Section: Software and Platforms
FTA: Failure Trace Archive
The Failure Trace Archive  is available at http://fta.inria.fr . Since Derrick Kondo left on sabbatical, the Failure Trace Archive has been migrated to University of Western Sidney, Australia (http://fta.scem.uws.edu.au/ ), which allows an easier management by his colleagues Bahman Javadi who was working as a post-doc in the MESCAL team while initializing the FTA.
With the increasing functionality, scale, and complexity of distributed systems, resource failures are inevitable. While numerous models and algorithms for dealing with failures exist, the lack of public trace data sets and tools has prevented meaningful comparisons. To facilitate the design, validation, and comparison of fault-tolerant models and algorithms, we led the creation of the Failure Trace Archive (FTA), an on-line public repository of availability traces taken from diverse parallel and distributed systems.
While several archives exist, the FTA differs in several respects. First, it defines a standard format that facilitates the use and comparison of traces. Second, the archive contains traces in that format for over 20 diverse systems over a time span of 10 years. Third, it provides a public toolbox for failure trace interpretation, analysis, and modeling. The FTA was released in November 2009. It has received over 11,000 hits since then. The FTA has had national and international impact. Several published works have already cited and benefited from the traces and tools of the FTA. Simulation toolkits for distributed systems, such as SimGrid (CNRS/Inria, France) and GridSim (University of Melbourne, Australia), have incorporated the traces to allow for simulations with failures.