Twizzler: A Data-centric OS for Non-volatile Memory

Author:

Bittman Daniel1ORCID,Alvaro Peter2,Mehra Pankaj3,Long Darrell D. E.2,Miller Ethan L.4

Affiliation:

1. UC Santa Cruz, USA

2. UC Santa Cruz, Santa Cruz, USA

3. IEEE Member, USA

4. UC Santa Cruz, USA and Pure Storage, Santa Cruz, CA, Pure Storage, CA, USA

Abstract

Byte-addressable, non-volatile memory (NVM) presents an opportunity to rethink the entire system stack. We present Twizzler, an operating system redesign for this near-future. Twizzler removes the kernel from the I/O path, provides programs with memory-style access to persistent data using small (64 bit), object-relative cross-object pointers, and enables simple and efficient long-term sharing of data both between applications and between runs of an application. Twizzler provides a clean-slate programming model for persistent data, realizing the vision of Unix in a world of persistent RAM. We show that Twizzler is simpler, more extensible, and more secure than existing I/O models and implementations by building software for Twizzler and evaluating it on NVM DIMMs. Most persistent pointer operations in Twizzler impose less than 0.5 ns added latency. Twizzler operations are up to faster than Unix , and SQLite queries are up to faster than on PMDK. YCSB workloads ran 1.1– faster on Twizzler than on native and NVM-optimized SQLite backends.

Funder

National Science Foundation

Intel Corporation

UCSC Center for Research in Storage Systems

Publisher

Association for Computing Machinery (ACM)

Subject

Hardware and Architecture

Reference69 articles.

1. [n.d.]. The musl C Library. Retrieved from https://musl.libc.org/. [n.d.]. The musl C Library. Retrieved from https://musl.libc.org/.

2. [n.d.]. The Rust Programming Language. Retrieved from https://www.rust-lang.org/. [n.d.]. The Rust Programming Language. Retrieved from https://www.rust-lang.org/.

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Enabling Efficient NVM-Based Text Analytics without Decompression;2024 IEEE 40th International Conference on Data Engineering (ICDE);2024-05-13

2. Taming Memory With Disaggregation;Computer;2022-09

3. PMLiteDB: Streamlining Access Paths for High-Performance Persistent Memory Document Database Systems;IEEE Transactions on Computers;2022

4. Empirical Analysis of Architectural Primitives for NVRAM Consistency;2021 IEEE 28th International Conference on High Performance Computing, Data, and Analytics (HiPC);2021-12

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3