CDN Proxy for Distributed File System Latency

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing distributed file systems face challenges in providing efficient access to data stored across multiple geographically separate datacenters, leading to suboptimal performance due to the need for clients to access data from distant locations, which can hinder read and write operations.

Innovation Solution

Implementing a content delivery network (CDN) that acts as a proxy and cache within a distributed file system, dynamically determining the optimal datacenter for client requests and managing metadata to optimize data access, thereby reducing the need for clients to access remote datacenters for read and write operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If clients access data from geographically separate datacenters in a distributed file system, then data storage capacity and system scalability are improved, but data access latency and read/write operation performance deteriorate

Engineering Contradiction:
Improvedata storage capacityVSAvoiddata access latency
Core Design Contradiction:
Quantity of substanceVSLoss of time

Solution Approach 1:

The patent introduces a CDN network as an intermediary layer between clients and the distributed file system datacenters. The CDN edge servers cache file data and serve client requests, acting as a mediator that reduces the distance clients must access data. This resolves the contradiction by maintaining the distributed storage architecture while adding an intermediate caching layer that improves access speed without reducing storage capacity.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary actions by pre-caching file data at CDN edge servers before clients need to access it. When files are stored or accessed in the distributed file system, the CDN proactively caches copies at edge locations closer to clients. This preliminary caching action reduces subsequent access latency while preserving the full distributed storage capacity of the original system.

Inventive Principle:
Principle #10Preliminary action

2Loss of time

If a CDN is implemented as a proxy and cache in the distributed file system, then data access latency is reduced, but system complexity increases

Engineering Contradiction:
Improvedata access latencyVSAvoidsystem complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The CDN edge servers perform multiple functions: they act as cache storage, proxy servers, and metadata coordination points. By making these components multi-functional, the system reduces the need for separate dedicated components for each function, thereby managing complexity while achieving reduced access latency through caching and proxy operations.

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

Solution Approach 2:

The CDN system implements self-service mechanisms where edge servers automatically cache content, manage their own metadata, and coordinate with the distributed file system without requiring complex centralized control for every operation. This autonomy reduces the overall system complexity while maintaining performance benefits.

Inventive Principle:
Principle #25Self-service

3Productivity

If CDN edge servers cache file data, then read operation performance is improved, but write operation complexity and metadata management increase

Engineering Contradiction:
Improveread operation performanceVSAvoidmetadata management complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system segments metadata management between the distributed file system's central metadata service and the CDN edge servers' local caching metadata. This segmentation allows read operations to be served quickly from edge caches with simple local metadata, while write operations coordinate with the central system. The segmentation improves read performance while distributing metadata complexity across multiple levels.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS10795866B2Distributed file systems on content delivery networks
Publication Date: 2020.10.06 EMC IP HLDG CO LLC
  • US10795866B2 patent drawing
  • US10795866B2 patent drawing
  • US10795866B2 patent drawing

AI summary

A method, article of manufacture, and apparatus for accessing a distributed file system using a content delivery network is discussed. An IO request for an object is received at a metadata server comprising metadata mapping a plurality of objects to an object store. An object identifier associated with the object and a CDN domain associated with the object store are determined. A URL is generated from the object identifier and the CDN domain. The URL is then returned to the client.