While consistently delivering on bandwidth needs, many storage fabrics have struggled to keep pace with customer expectations around storage infrastructures powered by AIOps, intelligently tiered storage and provisioning. Building an autonomous, self-driving storage fabric requires shared intelligence between endpoints, strong awareness of fabric conditions and decisive action that automates best practices. This session will explore and evangelize the upcoming NVMe/FC and NVMe/TCP fabric technologies like Fabric Notifications (FPINs), application tracking (VM-ID), congestion control (new reno), intelligent discovery services (nameservers and CDC) and the resulting OS stack integrations that comprise the industry’s quest for a self-driving, autonomous storage fabric.
The Quest for an Autonomous Storage Fabric
- Understand the market dynamics driving the need for advanced automatic decision making in the operation of a storage fabric
- Outline the current advancement in telemetry and fabric condition detection that provides the foundation of in-depth awareness, spanning VM-ID, Discovery controllers and hardware notifications
- Articulate the progress and challenges in implementing decisive actions to changing fabric conditions – including MPIO and IO queueing advancements.
- Review operational and deployment feedback on such implementations from customers and partners and seek industry collaboration to share ideas and intelligence.
---
- Shyam SundarMarvell
nvme-stas is an open source Linux project that provides: - A Central Discovery Controller (CDC) client for Linux - Asynchronous Event Notifications (AEN) handling - Automated NVMe subsystem connect
NVMe over IP is a technology able to provide complete and scalable SAN solutions.
Costs and risks of implementing High-Performance Embedded Systems such as Centralized Car Servers for Autonomous Vehicles can be reduced when borrowing from modern datacenter technology.
- Marcus PietzschFraunhofer IPMS
Introduced in 2021, Fabric Notifications developed into a key resiliency solution for storage networks.
Writing a storage network server based on TCP sockets seems straightfoward - you call send() and recv() on the socket and parse the data. But the reality is not so simple.
SNIA Developer Conference
September 15-17, 2025
SDC 2025 is brought to you by SNIA. SNIA is an industry association committed to its mission of worldwide leadership developing and promoting architectures, standards, education and vendor-neutral collaboration.
