Today we recognize a high demand for powerful storage. In industry this issue is tackled either with large storage area networks, or by deploying parallel file systems on top of RAID systems or on smaller storage networks. The bigger the system gets the more important is the ability to analyze the performance and to identify bottlenecks in the architecture and the applications. We extended the performance monitor available in the parallel file system PVFS2 by including statistics of the server process and information of the system. Performance monitor data is available during runtime and the server process was modified to store this data in off-line traces suitable for post-mortem analysis. These values can be used to detect bottlenecks in the system. Some measured results demonstrate how these help to identify bottlenecks and may assists to rank the servers depending on their capabilities

@inproceedings{BDIPFSWTPM08,
	author	 = {Julian Kunkel and Thomas Ludwig},
	title	 = {{Bottleneck Detection in Parallel File Systems with Trace-Based Performance Monitoring}},
	year	 = {2008},
	booktitle	 = {{Euro-Par '08: Proceedings of the 14th international Euro-Par conference on Parallel
      Processing}},
	publisher	 = {Springer-Verlag},
	address	 = {Berlin, Heidelberg},
	pages	 = {212--221},
	conference	 = {Euro-Par-08},
	organization	 = {University of Las Palmas de Gran Canaria},
	location	 = {Las Palmas de Gran Canaria, Spain},
	isbn	 = {978-3-540-85450-0},
	doi	 = {http://dx.doi.org/10.1007/978-3-540-85451-7_23},
	abstract	 = {Today we recognize a high demand for powerful storage. In industry this issue is
      tackled either with large storage area networks, or by deploying parallel file systems on top
      of RAID systems or on smaller storage networks. The bigger the system gets the more important
      is the ability to analyze the performance and to identify bottlenecks in the architecture and
      the applications. We extended the performance monitor available in the parallel file system
      PVFS2 by including statistics of the server process and information of the system. Performance
      monitor data is available during runtime and the server process was modified to store this
      data in off-line traces suitable for post-mortem analysis. These values can be used to detect
      bottlenecks in the system. Some measured results demonstrate how these help to identify
      bottlenecks and may assists to rank the servers depending on their capabilities},
	url	 = {http://www.springerlink.com/content/5rl1j3j05164608g/fulltext.pdf},
}