STORAGEDB

Enhancing the storage sub-system with DBMS functionalities

Lin Qiao, Balakrishna R. Iyer, Divyakant Agrawal, Amr El Abbadi, Sandeep Uttamchandani

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

Abstract

This paper proposes STORAGEDB: a paradigm for implementing storage virtualation using databases. It describes details for storing the logical-to-physical mapping information as tables within the database; handling the incoming I/O requests of the application as database queries; bookkeeping of the I/O operations as database transactions. In addition, STORAGEDB uses built-in DBMS features to support storage virtualization functionalities; as an example we describe how online table space migration can be used to support reallocation of logical disks. Finally, we describe our modifications to a traditional RDBMS implementation, in order to make it light-weight. Improving the performance of a traditional DBMS is critical for the acceptance of STORAGEDB since the performace overheads are considered a primary challenge in replacing existing storage virtualization engines. Our current lightweight RDBMS has a 19 times shorter invocation path length than the original. In comparision to the open-source virtualization software, namely LVM, the extra cost of STORAGEDB is within 20% of LVM in trace-driven tests. (unlike STORAGEDB, LVM did not have logging overhead). We consider these initial results as the "stepping stone" in the paradigm of applying databases for storage virtualization.

Original languageEnglish
Title of host publicationProceedings - Twenty -second IEEE/Thirteenth NASA Goddard Conference on Mass Storage Systems and Technologies
Pages218-223
Number of pages6
Publication statusPublished - 31 Oct 2005
Externally publishedYes
EventTwenty-second IEEE/Thirteenth NASA Goddard Conference on Mass Storage Systems and Technologies, IEEE/NASA MSST2005 - Monterey, CA, United States
Duration: 11 Apr 200514 Apr 2005

Other

OtherTwenty-second IEEE/Thirteenth NASA Goddard Conference on Mass Storage Systems and Technologies, IEEE/NASA MSST2005
CountryUnited States
CityMonterey, CA
Period11/4/0514/4/05

Fingerprint

Engines
Virtualization
Costs

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Qiao, L., Iyer, B. R., Agrawal, D., El Abbadi, A., & Uttamchandani, S. (2005). STORAGEDB: Enhancing the storage sub-system with DBMS functionalities. In Proceedings - Twenty -second IEEE/Thirteenth NASA Goddard Conference on Mass Storage Systems and Technologies (pp. 218-223)

STORAGEDB : Enhancing the storage sub-system with DBMS functionalities. / Qiao, Lin; Iyer, Balakrishna R.; Agrawal, Divyakant; El Abbadi, Amr; Uttamchandani, Sandeep.

Proceedings - Twenty -second IEEE/Thirteenth NASA Goddard Conference on Mass Storage Systems and Technologies. 2005. p. 218-223.

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

Qiao, L, Iyer, BR, Agrawal, D, El Abbadi, A & Uttamchandani, S 2005, STORAGEDB: Enhancing the storage sub-system with DBMS functionalities. in Proceedings - Twenty -second IEEE/Thirteenth NASA Goddard Conference on Mass Storage Systems and Technologies. pp. 218-223, Twenty-second IEEE/Thirteenth NASA Goddard Conference on Mass Storage Systems and Technologies, IEEE/NASA MSST2005, Monterey, CA, United States, 11/4/05.
Qiao L, Iyer BR, Agrawal D, El Abbadi A, Uttamchandani S. STORAGEDB: Enhancing the storage sub-system with DBMS functionalities. In Proceedings - Twenty -second IEEE/Thirteenth NASA Goddard Conference on Mass Storage Systems and Technologies. 2005. p. 218-223
Qiao, Lin ; Iyer, Balakrishna R. ; Agrawal, Divyakant ; El Abbadi, Amr ; Uttamchandani, Sandeep. / STORAGEDB : Enhancing the storage sub-system with DBMS functionalities. Proceedings - Twenty -second IEEE/Thirteenth NASA Goddard Conference on Mass Storage Systems and Technologies. 2005. pp. 218-223
@inproceedings{079224dd07624539afddbad3ec26e713,
title = "STORAGEDB: Enhancing the storage sub-system with DBMS functionalities",
abstract = "This paper proposes STORAGEDB: a paradigm for implementing storage virtualation using databases. It describes details for storing the logical-to-physical mapping information as tables within the database; handling the incoming I/O requests of the application as database queries; bookkeeping of the I/O operations as database transactions. In addition, STORAGEDB uses built-in DBMS features to support storage virtualization functionalities; as an example we describe how online table space migration can be used to support reallocation of logical disks. Finally, we describe our modifications to a traditional RDBMS implementation, in order to make it light-weight. Improving the performance of a traditional DBMS is critical for the acceptance of STORAGEDB since the performace overheads are considered a primary challenge in replacing existing storage virtualization engines. Our current lightweight RDBMS has a 19 times shorter invocation path length than the original. In comparision to the open-source virtualization software, namely LVM, the extra cost of STORAGEDB is within 20{\%} of LVM in trace-driven tests. (unlike STORAGEDB, LVM did not have logging overhead). We consider these initial results as the {"}stepping stone{"} in the paradigm of applying databases for storage virtualization.",
author = "Lin Qiao and Iyer, {Balakrishna R.} and Divyakant Agrawal and {El Abbadi}, Amr and Sandeep Uttamchandani",
year = "2005",
month = "10",
day = "31",
language = "English",
isbn = "0769523188",
pages = "218--223",
booktitle = "Proceedings - Twenty -second IEEE/Thirteenth NASA Goddard Conference on Mass Storage Systems and Technologies",

}

TY - GEN

T1 - STORAGEDB

T2 - Enhancing the storage sub-system with DBMS functionalities

AU - Qiao, Lin

AU - Iyer, Balakrishna R.

AU - Agrawal, Divyakant

AU - El Abbadi, Amr

AU - Uttamchandani, Sandeep

PY - 2005/10/31

Y1 - 2005/10/31

N2 - This paper proposes STORAGEDB: a paradigm for implementing storage virtualation using databases. It describes details for storing the logical-to-physical mapping information as tables within the database; handling the incoming I/O requests of the application as database queries; bookkeeping of the I/O operations as database transactions. In addition, STORAGEDB uses built-in DBMS features to support storage virtualization functionalities; as an example we describe how online table space migration can be used to support reallocation of logical disks. Finally, we describe our modifications to a traditional RDBMS implementation, in order to make it light-weight. Improving the performance of a traditional DBMS is critical for the acceptance of STORAGEDB since the performace overheads are considered a primary challenge in replacing existing storage virtualization engines. Our current lightweight RDBMS has a 19 times shorter invocation path length than the original. In comparision to the open-source virtualization software, namely LVM, the extra cost of STORAGEDB is within 20% of LVM in trace-driven tests. (unlike STORAGEDB, LVM did not have logging overhead). We consider these initial results as the "stepping stone" in the paradigm of applying databases for storage virtualization.

AB - This paper proposes STORAGEDB: a paradigm for implementing storage virtualation using databases. It describes details for storing the logical-to-physical mapping information as tables within the database; handling the incoming I/O requests of the application as database queries; bookkeeping of the I/O operations as database transactions. In addition, STORAGEDB uses built-in DBMS features to support storage virtualization functionalities; as an example we describe how online table space migration can be used to support reallocation of logical disks. Finally, we describe our modifications to a traditional RDBMS implementation, in order to make it light-weight. Improving the performance of a traditional DBMS is critical for the acceptance of STORAGEDB since the performace overheads are considered a primary challenge in replacing existing storage virtualization engines. Our current lightweight RDBMS has a 19 times shorter invocation path length than the original. In comparision to the open-source virtualization software, namely LVM, the extra cost of STORAGEDB is within 20% of LVM in trace-driven tests. (unlike STORAGEDB, LVM did not have logging overhead). We consider these initial results as the "stepping stone" in the paradigm of applying databases for storage virtualization.

UR - http://www.scopus.com/inward/record.url?scp=27144515300&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27144515300&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0769523188

SN - 9780769523187

SP - 218

EP - 223

BT - Proceedings - Twenty -second IEEE/Thirteenth NASA Goddard Conference on Mass Storage Systems and Technologies

ER -