NVMe-oF Packet Routing via Automatic Signature Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network infrastructure devices face challenges in efficiently handling NVMe-oF traffic, as they often require frequent configuration updates and resource-intensive lossless queues, which can lead to inefficiencies and packet loss when processing both lossless and lossy protocols simultaneously.
Innovation Solution
Implementing automatic detection and routing of NVMe-oF network packets using signature recognition and priority flow control, allowing NVMe-oF packets to be routed to lossless queues while non-NVMe-oF packets are handled differently, reducing the need for frequent configuration changes and optimizing resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If NVMe-oF packets are routed through lossless queues to ensure reliable delivery, then packet loss is reduced, but device complexity and resource consumption increase
Solution Approach 1:
The patent segments network traffic into different queues based on protocol type (NVMe-oF versus other protocols). By creating dedicated lossless queues specifically for NVMe-oF traffic while allowing other traffic to use standard lossy queues, the system ensures reliable delivery for storage protocols without applying lossless queue overhead to all traffic, thereby reducing overall device complexity while maintaining reliability where needed
Solution Approach 2:
The patent applies lossless queue handling selectively only to NVMe-oF packets that require guaranteed delivery, rather than uniformly applying lossless queue management to all network traffic. This localized approach ensures that reliability enhancements are applied precisely where needed for storage protocols while avoiding unnecessary complexity for other traffic types
2Measurement precision
If manual configuration updates are applied to handle NVMe-oF traffic, then routing accuracy is improved, but ease of operation deteriorates due to frequent configuration changes
Solution Approach 1:
The patent implements automatic detection mechanisms that enable network infrastructure devices to self-identify and route NVMe-oF packets based on packet signatures and characteristics. This self-service capability eliminates the need for manual configuration updates, allowing the system to automatically adapt to NVMe-oF traffic while maintaining accurate routing without requiring operator intervention for configuration changes
3Reliability
If resource-intensive lossless queues are used for all packets, then reliability is improved, but productivity deteriorates due to resource consumption
Solution Approach 1:
The patent segments network traffic into NVMe-oF packets requiring lossless handling and other packets that can tolerate lossy queues. By directing only NVMe-oF traffic through resource-intensive lossless queues while allowing other traffic to flow through standard queues, the system maintains high reliability for storage protocols while preserving overall network throughput and avoiding unnecessary resource consumption
Data Source
AI summary
Non-volatile memory express (NVMe) is a data transfer protocol used to enable high-speed data transfer between a host computer system and a solid-state drive (SSD). NVMe may be implemented over network fabrics and referred to as NVMe over fabrics (NVMe-oF). Access to SSD storage over network fabrics via NVMe-oF allows software defined storage to scale to allow access to a number of NVMe devices and extend distances between devices within a datacenter over which NVMe devices may be accessed. A network device is provided to automatically detect, prioritize, and route NVMe network packets in a network that includes multiple data communication protocols. For example, the network device may obtain network packets, analyze network packets to identify packet type and protocol, and redirect the network packets based on the analysis and detection. Thus, a processing priority may be provided for NVMe packets to assist in lossless communication implementations for storage across a network.