Tenant-Aware Cache Reclamation Under Skewed Memory Usage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In cloud computing environments with multi-tenant databases, existing memory reclamation methods based on overall cache utilization thresholds can lead to inefficient cache management, as individual tenant activity levels vary, skewing overall usage and affecting other tenants.
Innovation Solution
Implementing a cache broker that tracks cache memory usage by individual tenants and generates activeness signals, allowing for selective and multi-tiered reclamation of cache entries based on tenant activity, with resource monitors determining and reclaiming portions of cache memory accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If process-wide memory reclamation is used to reclaim cache memory when utilization is below a threshold, then overall cache memory utilization is improved, but active tenants may be negatively impacted due to skewed resource allocation
Solution Approach 1:
The patent segments the cache memory reclamation process into multiple tiers: process-wide reclamation for overall cache management, tenant-level reclamation for individual tenant control, and object-level reclamation for fine-grained management. This segmentation allows the system to address both overall utilization and individual tenant needs simultaneously, preventing active tenants from being negatively impacted while maintaining efficient resource allocation.
2Device complexity
If cache memory is reclaimed without tenant-level differentiation, then reclamation simplicity is maintained, but resource allocation becomes unequal among tenants with different activity levels
Solution Approach 1:
The patent implements dynamic reclamation policies where the system can adapt its behavior based on tenant activity levels and cache utilization patterns. The multi-tiered approach allows the system to dynamically switch between process-wide, tenant-level, and object-level reclamation strategies, optimizing resource allocation efficiency while maintaining manageable complexity through automated decision-making.
3Productivity
If fine-grained tenant-level monitoring and selective reclamation is implemented, then resource allocation efficiency is improved, but system complexity increases
Solution Approach 1:
The patent employs a nested hierarchical structure where process-wide reclamation operates at the top level, tenant-level reclamation operates at the middle level, and object-level reclamation operates at the bottom level. This nested architecture allows fine-grained control and efficient resource allocation while managing complexity through a clear, hierarchical organization of control mechanisms.
Data Source
AI summary
Reclamation of a portion of a cache memory in a cloud computing environment is described herein. A cache activeness signal is received from a cache broker. The cache activeness signal is representative of a usage of a first set of cache entries of the cache memory by a first group of computing nodes in a cluster of nodes. A determination to reclaim a portion of the first set of cache entries or of a second set of cache entries is made based at least on the cache activeness signal. The second set of cache entries are utilized by a second group of computing nodes in the cluster of nodes. The determined portion of memory is reclaimed. In an aspect, the cache broker determines a usage of the set of cache entries by the first group of computing nodes and generates the cache activeness signal representative of the determined usage.