Systems and methods for multi-zone data tiering for endurance extension in solid state drives
Systems and methods for increasing the endurance of a solid state drive are disclosed. The disclosed systems and methods can assign different levels of error protection to a plurality of blocks of the solid state drive. The disclosed methods can provide a plurality of error correction mechanisms, each having a plurality of corresponding error correction levels and associate a first plurality of blocks of the solid state drive with a first zone and a second plurality of blocks of the solid state drive with a second zone. The disclosed methods can assign a first error correction mechanism and a first corresponding error correction level to the first zone and can assign a second error correction mechanism and a second corresponding error correction level to the second zone.
1. A storage device, comprising:
one or more memories; and
one or more controllers configured to cause:
allocating first blocks of the one or more memories to a first zone and second blocks of the one or more memories to a second zone;
assigning a first error correction mechanism to the first zone and a second error correction mechanism to the second zone;
directing first write requests to the one or more memories into the first zone and second write requests into the second zone, wherein the first write requests are for data that is overwritten more frequently than data for the second write requests;
re-directing at least one write request from the first write requests into the second zone; and
filtering out write requests with random traffic patterns from the second zone.
2. The storage device of claim 1 , wherein the one or more controllers are configured to cause:
allocating third blocks of the one or more memories to a third zone;
assigning the second error correction mechanism to the third zone;
receiving third write requests, wherein the third write requests are for data that is overwritten more frequently than data for the second write requests;
changing an error correction mechanism of the third zone by assigning the first error correction mechanism to the third zone; and
directing the third write requests into the third zone.
3. The storage device of claim 1 , wherein the one or more controllers are configured to cause re-allocating a block from the first blocks from the first zone to the second zone, when the block has an error count higher than a threshold error count.
4. The storage device of claim 1 , wherein the one or more controllers are configured to cause re-allocating a block from the second blocks from the second zone to the first zone, when the block has an error count lower than a threshold error count.
5. The storage device of claim 1 , wherein the one or more controllers are configured to cause:
assigning, to the first zone, a first error correction level associated with the first error correction mechanism; and
assigning to the second zone a second error correction level associated with the second error correction mechanism.
6. The storage device of claim 5 , wherein the one or more controllers are configured to cause:
re-assigning, to the first zone, the first error correction mechanism and a third error correction level,
wherein the first error correction mechanism and the third error correction level provide higher error correction than the first error correction mechanism and the first error correction level.
7. The storage device of claim 5 , wherein the one or more controllers are configured to cause:
re-assigning, to the first zone, a third error correction mechanism and the first error correction level,
wherein the third error correction mechanism and the first error correction level provide higher error correction than the first error correction mechanism and the first error correction level.
8. The storage device of claim 1 ,
wherein write requests of the first write requests are to generate higher write amplification than write requests of the second write requests.
9. The storage device of claim 1 , wherein the one or more memories are a multi-level cell flash device, and wherein the one or more controllers are configured to cause:
dividing the multi-level cell flash device into at least one region; and
assigning the first zone into the at least one region that is in a single-level cell mode.
10. The storage device of claim 1 ,
wherein the first zone is configured to support a larger number of program/erase cycles compared to the second zone by limiting programming to lower pages in the first zone.
11. A method, comprising:
allocating first blocks of one or more memories to a first zone and second blocks of the one or more memories to a second zone;
assigning a first error correction mechanism to the first zone and a second error correction mechanism to the second zone;
directing first write requests to the one or more memories into the first zone and second write requests into the second zone, wherein the first write requests are for data that is overwritten more frequently than data for the second write requests; and
re-directing at least one write request from the first write requests into the second zone;
filtering out write requests with random traffic patterns from the second zone.
12. The method of claim 11 , comprising:
allocating third blocks of the one or more memories to a third zone;
assigning the second error correction mechanism to the third zone;
receiving third write requests, wherein the third write requests are for data that is overwritten more frequently than data for the second write requests;
changing an error correction mechanism of the third zone by assigning the first error correction mechanism to the third zone; and
directing the third write requests into the third zone.
13. The method of claim 11 , comprising: re-allocating a block from the first blocks from the first zone to the second zone, when the block has an error count higher than a threshold error count.
14. The method of claim 11 , comprising:
assigning, to the first zone, a first error correction level associated with the first error correction mechanism; and
assigning, to the second zone, a second error correction level associated with the second error correction mechanism.
15. The method of claim 14 , comprising:
re-assigning, to the first zone, the first error correction mechanism and a third error correction level,
wherein the first error correction mechanism and the third error correction level provide higher error correction than the first error correction mechanism and the first error correction level.
16. The method of claim 14 , comprising:
re-assigning, to the first zone, a third error correction mechanism and the first error correction level,
wherein the third error correction mechanism and the first error correction level provide higher error correction than the first error correction mechanism and the first error correction level.
17. An apparatus, comprising:
means for allocating first blocks of one or more memories to a first zone and second blocks of the one or more memories to a second zone;
means for assigning a first error correction mechanism to the first zone and a second error correction mechanism to the second zone;
means for directing first write requests to the one or more memories into the first zone and second write requests into the second zone, wherein the first write requests are for data that is overwritten more frequently than data for the second write requests;
means for re-directing at least one write request from the first write requests into the second zone; and
means for filtering out write requests with random traffic patterns from the second zone.
18. The apparatus of claim 17 , comprising:
means for allocating third blocks of the one or more memories to a third zone;
means for assigning the second error correction mechanism to the third zone;
means for receiving third write requests, wherein the third write requests are for data that is overwritten more frequently than data for the second write requests;
means for changing an error correction mechanism of the third zone by assigning the first error correction mechanism to the third zone; and
means for directing the third write requests into the third zone.