@inproceedings{KlettkeStoerlShenavaietal., author = {Klettke, Meike and St{\"o}rl, Uta and Shenavai, Manuel and Scherzinger, Stefanie and Storl, Uta}, title = {NoSQL schema evolution and big data migration at scale}, series = {2016 IEEE International Conference on Big Data (Big Data), 5-8 Dec. 2016, Washington, DC}, booktitle = {2016 IEEE International Conference on Big Data (Big Data), 5-8 Dec. 2016, Washington, DC}, publisher = {IEEE}, doi = {10.1109/BigData.2016.7840924}, pages = {2764 -- 2774}, abstract = {This paper explores scalable implementation strategies for carrying out lazy schema evolution in NoSQL data stores. For decades, schema evolution has been an evergreen in database research. Yet new challenges arise in the context of cloud-hosted data backends: With all database reads and writes charged by the provider, migrating the entire data instance eagerly into a new schema can be prohibitively expensive. Thus, lazy migration may be more cost-efficient, as legacy entities are only migrated in case they are actually accessed by the application. Related work has shown that the overhead of migrating data lazily is affordable when a single evolutionary change is carried out, such as adding a new property. In this paper, we focus on long-term schema evolution, where chains of pending schema evolution operations may have to be applied. Chains occur when legacy entities written several application releases back are finally accessed by the application. We discuss strategies for dealing with chains of evolution operations, in particular, the composition into a single, equivalent composite migration that performs the required version jump. Our experiments with MongoDB focus on scalable implementation strategies. Our lineup further compares the number of write operations, and thus, the operational costs of different data migration strategies.}, language = {en} } @inproceedings{StoerlTekleabKlettkeetal., author = {St{\"o}rl, Uta and Tekleab, Alexander and Klettke, Meike and Scherzinger, Stefanie and Storl, Uta}, title = {In for a Surprise When Migrating NoSQL Data}, series = {2018 IEEE 34th International Conference on Data Engineering (ICDE), 16-19 April 2018, Paris, France}, booktitle = {2018 IEEE 34th International Conference on Data Engineering (ICDE), 16-19 April 2018, Paris, France}, publisher = {IEEE}, doi = {10.1109/ICDE.2018.00202}, pages = {1662}, abstract = {Schema-flexible NoSQL data stores lend themselves nicely for storing versioned data, a product of schema evolution. In this lightning talk, we apply pending schema changes to records that have been persisted several schema versions back. We present first experiments with MongoDB and Cassandra, where we explore the trade-off between applying chains of pending changes stepwise (one after the other), and as composite operations. Contrary to intuition, composite migration is not necessarily faster. The culprit is the computational overhead for deriving the compositions. However, caching composition formulae achieves a speed up: For Cassandra, we can cut the runtime by nearly 80\%. Surprisingly, the relative speedup seems to be system-dependent. Our take away message is that in applying pending schema changes in NoSQL data stores, we need to base our design decisions on experimental evidence rather than on intuition alone.}, language = {en} } @inproceedings{StoerlMuellerTekleabetal., author = {St{\"o}rl, Uta and M{\"u}ller, Daniel and Tekleab, Alexander and Tolale, Stephane and Stenzel, Julian and Klettke, Meike and Scherzinger, Stefanie and Storl, Uta and Muller, Daniel}, title = {Curating Variational Data in Application Development}, series = {2018 IEEE 34th International Conference on Data Engineering, 16-19 April 2018, Paris, France}, booktitle = {2018 IEEE 34th International Conference on Data Engineering, 16-19 April 2018, Paris, France}, publisher = {IEEE}, doi = {10.1109/ICDE.2018.00187}, pages = {1605 -- 1608}, abstract = {Building applications for processing data lakes is a software engineering challenge. We present Darwin, a middleware for applications that operate on variational data. This concerns data with heterogeneous structure, usually stored within a schema-flexible NoSQL database. Darwin assists application developers in essential data and schema curation tasks: Upon request, Darwin extracts a schema description, discovers the history of schema versions, and proposes mappings between these versions. Users of Darwin may interactively choose which mappings are most realistic. Darwin is further capable of rewriting queries at runtime, to ensure that queries also comply with legacy data. Alternatively, Darwin can migrate legacy data to reduce the structural heterogeneity. Using Darwin, developers may thus evolve their data in sync with their code. In our hands-on demo, we curate synthetic as well as real-life datasets.}, language = {en} } @inproceedings{KlettkeAwolinStoerletal., author = {Klettke, Meike and Awolin, Hannes and St{\"o}rl, Uta and M{\"u}ller, Daniel and Scherzinger, Stefanie and Storl, Uta and Muller, Daniel}, title = {Uncovering the evolution history of data lakes}, series = {2017 IEEE International Conference on Big Data (Big Data),,11-14 Dec. 2017, Boston, MA, USA}, booktitle = {2017 IEEE International Conference on Big Data (Big Data),,11-14 Dec. 2017, Boston, MA, USA}, publisher = {IEEE}, doi = {10.1109/BigData.2017.8258204}, pages = {2462 -- 2471}, abstract = {Data accumulating in data lakes can become inaccessible in the long run when its semantics are not available. The heterogeneity of data formats and the sheer volumes of data collections prohibit cleaning and unifying the data manually. Thus, tools for automated data lake analysis are of great interest. In this paper, we target the particular problem of reconstructing the schema evolution history from data lakes. Knowing how the data is structured, and how this structure has evolved over time, enables programmatic access to the lake. By deriving a sequence of schema versions, rather than a single schema, we take into account structural changes over time. Moreover, we address the challenge of detecting inclusion dependencies. This is a prerequisite for mapping between succeeding schema versions, and in particular, detecting nontrivial changes such as a property having been moved or copied. We evaluate our approach for detecting inclusion dependencies using the MovieLens dataset, as well an adaption of a dataset containing botanical descriptions, to cover specific edge cases.}, language = {en} } @misc{ScharfenbergMottokArtmannetal., author = {Scharfenberg, Georg and Mottok, J{\"u}rgen and Artmann, Christina and Hobelsberger, Martin and Paric, Ivan and Großmann, Benjamin and Pohlt, Clemens and Wackerbarth, Alena and Pausch, Uli and Heidrich, Christiane and Fadanelli, Martin and Elsner, Michael and P{\"o}cher, Daniel and Pittroff, Lenz and Beer, Stefan and Br{\"u}ckl, Oliver and Haslbeck, Matthias and Sterner, Michael and Thema, Martin and Muggenthaler, Nicole and Lenck, Thorsten and G{\"o}tz, Philipp and Eckert, Fabian and Deubzer, Michael and Stingl, Armin and Simsek, Erol and Kr{\"a}mer, Stefan and Großmann, Benjamin and Schlegl, Thomas and Niedersteiner, Sascha and Berlehner, Thomas and Joblin, Mitchell and Mauerer, Wolfgang and Apel, Sven and Siegmund, Janet and Riehle, Dirk and Weber, Joachim and Palm, Christoph and Zobel, Martin and Al-Falouji, Ghassan and Prestel, Dietmar and Scharfenberg, Georg and Mandl, Roland and Deinzer, Arnulf and Halang, W. and Margraf-Stiksrud, Jutta and Sick, Bernhard and Deinzer, Renate and Scherzinger, Stefanie and Klettke, Meike and St{\"o}rl, Uta and Wiech, Katharina and Kubata, Christoph and Sindersberger, Dirk and Monkman, Gareth J. and Dollinger, Markus and Dembianny, Sven and K{\"o}lbl, Andreas and Welker, Franz and Meier, Matthias and Thumann, Philipp and Swidergal, Krzysztof and Wagner, Marcus and Haug, Sonja and Vernim, Matthias and Seidenst{\"u}cker, Barbara and Weber, Karsten and Arsan, Christian and Schone, Reinhold and M{\"u}nder, Johannes and Schroll-Decker, Irmgard and Dillinger, Andrea Elisabeth and Fuchshofer, Rudolf and Monkman, Gareth J. and Shamonin (Chamonine), Mikhail and Geith, Markus A. and Koch, Fabian and {\"U}hlin, Christian and Schratzenstaller, Thomas and Saßmannshausen, Sean Patrick and Auchter, Eberhard and Kriz, Willy and Springer, Othmar and Thumann, Maria and Kusterle, Wolfgang and Obermeier, Andreas and Udalzow, Anton and Schmailzl, Anton and Hierl, Stefan and Langer, Christoph and Schreiner, Rupert}, title = {Forschungsbericht / Ostbayerische Technische Hochschule Regensburg}, editor = {Baier, Wolfgang}, address = {Regensburg}, organization = {Ostbayerische Technische Hochschule Regensburg}, isbn = {978-3-00-048589-3}, doi = {10.35096/othr/pub-1386}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-13867}, language = {de} } @misc{BeimlerLeisslEbneretal., author = {Beimler, Josef and Leißl, Caroline and Ebner, Lena and Elsner, Michael and M{\"u}hlbauer, Gerhard and Kohlert, Dieter and Schubert, Martin J. W. and Weiß, Andreas P. and Sterner, Michael and Raith, Thomas and Afranseder, Martin and Krapf, Tobias and Mottok, J{\"u}rgen and Siemers, Christian and Großmann, Benjamin and H{\"o}cherl, Johannes and Schlegl, Thomas and Schneider, Ralph and Milaev, Johannes and Rampelt, Christina and Roduner, Christian and Glowa, Christoph and Bachl, Christoph and Schliekmann, Claus and Gnan, Alfons and Grill, Martin and Ruhland, Karl and Piehler, Thomas and Friers, Daniel and Wels, Harald and Pflug, Kenny and Kucera, Markus and Waas, Thomas and Schlachetzki, Felix and Boy, Sandra and Pemmerl, Josef and Leis, Alexander and Welsch, Andreas F.X. and Graf, Franz and Zenger, Gerhard and Volbert, Klaus and Waas, Thomas and Scherzinger, Stefanie and Klettke, Meike and St{\"o}rl, Uta and Heyl, C. and Boldenko, A. and Monkman, Gareth J. and Kujat, Richard and Briem, Ulrich and Hierl, Stefan and Talbot, Sebastian and Schmailzl, Anton and Ławrowski, Robert Damian and Prommesberger, Christian and Langer, Christoph and Dams, Florian and Schreiner, Rupert and Valentino, Piergiorgio and Romano, Marco and Ehrlich, Ingo and Furgiuele, Franco and Gebbeken, Norbert and Eisenried, Michael and Jungbauer, Bastian and Hutterer, Albert and Bauhuber, Michael and Mikrievskij, Andreas and Argauer, Monika and Hummel, Helmut and Lechner, Alfred and Liebetruth, Thomas and Schumm, Michael and Joseph, Saskia and Reschke, Michael and Soska, Alexander and Schroll-Decker, Irmgard and Putzer, Michael and Rasmussen, John and Dendorfer, Sebastian and Weber, Tim and Al-Munajjed, Amir Andreas and Verkerke, Gijsbertus Jacob and Renkawitz, Tobias and Haug, Sonja and Rudolph, Clarissa and Zeitler, Annika and Schaubeck, Simon and Steffens, Oliver and Rechenauer, Christian and Schulz-Brize, Thekla and Fleischmann, Florian and Kusterle, Wolfgang and Beer, Anne and Wagner, Bernd and Neidhart, Thomas}, title = {Forschungsbericht 2013}, editor = {Baier, Wolfgang}, address = {Regensburg}, organization = {Ostbayerische Technische Hochschule Regensburg}, doi = {10.35096/othr/pub-799}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-7990}, pages = {80}, language = {de} } @misc{WeberDendorferSuessetal., author = {Weber, Karsten and Dendorfer, Sebastian and S{\"u}ß, Franz and Kubowitsch, Simone and Schratzenstaller, Thomas and Haug, Sonja and Mohr, Christa and Kiesl, Hans and Drechsler, J{\"o}rg and Westner, Markus and Kobus, J{\"o}rn and Schubert, Martin J. W. and Zenger, Stefan and Pietsch, Alexander and Weiß, Josef and Hinterseer, Sebastian and Schieck, Roland and Scherzinger, Stefanie and Klettke, Meike and Ringlstetter, Andreas and St{\"o}rl, Uta and Bissyand{\´e}, Tegawend{\´e} F. and Seeburger, Achim and Schindler, Timo and Ramsauer, Ralf and Kiszka, Jan and K{\"o}lbl, Andreas and Lohmann, Daniel and Mauerer, Wolfgang and Maier, Johannes and Scorna, Ulrike and Palm, Christoph and Soska, Alexander and Mottok, J{\"u}rgen and Ellermeier, Andreas and V{\"o}gele, Daniel and Hierl, Stefan and Briem, Ulrich and Buschmann, Knut and Ehrlich, Ingo and Pongratz, Christian and Pielmeier, Benjamin and Tyroller, Quirin and Monkman, Gareth J. and Gut, Franz and Roth, Carina and Hausler, Peter and Bierl, Rudolf and Prommesberger, Christian and Ławrowski, Robert Damian and Langer, Christoph and Schreiner, Rupert and Huang, Yifeng and She, Juncong and Ottl, Andreas and Rieger, Walter and Kraml, Agnes and Poxleitner, Thomas and Hofer, Simon and Heisterkamp, Benjamin and Lerch, Maximilian and Sammer, Nike and Golde, Olivia and Wellnitz, Felix and Schmid, Sandra and Muntschick, Claudia and Kusterle, Wolfgang and Paric, Ivan and Br{\"u}ckl, Oliver and Haslbeck, Matthias and Schmidt, Ottfried and Schwanzer, Peter and Rabl, Hans-Peter and Sterner, Michael and Bauer, Franz and Steinmann, Sven and Eckert, Fabian and Hofrichter, Andreas}, title = {Forschungsbericht 2017}, editor = {Baier, Wolfgang}, address = {Regensburg}, organization = {Ostbayerische Technische Hochschule Regensburg}, isbn = {978-3-9818209-3-5}, doi = {10.35096/othr/pub-1383}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-13835}, subject = {Forschung}, language = {de} } @inproceedings{HillenbrandLevchenkoStoerletal., author = {Hillenbrand, Andrea and Levchenko, Maksym and St{\"o}rl, Uta and Scherzinger, Stefanie and Klettke, Meike}, title = {MigCast : Putting a Price Tag on Data Model Evolution in NoSQL Data Stores}, series = {Proceedings of the 2019 International Conference on Management of Data (SIGMOD/PODS '19) June 2019, Amsterdam, Netherlands}, booktitle = {Proceedings of the 2019 International Conference on Management of Data (SIGMOD/PODS '19) June 2019, Amsterdam, Netherlands}, editor = {Boncz, Peter and Manegold, Stefan and Ailamaki, Anastasia and Deshpande, Amol and Kraska, Tim}, publisher = {ACM}, address = {New York, NY, USA}, isbn = {9781450356435}, doi = {10.1145/3299869.3320223}, pages = {1925 -- 1928}, abstract = {We demonstrate MigCast, a tool-based advisor for exploring data migration strategies in the context of developing NoSQL-backed applications. Users of MigCast can consider their options for evolving their data model along with legacy data already persisted in the cloud-hosted production data-base. They can explore alternative actions as the financial costs are predicted respective to the cloud provider chosen. Thereby they are better equipped to assess potential consequences of imminent data migration decisions. To this end, MigCast maintains an internal cost model, taking into account characteristics of the data instance, expected work-load, data model changes, and cloud provider pricing models. Hence, MigCast enables software project stakeholders to remain in control of the operative costs and to make informed decisions evolving their applications.}, language = {en} } @article{StoerlKlettkeScherzinger, author = {St{\"o}rl, Uta and Klettke, Meike and Scherzinger, Stefanie}, title = {Kurz erkl{\"a}rt: Objekt-NoSQL-Mapping}, series = {Datenbank-Spektrum}, volume = {16}, journal = {Datenbank-Spektrum}, number = {1}, publisher = {Springer}, doi = {10.1007/s13222-016-0212-y}, pages = {83 -- 87}, language = {de} } @incollection{StoerlMuellerKlettkeetal., author = {St{\"o}rl, Uta and M{\"u}ller, Daniel and Klettke, Meike and Scherzinger, Stefanie}, title = {Enabling Efficient Agile Software Development of NoSQL-backed Applications}, series = {Datenbanksysteme f{\"u}r Business, Technologie und Web (BTW 2017) : 17. Fachtagung des GI-Fachbereichs "Datenbanken und Informationssyteme" (DBIS) : 06.-10.03.2017 in Stuttgart Deutschland}, booktitle = {Datenbanksysteme f{\"u}r Business, Technologie und Web (BTW 2017) : 17. Fachtagung des GI-Fachbereichs "Datenbanken und Informationssyteme" (DBIS) : 06.-10.03.2017 in Stuttgart Deutschland}, editor = {Mitschang, Bernhard}, publisher = {Gesellschaft f{\"u}r Informatik e.V. (GI)}, address = {Bonn}, isbn = {978-3-88579-659-6}, abstract = {NoSQL databases are popular in agile software development, where a frequently changing database schema imposes challenges for the production database. In this demo, we present Darwin, a middleware for systematic, tool-based support specifically designed for NoSQL database systems. Darwin carries out schema evolution and data migration tasks. To the best of our knowledge, Darwin is the first tool of its kind that supports both eager and lazy NoSQL data migration.}, language = {en} }