Granted Patent B1

US 11,372,561 · App. 17/112,345 · Granted Jun 28, 2022

Inventors: Bina K. Thakkar (Cary, NC); Ashish A. Pancholi (Cary, NC); David C. Waser (Holly Springs, NC)

Assignee: EMC IP Holding Company LLC

G06F3/0631G06F3/0611G06F3/0685

Abstract

Claims (47)

1. A method of determining drive configurations comprising:

determining that an existing tier distribution, of an existing data storage system, is non-optimal;

and in response to determining that the existing tier distribution is non-optimal, reconfiguring the existing tier distribution, wherein said reconfiguring the existing tier distribution further comprises:

receiving a data set including a plurality of tier distributions of a plurality of data storage systems;

applying principal component analysis to the data set to generate a resulting data set, wherein the data set has a first number of dimensions and the resulting data set has a second number of dimensions less than the first number of dimensions;

determining a plurality of clusters using the resulting data set, wherein each of the plurality of clusters includes a portion of the plurality of tier distributions, wherein each of the plurality of clusters has an associated cluster tier distribution determined in accordance with the portion of the plurality of tier distributions in said each cluster;

selecting the associated cluster tier distribution of one cluster of the plurality of clusters;

and performing first processing that determines, in accordance with a storage capacity requirement and in accordance with the associated cluster tier distribution of the one cluster of the plurality of clusters, a drive configuration.

2. The method of claim 1 , wherein each of the plurality of data storage systems includes at least two storage tiers of physical storage devices.

3. The method of claim 2 , wherein at least one of the plurality of data storage systems include a first plurality of storage tiers comprising rotating disk drives and non-volatile solid state storage devices (SSDs).

4. The method of claim 2 , wherein at least one of the plurality of data storage systems include a second plurality of storage tiers and wherein each tier of the second plurality of tiers includes SSDs.

5. The method of claim 2 , wherein each of the plurality of tier distributions is associated with a corresponding one of the plurality of data storage systems, and wherein said each tier distribution specifies a percentage of each of a plurality of storage tiers of said corresponding one of the plurality of data storage systems.

6. The method of claim 2 , wherein the associated cluster tier distribution of each of the plurality of clusters specifies a plurality of percentages of a plurality of storage tiers, wherein each of the plurality of percentages denotes a percentage of one of the plurality of storage tiers.

7. The method of claim 1 , further comprising:

determining a first expected I/O workload capability of the drive configuration; and

determining whether the first expected I/O workload capability meets a specified I/O workload requirement.

8. The method of claim 7 , further comprising:

responsive to determining the first expected I/O workload capability meets the specified I/O workload requirement, recommending the associated cluster tier distribution of the one cluster of the plurality of clusters.

9. The method of claim 1 , further comprising:

determining whether the drive configuration is in accordance with one or more requirements of a specified model of data storage system.

10. The method of claim 9 , wherein the one or more requirements includes a requirement specifying a maximum number of allowable physical storage devices in the specified model of the data storage system.

11. The method of claim 1 , wherein the drive configuration includes a first number of physical storage devices of a first storage tier and a second number of physical devices of a second storage tier different from the first storage tier.

12. The method of claim 1 , further comprising:

determining an initial number of physical storage devices in each of a plurality of storage tiers in accordance with the storage capacity requirement; and

determining a revised number of physical devices in each of the plurality of storage tiers, wherein said determining the revised number includes adjusting the initial number of physical storage devices in each of the plurality of tiers in accordance with one or more spare rules and one or more RAID group rules.

13. The method of claim 1 , wherein the existing tier distribution is determined to be non-optimal responsive to determining that the existing tier distribution includes a percentage for a storage tier and the percentage is not at least a specified minimum percentage.

14. The method of claim 1 , wherein the existing tier distribution is determined to be non-optimal when a lowest performance tier of a plurality of tiers of the existing data storage system is determined to be overloaded.

15. A system comprising:

one or more processors;

and one or more memories comprising code stored thereon that, when executed, performs a method of determining drive configurations comprising:

determining that an existing tier distribution, of an existing data storage system, is non-optimal;

and in response to determining that the existing tier distribution is non-optimal, reconfiguring the existing tier distribution, wherein said reconfiguring the existing tier distribution further comprises:

receiving a data set including a plurality of tier distributions of a plurality of data storage systems;

applying principal component analysis to the data set to generate a resulting data set, wherein the data set has a first number of dimensions and the resulting data set has a second number of dimensions less than the first number of dimensions;

determining a plurality of clusters using the resulting data set, wherein each of the plurality of clusters includes a portion of the plurality of tier distributions, wherein each of the plurality of clusters has an associated cluster tier distribution determined in accordance with the portion of the plurality of tier distributions in said each cluster;

selecting the associated cluster tier distribution of one cluster of the plurality of clusters;

and performing first processing that determines, in accordance with a storage capacity requirement and in accordance with the associated cluster tier distribution of the one cluster of the plurality of clusters, a drive configuration.

16. A non-transitory computer readable medium comprising code stored thereon that, when executed, performs a method of determining drive configurations comprising:

determining that an existing tier distribution, of an existing data storage system, is non-optimal;

and in response to determining that the existing tier distribution is non-optimal, reconfiguring the existing tier distribution, wherein said reconfiguring the existing tier distribution further comprises:

receiving a data set including a plurality of tier distributions of a plurality of data storage systems;

applying principal component analysis to the data set to generate a resulting data set, wherein the data set has a first number of dimensions and the resulting data set has a second number of dimensions less than the first number of dimensions;

determining a plurality of clusters using the resulting data set, wherein each of the plurality of clusters includes a portion of the plurality of tier distributions, wherein each of the plurality of clusters has an associated cluster tier distribution determined in accordance with the portion of the plurality of tier distributions in said each cluster;

selecting the associated cluster tier distribution of one cluster of the plurality of clusters;

and performing first processing that determines, in accordance with a storage capacity requirement and in accordance with the associated cluster tier distribution of the one cluster of the plurality of clusters, a drive configuration.

17. The non-transitory computer readable medium of claim 16 , wherein each of the plurality of data storage systems includes at least two storage tiers of physical storage devices.

18. The non-transitory computer readable medium of claim 17 , wherein at least one of the plurality of data storage systems includes a first plurality of storage tiers comprising rotating disk drives and non-volatile solid state storage devices (SSDs).

Assignments (9)