SNIA Developer Conference September 15-17, 2025 | Santa Clara, CA
Leveraging SPDK Acceleration Framework for Optimal IPU Storage Workflows
Infrastructure Processing Units (IPUs) is revolutionizing the networked storage paradigm for cloud service providers (CSPs). The type of device enhances system architecture by exposing NVMe PCI devices to the host and offloading network storage tasks onto the IPU. The Storage Performance Development Kit (SPDK) Acceleration Framework is perfectly suited to operate on these devices, capitalizing on their hardware offloading capabilities for efficient data movement and transformation.
Evaluating Discovery Automation on a Large Scale NVMe-oF Deployment
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.
Optimizing NVMe Over TCP Disaggregated Storage architecture on DPUs
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.
Recovering from a Loss of Communication with an NVMe Controller
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.
Product Circularity: Integrating Sustainability into Storage Design and Development
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:
No More LRU: Simple Scalable Caching with Only FIFO Queues
- 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.
Sustainability Initiatives by Open Compute Project – 3 Categories of work for Pro-Sustainability Design and Circular Economy in Storage
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.