@inproceedings{SchuettSchintkeReinefeld2003, author = {Sch{\"u}tt, Thorsten and Schintke, Florian and Reinefeld, Alexander}, title = {Efficient Synchronization of Replicated Data in Distributed Systems}, series = {Computational Science - ICCS 2003, International Conference, Melbourne, Australia and St. Petersburg, Russia, June 2-4, 2003. Proceedings, Part I}, volume = {2657}, booktitle = {Computational Science - ICCS 2003, International Conference, Melbourne, Australia and St. Petersburg, Russia, June 2-4, 2003. Proceedings, Part I}, editor = {Sloot, Peter and Abramson, David and Bogdanov, Alexander and Dongarra, Jack and Zomaya, Albert and Gorbachev, Yuri}, publisher = {Springer}, doi = {10.1007/3-540-44860-8_28}, pages = {274 -- 283}, year = {2003}, language = {en} } @inproceedings{AndrzejakReinefeldSchintkeetal.2006, author = {Andrzejak, Artur and Reinefeld, Alexander and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {On Adaptability in Grid Systems}, series = {Future Generation Grids: Proceedings of the Workshop on Future Generation Grids, November 1-5, 2004, Dagstuhl, Germany}, booktitle = {Future Generation Grids: Proceedings of the Workshop on Future Generation Grids, November 1-5, 2004, Dagstuhl, Germany}, editor = {Getov, Vladimir and Laforenza, Domenico and Reinefeld, Alexander}, publisher = {Springer}, doi = {10.1007/978-0-387-29445-2_2}, pages = {29 -- 46}, year = {2006}, language = {en} } @inproceedings{SchuettSchintkeReinefeld2006, author = {Sch{\"u}tt, Thorsten and Schintke, Florian and Reinefeld, Alexander}, title = {Structured Overlay without Consistent Hashing: Empirical Results}, series = {Sixth Workshop on Global and Peer-to-Peer Computing (GP2PC'06) at Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGrid 2006), 16-19 May 2006, Singapore}, booktitle = {Sixth Workshop on Global and Peer-to-Peer Computing (GP2PC'06) at Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGrid 2006), 16-19 May 2006, Singapore}, publisher = {IEEE Computer Society}, doi = {10.1109/CCGRID.2006.175}, pages = {8}, year = {2006}, language = {en} } @inproceedings{SchuettSchintkeReinefeld2007, author = {Sch{\"u}tt, Thorsten and Schintke, Florian and Reinefeld, Alexander}, title = {A Structured Overlay for Multi-dimensional Range Queries}, series = {Euro-Par Conference}, volume = {4641}, booktitle = {Euro-Par Conference}, editor = {Kermarrec, Anne-Marie}, publisher = {Springer}, doi = {10.1007/978-3-540-74466-5_54}, pages = {503 -- 513}, year = {2007}, language = {en} } @misc{ReinefeldSchintkeSchuett2007, author = {Reinefeld, Alexander and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {Device and method for retrieving / storing electronic data in a system with a plurality of data processing units}, publisher = {United States Patent Application Publication No. US 2007/0165619 A1}, year = {2007}, language = {en} } @inproceedings{AnderssonSachsTumaetal., author = {Andersson, Stefan and Sachs, Stephen and Tuma, Christian and Sch{\"u}tt, Thorsten}, title = {DataWarp: First Experiences}, series = {Cray User Group}, booktitle = {Cray User Group}, language = {en} } @inproceedings{SkrzypczakSchintkeSchuett, author = {Skrzypczak, Jan and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {Linearizable State Machine Replication of State-Based CRDTs without Logs}, series = {Proceedings of the 2019 ACM Symposium on Principles of Distributed Computing, PODC 2019}, booktitle = {Proceedings of the 2019 ACM Symposium on Principles of Distributed Computing, PODC 2019}, doi = {10.1145/3293611.3331568}, pages = {455 -- 457}, abstract = {General solutions of state machine replication have to ensure that all replicas apply the same commands in the same order, even in the presence of failures. Such strict ordering incurs high synchronization costs due to the use of distributed consensus or a leader. This paper presents a protocol for linearizable state machine replication of conflict-free replicated data types (CRDTs) that neither requires consensus nor a leader. By leveraging the properties of state-based CRDTs—in particular the monotonic growth of a join semilattice—synchronization overhead is greatly reduced. In addition, updates just need a single round trip and modify the state 'in-place' without the need for a log. Furthermore, the message size overhead for coordination consists of a single counter per message. While reads in the presence of concurrent updates are not wait-free without a coordinator, we show that more than 97 \% of reads can be handled in one or two round trips under highly concurrent accesses. Our protocol achieves high throughput without auxiliary processes such as command log management or leader election. It is well suited for all practical scenarios that need linearizable access on CRDT data on a fine-granular scale.}, language = {en} } @article{SkrzypczakSchintkeSchuett, author = {Skrzypczak, Jan and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {RMWPaxos: Fault-Tolerant In-Place Consensus Sequences}, series = {IEEE Transactions on Parallel and Distributed Systems}, volume = {31}, journal = {IEEE Transactions on Parallel and Distributed Systems}, number = {10}, issn = {1045-9219}, doi = {10.1109/TPDS.2020.2981891}, pages = {2392 -- 2405}, language = {en} } @inproceedings{HartungSchintkeSchuett, author = {Hartung, Marc and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {Pinpoint Data Races via Testing and Classification}, series = {2019 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW); 3rd International Workshop on Software Faults (IWSF 2019)}, booktitle = {2019 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW); 3rd International Workshop on Software Faults (IWSF 2019)}, doi = {10.1109/ISSREW.2019.00100}, pages = {386 -- 393}, language = {en} } @inproceedings{SchmidtkeSchintkeSchuett, author = {Schmidtke, Robert and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {From Application to Disk: Tracing I/O Through the Big Data Stack}, series = {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)}, 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}, 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} } @article{SkrzypczakSchintkeSchuett, author = {Skrzypczak, Jan and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {Linearizable State Machine Replication of State-Based CRDTs without Logs}, series = {arXiv}, journal = {arXiv}, abstract = {General solutions of state machine replication have to ensure that all replicas apply the same commands in the same order, even in the presence of failures. Such strict ordering incurs high synchronization costs caused by distributed consensus or by the use of a leader. This paper presents a protocol for linearizable state machine replication of conflict-free replicated data types (CRDTs) that neither requires consensus nor a leader. By leveraging the properties of state-based CRDTs - in particular the monotonic growth of a join semilattice - synchronization overhead is greatly reduced. In addition, updates just need a single round trip and modify the state `in-place' without the need for a log. Furthermore, the message size overhead for coordination consists of a single counter per message. While reads in the presence of concurrent updates are not wait-free without a coordinator, we show that more than 97\% of reads can be handled in one or two round trips under highly concurrent accesses. Our protocol achieves high throughput without auxiliary processes like command log management or leader election. It is well suited for all practical scenarios that need linearizable access on CRDT data on a fine-granular scale.}, language = {en} } @article{SchuettSchintkeSkrzypczak, author = {Sch{\"u}tt, Thorsten and Schintke, Florian and Skrzypczak, Jan}, title = {Transactions on Red-black and AVL trees in NVRAM}, series = {arXiv}, journal = {arXiv}, language = {en} } @misc{ReinefeldSchintkeSchuett, author = {Reinefeld, Alexander and Schintke, Florian and Sch{\"u}tt, Thorsten}, title = {P2P Routing of Range Queries in Skewed Multidimensional Data Sets}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-9671}, number = {07-23}, abstract = {We present a middleware to store multidimensional data sets on Internet-scale distributed systems and to efficiently perform range queries on them. Our structured overlay network \emph{SONAR (Structured Overlay Network with Arbitrary Range queries)} puts keys which are adjacent in the key space on logically adjacent nodes in the overlay and is thereby able to process multidimensional range queries with a single logarithmic data lookup and local forwarding. The specified ranges may have arbitrary shapes like rectangles, circles, spheres or polygons. Empirical results demonstrate the routing performance of SONAR on several data sets, ranging from real-world data to artificially constructed worst case distributions. We study the quality of SONAR's routing information which is based on local knowledge only and measure the indegree of the overlay nodes to find potential hot spots in the routing process. We show that SONAR's routing table is self-adjusting, even under extreme situations, keeping always a maximum of \$\lceil \log N \rceil\$ routing entries.}, language = {en} } @misc{SchuettSchintkeReinefeld, author = {Sch{\"u}tt, Thorsten and Schintke, Florian and Reinefeld, Alexander}, title = {Chord\#: Structured Overlay Network for Non-Uniform Load-Distribution}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-8736}, number = {05-40}, abstract = {\newcommand{\chordsharp}{Chord\$^\\#\#\$} Data lookup is a fundamental problem in peer-to-peer systems: Given a key, find the node that stores the associated object. Chord and other P2P algorithms use distributed hash tables (DHTs) to distribute the keys and nodes evenly across a logical ring. Using an efficient routing strategy, DHTs provide a routing performance of \$O (\log N)\$ in networks of \$N\$ nodes. While the routing performance has been shown to be optimal, the uniform key distribution makes it impossible for DHTs to support range queries. For range queries, consecutive keys must be stored on lo gically neighboring nodes. In this paper, we present an enhancement of Chord that eliminates the hash function while keeping the same routing performance. The resulting algorithm, named \chordsharp{}, provides a richer function ality while maintaining the same complexity. In addition to Chord, \chordsharp{} adapts to load imbalance.}, language = {en} } @misc{DoebbelinSchuettReinefeld, author = {D{\"o}bbelin, Robert and Sch{\"u}tt, Thorsten and Reinefeld, Alexander}, title = {Building Large Compressed PDBs for the Sliding Tile Puzzle}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-18095}, abstract = {The performance of heuristic search algorithms depends crucially on the effectiveness of the heuristic. A pattern database (PDB) is a powerful heuristic in the form of a pre-computed lookup table. Larger PDBs provide better bounds and thus allow more cut-offs in the search process. Today, the largest PDB for the 24-puzzle is a 6-6-6-6 PDB with a size of 486 MB. We created 8-8-8, 9-8-7 and 9-9-6 PDBs that are three orders of magnitude larger (up to 1.4 TB) than the 6-6-6-6 PDB. We show how to compute such large PDBs and we present statistical and empirical data on their efficiency. The largest single PDB gives on average an 8-fold improvement over the 6-6-6-6 PDB. Combining several large PDBs gives on average an 12-fold improvement.}, language = {en} } @inproceedings{WendeNoackSchuettetal., author = {Wende, Florian and Noack, Matthias and Sch{\"u}tt, Thorsten and Sachs, Stephen and Steinke, Thomas}, title = {Application Performance on a Cray XC30 Evaluation System with Xeon Phi Coprocessors at HLRN-III}, series = {Cray User Group}, booktitle = {Cray User Group}, language = {en} } @inproceedings{SalemSchuettSchintkeetal., author = {Salem, Farouk and Sch{\"u}tt, Thorsten and Schintke, Florian and Reinefeld, Alexander}, title = {Scheduling Data Streams for Low Latency and High Throughput on a Cray XC40 Using Libfabric}, series = {CUG Conference Proceedings}, booktitle = {CUG Conference Proceedings}, abstract = {Achieving efficient many-to-many communication on a given network topology is a challenging task when many data streams from different sources have to be scattered concurrently to many destinations with low variance in arrival times. In such scenarios, it is critical to saturate but not to congest the bisectional bandwidth of the network topology in order to achieve a good aggregate throughput. When there are many concurrent point-to-point connections, the communication pattern needs to be dynamically scheduled in a fine-grained manner to avoid network congestion (links, switches), overload in the node's incoming links, and receive buffer overflow. Motivated by the use case of the Compressed Baryonic Matter experiment (CBM), we study the performance and variance of such communication patterns on a Cray XC40 with different routing schemes and scheduling approaches. We present a distributed Data Flow Scheduler (DFS) that reduces the variance of arrival times from all sources at least 30 times and increases the achieved aggregate bandwidth by up to 50\%.}, language = {en} } @article{SalemSchintkeSchuettetal., author = {Salem, Farouk and Schintke, Florian and Sch{\"u}tt, Thorsten and Reinefeld, Alexander}, title = {Scheduling data streams for low latency and high throughput on a Cray XC40 using Libfabric}, series = {Concurrency and Computation Practice and Experience}, volume = {32}, journal = {Concurrency and Computation Practice and Experience}, number = {20}, doi = {10.1002/cpe.5563}, pages = {1 -- 14}, language = {en} } @article{SalemSchintkeSchuettetal., author = {Salem, Farouk and Schintke, Florian and Sch{\"u}tt, Thorsten and Reinefeld, Alexander}, title = {Improving the throughput of a scalable FLESnet using the Data-Flow Scheduler}, series = {CBM Progress Report 2018}, journal = {CBM Progress Report 2018}, isbn = {978-3-9815227-6-1}, doi = {10.15120/GSI-2019-01018}, pages = {149 -- 150}, language = {en} } @article{SalemSchintkeSchuettetal., author = {Salem, Farouk and Schintke, Florian and Sch{\"u}tt, Thorsten and Reinefeld, Alexander}, title = {Supporting various interconnects in FLESnet using Libfabric}, series = {CBM Progress Report 2016}, journal = {CBM Progress Report 2016}, isbn = {978-3-9815227-4-7}, pages = {159 -- 160}, language = {en} }