Ensuring the ACID properties of transactions is the fundamental functionality of transactional DBMSs. However, through our study on existing solutions on transaction management, we found that transaction implementations in some mainstream databases, such as MySQL, MariaDB and TiDB, may violate what they claim in their documentation, in the form of incorrect database state or query results. Since there is still a lack of efficient and comprehensive testing methods to detect bugs within transaction management implementation for off-the-shelf DBMSs at present, we propose Fucci, a fuzzing framework, to solve the problem. Given a target DBMS, Fucci improves the efficiency of detecting transaction bugs through three key components: Random Conflict Construction (RCC), Multilevel Constraint Solving (MCS), and Experience-driven Automatic Simplification (EAS). RCC addresses the issue of inadequate case validity by ensuring the presence of read-write or write-write conflicts between transactions. MCS enhances the accuracy and efficiency of the transaction oracle by employing an external multi-version control system to solve data visibility. EAS is ultimately adopted to improve the efficiency of simplification and the readability of the identified bug cases. All of the above strategies are tested on commercial databases such as MySQL, MariaDB and TiDB. Accordingly, 6 previously unknown transaction bugs and 14 known duplicate transaction bugs have been newly discovered, most of which have been officially acknowledged.

Due to the increasing demand for extreme-scale time-series data workloads in data centers, it is required to build a high-performance semantic caching system that leverages the semantics and results of historical queries to answer time-series queries. Existing caching solutions either ignore the semantics of queries, offering suboptimal performance, or focus only on specific scenarios, providing small-capacity, limited functionality. In this paper, we summarize the query patterns of time-series data workload and propose the definition of semantic time-series caching for the first time. Accordingly, we present a semantic time-series caching system, STsCache, based on a hybrid storage model with memory and NVMe SSD. We propose a series of optimized strategies, such as slab-based semantic data management, semantic index, semantic value-driven batch eviction, time-aware deduplication insertion, and lazy compaction. We implemented and evaluated STsCache via benchmarks and production environments. STsCache can increase throughput of popular time-series databases (InfluxDB, TimescaleDB) by 4.8–10.8X and reduce latency by 79.9%-93.5%. Compared with the latest time-series caching schemes (TSCache, BSCache), STsCache can increase throughput by 1.5–4.5X, reduce latency by 59.4%-81.9%, and increase hit ratios by 22.5%-82.4%.

Proximity graphs (PG) have gained increasing popularity as the state-of-the-art solutions to k -approximate nearest neighbor ( k -ANN) search on high-dimensional data, which serves as a fundamental function in various fields, e.g., retrieval-augmented generation. Although PG-based approaches have the best k -ANN search performance, their index construction cost is superlinear to the number of points. Such superlinear cost substantially limits their scalability in the era of big data. Hence, the goal of this paper is to accelerate the construction of PG-based methods without compromising their k -ANN search performance. To achieve this goal, two mainstream categories of PG are revisited: relative neighborhood graph (RNG) and navigable small world graph (NSWG). By revisiting their construction process, we find the issues of construction efficiency. To address these issues, we propose a new construction framework with a novel pruning strategy for edge selection, which accelerates RNG construction while keeping its k -ANN search performance. Then, we integrate this framework into NSWG construction to enhance both the construction efficiency and k -ANN search performance of NSWG. Extensive experiments are conducted to validate our construction framework for both RNG and NSWG, and that it significantly reduces the PG construction cost, achieving up to 5.6x speedup, while not compromising the k -ANN search performance.

In database management systems, concurrency control manages the interleaved execution of multiple transactions, ensuring data integrity and consistency. However, in high-conflict scenarios, current strategies often lead to frequent transaction aborts, resulting in a significant waste of time on ineffective operations. To effectively address this challenge, we introduce an innovative Prior Cascading Concurrency Control (PC3) mechanism. This mechanism aims to proactively predict conflicts and minimize the performance penalty caused by these conflicts through a series of precise decisions. Specifically, PC3employs various prediction models to forecast transaction working sets, providing accurate transaction information for conflict detection. On this basis, we implemented a hash-based conflict detection method and established a cascading decision algorithm to minimize transaction abort frequency. Experimental results on the TPC-C workload show that in high-conflict scenarios with a Zipfian skew and thread counts between 5 and 40, PC3reduces the number of erroneous transactions by 18 times, and increases throughput by approximately 30.7%. compared to the best-performing optimistic methods.

Given an sql, a rdbms performs a series of operations to generate a Query Execution Plan (qep), which tells how the results will be collected and returned eventually. The whole pipeline for obtaining the qep is the core functionality of a rdbms, thus is definitely a fundamental knowledge that must be acquired by database learners and junior engineers of any rdbms. Unfortunately, though the majority of rdbmss provide EXPLAIN statement to show the qep, general users cannot see how/why these plans are generated. The only way for learning that is to turn to the textbook, which contains limited number of predefined examples accordingly. However, they are too sketchy to allow us to have a hand-on experience in practice. In this work, we present a general framework, DBinsight, that unveils the query processing pipeline visually at each phase during the processing pipeline, including parsing, translating, query optimization, etc. Considering that the underlying designs and optimization strategies of rdbmss are different, in DBinsight we present an SQPProfile interface, such that heterogeneous data structures in various rdbmss are normalized to a uniform format. Thanks to that, in DBinsight we only need to focus on offering the presentation and interaction functionalities based on the uniformed SQPProfile, and do not need to worry about the difference in the underlying rdbmss.

Vehicle re-identification (re-ID) has received more attention in recent years as a significant work, making huge contribution to the intelligent video surveillance. The complex intra-class and inter-class variation of vehicle images bring huge challenges for vehicle re-ID, especially for the similar vehicle re-ID. In this paper we focus on an interesting and challenging problem, vehicle re-ID of the same/similar model. Previous works mainly focus on extracting global features using deep models, ignoring the individual loa-cal regions in vehicle front window, such as decorations and stickers attached to the windshield, that can be more discriminative for vehicle re-ID. Instead of directly embedding these regions to learn their features, we propose a Regional Structure-Aware model (RSA) to learn structure-aware cues with the position distribution of individual local regions in vehicle front window area, constructing a FW structural map space. In this map sapce, deep models are able to learn more robust and discriminative spatial structure-aware features to improve the performance for vehicle re-ID of the same/similar model. We evaluate our method on a large-scale vehicle re-ID dataset Vehicle-1M. The experimental results show that our method can achieve promising performance and outperforms several recent state-of-the-art approaches.