BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Debugging Distributed Systems: A worked example - George Neville-N
 eil 
DTSTART:20150209T140500Z
DTEND:20150209T145500Z
UID:TALK57911@talks.cam.ac.uk
CONTACT:Andrew Rice
DESCRIPTION:"The system is slow!"\, is both a very poor and a very common 
 bug report for a distributed system.  Systems deployed on a data center\, 
 or wider\, scale are subject to bugs and performance degradation on a dail
 y basis.  Organizations that deploy these systems often debug\nthem in an 
 ad hoc manner\, because there is very little in the software or coherent l
 iterature on how one might approach these problems.  Debugging distributed
  systems remains one of the dark arts.  During this talk I will give a wor
 ked example\, from industry\, of how such problems are tracked down and so
 lved.  Along the way I will point out areas that are fertile for researche
 rs  and developers to help bring a more coherent set of tools and methods 
 to these problems.
LOCATION:LT1\, Computer Laboratory\, William Gates Builiding
END:VEVENT
END:VCALENDAR