Achieving Elasticity for Cloud MapReduce Jobs

Khaled Salah, Jose Alcaraz Calero

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

These days, both the cloud computing paradigm and MapReduce programming framework have become key enablers for running big data analytics and large-scale compute-and data-intensive applications. Achieving proper elasticity for cloud MapReduce jobs is a critical research problem that has been overlooked. In this paper, we focus on how to achieve proper elasticity for MapReduce jobs when executed on cloud clusters. In particular, we present an analytical queueing model that can be used to determine at any given time and under different workload conditions the minimal number of mappers and reducers needed to satisfy the Service Level Objective (SLO) response time.
Original languageEnglish
Title of host publicationPROCEEDINGS OF THE 2013 IEEE 2ND INTERNATIONAL CONFERENCE ON CLOUD NETWORKING (CLOUDNET)
EditorsX Fu, P Sharma, D Huang, D Medhi
PublisherIEEE
Pages195-199
ISBN (Print)978-1-4799-0568-3
DOIs
Publication statusPublished - 2013

Publication series

NameIEEE International Conference on Cloud Networking
PublisherIEEE
ISSN (Print)2374-3239

Keywords

  • MapReduce
  • Cloud Computing
  • Elasticity
  • Netwrok and Sevice Delays
  • Queueing Analysis
  • Performance

Cite this

Salah, K., & Alcaraz Calero, J. (2013). Achieving Elasticity for Cloud MapReduce Jobs. In X. Fu, P. Sharma, D. Huang, & D. Medhi (Eds.), PROCEEDINGS OF THE 2013 IEEE 2ND INTERNATIONAL CONFERENCE ON CLOUD NETWORKING (CLOUDNET) (pp. 195-199). (IEEE International Conference on Cloud Networking). IEEE. https://doi.org/10.1109/CloudNet.2013.6710577
Salah, Khaled ; Alcaraz Calero, Jose. / Achieving Elasticity for Cloud MapReduce Jobs. PROCEEDINGS OF THE 2013 IEEE 2ND INTERNATIONAL CONFERENCE ON CLOUD NETWORKING (CLOUDNET). editor / X Fu ; P Sharma ; D Huang ; D Medhi. IEEE, 2013. pp. 195-199 (IEEE International Conference on Cloud Networking).
@inproceedings{bd373680997f45a8ace0e94960039dff,
title = "Achieving Elasticity for Cloud MapReduce Jobs",
abstract = "These days, both the cloud computing paradigm and MapReduce programming framework have become key enablers for running big data analytics and large-scale compute-and data-intensive applications. Achieving proper elasticity for cloud MapReduce jobs is a critical research problem that has been overlooked. In this paper, we focus on how to achieve proper elasticity for MapReduce jobs when executed on cloud clusters. In particular, we present an analytical queueing model that can be used to determine at any given time and under different workload conditions the minimal number of mappers and reducers needed to satisfy the Service Level Objective (SLO) response time.",
keywords = "MapReduce, Cloud Computing, Elasticity, Netwrok and Sevice Delays, Queueing Analysis, Performance",
author = "Khaled Salah and {Alcaraz Calero}, Jose",
note = "Conference: 2nd IEEE International Conference on Cloud Networking (CloudNet) Location: San Francisco, CA Date: NOV 11-13, 2013 Sponsor(s):IEEE; IEEE Commun Soc; IEEE Cloud Comp; UMKC, Sch Comp & Engn",
year = "2013",
doi = "10.1109/CloudNet.2013.6710577",
language = "English",
isbn = "978-1-4799-0568-3",
series = "IEEE International Conference on Cloud Networking",
publisher = "IEEE",
pages = "195--199",
editor = "X Fu and P Sharma and D Huang and D Medhi",
booktitle = "PROCEEDINGS OF THE 2013 IEEE 2ND INTERNATIONAL CONFERENCE ON CLOUD NETWORKING (CLOUDNET)",
address = "United States",

}

Salah, K & Alcaraz Calero, J 2013, Achieving Elasticity for Cloud MapReduce Jobs. in X Fu, P Sharma, D Huang & D Medhi (eds), PROCEEDINGS OF THE 2013 IEEE 2ND INTERNATIONAL CONFERENCE ON CLOUD NETWORKING (CLOUDNET). IEEE International Conference on Cloud Networking, IEEE, pp. 195-199. https://doi.org/10.1109/CloudNet.2013.6710577

Achieving Elasticity for Cloud MapReduce Jobs. / Salah, Khaled; Alcaraz Calero, Jose.

PROCEEDINGS OF THE 2013 IEEE 2ND INTERNATIONAL CONFERENCE ON CLOUD NETWORKING (CLOUDNET). ed. / X Fu; P Sharma; D Huang; D Medhi. IEEE, 2013. p. 195-199 (IEEE International Conference on Cloud Networking).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Achieving Elasticity for Cloud MapReduce Jobs

AU - Salah, Khaled

AU - Alcaraz Calero, Jose

N1 - Conference: 2nd IEEE International Conference on Cloud Networking (CloudNet) Location: San Francisco, CA Date: NOV 11-13, 2013 Sponsor(s):IEEE; IEEE Commun Soc; IEEE Cloud Comp; UMKC, Sch Comp & Engn

PY - 2013

Y1 - 2013

N2 - These days, both the cloud computing paradigm and MapReduce programming framework have become key enablers for running big data analytics and large-scale compute-and data-intensive applications. Achieving proper elasticity for cloud MapReduce jobs is a critical research problem that has been overlooked. In this paper, we focus on how to achieve proper elasticity for MapReduce jobs when executed on cloud clusters. In particular, we present an analytical queueing model that can be used to determine at any given time and under different workload conditions the minimal number of mappers and reducers needed to satisfy the Service Level Objective (SLO) response time.

AB - These days, both the cloud computing paradigm and MapReduce programming framework have become key enablers for running big data analytics and large-scale compute-and data-intensive applications. Achieving proper elasticity for cloud MapReduce jobs is a critical research problem that has been overlooked. In this paper, we focus on how to achieve proper elasticity for MapReduce jobs when executed on cloud clusters. In particular, we present an analytical queueing model that can be used to determine at any given time and under different workload conditions the minimal number of mappers and reducers needed to satisfy the Service Level Objective (SLO) response time.

KW - MapReduce

KW - Cloud Computing

KW - Elasticity

KW - Netwrok and Sevice Delays

KW - Queueing Analysis

KW - Performance

U2 - 10.1109/CloudNet.2013.6710577

DO - 10.1109/CloudNet.2013.6710577

M3 - Conference contribution

SN - 978-1-4799-0568-3

T3 - IEEE International Conference on Cloud Networking

SP - 195

EP - 199

BT - PROCEEDINGS OF THE 2013 IEEE 2ND INTERNATIONAL CONFERENCE ON CLOUD NETWORKING (CLOUDNET)

A2 - Fu, X

A2 - Sharma, P

A2 - Huang, D

A2 - Medhi, D

PB - IEEE

ER -

Salah K, Alcaraz Calero J. Achieving Elasticity for Cloud MapReduce Jobs. In Fu X, Sharma P, Huang D, Medhi D, editors, PROCEEDINGS OF THE 2013 IEEE 2ND INTERNATIONAL CONFERENCE ON CLOUD NETWORKING (CLOUDNET). IEEE. 2013. p. 195-199. (IEEE International Conference on Cloud Networking). https://doi.org/10.1109/CloudNet.2013.6710577