R&D: Containerized In-Storage Processing and Computing-Enabled SSD Disaggregation

IEEE Micro has published an article written by Miryeong Kwon, Donghyun Gouk, Eunjee Na, Jiseon Kim, Junhee Kim, Hyein Woo, Eojin Ryu, Hyunkyu Choi, Jinwoo Baek, Hanyeoreum Bae, Next-Generation Silicon and Research Division, Panmnesia, Inc., Daejeon, South Korea, Mahmut Kandemir, Pennsylvania State University, Pennsylvania, United States, and Myoungsoo Jung, Next-Generation Silicon and Research Division, Panmnesia, Inc., Daejeon, South Korea, KAIST, Daejeon, South Korea, and Advanced Product Engineering Division, Panmnesia, Inc., Seoul, South Korea.

Abstract: “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.“