Felix Martin Schuhknecht

The uncracked pieces in database cracking

Database cracking has been an area of active research in recent years. The core idea of database cracking is to create indexes adaptively and incrementally as a side-product of query processing. Several works have proposed different cracking techniques for different aspects including updates, tuple-reconstruction, convergence, concurrency-control, and robustness. However, there is a lack of any comparative study of these different methods by an independent group. In this paper, we conduct an experimental study on database cracking. Our goal is to critically review several aspects, identify the potential, and propose promising directions in database cracking. With this study, we hope to expand the scope of database cracking and possibly leverage cracking in database engines other than MonetDB. We repeat several prior database cracking works including the core cracking algorithms as well as three other works on convergence (hybrid cracking), tuple-reconstruction (sideways cracking), and robustness (stochastic cracking) respectively. We evaluate these works and show possible directions to do even better. We further test cracking under a variety of experimental settings, including high selectivity queries, low selectivity queries, and multiple query access patterns. Finally, we compare cracking against different sorting algorithms as well as against different main-memory optimised indexes, including the recently proposed Adaptive Radix Tree (ART). Our results show that: (i) the previously proposed cracking algorithms are repeatable, (ii) there is still enough room to significantly improve the previously proposed cracking algorithms, (iii) cracking depends heavily on query selectivity, (iv) cracking needs to catch up with modern indexing trends, and (v) different indexing algorithms have different indexing signatures.

Main memory adaptive indexing for multi-core systems

Adaptive indexing is a concept that considers index creation in databases as a by-product of query processing; as opposed to traditional full index creation where the indexing effort is performed up front before answering any queries. Adaptive indexing has received a considerable amount of attention, and several algorithms have been proposed over the past few years; including a recent experimental study comparing a large number of existing methods. Until now, however, most adaptive indexing algorithms have been designed single-threaded, yet with multi-core systems already well established, the idea of designing parallel algorithms for adaptive indexing is very natural. In this regard, and to the best of our knowledge, only one parallel algorithm for adaptive indexing has recently appeared in the literature: The parallel version of standard cracking. In this paper we describe three alternative parallel algorithms for adaptive indexing, including a second variant of a parallel standard cracking algorithm. Additionally, we describe a hybrid parallel sorting algorithm, and a NUMA-aware method based on sorting. We then thoroughly compare all these algorithms experimentally. Parallel sorting algorithms serve as a realistic baseline for multi-threaded adaptive indexing techniques. In total we experimentally compare seven parallel algorithms. The initial set of experiments considered in this paper indicates that our parallel algorithms significantly improve over previously known ones. Our results also suggest that, although adaptive indexing algorithms are a good design choice in single-threaded environments, the rules change considerably in the parallel case. That is, in future highly-parallel environments, sorting algorithms could be serious alternatives to adaptive indexing.

On the surprising difficulty of simple things: the case of radix partitioning

Partitioning a dataset into ranges is a task that is common in various applications such as sorting [1,6,7,8,9] and hashing [3] which are in turn building blocks for almost any type of query processing. Especially radix-based partitioning is very popular due to its simplicity and high performance over comparison-based versions [6].

An experimental evaluation and analysis of database cracking

Database cracking has been an area of active research in recent years. The core idea of database cracking is to create indexes adaptively and incrementally as a side product of query processing. Several works have proposed different cracking techniques for different aspects including updates, tuple reconstruction, convergence, concurrency control, and robustness. Our 2014 VLDB paper “The Uncracked Pieces in Database Cracking” (PVLDB 7:97–108, 2013/VLDB 2014) was the first comparative study of these different methods by an independent group. In this article, we extend our published experimental study on database cracking and bring it to an up-to-date state. Our goal is to critically review several aspects, identify the potential, and propose promising directions in database cracking. With this study, we hope to expand the scope of database cracking and possibly leverage cracking in database engines other than MonetDB. We repeat several prior database cracking works including the core cracking algorithms as well as three other works on convergence (hybrid cracking), tuple reconstruction (sideways cracking), and robustness (stochastic cracking), respectively. Additionally to our conference paper, we now also look at a recently published study about CPU efficiency (predication cracking). We evaluate these works and show possible directions to do even better. As a further extension, we evaluate the whole class of parallel cracking algorithms that were proposed in three recent works. Altogether, in this work we revisit 8 papers on database cracking and evaluate in total 18 cracking methods, 6 sorting algorithms, and 3 full index structures. Additionally, we test cracking under a variety of experimental settings, including high selectivity (Low selectivity means that many entries qualify. Consequently, a high selectivity means, that only few entries qualify) queries, low selectivity queries, varying selectivity, and multiple query access patterns. Finally, we compare cracking against different sorting algorithms as well as against different main memory optimized indexes, including the recently proposed adaptive radix tree (ART). Our results show that: (1) the previously proposed cracking algorithms are repeatable, (2) there is still enough room to significantly improve the previously proposed cracking algorithms, (3) parallelizing cracking algorithms efficiently is a hard task, (4) cracking depends heavily on query selectivity, (5) cracking needs to catch up with modern indexing trends, and (6) different indexing algorithms have different indexing signatures.

Accelerating Analytical Processing in MVCC using Fine-Granular High-Frequency Virtual Snapshotting

Efficient transaction management is a delicate task. As systems face transactions of inherently different types, ranging from point updates to long-running analytical queries, it is hard to satisfy their requirements with a single execution engine. Unfortunately, most systems rely on such a design that implements its parallelism using multi-version concurrency control. While MVCC parallelizes short-running OLTP transactions well, it struggles in the presence of mixed workloads containing long-running OLAP queries, as scans have to work their way through vast amounts of versioned data. To overcome this problem, we reintroduce the concept of hybrid processing and combine it with state-of-the-art MVCC: OLAP queries are outsourced to run on separate virtual snapshots while OLTP transactions run on the most recent version of the database. Inside both execution engines, we still apply MVCC. The most significant challenge of a hybrid approach is to generate the snapshots at a high frequency. Previous approaches heavily suffered from the high cost of snapshot creation. In our approach termed AnKer, we follow the current trend of co-designing underlying system components and the DBMS, to overcome the restrictions of the OS by introducing a custom system call vm_snapshot. It allows fine-granular snapshot creation that is orders of magnitudes faster than state-of-the-art approaches. Our experimental evaluation on an HTAP workload based on TPC-C transactions and OLAP queries show that our snapshotting mechanism is more than a factor of 100x faster than fork-based snapshotting and that the latency of OLAP queries is up to a factor of 4x lower than MVCC in a single execution engine. Besides, our approach enables a higher OLTP throughput than all state-of-the-art methods.

Closing the circle of algorithmic and system-centric database optimization : a comprehensive survey on adaptive indexing, data partitioning, and the rewiring of virtual memory

Over the decades, with the increase of computing resources, the amount of data to manage also increased tremendously. Besides of the sheer quantity of information, the quality of it highly varies today. Indexing all this data with equal effort is cumbersome and wasteful. Thus, adaptive indexing algorithms refine parts of interest more carefully. Unfortunately, the adaptivity also introduces a set of new problems. High variance in response times and low robustness against certain workloads are just two issues to mention. A vast amount of methods have been proposed to deal with these problems. Thus, in the first part of this thesis, we will reinvestigate, analyze, and enhance the class of adaptive indexing methods in a comprehensive evaluation on the algorithmic level. In total, we discuss 18 cracking methods, 6 sorting algorithms, and 3 full index structures, including our own proposed methods. Consequently, we identify data partitioning as the common component. Thus, in the second part, we analyze the surprising amount of optimizations possible to enhance partitioning. Interestingly, they mostly originate from a more sophisticated mapping of the method to the system properties, thus shifting our perspective to a system-centric view. Subsequently, in the third part, we dig down to the ground level by exploiting a core feature of any modern operating system, the virtual memory system. We investigate how virtual and physical memory can be separated in user space and how the mappings between the two memory types can be rewired freely at runtime. Using rewiring, we are able to significantly enhance core applications of data management systems. Finally, we apply the techniques identified in this thesis to the initial adaptive indexing algorithm to significantly improve it — and close the circle.