@inproceedings{domke-fail-2014,
	author = {Domke, Jens and Hoefler, Torsten and Matsuoka, Satoshi},
	title = {{Fail-in-place Network Design: Interaction Between Topology, Routing Algorithm and Failures}},
	booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis},
	series = {SC '14},
	year = {2014},
	isbn = {978-1-4799-5500-8},
	location = {New Orleans, Louisana},
	pages = {597--608},
	numpages = {12},
	url = {http://dx.doi.org/10.1109/SC.2014.54},
	doi = {10.1109/SC.2014.54},
	acmid = {2683659},
	publisher = {IEEE Press},
	address = {Piscataway, NJ, USA},
	abstract = {The growing system size of high performance computers results in a steady decrease of the mean time between failures. Exchanging network components often requires whole system downtime which increases the cost of failures. In this work, we study a fail-in-place strategy where broken network elements remain untouched. We show, that a fail-in-place strategy is feasible for todays networks and the degradation is manageable, and provide guidelines for the design. Our network failure simulation toolchain allows system designers to extrapolate the performance degradation based on expected failure rates, and it can be used to evaluate the current state of a system. In a case study of real-world HPC systems, we will analyze the performance degradation throughout the systems lifetime under the assumption that faulty network components are not repaired, which results in a recommendation to change the used routing algorithm to improve the network performance as well as the fail-in-place characteristic.},
}