue based on the utilization level determined, where the number of sub-LUNs in the storage system is controlled to manage an amount of data accessed within a range of sub-LUNs including a particular sub-LUN with respect to an amount of available data storage within the range of sub-LUNs including the particular sub-LUN.

16. The storage system of claim 15, wherein the metadata for each sub-LUN comprises:

an accumulated access time to the sub-LUN;

an accumulated access measurement associated with the sub-LUN, the accumulated access measurement being at least one of;

an input/output count, and a size of data transfer;

a time stamp for most recent access to the sub-LUN; and

an indicator configured for indicating whether the sub-LUN is moved to the higher performing tier.

17. The storage system of claim 16, wherein the at least one frequently accessed sub-LUN further is identified by

calculating a utilization rate for each sub-LUN having metadata held in the metadata queue, the utilization rate being calculated at least partially based on the accumulated access time and the accumulated access measurement associated with each sub-LUN;

and

identifying at least one frequently accessed sub-LUN based on the utilization rate for each sub-LUN having metadata held in the metadata queue.

18. The storage system of claim 15, wherein the size of the metadata queue is adjusted based on the utilization level determined by

increasing the size of the metadata queue to hold metadata for at least one additional sub-LUN when the utilization level of the higher performing tier is below a predetermined level;

and

decreasing the size of the metadata queue to hold metadata for at least one less sub-LUN when the utilization level of the higher performing tier is above a predetermined level.

19. The storage system of claim 15, wherein the amount of data accessed within the range of sub-LUNs including the particular sub-LUN with respect to an amount of available data storage within the range of sub-LUNs including the particular sub-LUN is at least approximately 80%.

20. The storage system of claim 15, wherein the metadata queue utilizes a least recently used algorithm.