Fuzzy modeling based resource management for virtualized database systems

Lixi Wang, Jing Xu, Ming Zhao, Yicheng Tu, José A B Fortes

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

28 Citations (Scopus)

Abstract

The hosting of databases on virtual machines (VMs) has great potential to improve the efficiency of resource utilization and the ease of deployment of database systems. This paper considers the problem of on-demand allocation of resources to a VM running a database serving dynamic and complex query workloads while meeting QoS (Quality of Service) requirements. An autonomic resource-management approach is proposed to address this problem. It uses adaptive fuzzy modeling to capture the behavior of a VM hosting a database with dynamically changing workloads and to predict its multi-type resource needs. A prototype of the proposed approach is implemented on Xen-based VMs and evaluated using workloads based on TPC-H and RUBiS. The results demonstrate that CPU and disk I/O bandwidth can be efficiently allocated to database VMs serving workloads with dynamically changing intensity and composition while meeting QoS targets. For TPC-H-based experiments, the resulting throughput is within 89.5 - 100% of what would be obtained using resource allocation based on peak loads, For RUBiS, the response time target (set based on the performance under peak-load-based allocation) is met for 97% of the time. Moreover, substantial resources are saved (about 62.6% of CPU and 76.5% of disk I/O bandwidth) in comparison to peak-load-based allocation.

Original languageEnglish (US)
Title of host publicationIEEE International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems - Proceedings
Pages32-42
Number of pages11
DOIs
StatePublished - 2011
Externally publishedYes
Event19th Annual IEEE/ACM International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2011 - Singapore, Singapore
Duration: Jul 25 2011Jul 27 2011

Other

Other19th Annual IEEE/ACM International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2011
CountrySingapore
CitySingapore
Period7/25/117/27/11

Fingerprint

Fuzzy Modeling
Virtual Machine
Database Systems
Resource Management
Workload
Resources
Quality of Service
Program processors
Quality of service
Bandwidth
Multitype
Target
Resource Allocation
Response Time
Resource allocation
Throughput
Virtual machine
Prototype
Query
Predict

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Information Systems
  • Modeling and Simulation

Cite this

Wang, L., Xu, J., Zhao, M., Tu, Y., & Fortes, J. A. B. (2011). Fuzzy modeling based resource management for virtualized database systems. In IEEE International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems - Proceedings (pp. 32-42). [6005366] https://doi.org/10.1109/MASCOTS.2011.70

Fuzzy modeling based resource management for virtualized database systems. / Wang, Lixi; Xu, Jing; Zhao, Ming; Tu, Yicheng; Fortes, José A B.

IEEE International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems - Proceedings. 2011. p. 32-42 6005366.

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

Wang, L, Xu, J, Zhao, M, Tu, Y & Fortes, JAB 2011, Fuzzy modeling based resource management for virtualized database systems. in IEEE International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems - Proceedings., 6005366, pp. 32-42, 19th Annual IEEE/ACM International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2011, Singapore, Singapore, 7/25/11. https://doi.org/10.1109/MASCOTS.2011.70
Wang L, Xu J, Zhao M, Tu Y, Fortes JAB. Fuzzy modeling based resource management for virtualized database systems. In IEEE International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems - Proceedings. 2011. p. 32-42. 6005366 https://doi.org/10.1109/MASCOTS.2011.70
Wang, Lixi ; Xu, Jing ; Zhao, Ming ; Tu, Yicheng ; Fortes, José A B. / Fuzzy modeling based resource management for virtualized database systems. IEEE International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems - Proceedings. 2011. pp. 32-42
@inproceedings{dc35a5bea9df460aa60bc338367cfd66,
title = "Fuzzy modeling based resource management for virtualized database systems",
abstract = "The hosting of databases on virtual machines (VMs) has great potential to improve the efficiency of resource utilization and the ease of deployment of database systems. This paper considers the problem of on-demand allocation of resources to a VM running a database serving dynamic and complex query workloads while meeting QoS (Quality of Service) requirements. An autonomic resource-management approach is proposed to address this problem. It uses adaptive fuzzy modeling to capture the behavior of a VM hosting a database with dynamically changing workloads and to predict its multi-type resource needs. A prototype of the proposed approach is implemented on Xen-based VMs and evaluated using workloads based on TPC-H and RUBiS. The results demonstrate that CPU and disk I/O bandwidth can be efficiently allocated to database VMs serving workloads with dynamically changing intensity and composition while meeting QoS targets. For TPC-H-based experiments, the resulting throughput is within 89.5 - 100{\%} of what would be obtained using resource allocation based on peak loads, For RUBiS, the response time target (set based on the performance under peak-load-based allocation) is met for 97{\%} of the time. Moreover, substantial resources are saved (about 62.6{\%} of CPU and 76.5{\%} of disk I/O bandwidth) in comparison to peak-load-based allocation.",
author = "Lixi Wang and Jing Xu and Ming Zhao and Yicheng Tu and Fortes, {Jos{\'e} A B}",
year = "2011",
doi = "10.1109/MASCOTS.2011.70",
language = "English (US)",
isbn = "9780769544304",
pages = "32--42",
booktitle = "IEEE International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems - Proceedings",

}

TY - GEN

T1 - Fuzzy modeling based resource management for virtualized database systems

AU - Wang, Lixi

AU - Xu, Jing

AU - Zhao, Ming

AU - Tu, Yicheng

AU - Fortes, José A B

PY - 2011

Y1 - 2011

N2 - The hosting of databases on virtual machines (VMs) has great potential to improve the efficiency of resource utilization and the ease of deployment of database systems. This paper considers the problem of on-demand allocation of resources to a VM running a database serving dynamic and complex query workloads while meeting QoS (Quality of Service) requirements. An autonomic resource-management approach is proposed to address this problem. It uses adaptive fuzzy modeling to capture the behavior of a VM hosting a database with dynamically changing workloads and to predict its multi-type resource needs. A prototype of the proposed approach is implemented on Xen-based VMs and evaluated using workloads based on TPC-H and RUBiS. The results demonstrate that CPU and disk I/O bandwidth can be efficiently allocated to database VMs serving workloads with dynamically changing intensity and composition while meeting QoS targets. For TPC-H-based experiments, the resulting throughput is within 89.5 - 100% of what would be obtained using resource allocation based on peak loads, For RUBiS, the response time target (set based on the performance under peak-load-based allocation) is met for 97% of the time. Moreover, substantial resources are saved (about 62.6% of CPU and 76.5% of disk I/O bandwidth) in comparison to peak-load-based allocation.

AB - The hosting of databases on virtual machines (VMs) has great potential to improve the efficiency of resource utilization and the ease of deployment of database systems. This paper considers the problem of on-demand allocation of resources to a VM running a database serving dynamic and complex query workloads while meeting QoS (Quality of Service) requirements. An autonomic resource-management approach is proposed to address this problem. It uses adaptive fuzzy modeling to capture the behavior of a VM hosting a database with dynamically changing workloads and to predict its multi-type resource needs. A prototype of the proposed approach is implemented on Xen-based VMs and evaluated using workloads based on TPC-H and RUBiS. The results demonstrate that CPU and disk I/O bandwidth can be efficiently allocated to database VMs serving workloads with dynamically changing intensity and composition while meeting QoS targets. For TPC-H-based experiments, the resulting throughput is within 89.5 - 100% of what would be obtained using resource allocation based on peak loads, For RUBiS, the response time target (set based on the performance under peak-load-based allocation) is met for 97% of the time. Moreover, substantial resources are saved (about 62.6% of CPU and 76.5% of disk I/O bandwidth) in comparison to peak-load-based allocation.

UR - http://www.scopus.com/inward/record.url?scp=80053040799&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053040799&partnerID=8YFLogxK

U2 - 10.1109/MASCOTS.2011.70

DO - 10.1109/MASCOTS.2011.70

M3 - Conference contribution

SN - 9780769544304

SP - 32

EP - 42

BT - IEEE International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems - Proceedings

ER -