DBOS: a DBMS-oriented operating system

Athinagoras Skiadopoulos; Qian Li; Peter Kraft; Kostis Kaffes; Daniel Hong; Shana Mathew; David Bestor; Michael Cafarella; Vijay Gadepally; Goetz Graefe; Jeremy Kepner; Christos Kozyrakis; Tim Kraska; Michael Stonebraker; Lalith Suresh; Matei Zaharia

doi:10.14778/3485450.3485454

DBOS: a DBMS-oriented operating system

Athinagoras Skiadopoulos Stanford

Qian Li Stanford

Peter Kraft Stanford

Kostis Kaffes Stanford

Daniel Hong MIT

Shana Mathew MIT

David Bestor MIT

Michael Cafarella MIT

Vijay Gadepally MIT

Goetz Graefe Google

Jeremy Kepner MIT

Christos Kozyrakis Stanford

Tim Kraska MIT

Michael Stonebraker MIT

Lalith Suresh VMware

Matei Zaharia Stanford

The International Journal on Very Large Data Bases (VLDB), 2021

DOI: 10.14778/3485450.3485454

Abstract

This paper presents the rationale and initial implementation results for DBOS, a database-oriented operating system architecture for scalable cluster computing. Instead of combining a traditional single-node OS with separate cluster schedulers, distributed file systems, and network managers, DBOS uses a distributed transactional DBMS as the foundation for scheduling, file management, inter-process communication, analytics, and high availability.

Materials

Bibtex

@inproceedings{2021dbosaproposalforadatacentricoperatingsystem,
  title = {DBOS: a DBMS-oriented operating system},
  author = {Athinagoras Skiadopoulos and Qian Li and Peter Kraft and Kostis Kaffes and Daniel Hong and Shana Mathew and David Bestor and Michael Cafarella and Vijay Gadepally and Goetz Graefe and Jeremy Kepner and Christos Kozyrakis and Tim Kraska and Michael Stonebraker and Lalith Suresh and Matei Zaharia},
  booktitle = {The International Journal on Very Large Data Bases (VLDB)},
  year = {2021},
  doi = {10.14778/3485450.3485454},
}

Hi, we are the Stanford MAST team

DBOS: a DBMS-oriented operating system

Abstract

Materials

Bibtex