Selective powering of storage drive components in a storage node based on system performance limits

Patent metadata

Field	Value
Publication number	US-12093538-B2
Application number	US-202217718719-A
Country	US
Kind code	B2
Filing date	Apr 12, 2022
Priority date	Apr 12, 2022
Publication date	Sep 17, 2024
Grant date	Sep 17, 2024

Abstract

Techniques are provided for selective powering of storage drive components in a storage node based on system performance limits. One method comprises determining a number of storage drive components, of multiple storage drive components in a storage node, needed to support at least one workload of the storage node, wherein the determining is based at least in part on a number of storage drive components needed to support a system performance limit determined using a component performance limit of at least one other component of the storage node, wherein the component performance limit is based at least in part on one or more of an expected number of input/output operations of the storage node and an expected bandwidth of the storage node; and initiating an application of power to the determined number of storage drive components of the storage node.

First claim

What is claimed is:

1. A method, comprising:
determining a number of storage drive components, of a plurality of storage drive components in at least one storage node, of a plurality of storage nodes, of a storage system, needed to support at least one workload of the at least one storage node, wherein the determining is based at least in part on a number of storage drive components needed to support a system performance limit determined using a component performance limit of at least one other component of the at least one storage node, wherein the component performance limit is based at least in part on one or more of an expected number of input-output operations of the at least one storage node and an expected bandwidth of the at least one storage node, wherein the component performance limit of the at least one other component provides a limit on the one or more of the expected number of input-output operations of the at least one storage node and the expected bandwidth of the at least one storage node to be supported by the determined number of storage drive components of the at least one storage node; and
initiating an application of power to the determined number of storage drive components of the at least one storage node;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.

2. The method of claim 1 , wherein the determining the number of storage drive components needed to support the at least one workload is further based on an expected storage capacity demand of the at least one workload determined using at least one predicted storage capacity demand of the at least one workload based at least in part on a historical storage capacity utilization of the at least one workload.

3. The method of claim 1 , wherein the component performance limit based on the expected number of input-output operations is determined by a component performance limit of at least one processing unit component associated with the at least one storage node.

4. The method of claim 1 , further comprising updating the determined number of storage drive components that have an application of power in response to a change in at least one of: (i) an expected capacity demand of the at least one workload, and (ii) the component performance limit based on the one or more of the expected number of input-output operations of the at least one storage node and the expected bandwidth of the at least one storage node.

5. The method of claim 1 , wherein the plurality of storage drive components in the at least one storage node comprises at least a solid-state drive class of storage drive components and a hard disk drive class of storage drive components and wherein the determining the number of storage drive components needed to support the at least one workload is separately determined for at least the solid-state drive class of storage drive components.

6. The method of claim 1 , wherein the expected bandwidth of the at least one storage node comprises the expected number of input-output operations of the at least one storage node multiplied by an expected size of the input-output operations of the at least one storage node.

7. The method of claim 1 , further comprising monitoring a wear level of at least some of the plurality of storage drive components and dynamically adjusting, based at least in part on the monitored wear level, one or more of: (i) the determined number of storage drive components of the at least one storage node that have an application of power, and (ii) a membership of the storage drive components of the at least one storage node that have an application of power.

8. The method of claim 1 , wherein the system performance limit is determined by a minimum component performance limit of the at least one other component of the at least one storage node.

9. The method of claim 1 , wherein initiation of an application of power to one or more additional storage drive components of the at least one storage node is at least temporarily delayed relative to the initiation of the application of power to the determined number of storage drive components.

10. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured to implement the following steps:
determining a number of storage drive components, of a plurality of storage drive components in at least one storage node, of a plurality of storage nodes, of a storage system, needed to support at least one workload of the at least one storage node, wherein the determining is based at least in part on a number of storage drive components needed to support a system performance limit determined using a component performance limit of at least one other component of the at least one storage node, wherein the component performance limit is based at least in part on one or more of an expected number of input-output operations of the at least one storage node and an expected bandwidth of the at least one storage node, wherein the component performance limit of the at least one other component provides a limit on the one or more of the expected number of input-output operations of the at least one storage node and the expected bandwidth of the at least one storage node to be supported by the determined number of storage drive components of the at least one storage node; and
initiating an application of power to the determined number of storage drive components of the at least one storage node.

11. The apparatus of claim 10 , wherein the determining the number of storage drive components needed to support the at least one workload is further based on an expected storage capacity demand of the at least one workload determined using at least one predicted storage capacity demand of the at least one workload based at least in part on a historical storage capacity utilization of the at least one workload.

12. The apparatus of claim 10 , further comprising updating the determined number of storage drive components that have an application of power in response to a change in at least one of: (i) an expected capacity demand of the at least one workload, and (ii) the component performance limit based on the one or more of the expected number of input-output operations of the at least one storage node and the expected bandwidth of the at least one storage node.

13. The apparatus of claim 10 , wherein the plurality of storage drive components in the at least one storage node comprises at least a solid-state drive class of storage drive components and a hard disk drive class of storage drive components and wherein the determining the number of storage drive components needed to support the at least one workload is separately determined for at least the solid-state drive class of storage drive components.

14. The apparatus of claim 10 , further comprising monitoring a wear level of at least some of the plurality of storage drive components and dynamically adjusting, based at least in part on the monitored wear level, one or more of: (i) the determined number of storage drive components of the at least one storage node that have an application of power, and (ii) a membership of the storage drive components of the at least one storage node that have an application of power.

15. The apparatus of claim 10 , wherein the system performance limit is determined by a minimum component performance limit of the at least one other component of the at least one storage node.

16. A non-transitory processor-readable storage medium having stored therein program code of one or m

Assignees

• Dell Products Lp

Inventors

• Aharoni Dan
• Trudel Christopher
• Srabstein Pablo

Classifications

• G06F3/0685

  Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays · CPC title

• G06F1/3203

  Power management, i.e. event-based initiation of a power-saving mode · CPC title

• G06F1/3287

  by switching off individual functional units in the computer system · CPC title

• G06F3/0679

  Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP] · CPC title

• G06F3/0629

  Configuration or reconfiguration of storage systems · CPC title