RAID Disk Power Management via Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Data storage systems face challenges in balancing performance and power consumption, particularly in RAID configurations where some disk drives can spin down to save power, while others cannot, leading to inefficiencies and potential data unavailability issues due to increased latency when spinning disks back up.

Innovation Solution

A method is implemented to identify and group data storage system elements capable of power saving modes into RAID groups, creating logical units that can be associated with servers and enabling power saving settings to optimize power usage without compromising performance, including the ability to power down subsets of drives within a RAID group.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Use of energy by stationary object

If disk drives are spun down to save power, then power consumption is reduced, but response time and data availability deteriorate due to increased latency when spinning disks back up

Engineering Contradiction:

Improvepower consumptionVSAvoidresponse time

Core Design Contradiction:

Use of energy by stationary objectVSLoss of time

Solution Approach 1:

The system segments disk drives into different groups based on their power saving capabilities and operational characteristics. By dividing the storage array into segments that can be independently managed, the system can spin down specific segments to save power while keeping other segments operational, thus reducing the impact on overall response time. This segmentation allows selective power management rather than shutting down the entire storage array.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system dynamically adjusts the operational state of disk drives based on real-time workload patterns and power saving opportunities. By continuously monitoring I/O requests and drive utilization, the system can dynamically spin down drives that are not currently needed while maintaining the ability to quickly spin them back up when required. This dynamic approach optimizes the balance between power savings and response time.

Inventive Principle:

Principle #15Dynamics

2Device complexity

If all disk drives in a RAID group are treated uniformly, then system management is simplified, but power saving efficiency deteriorates when some drives are capable of power saving modes while others are not

Engineering Contradiction:

Improvesystem management complexityVSAvoidpower saving efficiency

Core Design Contradiction:

Device complexityVSUse of energy by stationary object

Solution Approach 1:

The system applies different power management policies to different disk drives within the same RAID group based on their individual capabilities. By identifying which drives support power saving modes and which do not, the system can selectively apply spin-down operations only to capable drives, optimizing power savings without compromising the operational integrity of the RAID group. This local differentiation allows fine-grained power management.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system divides the RAID group into subsets based on drive capabilities, separating drives that support power saving modes from those that do not. This segmentation enables the system to manage power savings independently for each subset, applying appropriate policies to each group while maintaining overall system coherence. The segmentation approach resolves the contradiction by allowing differentiated management without increasing overall complexity.

Inventive Principle:

Principle #1Segmentation

3Use of energy by stationary object

If disk drives are spun down to save power, then energy consumption is reduced, but data availability deteriorates due to potential unavailability during spin-up transitions

Engineering Contradiction:

Improveenergy consumptionVSAvoiddata availability

Core Design Contradiction:

Use of energy by stationary objectVSReliability

Solution Approach 1:

The system performs preliminary actions by pre-positioning data on drives that are more likely to remain operational or by pre-warming drives that may be needed soon. By anticipating data access patterns and pre-preparing the storage system in advance, the system can reduce the impact of spin-down operations on data availability. This preliminary action ensures that critical data remains accessible even when some drives are in power-saving mode.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements beforehand cushioning by maintaining a buffer of operational drives or cache mechanisms that can compensate for the unavailability of spun-down drives. By having redundant operational capacity built into the system beforehand, the system can absorb the impact of drive spin-down operations without significantly affecting overall data availability. This cushioning approach protects against the reliability deterioration that would otherwise occur.

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

Data Source

PatentUS9983816B1Managing disk drive power savings in data storage systems

Publication Date: 2018.05.29 EMC IP HLDG CO LLC

AI summary

A method is used in managing disk drive power saving in data storage systems. Multiple data storage systems storage elements capable of operating in a power saving mode are identified and grouped into a RAID group. One or more logical units are created from the RAID group. The one or more logical units are exposed to a server. The one or more logical units are associated to an application at the server. Power saving settings are determined. A power saving mode based on the power saving settings is enabled.