Containerized In-Storage Processing and Computing-Enabled Solid-State Drive Disaggregation
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 2.0× better performance for I/O-intensive workloads, and 7.9× improvement in distributed LLM inference.
Authors
- Honguk Woo (ORCID: https://orcid.org/0000-0001-6948-3440)
- Hanyeoreum Bae (ORCID: https://orcid.org/0000-0002-0946-9986)
- Mahmut Kandemir (ORCID: https://orcid.org/0000-0002-9940-9951)
- Donghyun Gouk (ORCID: https://orcid.org/0000-0002-4229-0101)
- Junhee Kim
- Miryeong Kwon (ORCID: https://orcid.org/0000-0002-0313-1319)
- Myoungsoo Jung (ORCID: https://orcid.org/0000-0002-9832-5801)
- Jiseon Kim (ORCID: https://orcid.org/0000-0002-8143-3363)
- Hyunkyu Choi (ORCID: https://orcid.org/0009-0001-6693-6720)
- Jinwoo Baek
- Eunjee Na
- Eojin Ryu
Institutions
- Pennsylvania State University (US)
- College of Micronesia-FSM (FM)
Publication Details
- Journal
- IEEE Micro
- Published
- 2025-05-30
- DOI
- https://doi.org/10.1109/mm.2025.3574261
- Citations
- 1
- Primary Topic
- Advanced Data Storage Technologies
- Type
- article
- Field-Weighted Citation Impact
- 1.49