An NVMe-oF IP-Based SAN consists of Multiple Hosts, NVM Subsystems connected to Network switches that provide the IP connectivity. As the number of endpoints(devices) grow, a NVMe IP-Based SAN becomes difficult to manage with traditional discovery mechanisms that require, administrators to explicitly configure each host to access each of the NVM subsystems. To eliminate the challenges of traditional discovery, automated discovery techniques such as Direct Discovery Controller (DDC)/Centralized Discovery Controller (CDC) are recently introduced in the industry, by NVMe experts.

/*-->*/

A prominent trend in disaggregated storage is the use of Non-Volatile Memory Express over Fabric (NVME-oF) to connect to storage clusters. DPUs provide local NVMe controller to remote NVMe over Fabric storage offload, where the NVMe devices can appear as local PCIe controllers to the VMs and containers but can reach to namespaces provided over NVMe over Fabric target storage with the help of the DPU without the involvement of the host.

Just like SCSI, NVMeoF installations rely on multiple network paths to maximize the throughput between the NVMe host and controller. And, just like any network, sometimes those paths fail. Come learn about how to recover from those failures in a way that leaves your data intact. And then learn about how to recover more quickly. This presentation will require a basic understanding of the NVMeoF protocol.

The rapid growth of digital data and the increasing demand for storage solutions present challenges and sustainability opportunities. This session will explore how storage developers can embrace circular economy principles to reduce the environmental impact of storage devices and address supply chain constraints.

Key Takeaways:

• Caching is used in almost every component of today's storage systems to speed up data access and reduce data movement. The most important component of a cache is the eviction algorithm that decides which objects to keep in the very limited cache space. While Least-Recently-Used (LRU) is the most common eviction algorithm, it suffers from many problems.
• First, LRU is not scalable. LRU maintains objects in last-access order, which requires a doubly-linked list.

Open Compute Project’s (OCP) Sustainability Project was established in ~2020 as Datacenter Sustainability gained more and more importance. It has since spawned multiple workstreams working on different aspects of Sustainability in devices and are essential to enabling circular economy in Datacenter. Sustainable design encompasses a multitude of categories ranging from reduced power usage, power telemetry, carbon efficiency metrics, elongating lifespan of competitive use or telemetry for carbon metrics.

The Open Lakehouse paradigm is a transformative approach designed to minimize data movement and reduce vendor lock-in. Join Alex Merced, Senior Tech Evangelist at Dremio, as he explores the open-source standards driving this innovation. In this talk, Alex will introduce the fundamental technologies and frameworks that enable the creation of flexible, scalable, and cost-effective data platforms.

Sustainable and cost-effective long-term storage remains an unsolved problem. The most widely used enterprise storage technologies today are magnetic (hard disk drives and tape). They use media that degrades over time and has a limited lifetime, which leads to inefficient, wasteful, and costly solutions for long-lived data. This talk presents Silica: the first cloud storage system for archival data underpinned by quartz glass, an extremely resilient media that allows data to be left in place indefinitely.