Peer-to-Peer Data Movement for Geo-Distributed Cloud Centers

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing data movement solutions in cloud computing environments are inadequate for geo-distributed data centers, as they require complex topology configurations for multiple sites, are limited to national-level data distribution, and cannot handle diverse storage types or unreliable network conditions, leading to inefficiencies and failures in ensuring service level agreements across distant locations.

Innovation Solution

A peer-to-peer (P2P) data movement mechanism is implemented, allowing geo-distributed data centers to form a self-adapting network for transparent data sharing and relocation worldwide, using P2P agents and a torrent server to segment and re-compose data across different storage types, and dynamically adjust data placement based on cost considerations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional data movement solutions are used in geo-distributed data centers, then data distribution can be achieved, but the system requires complex topology configurations and is limited to national-level distribution

Engineering Contradiction:

Improvedata distribution scopeVSAvoidtopology configuration complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the data distribution system into autonomous peer nodes that independently manage their own data segments. Each peer acts as both client and server, eliminating the need for complex centralized topology configurations. This segmentation enables global distribution by allowing any peer to serve data requests without requiring pre-configured hierarchical relationships.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent implements universal peer nodes that can simultaneously perform multiple functions: storing data, serving data requests, discovering other peers, and relaying traffic. This multi-functionality eliminates the need for specialized components for each function, simplifying the overall system architecture while enabling global reach through any peer's ability to route requests.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Adaptability or versatility

If existing data movement mechanisms are deployed across distant locations, then global data sharing is enabled, but service level agreements cannot be ensured due to unreliable network conditions

Engineering Contradiction:

Improvenetwork condition adaptabilityVSAvoidservice level agreement guarantee

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent implements dynamic peer selection and data routing that adapts to current network conditions. Peers can dynamically join and leave the network, and data requests are routed through available peers based on real-time network state. This dynamic behavior allows the system to maintain service level agreements by automatically adjusting to unreliable network conditions rather than requiring static, pre-configured paths.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent incorporates feedback mechanisms where peers report their status, data availability, and network conditions to the distributed system. This feedback enables intelligent routing decisions that avoid unreliable peers and paths, ensuring service level agreements are met by continuously adapting to actual network conditions across distant locations.

Inventive Principle:

Principle #23Feedback

3Adaptability or versatility

If data is distributed across multiple storage types in geo-distributed centers, then storage flexibility is improved, but data segmentation and re-composition becomes more complex

Engineering Contradiction:

Improvestorage type diversityVSAvoiddata segmentation complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent changes the parameter of data representation into a standardized segmented format that is independent of underlying storage types. Each data segment is encoded with metadata that describes its properties, allowing the same segmentation logic to work across diverse storage systems. This parameter standardization enables flexible storage type selection without increasing segmentation complexity.

Inventive Principle:

Principle #35Parameter changes

4Productivity

If peer-to-peer data movement is implemented globally, then data distribution speed is improved, but network bandwidth consumption increases

Engineering Contradiction:

Improvedata distribution speedVSAvoidnetwork bandwidth consumption

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The patent merges multiple data requests into single peer-to-peer transfers by allowing peers to cache and serve data for multiple requesting peers. When one peer transfers data to another, that receiving peer can subsequently serve other peers without requiring additional origin-to-peer transfers. This merging of transfer operations maintains high distribution speed while significantly reducing total network bandwidth consumption across the global peer network.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS10326835B1Global data movement in cloud computing environment

Publication Date: 2019.06.18 EMC IP HLDG CO LLC

AI summary

A data movement method includes enabling a given data center operatively coupled to one or more other data centers via a communication network to move data between itself and the one or more other data centers in accordance with a peer-to-peer protocol. The given data center and the one or more other data centers thereby form a peer-to-peer network. At least a portion of the given data center and the one or more other data centers are implemented on a cloud computing platform.