MashCache: Taming flash crowds by using their good features

Hikaru Horie, Masato Asahara, Hiroshi Yamada, Kenji Kono

Research output: Contribution to journalArticle

Abstract

This paper presents MashCache, a scalable client-side architecture for taming harsh effects of flash crowds. Like previous systems, MashCache extensively makes use of client resources to cache and share frequently accessed contents. To design MashCache, we carefully investigated the quantitative analysis of flash crowds in the wild and found out that flash crowds have three good features that can be used to simplify the overall design of MashCache. First, flash crowds start up very slowly. MashCache has enough time to prepare for the coming flash crowds. Second, flash crowds last for a short period. Since the accessed content is rarely updated in this short period, MashCache can employ a simple mechanism for cache consistency. Finally, the clients issue the same requests on the target web sites. This feature simplifies the cache management of MashCache because the cache explosion can be avoided. By using these good features of flash crowds, MashCache advances the state-of-the-art of P2P based caching systems for flash crowds; MashCache is a pure P2P system that combines 1) aggressive caching, 2) query-origin key, 3) two-phase delta consistency, and 4) carefully designed cache meta data. MashCache has another advantage. Since it works completely on client-side, MashCache can tolerate flash crowds even if the external services the mashup depends on are not equipped with flash-crowd-resistant mechanisms. In the experiments with up to 2,500 emulated clients, a prototype of MashCache reduces the number of requests to the original web servers by 98.2% with moderate overheads.

Original languageEnglish
Pages (from-to)21-33
Number of pages13
JournalIPSJ Online Transactions
Volume5
Issue number1
DOIs
Publication statusPublished - 2012

Fingerprint

Metadata
Explosions
Websites
Servers
Chemical analysis
Experiments

Keywords

  • Content delivery
  • Flash crowds
  • Mashups
  • Peer-to-peer

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

MashCache : Taming flash crowds by using their good features. / Horie, Hikaru; Asahara, Masato; Yamada, Hiroshi; Kono, Kenji.

In: IPSJ Online Transactions, Vol. 5, No. 1, 2012, p. 21-33.

Research output: Contribution to journalArticle

Horie, Hikaru ; Asahara, Masato ; Yamada, Hiroshi ; Kono, Kenji. / MashCache : Taming flash crowds by using their good features. In: IPSJ Online Transactions. 2012 ; Vol. 5, No. 1. pp. 21-33.
@article{5c5819f47ec74477b89e16b1b2589116,
title = "MashCache: Taming flash crowds by using their good features",
abstract = "This paper presents MashCache, a scalable client-side architecture for taming harsh effects of flash crowds. Like previous systems, MashCache extensively makes use of client resources to cache and share frequently accessed contents. To design MashCache, we carefully investigated the quantitative analysis of flash crowds in the wild and found out that flash crowds have three good features that can be used to simplify the overall design of MashCache. First, flash crowds start up very slowly. MashCache has enough time to prepare for the coming flash crowds. Second, flash crowds last for a short period. Since the accessed content is rarely updated in this short period, MashCache can employ a simple mechanism for cache consistency. Finally, the clients issue the same requests on the target web sites. This feature simplifies the cache management of MashCache because the cache explosion can be avoided. By using these good features of flash crowds, MashCache advances the state-of-the-art of P2P based caching systems for flash crowds; MashCache is a pure P2P system that combines 1) aggressive caching, 2) query-origin key, 3) two-phase delta consistency, and 4) carefully designed cache meta data. MashCache has another advantage. Since it works completely on client-side, MashCache can tolerate flash crowds even if the external services the mashup depends on are not equipped with flash-crowd-resistant mechanisms. In the experiments with up to 2,500 emulated clients, a prototype of MashCache reduces the number of requests to the original web servers by 98.2{\%} with moderate overheads.",
keywords = "Content delivery, Flash crowds, Mashups, Peer-to-peer",
author = "Hikaru Horie and Masato Asahara and Hiroshi Yamada and Kenji Kono",
year = "2012",
doi = "10.2197/ipsjtrans.5.21",
language = "English",
volume = "5",
pages = "21--33",
journal = "IPSJ Online Transactions",
issn = "1882-6660",
publisher = "Information Processing Society of Japan",
number = "1",

}

TY - JOUR

T1 - MashCache

T2 - Taming flash crowds by using their good features

AU - Horie, Hikaru

AU - Asahara, Masato

AU - Yamada, Hiroshi

AU - Kono, Kenji

PY - 2012

Y1 - 2012

N2 - This paper presents MashCache, a scalable client-side architecture for taming harsh effects of flash crowds. Like previous systems, MashCache extensively makes use of client resources to cache and share frequently accessed contents. To design MashCache, we carefully investigated the quantitative analysis of flash crowds in the wild and found out that flash crowds have three good features that can be used to simplify the overall design of MashCache. First, flash crowds start up very slowly. MashCache has enough time to prepare for the coming flash crowds. Second, flash crowds last for a short period. Since the accessed content is rarely updated in this short period, MashCache can employ a simple mechanism for cache consistency. Finally, the clients issue the same requests on the target web sites. This feature simplifies the cache management of MashCache because the cache explosion can be avoided. By using these good features of flash crowds, MashCache advances the state-of-the-art of P2P based caching systems for flash crowds; MashCache is a pure P2P system that combines 1) aggressive caching, 2) query-origin key, 3) two-phase delta consistency, and 4) carefully designed cache meta data. MashCache has another advantage. Since it works completely on client-side, MashCache can tolerate flash crowds even if the external services the mashup depends on are not equipped with flash-crowd-resistant mechanisms. In the experiments with up to 2,500 emulated clients, a prototype of MashCache reduces the number of requests to the original web servers by 98.2% with moderate overheads.

AB - This paper presents MashCache, a scalable client-side architecture for taming harsh effects of flash crowds. Like previous systems, MashCache extensively makes use of client resources to cache and share frequently accessed contents. To design MashCache, we carefully investigated the quantitative analysis of flash crowds in the wild and found out that flash crowds have three good features that can be used to simplify the overall design of MashCache. First, flash crowds start up very slowly. MashCache has enough time to prepare for the coming flash crowds. Second, flash crowds last for a short period. Since the accessed content is rarely updated in this short period, MashCache can employ a simple mechanism for cache consistency. Finally, the clients issue the same requests on the target web sites. This feature simplifies the cache management of MashCache because the cache explosion can be avoided. By using these good features of flash crowds, MashCache advances the state-of-the-art of P2P based caching systems for flash crowds; MashCache is a pure P2P system that combines 1) aggressive caching, 2) query-origin key, 3) two-phase delta consistency, and 4) carefully designed cache meta data. MashCache has another advantage. Since it works completely on client-side, MashCache can tolerate flash crowds even if the external services the mashup depends on are not equipped with flash-crowd-resistant mechanisms. In the experiments with up to 2,500 emulated clients, a prototype of MashCache reduces the number of requests to the original web servers by 98.2% with moderate overheads.

KW - Content delivery

KW - Flash crowds

KW - Mashups

KW - Peer-to-peer

UR - http://www.scopus.com/inward/record.url?scp=84862133129&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862133129&partnerID=8YFLogxK

U2 - 10.2197/ipsjtrans.5.21

DO - 10.2197/ipsjtrans.5.21

M3 - Article

AN - SCOPUS:84862133129

VL - 5

SP - 21

EP - 33

JO - IPSJ Online Transactions

JF - IPSJ Online Transactions

SN - 1882-6660

IS - 1

ER -