SAN Bandwidth Allocation via Granular Rate Limiting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High-bandwidth storage area networks face challenges in efficiently managing bandwidth allocation, leading to potential resource contention and violations of quality of service guarantees, especially in decentralized environments where multiple flows converge on a single target.
Innovation Solution
Implementing rate limiting based on quality of service information at various granularities (target, LUN, initiator-target-LUN, initiator-target) to guarantee minimum and maximum bandwidth, using techniques like virtualization and shared memory for precise control and management of bandwidth allocation, ensuring that traffic is shaped to meet requested service levels without dropping frames.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple flows are allowed to converge on a single target in a decentralized SAN, then network bandwidth utilization is improved, but resource contention and quality of service violations occur
Solution Approach 1:
The patent segments the network traffic into different classes (guaranteed bandwidth flows and best-effort flows) and allocates bandwidth separately to each class. This segmentation allows multiple flows to coexist on the same network infrastructure while preventing any single flow from monopolizing resources, thus resolving the contradiction between high bandwidth utilization and quality of service guarantees.
Solution Approach 2:
The patent changes the parameter of bandwidth allocation from a uniform approach to a differentiated approach based on flow classification. By modifying bandwidth allocation parameters dynamically according to flow type and priority, the system achieves both high overall bandwidth utilization and reliable quality of service guarantees for critical flows.
2Reliability
If rate limiting is implemented to guarantee bandwidth, then quality of service is improved, but network flexibility and adaptability decrease
Solution Approach 1:
The patent implements dynamic rate limiting that adjusts bandwidth allocation in real-time based on current network conditions and flow characteristics. The system monitors actual bandwidth consumption and dynamically modifies rate limits to guarantee minimum bandwidth while allowing excess bandwidth to be utilized when available, thus maintaining both reliability and adaptability.
Solution Approach 2:
The system allows flows to self-regulate their bandwidth consumption within allocated limits. By implementing self-service mechanisms where flows monitor and adjust their own transmission rates based on network feedback, the system maintains quality of service guarantees without requiring rigid external control, preserving network flexibility.
3Reliability
If frames are dropped to enforce bandwidth limits, then quality of service control is improved, but network efficiency decreases
Solution Approach 1:
The patent applies preliminary rate limiting at the ingress point of the network, preventing excessive bandwidth consumption before it can impact other flows. By proactively limiting rates at the source rather than reactively dropping frames downstream, the system maintains bandwidth control while maximizing network efficiency and avoiding frame loss.
Data Source
AI summary
In one embodiment, a solution is provided wherein a minimum and/or maximum bandwidth may be guaranteed for specific flows. These guarantees can be associated to various levels of granularity, such as target (T), target-Logical Unit Number (LUN) coupling (TL), initiator-target-LUN coupling (ITL), and initiator-target coupling (IT). This may be accomplished by rate limiting frames in the storage area network based upon quality of service information provided by a user. As such, the traffic can be shaped in a way that guarantees requested levels of service without dropping frames.