BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Elastic In-Memory Transaction Processing for Multi-Tenant Database
  Systems
DTSTART:20180605T130000
DTEND:20180605T150000
DTSTAMP:20260407T043448Z
UID:a39c525cc0aede43cd3391a22f92927c4afd2efbdfb003adda4e8db2
CATEGORIES:Conferences - Seminars
DESCRIPTION:Seyedeh Sharareh Mirzargar\nEDIC candidacy exam\nExam presiden
 t: Prof. Edouard Bugnion\nThesis advisor: Prof. Anastasia Ailamaki\nCo-exa
 miner: Prof. James Larus\n\nAbstract\nOnline Transaction Processing (OLTP)
  is one of the most important database applications. In recent years\, the
  emergence of new internet-scale companies (e.g.\, Facebook)\, has increas
 ed the need for ever higher transactional throughput. For example\, OLTP d
 eployments at Facebook process over 170 million transactions each second. 
 This new OLTP market has time-varying workloads due to daily\, weekly or s
 easonal fluctuations in demand. Despite this highly variable and diverse l
 oad\, OLTP database management systems need to maintain their high through
 put. Thus\, in order to support these applications\, OLTP DBMS has recentl
 y started to migrate from on-premise setting to the cloud infrastructure t
 o benefit from the available elasticity.\n\nIn this proposal\, we will fir
 st demonstrate how in-memory transaction processing has successfully provi
 ded high throughput for OLTP engines by making fundamental changes to the 
 system architecture. Subsequently\, we discuss a fine-grained repartitioni
 ng framework which provides elasticity for on-premise shared-nothing OLTP 
 DBMS. Then\, we will discuss elastic transaction processing in multi-tenan
 t cloud infrastructure. We present SQLVM which provides an abstraction of 
 a virtual machine inside the DBMS to isolate the performance of multiple t
 enants from each other with low overhead. Finally\, we conclude with our r
 esearch proposal regarding elastic in-memory transaction processing for mu
 lti-tenant scale-up OLTP deployment.\n\nBackground papers\nThe End of an A
 rchitecture Era (It's Time for a Complete Rewrite) In the proceedings of 
 the 33rd International Conference on Very Large Databases (VLDB'07)\, by S
 tonebraker M.\, et al.\nE-Store: Fine-Grained Elastic Partitioning for Dis
 tributed Transaction Processing Systems. In the proceedings of the 41st I
 nternational Conference on Very Large Databases (VLDB'15)\, by Taft R.\, e
 t al.\nSQLVM: Performance Isolation in Multi-Tenant Relational Database-as
 -a-Service. In 6th Biennial Conference on Innovative Data Systems Resear
 ch(CIDR'13)\, by Narasayya V.\, et al.
LOCATION:BC 229 https://plan.epfl.ch/?room==BC%20229
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR