Multi-Instance Cloud Data Processing on Shared Memory
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Big data software processing on multiple machines introduces network latency, degrading performance and causing errors due to communication delays between machines with unique IP addresses, which limits scalability and efficiency in cloud-based applications.
Innovation Solution
Deploying big data software, visualization tools, and business analytics in a multi-instance mode on a large, coherent shared memory many-core computing system, allowing multiple application instances to run on a single machine, thereby reducing latency and enhancing scalability and resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple machines execute multiple copies of big data software to process large amounts of data faster, then processing speed is improved, but network latency increases due to communication between machines with unique IP addresses
Solution Approach 1:
The patent merges multiple application instances onto a single machine with a many-core processor and large coherent shared memory system. This consolidation eliminates the need for inter-machine network communication while preserving parallel processing capabilities through multiple cores, thereby resolving the contradiction between processing speed and network latency.
Solution Approach 2:
The patent creates multiple copies (instances) of the big data software application that run in parallel on different cores of the same machine. These copies process data independently and communicate through shared memory rather than network, achieving high processing throughput without network latency penalties.
2Productivity
If multiple machines are used to process big data, then data processing capacity is improved, but system complexity increases due to each machine having its own IP address and requiring network communication
Solution Approach 1:
The patent combines multiple application instances and their associated data processing operations onto a single machine with many cores. This merging reduces system complexity by eliminating the need for multiple IP addresses, network stack configurations, and inter-machine communication protocols, while maintaining high processing capacity through parallelism.
3Device complexity
If big data software is deployed in single instance mode on a many-core system, then system simplicity is maintained, but scalability is limited
Solution Approach 1:
The patent segments the single application into multiple independent instances that can be deployed on a many-core system. Each instance can be configured with different resource allocations and executed in parallel, enabling the system to scale from single-instance to multi-instance modes based on workload requirements while maintaining manageable complexity through a unified deployment framework.
Data Source
AI summary
A system deploys visualization tools, business analytics software, and big data software in a multi-instance mode on a large, coherent shared memory many-core computing system. The single machine solution provides or high performance and scalability and may be implemented remotely as a large capacity server (i.e., in the cloud) or locally to a user. Most big data software running in a single instance mode has limitations in scalability when running on a many-core and large coherent shared memory system. A configuration and deployment technique using a multi-instance approach, which also includes visualization tools and business analytics software, maximizes system performance and resource utilization, reduces latency and provides scalability as needed, for end-user applications in the cloud.