Standard

Subordination: Cluster management without distributed consensus. / Gankevich, I.; Tipikin, Y.; Gaiduchok, V.

Proceedings of International Conference on High Performance Computing & Simulation (HPCS), 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 639-642.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research

Harvard

Gankevich, I, Tipikin, Y & Gaiduchok, V 2015, Subordination: Cluster management without distributed consensus. in Proceedings of International Conference on High Performance Computing & Simulation (HPCS), 2015. Institute of Electrical and Electronics Engineers Inc., pp. 639-642. https://doi.org/10.1109/HPCSim.2015.7237106

APA

Gankevich, I., Tipikin, Y., & Gaiduchok, V. (2015). Subordination: Cluster management without distributed consensus. In Proceedings of International Conference on High Performance Computing & Simulation (HPCS), 2015 (pp. 639-642). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HPCSim.2015.7237106

Vancouver

Gankevich I, Tipikin Y, Gaiduchok V. Subordination: Cluster management without distributed consensus. In Proceedings of International Conference on High Performance Computing & Simulation (HPCS), 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 639-642 https://doi.org/10.1109/HPCSim.2015.7237106

Author

Gankevich, I. ; Tipikin, Y. ; Gaiduchok, V. / Subordination: Cluster management without distributed consensus. Proceedings of International Conference on High Performance Computing & Simulation (HPCS), 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 639-642

BibTeX

@inproceedings{b63ecb7a89974357b576abc7e0288793,
title = "Subordination: Cluster management without distributed consensus",
abstract = "Nowadays, many cluster management systems rely on distributed consensus algorithms to elect a leader that orchestrates subordinate nodes. Contrary to these studies we propose consensus-free algorithm that arranges cluster nodes into multiple levels of subordination. The algorithm structures IP address range of cluster network so that each node has ranked list of candidates, from which it chooses a leader. The results show that this approach easily scales to a large number of nodes due to its asynchronous nature, and enables fast recovery from node failures as they occur only on one level of hierarchy. Multiple levels of subordination are useful for efficiently collecting monitoring and accounting data from large number of nodes, and for scheduling general-purpose tasks on a cluster.",
author = "I. Gankevich and Y. Tipikin and V. Gaiduchok",
year = "2015",
doi = "10.1109/HPCSim.2015.7237106",
language = "English",
isbn = "9781467378123",
pages = "639--642",
booktitle = "Proceedings of International Conference on High Performance Computing & Simulation (HPCS), 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

RIS

TY - GEN

T1 - Subordination: Cluster management without distributed consensus

AU - Gankevich, I.

AU - Tipikin, Y.

AU - Gaiduchok, V.

PY - 2015

Y1 - 2015

N2 - Nowadays, many cluster management systems rely on distributed consensus algorithms to elect a leader that orchestrates subordinate nodes. Contrary to these studies we propose consensus-free algorithm that arranges cluster nodes into multiple levels of subordination. The algorithm structures IP address range of cluster network so that each node has ranked list of candidates, from which it chooses a leader. The results show that this approach easily scales to a large number of nodes due to its asynchronous nature, and enables fast recovery from node failures as they occur only on one level of hierarchy. Multiple levels of subordination are useful for efficiently collecting monitoring and accounting data from large number of nodes, and for scheduling general-purpose tasks on a cluster.

AB - Nowadays, many cluster management systems rely on distributed consensus algorithms to elect a leader that orchestrates subordinate nodes. Contrary to these studies we propose consensus-free algorithm that arranges cluster nodes into multiple levels of subordination. The algorithm structures IP address range of cluster network so that each node has ranked list of candidates, from which it chooses a leader. The results show that this approach easily scales to a large number of nodes due to its asynchronous nature, and enables fast recovery from node failures as they occur only on one level of hierarchy. Multiple levels of subordination are useful for efficiently collecting monitoring and accounting data from large number of nodes, and for scheduling general-purpose tasks on a cluster.

U2 - 10.1109/HPCSim.2015.7237106

DO - 10.1109/HPCSim.2015.7237106

M3 - Conference contribution

SN - 9781467378123

SP - 639

EP - 642

BT - Proceedings of International Conference on High Performance Computing & Simulation (HPCS), 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

ID: 3943793