Presentation 2006-07-20
Automatic determination method for machine in performance trouble in distributed system
Sei KATO, Toshiyuki YAMANE, Takahide NOGAYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A new approach for performance problem management in distributed system is proposed. The method detects and localizes the machine in trouble automatically by estimating and monitoring a performance metric, service demand, which is not affected by the external environment changes, such as transaction mix change and intensity increase. We implemented this method as a networkbase performance problem determination system and the verification experiment showed its effectiveness in practice.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Performance problem determination / distributed system / performance management
Paper # IA2006-12
Date of Issue

Conference Information
Committee IA
Conference Date 2006/7/13(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Internet Architecture(IA)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Automatic determination method for machine in performance trouble in distributed system
Sub Title (in English)
Keyword(1) Performance problem determination
Keyword(2) distributed system
Keyword(3) performance management
1st Author's Name Sei KATO
1st Author's Affiliation IBM Research, Tokyo Research Laboratory()
2nd Author's Name Toshiyuki YAMANE
2nd Author's Affiliation IBM Research, Tokyo Research Laboratory
3rd Author's Name Takahide NOGAYAMA
3rd Author's Affiliation IBM Research, Tokyo Research Laboratory
Date 2006-07-20
Paper # IA2006-12
Volume (vol) vol.106
Number (no) 173
Page pp.pp.-
#Pages 5
Date of Issue