Neighbor based and dynamic hot threshold based hot data identification

Patent metadata

Field	Value
Publication number	US-9342389-B2
Application number	US-201414169877-A
Country	US
Kind code	B2
Filing date	Jan 31, 2014
Priority date	Apr 4, 2013
Publication date	May 17, 2016
Grant date	May 17, 2016

Abstract

An address is received. One or more neighbors associated with the received address is/are determined. One or more neighboring hot metrics is/are determined for the one or more neighbors associated with the received address. A hot metric for the received address is determined based at least in part on the neighboring hot metrics.

First claim

What is claimed is:

1. A system, comprising:
a memory with a cache portion and a non-cache portion;
a neighbor generator configured to:
receive an address; and
determine one or more neighbors associated with the received address;

a hot data identifier configured to determine one or more neighboring hot metrics for the one or more neighbors associated with the received address; and
a comparator configured to determine, based at least in part on the neighboring hot metrics, a hot metric for the received address,
wherein the received address is written to the cache portion of the memory when the determined hot metric for the received address corresponds to a hot data value.

2. The system of claim 1 , wherein the received address is associated with a host write.

3. The system of claim 1 , wherein the received address is associated with garbage collection.

4. The system of claim 1 , wherein the hot data identifier is configured to determine the neighboring hot metrics, including by:
obtaining a range of neighbors to consider;
determining one or more neighboring addresses on a first side of the received address based on the range;
determining one or more neighboring addresses on a second side of the received address based on the range;
determining, for the neighboring addresses on the first side, one or more neighboring hot metrics on the first side; and
determining, for the neighboring addresses on the second side, one or more neighboring hot metrics on the second side.

5. The system of claim 1 , wherein the comparator is configured to determine the hot metric for the received address, including by:
determining if at least one neighboring hot metric corresponds to a hot value;
in the event it is determined that at least one neighboring hot metric corresponds to the hot value, setting the hot metric for the received address to the hot data value; and
in the event it is determined that at least one neighboring hot metric does not correspond to the hot value, setting the hot metric for the received address to a cold data value.

6. The system of claim 1 , wherein the hot data identifier is configured to determine the neighboring hot metrics, including by:
determining a dynamic hot threshold; and
for each of the one or more neighbors:
determining a metric associated with a given neighbor to compare against the dynamic hot threshold; and
determining, based at least in part on the metric associated with the given neighbor and the dynamic hot threshold, a hot metric for the given neighbor.

7. The system of claim 6 , wherein the hot data identifier is configured to determine the dynamic hot threshold, including by determining the dynamic hot threshold using an average access count of logical block addresses (LBAs) in a block of interest.

8. The system of claim 6 , wherein the hot data identifier is configured to determine the dynamic hot threshold, including by determining the dynamic hot threshold using a measure of fullness of the cache portion of the memory.

9. The system of claim 6 , wherein the hot data identifier is configured to determine the dynamic hot threshold, including by determining the dynamic hot threshold using a difference between a wear level of the cache portion and a wear level of the non-cache portion of the memory.

10. A system, comprising:
a memory including a cache portion and a non-cache portion;
a dynamic hot threshold generator configured to determine a dynamic hot threshold; and
a hot data identifier configured to:
receive an address;
determine a metric associated with the received address to compare against the dynamic hot threshold; and
determine, based at least in part on the metric associated with the received address and the dynamic hot threshold, a hot metric for the received address,
wherein the received address is written to the cache portion of the memory when the determined hot metric for the received address corresponds to a hot data value.

11. The system of claim 10 , wherein the received address is associated with a host write.

12. The system of claim 10 , wherein the received address is associated with garbage collection.

13. The system of claim 10 , wherein the hot data identifier is configured to determine the dynamic hot threshold including by determining the dynamic hot threshold using an average access count of logical block addresses (LBAs) in a block of interest.

14. The system of claim 10 , wherein the hot data identifier is configured to determine the dynamic hot threshold including by determining the dynamic hot threshold using a measure of fullness of the cache portion of the memory.

15. The system of claim 10 , wherein the hot data identifier is configured to determine the dynamic hot threshold including by determining the dynamic hot threshold using a difference between a wear level of the cache portion and the wear level of the non-cache portion of the memory.

16. A method, comprising:
receiving an address;
determining one or more neighbors associated with the received address;
using a processor to determine one or more neighboring hot metrics for the one or more neighbors associated with the received address;
determining, based at least in part on the neighboring hot metrics, a hot metric for the received address; and
writing the received address to a cache portion of a memory when the determined hot metric for the received address corresponds to a hot data value.

17. The method of claim 16 , wherein using the processor to determine the neighboring hot metrics includes:
obtaining a range of neighbors to consider;
determining one or more neighboring addresses on a first side of the received address based on the range;
determining one or more neighboring addresses on a second side of the received address based on the range;
determining, for the neighboring addresses on the first side, one or more neighboring hot metrics on the first side; and
determining, for the neighboring addresses on the second side, one or more neighboring hot metrics on the second side.

18. The method of claim 16 , wherein determining the hot metric for the received address includes:
determining if at least one neighboring hot metric corresponds to a hot value;
in the event it is determined that at least one neighboring hot metric corresponds to the hot value, setting the hot metric for the received address to the hot data value; and
in the event it is determined that at least one neighboring hot metric does not correspond to the hot value, setting the hot metric for the received address to a cold data value.

19. The method of claim 16 , wherein using the processor to determine the neighboring hot metrics includes:
determining a dynamic hot threshold; and
for each of the one or more neighbors:
determining a metric associated with a given neighbor to compare against the dynamic hot threshold; and
determining, based at least in part on the metric associated with the given neighbor and the dynamic hot threshold, a hot metric for the given neighbor.

20. A method, comprising:
using a processor to determine a dynamic hot threshold; and
receiving an address;
determining a metric associated with the received address to compare against the dynamic hot threshold;
determining, based at least in part on the metric associated with the received address and the dynamic hot threshold, a hot metric for the received address; and
writing the received address to a cache portion of a memory when the determined hot metric for the received address c

Assignees

• Sk Hynix Inc

Inventors

• Tang Xiangyu
• Lee Frederick K H
• Bellorado Jason
• Zeng Lingqi
• Wu Zheng

Classifications

• G06F3/0616 Primary

  in relation to life time, e.g. increasing Mean Time Between Failures [MTBF] · CPC title

• G06F11/00 Primary

  Error detection; Error correction; Monitoring (error detection, correction or monitoring in information storage based on relative movement between record carrier and transducer G11B20/18; monitoring, i.e. supervising the progress of recording or reproducing G11B27/36; in static stores G11C29/00) · CPC title

• G06F11/3471

  Address tracing · CPC title

• G06F11/3409

  for performance assessment · CPC title

• G06F3/0679

  Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP] · CPC title