Validate the I/O completion framework across broader storage conditions

Validate the device-completion model and cross-layer wait-chain analysis across more SSDs, mixed read/write workloads, and shared-device interference scenarios.

Background

The paper develops a host-visible device-completion model based on first-completion wait and finite-batch completion capacity, and connects it to upper-layer waiting through folio--bio--request mappings. Its empirical validation is concentrated on a limited set of SSD configurations and controlled read workloads. The authors explicitly identify broader validation across heterogeneous devices, mixed workloads, and contention from shared-device use as unresolved future work.

Extending the evaluation to these settings would test whether the calibrated completion parameters and cross-layer predictions remain reliable when read and write traffic interact, multiple tenants compete for device resources, and device characteristics vary beyond the measured platforms.

References

Our real-device evidence is currently concentrated on a limited number of SSDs and controlled read workloads; validation across more devices, mixed read/write workloads, and shared-device interference remains future work.

— Behind a Simple Read: Understanding Work and Waiting in the Linux I/O Stack  (2610.10137 - Shen et al., 7 Oct 2026) in Section 8, Discussion and Limitations