Data storage device and method for using secondary non-volatile memory for temporary metadata storage

Patent metadata

Field	Value
Publication number	US-9836232-B1
Application number	US-201514870571-A
Country	US
Kind code	B1
Filing date	Sep 30, 2015
Priority date	Sep 30, 2015
Publication date	Dec 5, 2017
Grant date	Dec 5, 2017

Abstract

A data storage device is disclosed comprising a volatile memory, a primary and a first secondary non-volatile memory (NVM), and control circuitry coupled to the volatile memory and the primary and first secondary NVM and configured to (a) write metadata and user data associated with a host write command to the volatile memory; (b) write the user data to the primary NVM; (c) continue to write metadata associated with each of one or more host write commands to the volatile memory, and when a first condition is met, write metadata that has accumulated in the volatile memory to the first secondary NVM; and (d) repeat (c), and when a second condition is met, then write at least a portion of the metadata that has accumulated in the first secondary NVM or the volatile memory to the primary NVM.

First claim

What is claimed is:

1. A data storage device comprising:
a volatile memory;
a primary non-volatile memory (NVM);
a first secondary NVM;
control circuitry coupled to the volatile memory and the first secondary and the primary NVM;
wherein the control circuitry is configured to:
(a) write metadata and user data associated with a host write command to the volatile memory;
(b) write the user data to the primary NVM;
(c) continue to write metadata associated with each of one or more host write commands to the volatile memory, and when a first condition is met, write metadata that has accumulated in the volatile memory to the first secondary NVM; and
(d) repeat (c), and when a second condition is met, then write at least a portion of the metadata that has accumulated in the first secondary NVM or the volatile memory to the primary NVM,

wherein the primary NVM is a disk comprising a plurality of data tracks, wherein the control circuitry is further configured to write user data associated with each host write command to at least one of the data tracks, and wherein the first condition is met when the control circuitry has written user data to a first number of data tracks.

2. The data storage device as recited in claim 1 , wherein the metadata associated with each host write command comprises a mapping table update, and wherein the first condition is met when the volatile memory receives a first number of mapping table updates.

3. The data storage device as recited in claim 2 , wherein the primary NVM comprises a disk comprising a media-based cache, and wherein the mapping table update comprises an update for a media-based cache mapping table.

4. The data storage device as recited in claim 1 , wherein the first condition is met after a predetermined amount of time has expired after a first write of metadata to the first secondary NVM.

5. The data storage device as recited in claim 1 , wherein the primary NVM comprises a plurality of zones, and wherein the metadata associated with each host write command comprises a zone write pointer update, and wherein the first condition is met when a number of open zones reaches a threshold.

6. The data storage device as recited in claim 5 , wherein the primary NVM comprises a metadata region, and wherein, prior to receiving the host write command, the control circuitry is further configured to create one or more tables in the volatile memory for zone write pointers.

7. The data storage device as recited in claim 1 , wherein the first condition is based on a rate of metadata generated relative to a throughput of the first secondary NVM.

8. The data storage device as recited in claim 1 , wherein the first condition is met when the control circuitry detects an unexpected power loss to the data storage device.

9. The data storage device as recited in claim 1 , wherein the second condition is met when one or more of the following occurs:
a first amount of metadata has accumulated in the first secondary NVM,
the first secondary NVM is substantially full, or
when the host enters an idle state or when the data storage device enters a state in which no metadata is created.

10. The data storage device as recited in claim 1 , wherein the control circuitry is further configured to erase metadata in the first secondary NVM after metadata has been written to the first secondary NVM according to a predetermined block ratio of metadata erased to metadata written.

11. The data storage device as recited in claim 1 , wherein the primary NVM comprises a metadata region, and wherein, when the data storage device is powered up, the control circuitry is further configured to:
read metadata in the metadata region of the primary NVM and metadata in the first secondary NVM;
merge the metadata from the metadata region of the primary NVM and the metadata in the first secondary NVM to form updated metadata; and
write the updated metadata to the metadata region of the primary NVM.

12. The data storage device as recited in claim 11 , wherein the updated metadata in the first secondary NVM is erased after the updated metadata has been written to the metadata region of the primary NVM.

13. The data storage device as recited in claim 1 , further comprising a second secondary NVM, wherein the control circuitry is further configured to alternately write metadata that has accumulated in the volatile memory to the first and second secondary NVMs each time the first condition is met, and wherein each of the first and the second secondary NVM comprises an independently operable memory device or a memory bank.

14. The data storage device as recited in claim 13 , wherein the control circuitry is further configured to erase metadata in the first secondary NVM when writing metadata to the second secondary NVM, and vice versa.

15. The data storage device as recited in claim 1 , further comprising a second secondary NVM, wherein, each time the first condition is met, the control circuitry is further configured to write metadata that has accumulated in the volatile memory to the first secondary NVM until it is substantially full, and then write metadata that has accumulated in the volatile memory to the second secondary NVM, and wherein each of the first and the second secondary NVM comprises a discrete memory device or a memory bank.

16. The data storage device as recited in claim 1 , wherein the first condition is met when the amount of metadata in the volatile memory reaches a power safe limit of the volatile memory.

17. A method to manage metadata associated with user data in a data storage device comprising volatile memory, a first secondary non-volatile memory (NVM), and a primary NVM, the method comprising:
(a) writing metadata and user data associated with a host write command to the volatile memory;
(b) writing the user data to the primary NVM, wherein the primary NVM is a disk comprising a plurality of data tracks;
(c) continue writing metadata associated with each of one or more host write commands to the volatile memory, and when a first condition is met, writing metadata that has accumulated in the volatile memory to the first secondary NVM; and
(d) repeating (c), and when a second condition is met, then writing at least a portion of metadata that has accumulated in the first secondary NVM or the volatile memory to the primary NVM;
wherein writing user data to primary NVM comprises writing user data associated with each host write command to at least one of the data tracks, and wherein the first condition is met when user data has been written to a first number of data tracks.

18. The method as recited in claim 17 , wherein the primary NVM comprises a plurality of zones, and wherein the metadata associated with each host write command comprises a zone write pointer update, and wherein the first condition is met when a number of open zones reaches a threshold.

19. The method as recited in claim 18 , wherein the primary NVM comprises a metadata region, and wherein, prior to receiving the host write command, further comprising creating one or more tables in the volatile memory for zone write pointers.

20. The method as recited in claim 17 , wherein the first condition is based on a rate of metadata generated relative to a throughput of the first secondary NVM.

21. The method as recited in claim 17 , wherein the first condition is met when an unexpected power loss to the data storage device is detected.

22. The method as recited in claim 17 , wherein the second con

Assignees

• Western Digital Tech Inc

Inventors

• Vasquez Steven R
• Malina James N

Classifications

• G06F2212/1016

  Performance improvement · CPC title

• G06F11/1441

  Resetting or repowering · CPC title

• G06F2212/1032

  Reliability improvement, data loss prevention, degraded operation etc · CPC title

• G06F3/0613

  in relation to throughput · CPC title

• G06F3/0656 Primary

  Data buffering arrangements · CPC title