Data storage device and method of operating the same
US-2017277432-A1 · Sep 28, 2017 · US
US10248330B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10248330-B2 |
| Application number | US-201715608203-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 30, 2017 |
| Priority date | May 30, 2017 |
| Publication date | Apr 2, 2019 |
| Grant date | Apr 2, 2019 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A data storage device with one or more buffers can employ buffer tenure management with at least a data storage device having a first buffer, a second buffer, a buffer manager, and a non-volatile memory. The first buffer can be located on-chip while the second buffer is located off-chip. The first buffer may be filled with data having a tenure of less than a predetermined tenure threshold as directed by the buffer manager.
Opening claim text (preview).
What is claimed is: 1. An apparatus comprising a data storage device having a first buffer, a second buffer, a buffer manager, and a non-volatile memory, the first buffer and a local controller each constructed of a silicon material of a single wafer chip, the second buffer positioned external to and interconnected to the single wafer chip, the first buffer filled with data having a predicted tenure of less than a predetermined tenure threshold as directed by the buffer manager, the predicted tenure generated by a prediction module of the buffer manager, the predicted tenure corresponding with an amount of time data associated with a write request is forecasted to remain in the first buffer, the tenure threshold is generated based on an algorithm, current data storage device activity, data storage device past performance, and pending write request volume. 2. The apparatus of claim 1 , wherein the first buffer is static random access memory. 3. The apparatus of claim 1 , wherein the second buffer is dynamic random access memory. 4. The apparatus of claim 1 , wherein the non-volatile memory is NAND flash. 5. The apparatus of claim 1 , wherein the second buffer is positioned within a housing of the data storage device. 6. A method comprising: activating a data storage device, the data storage device having a first buffer, a second buffer, a buffer manager, and a non-volatile memory; generating a tenure threshold with the buffer manager, the tenure threshold is generated based on an algorithm, current data storage device activity, data storage device past performance, and pending write request volume; evicting a first data sector from the first buffer with the buffer manager in response to the first data sector exceeding the tenure threshold; and storing a second data sector in the first buffer as directed by the buffer manager to fill the first buffer with data having a tenure of less than the tenure threshold. 7. The method of claim 6 , wherein the tenure threshold matches a latency speed of the second buffer. 8. The method of claim 6 , wherein the buffer manager evicts the first data sector to the second buffer. 9. The method of claim 6 , wherein the second data sector subsequently is written to the non-volatile memory. 10. The method of claim 6 , wherein the buffer manager stores readback data from the non-volatile memory in the second buffer without the readback data being stored in the first buffer. 11. The method of claim 6 , wherein the buffer manager reacts to a dynamic event by re-routing the second data sector from the first buffer to the second buffer. 12. The method of claim 11 , wherein the dynamic event is a data error corresponding with a reduction in data storage device performance. 13. The method of claim 11 , wherein the dynamic event is an addressing conflict corresponding with a reduction in data storage device performance. 14. A method comprising: activating a data storage device, the data storage device having a first buffer, a second buffer, a buffer manager, and a non-volatile memory; generating a tenure threshold with the buffer manager; predicting a tenure of a first data sector with a prediction module of the buffer manager, the predicted tenure generated based on an algorithm, current data storage device activity, data storage device past performance, and pending write request volume to correspond with an amount of time data associated with a write request is forecasted to remain in the first buffer; storing the first data sector in the second buffer in response to the predicted tenure being greater than the tenure threshold; predicting a tenure of a second data sector with the buffer manager; evicting a third data sector from the first buffer with the buffer manager in response to the third data sector exceeding the tenure threshold; and storing the second data sector in the first buffer as directed by the buffer manager to fill the first buffer with data having a tenure of less than the tenure threshold. 15. The method of claim 14 , wherein the buffer manager sets a custom timer in response to a prediction module evaluating the second data sector. 16. The method of claim 15 , wherein the custom timer is different than the tenure threshold. 17. The method of claim 14 , wherein the buffer manager alters the second data sector in response to the predicted tenure of the second data sector. 18. The method of claim 17 , wherein the buffer manager splits the second data sector into first and second sub-sectors, the first sub-sector stored in the first buffer, the second sub-sector stored in the second buffer. 19. The method of claim 14 , wherein the buffer manager predicts at least one data storage device performance metric during each predicting step.
with dedicated cache, e.g. instruction or stack · CPC title
Improving I/O performance · CPC title
Single storage device · CPC title
Data buffering arrangements · CPC title
Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP] · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.