http://dl.gi.de/handle/20.500.12116/21086 Thu, 23 Jul 2026 07:57:08 GMT 2026-07-23T07:57:08Z http://dl.gi.de:80/bitstream/id/4b20cebb-4741-49d5-9ff4-02db7ea0c930/ http://dl.gi.de/handle/20.500.12116/21086 http://dl.gi.de/handle/20.500.12116/17358 Logical recovery from single-page failures Graefe, Goetz; Seeger, Bernhard Markl, Volker; Saake, Gunter; Sattler, Kai-Uwe; Hackenbroich, Gregor; Mitschang, Bernhard; Härder, Theo; Köppen, Veit Modern hardware technologies and ever-increasing data sizes increase probability and frequency of local storage failures, e.g., unrecoverable read errors on individual disk sectors or pages on flash storage. Our prior work has formalized singlepage failures and outlined efficient methods for their detection and recovery. These prior techniques rely on old backup copies of individual pages, e.g., as part of a database backup or as old versions retained after a page migration. Those might not be available, however, e.g., after recent index creation in “non-logged” or “allocation-only logging” mode, which industrial database products commonly use. The present paper introduces techniques for single-page recovery without backup copies, e.g., pages of new indexes created in allocation-only logging mode. By rederiving lost contents of individual pages, these techniques enable efficient recovery of data lost due to damaged storage structures or storage devices. Recovery performance depends on the size of the failure and of the required data sources; it is independent of the sizes of device, index structure, etc. Tue, 01 Jan 2013 00:00:00 GMT http://dl.gi.de/handle/20.500.12116/17358 2013-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/17357 Resource description and selection for range query processing in general metric spaces Blank, Daniel; Henrich, Andreas Markl, Volker; Saake, Gunter; Sattler, Kai-Uwe; Hackenbroich, Gregor; Mitschang, Bernhard; Härder, Theo; Köppen, Veit Similarity search in general metric spaces is a key aspect in many application fields. Metric space indexing provides a flexible indexing paradigm and is solely based on the use of a distance metric. No assumption is made about the representation of the database objects. Nowadays, ever-increasing data volumes require large-scale distributed retrieval architectures. Here, local and global indexing schemes are distinguished. In the local indexing approach, every resource administers a set of documents and indexes them locally. Resource descriptions providing the basis for resource selection can be disseminated to avoid all resources being contacted when answering a query. On the other hand, global indexing schemes are based on a single index which is distributed so that every resource is responsible for a certain part of the index. For local indexing, only few exact approaches have been proposed which support general metric space indexing. In this paper, we introduce RS4MI-an exact resource selection approach for general metric space indexing. We compare RS4MI with approaches presented in literature based on a peer-to-peer scenario when searching for similar images by image content. RS4MI can outperform two exact general metric space resource selection schemes in case of range queries. Fewer resources are contacted by RS4MI with-at the same time-more space efficient resource descriptions. Tue, 01 Jan 2013 00:00:00 GMT http://dl.gi.de/handle/20.500.12116/17357 2013-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/17356 Taking the edge off cardinality estimation errors using incremental execution Neumann, Thomas; Galindo-Legaria, Cesar Markl, Volker; Saake, Gunter; Sattler, Kai-Uwe; Hackenbroich, Gregor; Mitschang, Bernhard; Härder, Theo; Köppen, Veit Query optimization is an essential ingredient for efficient query processing, as semantically equivalent execution alternatives can have vastly different runtime behavior. The query optimizer is largely driven by cardinality estimates when selecting execution alternatives. Unfortunately these estimates are largely inaccurate, in particular for complex predicates or skewed data. We present an incremental execution framework to make the query optimizer more resilient to cardinality estimation errors. The framework computes the sensitivity of execution plans relative to cardinality estimation errors, and if necessary executes parts of the query to remove uncertainty. This technique avoids optimization decisions based upon gross misestimation, and makes query optimization (and thus processing) much more robust. We demonstrate the effectiveness of these techniques on large real-world and synthetic data sets. Tue, 01 Jan 2013 00:00:00 GMT http://dl.gi.de/handle/20.500.12116/17356 2013-01-01T00:00:00Z http://dl.gi.de/handle/20.500.12116/17355 Extending the MPSM join Albutiu, Martina-Cezara; Kemper, Alfons; Neumann, Thomas Markl, Volker; Saake, Gunter; Sattler, Kai-Uwe; Hackenbroich, Gregor; Mitschang, Bernhard; Härder, Theo; Köppen, Veit Hardware vendors are improving their (database) servers in two main aspects: (1) increasing main memory capacities of several TB per server, mostly with non-uniform memory access (NUMA) among sockets, and (2) massively parallel multi-core processing. While there has been research on the parallelization of database operations, still many algorithmic and control techniques in current database technology were devised for disk-based systems where I/O dominated the performance. Furthermore, NUMA has only recently caught the community's attention. In [AKN12], we analyzed the challenges that modern hardware poses to database algorithms on a 32-core machine with 1 TB of main memory (four NUMA partitions) and derived three rather simple rules for NUMA-affine scalable multi-core parallelization. Based on our findings, we developed MPSM, a suite of massively parallel sort-merge join algorithms, and showed its competitive performance on large main memory databases with billions of objects. In this paper, we go one step further and investigate the effectiveness of MPSM for non-inner join variants and complex query plans. We show that for noninner join variants, MPSM incurs no extra overhead. Further, we point out ways of exploiting the roughly sorted output of MPSM in subsequent joins. In our evaluation, we compare these ideas to the basic execution of sequential MPSM joins and find that the original MPSM performs very well in complex query plans. Tue, 01 Jan 2013 00:00:00 GMT http://dl.gi.de/handle/20.500.12116/17355 2013-01-01T00:00:00Z