What is Jetstream? Jetstream will be a user-friendly cloud environment designed to give researchers access to interactive computing and data analysis resources on demand, whenever and wherever they want to analyze their data. It will provide a library of virtual machines designed to do discipline specific scientific analysis. Software creators and researchers will also be able to create their own customized virtual machines or their own private computing system within Jetstream.
Who will Jetstream support? This project is designed for people whose research requires interactive computing resources that are well suited for cloud environments. This is essentially any researcher with “born digital” data who does not use a traditional supercomputer. The goal of the project is to broaden the user-base supported by the NSF eXtreme Digital (XD) program. As called for by the NSF in solicitation 14-536, the system “is intended to complement previous NSF investments in advanced computational infrastructure by exploring new and creative approaches to delivering innovative computational resources to an increasingly diverse community and portfolio of scientific research and education.” The project will embrace this by targeting communities not well-served with existing resources. It will enable many discoveries across disciplines such as biology, atmospheric science, economics, network science, observational astronomy, and social sciences. Examples of this are partnerships with two existing biology platforms, iPlant and Galaxy.
When will Jetstream be available? Jetstream is scheduled to enter production in January 2016.
How will Jetstream be allocated? Jetstream will be allocated through the XSEDE Resource Allocation System (XRAS). Startup allocations will be available for researchers to quickly access the system. Researchers from any US open science institution will be able to apply to use Jetstream free of charge.
Who are the Jetstream partners? The project will be led by Indiana University’s Pervasive Technology Institute with the following partners: University of Texas at Austin’s Texas Advanced Computing Center (TACC), the Computation Institute at the University of Chicago, the iPlant Collaborative at the University of Arizona, and the University of Texas, San Antonio.
The project will also involve collaborators from Johns Hopkins University, Penn State University, Cornell University, the University of Arkansas at Pine Bluff, University of Hawaii, National Snow and Ice Data Center (NSIDC), the Odum Institute at the University of North Carolina, and the National Center for Genome Analysis Support.
Dell is the vendor partner for Jetstream.
What is the architecture of Jetstream? Jetstream will feature a web-based user interface based on the popular Atmosphere cloud computing environment developed by the iPlant Collaborative and extended to support science and engineering research generally. The operational software environment will be based on OpenStack.
The computing environment will consist of two homogenous clusters at Indiana University and TACC with a test environment at the University of Arizona. The system will provide over ½ a PetaFLOPS of computational capacity and 2 petabytes of block and object storage. The individual nodes will contain two Intel “Haswell” processors, 128 GB of RAM, 2 terabytes of local storage, and 10 gigabit Ethernet networking. The system will leverage 40 gigabit Ethernet for network aggregation and each of the production clusters will connect to Internet2 at 100 Gbps. The physically distributed system will allow it to be highly available and resilient even if there were to be some sort of event that made one of the two sites inoperable .
For more information visit the website http://pti.iu.edu/jetstream/index.php