An efficient stream archiving method by operator merge and write control

Taiga Abe, Hideyuki Kawashima, Hiroyuki Kitagawa

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

1 Citation (Scopus)

Abstract

Stream data have become ubiquitous with the development of sensing devices, and therefore stream processing technology has also gained significance. A requirement of stream data processing is to provide persistence to stream data. This is simple, however it is not a trivial problem because, to provide persistence to data, data should be written to a persistent device such as disk. Disk access speed tends to be degraded by random accesses, and multiple queries exacerbate the problem. In this paper, we propose an efficient archiving method for data streams. The first technique is referred to as goperator merge. h It merges multiple operators to a single operator. Since the number of operators accessing the disk is reduced from N to 1 for each stream, the number of disk accesses is reduced, thereby accelerating archiving. The second technique is referred to as gwrite control. h It divides archiving procedures into three parts, it then assigns threads for each part so that the threads run simultaneously. The first thread conducts operators, the second writes tuples to a shared intermediate region on disk, and the third reads tuples from it and finalizes the writing of tuples. Controlling the threads so that they do not interfere with disk accesses accelerates archiving. Experiments showed that our proposal dramatically improved performance compared with the nave method. With a tuple size of 10KB, our proposed system did not violate any deadline misses until the input rate reached 100 tuples /s.

Original languageEnglish
Title of host publicationProceedings - 26th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012
Pages783-788
Number of pages6
DOIs
Publication statusPublished - 2012 May 14
Externally publishedYes
Event26th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012 - Fukuoka, Japan
Duration: 2012 Mar 262012 Mar 29

Other

Other26th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012
CountryJapan
CityFukuoka
Period12/3/2612/3/29

Fingerprint

Processing
Experiments

Keywords

  • data archiving
  • Data streams
  • multiple query optimization

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

Abe, T., Kawashima, H., & Kitagawa, H. (2012). An efficient stream archiving method by operator merge and write control. In Proceedings - 26th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012 (pp. 783-788). [6185490] https://doi.org/10.1109/WAINA.2012.227

An efficient stream archiving method by operator merge and write control. / Abe, Taiga; Kawashima, Hideyuki; Kitagawa, Hiroyuki.

Proceedings - 26th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012. 2012. p. 783-788 6185490.

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

Abe, T, Kawashima, H & Kitagawa, H 2012, An efficient stream archiving method by operator merge and write control. in Proceedings - 26th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012., 6185490, pp. 783-788, 26th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012, Fukuoka, Japan, 12/3/26. https://doi.org/10.1109/WAINA.2012.227
Abe T, Kawashima H, Kitagawa H. An efficient stream archiving method by operator merge and write control. In Proceedings - 26th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012. 2012. p. 783-788. 6185490 https://doi.org/10.1109/WAINA.2012.227
Abe, Taiga ; Kawashima, Hideyuki ; Kitagawa, Hiroyuki. / An efficient stream archiving method by operator merge and write control. Proceedings - 26th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012. 2012. pp. 783-788
@inproceedings{12dd4205a3764791956727b24fa73aec,
title = "An efficient stream archiving method by operator merge and write control",
abstract = "Stream data have become ubiquitous with the development of sensing devices, and therefore stream processing technology has also gained significance. A requirement of stream data processing is to provide persistence to stream data. This is simple, however it is not a trivial problem because, to provide persistence to data, data should be written to a persistent device such as disk. Disk access speed tends to be degraded by random accesses, and multiple queries exacerbate the problem. In this paper, we propose an efficient archiving method for data streams. The first technique is referred to as goperator merge. h It merges multiple operators to a single operator. Since the number of operators accessing the disk is reduced from N to 1 for each stream, the number of disk accesses is reduced, thereby accelerating archiving. The second technique is referred to as gwrite control. h It divides archiving procedures into three parts, it then assigns threads for each part so that the threads run simultaneously. The first thread conducts operators, the second writes tuples to a shared intermediate region on disk, and the third reads tuples from it and finalizes the writing of tuples. Controlling the threads so that they do not interfere with disk accesses accelerates archiving. Experiments showed that our proposal dramatically improved performance compared with the nave method. With a tuple size of 10KB, our proposed system did not violate any deadline misses until the input rate reached 100 tuples /s.",
keywords = "data archiving, Data streams, multiple query optimization",
author = "Taiga Abe and Hideyuki Kawashima and Hiroyuki Kitagawa",
year = "2012",
month = "5",
day = "14",
doi = "10.1109/WAINA.2012.227",
language = "English",
isbn = "9780769546520",
pages = "783--788",
booktitle = "Proceedings - 26th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012",

}

TY - GEN

T1 - An efficient stream archiving method by operator merge and write control

AU - Abe, Taiga

AU - Kawashima, Hideyuki

AU - Kitagawa, Hiroyuki

PY - 2012/5/14

Y1 - 2012/5/14

N2 - Stream data have become ubiquitous with the development of sensing devices, and therefore stream processing technology has also gained significance. A requirement of stream data processing is to provide persistence to stream data. This is simple, however it is not a trivial problem because, to provide persistence to data, data should be written to a persistent device such as disk. Disk access speed tends to be degraded by random accesses, and multiple queries exacerbate the problem. In this paper, we propose an efficient archiving method for data streams. The first technique is referred to as goperator merge. h It merges multiple operators to a single operator. Since the number of operators accessing the disk is reduced from N to 1 for each stream, the number of disk accesses is reduced, thereby accelerating archiving. The second technique is referred to as gwrite control. h It divides archiving procedures into three parts, it then assigns threads for each part so that the threads run simultaneously. The first thread conducts operators, the second writes tuples to a shared intermediate region on disk, and the third reads tuples from it and finalizes the writing of tuples. Controlling the threads so that they do not interfere with disk accesses accelerates archiving. Experiments showed that our proposal dramatically improved performance compared with the nave method. With a tuple size of 10KB, our proposed system did not violate any deadline misses until the input rate reached 100 tuples /s.

AB - Stream data have become ubiquitous with the development of sensing devices, and therefore stream processing technology has also gained significance. A requirement of stream data processing is to provide persistence to stream data. This is simple, however it is not a trivial problem because, to provide persistence to data, data should be written to a persistent device such as disk. Disk access speed tends to be degraded by random accesses, and multiple queries exacerbate the problem. In this paper, we propose an efficient archiving method for data streams. The first technique is referred to as goperator merge. h It merges multiple operators to a single operator. Since the number of operators accessing the disk is reduced from N to 1 for each stream, the number of disk accesses is reduced, thereby accelerating archiving. The second technique is referred to as gwrite control. h It divides archiving procedures into three parts, it then assigns threads for each part so that the threads run simultaneously. The first thread conducts operators, the second writes tuples to a shared intermediate region on disk, and the third reads tuples from it and finalizes the writing of tuples. Controlling the threads so that they do not interfere with disk accesses accelerates archiving. Experiments showed that our proposal dramatically improved performance compared with the nave method. With a tuple size of 10KB, our proposed system did not violate any deadline misses until the input rate reached 100 tuples /s.

KW - data archiving

KW - Data streams

KW - multiple query optimization

UR - http://www.scopus.com/inward/record.url?scp=84860764298&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860764298&partnerID=8YFLogxK

U2 - 10.1109/WAINA.2012.227

DO - 10.1109/WAINA.2012.227

M3 - Conference contribution

AN - SCOPUS:84860764298

SN - 9780769546520

SP - 783

EP - 788

BT - Proceedings - 26th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2012

ER -