Siglm: Signature-driven load management for cloud computing infrastructures

Zhenhuan Gong, Prakash Ramaswamy, Xiaohui Gu, Xiaosong Ma

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

13 Citations (Scopus)

Abstract

Cloud computing has emerged as a promising platform that grants users with direct yet shared access to computing resources and services without worrying about the internal complex infrastructure. Unlike traditional batch service model, cloud service model adopts a pay-as-you-go form, which demands explicit and precise resource control. In this paper, we present SigLM, a novel Signature-driven Load Management system to achieve quality-aware service delivery in shared cloud computing infrastructures. SigLM dynamically captures fine-grained signatures of different application tasks and cloud nodes using time series patterns, and performs precise resource metering and allocation based on the extracted signatures. SigLM employs dynamic time warping algorithm and multi-dimensional time series indexing to achieve efficient signature pattern matching. Our experiments using real load traces collected on the PlanetLab show that SigLM can improve resource provisioning performance by 30-80% compared to existing approaches. SigLM is scalable and efficient, which imposes less than 1% overhead to the system and can perform signature matching within tens of milliseconds.

Original languageEnglish
Title of host publicationIEEE International Workshop on Quality of Service, IWQoS
DOIs
Publication statusPublished - 20 Nov 2009
Externally publishedYes
Event2009 17th International Workshop on Quality of Service, IWQoS 2009 - Charleston, SC, United States
Duration: 13 Jul 200915 Jul 2009

Other

Other2009 17th International Workshop on Quality of Service, IWQoS 2009
CountryUnited States
CityCharleston, SC
Period13/7/0915/7/09

Fingerprint

Cloud computing
Time series
Pattern matching
Experiments

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Gong, Z., Ramaswamy, P., Gu, X., & Ma, X. (2009). Siglm: Signature-driven load management for cloud computing infrastructures. In IEEE International Workshop on Quality of Service, IWQoS [5201413] https://doi.org/10.1109/IWQoS.2009.5201413

Siglm : Signature-driven load management for cloud computing infrastructures. / Gong, Zhenhuan; Ramaswamy, Prakash; Gu, Xiaohui; Ma, Xiaosong.

IEEE International Workshop on Quality of Service, IWQoS. 2009. 5201413.

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

Gong, Z, Ramaswamy, P, Gu, X & Ma, X 2009, Siglm: Signature-driven load management for cloud computing infrastructures. in IEEE International Workshop on Quality of Service, IWQoS., 5201413, 2009 17th International Workshop on Quality of Service, IWQoS 2009, Charleston, SC, United States, 13/7/09. https://doi.org/10.1109/IWQoS.2009.5201413
Gong Z, Ramaswamy P, Gu X, Ma X. Siglm: Signature-driven load management for cloud computing infrastructures. In IEEE International Workshop on Quality of Service, IWQoS. 2009. 5201413 https://doi.org/10.1109/IWQoS.2009.5201413
Gong, Zhenhuan ; Ramaswamy, Prakash ; Gu, Xiaohui ; Ma, Xiaosong. / Siglm : Signature-driven load management for cloud computing infrastructures. IEEE International Workshop on Quality of Service, IWQoS. 2009.
@inproceedings{c49c92c1e33c46ba96ab35a22703263e,
title = "Siglm: Signature-driven load management for cloud computing infrastructures",
abstract = "Cloud computing has emerged as a promising platform that grants users with direct yet shared access to computing resources and services without worrying about the internal complex infrastructure. Unlike traditional batch service model, cloud service model adopts a pay-as-you-go form, which demands explicit and precise resource control. In this paper, we present SigLM, a novel Signature-driven Load Management system to achieve quality-aware service delivery in shared cloud computing infrastructures. SigLM dynamically captures fine-grained signatures of different application tasks and cloud nodes using time series patterns, and performs precise resource metering and allocation based on the extracted signatures. SigLM employs dynamic time warping algorithm and multi-dimensional time series indexing to achieve efficient signature pattern matching. Our experiments using real load traces collected on the PlanetLab show that SigLM can improve resource provisioning performance by 30-80{\%} compared to existing approaches. SigLM is scalable and efficient, which imposes less than 1{\%} overhead to the system and can perform signature matching within tens of milliseconds.",
author = "Zhenhuan Gong and Prakash Ramaswamy and Xiaohui Gu and Xiaosong Ma",
year = "2009",
month = "11",
day = "20",
doi = "10.1109/IWQoS.2009.5201413",
language = "English",
isbn = "9781424438761",
booktitle = "IEEE International Workshop on Quality of Service, IWQoS",

}

TY - GEN

T1 - Siglm

T2 - Signature-driven load management for cloud computing infrastructures

AU - Gong, Zhenhuan

AU - Ramaswamy, Prakash

AU - Gu, Xiaohui

AU - Ma, Xiaosong

PY - 2009/11/20

Y1 - 2009/11/20

N2 - Cloud computing has emerged as a promising platform that grants users with direct yet shared access to computing resources and services without worrying about the internal complex infrastructure. Unlike traditional batch service model, cloud service model adopts a pay-as-you-go form, which demands explicit and precise resource control. In this paper, we present SigLM, a novel Signature-driven Load Management system to achieve quality-aware service delivery in shared cloud computing infrastructures. SigLM dynamically captures fine-grained signatures of different application tasks and cloud nodes using time series patterns, and performs precise resource metering and allocation based on the extracted signatures. SigLM employs dynamic time warping algorithm and multi-dimensional time series indexing to achieve efficient signature pattern matching. Our experiments using real load traces collected on the PlanetLab show that SigLM can improve resource provisioning performance by 30-80% compared to existing approaches. SigLM is scalable and efficient, which imposes less than 1% overhead to the system and can perform signature matching within tens of milliseconds.

AB - Cloud computing has emerged as a promising platform that grants users with direct yet shared access to computing resources and services without worrying about the internal complex infrastructure. Unlike traditional batch service model, cloud service model adopts a pay-as-you-go form, which demands explicit and precise resource control. In this paper, we present SigLM, a novel Signature-driven Load Management system to achieve quality-aware service delivery in shared cloud computing infrastructures. SigLM dynamically captures fine-grained signatures of different application tasks and cloud nodes using time series patterns, and performs precise resource metering and allocation based on the extracted signatures. SigLM employs dynamic time warping algorithm and multi-dimensional time series indexing to achieve efficient signature pattern matching. Our experiments using real load traces collected on the PlanetLab show that SigLM can improve resource provisioning performance by 30-80% compared to existing approaches. SigLM is scalable and efficient, which imposes less than 1% overhead to the system and can perform signature matching within tens of milliseconds.

UR - http://www.scopus.com/inward/record.url?scp=70449602378&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449602378&partnerID=8YFLogxK

U2 - 10.1109/IWQoS.2009.5201413

DO - 10.1109/IWQoS.2009.5201413

M3 - Conference contribution

AN - SCOPUS:70449602378

SN - 9781424438761

BT - IEEE International Workshop on Quality of Service, IWQoS

ER -