BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Leveraging RDMA to Build a Real-Time Cloud for the Internet of Thi
 ngs  - Ken Birman (Cornell University)
DTSTART:20160922T140000Z
DTEND:20160922T150000Z
UID:TALK67715@talks.cam.ac.uk
CONTACT:Liang Wang
DESCRIPTION:We've all read the hype about the Internet of Things: a techno
 logy trend that seems endlessly about to happen\, yet has been stubbornly 
 hard to integrate with cloud computing.  In this talk I want to ask why th
 is has been so\, and how we can fix it.   \n\nI'll start by describing wor
 k Cornell has done over the past few years on creating a cloud platform to
  host "smart power grid" applications.  This involves (1) new rack-scale m
 anagement solutions aimed at applications that need to run 24x7\, (2) repl
 ication with ultra-fast updates for scalable real-time responsiveness\,  a
 nd (3) new real-time storage solutions\, to enable a new kind of big-data 
 temporal computing.  But new models also create huge performance puzzles. 
  For our work\, these center on how to overcome Brewer's CAP principle.  C
 AP was about performance tradeoffs\, and the key to conquering CAP is to l
 everage RDMA and NVRAM hardware\, which offer amazing speedups for critica
 l data paths.   By working from the ground up\, and using RDMA and NVRAM a
 s accelerators for data replication\, storage and management solutions\, w
 e can get huge speedups compared to older styles of cloud computing\, even
  when consistency and fault-tolerance are required.\n\nThis work is all op
 en-source\, and should be as useful on cloud systems as on clusters\, as l
 ong as the cloud runs a container OS:  With older styles of cloud virtuali
 zation\, it can be incredibly hard to offer scheduling guarantees\, and te
 chnologies like RDMA and NVRAM are very hard to virtualize.  Containers el
 iminate both of those obstacles.  \n\nBio: Ken Birman has been a systems r
 esearcher and faculty member at Cornell University since getting his PhD f
 rom UC Berkeley in 1981.  He is best known for work on virtually synchrono
 us process group computing models (an early version of what has become kno
 wn as the Paxos family of protocols)\, and his software has been widely us
 ed. The Isis Toolkit that Ken built ran the NYSE for more than a decade\, 
 and is still used to operate many aspects of the communication system in t
 he French air traffic control system.  A follow-on named Vsync is widely u
 sed in graduate courses that teach distributed computing.  This talk is ac
 tually based on his newest system\, called Derecho.
LOCATION:FW26\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR