@article{SeibertPetersSchintke2018, author = {Seibert, Felix and Peters, Mathias and Schintke, Florian}, title = {Improving I/O Performance Through Colocating Interrelated Input Data and Near-Optimal Load Balancing}, volume = {2018}, journal = {Proceedings of the IPDPSW; Fourth IEEE International Workshop on High-Performance Big Data, Deep Learning, and Cloud Computing (HPBDC)}, doi = {10.1109/IPDPSW.2018.00081}, pages = {448 -- 457}, year = {2018}, abstract = {Most distributed file systems assign new files to storage servers randomly. While working well in some situations, this does not help to optimize the input performance for most MapReduce computations' data access patterns. In this work, we consider an access pattern where input files are partitioned into groups of heterogeneous size. Each group is accessed by exactly one process. We design and implement a data placement strategy that places these file groups together on the same storage server. This colocation approach is combined with near-optimal storage load balancing. To do so, we use a classical scheduling approximation algorithm to solve the NP hard group assignment problem. We argue that local processing is not only beneficial because of reduced network traffic, but especially because it imposes an even resource schedule. Our experiments, based on the parallel processing of remote sensing images, reveal an enormous reduction of network traffic and up to 39 \% faster input read times. Further, simulations show that our approximate assignments limit storage server imbalances to less than 5 \% above the theoretical minimum, in contrast to more than 85 \% with random assignment.}, language = {en} } @misc{SchefflerSipsBehlingetal.2016, author = {Scheffler, Daniel and Sips, Mike and Behling, Robert and Dransch, Doris and Eggert, Daniel and Fajerski, Jan and Freytag, Johann-Christoph and Griffiths, Patrick and Hollstein, Andr{\´e} and Hostert, Patrick and K{\"o}thur, Patrick and Peters, Mathias and Pflugmacher, Dirk and Rabe, Andreas and Reinefeld, Alexander and Schintke, Florian and Segel, Karl}, title = {GeoMultiSens - Scalable Multisensoral Analysis of Satellite Remote Sensing Data}, journal = {ESA Living Planet Symposium, EO Open Science Posters}, year = {2016}, language = {en} } @inproceedings{SchefflerSipsBehlingetal.2016, author = {Scheffler, Daniel and Sips, Mike and Behling, Robert and Dransch, Doris and Eggert, Daniel and Fajerski, Jan and Freytag, Johann-Christoph and Griffiths, Patrick and Hollstein, Andr{\´e} and Hostert, Patrick and K{\"o}thur, Patrick and Peters, Mathias and Pflugmacher, Dirk and Rabe, Andreas and Reinefeld, Alexander and Schintke, Florian and Segel, Karl}, title = {Geomultisens - a common automatic processing and analysis system for multi-sensor satellite data}, booktitle = {Advancing Horizons for Land Cover Services Entering the Big Data Era, Second joint Workshop of the EARSeL Special Interest Group on Land Use \& Land Cover and the NASA LCLUC Program}, pages = {18 -- 19}, year = {2016}, language = {en} }