METHODS, SYSTEMS, AND COMPUTER READABLE MEDIA FOR PROVIDING FLEXIBLE HOST MEMORY BUFFER

• US 20160026406A1
• Filed: 07/30/2015
• Published: 01/28/2016
• Est. Priority Date: 06/05/2014
• Status: Active Grant

• Current Assignee: SanDisk Technologies LLC (Western Digital Corporation)
• Original Assignee: Sandisk Technologies Incorporated (Western Digital Corporation)
• Inventors: Hahn, Judah Gamliel, Desai, Girish Bhaurao, Dhulipala, Venkata Krishna Nadh, Erez, Eran, Jean, Sebastien Andre
• Granted Patent: US 9,563,382 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 12/0246 in block erasable memory, e.g. flash memory
• CPC Class Codes: G06F 12/0802 Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
• CPC Class Codes: G06F 12/0871 Allocation or management of cache space
• CPC Class Codes: G06F 12/0873 Mapping of cache memory to specific storage devices or parts thereof
• CPC Class Codes: G06F 2212/1016 Performance improvement
• CPC Class Codes: G06F 2212/1021 Hit rate improvement
• CPC Class Codes: G06F 2212/1041 Resource optimization
• CPC Class Codes: G06F 2212/1044 Space efficiency improvement
• CPC Class Codes: G06F 2212/205 Hybrid memory, e.g. using both volatile and non-volatile memory
• CPC Class Codes: G06F 2212/221 Static RAM
• CPC Class Codes: G06F 2212/283 Plural cache memories
• CPC Class Codes: G06F 2212/311 In host system
• CPC Class Codes: G06F 2212/313 In storage device
• CPC Class Codes: G06F 2212/466 Metadata, control data
• CPC Class Codes: G06F 2212/601 Reconfiguration of cache memory
• CPC Class Codes: G06F 2212/608 Details relating to cache mapping
• CPC Class Codes: G06F 2212/7201 Logical to physical mapping or translation of blocks or pages
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/0631 by allocating resources to storage systems
• CPC Class Codes: G06F 3/0656 Data buffering arrangements
• CPC Class Codes: G06F 3/0685 : Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
• CPC Class Codes: Y02D 10/00 : Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Methods, systems, and computer readable media for providing a flexible host memory buffer are disclosed. One method includes allocating an amount of host memory as a host memory buffer accessible by a solid state drive (SSD) as a cache for SSD data. The method further includes caching data from the solid state drive in the host memory buffer. The method further includes monitoring utilization of the host memory buffer. The method further includes dynamically increasing or decreasing the amount of host memory allocated for the host memory buffer based on the utilization.

Claims

1. A method for providing a flexible host memory buffer, the method comprising:

allocating an amount of host memory as a host memory buffer accessible by a solid state drive (SSD) as a cache for SSD data;

caching data from the solid state drive in the host memory buffer;

monitoring utilization of the host memory buffer; and

dynamically increasing or decreasing the amount of host memory allocated for the host memory buffer based on the utilization.

2. The method of claim 1 wherein allocating the amount of host memory for use as the host memory buffer includes performing an initial allocation of host memory space at startup of a host computing system.

3. The method of claim 1 wherein caching data from the SSD in the host memory buffer includes caching flash translation layer (FTL) tables in the host memory buffer.

4. The method of claim 1 wherein monitoring utilization of the host memory buffer includes determining whether a current workload on the host memory buffer is random input/output (I/O) intensive.

5. The method of claim 4 comprising, in response to determining that the workload is random I/O intensive, determining whether a current size of the host memory buffer is sufficient.

6. The method of claim 5 wherein determining whether a current size of the host memory buffer is sufficient includes determining whether a ratio of swaps between SSD memory and the host memory buffer and host reads has a predetermined relationship with respect to a threshold.

7. The method of claim 5 comprising, in response to determining that the current size of the host memory buffer is not sufficient, dynamically increasing the size of the host memory buffer.

8. The method of claim 4 comprising, in response to determining that the workload is not random I/O intensive, determining whether the current workload relating to accesses to the host memory buffer is CPU intensive.

9. The method of claim 8 wherein determining whether the current workload is CPU intensive includes determining whether a ratio of CPU cycles to CPU cycles relating to accesses to the host memory buffer has a predetermined relationship with respect to a threshold.

10. The method of claim 8 comprising, in response to determining that the workload is CPU intensive, dynamically reducing the amount of host memory allocated for the host memory buffer.

11. A system for providing a flexible host memory buffer, the system comprising:

a solid state drive (SSD);

a host memory including a host memory buffer accessible by the solid state drive as a cache for SSD data, wherein the solid state drive is configured to cache data from the solid state drive in the host memory buffer;

a workload analyzer for monitoring utilization of the host memory buffer; and

a host memory buffer manager for dynamically increasing or decreasing the amount of host memory allocated for the host memory buffer based on the utilization.

12. The system of claim 11 wherein the SSD is configured to cache flash translation layer (FTL) tables in the host memory buffer.

13. The system of claim 11 wherein the workload analyzer is configured to determine whether a current workload on the host memory buffer is random input/output (I/O) intensive.

14. The system of claim 13 wherein, in response to determining that the workload is random I/O intensive, the workload analyzer is configured to determine whether a current size of the host memory buffer is sufficient.

15. The system of claim 14 wherein the workload analyzer is configured to determine whether the current workload is random I/O intensive based on whether a ratio of swaps between SSD memory and the host memory buffer and host reads has a predetermined relationship with respect to a threshold.

16. The system of claim 14 wherein, in response to determining that the current size of the host memory buffer is not sufficient, the host memory buffer manager is configured to dynamically increase the size of the host memory buffer.

17. The system of claim 13 wherein, in response to determining that the workload is not random I/O intensive, the workload analyzer is configured to determine whether the current workload relating to accesses to the host memory buffer is CPU intensive.

18. The system of claim 17 wherein the workload analyzer is configured to determine whether the current workload is CPU intensive based on whether a ratio of CPU cycles to CPU cycles relating to accesses to the host memory buffer has a predetermined relationship with respect to a threshold.

19. The system of claim 17 wherein, in response to a determination that the workload is CPU intensive, the host memory buffer manager is configured to reduce the amount of host memory allocated for the host memory buffer.

20. A non-transitory computer readable medium having stored thereon executable instructions that when accessed by the processor a computer control the computer to perform steps comprising:

allocating an amount of host memory as a host memory buffer accessible by a solid state drive (SSD) as a cache for SSD data;

caching data from the solid state drive in the host memory buffer;

monitoring utilization of the host memory buffer; and

dynamically increasing or decreasing the amount of host memory allocated for the host memory buffer based on the utilization.

21. A method for allocating and reclaiming space for a host cache, the method comprising:

allocating an initial amount of host memory space for use as a host cache accessible by a solid state drive (SSD);

determining whether the host needs some or all of the space allocated for the host cache; and

in response to determining that the host needs some of all of the memory space allocated for the host cache, reclaiming, by the host system, at least some of the memory space allocated for the host cache.