The performance of parallel distributed file systems suffers from many clients executing a large number of operations in parallel, because the I/O subsystem can be easily overwhelmed by the sheer amount of incoming I/O operations. This, in turn, can slow down the whole distributed system. Many optimizations exist that try to alleviate this problem. Client-side optimizations perform preprocessing to minimize the amount of work the file servers have to do. Server-side optimizations use server-internal knowledge to improve performance. This paper provides an overview of existing client-side optimizations and presents new modifications of the Two-Phase protocol. Interleaved Two-Phase is a modification of ROMIO's Two-Phase protocol, which iterates over the file differently to reduce the number of seek operations on disk. Pipelined Two-Phase uses a pipelined scheme which overlaps I/O and communication phases to utilize the network and I/O subsystems concurrently.

@inproceedings{OFTCIKKTML12,
	author	 = {Michael Kuhn and Julian Kunkel and Yuichi Tsujita and Hidetaka Muguruma and Thomas Ludwig},
	title	 = {{Optimizations for Two-Phase Collective I/O}},
	year	 = {2012},
	booktitle	 = {{Applications, Tools and Techniques on the Road to Exascale Computing}},
	editor	 = {Koen De Bosschere and Erik H. D'Hollander and Gerhard R. Joubert and David Padua and Frans Peters},
	publisher	 = {IOS Press},
	address	 = {Amsterdam, Berlin, Tokyo, Washington DC},
	series	 = {Advances in Parallel Computing},
	number	 = {22},
	pages	 = {455--462},
	conference	 = {ParCo 2011},
	organization	 = {University of Ghent, ELIS Department},
	location	 = {Ghent, Belgium},
	isbn	 = {978-1-61499-040-6},
	issn	 = {0927-5452},
	doi	 = {https://doi.org/10.3233/978-1-61499-041-3-455},
	abstract	 = {The performance of parallel distributed file systems suffers from many clients executing a large number of operations in parallel, because the I/O subsystem can be easily overwhelmed by the sheer amount of incoming I/O operations. This, in turn, can slow down the whole distributed system. Many optimizations exist that try to alleviate this problem. Client-side optimizations perform preprocessing to minimize the amount of work the file servers have to do. Server-side optimizations use server-internal knowledge to improve performance. This paper provides an overview of existing client-side optimizations and presents new modifications of the Two-Phase protocol. Interleaved Two-Phase is a modification of ROMIO's Two-Phase protocol, which iterates over the file differently to reduce the number of seek operations on disk. Pipelined Two-Phase uses a pipelined scheme which overlaps I/O and communication phases to utilize the network and I/O subsystems concurrently.},
}