Parallel event processing for content-based publish/subscribe systems

Amer Farroukh; Elias Ferzli; Naweed Tajuddin; Hans Arno Jacobsen

doi:10.1145/1619258.1619269

Parallel event processing for content-based publish/subscribe systems

Amer Farroukh, Elias Ferzli, Naweed Tajuddin, Hans Arno Jacobsen

University of Toronto

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

19 Scopus citations

Abstract

Event processing systems are a promising technology for enterprise-scale applications. However, achieving scalability yet maintaining high performance is a challenging problem. This work introduces a parallel matching engine which leverages current chip multi-processors to increase throughput and to reduce the matching time. We present three parallelization techniques, as well as lock-based and software transactional memory-based implementations of each technique, and discuss their impact. The results show a 74% reduction of the average matching time and an improved throughput of over 1600 events/second when using eight processors.

Original language	English
Title of host publication	Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009
Publisher	Association for Computing Machinery
Pages	1-4
Number of pages	4
ISBN (Print)	9781605586656
DOIs	https://doi.org/10.1145/1619258.1619269
State	Published - 2009
Externally published	Yes
Event	3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009 - Nashville, TN, United States Duration: 6 Jul 2009 → 9 Jul 2009

Publication series

Name	Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009
Volume	2009-January

Conference

Conference	3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009
Country/Territory	United States
City	Nashville, TN
Period	6/07/09 → 9/07/09

Access to Document

10.1145/1619258.1619269

Cite this

Farroukh, A., Ferzli, E., Tajuddin, N., & Jacobsen, H. A. (2009). Parallel event processing for content-based publish/subscribe systems. In Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009 (pp. 1-4). (Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009; Vol. 2009-January). Association for Computing Machinery. https://doi.org/10.1145/1619258.1619269

Farroukh, Amer ; Ferzli, Elias ; Tajuddin, Naweed et al. / Parallel event processing for content-based publish/subscribe systems. Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009. Association for Computing Machinery, 2009. pp. 1-4 (Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009).

@inproceedings{f7d9f3e525ee419f8a5afa5c975144f8,

title = "Parallel event processing for content-based publish/subscribe systems",

abstract = "Event processing systems are a promising technology for enterprise-scale applications. However, achieving scalability yet maintaining high performance is a challenging problem. This work introduces a parallel matching engine which leverages current chip multi-processors to increase throughput and to reduce the matching time. We present three parallelization techniques, as well as lock-based and software transactional memory-based implementations of each technique, and discuss their impact. The results show a 74% reduction of the average matching time and an improved throughput of over 1600 events/second when using eight processors.",

author = "Amer Farroukh and Elias Ferzli and Naweed Tajuddin and Jacobsen, {Hans Arno}",

note = "Publisher Copyright: {\textcopyright} 2009 ACM.; 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009 ; Conference date: 06-07-2009 Through 09-07-2009",

year = "2009",

doi = "10.1145/1619258.1619269",

language = "English",

isbn = "9781605586656",

series = "Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009",

publisher = "Association for Computing Machinery",

pages = "1--4",

booktitle = "Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009",

}

Farroukh, A, Ferzli, E, Tajuddin, N & Jacobsen, HA 2009, Parallel event processing for content-based publish/subscribe systems. in Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009. Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009, vol. 2009-January, Association for Computing Machinery, pp. 1-4, 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009, Nashville, TN, United States, 6/07/09. https://doi.org/10.1145/1619258.1619269

Parallel event processing for content-based publish/subscribe systems. / Farroukh, Amer; Ferzli, Elias; Tajuddin, Naweed et al.
Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009. Association for Computing Machinery, 2009. p. 1-4 (Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009; Vol. 2009-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Parallel event processing for content-based publish/subscribe systems

AU - Farroukh, Amer

AU - Ferzli, Elias

AU - Tajuddin, Naweed

AU - Jacobsen, Hans Arno

PY - 2009

Y1 - 2009

N2 - Event processing systems are a promising technology for enterprise-scale applications. However, achieving scalability yet maintaining high performance is a challenging problem. This work introduces a parallel matching engine which leverages current chip multi-processors to increase throughput and to reduce the matching time. We present three parallelization techniques, as well as lock-based and software transactional memory-based implementations of each technique, and discuss their impact. The results show a 74% reduction of the average matching time and an improved throughput of over 1600 events/second when using eight processors.

AB - Event processing systems are a promising technology for enterprise-scale applications. However, achieving scalability yet maintaining high performance is a challenging problem. This work introduces a parallel matching engine which leverages current chip multi-processors to increase throughput and to reduce the matching time. We present three parallelization techniques, as well as lock-based and software transactional memory-based implementations of each technique, and discuss their impact. The results show a 74% reduction of the average matching time and an improved throughput of over 1600 events/second when using eight processors.

UR - http://www.scopus.com/inward/record.url?scp=77957260315&partnerID=8YFLogxK

U2 - 10.1145/1619258.1619269

DO - 10.1145/1619258.1619269

M3 - Conference contribution

AN - SCOPUS:77957260315

SN - 9781605586656

T3 - Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009

SP - 1

EP - 4

BT - Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009

PB - Association for Computing Machinery

T2 - 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009

Y2 - 6 July 2009 through 9 July 2009

ER -

Farroukh A, Ferzli E, Tajuddin N, Jacobsen HA. Parallel event processing for content-based publish/subscribe systems. In Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009. Association for Computing Machinery. 2009. p. 1-4. (Proceedings of the 3rd ACM International Conference on Distributed Event-Based Systems, DEBS 2009). doi: 10.1145/1619258.1619269

Parallel event processing for content-based publish/subscribe systems

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this