Title: DTIA – Routing at Inter-Domain Level

Paulo Pinto (Science and Technology Faculty of the
Universidade Nova de Lisboa)

Abstract: This presentation describes an inter-domain routing
architecture called DTIA (Dynamic Topological Information
Architecture) which aims at replacing BGP without creating a
disruptive reality. DTIA separates various aspects having a layered
approach to the problem: it begins with reachability, then routing, and
finishes with traffic engineering. This paper is about the second aspect.
Our approach was to select relevant BGP features that should be part of
the architecture and construct the routing protocol. Other features will
be handled at higher level. One major requirement has been not to change
IP packets and the commercial relations in the Internet. Autonomous
Systems (ASes) receive a network map and they only exchange signaling
about failures. They perform routing based on link types
(provider-costumer, peer, primary, backup, etc.) and routing rules,
defining a closed system. We show that this system is monotone
guaranteeing convergence of the routing protocol and creating a multipath
system with very little overhead. DTIA routes packets using AS
identifiers instead of network prefixes requiring a mapping service
between them. The separation between reachability and routing provides
some advantages being one of them the reduction of algorithm complexity.
We use “regions” to cope with scalability and the reduction of algorithm
complexity allows us to have quite large regions.

Index Terms­ BGP; convergence; inter-domain routing; policy
routing; scalability

Paulo Pinto graduated in Electrical and Computer Engineering at
the Instituto Superior Técnico, Lisboa, Portugal in 1983. He got the MSc.
degree in Electrical and Computer Engineering at the same institute in
1987 and the Ph.D. in Computer Science at the University of Kent, at
Canterbury, UK, in 1993. He taught at Instituto Superior Técnico from
1982 to 1998 as teaching assistant until Assistant Professor.. Presently
he is an Associate Professor at the Science and Technology Faculty of the
Universidade Nova de Lisboa and coordinates the Telecommunication Sector
at the Faculty and a research group at Uninova (research centre). He has
been involved in many research and development activities in the area of
Telecommunications and has participated in several EU, National and
EURESCOM funded projects. His research interests are large-scale
distributed systems, middleware, network management, traffic control and
mobility. He has published a number of papers in international refereed
conferences and journals.

DAMA-UPC research group investes you to the following talk:

Title: Many Task Computing in Scientific Workflows
Speaker: Marta Mattoso (Universidade Federal de Rio de Janeiro)
Date: 22-Feb-2010 @ 10:30
Room: Sala d'actes de la FIB

Abstract

One of the main advantages of using a scientific workflow management system (SWfMS) to orchestrate data flows among scientific activities, is to control and register the whole workflow execution. The execution of activities within a workflow with high performance computing (HPC) presents challenges in SWfMS execution control. Remote execution control and provenance registry of the parallel activities is limited from the SWfMS side. This talk aims at showing a middleware solution as a bridge between SWfMS and HPC supporting workflow parallelization and provenance combined to MTC (Many Task Computing). It presents Hydra, a set of components to be included on the workflow specification of any SWMfS to control parallelization of activities as MTC. Hydra works in map/reduce style. Through Hydra's components, an MTC parallelization strategy can be registered, reused, and provenance may be uniformly gathered. Hydra aims at reducing the complexity involved in designing and managing activity/workflow parallel executions within scientific experiments. The main contributions of this work resides in helping the scientist in: (i) identifying parallel workflow activities in an abstract level, (ii) modeling workflow activities using MTC paradigm, (iii) submitting activities from the SWfMS to the distributed environment, (iv) steering by finding failures, detecting performance bottlenecks, monitoring processes status to let the SWfMS aware of the remote execution, and (v) gathering prospective and remote retrospective provenance data. We have evaluated Hydra in a Computational Fluid Dynamics (CFD) workflow and in a sensitivity analysis workflow for computing model constants in Large Eddy Simulation (LES) of turbulence. Experimental results show that a systematic approach for distributing parallel activities is viable, sparing scientist time and diminishing operational errors, with the additional benefits of distributed provenance support.