ioflow · research

IOFlow

IOFlow is a research architecture that exposes storage-stage queues to a logically centralized controller for end-to-end I/O policies.

The controller maps high-level flows onto stage queues with service and routing controls. Storage tokens represent operation cost, not simply request-header bytes. [1]

Its Windows prototype inserts drivers around SMB stages without requiring application or VM changes. Requests already inside an uncontrolled device remain outside its priority decisions; limiting outstanding work retains more scheduling choice upstream. [1]

For evaluation, name the enforcement stage, operation-cost model and outstanding-request boundary. A configured rate alone does not establish application tail latency.

Relations

related
sRoute, I/O scheduler, mClock, Queue depth

Advantages

  • A controller can coordinate policies across several storage stages. [1]

Limitations

  • Priority enforcement depends on where contention occurs and which stages expose control. [1]

Citations

  1. Thereska et al. IOFlow: A Software-Defined Storage Architecture. SOSP 2013, sections 3.1, 4.1 and 5; DOI 10.1145/2517349.2522723. (accessed 2026-11-19)
Sources & caveats
  • Primary-paper architecture review; no prototype execution or contemporary performance measurement.

JSON: /data/terms/ioflow.json

Published by Hesela team · Updated

Report a correction · Editorial standards · Reuse guidance

Cite this page
Hesela team. IOFlow. Hesela. 2026-11-19. https://hesela.dev/terms/ioflow/