TY - JOUR A1 - Schütt, Thorsten A1 - Reinefeld, Alexander A1 - Döbbelin, Robert T1 - MR-search: massively parallel heuristic search JF - Concurrency and Computation: Practice and Experience Y1 - 2011 U6 - https://doi.org/10.1002/cpe.1833 VL - 25 IS - 1 SP - 40 EP - 54 ER - TY - JOUR A1 - Salem, Farouk A1 - Schintke, Florian A1 - Schütt, Thorsten A1 - Reinefeld, Alexander T1 - Improving the throughput of a scalable FLESnet using the Data-Flow Scheduler JF - CBM Progress Report 2018 Y1 - 2019 SN - 978-3-9815227-6-1 U6 - https://doi.org/10.15120/GSI-2019-01018 SP - 149 EP - 150 ER - TY - CHAP A1 - Hartung, Marc A1 - Schintke, Florian A1 - Schütt, Thorsten T1 - Pinpoint Data Races via Testing and Classification T2 - 2019 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW); 3rd International Workshop on Software Faults (IWSF 2019) Y1 - 2019 U6 - https://doi.org/10.1109/ISSREW.2019.00100 SP - 386 EP - 393 ER - TY - JOUR A1 - Salem, Farouk A1 - Schintke, Florian A1 - Schütt, Thorsten A1 - Reinefeld, Alexander T1 - Scheduling data streams for low latency and high throughput on a Cray XC40 using Libfabric JF - Concurrency and Computation Practice and Experience Y1 - 2020 U6 - https://doi.org/10.1002/cpe.5563 VL - 32 IS - 20 SP - 1 EP - 14 ER - TY - JOUR A1 - Skrzypczak, Jan A1 - Schintke, Florian A1 - Schütt, Thorsten T1 - RMWPaxos: Fault-Tolerant In-Place Consensus Sequences JF - IEEE Transactions on Parallel and Distributed Systems Y1 - 2020 U6 - https://doi.org/10.1109/TPDS.2020.2981891 SN - 1045-9219 VL - 31 IS - 10 SP - 2392 EP - 2405 ER - TY - JOUR A1 - Schütt, Thorsten A1 - Schintke, Florian A1 - Skrzypczak, Jan T1 - Transactions on Red-black and AVL trees in NVRAM JF - arXiv Y1 - 2020 ER - TY - CHAP A1 - Skrzypczak, Jan A1 - Schintke, Florian A1 - Schütt, Thorsten T1 - Linearizable State Machine Replication of State-Based CRDTs without Logs T2 - Proceedings of the 2019 ACM Symposium on Principles of Distributed Computing, PODC 2019 N2 - 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. Y1 - 2019 U6 - https://doi.org/10.1145/3293611.3331568 SP - 455 EP - 457 ER - TY - CHAP A1 - Salem, Farouk A1 - Schütt, Thorsten A1 - Schintke, Florian A1 - Reinefeld, Alexander T1 - Scheduling Data Streams for Low Latency and High Throughput on a Cray XC40 Using Libfabric T2 - CUG Conference Proceedings N2 - 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%. Y1 - 2019 ER - TY - JOUR A1 - Skrzypczak, Jan A1 - Schintke, Florian A1 - Schütt, Thorsten T1 - Linearizable State Machine Replication of State-Based CRDTs without Logs JF - arXiv N2 - 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. Y1 - 2019 ER - TY - CHAP A1 - Schintke, Florian A1 - Reinefeld, Alexander A1 - Haridi, Seif A1 - Schütt, Thorsten T1 - Enhanced Paxos Commit for Transactions on DHTs T2 - CCGRID Y1 - 2010 U6 - https://doi.org/10.1109/CCGRID.2010.41 SP - 448 EP - 454 PB - IEEE ER - TY - CHAP A1 - Reinefeld, Alexander A1 - Schütt, Thorsten T1 - Out-of-Core Parallel Frontier Search with MapReduce T2 - HPCS Y1 - 2009 U6 - https://doi.org/10.1007/978-3-642-12659-8_24 VL - 5976 SP - 323 EP - 336 PB - Springer ER - TY - CHAP A1 - Schütt, Thorsten A1 - Reinefeld, Alexander A1 - Schintke, Florian A1 - Hennig, C. T1 - Self-Adaptation in Large-Scale Systems: A Study on Structured Overlays Across Multiple Datacenters T2 - Architectures and Languages for Self-Managing Distributed Systems (SelfMan@SASO) Y1 - 2009 U6 - https://doi.org/10.1109/SASOW.2010.65 ER - TY - CHAP A1 - Schütt, Thorsten A1 - Moser, Monika A1 - Plantikow, Stefan A1 - Schintke, Florian A1 - Reinefeld, Alexander T1 - A Transactional Scalable Distributed Data Store T2 - 1st IEEE International Scalable Computing Challenge, co-located with CCGrid’08 Y1 - 2008 ER - TY - GEN A1 - Andrzejak, Artur A1 - Reinefeld, Alexander A1 - Schintke, Florian A1 - Schütt, Thorsten A1 - Mastroianni, Carlo A1 - Fragopoulou, Paraskevi A1 - Kondo, Derrick A1 - Malecot, Paul A1 - Cosmin Silaghi, Gheorghe A1 - Moura Silva, Luis A1 - Trunfio, Paolo A1 - Zeinalipour-Yazti, Demetris A1 - Zimeo, Eugenio T1 - Grid Architectural Issues: State-of-the-art and Future Trends Y1 - 2008 UR - http://coregrid.ercim.eu//mambo/images/stories/WhitePapers/whp-0004.pdf IS - WHP-0004 PB - Institute on Architectural Issues: Scalability, Dependability, Adaptability, CoreGRID - Network of Excellence ER - TY - CHAP A1 - Shafaat, Tallat A1 - Moser, Monika A1 - Ghodsi, Ali A1 - Schütt, Thorsten A1 - Haridi, Seif A1 - Reinefeld, Alexander T1 - Key-Based Consistency and Availability in Structured Overlay Networks T2 - International ICST Conference on Scalable Information Systems Y1 - 2008 ER - TY - THES A1 - Schütt, Thorsten T1 - Range queries in distributed hash tables Y1 - 2010 UR - http://www.dr.hut-verlag.de/978-3-86853-370-5.html ER - TY - CHAP A1 - Reinefeld, Alexander A1 - Schütt, Thorsten A1 - Döbbelin, Robert ED - Hariri, Salim ED - Keahey, Kate T1 - Very large pattern databases for heuristic search T2 - HPDC Y1 - 2010 U6 - https://doi.org/10.1145/1851476.1851592 SP - 803 EP - 809 PB - ACM ER - TY - CHAP A1 - Reinefeld, Alexander A1 - Schintke, Florian A1 - Schütt, Thorsten A1 - Haridi, Seif ED - Tselentis, G. ED - Domingue, J. ED - Galis, A. ED - Gavras, A. ED - Hausheer, D. ED - Krco, S. ED - Lotz, V. ED - Zahariadis, T. T1 - A Scalable, Transactional Data Store for Future Internet Services T2 - Towards the Future Internet - A European Research Perspective Y1 - 2009 U6 - https://doi.org/10.3233/978-1-60750-007-0-148 SP - 148 EP - 159 PB - IOS Press ER - TY - CHAP A1 - Schütt, Thorsten A1 - Reinefeld, Alexander A1 - Schintke, Florian A1 - Hoffmann, Marie T1 - Gossip-based Topology Inference for Efficient Overlay Mapping on Data Centers T2 - Peer-to-Peer Computing Y1 - 2009 U6 - https://doi.org/10.1109/P2P.2009.5284553 SP - 147 EP - 150 ER - TY - CHAP A1 - Högqvist, Mikael A1 - Haridi, Seif A1 - Kruber, Nico A1 - Reinefeld, Alexander A1 - Schütt, Thorsten T1 - Using Global Information for Load Balancing in DHTs T2 - Workshop on Decentralized Self Management for Grids, P2P, and User Communities Y1 - 2008 ER -