Read policy for system data of solid state drives
An apparatus includes a plurality of memory dies and a controller. The controller may be communicatively coupled to the plurality of memory dies and configured to utilize multiple copies of a root record containing system data during a boot-up process. The multiple copies of the root record are stored using at least two of the plurality of memory dies.
1. An apparatus comprising:
a plurality of memory dies; and
a controller communicatively coupled to the plurality of memory dies and configured to utilize multiple copies of a root record containing system data during a boot-up process, wherein the multiple copies of the root record are stored using at least two of the plurality of memory dies, during the boot-up process, the controller is enabled to decode root record data stored in a particular location in a particular memory die of the plurality of memory dies and if decoding the root record data fails, the controller is enabled to decode a copy of the root record data stored in a different location in the particular memory die or in a particular location in at least one other memory die of the plurality of memory dies.
2. The apparatus according to claim 1 , wherein the controller is configured to utilize three or more copies of the root record stored using two of the plurality of memory dies.
3. The apparatus according to claim 1 , wherein the controller is configured to utilize three or more copies of the root record stored using three of the plurality of memory dies.
4. The apparatus according to claim 1 , wherein the controller is configured to randomly select between the multiple copies of the root record for each boot-up.
5. The apparatus according to claim 4 , wherein the controller is configured to make a non-uniform random selection between the multiple copies of the root record for each boot-up.
6. The apparatus according to claim 5 , wherein the controller is configured to rotate the non-uniform random selection between the multiple copies of the root record.
7. The apparatus according to claim 6 , wherein the controller is configured to rotate the non-uniform random selection among all copies whenever a root record is re-written.
8. The apparatus according to claim 1 , wherein the controller is configured to maintain multiple copies of the root record using a pool of dedicated blocks in one of the plurality of dies.
9. The apparatus according to claim 8 , wherein the pool of dedicated blocks is defined by a number of predetermined address bits.
10. The apparatus according to claim 1 , wherein the controller is configured to minimize read disturb of the root record.
11. The apparatus according to claim 10 , wherein the controller is configured to collect and save statistics on the root record during boot-up to minimize read disturb of the root record.
12. The apparatus according to claim 1 , wherein the controller utilizes multiple copies of system data to mitigate an error floor of a hard-decision low density parity check code.
13. The apparatus according to claim 1 , wherein:
during the boot-up process, the controller is enabled to perform a hard-decision decoding of the root record data.
14. The apparatus according to claim 1 , wherein the controller comprises a read only memory (ROM) containing firmware for the boot-up process.
15. The apparatus according to claim 13 , wherein the controller is configured to enable soft-decision decoding after the root record data is successfully read.
16. The apparatus according to claim 1 , wherein the root record data comprises firmware specific to a type of the plurality of memory dies.
17. A method for implementing a system data read policy in a storage device comprising:
configuring a plurality of memory dies and a controller as a solid-state drive or disk (SSD);
storing multiple copies of a root record containing system data using at least two of the plurality of memory dies; and
configuring the controller to utilize the multiple copies of the root record during a boot-up process of the SSD, wherein, during the boot-up process, the controller is enabled to decode root record data stored in a particular location in a particular memory die of the plurality of memory dies and if decoding the root record data fails, the controller is enabled to decode a copy of the root record data stored in a different location in the particular memory die or in a particular location in at least one other memory die of the plurality of memory dies.
18. A storage controller comprising:
an interface circuit configured to communicatively couple the storage controller to a plurality of memory dies; and
a processor communicatively coupled to the interface circuit and configured to utilize multiple copies of a root record containing system data during a boot-up process, wherein the multiple copies of the root record are stored using at least two of the plurality of memory dies, during the boot-up process, the controller is enabled to decode root record data stored in a particular location in a particular memory die of the plurality of memory dies and if decoding the root record data fails, the controller is enabled to decode a copy of the root record data stored in a different location in the particular memory die or in a particular location in at least one other memory die of the plurality of memory dies.
19. The storage controller according to claim 18 , wherein the multiple copies of the root record are stored in a block 0 of each of the at least two of the plurality of memory dies and at least one of a pool of predetermined non-zero blocks in at least one of the plurality of memory dies.
20. The storage controller according to claim 18 , wherein during the boot-up process, the controller is enabled to perform a hard-decision decoding of the root record data.