End of life performance throttling to prevent data loss
AssigneeMicron Technology, Inc.
InventorSebastien Andre Jean
Life of this patent
Estimating the term…
Abstract
Disclosed in some examples are methods, systems, memory devices, machine readable mediums configured to intentionally degrade NAND performance when a value of a NAND health metric indicates a potential for failure to encourage users to replace or backup their devices before data loss occurs. For example, the system may track a NAND health metric and when that metric reaches a predetermined threshold or state, the system may intentionally degrade performance. This performance degradation may be more effective than a warning to effect device backup or replacement.
Claims20
A NAND memory device comprising:
- a NAND memory array including a first pool of memory;
- and
- a controller, the controller executing instructions, to cause the controller to perform operations comprising:
- monitoring a NAND device health metric;
- determining that the NAND device health metric meets a degradation criterion indicating NAND device degradation has already occurred;
- responsive to determining that the NAND device health metric meets the degradation criterion:
- determining a set of one or more host operations to be degraded based upon the NAND device health metric, the set of one or more host operations to be degraded increasing in numerosity as the NAND device health metric indicates worsening NAND device health;
- determining a slowdown rate based upon the NAND device health metric;
- and
- degrading a performance of the NAND memory device based upon the slowdown rate for the set of host operations to be degraded.
A method performed by a controller of a NAND memory device, the method comprising:
- monitoring a NAND device health metric;
- determining that the NAND device health metric meets a degradation criterion indicating NAND device degradation has already occurred;
- responsive to determining that the NAND device health metric meets the degradation criterion:
- determining a set of one or more host operations to be degraded based upon the NAND device health metric, the set of one or more host operations to be degraded increasing in numerosity as the NAND device health metric indicates worsening NAND device health;
- determining a slowdown rate based upon the NAND device health metric;
- and
- degrading a performance of the NAND memory device based upon the slowdown rate for the set of host operations to be degraded.
A non-transitory machine-readable medium, storing instructions, which when executed by a controller of a NAND memory device, cause the memory controller to perform operations comprising:
- monitoring a NAND device health metric;
- determining that the NAND device health metric meets a degradation criterion indicating NAND device degradation has already occurred;
- responsive to determining that the NAND device health metric meets the degradation criterion:
- determining a set of one or more host operations to be degraded based upon the NAND device health metric, the set of one or more host operations to be degraded increasing in numerosity as the NAND device health metric indicates worsening NAND device health;
- determining a slowdown rate based upon the NAND device health metric;
- and
- degrading a performance of the NAND memory device based upon the slowdown rate for the set of host operations to be degraded.
Dependencies are inferred from the claim text.