BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Dynamic Causal Monitoring for Distributed Systems - Rodrigo Fonsec
 a
DTSTART:20150817T130500Z
DTEND:20150817T135500Z
UID:TALK60351@talks.cam.ac.uk
CONTACT:Andrew Rice
DESCRIPTION:Monitoring and troubleshooting distributed systems is notoriou
 sly difficult\; potential problems are complex\, varied\, and unpredictabl
 e.  The de-facto monitoring and diagnosis tools at our disposal today -- l
 ogs\, counters\, and metrics -- have two important limitations: what gets 
 recorded is defined a priori\, and the information is recorded in a compon
 ent- or machine-centric way\, making it hard to correlate events that cros
 s these boundaries.\n\nIn this talk I will describe Pivot Tracing\, a moni
 toring framework for distributed systems that addresses both limitations b
 y combining dynamic instrumentation with causal tracing to fundamentally i
 ncrease the power of both.  Through a novel relational operator -- the hap
 pened-before join\, Pivot Tracing gives users\, at runtime\, the ability t
 o define arbitrary metrics at one point of the system\, while being able t
 o select\, filter\, and group by events meaningful at other parts of the s
 ystem\, even when crossing component or machine boundaries.\n\nI will desc
 ribe our prototype of Pivot Tracing for Java-based systems\, and show some
  examples of our evaluation on a heterogeneous Hadoop cluster comprising H
 DFS\, HBase\, MapReduce\, and YARN.  We found that Pivot Tracing can effec
 tively identify a diverse range\nof root causes such as software bugs\, mi
 sconfiguration\, and limping hardware.  Further\, Pivot Tracing is dynamic
 \, extensible\, and enables cross-tier analysis between any inter-operatin
 g applications\, with low execution overhead.\n\nBio:\nRodrigo Fonseca is 
 an assistant professor at Brown University's Computer Science Department. 
 He holds a PhD from UC Berkeley\, and prior to Brown was a visiting resear
 cher at Yahoo! Research. He is broadly interested  in networking\, distrib
 uted systems\, and operating systems.  His research involves seeking bette
 r ways to build\, operate\, and diagnose distributed systems\, including l
 arge-scale internet systems\, cloud computing\, and mobile computing. He i
 s currently working on dynamic tracing infrastructures for these systems\,
  on new ways\nto leverage network programmability\, and on better ways to 
 manage energy usage in mobile devices.\n
LOCATION:LT1\, Computer Laboratory\, William Gates Builiding
END:VEVENT
END:VCALENDAR