Cache Tuning Device for Virtual Machine Performance Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In a virtual cloud environment, users often fail to notify operators about cache usage by applications, making it unclear how to control cache allocation for optimal performance, especially since real-time performance values are not typically shared.
Innovation Solution
A cache tuning device with a measurement unit to assess cache usage, a calculation unit to determine optimal cache allocation, and an allocation unit to dynamically adjust cache capacity based on cache sensitivity and pollutivity indices, ensuring efficient cache allocation for each application.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If cache occupancy is increased to improve application performance, then normalized performance improves, but cache occupancy consumes more memory resources
Solution Approach 1:
The patent applies local quality by differentiating cache allocation strategies based on application characteristics. It introduces cache sensitivity and cache pollutivity indices to identify which applications benefit most from cache occupancy, then allocates cache resources selectively to those applications rather than uniformly across all applications, thereby improving performance while conserving memory resources.
Solution Approach 2:
The patent changes the parameter of cache occupancy from a static global setting to a dynamic per-application parameter. By calculating cache sensitivity and cache pollutivity indices for each application and using these to determine individual cache occupancy values, the system optimizes the balance between performance improvement and memory consumption for each application based on its specific characteristics.
2Manufacturing precision
If manual cache allocation control is implemented, then cache allocation precision improves, but operational complexity increases
Solution Approach 1:
The patent implements self-service by enabling the system to automatically measure cache usage conditions, calculate cache sensitivity and cache pollutivity indices, and determine optimal cache occupancy values without requiring manual intervention. The measurement unit continuously monitors cache usage, the calculation unit processes this data to generate allocation decisions, and the control unit implements them, creating a closed-loop autonomous system that achieves precise cache allocation while reducing operational complexity.
Solution Approach 2:
The patent employs feedback mechanisms where the measurement unit continuously monitors actual cache usage conditions and feeds this information back to the calculation unit. This feedback loop enables the system to dynamically adjust cache occupancy values based on real-time performance data, achieving precise cache allocation automatically without requiring manual tuning or complex operational procedures.
3Device complexity
If cache is allocated uniformly to all applications, then device complexity is reduced, but application performance optimization deteriorates
Solution Approach 1:
The patent applies segmentation by dividing the cache allocation process into distinct functional components: a measurement unit that monitors cache usage conditions, a calculation unit that computes cache sensitivity and cache pollutivity indices, and a control unit that determines and applies individual cache occupancy values. This segmentation enables sophisticated per-application optimization while keeping each individual component relatively simple and modular.
Solution Approach 2:
The patent introduces dynamics by transitioning from static uniform cache allocation to dynamic per-application cache occupancy control. The system continuously measures cache usage conditions, recalculates sensitivity and pollutivity indices, and adjusts cache allocation in real-time based on actual application behavior, enabling performance optimization without requiring overly complex manual management mechanisms.
Data Source
AI summary
Performance optimization is achieved by clarifying cache usage characteristics of each application from usage conditions of physical resources (caches) in real time and automatically controlling the cache usage amount of each application. Thus, a system includes a main memory to and from which data is written and read, a level 3 cache memory which can be accessed faster than the main memory, a CPU core configured to execute processing by performing write and read to and from the memory and the cache, a usage amount measurement unit configured to measure a usage condition of a cache of each virtual machine (13a to 13c) executed by the CPU core, an allocation amount calculation unit configured to calculate cache capacity to be allocated to each virtual machine (13a to 13c) from the usage condition, and a control unit configured to allocate the cache capacity to each virtual machine (13a to 13c).