Methods, devices and systems for tracking and relocating intermittently defective disk sectors to prevent indefinite recycling thereof
View Patent ↗A data storage device may comprise storage media comprising a plurality of sectors, and a controller configured to selectively read and write data thereto. The controller may be further configured to tag a sector as a bad sector to be relocated after a first failed read and to untag the tagged sector after a successful write attempt after the first failed read. After a second failed read from the sector subsequent to the successful write, the controller may tag the untagged sector as a bad sector to be relocated and adjust a recurring bad sector counter for that sector. On a subsequent write request, based at least in part on the bad sector counter and a threshold, the controller may determine whether to relocate data stored at a physical location on the data storage device corresponding to the sector to a spare location on the data storage device.
1. A data storage device, comprising:
storage media comprising a plurality of sectors configured to store data; and
a controller configured to selectively read and write data to the plurality of sectors, the controller being further configured to:
tag a sector of the plurality of sectors as a bad sector to be relocated after a first failed read;
untag the tagged sector after a successful write attempt to the sector after the first failed read, a successful write attempt being a write attempt, carried out after a prior failed read, in which data written to the tagged sector is successfully verified;
after a second failed read from the sector subsequent to the successful write:
tag the untagged sector as a bad sector to be relocated;
adjust a recurring bad sector counter for the sector; and
on a subsequent write request, consult a log detailing previous tagging and untagging of the plurality of sectors, and based at least in part on the consulted log, the bad sector counter and a threshold, determine whether to relocate data stored at a physical location on the data storage device corresponding to the sector to a spare location on the data storage device.
2. The data storage device of claim 1 , wherein the controller is further configured to relocate data stored at a physical location on the data storage device corresponding to the sector to a spare location on the data storage device when the bad sector counter reaches the threshold.
3. The data storage device of claim 1 , wherein the controller is further configured to disallow further reads or writes to the physical location on the data storage device corresponding to the sector.
4. The data storage device of claim 1 , wherein the controller is further configured to tag the sector as a Transparent Auto-Relocation Entry (TARE).
5. The data storage device of claim 1 , further comprising, after the second failed read, returning a message to a host coupled to the data storage device.
6. The data storage device of claim 5 , wherein the message comprises an indication that an uncorrectable read error has occurred.
7. The data storage device of claim 1 , wherein the threshold is at least two.
8. The data storage device of claim 1 , wherein the storage media comprises a rotating media storage device.
9. A method of reading a sector of a storage device, comprising:
attempting to read the sector upon receipt of a read command from a host;
if the attempted read is unsuccessful:
tagging the sector as a bad sector to be relocated and correspondingly recording the tagging of the sector in a log detailing previous tagging and untagging of sectors of the storage device;
if the sector was logged in the log as having been previously untagged as a bad sector to be relocated after a successful write in which data written to a previously tagged sector is successfully verified, adjusting a recurring bad sector counter for the sector, and
returning a message to the host.
10. The method of claim 9 , wherein tagging comprises tagging the sector as a Transparent Auto-Relocation Entry (TARE).
11. The method of claim 9 , further comprising untagging the sector upon successfully writing to the tagged sector and correspondingly updating the log with the untagging of the sector.
12. The method of claim 9 , wherein the message returned to the host comprises an indication that an uncorrectable read error has occurred.
13. The method of claim 9 , further comprising relocating data stored at the sector after the recurring bad sector counter has reached a predetermined threshold.
14. The method of claim 13 , wherein the predetermined threshold is at least two.
15. The method of claim 9 , wherein the sector is associated with a Logical Block Address (LBA).
16. A method of writing to a sector of a data storage device, comprising:
determining whether the sector is tagged as a bad sector to be relocated:
if the sector is not tagged as a bad sector to be relocated, writing to the sector;
if the sector is tagged as a bad sector to be relocated:
attempting to write to the tagged sector and,
if the write to the tagged sector was successful such that data written to the tagged sector is successfully verified, untagging the sector and logging the untagging of the sector in a log detailing previous tagging and untaggings of sectors of the data storage device; and
if the write to the tagged sector was unsuccessful, relocating data stored at a physical location on the data storage device corresponding to the sector to a spare location on the data storage device.
17. The method of claim 16 , wherein the tagged sector is associated with a Transparent Auto-Relocation Entry (TARE).
18. The method of claim 16 , wherein the sector is associated with a Logical Block Address (LBA).
19. A method of operating a data storage device, comprising:
tagging a sector as a bad sector to be relocated after a first failed;
untagging the tagged sector after a successful write attempt to the sector after the first failed read, a successful write attempt being a write attempt, carried out after a prior failed read, in which data written to the tagged sector is successfully verified;
after a second failed read from the sector subsequent to the successful write attempt, as determined after consulting a log detailing previous tagging and untagging of sectors of the data storage device:
tagging the untagged sector as a bad sector to be relocated;
adjusting a recurring bad sector counter for the sector; and
relocating data stored at the sector to a spare location on the data storage device after the recurring bad sector counter has reached a predetermined threshold.
20. The method of claim 19 , wherein relocating comprises disallowing further reads or writes to a physical location on the data storage device corresponding to the sector.
21. The method of claim 19 , wherein tagging comprises tagging the sector as a Transparent Auto-Relocation Entry (TARE).
22. The method of claim 19 , further comprising, after the second failed read, returning a message to a host coupled to the storage device.
23. The method of claim 22 , wherein the message comprises an indication that an uncorrectable read error has occurred.
24. The method of claim 19 , wherein the threshold is at least two.