Containers or hypervisors: Which is better for database consolidation?

Asraa Abdulrazak Ali Mardan, Kenji Kono

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

5 Citations (Scopus)

Abstract

Database management systems (DBMS) is a common service in clouds. Cloud platforms use virtualization to consolidate servers for efficient resource utilization and to isolate collocated users' workloads. The underlying virtualization technologies have critical impact on the performance and isolation, especially in disk I/O, in DBMS. There are two major virtualization approaches: The hypervisor-based (virtual machines) and the operating-system-level virtualization (containers). Containers are widely believed to outperform virtual machines because of negligible virtualization overheads, while virtual machines are expected to provide stronger performance isolation. This paper argues against the above beliefs by investigating MySQL I/O performance and isolation in KVM and LXC. Contrary to the general belief, our results show that KVM outperforms LXC by up to 86% without compromising the isolation. Our analysis reveals that file system journaling has negative impact on both the performance and isolation in LXC. Since containers share a journaling mechanism unlike virtual machines, journaling activities are serialized and bundled with each other, resulting in inferior performance and isolation.

Original languageEnglish
Title of host publicationProceedings - 8th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2016
PublisherIEEE Computer Society
Pages564-571
Number of pages8
ISBN (Electronic)9781509014453
DOIs
Publication statusPublished - 2017 Jan 23
Event8th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2016 - Luxembourg, Luxembourg
Duration: 2016 Dec 122016 Dec 15

Other

Other8th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2016
CountryLuxembourg
CityLuxembourg
Period16/12/1216/12/15

Fingerprint

Consolidation
Container
Virtualization
Isolation
Containers
Virtual Machine
Computer operating systems
File System
Operating Systems
Servers
Workload
Server
Virtual machine
Resources

Keywords

  • Container
  • DBMS
  • Performance Isolation
  • Virtualization

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Software
  • Theoretical Computer Science

Cite this

Mardan, A. A. A., & Kono, K. (2017). Containers or hypervisors: Which is better for database consolidation? In Proceedings - 8th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2016 (pp. 564-571). [7830739] IEEE Computer Society. https://doi.org/10.1109/CloudCom.2016.0098

Containers or hypervisors : Which is better for database consolidation? / Mardan, Asraa Abdulrazak Ali; Kono, Kenji.

Proceedings - 8th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2016. IEEE Computer Society, 2017. p. 564-571 7830739.

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

Mardan, AAA & Kono, K 2017, Containers or hypervisors: Which is better for database consolidation? in Proceedings - 8th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2016., 7830739, IEEE Computer Society, pp. 564-571, 8th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2016, Luxembourg, Luxembourg, 16/12/12. https://doi.org/10.1109/CloudCom.2016.0098
Mardan AAA, Kono K. Containers or hypervisors: Which is better for database consolidation? In Proceedings - 8th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2016. IEEE Computer Society. 2017. p. 564-571. 7830739 https://doi.org/10.1109/CloudCom.2016.0098
Mardan, Asraa Abdulrazak Ali ; Kono, Kenji. / Containers or hypervisors : Which is better for database consolidation?. Proceedings - 8th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2016. IEEE Computer Society, 2017. pp. 564-571
@inproceedings{03430ca3969849daa13acfbe8ba5d205,
title = "Containers or hypervisors: Which is better for database consolidation?",
abstract = "Database management systems (DBMS) is a common service in clouds. Cloud platforms use virtualization to consolidate servers for efficient resource utilization and to isolate collocated users' workloads. The underlying virtualization technologies have critical impact on the performance and isolation, especially in disk I/O, in DBMS. There are two major virtualization approaches: The hypervisor-based (virtual machines) and the operating-system-level virtualization (containers). Containers are widely believed to outperform virtual machines because of negligible virtualization overheads, while virtual machines are expected to provide stronger performance isolation. This paper argues against the above beliefs by investigating MySQL I/O performance and isolation in KVM and LXC. Contrary to the general belief, our results show that KVM outperforms LXC by up to 86{\%} without compromising the isolation. Our analysis reveals that file system journaling has negative impact on both the performance and isolation in LXC. Since containers share a journaling mechanism unlike virtual machines, journaling activities are serialized and bundled with each other, resulting in inferior performance and isolation.",
keywords = "Container, DBMS, Performance Isolation, Virtualization",
author = "Mardan, {Asraa Abdulrazak Ali} and Kenji Kono",
year = "2017",
month = "1",
day = "23",
doi = "10.1109/CloudCom.2016.0098",
language = "English",
pages = "564--571",
booktitle = "Proceedings - 8th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2016",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Containers or hypervisors

T2 - Which is better for database consolidation?

AU - Mardan, Asraa Abdulrazak Ali

AU - Kono, Kenji

PY - 2017/1/23

Y1 - 2017/1/23

N2 - Database management systems (DBMS) is a common service in clouds. Cloud platforms use virtualization to consolidate servers for efficient resource utilization and to isolate collocated users' workloads. The underlying virtualization technologies have critical impact on the performance and isolation, especially in disk I/O, in DBMS. There are two major virtualization approaches: The hypervisor-based (virtual machines) and the operating-system-level virtualization (containers). Containers are widely believed to outperform virtual machines because of negligible virtualization overheads, while virtual machines are expected to provide stronger performance isolation. This paper argues against the above beliefs by investigating MySQL I/O performance and isolation in KVM and LXC. Contrary to the general belief, our results show that KVM outperforms LXC by up to 86% without compromising the isolation. Our analysis reveals that file system journaling has negative impact on both the performance and isolation in LXC. Since containers share a journaling mechanism unlike virtual machines, journaling activities are serialized and bundled with each other, resulting in inferior performance and isolation.

AB - Database management systems (DBMS) is a common service in clouds. Cloud platforms use virtualization to consolidate servers for efficient resource utilization and to isolate collocated users' workloads. The underlying virtualization technologies have critical impact on the performance and isolation, especially in disk I/O, in DBMS. There are two major virtualization approaches: The hypervisor-based (virtual machines) and the operating-system-level virtualization (containers). Containers are widely believed to outperform virtual machines because of negligible virtualization overheads, while virtual machines are expected to provide stronger performance isolation. This paper argues against the above beliefs by investigating MySQL I/O performance and isolation in KVM and LXC. Contrary to the general belief, our results show that KVM outperforms LXC by up to 86% without compromising the isolation. Our analysis reveals that file system journaling has negative impact on both the performance and isolation in LXC. Since containers share a journaling mechanism unlike virtual machines, journaling activities are serialized and bundled with each other, resulting in inferior performance and isolation.

KW - Container

KW - DBMS

KW - Performance Isolation

KW - Virtualization

UR - http://www.scopus.com/inward/record.url?scp=85012977968&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85012977968&partnerID=8YFLogxK

U2 - 10.1109/CloudCom.2016.0098

DO - 10.1109/CloudCom.2016.0098

M3 - Conference contribution

AN - SCOPUS:85012977968

SP - 564

EP - 571

BT - Proceedings - 8th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2016

PB - IEEE Computer Society

ER -