OffloadFS: Leveraging Disaggregated Storage for Computation Offloading

2026-04-15

AI Summary

This work addresses the low computational resource utilization and inefficiency in I/O-intensive tasks inherent in traditional disaggregated storage systems by proposing OffloadFS, a user-space file system built upon NVMe over Fabrics. OffloadFS is the first to enable near-data task offloading without requiring distributed locks in a disaggregated storage architecture. It supports flexible cross-node scheduling and mitigates multi-threaded I/O cache interference through optimized design, effectively offloading tasks such as MemTable flushes, compaction, and image preprocessing. Experimental results demonstrate that, compared to OCFS2, OffloadFS achieves up to a 3.36× performance improvement for RocksDB and accelerates machine learning image preprocessing by up to 1.85×.

Technology Category

• Search and Optimization: Distributed Search
• Machine Learning: Hardware-aware ML
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Disaggregated storage systems improve resource utilization and enable independent scaling of storage and compute resources by separating storage resources from computing resources in data centers. NVMe over fabrics (NVMeoF) is a key technology that underpins the functionality and benefits of disaggregated storage systems. While NVMeoF inherently possesses substantial computing and memory capacity, these resources are often underutilized for tasks beyond simple I/O delegation. This study proposes OffloadFS, a user-level file system that enables offloaded IO-intensive tasks primarily to a disaggregated storage node for near-data processing, with the option to offload to peer compute nodes as well, without the need for distributed lock management. OffloadFS optimizes cache management by reducing interference between threads performing distinct I/O operations. On top of OffloadFS, we develop OffloadDB, which enables RocksDB to offload MemTable flush and compaction operations, and OffloadPrep, which offloads image pre-processing tasks for machine learning to disaggregated storage nodes. Our evaluation shows that OffloadFS improves the performance of RocksDB and machine learning pre-processing tasks by up to 3.36x and 1.85x, respectively, compared to OCFS2.

Problem

• disaggregated storage
• computation offloading
• NVMe over Fabrics
• I/O-intensive tasks
• near-data processing

Innovation

• Disaggregated Storage
• Computation Offloading
• NVMe over Fabrics
• Near-Data Processing
• User-Level File System