DAX: A widely distributed multi-tenant storage service for DBMS hosting

Rui Liu, Ashraf Aboulnaga, Kenneth Salem

Research output: Chapter in Book/Report/Conference proceedingChapter

7 Citations (Scopus)

Abstract

Many applications hosted on the cloud have sophisticated data management needs that are best served by a SQL-based relational DBMS. It is not diffcult to run a DBMS in the cloud, and in many cases one DBMS instance is enough to support an application's workload. However, a DBMS running in the cloud (or even on a local server) still needs a way to persistently store its data and protect it against failures. One way to achieve this is to provide a scalable and reliable storage service that the DBMS can access over a network. This paper describes such a service, which we call DAX. DAX relies on multi-master replication and Dynamostyle exible consistency, which enables it to run in multiple data centers and hence be disaster tolerant. Flexible consistency allows DAX to control the consistency level of each read or write operation, choosing between strong consistency at the cost of high latency or weak consistency with low latency. DAX makes this choice for each read or write operation by applying protocols that we designed based on the storage tier usage characteristics of database systems. With these protocols, DAX provides a storage service that can host multiple DBMS tenants, scaling with the number of tenants and the required storage capacity and bandwidth. DAX also provides high availability and disaster tolerance for the DBMS storage tier. Experiments using the TPC-C benchmark show that DAX provides up to a factor of 4 performance improvement over baseline solutions that do not exploit exible consistency.

Original languageEnglish
Title of host publicationProceedings of the VLDB Endowment
Pages253-264
Number of pages12
Volume6
Edition4
Publication statusPublished - 2013
Externally publishedYes

Fingerprint

Disasters
Network protocols
Information management
Servers
Availability
Bandwidth
Experiments

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Computer Science(all)

Cite this

Liu, R., Aboulnaga, A., & Salem, K. (2013). DAX: A widely distributed multi-tenant storage service for DBMS hosting. In Proceedings of the VLDB Endowment (4 ed., Vol. 6, pp. 253-264)

DAX : A widely distributed multi-tenant storage service for DBMS hosting. / Liu, Rui; Aboulnaga, Ashraf; Salem, Kenneth.

Proceedings of the VLDB Endowment. Vol. 6 4. ed. 2013. p. 253-264.

Research output: Chapter in Book/Report/Conference proceedingChapter

Liu, R, Aboulnaga, A & Salem, K 2013, DAX: A widely distributed multi-tenant storage service for DBMS hosting. in Proceedings of the VLDB Endowment. 4 edn, vol. 6, pp. 253-264.
Liu R, Aboulnaga A, Salem K. DAX: A widely distributed multi-tenant storage service for DBMS hosting. In Proceedings of the VLDB Endowment. 4 ed. Vol. 6. 2013. p. 253-264
Liu, Rui ; Aboulnaga, Ashraf ; Salem, Kenneth. / DAX : A widely distributed multi-tenant storage service for DBMS hosting. Proceedings of the VLDB Endowment. Vol. 6 4. ed. 2013. pp. 253-264
@inbook{84f644c8c05e4ccfa7e0293b279863bc,
title = "DAX: A widely distributed multi-tenant storage service for DBMS hosting",
abstract = "Many applications hosted on the cloud have sophisticated data management needs that are best served by a SQL-based relational DBMS. It is not diffcult to run a DBMS in the cloud, and in many cases one DBMS instance is enough to support an application's workload. However, a DBMS running in the cloud (or even on a local server) still needs a way to persistently store its data and protect it against failures. One way to achieve this is to provide a scalable and reliable storage service that the DBMS can access over a network. This paper describes such a service, which we call DAX. DAX relies on multi-master replication and Dynamostyle exible consistency, which enables it to run in multiple data centers and hence be disaster tolerant. Flexible consistency allows DAX to control the consistency level of each read or write operation, choosing between strong consistency at the cost of high latency or weak consistency with low latency. DAX makes this choice for each read or write operation by applying protocols that we designed based on the storage tier usage characteristics of database systems. With these protocols, DAX provides a storage service that can host multiple DBMS tenants, scaling with the number of tenants and the required storage capacity and bandwidth. DAX also provides high availability and disaster tolerance for the DBMS storage tier. Experiments using the TPC-C benchmark show that DAX provides up to a factor of 4 performance improvement over baseline solutions that do not exploit exible consistency.",
author = "Rui Liu and Ashraf Aboulnaga and Kenneth Salem",
year = "2013",
language = "English",
volume = "6",
pages = "253--264",
booktitle = "Proceedings of the VLDB Endowment",
edition = "4",

}

TY - CHAP

T1 - DAX

T2 - A widely distributed multi-tenant storage service for DBMS hosting

AU - Liu, Rui

AU - Aboulnaga, Ashraf

AU - Salem, Kenneth

PY - 2013

Y1 - 2013

N2 - Many applications hosted on the cloud have sophisticated data management needs that are best served by a SQL-based relational DBMS. It is not diffcult to run a DBMS in the cloud, and in many cases one DBMS instance is enough to support an application's workload. However, a DBMS running in the cloud (or even on a local server) still needs a way to persistently store its data and protect it against failures. One way to achieve this is to provide a scalable and reliable storage service that the DBMS can access over a network. This paper describes such a service, which we call DAX. DAX relies on multi-master replication and Dynamostyle exible consistency, which enables it to run in multiple data centers and hence be disaster tolerant. Flexible consistency allows DAX to control the consistency level of each read or write operation, choosing between strong consistency at the cost of high latency or weak consistency with low latency. DAX makes this choice for each read or write operation by applying protocols that we designed based on the storage tier usage characteristics of database systems. With these protocols, DAX provides a storage service that can host multiple DBMS tenants, scaling with the number of tenants and the required storage capacity and bandwidth. DAX also provides high availability and disaster tolerance for the DBMS storage tier. Experiments using the TPC-C benchmark show that DAX provides up to a factor of 4 performance improvement over baseline solutions that do not exploit exible consistency.

AB - Many applications hosted on the cloud have sophisticated data management needs that are best served by a SQL-based relational DBMS. It is not diffcult to run a DBMS in the cloud, and in many cases one DBMS instance is enough to support an application's workload. However, a DBMS running in the cloud (or even on a local server) still needs a way to persistently store its data and protect it against failures. One way to achieve this is to provide a scalable and reliable storage service that the DBMS can access over a network. This paper describes such a service, which we call DAX. DAX relies on multi-master replication and Dynamostyle exible consistency, which enables it to run in multiple data centers and hence be disaster tolerant. Flexible consistency allows DAX to control the consistency level of each read or write operation, choosing between strong consistency at the cost of high latency or weak consistency with low latency. DAX makes this choice for each read or write operation by applying protocols that we designed based on the storage tier usage characteristics of database systems. With these protocols, DAX provides a storage service that can host multiple DBMS tenants, scaling with the number of tenants and the required storage capacity and bandwidth. DAX also provides high availability and disaster tolerance for the DBMS storage tier. Experiments using the TPC-C benchmark show that DAX provides up to a factor of 4 performance improvement over baseline solutions that do not exploit exible consistency.

UR - http://www.scopus.com/inward/record.url?scp=84881244116&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881244116&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:84881244116

VL - 6

SP - 253

EP - 264

BT - Proceedings of the VLDB Endowment

ER -