Cloud Storage Node Selection Using Sequential Policy Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud storage systems face challenges in efficiently selecting storage areas and data nodes for optimal data replication, balancing factors like network latency, processing load, and availability, which affects data accessibility and reliability.
Innovation Solution
A method is introduced that uses multiple storage policies sequentially to select storage areas and data nodes, prioritizing locality, low-cost, load-balancing, and space-balancing policies to ensure high reliability and availability, by measuring and comparing network latency, processing loads, and availability rates across different areas and nodes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple storage policies are applied sequentially to select storage areas and data nodes, then data accessibility and reliability are improved, but system complexity increases
Solution Approach 1:
The storage selection process is segmented into multiple independent stages, each applying a specific storage policy (locality policy, low-cost policy, load-balancing policy, space-balancing policy). Each stage focuses on a single aspect of optimization, making the overall complex selection process manageable through modular policy application.
Solution Approach 2:
The storage selection system dynamically adjusts the selection criteria based on different storage policies that can be applied in sequence. The system adapts its behavior by switching between different policy frameworks depending on the specific storage requirements and current system state, enabling flexible optimization.
2Speed
If storage areas are selected based on locality policy to minimize network latency, then data accessibility is improved, but storage cost increases
Solution Approach 1:
The selection process separates the locality optimization stage from the cost optimization stage. First, storage areas are selected based on locality policy to minimize network latency, then subsequent policies (low-cost, load-balancing, space-balancing) are applied to optimize cost and distribution, allowing both speed and cost considerations to be addressed independently.
Solution Approach 2:
Different storage policies are applied to different aspects of the selection process. The locality policy prioritizes proximity for high-speed access, while the low-cost policy prioritizes economical storage locations. This allows the system to accept that different locations serve different optimization goals.
3Reliability
If load-balancing policy is applied to distribute processing loads evenly, then system reliability is improved, but selection time increases
Solution Approach 1:
The load-balancing policy is applied as a distinct stage in the sequential selection process, after locality and cost considerations have been addressed. This segmentation allows the system to perform load balancing calculations only after the initial storage area selection is complete, reducing the overall time required compared to simultaneously optimizing all factors.
Solution Approach 2:
The system performs preliminary selection based on locality and cost policies before applying load-balancing considerations. This preliminary action narrows down the candidate storage areas, making the subsequent load-balancing calculation more efficient and less time-consuming.
4Reliability
If space-balancing policy is applied to maximize storage availability, then data reliability is improved, but processing complexity increases
Solution Approach 1:
The space-balancing policy is implemented as a separate final stage in the sequential selection process. By this point, storage areas have already been selected based on locality, cost, and load-balancing criteria, so the space-balancing step only needs to consider availability within the already-narrowed candidate set, reducing processing complexity.
Solution Approach 2:
The system dynamically adjusts the selection criteria based on different storage policies that can be applied in sequence. The space-balancing policy is applied only when necessary and only after previous policies have established a baseline selection, enabling flexible optimization without excessive processing complexity.
Data Source
AI summary
Provided are a method and a server for selecting data nodes for storing an object and replicas thereof in a cloud storage system having a plurality of data nodes grouped in a plurality of storage areas. The method may include selecting at least one storage area for storing the object and the replicas thereof sequentially with a locality policy, a low-cost policy, a load-balancing policy, and a space-balancing policy and selecting at least one data node from the selected at least one storage area sequentially using a load-balancing policy and a space-balancing policy.