The Lambda Station Project


The upcoming era of LHC high data volume distributed GRID computing implies extra requirements on the resource management and network aware applications. There is a large demand for applications that are capable to dynamically allocate a high performance network path with predictable performance characteristics. Over the past several years, there has been a great deal of research effort and funding put into the deployment of optical-based, advanced research networks, such as National Lambda Rail, DataTag, CAnet4, Netherlight, UKLight, and most recently, the DOE Science UltraNet.

The Lambda Station project is aimed to enable dynamic allocation of alternate network paths for traffic of production SciDAC applications and to forward designated flows across LAN, negotiates with reservation and provisioning systems of WAN control planes, be it based on SONET channels, demand tunnels, or dynamic circuit networks. It creates End-To-End circuit between single hosts, computer farms or networks with predictable performance characteristics, preserving QoS if supported in LAN and WAN and tied security policy allowing only specific traffic to be forwarded or received through created path. Lambda Station project also explores Network Awareness capabilities.

How Lambda Station Works

Lambda Station services are intended to incur no additional equipment cost to the storage systems and very small additional equipment costs to enhance the local network infrastructure. If one envisions the optical network paths provided by UltraNet, National Lambda Rail, and other advanced optical-based research networks as high bandwidth data railways, then LambdaStation would functionally be the railroad terminal that regulates which flows at the local site get directed onto the high bandwidth data railways.

The following animations present some typical use cases of Lambda Station services:

[Fullsize Window]

[Fullsize Window]

[Fullsize Window]

Lambda Station Accomplishments

Current Status - The Lambda Station Project has completed its R&D phase and is in the process of developing a production quality product. Meanwhile several sites, including Fermilab, Caltech, and the University of Nebraska Lincoln, are already using Lambda Station services to steer production traffic via ESNet/Internet2 Dynamic Circuit Network or High Impact Networks such as UltraLight.

Internet2 Fall Members Meetings, 2007 - It was demonstrated Lambda Station capabilities to request a dynamic circuit across Internet2/ESNet networks and steer traffic of production clusters of US CMS Tier1 center and Tier2 center at University of Nebraska Lincoln.

Supercomputing 2007 - It was demonstrated detection of significant traffic between production facilities at USCMS Tier1 Center and Tier2 in UNL based on netflow analysis and requesting dynamic circuit across Internet2/ESNet DCN, steer that traffic into circuit and gracefully redirect traffic back onto conventional path when ticket is expired.

Supercomputing 2005 - Dynamic switching of flow between two alternate paths on demand of gridFTP application,