@InProceedings{abawajy:scheduling,
  author = {J. H. Abawajy},
  title = {Performance Analysis of Parallel {I/O} Scheduling Approaches on
  Cluster Computing Systems},
  booktitle = {Workshop on Parallel I/O in Cluster Computing and Computational
  Grids},
  year = {2003},
  month = {May},
  pages = {724--729},
  organization = {Carleton University},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo},
  note = {Organized at the IEEE/ACM International Symposium on Cluster
  Computing and the Grid 2003},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190724abs.htm},
  keywords = {parallel I/O, I/O scheduling algorithms, pario-bib},
  abstract = {As computation and communication hardware performance continue to
  rapidly increase, I/O represents a growing fraction of application execution
  time. This gap between the I/O subsystem and others is expected to increase
  in future since I/O performance is limited by physical motion. Therefore, it
  is imperative that novel techniques for improveing I/O performance be
  developed. Parallel I/O is a promising approach to alleviating this
  bottleneck. However, very little work exist with respect to scheduling
  parallel I/O operations explicitly. In this paper, we address the problem of
  effective management of parallel I/O in cluster computing systems by using
  appropriate I/O scheduling strategies. We propose two new I/O scheduling
  algorithms and compare them with two existing scheduling Approaches. The
  preliminary results show that the proposed policies outperform existing
  policies substantially.}
}

@InProceedings{cerin:sorting,
  author = {Christophe C\'erin and Hazem Fkaier and Mohamed Jemni},
  title = {A Synthesis of Parallel Out-of-core Sorting Programs on
  Heterogeneous Clusters},
  booktitle = {Proceedings of the Third IEEE/ACM International Symposium on
  Cluster Computing and the Grid},
  year = {2003},
  month = {May},
  pages = {78--85},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo, Japan},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190078abs.htm},
  keywords = {out-of-core, sorting, parallel I/O, load balancing, data
  distribution, pario-app, pario-bib},
  abstract = {The paper considers he problem of parallel external sorting in
  the contex of a form of heterogeneous clusters. We introduce two algorithms
  and we compare them two another one that we have previously developed. Since
  most common sort algorithms assume high-speed random access to all
  intermediate memory, they are unsuitable if the values to be sorted don't fit
  in main memory. This is the case for cluster computing platforms which are
  made of standard, cheap and scarce components. For that class of computing
  resources a good use of I/O operations compatible with the requirements of
  load balancing and computational complexity are the key to success. We
  explore three techniques and show how they can be deployed for clusters with
  processor performances related by a multiplicative factor. We validate the
  approaches in showing experimental results for the load balancing factor.}
}

@InProceedings{ching:noncontiguous,
  author = {Avery Ching and Alok Choudhary and Kenin Coloma and Wei-keng Liao
  and Robert Ross and William Gropp},
  title = {Noncontiguous {I/O} Accesses Through {MPI-IO}},
  booktitle = {Proceedings of the Third IEEE/ACM International Symposium on
  Cluster Computing and the Grid},
  year = {2003},
  month = {May},
  pages = {104--111},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo, Japan},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190104abs.htm},
  keywords = {parallel I/O, MPI-IO, ROMIO, list I/O, noncontiguous access,
  pario-bib},
  abstract = {I/O performance remains a weakness of parallel computing systems
  today. While this weakness is partly attributed to rapid advances in other
  system components, I/O interfaces available to programmers and the I/O
  methods supported by file systems have traditionally not matched efficiently
  with the types of I/O operations that scientific applications perform,
  particularly noncontiguous accesses. The MPI-IO interface allows for rich
  descriptions of the I/O patterns desired for scientific applications and
  implementations such as ROMIO have taken advantage of this ability while
  remaining limited by underlying file system methods. \par A method of
  noncontiguous data access, list I/O, was recently implemented in the Parallel
  Virtual File System (PVFS). We implement support for this interface in the
  ROMIO MPI-IO implementation. Through a suite of non-contiguous I/O tests we
  compared ROMIO list I/O to current methods of ROMIO noncontiguous access and
  found that the list I/O interface provides performance benefits in many
  noncontiguous cases.}
}

@InProceedings{cozette:read2,
  author = {Olivier Cozette and Cyril Randriamaro},
  title = {{READ^2}: Put disks at network level},
  booktitle = {Workshop on Parallel I/O in Cluster Computing and Computational
  Grids},
  year = {2003},
  month = {May},
  pages = {698--704},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo},
  note = {Organized at the IEEE/ACM International Symposium on Cluster
  Computing and the Grid 2003},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190698abs.htm},
  keywords = {parallel I/O, pario-bib},
  abstract = {Grand challenge applications have to process large amounts of
  data, and then require high performance IO systems. Cluster computing is a
  good alternative to proprietary system for building cost effective IO
  intensive platform: some cluster architectures won sorting benchmark
  (MinuteSort, Datamation)! Recent advances in IO component technologies (disk,
  controller and network) let us expect higher IO performance for data
  intensive applications on cluster. The counterpart of this evolution is that
  much stress is put on the different buses (memory, IO) of each node which
  cannot be scaled. In this paper we investigate a strategy we called READ2
  (Remote Efficient Access to Distant Device) to reduce the stress. With READ2
  any cluster node accesses directly to remote disk: the remote processor and
  the remote memory are removed from the control and data path: Inputs/Outputs
  don't interfere with the host processor and the host memory activity. With
  READ2 strategy, a cluster can be considered as a shared disk architecture
  instead of a shared nothing one. This papers describes an implementation of
  READ^2 on Myrinet Networks. First experimental results show IO performance
  improvement.}
}

@InProceedings{ho:reorganization,
  author = {T. K. Ho and Jack Y. B. Lee},
  title = {A Row-Permutated Data Reorganization Algorithm for Growing
  Server-less Video-on-Demand Systems},
  booktitle = {Proceedings of the Third IEEE/ACM International Symposium on
  Cluster Computing and the Grid},
  year = {2003},
  month = {May},
  pages = {44--51},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo, Japan},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190044abs.htm},
  keywords = {data reorganization, video on demand, video streaming,
  pario-bib},
  abstract = {Recently, a new server-less architecture is proposed for building
  low-cost yet scalable video streaming systems. Compare to conventional
  client-server-based video streaming systems, this server-less architecture
  does not need any dedicated video server and yet is highly scalable. Video
  data are distributed among user hosts and these hosts cooperate to stream
  video data to one another. Thus as new hosts join the system, they also add
  streaming and storage capacity to absorb the added streaming load. This study
  investigates the data reorganization problem when growing a server-less video
  streaming system. Specifically, as video data are distributed among user
  hosts, these data will need to be redistributed to newly joined hosts to
  utilize their storage and streaming capacity. This study presents a new data
  reorganization algorithm that allows controllable tradeoff between data
  reorganization overhead and streaming load balance.}
}

@InProceedings{mayr:query,
  author = {Tobias Mayr and Philippe Bonnet and Johannes Gehrke and Praveen
  Seshadri},
  title = {Leveraging Non-Uniform Resources for Parallel Query Processing},
  booktitle = {Proceedings of the Third IEEE/ACM International Symposium on
  Cluster Computing and the Grid},
  year = {2003},
  month = {May},
  pages = {120--129},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo, Japan},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190120abs.htm},
  keywords = {parallel query processing, load balancing, parallel I/O,
  pario-bib},
  abstract = {Modular clusters are now composed of non- uniform nodes with
  different CPUs, disks or network cards so that customers can adapt the
  cluster configuration to the changing technologies and to their changing
  needs. This challenges dataflow parallelism as the primary load balancing
  technique of existing parallel database systems. We show in this paper that
  dataflow parallelism alone is ill suited for modular clusters because running
  the same operation on different subsets of the data can not fully utilize
  non-uniform hardware resources. We propose and evaluate new load balancing
  techniques that blend pipeline parallelism with data parallelism. We consider
  relational operators as pipelines of fine-grained operations that can be
  located on different cluster nodes and executed in parallel on different data
  subsets to best exploit non-uniform resources. We present an experimental
  study that confirms the feasibility and effectiveness of the new techniques
  in a parallel execution engine prototype based on the open-source DBMS
  Predator.}
}

@InProceedings{perez:allocation,
  author = {Jose Maria Perez and Felix Garcia and Jesus Carretero and Alejandro
  Calderon and Luis Miguel Sanchez},
  title = {Data Allocation and Load Balancing for Heterogeneous Cluster Storage
  Systems},
  booktitle = {Workshop on Parallel I/O in Cluster Computing and Computational
  Grids},
  year = {2003},
  month = {May},
  pages = {718--723},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo},
  note = {Organized at the IEEE/ACM International Symposium on Cluster
  Computing and the Grid 2003},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190718abs.htm},
  keywords = {parallel I/O, load balancing, pario-bib},
  abstract = {Distributed filesystems are a typical solution in networked
  environments as clusters and grids. Parallel filesystems are a typical
  solution in order to reach high performance I/O distributed environment, but
  those filesystems have some limitations in heterogeneous storage systems.
  Usually in distributed systems, load balancing is used as a solution to
  improve the performance, but typically the distribution is made between
  peer-to-peer computational resources and from the processor point of view. In
  heterogeneous systems, like heterogeneous clusters of workstations, the
  existing solutions do not work so well. However, the utilization of those
  systems is more extended every day, having an extreme example in the grid
  environment. In this paper we bring attention to those aspects of
  heterogeneous distributed data systems presenting a parallel file system that
  take into account heterogeneity of storage nodes, the dynamic addition of new
  storage nodes, and an algorithm to group requests in heterogeneous systems.}
}

@InProceedings{segawa:pvfs-pm,
  author = {Koji Segawa and Osamu Tatebe and Yuetsu Kodama and Tomohiro Kudoh
  and Toshiyuki Shimizu},
  title = {Design and implementation of {PVFS-PM}: a cluster file system on
  {SC}ore},
  booktitle = {Workshop on Parallel I/O in Cluster Computing and Computational
  Grids},
  year = {2003},
  month = {May},
  pages = {705--711},
  organization = {National Institute of Advanced Industrial Science and
  Technology (AIST)},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo},
  note = {Organized at the IEEE/ACM International Symposium on Cluster
  Computing and the Grid 2003},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190705abs.htm},
  keywords = {parallel I/O, pario-bib},
  abstract = {This paper discusses the design and implementation of a cluster
  file system, called PVFS-PM, on the SCore cluster system software. This is
  the first attempt to implement a cluster file system on the SCore system. It
  is based on the PVFS cluster file system but replaces TCP with the PMv2
  communication library supported by SCore to provide a scalable,
  high-performance cluster file system. PVFS-PM improves the performance by
  factors of 1.07 and 1.93 for writing and reading,respectively, with 8 I/O
  nodes, compared with the original PVFS on TCP on a Gigabit Ethernet-connected
  SCore cluster.}
}

@InProceedings{uk:protein-folding,
  author = {B. Uk and M. Taufer and T. Stricker and G. Settanni and A. Cavalli
  and A. Caflisch},
  title = {Combining Task- and Data Parallelism to Speed up Protein Folding on
  a Desktop Grid Platform},
  booktitle = {Proceedings of the Third IEEE/ACM International Symposium on
  Cluster Computing and the Grid},
  year = {2003},
  month = {May},
  pages = {240--249},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo, Japan},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190240abs.htm},
  keywords = {protein folding, grid application, parallel I/O, pario-app,
  pario-bib},
  abstract = {The steady increase of computing power at lower and lower cost
  enables molecular dynamics simulations to investigate the process of protein
  folding with an explicit treatment of water molecules. Such simulations are
  typically done with well known computational chemistry codes like CHARMM.
  Desktop grids such as the United Devices MetaProcessor are highly attractive
  platforms, since scavenging for unused machines on Intra- and Internet
  delivers compute power that is almost free. However, the predominant
  programming paradigm for current desktop grids is pure task parallelism and
  might not fit the needs for protein folding simulations with explicit water
  molecules. A short overall turn-around time of a simulation remains highly
  important for research productivity, but the need for an accurate model and
  long simulation time-scales leads to tasks that are too large for optimal
  scheduling on a desktop grid. To address this problem, we introduce a
  combination of task- and data parallelism as a well suitable computing
  paradigm for protein folding investigations on grid platforms. As a proof of
  concept, we design and implement a simple system for protein folding
  simulations based on the notion of combined task and data parallelism with
  clustered workers. Clustered workers are machines grouped into small clusters
  according to network and CPU performance criteria and act as super-nodes
  within a desktop grid, permitting the utilization of data parallelism in
  addition to the task parallelism. We integrate our new paradigm into the
  existing software environment of the United Devices MetaProcessor. For a test
  protein, we reach a better quality of the folding calculations than we
  reached using just task parallelism on distributed systems.}
}

@InProceedings{vilayannur:caching,
  author = {Murali Vilayannur and Anand Sivasubramaniam and Mahmut Kandemir and
  Rajeev Thakur and Robert Ross},
  title = {Discretionary Caching for {I/O} on Clusters},
  booktitle = {Proceedings of the Third IEEE/ACM International Symposium on
  Cluster Computing and the Grid},
  year = {2003},
  month = {May},
  pages = {96--103},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo, Japan},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190096abs.htm},
  keywords = {caching, parallel I/O, pario-bib},
  abstract = {I/O bottlenecks are already a problem in many large-scale
  applications that manipulate huge datasets. This problem is expected to get
  worse as applications get larger, and the I/O subsystem performance lags
  behind processor and memory speed improvements. Caching I/O blocks is one
  effective way of alleviating disk latencies, and there can be multiple levels
  of caching on a cluster of workstations. Previous studies have shown the
  benefits of caching - whether it be local to a particular node, or a shared
  global cache across the cluster - for certain applications. However, we show
  that while caching is useful in some situations, it can hurt performance if
  we are not careful about what to cache and when to bypass the cache. This
  paper presents compilation techniques and runtime support to address this
  problem. These techniques are implemented and evaluated on an experimental
  Linux/Pentium cluster running a parallel file system. Our results using a
  diverse set of applications (scientific and commercial) demonstrate the
  benefits of a discretionary approach to caching for I/O subsystems on
  clusters, providing as much as 33% savings over indiscriminately caching
  everything in some applications.}
}

@InProceedings{wiebalck:enbd,
  author = {Arne Wiebalck and Peter T. Breuer and Volker Lindenstruth and Timm
  M. Steinbeck},
  title = {Fault-Tolerant Distributed Mass Storage for LHC Computing},
  booktitle = {Proceedings of the Third IEEE/ACM International Symposium on
  Cluster Computing and the Grid},
  year = {2003},
  month = {May},
  pages = {266--275},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo, Japan},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190266abs.htm},
  keywords = {RAID, fault-tolerance, high-energy physics, parallel I/O,
  pario-app, pario-bib},
  abstract = {In this paper we present the concept and first prototyping
  results of a modular fault-tolerant distributed mass storage architecture for
  large Linux PC clusters as they are deployed by the upcoming particle physics
  experiments. The device masquerading technique using an Enhanced Network
  Block Device (ENBD) enables local RAID over remote disks as the key concept
  of the ClusterRAID system. The block level interface to remote files,
  partitions or disks provided by the ENBD makes it possible to use the
  standard Linux software RAID to add fault-tolerance to the system.
  Preliminary performance measurements indicate that the latency is comparable
  to a local hard drive. With four disks throughput rates of up to 55MB/s were
  achieved with first prototypes for a RAID0 setup, and about 40MB/s for a
  RAID5 setup.}
}

@InProceedings{zhang:n-spek,
  author = {Ming Zhang and Qing Yang},
  title = {Performability Evaluation of Networked Storage Systems Using
  N-SPEK},
  booktitle = {Workshop on Parallel I/O in Cluster Computing and Computational
  Grids},
  year = {2003},
  month = {May},
  pages = {736--741},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo},
  note = {Organized at the IEEE/ACM International Symposium on Cluster
  Computing and the Grid 2003},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190736abs.htm},
  keywords = {benchmarking, performance, block-level access, pario-bib},
  abstract = {This paper introduces a new benchmark tool for evaluating
  performance and availability (performability) of networked storage systems,
  specifically storage area network (SAN) that is intended for providing
  block-level data storage with high performance and availability. The new
  benchmark tool, named N-SPEK (Networked-Storage Performability Evaluation
  Kernel module), consists of a controller, several workers, one or more
  probers, and several fault injection modules. N-SPEK is highly accurate and
  efficient since it runs at kernel level and eliminates skews and overheads
  caused by file systems. It allows a SAN architect to generate configurable
  storage workloads to the SAN under test and to inject different faults into
  various SAN components such as network devices, storage devices, and
  controllers. Available performances under different workloads and failure
  conditions are dynamically collected and recorded in the N-SPEK over a
  spectrum of time. To demonstrate its functionality, we apply N-SPEK to
  evaluate the performability of a specific iSCSI-based SAN under Linux
  environment. Our experiments show that N-SPEK not only efficiently generates
  quantitative performability results but also reveals a few optimization
  opportunities for future iSCSI implementations.}
}

@InProceedings{zhou:greedy,
  author = {Xinrong Zhou and Tong Wei},
  title = {A Greedy {I/O} Scheduling Method in the Storage System of Clusters},
  booktitle = {Workshop on Parallel I/O in Cluster Computing and Computational
  Grids},
  year = {2003},
  month = {May},
  pages = {712--717},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo},
  note = {Organized at the IEEE/ACM International Symposium on Cluster
  Computing and the Grid 2003},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190712abs.htm},
  keywords = {parallel I/O, disk scheduling, pario-bib},
  abstract = {As the size of cluster becomes larger, the process ability of a
  cluster increases rapidly. Users will exploit this increased power to run
  scientific, physical and multimedia applications. These kinds of
  data-intensive applications require high performance storage subsystem.
  Parallel storage system such as RAID is widely used in today's clusters. In
  this paper, we bring out a "greedy" I/O scheduling method that utilizes
  Scatter and Gather operations inside the PCI-SCSI adapter to combine as many
  I/O operations within the same disk as possible. In this way we reduce the
  numbers of I/O operations and improve the performance of the whole storage
  system. After analyzing RAID control strategy, we find out that I/O commands'
  combination may also bring up data movement in memory and this kind of
  movement will increase the system's overhead. The experiment results in our
  real time operating environment show that a better performance can be
  achieved. The longer the data length is, the better improvement we can get,
  in some case, we can even get over 40% enhancement.}
}

@InProceedings{zhu:ceft-pvfs,
  author = {Yifeng Zhu and Hong Jiang and Xiao Qin and Dan Feng and David R.
  Swanson},
  title = {Improved Read Performance in a Cost-Effective, Fault-Tolerant
  Parallel Virtual File System {(CEFT-PVFS)}},
  booktitle = {Workshop on Parallel I/O in Cluster Computing and Computational
  Grids},
  year = {2003},
  month = {May},
  pages = {730--735},
  publisher = {IEEE Computer Society Press},
  address = {Tokyo},
  note = {Organized at the IEEE/ACM International Symposium on Cluster
  Computing and the Grid 2003},
  URL =
  {http://csdl.computer.org/comp/proceedings/ccgrid/2003/1919/00/19190730abs.htm},
  keywords = {parallel I/O, fault-tolerance, read performance, parallel file
  system, PVFS, pario-bib},
  abstract = {Due to the ever-widening performance gap between processors and
  disks, I/O operations tend to become the major performance bottleneck of
  data-intensive applications on modern clusters. If all the existing disks on
  the nodes of a cluster are connected together to establish high performance
  parallel storage systems, the cluster's overall performance can be boosted at
  no additional cost. CEFT-PVFS (a RAID 10 style parallel file system that
  extends the original PVFS), as one such system, divides the cluster nodes
  into two groups, stripes the data across one group in a round-robin fashion,
  and then duplicates the same data to the other group to provide storage
  service of high performance and high reliability. Previous research has shown
  that the system reliability is improved by a factor of more than 40 with
  mirroring while maintaining a comparable write performance. This paper
  presents another benefit of CEFT-PVFS in which the aggregate peak read
  performance can be improved by as much as 100% over that of the original PVFS
  by exploiting the increased parallelism. \par Additionally, when the data
  servers, which typically are also computational nodes in a cluster
  environment, are loaded in an unbalanced way by applications running in the
  cluster, the read performance of PVFS will be degraded significantly. On the
  contrary, in the CEFT-PVFS, a heavily loaded data server can be skipped and
  all the desired data is read from its mirroring node. Thus the performance
  will not be affected unless both the server node and its mirroring node are
  heavily loaded.}
}