.png){kind=icon}
.png){kind=icon}
Return
Containerized In-Storage Processing and Computing-Enabled Solid-State Drive Disaggregation
.png){kind=icon}
PRE
AI
DOI：10.1109/MM.2025.3574261.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In-storage processing (ISP) minimizes data transfer for analytics but faces challenges in adaptation and disaggregation. We propose DockerSSD, an ISP model that leverages operating system-level virtualization and lightweight firmware to enable containerized data processing directly on solid-state devices. The key features include Ethernet over Non-volatile Memory Express 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 large language model (LLM) inference. It achieves up to 2x better performance for input-output-intensive workloads, and 7.9x improvement in distributed LLM inference.
Keywords:
Microprogramming
Containers
Kernel
Ethernet
Nonvolatile memory
Computational modeling
Virtualization
Runtime
Media
Training
Journal
IF:
2.9
Papers:
125
Citations:
2.7K