[email protected]
©
CHARACTERIZATION OF WORKLOAD
AND RESOURCE CONSUMPTION FOR
AN ONLINE TRAVEL AND BOOKING SITE!
AA 2011/2012
[email protected]
16 Maggio 2012
Refs
¨ 
Characterization of Workload and Resource
Consumption for an Online Travel and Booking Site.
Nicolás Poggi, David Carrera, Ricard Gavaldà, Jordi
Torres, Eduard Ayguadé. 2010 IEEE Intl. Symp. on
Workload Characterization (IISWC) IEEE Press,
2010.
¤  http://www.lsi.upc.edu/%7Egavalda/iiscw10.pdf
[email protected]
©
16 Maggio 2012
Characterization of Workload and Resource
Consumption for an Online Travel and Booking Site
A mix of products
¨  A mix of technologies
¨  Great variability of access pattern
¨ 
A challenge for workload characterization
[email protected]
©
16 Maggio 2012
Characterization of Workload and Resource
Consumption for an Online Travel and Booking Site
¨ 
Real production log from OTA
¤  client
workload (1 week, milion of requests)
¤  load on 35+ nodes
¤  Ajax 3-tiers app on LAMP open source tech.
¨ 
Log includes
¤  HTTP
data
¤  Web server load status
¤  CPU time (user/system) application server
¤  DB access time and num of requests
¤  B2B external services service time
[email protected]
©
16 Maggio 2012
Characterization of Workload and Resource
Consumption for an Online Travel and Booking Site
¨ 
Workload characterization
¤  client
behaviour
¤  server resource consumption
[email protected]
©
16 Maggio 2012
Scenario
Application characteristics
¨  Computing Infrastructure
¨  Dataset properties
¨ 
[email protected]
©
16 Maggio 2012
Workload
characteristics
¨ 
No overload conditions
¨ 
6.0 pages/session
¨ 
6:48 minutes spent on the site
¨ 
¨ 
¨ 
¨ 
3.0s response time for dynamic
page generation
8MB of RAM memory
consumption
highest traffic is on Mondays
and decreases to the weekend.
Average page views as well as
the time spent on the site both
increase during the week,
peaking at the weekend
[email protected]
©
16 Maggio 2012
A model of traffic volume
[email protected]
©
16 Maggio 2012
Traffic composition
[email protected]
©
16 Maggio 2012
Per-session characteristics
[email protected]
©
16 Maggio 2012
Per-session model
[email protected]
©
16 Maggio 2012
Responce time analysis
[email protected]
©
16 Maggio 2012
Load average
[email protected]
©
16 Maggio 2012
R time vs Load avg
[email protected]
©
16 Maggio 2012
CPU % vs load avg
[email protected]
©
16 Maggio 2012
Memory % vs load avg
[email protected]
©
16 Maggio 2012
DB R time vs load avg
[email protected]
©
16 Maggio 2012
Ext R. time vs load avg
[email protected]
©
16 Maggio 2012
Num of click vs load avg
[email protected]
©
16 Maggio 2012
Resource usage
[email protected]
©
16 Maggio 2012
Resource usage
[email protected]
©
16 Maggio 2012
Progetti d’esame
[email protected]
©
16 Maggio 2012
Modellazione
¨ 
Realizzazione di un modello simulativo e studio
estensivo del comportamento del sistema al variare
dei parametri di ingresso
¤  Tipicamente
si parte da un sistema reale descritto in un
articolo scientifico e dalla relativa caratterizzazione
del carico
¨ 
Esempi di sistemi:
¤  Datacenter
¤  Cloud
federati
¤  Web clusters
[email protected]
©
16 Maggio 2012
Misure e caratterizzazione del carico
¨ 
Progettazione di un sistema di monitoraggio per
applicazioni web
¤  realizzazione
di un piccolo prototipo in laboratorio o
misura di un server reale
¤  caratterizzazione del carico
¨ 
Caratterizzazione di tracce reali (e.g. wikipedia)
[email protected]
©
16 Maggio 2012
Caratterizzazione del traffico
¨ 
Analysis of internet traffic traces
¤  DITL
¤  Internet
traffic
[email protected]
©
16 Maggio 2012
Scarica

characterization of workload and resource consumption for an