Managing wear balancing in mapped RAID storage systems
A method, computer program product, and computing system for managing wear balance in a mapped RAID storage system. According to embodiments, mapped RAID extents, which are comprised of storage disk extents, are assigned to particular mapped RAID groups based on one or more parameters related to wear experienced by disk extents associated with the RAID extent. Endurance parameters are measured and can be used by machine learning modules to predict future wear levels enabling predictive wear balancing in mapped RAID storage systems. Embodiments can be used when initially forming a mapped RAID group, when adding storage to an existing mapped RAID group, or when managing the ongoing performance of a mapped RAID group or storage system.
1. A method for use in managing wear balancing in mapped RAID storage systems, the method comprising:
determining an endurance parameter for a plurality of disk extents in a mapped RAID storage system, wherein one or more disk extents comprises a mapped RAID extent;
managing a mapped RAID group by locating one or more RAID extents within the mapped RAID group of disk extents having a similar endurance parameter;
determining a predicted number of write operations for the one or more RAID extents within the mapped RAID group of disk extents having a similar endurance parameter;
creating a RAID group using the one or more RAID extents within the mapped RAID group having a similar endurance parameter and a similar predicted write capability; and
reapportioning in an unequal fashion a write capability of one or more disk drives in order to create the RAID group.
2. The method of claim 1 , further comprising determining if an endurance parameter for a disk extent should be reapportioned.
3. The method of claim 1 , further comprising monitoring the endurance parameter for one or more of the plurality of disk extents.
4. The method of claim 1 , wherein the endurance parameter is one or more of: a write capability value, a maximum number of erase cycles, a manufacturer specified maximum wear value, a current total of erase cycles, a total time the disk extent has been in service, a total number of power-on hours, a wear rate, a desired life expectancy, a total number of write operations performed on a disk, a total number of disk extents per disk, a total number of read operations performed on a disk, an operating temperature for a disk, a room temperature for a location in which a disk is stored, a humidity level for a location in which a disk is stored, an atmospheric pressure for a location in which a disk is stored, an air quality for a location in which a disk is stored, a seismic activity for a location in which a disk is stored, or a power outage value for a location in which a disk is stored.
5. The method of claim 1 , wherein locating one or more RAID extents within the mapped RAID group on disk extents having a similar endurance parameter is further based on a predicted endurance parameter.
6. The method of claim 5 , wherein the predicted endurance parameter is determined using a machine learning module.
7. A system for use in managing wear balancing in mapped RAID storage systems, the system comprising a processor configured to:
determine an endurance parameter for a plurality of disk extents in a mapped RAID storage system, wherein one or more disk extents comprises a mapped RAID extent;
manage a mapped RAID group by locating one or more RAID extents within the mapped RAID group of disk extents having a similar endurance parameter;
determine a predicted number of write operations for the one or more RAID extents within the mapped RAID group of disk extents having a similar endurance parameter;
create a RAID group using the one or more RAID extents within the mapped RAID group having a similar endurance parameter and a similar predicted write capability; and
reapportion in an unequal fashion a write capability of one or more disk drives in order to create the RAID group.
8. The system of claim 7 , further configured to determine if an endurance parameter for a disk extent should be reapportioned.
9. The system of claim 7 , further configured to monitor the endurance parameter for one or more of the plurality of disk extents.
10. The system of claim 7 , wherein the endurance parameter is one or more of: a write capability value, a maximum number of erase cycles, a manufacturer specified maximum wear value, a current total of erase cycles, a total time the disk extent has been in service, a total number of power-on hours, a wear rate, a desired life expectancy, a total number of write operations performed on a disk, a total number of disk extents per disk, a total number of read operations performed on a disk, an operating temperature for a disk, a room temperature for a location in which a disk is stored, a humidity level for a location in which a disk is stored, an atmospheric pressure for a location in which a disk is stored, an air quality for a location in which a disk is stored, a seismic activity for a location in which a disk is stored, or a power outage value for a location in which a disk is stored.
11. The system of claim 7 , wherein locating one or more RAID extents within the mapped RAID group on disk extents having a similar endurance parameter is further based on a predicted endurance parameter.
12. The system of claim 11 , wherein the predicted endurance parameter is determined using a machine learning module.
13. A non-transitory computer readable medium with program instructions stored thereon for performing the following acts:
determine an endurance parameter for a plurality of disk extents in a mapped RAID storage system, wherein one or more disk extents comprises a mapped RAID extent;
manage a mapped RAID group by locating one or more RAID extents within the mapped RAID group of disk extents having a similar endurance parameter determine a predicted number of write operations for the one or more RAID extents within the mapped RAID group of disk extents having a similar endurance parameter;
create a RAID group using the one or more RAID extents within the mapped RAID group having a similar endurance parameter and a similar predicted write capability; and
reapportion in an unequal fashion a write capability of one or more disk drives in order to create the RAID group.
14. The non-transitory computer medium of claim 13 , further configured to determine if an endurance parameter for a disk extent should be reapportioned.
15. The non-transitory computer medium of claim 13 , further configured to monitor the endurance parameter for one or more of the plurality of disk extents.
16. The non-transitory computer medium of claim 13 , wherein the endurance parameter is one or more of: a write capability value, a maximum number of erase cycles, a manufacturer specified maximum wear value, a current total of erase cycles, a total time the disk extent has been in service, a total number of power-on hours, a wear rate, a desired life expectancy, a total number of write operations performed on a disk, a total number of disk extents per disk, a total number of read operations performed on a disk, an operating temperature for a disk, a room temperature for a location in which a disk is stored, a humidity level for a location in which a disk is stored, an atmospheric pressure for a location in which a disk is stored, an air quality for a location in which a disk is stored, a seismic activity for a location in which a disk is stored, or a power outage value for a location in which a disk is stored.
17. The non-transitory computer medium of claim 13 , wherein locating one or more RAID extents within the mapped RAID group on disk extents having a similar endurance parameter is further based on a predicted endurance parameter.
18. The non-transitory computer medium of claim 17 , wherein the predicted endurance parameter is determined using a machine learning module.