In Zeiten wachsender Datenbankgrößen ist es unumgänglich, Anfragen näherungsweise auszuwerten um schnelle Antworten zu erhalten. Dieser Artikel stellt verschiedene Methoden vor, dieses Ziel zu erreichen, und wendet sich anschließend dem Sampling zu, welches mit Hilfe einer Stichprobe schnell zu adäquaten Ergebnissen führt. Enthalten Datenbankanfragen Verbund- oder Gruppierungsoperationen, so sinkt die Genauigkeit vieler Sampling-Verfahren sehr stark; insbesondere werden vor allem kleine Gruppen nicht erkannt. Dieser Artikel befasst sich mit hierarchischen gruppenbasiertem Sampling, welches Sampling, Gruppierung und Verbundoperationen kombiniert. / In times of increasing database sizes it is crucial to process queries approximately in order to obtain answers quickly. This article introduces several methods for achieving this goal and afterwards focuses on sampling, yielding appropriate results by using only a subset of the actual data. If database queries contain join or group-by operations, the accuracy of many sampling methods drops significantly; especially small groups are not recognized. This article is concerned with hierarchical group-based sampling, which combines sampling, grouping and joins.

Query execution techniques in database systems constantly adapt to novel hardware features to achieve high query performance, in particular for analytical queries. In recent years, vectorization based on the Single Instruction Multiple Data parallel paradigm has been established as a state-of-the-art approach to increase single-query performance. However, since concurrent analytical queries running in parallel often access the same columns and perform a same set of vectorized operations, data accesses and computations among different queries may be executed redundantly. Various techniques have already been proposed to avoid such redundancy, ranging from concurrent scans via the construction of materialized views to applying multiple query optimization techniques. Continuing this line of research, we investigate the opportunity of sharing vector registers for concurrently running queries in analytical scenarios in this paper. In particular, our novel sharing approach relies on processing data elements of different queries together within a single vector register. As we are going to show, sharing vector registers to optimize the execution of concurrent analytical queries can be very beneficial in single-threaded as well as multi-thread environments. Therefore, we demonstrate the feasibility and applicability of such a novel work sharing strategy and thus open up a wide spectrum of future research opportunities.

Datenbanksysteme verwenden Indexstrukturen, um Suchanfragen zu beschleunigen. Im Laufe der letzten Jahre haben Forscher verschiedene Ansätze zur Indexierung von Datenbanktabellen im Hauptspeicher entworfen. Hauptspeicherindexstrukturen versuchen möglichst häufig Daten zu verwenden, die bereits im Zwischenspeicher der CPU vorrätig sind, anstatt, wie bei traditionellen Datenbanksystemen, die Zugriffe auf den externen Speicher zu optimieren. Die meisten vorgeschlagenen Indexstrukturen für den Hauptspeicher beschränken sich jedoch auf Punktabfragen und vernachlässigen die ebenso wichtigen Bereichsabfragen, die in zahlreichen Anwendungen, wie in der Analyse von Genomdaten, Sensornetzwerken, oder analytischen Datenbanksystemen, zum Einsatz kommen. Diese Dissertation verfolgt als Hauptziel die Fähigkeiten von modernen Hauptspeicherdatenbanksystemen im Ausführen von Bereichsabfragen zu verbessern. Dazu schlagen wir zunächst die Cache-Sensitive Skip List, eine neue aktualisierbare Hauptspeicherindexstruktur, vor, die für die Zwischenspeicher moderner Prozessoren optimiert ist und das Ausführen von Bereichsabfragen auf einzelnen Datenbankspalten ermöglicht. Im zweiten Abschnitt analysieren wir die Performanz von multidimensionalen Bereichsabfragen auf modernen Serverarchitekturen, bei denen Daten im Hauptspeicher hinterlegt sind und Prozessoren über SIMD-Instruktionen und Multithreading verfügen. Um die Relevanz unserer Experimente für praktische Anwendungen zu erhöhen, schlagen wir zudem einen realistischen Benchmark für multidimensionale Bereichsabfragen vor, der auf echten Genomdaten ausgeführt wird. Im letzten Abschnitt der Dissertation präsentieren wir den BB-Tree als neue, hochperformante und speichereffziente Hauptspeicherindexstruktur. Der BB-Tree ermöglicht das Ausführen von multidimensionalen Bereichs- und Punktabfragen und verfügt über einen parallelen Suchoperator, der mehrere Threads verwenden kann, um die Performanz von Suchanfragen zu erhöhen. / Database systems employ index structures as means to accelerate search queries. Over the last years, the research community has proposed many different in-memory approaches that optimize cache misses instead of disk I/O, as opposed to disk-based systems, and make use of the grown parallel capabilities of modern CPUs. However, these techniques mainly focus on single-key lookups, but neglect equally important range queries. Range queries are an ubiquitous operator in data management commonly used in numerous domains, such as genomic analysis, sensor networks, or online analytical processing. The main goal of this dissertation is thus to improve the capabilities of main-memory database systems with regard to executing range queries. To this end, we first propose a cache-optimized, updateable main-memory index structure, the cache-sensitive skip list, which targets the execution of range queries on single database columns. Second, we study the performance of multidimensional range queries on modern hardware, where data are stored in main memory and processors support SIMD instructions and multi-threading. We re-evaluate a previous rule of thumb suggesting that, on disk-based systems, scans outperform index structures for selectivities of approximately 15-20% or more. To increase the practical relevance of our analysis, we also contribute a novel benchmark consisting of several realistic multidimensional range queries applied to real- world genomic data. Third, based on the outcomes of our experimental analysis, we devise a novel, fast and space-effcient, main-memory based index structure, the BB- Tree, which supports multidimensional range and point queries and provides a parallel search operator that leverages the multi-threading capabilities of modern CPUs.

Materialized views are a well-known optimization strategy with the potential for massive improvements in query processing time, especially for aggregation queries over large tables. To realize this potential, the query optimizer has to know how and when to exploit materialized views. Reporting functions represent a novel technique to formulate sequence-oriented queries in SQL. They provide a column-wise ordering, partitioning, and windowing mechanism for aggregation functions and therefore extend the well-known way of grouping and applying simple aggregation functions. Up to now, current work has not considered the frequently used reporting functions in data warehouse environments. In this paper, we introduce materialized reporting function views and show how to rewrite queries with reporting functions as well as aggregation queries to this new kind of materialized views. We demonstrate the efficiency of our approach with a large number of experiments.

In an increasing number of use cases, databases face the challenge of managing irregularly structured data. Irregularly structured data is characterized by a quickly evolving variety of entities without a common set of attributes. These entities do not show enough regularity to be captured in a traditional database schema. A common solution is to centralize the diverse entities in a universal table. Usually, this leads to a very sparse table. Although today's techniques allow efficient storage of sparse universal tables, query efficiency is still a problem. Queries that reference only a subset of attributes have to read the whole universal table including many irrelevant entities. One possible solution is to use a partitioning of the table, which allows pruning partitions of irrelevant entities before they are touched. Creating and maintaining such a partitioning manually is very laborious or even infeasible, due to the enormous complexity. Thus an autonomous solution is desirable. In this paper, we define the Online Partitioning Problem for irregularly structured data and present Cinderella. Cinderella is an autonomous online algorithm for horizontal partitioning of irregularly structured entities in universal tables. It is designed to keep its overhead low by incrementally assigning entities to partitions while they are touched anyway during modifications. The achieved partitioning allows queries that retrieve only entities with a subset of attributes easily pruning partitions of irrelevant entities. Cinderella increases the locality of queries and reduces query execution cost.

The hardware landscape is currently changing from homogeneous multi-core systems towards heterogeneous systems with many di↵erent computing units, each with their own characteristics. This trend is a great opportunity for database systems to increase the overall performance if the heterogeneous resources can be utilized eciently. To achieve this, the main challenge is to place the right work on the right computing unit. Current approaches tackling this placement for query processing assume that data cardinalities of intermediate results can be correctly estimated. However, this assumption does not hold for complex queries. To overcome this problem, we propose an adaptive placement approach being independent of cardinality estimation of intermediate results. Our approach is incorporated in a novel adaptive placement sequence. Additionally, we implement our approach as an extensible virtualization layer, to demonstrate the broad applicability with multiple database systems. In our evaluation, we clearly show that our approach significantly improves OLAP query processing on heterogeneous hardware, while being adaptive enough to react to changing cardinalities of intermediate query results.

Hardware vendors constantly decrease the feature sizes of integrated circuits to obtain better performance and energy efficiency. Due to cosmic rays, low voltage or heat dissipation, hardware -- both processors and memory -- becomes more and more unreliable as the error rate increases. From a database perspective bit flip errors in main memory will become a major challenge for modern in-memory database systems, which keep all their enterprise data in volatile, unreliable main memory. Although existing hardware error control techniques like ECC-DRAM are able to detect and correct memory errors, their detection and correction capabilities are limited. Moreover, hardware error correction faces major drawbacks in terms of acquisition costs, additional memory utilization, and latency. In this paper, we argue that slightly increasing data redundancy at the right places by incorporating context knowledge already increases error detection significantly. We use the B-Tree -- as a widespread index structure -- as an example and propose various techniques for online error detection and thus increase its overall reliability. In our experiments, we found that our techniques can detect more errors in less time on commodity hardware compared to non-resilient B-Trees running in an ECC-DRAM environment. Our techniques can further be easily adapted for other data structures and are a first step in the direction of resilient database systems which can cope with unreliable hardware.

Storage Class Memory (SCM) is emerging as a viable alternative to traditional DRAM, alleviating its scalability limits, both in terms of capacity and energy consumption, while being non-volatile. Hence, SCM has the potential to become a universal memory, blurring well-known storage hierarchies. However, along with opportunities, SCM brings many challenges. In this tutorial we will dissect SCM challenges and provide an in-depth view of existing programming models that circumvent them, as well as novel data structures that stem from these models. We will also elaborate on fail-safety testing challenges -- an often overlooked, yet important topic. Finally, we will discuss SCM emulation techniques for end-to-end testing of SCM-based software components. In contrast to surveys investigating the use of SCM in database systems, this tutorial is designed as a programming guide for researchers and professionals interested in leveraging SCM in database systems.

To efficiently support analytical applications from a data management perspective, in-memory column store database systems are state-of-the art. In this kind of database system, lossless lightweight integer compression schemes are crucial to keep the memory storage as low as possible and to speedup query processing. In this specific compression domain, BitPacking is one of the most frequently applied compression scheme. However, (de) compression should not come with any additional cost during run time, but should be provided transparently without compromising the overall system performance. To achieve that, we focus on acceleration of BitPacking using Field Programmable Gate Arrays (FPGAs). Therefore, we outline several FPGA designs for BitPacking in this paper. As we are going to show in our evaluation, our specific designs provide the BitPacking compression scheme with high-throughput.

Physical design has always been an important part of database administration. Today's commercial database management systems offer physical design tools, which recommend a physical design for a given workload. However, these tools work only with static workloads and ignore the fact that workloads, and physical designs, may change over time. Research has now begun to focus on dynamic physical design, which can account for time-varying workloads. In this paper, we consider a dynamic but constrained approach to physical design. The goal is to recommend dynamic physical designs that reflect major workload trends but that are not tailored too closely to the details of the input workloads. To achieve this, we constrain the number of changes that are permitted in the recommended design. In this paper we present our definition of the constrained dynamic physical design problem and discuss several techniques for solving it.