Dynamic Storage Cluster Membership for Power Savings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The growing power demands of storage clusters in modern computer networks lead to significant costs and environmental concerns, with existing solutions like MAID systems compromising on latency and throughput.
Innovation Solution
A power management system dynamically controls membership in storage clusters by setting resource usage thresholds, selecting storage servers to deactivate, and migrating resources to maintain efficient access and redundancy, thereby reducing power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If more storage servers are added to the storage cluster to provide large amounts of storage with high reliability, then storage capacity and reliability are improved, but power consumption increases significantly
Solution Approach 1:
The patent implements dynamic power management by transitioning storage servers between active and low-power states based on real-time workload conditions. The system continuously monitors resource usage metrics and dynamically adjusts the number of active storage servers in the cluster, allowing the infrastructure to adapt its power consumption to actual demand while maintaining required service levels and reliability.
2Use of energy by stationary object
If storage servers are deactivated to reduce power consumption, then power costs are reduced, but storage access reliability and performance may deteriorate
Solution Approach 1:
The system employs feedback mechanisms by continuously monitoring workload conditions, resource usage metrics, and performance thresholds. Based on this feedback, the power management system makes intelligent decisions about when to activate or deactivate storage servers, ensuring that reliability requirements are met while optimizing power consumption. The feedback loop allows the system to respond to changing conditions and maintain service levels.
Solution Approach 2:
The patent implements preliminary actions by proactively migrating data and resources before deactivating storage servers. The system prepares the cluster for server deactivation by redistributing workloads and ensuring data availability on remaining active servers, thereby preventing service disruption and maintaining reliability even as servers transition to low-power states.
3Use of energy by stationary object
If storage resources are migrated between servers to deactivate selected servers, then power consumption is reduced, but system complexity and migration overhead increase
Solution Approach 1:
The patent applies segmentation by dividing the storage cluster into manageable units and organizing resources in a modular fashion. This segmentation allows for systematic resource migration and server deactivation without requiring complex system-wide reconfiguration. The modular approach enables incremental changes and simplifies the management of power states across the cluster.
Data Source
AI summary
A system for controlling power usage in a storage cluster by dynamically controlling membership in the storage cluster is disclosed. The storage cluster includes multiple storage servers that provide access to one or more storage subsystems. The power management system uses a power management policy to set parameters for controlling membership in the storage cluster and monitors the storage cluster based on the policy. Based on the monitoring, the system detects when the number of storage servers in the storage cluster should be reduced or increased. To reduce the number, the system selects a storage server to deactivate and directs the selected storage server to migrate storage resources (e.g., data, metadata) associated with the server to a different storage server. The system then deactivates the selected storage server by directing it to transition to a low power mode. The system may increase the number of servers in the storage cluster by reversing these steps.