@inproceedings{lofstead:2011:nessie-staging,
 author= {Jay Lofstead and Ron Oldfiend and Todd Kordenbrock and Charles Reiss},
 title = {Extending Scalability of Collective IO Through Nessie and Staging},
 abstract = {The increasing fidelity of scientific simulations as they scale towards
exascale sizes is straining the proven IO techniques championed throughout
terascale computing. Chief among the successful IO techniques is the idea
of collective IO where processes coordinate and exchange data prior to writing
to storage in an effort to reduce the number of small, independent IO
operations. As well as collective IO works for efficiently creating a data set
in the canonical order, 3-D domain decompositions prove troublesome due to the
amount of data exchanged prior to writing to storage. When each process has a
tiny piece of a 3-D simulation space rather than a complete `pencil' or
`plane', 2-D or 1-D domain decompositions respectively, the communication
overhead to rearrange the data can dwarf the time spent actually writing to
storage~\cite{MPIcollectiveFix}. Our approach seeks to transparently increase
scalability and performance while maintaining both the IO routines in the
application and the final data format in the storage system. Accomplishing this
leverages both the Nessie~\cite{nessie} RPC framework and a staging area with
staging services. Through these tools, we employ a variety of data processing
operations prior to invoking the native API to write data to storage yielding
as much as a 3$\times$ performance improvement over the native calls.},
 year = {2011},
 month = {November},
 booktitle = {The Petascale Data Storage Workshop at Supercomputing},
 address = {Seattle, WA},
}