BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Leveraging Resource Utilization Patterns in Cluster Management
DTSTART:20170524T100000
DTEND:20170524T120000
DTSTAMP:20260406T184019Z
UID:faf485a104e8c3d0aa55f124fe6c3d7cd1c2b89acda51c762a189262
CATEGORIES:Conferences - Seminars
DESCRIPTION:Maria Borge Chavez\nEDIC Candidacy Exam\nExam president: Prof.
  Katerina Argyraki\nThesis advisor: Prof. Willy Zwaenepoel\nCo-examiner: P
 rof. Rachid Guerraoui\n\nAbstract\nEfficient server resource utilization r
 emains a challenge for large-scale cloud operators. Workload co-location a
 nd server resource over-commitment are some approaches to increase resourc
 e utilization and reduce costs in datacenters. Special care must be taken 
 to not impact application performance.\nWe review three cluster management
  systems\, namely Borg\, Quasar\, and History-based Harvesting. These syst
 ems rely on resource utilization patterns to perform workload co-location 
 and over-commitment without reducing performance. Finally\, we present fut
 ure research directions to quantify and exploit resource usage predictabil
 ity in cluster management decisions.​\n\nBackground papers\nLarge-scale 
 cluster management at Google with Borg by Verma\, A.\, et al.\n\nQuasar: R
 esource-Efficient and QoS-Aware Cluster Management\, by  Delimitrou\, C.\
 , and Kozyrakis\, C. \n\nHistory-Based Harvesting of Spare Cycles and Stor
 age in Large-Scale Datacenters Zhang\, Z.\,  Prekas\, G.\, et al.\n 
LOCATION:BC 329 https://plan.epfl.ch/?room==BC%20329
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR