Adaptive Performance Control for Multi-Stream Data Transfer

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Save point backups in data processing systems face performance issues due to over- or under-utilization of resources, leading to inefficient throughput and potential crashes, especially in volatile environments where manual configuration is time-consuming and ineffective in dynamic conditions.

Innovation Solution

An adaptive performance control (APC) system dynamically adjusts the number of active data streams during backups to optimize throughput by periodically activating or deactivating streams based on real-time performance monitoring, using a deterministic or probabilistic approach to maintain maximum efficiency with minimal resource usage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the number of data streams is increased to improve throughput, then data transfer speed improves, but resource utilization becomes over-utilized and performance degrades

Engineering Contradiction:

Improvedata transfer throughputVSAvoidbackup performance stability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system dynamically adjusts the number of active data streams based on real-time resource utilization conditions. The adaptive performance control monitors system state and modifies stream count during backup operations, transitioning from static to dynamic configuration to optimize both throughput and stability under varying workload conditions.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the parameter of data stream count based on detected resource conditions. When resources are over-utilized, the system reduces the number of active streams; when resources are under-utilized, it increases streams. This parameter adaptation resolves the contradiction between maximizing throughput and maintaining stable performance.

Inventive Principle:

Principle #35Parameter changes

2Productivity

If manual configuration of data streams is performed to optimize performance, then throughput can be improved, but time consumption and operational complexity increase

Engineering Contradiction:

Improvebackup throughputVSAvoidconfiguration time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs self-configuration of data stream parameters through automatic performance control. The adaptive mechanism monitors resource utilization and autonomously adjusts the number of active streams without administrator intervention, eliminating manual configuration time while maintaining optimized throughput.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements feedback loops that monitor backup performance and resource utilization, then automatically adjust data stream configuration based on this feedback. This closed-loop control replaces manual trial-and-error configuration with automated real-time optimization, reducing time loss while maintaining high throughput.

Inventive Principle:

Principle #23Feedback

3Ease of operation

If static configuration of data streams is used to simplify operations, then ease of operation improves, but adaptability to changing workload conditions deteriorates

Engineering Contradiction:

Improveconfiguration simplicityVSAvoidperformance adaptability

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The system combines the simplicity of static configuration with the adaptability of dynamic adjustment. The default static configuration provides ease of operation, while the embedded adaptive performance control automatically adjusts parameters in response to changing workload conditions, achieving both simplicity and adaptability simultaneously.

Inventive Principle:

Principle #15Dynamics

4Loss of energy

If the number of data streams is decreased to reduce resource usage, then resource efficiency improves, but throughput and productivity decrease

Engineering Contradiction:

Improveresource utilization efficiencyVSAvoidbackup throughput

Core Design Contradiction:

Loss of energyVSProductivity

Solution Approach 1:

The system dynamically changes the number of active data streams based on real-time resource conditions. When resources are under-utilized, the system increases stream count to maximize throughput; when resources are over-utilized, it decreases streams to improve efficiency. This dynamic parameter adjustment resolves the contradiction between resource efficiency and productivity.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS9699233B1Adaptive performance control of multi-stream data transfer from a source system to a target system

Publication Date: 2017.07.04 EMC IP HLDG CO LLC

AI summary

According to one embodiment, in response to a request to transfer a data set from a source system to a target system over a network, an adaptive performance control (APC) controller allocates a plurality of data streams for transferring the data set. The APC controller activates one or more data streams from the allocated data streams to transfer the data set from the source system to the target system. The APC controller monitors an overall throughput of the activated data streams assigned to transfer the data set from the source system to the target system. The APC controller dynamically adjusts a number of the activated data streams based on the monitored overall throughput of the activated data streams, such that a maximum overall throughput of the activated data streams is reached while maintaining a minimum number of the activated data streams.