BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Explorations in the Grid Computing Jungle - François Taiani (Lanc
 aster University)
DTSTART:20080506T144500Z
DTEND:20080506T154500Z
UID:TALK11956@talks.cam.ac.uk
CONTACT:Pedro Brandao
DESCRIPTION:*Slides "available":http://www.cl.cam.ac.uk/research/srg/opera
 /meetings/attachments/globus-cambridge-2008.2.pdf .*\n\n_*Note the unusual
  time*_\n\n*Abstract:*\nGrid Computing is the new highly publicized distri
 buted computing paradigm that aims at federating computing resources acros
 s large area networks to provide ubiquitous\, on-demand computing power. I
 t has recently evolved towards Web-Services\, another very popular distrib
 uted computing technology that has been proposed as the means to integrate
  software over the Internet into large scale added-value chains of service
 s. Grid Computing and Web Services are fairly recent technologies\, with m
 ultiple facets (SOAP\, WSDL\, WSRF\, etc.)\, involving numerous building b
 locks (XML\, .Net\, HTTP\, web servers\, J2EE\, etc.). It is sometimes dif
 ficult to understand how all the different components relate to each other
 \, and how mature these technologies are. In this talk we will report on o
 ur attempt to better understand the java core of the Globus platform\, a r
 eference implementation of the current grid computing standards. In partic
 ular\, we will present our efforts in tracking down the causes for amazing
 ly bad performance of the platform. As we had very little knowledge of Glo
 bus\, which is a large and highly complex piece of software\, we had to de
 velop pragmatic approaches to speed up our understanding with appropriate 
 reverse engineering techniques. In particular\, we will present the dynami
 c layering technique we have used to infer the structure of Globus\, and h
 ow we used this technique to visualize the raw profiling results we obtain
 ed and better understand how each component of the underlying Java platfor
 m contributed to the system's behavior. This is an ongoing\, very practica
 l work\, that we think offers interesting insights into modern middleware 
 developments. It may also have us wonder how long known problems might mix
  with new ones\, and to which extend current abstraction and reuse techniq
 ues may be useful for rapid software development.\n\n*Bio:* François is i
 nterested in developing open and principled middleware solutions for compl
 ex systems such as grid and large scale sensor networks. He is particularl
 y interested in problems of fault-tolerance and resilience\, and how aspec
 t-oriented programming and computational reflection can be applied to prov
 ide these properties in the above systems.\n\n\nFrançois has been a lectu
 rer at Lancaster since January 2005\, after an intervening spell as a post
 -doctoral researcher at AT&T Shannon Laboratory (NJ\, USA)\, on an INRIA s
 cholarship. He received his PhD in January 2004 for his work at LAAS-CNRS 
 (France) on multi-level reflection applied to fault-tolerant systems. At L
 AAS\, he has worked among others on the EU ISP Dependable Systems of Syste
 ms project (IST-1999-11595)\, and the EU Cabernet Network of Excellence. A
 t Lancaster he is co-investigator on the Divergent Grid project (EPSRC EP/
 C534891)\, and the EU FP7 Diva project (Dynamic Variability in complex\, A
 daptive systems).\n\nMore information on "Lancaster's web page":http://www
 .comp.lancs.ac.uk/department/staff.php?name=taiani and on "François's per
 sonal web page":http://ftaiani.ouvaton.org/ .\n
LOCATION:Room FW11\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR