@Article{cecchet:raidb,
  author = {Emmanuel Cecchet and Julie Marguerite and Willy Zwaenepoel},
  title = {Partial replication: Achieving scalability in redundant arrays of
  inexpensive databases},
  journal = {Lecture Notes in Computer Science},
  booktitle = {7th International Conference on  Principles of Distributed
  Systems (OPODIS 2003); December 10-13, 2003; MARTINIQUE},
  editor = {Papatrianatafilou, M; Hunel, P},
  year = {2004},
  month = {July},
  volume = {3144},
  pages = {58--70},
  publisher = {Springer-Verlag Heidelberg},
  copyright = {(c)2004 Institute for Scientific Information, Inc.},
  URL = {http://springerlink.metapress.com/link.asp?id=kay13m7clgg75utk},
  keywords = {replication strategies, RAIDb, database, pario-bib},
  abstract = {Clusters of workstations become more and more popular to power
  data server applications such as large scale Web sites or e-Commerce
  applications. There has been much research on scaling the front tiers (web
  servers and application servers) using clusters, but databases usually remain
  on large dedicated SMP machines. In this paper, we focus on the database tier
  using clusters of commodity hardware. Our approach consists of studying
  different replication strategies to achieve various degree of performance and
  fault tolerance.  Redundant Array of Inexpensive Databases (RAIDb) is to
  databases what RAID is to disks. In this paper, we focus on RAIDb-1 that
  offers full replication and RAIDb-2 that introduces partial replication, in
  which the user can define the degree of replication of each database table.
   We present a Java implementation of RAIDb called Clustered JDBC or C-JDBC.
  C-JDBC achieves both database performance scalability and high availability
  at the middleware level without changing existing applications. We show,
  using the TPC-W benchmark, that partial replication (RAIDb-2) can offer
  better performance scalability (up to 25\%) than full replication by allowing
  fine-grain control on replication. Distributing and restricting the
  replication of frequently written tables to a small set of backends reduces
  I/O usage and improves CPU utilization of each cluster node.}
}

@Article{feng:io-response,
  author = {Dan Feng and Hong Jiang and Yifeng Zhu},
  title = {{I/O} response time in a fault-tolerant parallel virtual file
  system},
  journal = {Lecture Notes in Computer Science},
  booktitle = {IFIP International Conference on Network and Parallel Computing;
  October 18-20, 2004; Wuhan, PEOPLES R CHINA},
  editor = {Jin, H; Gao, GR; Xu, ZW; Chen, H},
  year = {2004},
  month = {October},
  volume = {3222},
  pages = {248--251},
  institution = {Huazhong Univ Sci \& Technol, Coll Comp, Minist Educ, Key Lab
  Data Storage Syst, Wuhan 430074, Peoples R China; Univ Nebraska, Dept Comp
  Sci \& Engn, Lincoln, NE 68588 USA},
  publisher = {Springer-Verlag Heidelberg},
  copyright = {(c)2004 The Thomson Corporation},
  URL = {http://springerlink.metapress.com/link.asp?id=484ru5hgyxegr5r2},
  keywords = {fault-tolerance, PVFS, perforamance analysis, pario-bib},
  abstract = {A fault tolerant parallel virtual file system is designed and
  implemented to provide high I/O performance and high reliability. A queuing
  model is used to analyze in detail the average response time when multiple
  clients access the system. The results show that I/O response time is with a
  function of several operational parameters. It decreases with the increase in
  I/O buffer hit rate for read requests, write buffer size for write requests
  and number of server nodes in the parallel file system, while higher I/O
  requests arrival rate increases I/O response time.}
}

@Article{gropp:io-redundancy,
  author = {William D. Gropp and Robert Ross and Neill Miller},
  title = {Providing efficient {I/O} redundancy in {MPI} environments},
  journal = {Lecture Notes in Computer Science},
  booktitle = {11th European Parallel Virtural Machine and Message Passing
  Interface Users Group Meeting; September 19-22, 2004; Budapest, HUNGARY},
  editor = {Kranzlmuller, D; Kacsuk, P; Dongarra, J},
  year = {2004},
  month = {November},
  volume = {3241},
  pages = {77--86},
  institution = {Argonne Natl Lab, Div Math \& Comp Sci, 9700 S Cass Ave,
  Argonne, IL 60439 USA; Argonne Natl Lab, Div Math \& Comp Sci, Argonne, IL
  60439 USA},
  publisher = {Springer-Verlag Heidelberg},
  copyright = {(c)2004 Institute for Scientific Information, Inc.},
  URL = {http://www.springerlink.com/link.asp?id=wxx7xg3hb3xftx8b},
  keywords = {fault-tolerance, single-disk failures, MPI-IO, pario-bib},
  abstract = {Highly parallel applications often use either highly parallel
  file systems or large numbers of independent disks. Either approach can
  provide the high data rates necessary for parallel applications. However, the
  failure of a single disk or server can render the data useless. Conventional
  techniques, such as those based on applying erasure correcting codes to each
  file write, are prohibitively expensive for massively parallel scientific
  applications because of the granularity of access at which the codes are
  applied. In this paper we demonstrate a scalable method for recovering from
  single disk failures that is optimized for typical scientific data sets. This
  approach exploits coarser-grained (but precise) semantics to reduce the
  overhead of constructing recovery data and makes use of parallel computation
  (proportional to the data size and independent of number of processors) to
  construct data. Experiments are presented showing the efficiency of this
  approach on a cluster with independent disks, and a technique is described
  for hiding the creation of redundant data within the MPI-IO implementation.}
}

@InProceedings{isaila:integrating,
  author = {Florin Isaila and Guido Malpohl and Vlad Olaru and Gabor Szeder and
  Walter Tichy},
  title = {Integrating collective {I/O} and cooperative caching into the
  "clusterfile" parallel file system},
  booktitle = {Proceedings of the 18th Annual International Conference on
  Supercomputing},
  year = {2004},
  month = {July},
  pages = {58--67},
  publisher = {ACM Press},
  copyright = {(c)2004 Elsevier Engineering Information, Inc.},
  address = {Sain-Malo, France},
  URL = {http://doi.acm.org/10.1145/1006209.1006219},
  keywords = {disk-directed I/O, two-phase I/O, clusterfile parallel file
  system, cooperative cache, pario-bib},
  abstract = {This paper presents the integration of two collective I/O
  techniques into the Clusterfile parallel file system : disk-directed I/O and
  two-phase I/O. We show that global cooperative cache management improves the
  collective I/O performance. The solution focuses on integrating disk
  parallelism with other types of parallelism: memory (by buffering and caching
  on several nodes), network (by parallel I/O scheduling strategies) and
  processors (by redistributing the I/O related computation over several
  nodes). The performance results show considerable throughput increases over
  ROMIO's extended two-phase I/O.}
}

@Article{krammer:marmot,
  author = {Bettina Krammer and Matthias S. M{\"u}ller and Michael M. Resch},
  title = {{MPI I/O} analysis and error detection with {MARMOT}},
  journal = {Lecture Notes in Computer Science},
  booktitle = {Proceedings of the 11th European Parallel Virtural Machine and
  Message Passing Interface Users Group Meeting},
  editor = {Kranzlmuller, D; Kacsuk, P; Dongarra, J},
  year = {2004},
  month = {September},
  volume = {3241},
  pages = {242--250},
  institution = {Ctr High Performance Comp, Allmandring 30, D-70550 Stuttgart,
  Germany; Ctr High Performance Comp, D-70550 Stuttgart, Germany},
  publisher = {SPRINGER-VERLAG BERLIN},
  copyright = {(c)2004 Institute for Scientific Information, Inc.},
  address = {Budapest, Hungary},
  URL = {http://springerlink.metapress.com/link.asp?id=up8fqm0vlua6pjgl},
  keywords = {MPI I/O, error detection, performance analysis, MARMOT,
  pario-bib},
  abstract = {The most frequently used part of MPI-2 is MPI I/O. Due to the
  complexity of parallel programming in general, and of handling parallel I/O
  in particular, there is a need for tools that support the application
  development process. There axe many situations where incorrect usage of MPI
  by the application programmer can be automatically detected. In this paper we
  describe the MARMOT tool that uncovers some of these errors and we also
  analyze to what extent it is possible to do so for MPI I/O.}
}

@Article{latham:mpi-io-scalability,
  author = {Rob Latham and Rob Ross and Rajeev Thakur},
  title = {The impact of file systems on {MPI-IO} scalability},
  journal = {Lecture Notes in Computer Science},
  booktitle = {11th European Parallel Virtural Machine and Message Passing
  Interface Users Group Meeting; September 19-22, 2004; Budapest, HUNGARY},
  editor = {Kranzlmuller, D; Kacsuk, P; Dongarra, J},
  year = {2004},
  month = {November},
  volume = {3241},
  pages = {87--96},
  institution = {Argonne Natl Lab, 9700 S Cass Ave, Argonne, IL 60439 USA;
  Argonne Natl Lab, Argonne, IL 60439 USA},
  publisher = {Springer-Verlag Heidelberg},
  copyright = {(c)2004 Institute for Scientific Information, Inc.},
  URL = {http://www.springerlink.com/link.asp?id=m31px2lt90296b62},
  keywords = {scalability analysis, MPI-IO, pario-bib},
  abstract = {As the number of nodes in cluster systems continues to grow,
  leveraging scalable algorithms in all aspects of such systems becomes key to
  maintaining performance. While scalable algorithms have been applied
  successfully in some areas of parallel I/O, many operations are still
  performed in an uncoordinated manner. In this work we consider, in three file
  system scenarios, the possibilities for applying scalable algorithms to the
  many operations that make up the MPI-IO interface. From this evaluation we
  extract a set of file system characteristics that aid in developing scalable
  MPI-IO implementations.}
}

@Article{pinkenburg:tpo++,
  author = {Simon Pinkenburg and Wolfgang Rosenstiel},
  title = {Parallel {I/O} in an object-oriented message-passing library},
  journal = {Lecture Notes in Computer Science},
  booktitle = {11th European Parallel Virtural Machine and Message Passing
  Interface Users Group Meeting; September 19-22, 2004; Budapest, HUNGARY},
  editor = {Kranzlmuller, D; Kacsuk, P; Dongarra, J},
  year = {2004},
  month = {November},
  volume = {3241},
  pages = {251--258},
  institution = {Univ Tubingen, Dept Comp Engn, Wilhelm Schickard Inst
  Informat, Sand 13, D-72076 Tubingen, Germany; Univ Tubingen, Dept Comp Engn,
  Wilhelm Schickard Inst Informat, D-72076 Tubingen, Germany},
  publisher = {Springer-Verlag Heidelberg},
  copyright = {(c)2004 Institute for Scientific Information, Inc.},
  URL = {http://springerlink.metapress.com/link.asp?id=91qfhjbyrbgb7mhw},
  keywords = {object-oriented message passing, TPO++, parallel I/O interface,
  pario-bib},
  abstract = {The article describes the design and implementation of parallel
  I/O in the object-oriented message-passing library TPO++. TPO++ is
  implemented on top of the message passing standard MPI and provides an
  object-oriented, type-safe and data centric interface to message-passing.
  Starting with version 2, the MPI standard defines primitives for parallel I/O
  called MPI-IO. Based on this layer, we have implemented an object-oriented
  parallel I/O interface in TPO++. The project is part of our efforts to apply
  object-oriented methods to the development of parallel physical simulations.
  We give a short introduction to our message-passing library and detail its
  extension to parallel I/O. Performance measurements between TPO++ and MPI are
  compared and discussed.}
}

@Article{rajasekaran:out-of-core,
  author = {Sanguthevar Rajasekaran},
  title = {Out-of-core computing on mesh connected computers},
  journal = {Journal of Parallel and Distributed Computing},
  year = {2004},
  month = {November},
  volume = {64},
  number = {11},
  pages = {1311--1317},
  institution = {Univ Connecticut, Dept CSE, 371 Fairfield Rd, ITEB 257,
  Storrs, CT 06269 USA; Univ Connecticut, Dept CSE, Storrs, CT 06269 USA},
  publisher = {Academic Press Inc. Elsevier Science},
  copyright = {(c)2004 Elsevier Engineering Information, Inc.; The Thomson
  Corporation},
  URL = {http://dx.doi.org/10.1016/j.jpdc.2004.08.003},
  keywords = {out-of-core, sorting, parallel disk model, performance analysis,
  pario-bib},
  abstract = {Several models of parallel disks are found in the literature.
  These models have been proposed to alleviate the I/O bottleneck arising in
  handling voluminous data. These models have the general theme of assuming
  multiple disks. For instance the parallel disks model assumes D disks and a
  single computer. It is also assumed that a block of data from each of the D
  disks can be fetched into the main memory in one parallel I/O operation. In
  this paper, we study a model where there are more than one processors and
  each processor has an associated disk. In addition to the I/O cost, one also
  has to account for the inter-processor communication costs. To begin with we
  study the mesh and we investigate the performance of the mesh with respect to
  out-of-core computing. As a case study we consider the problem of sorting.
  The goal of this paper is to study the properties of this model. CP 2004
  Elsevier Inc. All rights reserved. (27 Refs.)}
}

@InProceedings{shah:algorithms,
  author = {Rahul Shah and Peter J. Varman and Jeffrey Scott Vitter},
  title = {Online algorithms for prefetching and caching on parallel disks},
  journal = {Annual ACM Symposium on Parallel Algorithms and Architectures},
  booktitle = {Proceedings of the Sixteenth Symposium on Parallel Algorithms
  and Architectures},
  year = {2004},
  month = {June},
  volume = {16},
  pages = {255--264},
  copyright = {(c)2004 Elsevier Engineering Information, Inc.},
  howpublished = {SPAA 2004 - Sixteenth Annual ACM Symposium on Parallelism in
  Algorithms and Architectures; 2004; v.16; p.255-264},
  address = {Barcelona, Spain},
  URL = {http://doi.acm.org/10.1145/1007912.1007950},
  keywords = {online algorithms, prefetching, caching, parallel disk model,
  threshold LRU, pario-bib},
  abstract = {Parallel disks provide a cost effective way of speeding up I/Os
  in applications that work with large amounts of data. The main challenge is
  to achieve as much parallelism as possible, using prefetching to avoid
  bottlenecks in disk access. Efficient algorithms have been developed for some
  particular patterns of accessing the disk blocks, In this paper, we consider
  general request sequences. When the request sequence consists of unique block
  requests, the problem is called prefetching and is a well-solved problem for
  arbitrary request sequences. When the reference sequence can have repeated
  references to the same block, we need to devise an effective caching policy
  as well. While optimum offline algorithms have been recently designed for the
  problem, in the online case, no effective algorithm was previously known. Our
  main contribution is a deterministic online algorithm threshold-LRU which
  achieves O((MD/L) {sup 2/3}) competitive ratio and a randomized online
  algorithm threshold-MARK which achieves O({square root}(MD/L) log(MD/L))
  competitive ratio for the caching/prefetching problem on the parallel disk
  model (PDM), where D is the number of disks, M is the size of fast memory
  buffer, and M + L is the amount of lookahead available in the request
  sequence. The best-known lower bound on the competitive ratio is {Omega}(
  {square root}MD/L) for lookahead L GRE M in both models. We also show that if
  the deterministic online algorithm is allowed to have twice the memory of the
  offline then a tight competitive ratio of {Theta}( {square root}MD/L) can be
  achieved. This problem generalizes the well-known paging problem on a single
  disk to the parallel disk model.}
}

@Article{shen:dpfs,
  author = {Xiaohui H. Shen and Alok Choudhary},
  title = {A high-performance distributed parallel file system for
  data-intensive computations},
  journal = {Journal of Parallel and Distributed Computing},
  year = {2004},
  month = {September},
  volume = {64},
  number = {10},
  pages = {1157--1167},
  institution = {Northwestern Univ, Dept Elect \& Comp Engn, Ctr Parallel \&
  Distributed Comp, Evanston, IL 60208 USA; Northwestern Univ, Dept Elect \&
  Comp Engn, Ctr Parallel \& Distributed Comp, Evanston, IL 60208 USA},
  publisher = {ACADEMIC PRESS INC ELSEVIER SCIENCE},
  copyright = {(c)2004 Institute for Scientific Information, Inc.},
  URL = {http://dx.doi.org/10.1016/j.jpdc.2004.07.001},
  keywords = {distributed file system, parallel file system, striping,
  pario-bib},
  abstract = {One of the challenges brought by large-scale scientific
  applications is how to avoid remote storage access by collectively using
  sufficient local storage resources to hold huge amounts of data generated by
  the simulation while providing high-performance I/O. DPFS, a distributed
  parallel file system, is designed and implemented to address this problem.
  DPFS collects locally distributed and unused storage resources as a
  supplement to the internal storage of parallel computing systems to satisfy
  the storage capacity requirement of large-scale applications. In addition,
  like parallel file systems, DPFS provides striping mechanisms that divide a
  file into small pieces and distributes them across multiple storage devices
  for parallel data access. The unique feature of DPFS is that it provides
  three file levels with each file level corresponding to a file striping
  method. In addition to the traditional linear striping method, DPFS also
  provides a novel Multidimensional striping method that can solve performance
  problems of linear striping for many popular access patterns. Other issues
  such as load-balancing and user interface are also addressed in DPFS. (C)
  2004 Elsevier Inc. All rights reserved.}
}

@Article{sun:dynamic,
  author = {Weitao T. Sun and Jiwu W. Shu and Weimin M. Zheng},
  title = {Dynamic file allocation in Storage Area Networks with neural network
  prediction},
  journal = {Lecture Notes in Computer Science},
  booktitle = {International Symposium on Neural Networks (ISSN 2004); August
  19-21, 2004; Dalian, PEOPLES R CHINA},
  editor = {Yin, FL; Wang, J; Guo, CG},
  year = {2004},
  month = {June},
  volume = {3174},
  pages = {719--724},
  institution = {Tsing Hua Univ, Dept Comp Sci \& Technol, Beijing 100084,
  Peoples R China},
  publisher = {Springer-Verlag Heidelberg},
  copyright = {(c)2004 Institute for Scientific Information, Inc.},
  URL = {http://www.springerlink.com/link.asp?id=7t97qycr7awnbw6j},
  keywords = {SAN, dynamic data reorganization, neural network, access pattern
  prediction, pario-bib},
  abstract = {Disk arrays are widely used in Storage Area Networks (SANs) to
  achieve mass storage capacity and high level I/O parallelism. Data
  partitioning and distribution among the disks is a promising approach to
  minimize the file access time and balance the I/O workload. But disk I/O
  parallelism by itself does not guarantee the optimal performance of an
  application. The disk access rates fluctuate with time because of access
  pattern variations, which leads to a workload imbalance. The user access
  pattern prediction is of great importance to dynamic data reorganization
  between hot and cool disks. Data migration occurs according to current and
  future disk allocation states and access frequencies. The objective of this
  paper is to develop a neural network based disk allocation trend prediction
  method and optimize the disks' file capacity to their balanced level. A
  Levenberg-Marquardt neural network was adopted to predict the disk access
  frequencies with the I/O track. History. Data reorganization on disk arrays
  was optimized to provide a good workload balance. The simulation results
  proved that the proposed method performs well.}
}