SDN Controller Bandwidth Allocation for Storage Burst Management

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In software-defined networking environments like data centers, managing bandwidth effectively is challenging, especially during events such as drive failures or simultaneous data requests from multiple clients, which can lead to bottlenecks and impact performance.

Innovation Solution

A software-defined networking (SDN) controller dynamically allocates and manages bandwidth by monitoring storage device failures and data traffic patterns, using models to predict and adjust bandwidth requirements, and allocating additional resources as needed to ensure efficient data replication and handling of burst demands.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If additional bandwidth is allocated for data replication after drive failure, then data replication reliability is improved, but bandwidth available for other services deteriorates

Engineering Contradiction:
Improvedata replication reliabilityVSAvoidbandwidth available for other services
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system dynamically adjusts bandwidth allocation based on real-time conditions. The SDN controller monitors drive failure events and automatically increases bandwidth allocation for data replication only when needed, then reduces it back to normal levels once replication is complete, making the bandwidth allocation flexible and adaptive to changing conditions

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system predicts burst bandwidth requirements using models that analyze historical data and traffic patterns. By predicting when data replication will be needed and estimating the required bandwidth in advance, the system can proactively allocate resources before the actual failure occurs, ensuring immediate availability when needed while optimizing overall bandwidth utilization

Inventive Principle:
Principle #10Preliminary action

2Speed

If bandwidth is increased to handle simultaneous data requests from multiple clients, then service response time is improved, but bandwidth for other operations deteriorates

Engineering Contradiction:
Improveservice response timeVSAvoidbandwidth for other operations
Core Design Contradiction:
SpeedVSProductivity

Solution Approach 1:

The system applies different bandwidth allocation strategies to different operations based on their specific requirements. When simultaneous data requests are detected, the SDN controller identifies the specific storage devices involved and allocates additional bandwidth only to those local paths experiencing demand, rather than increasing bandwidth system-wide, thus maintaining efficient service response time while preserving bandwidth for other operations

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system continuously monitors bandwidth usage patterns and client request rates, using this feedback to dynamically adjust bandwidth allocation. When multiple clients request data simultaneously, the feedback mechanism detects the increased demand and triggers automatic bandwidth reallocation to the affected storage devices, then adjusts back to normal allocation once the burst demand subsides

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS11038815B2Technologies for managing burst bandwidth requirements
Publication Date: 2021.06.15 INTEL CORP
  • US11038815B2 patent drawing
  • US11038815B2 patent drawing
  • US11038815B2 patent drawing

AI summary

Technologies for managing burst bandwidth requirements are disclosed. In the illustrative embodiment, a software-defined network (SDN) controller monitors storage devices in a data center. If a storage device fails, the SDN controller manages the bandwidth used to replicate the data that was stored on the failed storage device. The SDN controller may allocate an initial amount of bandwidth based on one or more parameters of the storage device, and the SDN controller may increase the bandwidth in a series of discrete steps. In another embodiment, the SDN controller may predict a bandwidth burst based on sequential writes at a storage sled from several compute devices, and allocate bandwidth accordingly in a tiered manner.