The Broadband Storage demonstration focuses on using the DAFS protocol to support standard kernel mode I/O. The demonstration shows a Broadband Storage NAS device connected by Fibre Channel to an application server running a kernel DAFS implementation, which allows unmodified applications to take advantage of the capabilities offered by running DAFS over a high-performance, low overhead network.

The Fujitsu demonstration shows high-performance data transfer by DAFS, using a Linux-based DAFS client and server, connected via Emulex cLAN network solutions.

The Duke University demonstration shows a DAFS client and a DAFS-compliant memory-based file server, running over Emulex cLAN network solutions on FreeBSD. The demonstration shows the power and performance of the DAFS asynchronous data transfer model and direct user-level I/O for applications. The DAFS client allows direct I/O from applications based on an external I/O toolkit (TPIE) developed at Duke. The TPIE toolkit supports a range of applications including analysis programs for Geographic Information Systems (GIS) processing on massive terrain grids. This is an early demonstration of a reference DAFS implementation for open-source systems such as Linux and FreeBSD. The FreeBSD support is jointly developed by research groups at Duke and Harvard Universities.

The University of British Columbia has implemented a kernel level DAFS server in the Linux kernel using Emulex cLAN network solutions with modified versions of the SDK test clients. This solution demonstrates the functionality of persistent locks and auto-recoverable locks surviving client crashes.

The Network Appliance demonstrations show a kernel DAFS implementation on a Solaris-based database server running IBM DB2 getting high-performance file service from a NetApp filer. The demonstration shows two transport scenarios: a Fibre Channel fabric using Troika VI/FC HBAs and a Brocade FC switch; and a Gigabit Ethernet interconnect using the Emulex GN9000/VI VI/IP host bus adapters. The resulting CPU, memory and network efficiency are monitored using Quest Software monitoring tools.