OFA Sunfish: New Applications for Distributed Storage with SNIA Swordfish®

The OpenFabrics Alliance (OFA), together with its partners, DMTF, SNIA, and the CXL Consortium, are continuing development of Sunfish, an open-source composable computing system framework, to provide a unified set of tools to control and monitor both computing resources and multiple network fabric types. The Sunfish workgroup has demonstrated management of disaggregated memory systems based on CXL and compute accelerators such as GPUs. We are now expanding our scope to encompass the management of scalable fabric attached storage resources with SNIA Swordfish®. In this presentation, we will update on the activities around support for distributed storage and demonstrate a Sunfish Agent that interacts with a SNIA Swordfish endpoint to configure and provision remote storage resources to applications.

Nathan Hanford

Computer Scientist

Livermore Computing Division, Lawrence Livermore National Laboratory

Want a deeper look into what’s new in standards-based storage management? Join us for an overview of the latest enhancements and new functionality in SNIA Swordfish® and how it works together with DMTF Redfish® to provide a unified approach for the management of storage and servers in AI, hyperscale and cloud environments. With the broad functionality base in Redfish and Swordfish today, there are now many capabilities available that may not be obvious at first glance. The session will highlight a couple of example use cases of new functionality, including: - An introduction to the Swordfish DNA Storage Model, including a live demo - The latest in NVMe Manageability Join this session to learn how to get started with Swordfish.

Richelle Ahlvers

SM Chair, SNIA Vice Chair, and Swordfish TWG Chair ------- Director of Ecosystem Enabling and Technology Initiatives

SNIA ------------ Intel

The Grand Unified File Index (GUFI) is a toolset built upon established technologies that helps manage massive amounts of filesystem metadata, which is becoming more and more important as the amount of data needing to be managed grows. GUFI provides powerful query capabilities via SQL that far surpass those provided by standard POSIX tools such as find, ls, and stat. GUFI provides results much faster than POSIX tools by virtue of running in parallel rather than being single threaded. GUFI allows for both filesystem administrators and users to query the same index without loss of security. All of this capability is available to all filesystems that are accessible via the POSIX filesystem interface (or can be mapped to it), removing the requirement of users needing to be experts with filesystem specific tools. In addition to general improvements to the codebase, recent developments have introduced a series of features that, when combined, makes GUFI a swiss army knife for data (in addition to metadata) processing while maintaining need-to-know: exposing GUFI trees as single tables via the SQLite virtual table mechanism allowing for SQLAlchemy to access GUFI trees, the ability to run arbitrary commands to return results as both individual values as well as whole tables, and the addition of SQLite-native vector embedding generation and tables allowing for nearest neighbor searches of user data. These additions have turned GUFI from a command line only tool to a full stack tool with powerful features also usable from fully featured front end GUIs. LA-UR-25-24971

Jason Lee

Scientist

Los Alamos National Laboratory