Object Storage Latency Optimization via Primary Replica Reconfiguration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining the latency of a logical disk in object storage systems is challenging due to asymmetric read and write operations across multiple storage devices, making it difficult to identify and address performance issues such as high latency affecting tenant performance in cloud computing environments.
Innovation Solution
Implementing a method to empirically determine latency by calculating read and write impact factors for each storage device, using mathematical models to simulate adding or removing devices based on their influence on the logical disk's performance, and reconfiguring storage devices to optimize performance by redistributing objects across storage devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If objects are distributed across multiple storage devices with replication, then reliability is improved, but latency increases due to asymmetric read/write operations
Solution Approach 1:
The patent applies local quality by differentiating the roles of storage devices into primary and replica designations. Primary storage devices handle read operations while replica storage devices handle write operations, allowing each device to specialize in its designated function. This differentiation resolves the contradiction by enabling reliable distributed storage while optimizing latency through specialized operation handling at each location.
Solution Approach 2:
The patent explicitly implements asymmetry by creating asymmetric read/write operations where read operations are directed to primary storage devices and write operations are directed to replica storage devices. This asymmetric design resolves the technical contradiction by allowing the system to maintain reliability through distribution while reducing latency through optimized operation routing based on device role.
2Productivity
If storage devices are reconfigured based on latency impact factors, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent implements feedback mechanisms by calculating latency impact factors for each storage device and using this information to dynamically reconfigure the storage system. The system continuously monitors performance metrics, computes the impact of each device on overall latency, and adjusts the primary/replica designations accordingly. This feedback-driven approach resolves the contradiction by automating the optimization process, improving productivity through performance tuning while managing complexity through algorithmic decision-making.
Solution Approach 2:
The patent applies parameter changes by modifying the operational parameters of storage devices based on calculated latency impact factors. Specifically, the system changes the designation parameters (primary vs. replica) of storage devices according to their measured performance characteristics. This parameter-based reconfiguration resolves the contradiction by enabling performance optimization through systematic parameter adjustment while maintaining manageable complexity through defined reconfiguration rules.
Data Source
AI summary
Approaches are disclosed for improving performance of logical disks. A logical disk can comprise several storage devices. In an object storage system (OSS), when a logical disk stores a file, fragments of the file are stored distributed across the storage devices. Each of the fragments of the file is asymmetrically stored in (write) and retrieved from (read) the storage devices. The performance of the logical disk is improved by reconfiguring one or more of the storage devices based on an influence that each of the storage devices has on performance of the logical disk and the asymmetric read and write operations of each of the storage devices. For example, latency of the logical disk can be reduced by reconfiguring one or more of the plurality of storage disks based on a proportion of the latency of the logical device that is attributable to each of the plurality of storage devices.