Columnar database systems can process complex mixed workloads on a single node. In case of increasing and peak analytical processing demand, we can offload read-only queries to replicas. Partial replication, i.e., duplicating only data subsets to additional nodes, is more cost-efficient than full replication for two primary reasons: (i) Partial replicas require less storage and can be set up faster. (ii) Partial replicas must synchronize only stored data subsets, allowing better scalability. However, determining which queries to offload is challenging for larger workloads because queries access overlapping data subsets and cause synchronization costs.

Indexes are important data structures for database tuning. However, finding the best indexes for a given workload is challenging. In this demonstration, we present our extensible open-source index selection evaluation platform and the corresponding interactive result analysis tool. The platform provides an automatic setup of the database, workload, and cost evaluation, which is otherwise often tedious work when evaluating index selection approaches. Users can also connect the platform to their own existing database and evaluate indexes for custom workloads. Our platform comprises multiple state-of-the-art index selection approaches, which can be used as baselines for new index selection proposals. Further, we present an application for thoroughly analyzing the selected database indexes. One can observe which indexes are used for which queries and their effect on processing costs. Also, it is possible to adapt the resulting index selections (i.e., add, remove, or change an index) and observe the impact. In this process, the application helps to understand the effects of indexes, improve index selections, and craft new index selection approaches.

Based on the performance requirements of modern spatio-temporal data mining applications, in-memory database systems are often used to store and process the data. To efficiently utilize the scarce DRAM capacities, modern database systems support various tuning possibilities to reduce the memory footprint (e.g., data compression) or increase performance (e.g., additional indexes). However, the selection of cost and performance balancing configurations is challenging due to the vast number of possible setups consisting of mutually dependent individual decisions. In this paper, we introduce a novel approach to jointly optimize the compression, sorting, indexing, and tiering configuration for spatio-temporal workloads. Further, we consider horizontal data partitioning, which enables the independent application of different tuning options on a fine-grained level. We propose different linear programming (LP) models addressing cost dependencies at different levels of accuracy to compute optimized tuning configurations for a given workload and memory budgets. To yield maintainable and robust configurations, we extend our LP-based approach to incorporate reconfiguration costs as well as a worst-case optimization for potential workload scenarios. Further, we demonstrate on a real-world dataset that our models allow to significantly reduce the memory footprint with equal performance or increase the performance with equal memory size compared to existing tuning heuristics.

Load balancing queries that access the same data fragments to the same node improves caching for a memory-efficient scale-out. However, to suitably allocate fragments to multiple nodes is a highly challenging problem, particularly when nodes might fail. The problem is to find a good balance between memory efficiency and allocating enough fragments to nodes to obtain robustness through load balancing flexibility. Existing allocation approaches are either not memory-efficient or result in load imbalances, both degrading cost/performance. In this paper, we present an optimal approach and a scalable heuristic, based on three mutually supportive linear programming models, to calculate memory-efficient fragment allocations that guarantee to distribute the workload evenly - even in the case of node failures. We demonstrate the applicability and the effectiveness of our three-step approach using numerical as well as end-to-end evaluations for TPC-H and TPC-DS workloads. We find that our robust solutions clearly outperform state-of-the-art heuristics by achieving a better workload distribution with even less memory.

The wide distribution of location-acquisition technologies has led to large volumes of spatio-temporal data, which are the foundation for a broad spectrum of applications. Based on these applications' performance requirements, in-memory databases are used to store and process the data. As DRAM capacities are limited and expensive, modern database systems apply various configuration optimizations (e.g., compression) to reduce the memory footprint. The selection of cost and performance balancing configurations is challenging due to the vast amount of possible setups consisting of mutually dependent individual decisions. In this paper, we present a linear programming approach to determine fine-grained configuration decisions for spatio-temporal workloads. By dividing the data into partitions of fixed size, we can apply the compression, sorting, and index selections on a fine-grained level to reflect spatiotemporal access patterns. Our approach jointly optimizes these configurations to maximize performance under a given memory budget. We demonstrate on a real-world dataset that models specifically optimized for spatio-temporal data characteristics allow us to reduce the memory footprint (up to 60% by equal performance) and increase the performance (up to 80% by equal memory size) compared to established rule-based heuristics.

Database replication is a mechanism to achieve scalability, for example, by executing queries independently on replica nodes. Partial replication is an approach to minimize the overall memory consumption of a replication cluster while still enabling a balanced load distribution among nodes to scale the query throughput linearly with the number of replicas. Partial replication reduces the cluster costs, speeds up data synchronization, and improves caching. However, load balancing may become skewed in the case of unexpected query distributions, unfavorable query timings, or node failures. To simulate and visualize the load balancing behavior for specific data fragment allocations, we implemented an interactive application. It allows users to retrace and evaluate the end-to-end performance of partially replicated database systems in varying experiments. Using our tool, we find that existing allocation approaches are either not memory-efficient or may result in load imbalances when nodes fail. We show that our novel robust allocation strategy achieves a better workload distribution with even less memory.

While finding the best selection of indexes is an important task the problem appears highly challenging as (i) indexes mutually affect their impact on performance and (ii) the number of index combinations can be enormous. Current selection approaches have limitations when problems are large and ignore the fact that future workloads are partially stochastic. In this paper, we propose a solver-based approach to find effective index selections for large-scale workloads. Our decomposition concept allows to deal with large candidate sets and makes it possible to address risk-averse problem versions, where multiple potential future workloads are taken into account. We demonstrate the applicability and the effectiveness of our approach for the TPC-DS benchmark workload. Our numerical results show that compared to state-of-the-art LP approaches index selections can be computed orders of magnitudes faster while still obtaining near-optimal performance results.

Abstract Challenges for self-driving database systems, which tune their physical design and configuration autonomously, are manifold: Such systems have to anticipate future workloads, find robust configurations efficiently, and incorporate knowledge gained by previous actions into later decisions. We present a component-based framework for self-driving database systems that enables database integration and development of self-managing functionality with low overhead by relying on separation of concerns. By keeping the components of the framework reusable and exchangeable, experiments are simplified, which promotes further research in that area. Moreover, to optimize multiple mutually dependent features, e.g., index selection and compression configurations, we propose a linear programming (LP) based algorithm to derive an efficient tuning order automatically. Afterwards, we demonstrate the applicability and scalability of our approach with reproducible examples.

In replication schemes, replica nodes can process read-only queries on snapshots of the master node without violating transactional consistency. By analyzing the workload, we can identify query access patterns and replicate data depending to its access frequency. In this paper, we define a linear programming (LP) model to calculate the set of partial replicas with the lowest overall memory capacity while evenly balancing the query load. Furthermore, we propose a scalable decomposition heuristic to calculate solutions for larger problem sizes. While guaranteeing the same performance as state-of-the-art heuristics, our decomposition approach calculates allocations with up to 23% lower memory footprint for the TPC-H benchmark.

Increasing demand for analytical processing capabilities can be managed by replication approaches. However, to evenly balance the replicas' workload shares while at the same time minimizing the data replication factor is a highly challenging allocation problem. As optimal solutions are only applicable for small problem instances, effective heuristics are indispensable. In this paper, we test and compare state-of-the-art allocation algorithms for partial replication. By visualizing and exploring their (heuristic) solutions for different benchmark workloads, we are able to derive structural insights and to detect an algorithm's strengths as well as its potential for improvement. Further, our application enables end-to-end evaluations of different allocations to verify their theoretical performance.

An efficient selection of indexes is indispensable for database performance. For large problem instances with hundreds of tables, existing approaches are not suitable: They either exhibit prohibitive runtimes or yield far from optimal index configurations by strongly limiting the set of index candidates or not handling index interaction explicitly. We introduce a novel recursive strategy that does not exclude index candidates in advance and effectively accounts for index interaction. Using large real-world workloads, we demonstrate the applicability of our approach. Further, we evaluate our solution end to end with a commercial database system using a reproducible setup. We show that our solutions are near-optimal for small index selection problems. For larger problems, our strategy outperforms state-of-the-art approaches in both scalability and solution quality.

Recent developments in database research introduced HTAP systems that are capable of handling both transactional and analytical workloads. These systems achieve their performance by storing the full data set in main memory. An open research question is how far one can reduce the main memory footprint without losing the performance superiority of main memory-resident databases. In this paper, we present a hybrid main memory-optimized database for mixed workloads that evicts cold data to less expensive storage tiers. It adapts the storage layout to mitigate the negative performance impact of secondary storage. A key challenge is to determine which data to place on which storage tier. We introduce a novel workload-driven model that determines Pareto-optimal allocations while also considering reallocation costs. We evaluate our concept for a production enterprise system as well as reproducible data sets.

Most online markets are characterized by competitive settings and limited demand information. Due to the complexity of such markets, efficient pricing strategies are hard to derive. We analyze stochastic dynamic pricing models in competitive markets with multiple offer dimensions, such as price, quality, and rating. In a first step, we use a simulated test market to study how sales probabilities are affected by specific customer behaviors and the strategic interaction of price reaction strategies. Further, we show how different state-of-the-art learning techniques can be used to estimate sales probabilities from partially observable market data. In a second step, we use a dynamic programming model to compute an effective pricing strategy which circumvents the curse of dimensionality. We demonstrate that the strategy is applicable even if the number of competitors is large and their strategies are unknown. We show that our heuristic can be tuned to smoothly balance profitability and speed of sales. Further, our approach is currently applied by a large seller on Amazon for the sale of used books. Sales results show that our data-driven strategy outperforms the rule-based strategy of an experienced seller by a profit increase of more than 20%.

Modern e-commerce platforms pose both opportunities as well as hurdles for merchants. While merchants can observe markets at any point in time and automatically reprice their products, they also have to compete simultaneously with dozens of competitors. Currently, retailers lack the possibility to test, develop, and evaluate their algorithms appropriately before releasing them into the real world. At the same time, it is challenging for researchers to investigate how pricing strategies interact with each other under heavy competition. To study dynamic pricing competition on online marketplaces, we built an open simulation platform. To be both flexible and scalable, the platform has a microservice-based architecture and handles large numbers of competing merchants and arriving consumers. It allows merchants to deploy the full width of pricing strategies, from simple rule-based strategies to more sophisticated data-driven strategies using machine learning. Our platform enables analyses of how a strategy's performance is affected by customer behavior, price adjustment frequencies, the competitors' strategies, and the exit/entry of competitors. Moreover, our platform allows to study the long-term behavior of self-adapting strategies.