RAID groups based on endurance sets

Patent metadata

Field	Value
Publication number	US-9946471-B1
Application number	US-201514674896-A
Country	US
Kind code	B1
Filing date	Mar 31, 2015
Priority date	Mar 31, 2015
Publication date	Apr 17, 2018
Grant date	Apr 17, 2018

Abstract

The wear of storage devices in a storage array or storage server cluster is unleveled via modal Read/Write to create a plurality of endurance sets, each endurance set having devices with statistically similar amount of wear in a given period of time, and different endurance sets are subjected to different amounts of wear over a given period of time. The storage devices are organized into RAID groups such that multiple devices associated with the same RAID group are not members of the same endurance set. The number of devices in each endurance set may be selected to match the number of spare failover storage devices.

First claim

What is claimed is:

1. An apparatus comprising: a plurality of physical storage devices configured as a plurality of RAID (Redundant Array of Independent Disks) groups; and at least one controller configured to present a logical storage device to at least one host device, the logical storage device associated with the physical storage devices of a first RAID group of the plurality of RAID groups, the controller being further configured to perform wear unleveling between the physical storage devices of the first RAID group via modal Read/Write of the physical storage devices such that each of the physical storage devices of the first RAID group fails at different times.

2. The apparatus of claim 1 wherein the at least one controller comprises at least one storage director of a storage array.

3. The apparatus of claim 1 wherein the controller is configured to perform wear unleveling of the physical storage devices via modal Read/Write to create a plurality of endurance sets, each endurance set comprising physical storage devices undergoing statistically similar amount of wear in a given period of time, and physical storage devices belonging to different endurance sets are subjected to different amounts of wear over a given time period.

4. The apparatus of claim 3 wherein the controller configures a number of physical storage devices per endurance set that is not greater than a number of spare failover physical storage devices.

5. The apparatus of claim 3 wherein the at least one controller is configured to observe writes and determine a distribution of writes per cycle for the physical storage devices.

6. The apparatus of claim 5 further comprising a virtualization table which maps between the presented logical storage device and a plurality of internal logical storage devices associated with the physical storage devices in accordance with the distribution of writes per cycle.

7. The apparatus of claim 5 wherein a number of cache slots for write are allocated to store data written by host to the first RAID group, and wherein at least one controller is configured to allocate the cache slots of the first RAID group to the storage devices of the first RAID group in accordance with the distribution of writes per cycle.

8. The apparatus of claim 7 wherein modal Read/Write state is updated based on a number of write pending cache slots relative to allocated cache slots for each physical storage device of the first RAID group.

9. The apparatus of claim 7 wherein the physical storage devices of the first RAID group are designated as either Write-only or Read-only during a time period, and modal Read/Write state is updated based on a number of write pending cache slots to the physical storage device designated as Write-only relative to a first threshold, and a number of write pending cache slots to one of the physical storage devices designated as Read-only relative to a second threshold.

10. The apparatus of claim 7 wherein the at least one controller is configured to level writes to the physical storage devices when a predetermined wear of the physical device is achieved.

11. A method comprising: configuring a plurality of physical storage devices as a plurality of RAID (Redundant Array of Independent Disks) groups; presenting a logical storage device to at least one host device, the logical storage device associated with the physical storage devices of a first RAID group of the plurality of RAID groups; and performing wear unleveling between the physical storage devices of the first RAID group via modal Read/Write of the physical storage devices such that each of the physical storage devices of the first RAID group fails at a different time.

12. The method of claim 11 comprising performing wear unleveling of the physical storage devices via modal Read/Write to create a plurality of endurance sets, each endurance set comprising physical storage devices undergoing statistically similar amount of wear in a given time period, and physical storage devices belonging to different endurance sets are subjected to different amounts of wear over a given period of time.

13. The method of claim 12 further comprising configuring the endurance sets to include a number of physical storage devices which is not greater than a number of spare failover physical storage devices.

14. The method of claim 11 comprising observing writes and determining a distribution of writes per cycle for the physical storage devices.

15. The method of claim 14 comprising maintaining a virtualization table which maps between the presented logical storage device and a plurality of internal logical storage devices associated with the physical storage devices in accordance with the distribution of writes per cycle.

16. The method of claim 14 comprising allocating a number of cache slots to the first RAID group, and allocating the cache slots of the first RAID group to the storage devices of the first RAID group in accordance with the distribution of writes per cycle.

17. The method of claim 16 comprising updating modal Read/Write state based on a number of write pending cache slots relative to allocated cache slots for each physical storage device of the first RAID group.

18. The method of claim 16 wherein the physical storage devices of the first RAID group are designated as either Write-only or Read-only during a time period, and comprising updating Read/Write state based on a number of write pending cache slots to the physical storage device designated as Write-only relative to a first threshold, and a number of write pending cache slots to one of the physical storage devices designated as Read-only relative to a second threshold.

19. The method of claim 16 comprising leveling writes to the physical storage devices when a predetermined wear of the physical storage devices is achieved.

20. A non-transitory computer-readable memory having program code comprising: logic which configures a plurality of physical storage devices as a plurality of RAID (Redundant Array of Independent Disks) groups; and logic configured to perform wear unleveling between the physical storage devices via modal Read/Write to create a plurality of endurance sets, each endurance set comprising ones of the physical storage devices undergoing statistically similar amount of wear in a given period of time, and different endurance sets are subjected to different amounts of wear over a given period of time.

Assignees

• Emc Corp
• Emc Ip Holding Co Llc

Inventors

• More Sachin
• Chilton Kendell
• Burke Barry A

Classifications

• G06F3/0616 Primary

  in relation to life time, e.g. increasing Mean Time Between Failures [MTBF] · CPC title

• G06F3/0689

  Disk arrays, e.g. RAID, JBOD · CPC title

• G06F11/004

  Error avoidance (G06F11/07 and subgroups take precedence) · CPC title

• G06F11/1076

  Parity data used in redundant arrays of independent storages, e.g. in RAID systems · CPC title

• G06F3/0631

  by allocating resources to storage systems · CPC title