Intelligent Hierarchical Caching Metrics Storage Lifespan

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Content delivery networks face high operational expenses and increased network usage due to the short lifespan of storage devices and frequent replacements, exacerbated by the high volume of dynamic content cached in data centers closer to clients.

Innovation Solution

Implementing intelligent hierarchical caching based on metrics for objects across different cache levels, which optimizes disk and network usage by determining whether to cache objects in lower-level caches based on size and request rate metrics, reducing writes and network traffic.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If content is cached in data centers closer to clients using storage devices, then response speed for requested content is improved, but the lifespan of storage devices becomes short and operational expenses increase

Engineering Contradiction:
Improveresponse speedVSAvoidlifespan of storage devices
Core Design Contradiction:
SpeedVSDuration of action of stationary object

Solution Approach 1:

The patent segments the caching system into multiple hierarchical levels (edge caches, regional caches, and central caches) with different storage device types optimized for different functions. This segmentation allows each level to handle specific traffic patterns, reducing the burden on any single level and extending overall system lifespan while maintaining fast response speeds at the edge.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes storage parameters by using different storage device types (SSD vs. HDD) at different hierarchical levels based on access patterns. Edge caches use SSDs for high-speed access to frequently requested content, while less frequently accessed content is stored in HDDs at lower levels, optimizing both response speed and device lifespan.

Inventive Principle:
Principle #35Parameter changes

2Quantity of substance

If larger quantities of dynamic content are provided to various clients, then network usage increases, but the frequency of replacing disks and associated network equipment rises

Engineering Contradiction:
Improvequantity of dynamic contentVSAvoidfrequency of replacing equipment
Core Design Contradiction:
Quantity of substanceVSProductivity

Solution Approach 1:

The patent introduces a hierarchical dimension to the caching system, organizing storage resources across multiple levels (edge, regional, central) rather than using a single flat caching layer. This dimensional organization allows the system to handle larger quantities of dynamic content by distributing the load across different levels, reducing equipment replacement frequency.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent creates a multi-functional caching system where different cache levels serve different purposes: edge caches handle immediate client requests for fast response, regional caches aggregate content for multiple edge locations, and central caches store large quantities of dynamic content. This universality allows the system to manage larger content volumes without proportionally increasing equipment replacement frequency.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS11216382B1Intelligent hierarchical caching based on metrics for objects in different cache levels
Publication Date: 2022.01.04 AMAZON TECH INC
  • US11216382B1 patent drawing
  • US11216382B1 patent drawing
  • US11216382B1 patent drawing

AI summary

A cache system may maintain size and/or request rate metrics for objects in a lower level cache and for objects in a higher level cache. When an L1 cache does not have an object, it requests the object from an L2 cache and sends to the L2 cache aggregate size and request rate metrics for objects in the L1 cache. The L2 cache may obtain a size metric and a request rate metric for the requested object and then determine, based on the aggregate size and request rate metrics for the objects in the L1 cache and the size metric and the request rate metric for the requested object in the L2 cache, an indication of whether or not the L1 cache should cache the requested object. The L2 cache provides the object and the indication to the L1 cache.