Database Cache Layer Using Internal Node Memory
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Database systems implementing a cache layer with network attached storage experience significant latency and additional costs when distributed across multiple physical nodes in different availability zones, which can be exacerbated by cloud-based hosting platforms.
Innovation Solution
Implementing a cache layer within the internal memory of physical nodes using containers to service data requests directly from the cache, reducing latency and potential costs by avoiding external storage access, and employing techniques for cache rehydration and high availability through container management and metadata coordination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If network attached storage is used for cache layer, then storage capacity and reliability are improved, but latency increases and costs increase
Solution Approach 1:
The system segments the cache layer by implementing separate cache instances on each physical node's internal memory, allowing local data access without relying on centralized network storage. Each node maintains its own cache segment, reducing dependency on network-attached storage and minimizing latency.
Solution Approach 2:
The patent introduces an intermediary mechanism where containers manage cache data locally on physical nodes while coordinating through a metadata service. This intermediary layer enables high availability through container orchestration without requiring direct network-attached storage access, resolving the latency-reliability tradeoff.
2Quantity of substance
If network attached storage is used for cache layer, then storage capacity is improved, but costs increase
Solution Approach 1:
The patent extracts the cache storage function from network-attached storage and implements it directly within physical nodes' internal memory. This extraction eliminates the need for expensive network storage infrastructure while maintaining adequate storage capacity through distributed local caches across multiple nodes.
Solution Approach 2:
Instead of using expensive network-attached storage, the system creates multiple copies of cache data distributed across different physical nodes' internal memory. This copying approach provides sufficient storage capacity through distribution while avoiding the cost premium of specialized network storage infrastructure.
3Reliability
If distributed architecture across multiple availability zones is implemented, then reliability and scalability are improved, but system complexity increases
Solution Approach 1:
The patent implements universal container instances that can operate across multiple availability zones with the same codebase and architecture. These multi-functional containers handle various operations (data caching, metadata management, coordination) through unified designs, reducing the complexity burden of distributed architectures while maintaining high reliability across availability zones.
Data Source
AI summary
Techniques are disclosed relating to implementing a cache layer for a distributed database system. In some embodiments, a distributed computing system that includes a plurality of physical nodes implementing a hosting service deploys, to a first of the plurality of physical nodes, a container that implements a cache for a distributed database system hosted by the hosting service. The container is executable to store the cache in a memory internal to the first physical node. The container receives, from the database system, a data request for data maintained in a persistent storage external to the first physical node. In response to determining that the requested data resides in the cache, the container services the data request from the internal memory of the first physical node.