Multi-Tiered Cache Workload Communication and Dynamic Resizing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional multi-tiered caching systems in data centers face inefficiencies due to fixed cache structures that fail to adapt dynamically to workload changes across different cache tiers, leading to redundancy and decreased performance.

Innovation Solution

A multi-tiered cache system where workload changes are communicated between tiers, allowing dynamically resizable cache elements to adjust their performance, such as resizing or instantiating/decommissioning virtual storage appliances to optimize cache behavior based on current workload characteristics.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional fixed cache structure is used, then cache organization is simple, but resource utilization decreases and performance deteriorates under dynamic workload

Engineering Contradiction:
Improvecache adaptability to workload changesVSAvoidcache structure complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic cache tiers where the size and configuration of cache layers can change in response to workload characteristics. The system monitors workload patterns and dynamically adjusts cache allocation, transforming the static cache structure into an adaptive one that evolves with usage patterns, thereby resolving the contradiction between simplicity and adaptability.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes cache parameters (size, tier configuration, allocation ratios) based on detected workload characteristics. By dynamically modifying these parameters rather than maintaining fixed values, the cache system adapts to varying workload demands while managing complexity through parameterized control mechanisms.

Inventive Principle:
Principle #35Parameter changes

2Loss of information

If traditional multi-tier cache protocol is used, then cache coordination is straightforward, but communication gap exists between tiers leading to duplicated effort

Engineering Contradiction:
Improveworkload information sharing between tiersVSAvoidinter-tier communication complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent establishes feedback loops where cache tiers exchange workload characteristic information with each other. Upper tiers communicate workload patterns to lower tiers, enabling coordinated caching decisions. This feedback mechanism eliminates information gaps and duplicated speculation efforts while managing communication complexity through structured information exchange protocols.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system introduces intermediary communication mechanisms that facilitate information exchange between cache tiers. Rather than direct complex peer-to-peer communication, intermediary structures enable streamlined information flow about workload characteristics, reducing communication overhead while improving inter-tier coordination.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Loss of energy

If fixed cache size allocation is used, then resource allocation is simple, but redundancy occurs and resources are wasted

Engineering Contradiction:
Improvecaching resource efficiencyVSAvoiddynamic cache resizing capability
Core Design Contradiction:
Loss of energyVSExtent of automation

Solution Approach 1:

The cache system performs self-adjustment by automatically detecting workload changes and resizing cache tiers without external intervention. The system monitors its own performance metrics and workload patterns, then autonomously reallocates caching resources to eliminate redundancy and improve efficiency, embodying self-service automation.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

Cache size allocation transitions from static to dynamic, with tiers automatically expanding or contracting based on real-time workload characteristics. This dynamic resizing capability eliminates resource waste from fixed allocations while the automation manages the complexity of continuous adjustment through embedded control logic.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP2761473B1Intelligence for controlling virtual storage appliance storage allocation
Publication Date: 2020.03.11 NETAPP INC
  • EP2761473B1 patent drawingFigure 1
  • EP2761473B1 patent drawingFigure 2
  • EP2761473B1 patent drawingFigure 3

AI summary

A change in workload characteristics detected at one tier of a multi-tiered cache is communicated to another tier of the multi-tiered cache. Multiple caching elements exist at different tiers, and at least one tier includes a cache element that is dynamically resizable. The communicated change in workload characteristics causes the receiving tier to adjust at least one aspect of cache performance in the multi-tiered cache. In one aspect, at least one dynamically resizable element in the multi-tiered cache is resized responsive to the change in workload characteristics.