Distributed Stream Processing Systems (DSPSs) form the backbone of real-time processing and analytics at ByteDance, where Apache Flink powers one of the largest production clusters worldwide. Ensuring resiliency, the ability to withstand and rapidly recover from failures, together with operational stability, which provides consistent and predictable performance under normal conditions, is essential for meeting strict Service Level Objectives (SLOs). However, achieving resiliency and stability in large-scale production environments remains challenging due to the cluster scale, business diversity, and significant operational overhead. In this work, we present StreamShield, a production-proven resiliency solution deployed in ByteDance's Flink clusters. Designed along complementary perspectives of the engine and cluster, StreamShield introduces key techniques to enhance resiliency, covering runtime optimization, fine-grained fault-tolerance, hybrid replication strategy, and high availability under external systems. Furthermore, StreamShield proposes a robust testing and deployment pipeline that ensures reliability and robustness in production releases. Extensive evaluations on a production cluster demonstrate the efficiency and effectiveness of techniques proposed by StreamShield.

Distributed stream processing systems rely on the dataflow model to define and execute streaming jobs, organizing computations as Directed Acyclic Graphs (DAGs) of operators. Adjusting the parallelism of these operators is crucial to handling fluctuating workloads efficiently while balancing resource usage and processing performance. However, existing methods often fail to effectively utilize execution histories or fully exploit DAG structures, limiting their ability to identify bottlenecks and determine the optimal parallelism. In this paper, we propose StreamTune, a novel approach for adaptive parallelism tuning in stream processing systems. StreamTune incorporates a pre-training and fine-tuning framework that leverages global knowledge from historical execution data for job-specific parallelism tuning. In the pre-training phase, StreamTune clusters the historical data with Graph Edit Distance and pre-trains a Graph Neural Network-based encoder per cluster to capture the correlation between the operator parallelism, DAG structures, and the identified operator-level bottlenecks. In the online tuning phase, Stream-Tu ne iteratively refines operator parallelism recommendations using an operator-level bottleneck prediction model enforced with a monotonic constraint, which aligns with the observed system performance behavior. Evaluation results demonstrate that StreamTune reduces reconfigurations by up to 29.6% and parallelism degrees by up to 30.8% in Apache Flink under a synthetic workload. In Timely Dataflow, StreamTune achieves up to an 83.3% reduction in parallelism degrees while maintaining comparable processing performance under the Nexmark benchmark, when compared to the state-of-the-art methods.

Large language models (LLMs) have shown increasing effectiveness in Text-to-SQL tasks. However, another closely related problem, Cross-System SQL Translation (a.k.a., SQL-to-SQL), which adapts a query written for one database system (e.g., MySQL) into its equivalent one for another system (e.g., ClickHouse), is of great practical importance but remains underexplored. Existing SQL benchmarks are not well-suited for SQL-to-SQL evaluation, which (1) focus on a limited set of database systems (often just SQLite) and (2) cannot capture many system-specific SQL dialects (e.g., customized functions, data types, and syntax rules). Thus, in this paper, we introduce PARROT, a Practical And Realistic BenchmaRk for CrOss-System SQL Translation. PARROT comprises 598 translation pairs from 38 open-source benchmarks and real-world business services, specifically prepared to challenge system-specific SQL understanding (e.g., LLMS achieve lower than 38.53% accuracy on average). We also provide multiple benchmark variants, including PARROT-Diverse with 28,003 translation (for extensive syntax testing) and PARROT-Simple with 5,306 representative samples (for focused stress testing), covering 22 production-grade database systems. To promote future research, we release a public leaderboard and source code at: https://code4db.github.io/parrot-bench/.

Modern analytical query engines (AQEs) are essential for large-scale data analysis and processing. These systems usually provide numerous query-level tunable knobs that significantly affect individual query performance. While several studies have explored automatic DBMS configuration tuning, they have several limitations to handle query-level tuning. Firstly, they fail to capture how knobs influence query plans, which directly affect query performance. Secondly, they overlook query failures during the tuning processing, resulting in low tuning efficiency. Thirdly, they struggle with cold-start problems for new queries, leading to prolonged tuning time. To address these challenges, we propose AQETuner, a novel Bayesian Optimization-based system tailored for reliable query-level knob tuning in AQEs. AQETuner first applies the attention mechanisms to jointly encode the knobs and plan query, effectively identifying the impact of knobs on plan nodes. Then, AQETuner employs a dual-task Neural Process to predict both query performance and failures, leveraging their interactions to guide the tuning process. Furthermore, AQETuner utilizes Particle Swarm Optimization to efficiently generate high-quality samples in parallel during the initial tuning stage for the new queries. Experimental results show that AQETuner significantly outperforms existing methods, reducing query latency by up to 23.7% and query failures by up to 51.2%.

The log-structured merge tree (LSM-tree) has been widely adopted as a backbone of modern key-value stores. However, the multiple exponentially increased levels of LSM-tree makes it suffer from high write amplification. Existing studies often improve the write performance by sacrificing the read performance, which is inefficient to make trade-offs between the update and search efficiency. In this paper, we exploit nonvolatile memory (NVM) to address the write amplification issue for systems with NVM-SSD hybrid storage, and further propose a reinforcement learning method to navigate between update and search efficiency on the varying workloads. Specifically, we first propose a lightweight hot data identification method to efficiently capture access recency as well as frequency in NVM with relative large capacity. On this basis, we can eliminate different versions of frequently updated data in high-performance NVM without pushing them to SSD. To improve the data access locality and facilitate fine-grained index tuning in each level, we devise a virtual-split method to partition the key space gradually without extra write amplification. Finally, we propose a cost based Q-learning algorithm to adaptively tune the data organizations of each partition according to the changing access patterns. Experimental results show that our approach outperforms existing methods by up to 2.67×.

Structure Learning for Bayesian network (BN) is an important problem with extensive research. It plays central roles in a wide variety of applications in Alibaba Group. However, existing structure learning algorithms suffer from considerable limitations in real-world applications due to their low efficiency and poor scalability. To resolve this, we propose a new structure learning algorithm LEAST, which comprehensively fulfills our business requirements as it attains high accuracy, efficiency and scalability at the same time. The core idea of LEAST is to formulate the structure learning into a continuous constrained optimization problem, with a novel differentiable constraint function measuring the acyclicity of the resulting graph. Unlike with existing work, our constraint function is built on the spectral radius of the graph and could be evaluated in near linear time w.r.t. the graph node size. Based on it, LEAST can be efficiently implemented with low storage overhead. According to our benchmark evaluation, LEAST runs 1-2 orders of magnitude faster than state-of-the-art method with comparable accuracy, and it is able to scale on BNs with up to hundreds of thousands of variables. In our production environment, LEAST is deployed and serves for more than 20 applications with thousands of executions per day. We describe a concrete scenario in a ticket booking service in Alibaba, where LEAST is applied to build a near real-time automatic anomaly detection and root error cause analysis system. We also show that LEAST unlocks the possibility of applying BN structure learning in new areas, such as large-scale gene expression data analysis and explainable recommendation system.

Cardinality estimation (CardEst) plays a significant role in generating high-quality query plans for a query optimizer in DBMS. In the last decade, an increasing number of advanced CardEst methods (especially ML-based) have been proposed with outstanding estimation accuracy and inference latency. However, there exists no study that systematically evaluates the quality of these methods and answer the fundamental problem: to what extent can these methods improve the performance of query optimizer in real-world settings, which is the ultimate goal of a CardEst method. In this paper, we comprehensively and systematically compare the effectiveness of CardEst methods in a real DBMS. We establish a new benchmark for CardEst, which contains a new complex real-world dataset STATS and a diverse query workload STATS-CEB. We integrate multiple most representative CardEst methods into an open-source DBMS PostgreSQL, and comprehensively evaluate their true effectiveness in improving query plan quality, and other important aspects affecting their applicability. We obtain a number of key findings under different data and query settings. Furthermore, we find that the widely used estimation accuracy metric (Q-Error) cannot distinguish the importance of different sub-plan queries during query optimization and thus cannot truly reflect the generated query plan quality. Therefore, we propose a new metric P-Error to evaluate the performance of CardEst methods, which overcomes the limitation of Q-Error and is able to reflect the overall end-to-end performance of CardEst methods. It could serve as a better optimization objective for future CardEst methods.

Query optimizers rely on accurate cardinality estimation (CardEst) to produce good execution plans. The core problem of CardEst is how to model the rich joint distribution of attributes in an accurate and compact manner. Despite decades of research, existing methods either over-simplify the models only using independent factorization which leads to inaccurate estimates, or over-complicate them by lossless conditional factorization without any independent assumption which results in slow probability computation. In this paper, we propose FLAT, a CardEst method that is simultaneously fast in probability computation, lightweight in model size and accurate in estimation quality. The key idea of FLAT is a novel unsupervised graphical model, called FSPN. It utilizes both independent and conditional factorization to adaptively model different levels of attributes correlations, and thus combines their advantages. FLAT supports efficient online probability computation in near linear time on the underlying FSPN model, provides effective offline model construction and enables incremental model updates. It can estimate cardinality for both single table queries and multi-table join queries. Extensive experimental study demonstrates the superiority of FLAT over existing CardEst methods: FLAT achieves 1--5 orders of magnitude better accuracy, 1--3 orders of magnitude faster probability computation speed and 1--2 orders of magnitude lower storage cost. We also integrate FLAT into Postgres to perform an end-to-end test. It improves the query execution time by 12.9% on the well-known IMDB benchmark workload, which is very close to the optimal result 14.2% using the true cardinality.

Location prediction is widely used to forecast users' next place to visit based on his/her mobility logs. It is an essential problem in location data processing, invaluable for surveillance, business, and personal applications. It is very challenging due to the sparsity issues of check-in data. An often ignored problem in recent studies is the variety across different check-in scenarios, which is becoming more urgent due to the increasing availability of more location check-in applications. In this paper, we propose a new feature fusion based prediction approach, GALLOP, i.e., GlobAL feature fused LOcation Prediction for different check-in scenarios. Based on the carefully designed feature extraction methods, we utilize a novel combined prediction framework. Specifically, we set out to utilize the density estimation model to profile geographical features, i.e., context information, the factorization method to extract collaborative information, and a graph structure to extract location transition patterns of users' temporal check-in sequence, i.e., content information. An empirical study on three different check-in datasets demonstrates impressive robustness and improvement of the proposed approach.