- About
-
The Global ETD Search service is a free service for researchers
to find electronic theses and dissertations. This service is
provided by the
Networked Digital Library of Theses and Dissertations.
Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
Search results
Showing 1 to 4 of 4 (0.103 seconds)Spelling suggestions: "subject:"arallel file atemsystem"" "subject:"arallel file systsystem""
| 1 |
Comparison and End-to-End Performance Analysis of Parallel FilesystemsKluge, Michael 20 September 2011 (has links) (PDF)
This thesis presents a contribution to the field of performance analysis for Input/Output (I/O) related problems, focusing on the area of High Performance Computing (HPC).
Beside the compute nodes, High Performance Computing systems need a large amount of supporting components that add their individual behavior to the overall performance characteristic of the whole system. Especially file systems in such environments have their own infrastructure. File operations are typically initiated at the compute nodes and proceed through a deep software stack until the file content arrives at the physical medium. There is a handful of shortcomings that characterize the current state of the art for performance analyses in this area. This includes a system wide data collection, a comprehensive analysis approach for all collected data, an adjusted trace event analysis for I/O related problems, and methods to compare current with archived performance data.
This thesis proposes to instrument all soft- and hardware layers to enhance the performance analysis for file operations. The additional information can be used to investigate performance characteristics of parallel file systems. To perform I/O analyses on HPC systems, a comprehensive approach is needed to gather related performance events, examine the collected data and, if necessary, to replay relevant parts on different systems. One larger part of this thesis is dedicated to algorithms that reduce the amount of information that are found in trace files to the level that is needed for an I/O analysis. This reduction is based on the assumption that for this type of analysis all I/O events, but only a subset of all synchronization events of a parallel program trace have to be considered. To extract an I/O pattern from an event trace, only these synchronization points are needed that describe dependencies among different I/O requests. Two algorithms are developed to remove negligible events from the event trace.
Considering the related work for the analysis of a parallel file systems, the inclusion of counter data from external sources, e.g. the infrastructure of a parallel file system, has been identified as a major milestone towards a holistic analysis approach. This infrastructure contains a large amount of valuable information that are essential to describe performance effects observed in applications. This thesis presents an approach to collect and subsequently process and store the data. Certain ways how to correctly merge the collected values with application traces are discussed. Here, a revised definition of the term "performance counter" is the first step followed by a tree based approach to combine raw values into secondary values. A visualization approach for I/O patterns closes another gap in the analysis process.
Replaying I/O related performance events or event patterns can be done by a flexible I/O benchmark. The constraints for the development of such a benchmark are identified as well as the overall architecture for a prototype implementation.
Finally, different examples demonstrate the usage of the developed methods and show their potential. All examples are real use cases and are situated on the HRSK research complex and the 100GBit Testbed at TU Dresden. The I/O related parts of a Bioinformatics and a CFD application have been analyzed in depth and enhancements for both are proposed. An instance of a Lustre file system was deployed and tuned on the 100GBit Testbed by the extensive use of external performance counters.
|
| 2 |
Comparison and End-to-End Performance Analysis of Parallel FilesystemsKluge, Michael 05 September 2011 (has links)
This thesis presents a contribution to the field of performance analysis for Input/Output (I/O) related problems, focusing on the area of High Performance Computing (HPC).
Beside the compute nodes, High Performance Computing systems need a large amount of supporting components that add their individual behavior to the overall performance characteristic of the whole system. Especially file systems in such environments have their own infrastructure. File operations are typically initiated at the compute nodes and proceed through a deep software stack until the file content arrives at the physical medium. There is a handful of shortcomings that characterize the current state of the art for performance analyses in this area. This includes a system wide data collection, a comprehensive analysis approach for all collected data, an adjusted trace event analysis for I/O related problems, and methods to compare current with archived performance data.
This thesis proposes to instrument all soft- and hardware layers to enhance the performance analysis for file operations. The additional information can be used to investigate performance characteristics of parallel file systems. To perform I/O analyses on HPC systems, a comprehensive approach is needed to gather related performance events, examine the collected data and, if necessary, to replay relevant parts on different systems. One larger part of this thesis is dedicated to algorithms that reduce the amount of information that are found in trace files to the level that is needed for an I/O analysis. This reduction is based on the assumption that for this type of analysis all I/O events, but only a subset of all synchronization events of a parallel program trace have to be considered. To extract an I/O pattern from an event trace, only these synchronization points are needed that describe dependencies among different I/O requests. Two algorithms are developed to remove negligible events from the event trace.
Considering the related work for the analysis of a parallel file systems, the inclusion of counter data from external sources, e.g. the infrastructure of a parallel file system, has been identified as a major milestone towards a holistic analysis approach. This infrastructure contains a large amount of valuable information that are essential to describe performance effects observed in applications. This thesis presents an approach to collect and subsequently process and store the data. Certain ways how to correctly merge the collected values with application traces are discussed. Here, a revised definition of the term "performance counter" is the first step followed by a tree based approach to combine raw values into secondary values. A visualization approach for I/O patterns closes another gap in the analysis process.
Replaying I/O related performance events or event patterns can be done by a flexible I/O benchmark. The constraints for the development of such a benchmark are identified as well as the overall architecture for a prototype implementation.
Finally, different examples demonstrate the usage of the developed methods and show their potential. All examples are real use cases and are situated on the HRSK research complex and the 100GBit Testbed at TU Dresden. The I/O related parts of a Bioinformatics and a CFD application have been analyzed in depth and enhancements for both are proposed. An instance of a Lustre file system was deployed and tuned on the 100GBit Testbed by the extensive use of external performance counters.
|
| 3 |
Sistemas de arquivos paralelos: alternativas para a redução do gargalo no acesso ao sistema de arquivos / Parallel File Systems: alternatives to reduce the bottleneck in accessing the file systemCarvalho, Roberto Pires de 23 September 2005 (has links)
Nos últimos anos, a evolução dos processadores e redes para computadores de baixo custo foi muito maior se comparada com o aumento do desempenho dos discos de armazenamento de dados. Com isso, muitas aplicações estão encontrando dificuldades em atingir o pleno uso dos processadores, pois estes têm de esperar até que os dados cheguem para serem utilizados. Uma forma popular para resolver esse tipo de empecílio é a adoção de sistemas de arquivos paralelos, que utilizam a velocidade da rede local, além dos recursos de cada máquina, para suprir a deficiência de desempenho no uso isolado de cada disco. Neste estudo, analisamos alguns sistemas de arquivos paralelos e distribuídos, detalhando aqueles mais interessantes e importantes. Por fim, mostramos que o uso de um sistema de arquivos paralelo pode ser mais eficiente e vantajoso que o uso de um sistema de arquivos usual, para apenas um cliente. / In the last years, the evolution of the data processing power and network transmission for low cost computers was much bigger if compared to the increase of the speed of getting the data stored in disks. Therefore, many applications are finding difficulties in reaching the full use of the processors, because they have to wait until the data arrive before using. A popular way to solve this problem is to use a parallel file system, which uses the local network speed to avoid the performance bottleneck found in an isolated disk. In this study, we analyze some parallel and distributed file systems, detailing the most interesting and important ones. Finally, we show the use of a parallel file system can be more efficient than the use of a usual local file system, for just one client.
|
| 4 |
Sistemas de arquivos paralelos: alternativas para a redução do gargalo no acesso ao sistema de arquivos / Parallel File Systems: alternatives to reduce the bottleneck in accessing the file systemRoberto Pires de Carvalho 23 September 2005 (has links)
Nos últimos anos, a evolução dos processadores e redes para computadores de baixo custo foi muito maior se comparada com o aumento do desempenho dos discos de armazenamento de dados. Com isso, muitas aplicações estão encontrando dificuldades em atingir o pleno uso dos processadores, pois estes têm de esperar até que os dados cheguem para serem utilizados. Uma forma popular para resolver esse tipo de empecílio é a adoção de sistemas de arquivos paralelos, que utilizam a velocidade da rede local, além dos recursos de cada máquina, para suprir a deficiência de desempenho no uso isolado de cada disco. Neste estudo, analisamos alguns sistemas de arquivos paralelos e distribuídos, detalhando aqueles mais interessantes e importantes. Por fim, mostramos que o uso de um sistema de arquivos paralelo pode ser mais eficiente e vantajoso que o uso de um sistema de arquivos usual, para apenas um cliente. / In the last years, the evolution of the data processing power and network transmission for low cost computers was much bigger if compared to the increase of the speed of getting the data stored in disks. Therefore, many applications are finding difficulties in reaching the full use of the processors, because they have to wait until the data arrive before using. A popular way to solve this problem is to use a parallel file system, which uses the local network speed to avoid the performance bottleneck found in an isolated disk. In this study, we analyze some parallel and distributed file systems, detailing the most interesting and important ones. Finally, we show the use of a parallel file system can be more efficient than the use of a usual local file system, for just one client.
|
Page generated in 0.115 seconds