English

Vilamb: Low Overhead Asynchronous Redundancy for Direct Access NVM

Operating Systems 2020-04-22 v1

Abstract

Vilamb provides efficient asynchronous systemredundancy for direct access (DAX) non-volatile memory (NVM) storage. Production storage deployments often use system-redundancy in form of page checksums and cross-page parity. State-of-the-art solutions for maintaining system-redundancy for DAX NVM either incur a high performance overhead or require specialized hardware. The Vilamb user-space library maintains system-redundancy with low overhead by delaying and amortizing the system-redundancy updates over multiple data writes. As a result, Vilamb provides 3--5x the throughput of the state-of-the-art software solution at high operation rates. For applications that need system-redundancy with high performance, and can tolerate some delaying of data redundancy, Vilamb provides a tunable knob between performance and quicker redundancy. Even with the delayed coverage, Vilamb increases the mean time to data loss due to firmware-induced corruptions by up to two orders of magnitude in comparison to maintaining no system-redundancy.

Keywords

Cite

@article{arxiv.2004.09619,
  title  = {Vilamb: Low Overhead Asynchronous Redundancy for Direct Access NVM},
  author = {Rajat Kateja and Andy Pavlo and Gregory R. Ganger},
  journal= {arXiv preprint arXiv:2004.09619},
  year   = {2020}
}
R2 v1 2026-06-23T14:58:52.843Z