MultiPath MultiGet

An Optimized Multiget Method Leveraging SSD Internal Parallelism

Kyungtae Song, Jaehyung Kim, Doogie Lee, Sang Hyun Park

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

Abstract

Accessing data with low latency is a major issue for big data platforms. Some platforms use a Multiget method when accessing data. The Multiget method can be used efficiently when a server should seek data with multiple keys or many single get requests are waiting in a command queue. The method is implemented to access multiple blocks of data using multiple keys. In this research, we developed MPMG, a novel multipath Multiget method for a solid state drive (SSD)-based key-value storage. In MPMG, we use the open source key-value storage RocksDB, which was developed by Facebook and is one of the most representative key-value NoSQL stores. Current RocksDB system cannot fully utilize the internal parallelism of SSD. The MPMG method was designed to leverage ssd internal parallelism and access data in SSD with parallel approach. The ability to support the parallel access inside SSD is efficient for performance. With multipath approach, the SSD can fully exploit its bandwidth, compared to the original approach. In an experiment, this method showed improvements in speed and throughput. The elapsed time for processing decreased up to 80.

Original languageEnglish
Title of host publicationProceedings of the 7th International Conference on Emerging Databases - Technologies, Applications, and Theory
EditorsWonik Choi, Wookey Lee, Min Song, Sungwon Jung
PublisherSpringer Verlag
Pages138-150
Number of pages13
ISBN (Print)9789811065194
DOIs
Publication statusPublished - 2018 Jan 1
Event7th International Conference on Emerging Databases: Technologies, Applications, and Theory, EDB 2017 - Busan, Korea, Republic of
Duration: 2017 Aug 72017 Aug 9

Publication series

NameLecture Notes in Electrical Engineering
Volume461
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Other

Other7th International Conference on Emerging Databases: Technologies, Applications, and Theory, EDB 2017
CountryKorea, Republic of
CityBusan
Period17/8/717/8/9

Fingerprint

Servers
Throughput
Bandwidth
Processing
Experiments
Big data

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Cite this

Song, K., Kim, J., Lee, D., & Park, S. H. (2018). MultiPath MultiGet: An Optimized Multiget Method Leveraging SSD Internal Parallelism. In W. Choi, W. Lee, M. Song, & S. Jung (Eds.), Proceedings of the 7th International Conference on Emerging Databases - Technologies, Applications, and Theory (pp. 138-150). (Lecture Notes in Electrical Engineering; Vol. 461). Springer Verlag. https://doi.org/10.1007/978-981-10-6520-0_15
Song, Kyungtae ; Kim, Jaehyung ; Lee, Doogie ; Park, Sang Hyun. / MultiPath MultiGet : An Optimized Multiget Method Leveraging SSD Internal Parallelism. Proceedings of the 7th International Conference on Emerging Databases - Technologies, Applications, and Theory. editor / Wonik Choi ; Wookey Lee ; Min Song ; Sungwon Jung. Springer Verlag, 2018. pp. 138-150 (Lecture Notes in Electrical Engineering).
@inproceedings{536097d3e8954c13bd1e95c1a5933df6,
title = "MultiPath MultiGet: An Optimized Multiget Method Leveraging SSD Internal Parallelism",
abstract = "Accessing data with low latency is a major issue for big data platforms. Some platforms use a Multiget method when accessing data. The Multiget method can be used efficiently when a server should seek data with multiple keys or many single get requests are waiting in a command queue. The method is implemented to access multiple blocks of data using multiple keys. In this research, we developed MPMG, a novel multipath Multiget method for a solid state drive (SSD)-based key-value storage. In MPMG, we use the open source key-value storage RocksDB, which was developed by Facebook and is one of the most representative key-value NoSQL stores. Current RocksDB system cannot fully utilize the internal parallelism of SSD. The MPMG method was designed to leverage ssd internal parallelism and access data in SSD with parallel approach. The ability to support the parallel access inside SSD is efficient for performance. With multipath approach, the SSD can fully exploit its bandwidth, compared to the original approach. In an experiment, this method showed improvements in speed and throughput. The elapsed time for processing decreased up to 80.",
author = "Kyungtae Song and Jaehyung Kim and Doogie Lee and Park, {Sang Hyun}",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-981-10-6520-0_15",
language = "English",
isbn = "9789811065194",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Verlag",
pages = "138--150",
editor = "Wonik Choi and Wookey Lee and Min Song and Sungwon Jung",
booktitle = "Proceedings of the 7th International Conference on Emerging Databases - Technologies, Applications, and Theory",
address = "Germany",

}

Song, K, Kim, J, Lee, D & Park, SH 2018, MultiPath MultiGet: An Optimized Multiget Method Leveraging SSD Internal Parallelism. in W Choi, W Lee, M Song & S Jung (eds), Proceedings of the 7th International Conference on Emerging Databases - Technologies, Applications, and Theory. Lecture Notes in Electrical Engineering, vol. 461, Springer Verlag, pp. 138-150, 7th International Conference on Emerging Databases: Technologies, Applications, and Theory, EDB 2017, Busan, Korea, Republic of, 17/8/7. https://doi.org/10.1007/978-981-10-6520-0_15

MultiPath MultiGet : An Optimized Multiget Method Leveraging SSD Internal Parallelism. / Song, Kyungtae; Kim, Jaehyung; Lee, Doogie; Park, Sang Hyun.

Proceedings of the 7th International Conference on Emerging Databases - Technologies, Applications, and Theory. ed. / Wonik Choi; Wookey Lee; Min Song; Sungwon Jung. Springer Verlag, 2018. p. 138-150 (Lecture Notes in Electrical Engineering; Vol. 461).

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

TY - GEN

T1 - MultiPath MultiGet

T2 - An Optimized Multiget Method Leveraging SSD Internal Parallelism

AU - Song, Kyungtae

AU - Kim, Jaehyung

AU - Lee, Doogie

AU - Park, Sang Hyun

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Accessing data with low latency is a major issue for big data platforms. Some platforms use a Multiget method when accessing data. The Multiget method can be used efficiently when a server should seek data with multiple keys or many single get requests are waiting in a command queue. The method is implemented to access multiple blocks of data using multiple keys. In this research, we developed MPMG, a novel multipath Multiget method for a solid state drive (SSD)-based key-value storage. In MPMG, we use the open source key-value storage RocksDB, which was developed by Facebook and is one of the most representative key-value NoSQL stores. Current RocksDB system cannot fully utilize the internal parallelism of SSD. The MPMG method was designed to leverage ssd internal parallelism and access data in SSD with parallel approach. The ability to support the parallel access inside SSD is efficient for performance. With multipath approach, the SSD can fully exploit its bandwidth, compared to the original approach. In an experiment, this method showed improvements in speed and throughput. The elapsed time for processing decreased up to 80.

AB - Accessing data with low latency is a major issue for big data platforms. Some platforms use a Multiget method when accessing data. The Multiget method can be used efficiently when a server should seek data with multiple keys or many single get requests are waiting in a command queue. The method is implemented to access multiple blocks of data using multiple keys. In this research, we developed MPMG, a novel multipath Multiget method for a solid state drive (SSD)-based key-value storage. In MPMG, we use the open source key-value storage RocksDB, which was developed by Facebook and is one of the most representative key-value NoSQL stores. Current RocksDB system cannot fully utilize the internal parallelism of SSD. The MPMG method was designed to leverage ssd internal parallelism and access data in SSD with parallel approach. The ability to support the parallel access inside SSD is efficient for performance. With multipath approach, the SSD can fully exploit its bandwidth, compared to the original approach. In an experiment, this method showed improvements in speed and throughput. The elapsed time for processing decreased up to 80.

UR - http://www.scopus.com/inward/record.url?scp=85032473790&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032473790&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-6520-0_15

DO - 10.1007/978-981-10-6520-0_15

M3 - Conference contribution

SN - 9789811065194

T3 - Lecture Notes in Electrical Engineering

SP - 138

EP - 150

BT - Proceedings of the 7th International Conference on Emerging Databases - Technologies, Applications, and Theory

A2 - Choi, Wonik

A2 - Lee, Wookey

A2 - Song, Min

A2 - Jung, Sungwon

PB - Springer Verlag

ER -

Song K, Kim J, Lee D, Park SH. MultiPath MultiGet: An Optimized Multiget Method Leveraging SSD Internal Parallelism. In Choi W, Lee W, Song M, Jung S, editors, Proceedings of the 7th International Conference on Emerging Databases - Technologies, Applications, and Theory. Springer Verlag. 2018. p. 138-150. (Lecture Notes in Electrical Engineering). https://doi.org/10.1007/978-981-10-6520-0_15