NAND data placement schema
Disclosed in some examples are improvements to data placement architectures in NAND that provide additional data protection through an improved NAND data placement schema that allows for recovery from certain failure scenarios. The present disclosure stripes data diagonally across page lines and planes to enhance the data protection. Parity bits are stored in SLC blocks for extra protection until the block is finished writing and then the parity bits may be deleted.
1. A memory controller device comprising:
a hardware processor configured to perform operations comprising:
receiving a data item from a host over a host interface;
programming a first portion of the received data item into an array of NAND memory cells organized into multiple planes and multiple pages at a first page of the multiple pages and at a first plane of the multiple planes;
programming a second portion of the received data item into the array at a second page of the multiple pages and at a second plane of the multiple planes, the second page being assigned a page line number greater than a page line number of the first page;
programming a third portion of the received data item into the array at a third page of the multiple pages and at a third plane of the multiple planes, the third page being assigned a page line number greater than the page line number of the second page; and
programming a fourth portion of the received data item into the array at a fourth page of the multiple pages and at a fourth plane of the multiple planes, the fourth page being assigned a page line number greater than the page line number assigned to the third page; and
wherein each data portion of the received data item is programmed on a different page line than every other data portion.
2. The memory controller device of claim 1 , wherein the first portion, second portion, third portion, and fourth portion each comprise one of a lower page, an upper page, an extra page, or a copy of one of the lower page, upper page, or extra page.
3. The memory controller device of claim 1 , wherein the hardware processor is further configured to calculate a parity value for the received data item based on the first portion, the second portion, and the third portion.
4. The memory controller device of claim 3 , wherein the hardware processor is further configured to store the parity value in a separate block of single-level cell (SLC) NAND memory cells.
5. The memory controller device of claim 1 , wherein the hardware processor is further configured to: assign a parity value calculated for the received data item to a first position of a parity cluster, the parity cluster comprising parity values for multiple received data items; and calculate a compressed parity value by performing an XOR operation on parity values occupying the first position in the parity cluster.
6. The memory controller device of claim 5 , wherein the hardware processor is further configured to recover a corrupted portion of the received data item by performing an XOR operation on the compressed parity value and non-corrupted portions of the received data item.
7. The memory controller device of claim 1 , wherein the hardware processor is further configured to shift an assignment of which data portion corresponds to a lower page, an upper page, and an extra page for each grouping of multiple received data items.
8. A method comprising:
receiving a data item from a host over a host interface; programming a first portion of the received data item into an array of NAND memory cells organized into multiple planes and multiple pages at a first page of the multiple pages and at a first plane of the multiple planes;
programming a second portion of the received data item into the array at a second page of the multiple pages and at a second plane of the multiple planes, the second page being assigned a page line number greater than a page line number of the first page;
programming a third portion of the received data item into the array at a third page of the multiple pages and at a third plane of the multiple planes, the third page being assigned a page line number greater than the page line number of the second page; and
programming a fourth portion of the received data item into the array at a fourth page of the multiple pages and at a fourth plane of the multiple planes, the fourth page being assigned a page line number greater than the page line number assigned to the third page; and
wherein each data portion of the received data item is programmed on a different page line than every other data portion.
9. The method of claim 8 , wherein the first portion, second portion, third portion, and fourth portion each comprise one of a lower page, an upper page, an extra page, or a copy of one of the lower page, upper page, or extra page.
10. The method of claim 8 , further comprising calculating a parity value for the received data item based on the first portion, the second portion, and the third portion.
11. The method of claim 10 , further comprising storing the parity value in a separate block of single-level cell (SLC) NAND memory cells.
12. The method of claim 8 , further comprising: assigning a parity value calculated for the received data item to a first position of a parity cluster, the parity cluster comprising parity values for multiple received data items; and calculating a compressed parity value by performing an XOR operation on parity values occupying the first position in the parity cluster.
13. The method of claim 12 , further comprising recovering a corrupted portion of the received data item by performing an XOR operation on the compressed parity value and non-corrupted portions of the received data item.
14. The method of claim 8 , further comprising shifting an assignment of which data portion corresponds to a lower page, an upper page, and an extra page for each grouping of multiple received data items.
15. A machine-readable medium, storing instructions, which when executed by a machine, cause the machine to perform operations comprising:
receiving a data item from a host over a host interface; programming a first portion of the received data item into an array of NAND memory cells organized into multiple planes and multiple pages at a first page of the multiple pages and at a first plane of the multiple planes;
programming a second portion of the received data item into the array at a second page of the multiple pages and at a second plane of the multiple planes, the second page being assigned a page line number greater than a page line number of the first page;
programming a third portion of the received data item into the array at a third page of the multiple pages and at a third plane of the multiple planes, the third page being assigned a page line number greater than the page line number of the second page; and
programming a fourth portion of the received data item into the array at a fourth page of the multiple pages and at a fourth plane of the multiple planes, the fourth page being assigned a page line number greater than the page line number assigned to the third page; and wherein each data portion of the received data item is programmed on a different page line than every other data portion.
16. The machine-readable medium of claim 15 , wherein the first portion, second portion, third portion, and fourth portion each comprise one of a lower page, an upper page, an extra page, or a copy of one of the lower page, upper page, or extra page.
17. The machine-readable medium of claim 15 , wherein the operations further comprise calculating a parity value for the received data item based on the first portion, the second portion, and the third portion.
18. The machine-readable medium of claim 17 , wherein the operations further comprise storing the parity value in a separate block of single-level cell (SLC) NAND memory cells.
19. The machine-readable medium of claim 15 , wherein the operations further comprise: assigning a parity value calculated for the received data item to a first position of a parity cluster, the parity cluster comprising parity values for multiple received data items; and calculating a compressed parity value by performing an XOR operation on parity values occupying the first position in the parity cluster.
20. The machine-readable medium of claim 19 , wherein the operations further comprise recovering a corrupted portion of the received data item by performing an XOR operation on the compressed parity value and non-corrupted portions of the received data item.