Auflistung nach Schlagwort "replication"
1 - 3 von 3
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelFault-tolerant data management in the gaston peer-to-peer file system(Wirtschaftsinformatik: Vol. 45, No. 3, 2003) Dynda, Vladimír; Rydlo, PavelGaston is a peer-to-peer large-scale file system designed to provide a fault-tolerant and highly available file service for a virtually unlimited number of users. Data management in Gaston disseminates and stores replicas of files on multiple machines to achieve the requested level of data availability and uses a dynamic tree-topology structure to connect replication schema members. We present generic algorithms for replication schema creation and maintenance according to file user requirements and autonomous constraints that are set on individual nodes. We also show specific data object structure as well as mechanisms for secure and efficient update propagation among replicas with data consistency control. Finally, we introduce a scalable and efficient technique improving fault-tolerance of the tree-topology structure connecting replicas.
- TextdokumentPartial Reload of Incrementally Updated Tables in Analytic Database Accelerators(BTW 2019, 2019) Stolze, Knut; Beier, Felix; Müller, JensThe IBM Db2 Analytics Accelerator (IDAA) is a state-of-the art hybrid database system that seamlessly extends the strong transactional capabilities of Db2 for z/OS (Db2z) with very fast column-store processing in Db2 Database for Linux, Unix, and Windows. IDAA maintains a copy of the data from Db2z in its backend database. The data can be synchronized in batch with a granularity of table partitions, or incrementally using replication technology for individual rows. In this paper we present the enablement of combining the batch loading of a true subset of a table’s partitions for replicated tables. The primary goal for such an integration is to ensure data consistency. A specific challenge is that no duplicated rows stemming from the two data transfer paths come into existence. We present a robust and yet simple approach that is based on IDAA’s implementation of multi-version concurrency control.
- TextdokumentTowards a Shared Evaluation Environment for Software-defined Networking(INFORMATIK 2017, 2017) Dittebrandt, Addis; König, Michael; Neumeister, FelixThe evaluation of Software-defined Networking control plane applications is a complicated task with many pitfalls. This paper introduces the vision of a shared evaluation environment for Software-defined Networking (called SEED), setting out to ease and speedup the process of designing, setting up and replicating simulative evaluations for both the researcher and reviewer. SEED introduces an additional configuration layer on top of existing simulators, specifically tailored towards SDN-research. SEED allows to load saved configuration files and run simulations based on them. It separates the specification of the simulated network from the application to evaluate and the precise experiment specification. This allows to publish, review and reuse simulation scenarios independently from applications. By exposing a unified interface for different simulators, it aims to cover a variety of use cases and make the configurations more widely usable.