DocumentCode
1998857
Title
Towards Self-Predicting Systems: What If You Could Ask "What-If"?
Author
Thereska, Eno ; Narayanan, Dushyanth ; Ganger, Gregory R.
Author_Institution
Carnegie Mellon Univ., Pittsburgh, PA
fYear
2005
fDate
26-26 Aug. 2005
Firstpage
196
Lastpage
200
Abstract
Today, management and tuning questions are approached using if...then... rules of thumb. This reactive approach requires expertise regarding of system behavior, making it difficult to deal with unforeseen uses of a system´s resources and leading to system unpredictability and large system management overheads. We propose a what...if... approach that allows interactive exploration of the effects of system changes, thus converting complex tuning problem into simpler search problems. Through two concrete management problems, automating system upgrades and deciding on service migrations, we identify system design changes that enable a system to answer what...if... questions about itself
Keywords
distributed processing; search problems; systems analysis; concrete management problem; if-then thumb rules; search problems; self-predicting systems; service migrations; system design changes; system management; system upgrade automation; tuning problem; what-if approach; Amplitude shift keying; Concrete; Costs; Delay; Hardware; Resource management; Search problems; Throughput; Thumb; Tuning;
fLanguage
English
Publisher
ieee
Conference_Titel
Database and Expert Systems Applications, 2005. Proceedings. Sixteenth International Workshop on
Conference_Location
Copenhagen
ISSN
1529-4188
Print_ISBN
0-7695-2424-9
Type
conf
DOI
10.1109/DEXA.2005.191
Filename
1508272
Link To Document