Predictive Storage Rebalancing with Controller Node Scaling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage systems fail to allocate resources of the storage controller at the appropriate timing, leading to inefficiencies in power usage and resource management.
Innovation Solution
A storage system with controller nodes that predict long-term load fluctuations, calculate addition/reduction completion times, and perform rebalancing processes based on load thresholds and bandwidth information to optimize resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If resource allocation is performed without predictive rebalancing, then system simplicity is maintained, but power saving efficiency deteriorates
Solution Approach 1:
The system performs predictive rebalancing by calculating future load fluctuations and determining optimal timing for controller node addition/reduction before actual load changes occur. This preliminary action enables the system to allocate resources proactively rather than reactively, improving power saving efficiency while managing complexity through automated prediction and planning.
2Loss of time
If controller node addition/reduction is performed without predictive planning, then system responsiveness is improved, but resource allocation timing accuracy deteriorates
Solution Approach 1:
The system calculates long-term load fluctuation predictions and determines addition/reduction completion target times in advance. This preliminary planning allows the system to maintain accurate resource allocation timing while preparing necessary infrastructure ahead of time, thus preserving responsiveness when actual changes are needed.
Solution Approach 2:
The system dynamically adjusts controller node capacity based on predicted load fluctuations rather than using fixed allocation. This dynamic approach enables the system to respond appropriately to changing conditions while maintaining timing accuracy through continuous prediction and adjustment cycles.
3Speed
If data rebalancing is performed without considering bandwidth constraints, then rebalancing speed is improved, but data movement cost increases
Solution Approach 1:
The system calculates rebalancing time by considering bandwidth information as a constraint parameter. Instead of maximizing rebalancing speed without constraints, the system adjusts the rebalancing process to respect bandwidth limitations, thereby reducing data movement cost while maintaining acceptable rebalancing speed through optimized parameter selection.
Data Source
AI summary
A storage system includes a plurality of drive nodes, a plurality of controller nodes controlling data from a host device to the plurality of drive nodes, and a processor that calculates long-term load fluctuation prediction as prediction of load fluctuation over a certain period of time in the future of the plurality of controller nodes based on time-series data of load of the plurality of controller nodes, and calculates an addition/reduction completion target time to complete addition or reduction of an operating controller node out of the plurality of controller nodes based on the long-term load fluctuation prediction and a load threshold value determined from a power performance model representing a relationship between the load and energy efficiency of the plurality of controller nodes.