Varying data redundancy in storage systems
View Patent ↗A disk drive is disclosed that varies its data redundancy policy for caching data in non-volatile solid-state memory as the memory degrades. As the non-volatile memory degrades, the redundancy of data stored in the non-volatile memory can be increased to counteract the effects of such degradation. Redundant data can be used to recover data stored in the non-volatile memory in case of a data corruption. Performance improvements and reduced costs of disk drives can thereby be attained.
1. In a storage system comprising non-volatile memory, a method of caching data in the non-volatile memory, the method comprising:
configuring a write operation of data to the non-volatile memory, the configuring comprising:
determining a reliability measurement of the non-volatile memory;
comparing the reliability measurement with first and second thresholds, the first threshold indicating higher reliability of the non-volatile memory than the second threshold;
if the reliability measurement falls below the first threshold but does not fall below the second threshold, determining a parity level and setting a redundancy level to the parity level;
if the reliability measurement falls below the second threshold, determining a mirroring level and setting the redundancy level to the mirroring level;
writing data to the non-volatile memory using the set redundancy level; and
increasing at least one of the parity and mirroring level when the reliability measurement has been determined to decrease.
2. The method of claim 1 , wherein when the redundancy level is set to the mirroring level, writing data to the non-volatile memory further comprises writing a number of copies of data corresponding to the mirroring level.
3. The method of claim 1 , wherein when the redundancy level is set to the parity level, writing data to the non-volatile memory further comprises:
creating a plurality of parity data units corresponding to data, wherein a number of parity data units in the plurality corresponds to the parity level; and
writing data along with the plurality of parity data units to the non-volatile memory.
4. The method of claim 1 , wherein the reliability measurement corresponds at least in part to a remaining usable life of the non-volatile memory.
5. The method of claim 4 , wherein the remaining usable life corresponds at least in part to one of: a number of remaining program-erase cycles of the non-volatile memory and a number of read errors of the non-volatile memory.
6. The method of claim 4 , wherein:
the non-volatile memory comprises multi-level cell solid-state memory; and
the remaining usable life corresponds at least in part to an adjustment of a voltage threshold of the multi-level cell memory.
7. The method of claim 1 , wherein non-volatile memory comprises solid-state memory.
8. The method of claim 1 , wherein the writing further comprises:
determining whether a write operation has been initiated;
if the write operation has not been initiated, writing data to the non-volatile memory using the set redundancy level; and
if the write operation has been initiated, writing data to the non-volatile memory using a previous redundancy level.
9. The method of claim 1 , wherein writing data to the non-volatile memory comprises:
if a new data storage unit has been allocated for writing data to the non-volatile memory, writing data to the non-volatile memory using the new data storage unit, the new data storage unit formatted according to the set redundancy level; and
if the new data storage unit has not been allocated for writing data to the non-volatile memory, writing data to the non-volatile memory using a previously allocated data storage unit, the previously allocated data storage unit formatted according a previous redundancy level.
10. A storage system for storing data received from a host system, the system comprising:
a non-volatile solid state memory configured to store data received from the host system; and
a controller configured to:
determine a reliability measurement of the non-volatile memory;
adjust a redundancy level used for writing data to the non-volatile memory based at least partly on the reliability measurement, wherein the redundancy level is increased when the reliability measurement has been determined to decrease; and
write data to the non-volatile memory using the adjusted redundancy level.
11. The system of claim 10 , wherein the controller is configured to write data to the non-volatile memory by:
if a new data storage unit has been allocated for writing data to the non-volatile memory, writing data to the non-volatile memory using the new data storage unit, the new data storage unit formatted according to the set redundancy level; and
if the new data storage unit has not been allocated for writing data to the non-volatile memory, writing data to the non-volatile memory using a previously allocated data storage unit, the previously allocated data storage unit formatted according a previous redundancy level.
12. The system of claim 10 , wherein the controller is further configured to increase the redundancy level of data to be written to the non-volatile memory when the determined reliability measurement indicates a degradation of reliability.
13. The system of claim 10 , wherein the reliability measurement corresponds to at least one of: a number of remaining program-erase cycles of the non-volatile memory and a number of read errors of the non-volatile memory.
14. The system of claim 10 , wherein the reliability measurement corresponds to an adjustment of programming algorithm parameters.
15. The system of claim 10 , wherein the controller is further configured to:
compare the reliability measurement to a parity threshold; and
if the reliability measurement falls below the parity threshold, determine a parity level based at least in part on the reliability measurement and set the redundancy level to the determined parity level.
16. The system of claim 15 , wherein the controller is further configured to:
compare the reliability measurement to a mirroring threshold, wherein the parity threshold indicates higher reliability of the non-volatile solid state memory than the mirroring threshold; and
if the reliability measurement falls below the mirroring threshold, determine a mirroring level based at least in part on the reliability measurement and set the redundancy level to the determined mirroring level.
17. The system of claim 16 , wherein:
when the redundancy level is set to the mirroring level, the controller is further configured to write a number of copies of data to the non-volatile memory, the number of copies corresponding to the mirroring level; and
when the redundancy level is set to the parity level, the controller is further configured to:
create a plurality of parity data units corresponding to data, wherein the number of parity data units in the plurality of parity data units corresponds to the parity level; and
write data along with the plurality of parity data units to the non-volatile memory.
18. The system of claim 10 , further comprising a magnetic medium configured to store data received from the host, wherein the controller is further configured to write data to the magnetic medium when the reliability measurement falls below a minimum reliability threshold.
19. The system of claim 10 , wherein the controller is further configured to determine the reliability measurement by receiving reliability information from a signal processing subsystem.
20. The system of claim 19 , wherein the signal processing subsystem is part of a bridge device coupled to the non-volatile memory.
21. The system of claim 10 , wherein the controller is further configured to:
if a write operation has not been initiated, write data to the non-volatile memory using the adjusted redundancy level; and
if the write operation has been initiated, write data to the non-volatile memory using a previous redundancy level.