Refresh operations using write/read commands
View Patent ↗Systems and methods for performing refresh operations using write/read commands are provided. In one embodiment, a disk drive comprises a disk partitioned into a plurality of refresh zones, a head configured to write data to and read data from the disk, and a controller. The controller is configured to receive an access command, to read data from at least one of the refresh zones using the head in response to the access command, to check a condition of the read data, and to determine whether to refresh the at least one refresh zone based on the condition of the read data, wherein the read data includes data from a portion of the at least one refresh zone not being accessed by the access command.
1. A disk drive, comprising:
a disk partitioned into a plurality of refresh zones;
a head configured to write data to and read data from the disk; and
a controller configured to receive an access command, to read data from a portion of at least one of the refresh zones using the head in response to the access command, to check a condition of the read data, and to determine whether to refresh the at least one refresh zone based on the condition of the read data, wherein the read data includes data from a portion of the at least one refresh zone not being accessed by the access command.
2. The disk drive of claim 1 , wherein the at least one refresh zone includes a track of the disk, and the access command accesses only a portion of the track.
3. The disk drive of claim 2 , wherein the at least one refresh zone corresponds to a single track of the disk.
4. The disk drive of claim 1 , wherein the access command is initiated by a host device.
5. The disk drive of claim 1 , wherein the access command comprises a read command.
6. The disk drive of claim 1 , wherein, when the controller determines not to refresh the at least one refresh zone, the controller is configured to reduce or clear a count value of a refresh counter associated with the at least one refresh zone.
7. The disk drive of claim 6 , wherein the controller is configured to increase the count value of the refresh counter when data is written to the at least one refresh zone or data is written to another one of the refresh zones.
8. The disk drive of claim 7 , wherein the controller is configured to check the condition of data in the at least one refresh zone when the count value of the refresh counter exceeds a first threshold.
9. The disk drive of claim 8 , wherein the controller is configured to refresh the at least one refresh zone when the count value of the refresh exceeds a second threshold, the second threshold being higher than the first threshold.
10. The disk drive of claim 6 , wherein the controller is configured to determine a quality of the read data, and to reduce the count value of the refresh counter by an amount based on the quality of the read data.
11. The disk drive of claim 1 , wherein the controller is configured to check the condition of the read data by performing an error correction code (ECC) scan of the read data, and to determine whether to refresh the at least one refresh zone based on one or more error counts obtained from the ECC scan, each error count corresponding to a sector in the at least one refresh zone.
12. The disk drive of claim 1 , wherein the controller is configured to check the condition of the read data by applying a low-density parity-check (LDPC) algorithm to the read data and determining a number of iterations performed by the LDPC algorithm to obtain correct data from the read data, and to determine whether to refresh the at least one refresh zone based on the number of iterations.
13. The disk drive of claim 1 , wherein the controller is configured to schedule the refresh of the at least one refresh zone based on a rotational position optimization (RPO) algorithm.
14. A method of refreshing in a disk drive including a disk partitioned into a plurality of refresh zones, comprising:
receiving an access command;
reading a portion of at least one of the refresh zones in response to the access command;
checking a condition of the read data; and
determining whether to refresh the at least one refresh zone based on the condition of the read data, wherein the read data includes data from a portion of the at least one refresh zone not being accessed by the access command.
15. The method of claim 14 , wherein the at least one refresh zone includes a track of the disk, and the access command accesses only a portion of the track.
16. The method of claim 14 , wherein the access command is initiated by a host device.
17. The method of claim 14 , wherein the access command comprises a read command.
18. The method of claim 14 , further comprising clearing or reducing a count value of a refresh counter associated with the at least one refresh zone when a determination is made not to refresh the at least one refresh zone.
19. The method of claim 18 , further comprising increasing the count value of the at least one refresh zone when data is written to the at least one refresh zone or data is written to another one of the refresh zones.
20. The method of claim 18 , further comprising determining a quality of the read data, and wherein the reducing the count value of the refresh counter comprises reducing the count value by an amount based on the quality of the read data.
21. The method of claim 14 , wherein the checking the condition of the read data comprises performing an error correction code (ECC) scan of the read data, and the determining whether to refresh the at least one refresh zone is based on one or more error counts obtained from the ECC scan, each error count corresponding to a sector in the at least one refresh zone.
22. The method of claim 14 , wherein the checking the condition of the read data comprises applying a low-density parity-check (LDPC) algorithm to the read data, and determining a number of iterations performed by the LDPC algorithm to obtain correct data from the read data, and the determining whether to refresh the at least one refresh zone is based on the number of iterations.
23. The method of claim 14 , further comprising scheduling the refresh of the at least one refresh zone based on a rotational position optimization (RPO) algorithm.