@masterthesis{Dillmann2013, type = {Bachelor Thesis}, author = {Dillmann, Johannes}, title = {Konsistentes Hinzuf{\"u}gen und Entfernen von Replikaten in XtreemFS}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-43109}, school = {Zuse Institute Berlin (ZIB)}, pages = {42}, year = {2013}, abstract = {In replizierten Systemen muss es m{\"o}glich sein ausgefallene Server zu ersetzen und Replikate dynamisch hinzuzuf{\"u}gen oder zu entfernen. Ver{\"a}nderungen an der Menge der eingesetzten Replikate k{\"o}nnen zu inkonsistenten Daten f{\"u}hren. In dieser Arbeit wird ein Algorithmus f{\"u}r das konsistente Hinzuf{\"u}gen und Entfernen von Replikaten f{\"u}r das verteilte Dateisystem XtreemFS vorgestellt. Der Algorithmus nutzt einen fehlertoleranten Service, der die Replikatliste speichert sowie Ver{\"a}nderungen koordiniert und diese aus globaler Sicht atomar ausf{\"u}hrt.}, language = {de} } @masterthesis{Kairies2013, type = {Bachelor Thesis}, author = {Kairies, Lukas}, title = {Leistungsanalyse von XtreemFS als Ersatz f{\"u}r HDFS in Hadoop}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-43130}, school = {Zuse Institute Berlin (ZIB)}, pages = {46}, year = {2013}, abstract = {In dieser Arbeit wird die Leistungsf{\"a}higkeit des MapReduce-Framework Hadoop mit XtreemFS als verteiltes und POSIX-konformes Dateisystem bestimmt. Damit wird XtreemFS das f{\"u}r die Nutzung mit Hadoop entwickelte Dateisystem HDFS ersetzen. HDFS und XtreemFS werden verglichen und XtreemFS f{\"u}r Nutzung unter Hadoop konfiguriert. Zudem werden Optimierungen an der Hadoop-Schnittstelle von XtreemFS vorgenommen. Die Leistung von Hadoop mit XtreemFS wird mittels synthetischer Benchmarks und realer Hadoop Anwendungen gemessen und mit der Leistung von Hadoop mit HDFS verglichen.}, language = {de} } @inproceedings{SchmidtkeSchintkeSchuett2018, author = {Schmidtke, Robert and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {From Application to Disk: Tracing I/O Through the Big Data Stack}, booktitle = {High Performance Computing ISC High Performance 2018 International Workshops, Frankfurt/Main, Germany, June 24 - 28, 2018, Revised Selected Papers, Workshop on Performance and Scalability of Storage Systems (WOPSSS)}, doi = {10.1007/978-3-030-02465-9_6}, pages = {89 -- 102}, year = {2018}, abstract = {Typical applications in data science consume, process and produce large amounts of data, making disk I/O one of the dominating — and thus worthwhile optimizing — factors of their overall performance. Distributed processing frameworks, such as Hadoop, Flink and Spark, hide a lot of complexity from the programmer when they parallelize these applications across a compute cluster. This exacerbates reasoning about I/O of both the application and the framework, through the distributed file system, such as HDFS, down to the local file systems. We present SFS (Statistics File System), a modular framework to trace each I/O request issued by the application and any JVM-based big data framework involved, mapping these requests to actual disk I/O. This allows detection of inefficient I/O patterns, both by the applications and the underlying frameworks, and builds the basis for improving I/O scheduling in the big data software stack.}, language = {en} } @inproceedings{Peter2011, author = {Peter, Kathrin}, title = {Reliability Study of Coding Schemes for Wide-Area Distributed Storage Systems}, booktitle = {PDP 2011: The 19th Euromicro International Conference on Parallel, Distributed and Network-Based Computing}, publisher = {Euromicro}, doi = {10.1109/PDP.2011.70}, year = {2011}, language = {en} } @inproceedings{StenderKolbeckHoegqvistetal.2010, author = {Stender, Jan and Kolbeck, Bj{\"o}rn and H{\"o}gqvist, Mikael and Hupfeld, Felix}, title = {BabuDB: Fast and Efficient File System Metadata Storage}, booktitle = {Storage Network Architecture and Parallel I/Os, IEEE International Workshop on}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, doi = {10.1109/SNAPI.2010.14}, pages = {51 -- 58}, year = {2010}, language = {en} } @article{KolbeckHoegqvistStenderetal.2011, author = {Kolbeck, Bj{\"o}rn and H{\"o}gqvist, Mikael and Stender, Jan and Hupfeld, Felix}, title = {Flease - Lease Coordination Without a Lock Server}, volume = {0}, journal = {Parallel and Distributed Processing Symposium, International}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, doi = {10.1109/IPDPS.2011.94}, pages = {978 -- 988}, year = {2011}, language = {en} } @phdthesis{Kolbeck2012, author = {Kolbeck, Bj{\"o}rn}, title = {A fault-tolerant and scalable protocol for replication in distributed file systems}, year = {2012}, language = {en} } @inproceedings{PeterReinefeld2012, author = {Peter, Kathrin and Reinefeld, Alexander}, title = {Consistency and fault tolerance for erasure-coded distributed storage systems}, booktitle = {Proceedings of the fifth international workshop on Data-Intensive Distributed Computing Date}, publisher = {ACM}, address = {New York, NY, USA}, doi = {10.1145/2286996.2287002}, pages = {23 -- 32}, year = {2012}, language = {en} } @inproceedings{PeterSobe2012, author = {Peter, Kathrin and Sobe, Peter}, title = {Application of Regenerating Codes for Fault Tolerance in Distributed Storage Systems}, booktitle = {Network Computing and Applications (NCA), 2012 11th IEEE International Symposium on}, doi = {10.1109/NCA.2012.35}, pages = {67 -- 70}, year = {2012}, language = {en} } @incollection{StenderBerlinReinefeld2013, author = {Stender, Jan and Berlin, Michael and Reinefeld, Alexander}, title = {XtreemFS - a File System for the Cloud}, booktitle = {Data Intensive Storage Services for Cloud Environments}, editor = {Kyriazis, D. and Voulodimos, A. and Gogouvitis, S. and Varvarigou, Theodora A.}, publisher = {IGI Global}, doi = {10.4018/978-1-4666-3934-8}, year = {2013}, language = {en} } @phdthesis{Sobe2013, author = {Sobe, Kathrin}, title = {Consistency and Fault Tolerance of Distributed Storage Systems}, year = {2013}, language = {en} } @phdthesis{Stender2013, author = {Stender, Jan}, title = {Snapshots in Large-Scale Distributed File Systems}, year = {2013}, language = {en} } @article{Schintke2013, author = {Schintke, Florian}, title = {XtreemFS \& Scalaris}, journal = {Science \& Technology}, number = {6}, publisher = {Pan European Networks}, pages = {54 -- 55}, year = {2013}, language = {en} } @article{Berlin2013, author = {Berlin, Michael}, title = {Consistent and Partition-Tolerant File Replication in the Cloud File System Xtreem FS}, volume = {36}, journal = {Praxis der Informationsverarbeitung und Kommunikation}, number = {1}, doi = {10.1515/pik-2012-0144}, pages = {39}, year = {2013}, language = {en} } @misc{Dillmann2017, type = {Master Thesis}, author = {Dillmann, Johannes}, title = {Implementierung und Evaluation von Erasure Coding im verteilten Dateisystem XtreemFS}, year = {2017}, language = {de} } @misc{Lieser2016, type = {Master Thesis}, author = {Lieser, Philippe}, title = {Ende-zu-Ende Verschl{\"u}sselung in XtreemFS}, year = {2016}, language = {de} } @inproceedings{SteinkePeterBorchert2010, author = {Steinke, Thomas and Peter, Kathrin and Borchert, Sebastian}, title = {Efficiency Considerations of Cauchy Reed-Solomon Implementations on Accelerator and Multi-Core Platforms}, booktitle = {Symposium on Application Accelerators in High Performance Computing (SAAHPC)}, address = {Knoxville, USA}, year = {2010}, language = {en} } @inproceedings{StenderHoegqvistKolbeck2010, author = {Stender, Jan and H{\"o}gqvist, Mikael and Kolbeck, Bj{\"o}rn}, title = {Loosely Time-Synchronized Snapshots in Object-Based File Systems}, booktitle = {Proceedings of the 29th IEEE International Performance, Computing, and Communications Conference}, publisher = {IEEE Computer Society}, doi = {10.1109/PCCC.2010.5682311}, year = {2010}, language = {en} } @inproceedings{SobePeter2008, author = {Sobe, Peter and Peter, Kathrin}, title = {Flexible Parameterization of XOR based Codes for Distributed Storage}, booktitle = {Proceedings of The Seventh IEEE International Symposium on Networking Computing and Applications, NCA 2008, July 10-12, 2008, Cambridge, Massachusetts, USA}, publisher = {IEEE Computer Society}, doi = {10.1109/NCA.2008.45}, pages = {101 -- 110}, year = {2008}, language = {en} } @article{Kolbeck2009, author = {Kolbeck, Bj{\"o}rn}, title = {A Protocol for Efficient and Fault-tolerant File Replication over Wide-Area Networks}, volume = {0}, journal = {TCPP Ph.D. Forum, Int. Parallel and Distributed Processing Symposium}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, doi = {10.1109/IPDPS.2009.5160863}, pages = {19}, year = {2009}, language = {en} }