Multi-tenant Database Data Segmentation and Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current database systems face scalability issues and high transaction costs in high-volume multi-tenant environments, struggling to efficiently store and retrieve large amounts of data to support business intelligence and analytics.
Innovation Solution
A scalable database system that differentiates between fact and dimensional tables, distributing metric data across nodes and compressing attribute data for local operation, with a data evaluation engine that predicts query needs and allocates storage dynamically to ensure rapid data access and management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If data is distributed across multiple nodes using Shared Nothing concept, then data access speed is improved, but scalability in high-volume multi-tenant environment deteriorates
Solution Approach 1:
The patent segments data into fact tables and dimensional tables, and further segments dimensional tables into multiple copies distributed across nodes. Fact tables are partitioned by tenant ID to enable independent access. This segmentation allows each node to handle specific data segments independently while maintaining overall system scalability in multi-tenant environments.
Solution Approach 2:
The patent creates multiple copies of dimensional tables across different nodes rather than distributing single copies. Each node maintains complete copies of dimensional data, enabling local joins and aggregations without cross-node communication. This copying strategy improves both access speed and scalability by allowing parallel processing across multiple nodes.
2Quantity of substance
If database compresses and stores maximum information, then storage efficiency is improved, but transaction cost and access speed deteriorate
Solution Approach 1:
The patent applies different storage strategies to different data types: dimensional tables are compressed and stored in multiple copies across nodes for efficient storage and local access, while fact tables are partitioned and stored with minimal compression to maintain fast write performance. This local quality differentiation optimizes both storage efficiency and access speed for each data type.
Solution Approach 2:
The patent pre-computes and stores aggregated dimensional data at each node before queries are executed. This preliminary action allows query execution to proceed without real-time compression/decompression operations, significantly reducing transaction costs and improving access speed while maintaining high storage efficiency.
3Reliability
If data is duplicated across multiple nodes, then data access reliability is improved, but storage requirements and management complexity increase
Solution Approach 1:
The patent segments duplication strategy by data type: dimensional tables are fully duplicated across all nodes for reliable local access, while fact tables are partitioned by tenant ID and distributed selectively. This segmentation reduces overall storage requirements compared to full duplication while maintaining access reliability for both data types through appropriate replication strategies.
Data Source
AI summary
Large-scale advanced database models, systems, and methods provide a responsive, scalable data storage solution which is ripe for use in data warehousing and analytics environments. These advanced database models, systems, and methods provide for dramatically increased performance in accessing data as well as increased storage capabilities in the data set.