Containerized In-Storage Processing and Computing-Enabled SSD Disaggregation
By: Miryeong Kwon , Donghyun Gouk , Eunjee Na and more
Potential Business Impact:
Makes computers faster by processing data on storage.
ISP minimizes data transfer for analytics but faces challenges in adaptation and disaggregation. We propose DockerSSD, an ISP model leveraging OS-level virtualization and lightweight firmware to enable containerized data processing directly on SSDs. Key features include Ethernet over NVMe for network-based ISP management and Virtual Firmware for secure, efficient container execution. DockerSSD supports disaggregated storage pools, reducing host overhead and enhancing large-scale services like LLM inference. It achieves up to 2.0x better performance for I/O-intensive workloads, and 7.9x improvement in distributed LLM inference.
Similar Papers
IDSS, a Novel P2P Relational Data Storage Service
Databases
Stores huge amounts of information faster and better.
Revisiting Computational Storage for Data Integrity and Security
Distributed, Parallel, and Cluster Computing
Puts computers inside storage to speed things up.
Intent-Driven Storage Systems: From Low-Level Tuning to High-Level Understanding
Hardware Architecture
Helps computers store data smarter using AI.