Modeling the dynamics of caching in content-based publish/subscribe systems

V. Sourlas, G.S. Paschos, Petteri Mannersalo, P. Flegkas, L. Tassiulas

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

7 Citations (Scopus)

Abstract

This paper considers cache dimensioning in the context of publish/subscribe (pub/sub) systems. We assume that each broker is equipped with a limited capacity cache and it decides upon a policy for caching and prioritizing messages. By using a request mechanism defined on top of the native pub/sub communication, a client may also request earlier published information. To study the survival time of published messages, a Markovian system model capturing the essential dynamics is defined. The model has a modular generic form which admits a variety of different policies and thus enables the calculation of their performance. For systems without message replication between the caching brokers, the distribution of message survival time is found using matrix analytic methods for solving absorbing Markov chains. For the general problem with messages copied from caches, we propose a heuristic approximation based on estimating the mean rate of copies. The approximate model is evaluated by a discrete event simulator and it is shown that for a wide set of parameters, the approximation provides a good basis for dimensioning the caches in the content-based pub/sub systems
Original languageEnglish
Title of host publicationProceedings of the ACM Symposium on Applied Computing, SAC '11
PublisherAssociation for Computing Machinery ACM
Pages478-485
ISBN (Print)978-1-4503-0113-8
DOIs
Publication statusPublished - 2011
MoE publication typeA4 Article in a conference publication
Event26th Annual ACM Symposium on Applied Computing, SAC 2011 - TaiChung, Taiwan, Province of China
Duration: 21 Mar 201124 Mar 2011

Conference

Conference26th Annual ACM Symposium on Applied Computing, SAC 2011
Abbreviated titleSAC 2011
CountryTaiwan, Province of China
CityTaiChung
Period21/03/1124/03/11

Fingerprint

Markov processes
Simulators
Communication

Keywords

  • Analytical modeling
  • Markov chains
  • model verification and validation
  • pub/sub systems

Cite this

Sourlas, V., Paschos, G. S., Mannersalo, P., Flegkas, P., & Tassiulas, L. (2011). Modeling the dynamics of caching in content-based publish/subscribe systems. In Proceedings of the ACM Symposium on Applied Computing, SAC '11 (pp. 478-485). Association for Computing Machinery ACM. https://doi.org/10.1145/1982185.1982291
Sourlas, V. ; Paschos, G.S. ; Mannersalo, Petteri ; Flegkas, P. ; Tassiulas, L. / Modeling the dynamics of caching in content-based publish/subscribe systems. Proceedings of the ACM Symposium on Applied Computing, SAC '11. Association for Computing Machinery ACM, 2011. pp. 478-485
@inproceedings{ed780531350246759ce2bf5b2d93a2d7,
title = "Modeling the dynamics of caching in content-based publish/subscribe systems",
abstract = "This paper considers cache dimensioning in the context of publish/subscribe (pub/sub) systems. We assume that each broker is equipped with a limited capacity cache and it decides upon a policy for caching and prioritizing messages. By using a request mechanism defined on top of the native pub/sub communication, a client may also request earlier published information. To study the survival time of published messages, a Markovian system model capturing the essential dynamics is defined. The model has a modular generic form which admits a variety of different policies and thus enables the calculation of their performance. For systems without message replication between the caching brokers, the distribution of message survival time is found using matrix analytic methods for solving absorbing Markov chains. For the general problem with messages copied from caches, we propose a heuristic approximation based on estimating the mean rate of copies. The approximate model is evaluated by a discrete event simulator and it is shown that for a wide set of parameters, the approximation provides a good basis for dimensioning the caches in the content-based pub/sub systems",
keywords = "Analytical modeling, Markov chains, model verification and validation, pub/sub systems",
author = "V. Sourlas and G.S. Paschos and Petteri Mannersalo and P. Flegkas and L. Tassiulas",
year = "2011",
doi = "10.1145/1982185.1982291",
language = "English",
isbn = "978-1-4503-0113-8",
pages = "478--485",
booktitle = "Proceedings of the ACM Symposium on Applied Computing, SAC '11",
publisher = "Association for Computing Machinery ACM",
address = "United States",

}

Sourlas, V, Paschos, GS, Mannersalo, P, Flegkas, P & Tassiulas, L 2011, Modeling the dynamics of caching in content-based publish/subscribe systems. in Proceedings of the ACM Symposium on Applied Computing, SAC '11. Association for Computing Machinery ACM, pp. 478-485, 26th Annual ACM Symposium on Applied Computing, SAC 2011, TaiChung, Taiwan, Province of China, 21/03/11. https://doi.org/10.1145/1982185.1982291

Modeling the dynamics of caching in content-based publish/subscribe systems. / Sourlas, V.; Paschos, G.S.; Mannersalo, Petteri; Flegkas, P.; Tassiulas, L.

Proceedings of the ACM Symposium on Applied Computing, SAC '11. Association for Computing Machinery ACM, 2011. p. 478-485.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Modeling the dynamics of caching in content-based publish/subscribe systems

AU - Sourlas, V.

AU - Paschos, G.S.

AU - Mannersalo, Petteri

AU - Flegkas, P.

AU - Tassiulas, L.

PY - 2011

Y1 - 2011

N2 - This paper considers cache dimensioning in the context of publish/subscribe (pub/sub) systems. We assume that each broker is equipped with a limited capacity cache and it decides upon a policy for caching and prioritizing messages. By using a request mechanism defined on top of the native pub/sub communication, a client may also request earlier published information. To study the survival time of published messages, a Markovian system model capturing the essential dynamics is defined. The model has a modular generic form which admits a variety of different policies and thus enables the calculation of their performance. For systems without message replication between the caching brokers, the distribution of message survival time is found using matrix analytic methods for solving absorbing Markov chains. For the general problem with messages copied from caches, we propose a heuristic approximation based on estimating the mean rate of copies. The approximate model is evaluated by a discrete event simulator and it is shown that for a wide set of parameters, the approximation provides a good basis for dimensioning the caches in the content-based pub/sub systems

AB - This paper considers cache dimensioning in the context of publish/subscribe (pub/sub) systems. We assume that each broker is equipped with a limited capacity cache and it decides upon a policy for caching and prioritizing messages. By using a request mechanism defined on top of the native pub/sub communication, a client may also request earlier published information. To study the survival time of published messages, a Markovian system model capturing the essential dynamics is defined. The model has a modular generic form which admits a variety of different policies and thus enables the calculation of their performance. For systems without message replication between the caching brokers, the distribution of message survival time is found using matrix analytic methods for solving absorbing Markov chains. For the general problem with messages copied from caches, we propose a heuristic approximation based on estimating the mean rate of copies. The approximate model is evaluated by a discrete event simulator and it is shown that for a wide set of parameters, the approximation provides a good basis for dimensioning the caches in the content-based pub/sub systems

KW - Analytical modeling

KW - Markov chains

KW - model verification and validation

KW - pub/sub systems

U2 - 10.1145/1982185.1982291

DO - 10.1145/1982185.1982291

M3 - Conference article in proceedings

SN - 978-1-4503-0113-8

SP - 478

EP - 485

BT - Proceedings of the ACM Symposium on Applied Computing, SAC '11

PB - Association for Computing Machinery ACM

ER -

Sourlas V, Paschos GS, Mannersalo P, Flegkas P, Tassiulas L. Modeling the dynamics of caching in content-based publish/subscribe systems. In Proceedings of the ACM Symposium on Applied Computing, SAC '11. Association for Computing Machinery ACM. 2011. p. 478-485 https://doi.org/10.1145/1982185.1982291