WIO: Upload-Enabled Computational Storage on CXL SSDs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915911783415808 |
|---|---|
| author | Yang, Yiwei Hu, Yanpeng Zheng, Yusheng Ramos, Estabon Su, Jianchang Quinn, Andi Zhang, Wei |
| author_facet | Yang, Yiwei Hu, Yanpeng Zheng, Yusheng Ramos, Estabon Su, Jianchang Quinn, Andi Zhang, Wei |
| contents | The widening gap between processor speed and storage latency has made data movement a dominant bottleneck in modern systems. Two lines of storage-layer innovation attempted to close this gap: persistent memory shortened the latency hierarchy, while computational storage devices pushed processing toward the data. Neither has displaced conventional NVMe SSDs at scale, largely due to programming complexity, ecosystem fragmentation, and thermal/power cliffs under sustained load. We argue that storage-side compute should be \emph{reversible}: computation should migrate dynamically between host and device based on runtime conditions. We present \sys, which realizes this principle on CXL SSDs by decomposing I/O-path logic into migratable \emph{storage actors} compiled to WebAssembly. Actors share state through coherent CXL.mem regions; an agility-aware scheduler migrates them via a zero-copy drain-and-switch protocol when thermal or power constraints arise. Our evaluation on an FPGA-based CXL SSD prototype and two production CSDs shows that \sys turns hard thermal cliffs into elastic trade-offs, achieving up to 2$\times$ throughput improvement and 3.75$\times$ write latency reduction without application modification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02442 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WIO: Upload-Enabled Computational Storage on CXL SSDs Yang, Yiwei Hu, Yanpeng Zheng, Yusheng Ramos, Estabon Su, Jianchang Quinn, Andi Zhang, Wei Operating Systems The widening gap between processor speed and storage latency has made data movement a dominant bottleneck in modern systems. Two lines of storage-layer innovation attempted to close this gap: persistent memory shortened the latency hierarchy, while computational storage devices pushed processing toward the data. Neither has displaced conventional NVMe SSDs at scale, largely due to programming complexity, ecosystem fragmentation, and thermal/power cliffs under sustained load. We argue that storage-side compute should be \emph{reversible}: computation should migrate dynamically between host and device based on runtime conditions. We present \sys, which realizes this principle on CXL SSDs by decomposing I/O-path logic into migratable \emph{storage actors} compiled to WebAssembly. Actors share state through coherent CXL.mem regions; an agility-aware scheduler migrates them via a zero-copy drain-and-switch protocol when thermal or power constraints arise. Our evaluation on an FPGA-based CXL SSD prototype and two production CSDs shows that \sys turns hard thermal cliffs into elastic trade-offs, achieving up to 2$\times$ throughput improvement and 3.75$\times$ write latency reduction without application modification. |
| title | WIO: Upload-Enabled Computational Storage on CXL SSDs |
| topic | Operating Systems |
| url | https://arxiv.org/abs/2604.02442 |