IEEE Conference on Massive Data Storage. April 16-20, 2012. Pacific Grove, CA.
John Bent*, Sorin Faibish*, Jim Ahrens^, Gary Grider^, John Patchett^, Percy Tzelnic*,
Jon Woodring^
*EMC
^Los Alamos National Laboratory
In the petascale era, the storage stack used by the extreme scale high performance computing community is fairly homogeneous across sites. On the compute edge of the stack, file system clients or IO forwarding services direct IO over an interconnect network to a relatively small set of IO nodes. These nodes forward the requests over a secondary storage network to a spindle-based parallel file system. Unfortunately, this architecture will become unviable in the exascale era.
As the density growth of disks continues to out-pace increases in their rotational speeds, disks are be- coming increasingly cost-effective for capacity but decreasingly so for bandwidth. Fortunately, new storage media such as solid state devices are filling this gap; although not cost-effective for capacity, they are so for performance. This suggests that the storage stack at exascale will incorporate solid state storage between the compute nodes and the parallel file systems. There are three natural places into which to position this new storage layer: within the compute nodes, the IO nodes, or the parallel file system. In this paper, we argue that the IO nodes are the appropriate location for HPC workloads and show results from a prototype system that we have built accordingly. Running a pipeline of computational simulation and visualization, we show that our prototype system reduces total time to completion by up to 30%.
FULL PAPER: pdf