With the prevalence of in-database AI-powered analytics, there is an increasing demand for database systems to efficiently manage the ever-expanding number and size of deep learning models. However, existing database systems typically store entire models as monolithic files or apply compression techniques that overlook the structural characteristics of deep learning models, resulting in suboptimal model storage overhead. This paper presents NeurStore, a novel in-database model management system that enables efficient storage and utilization of deep learning models. First, NeurStore employs a tensor-based model storage engine to enable fine-grained model storage within databases. In particular, we enhance the hierarchical navigable small world (HNSW) graph to index tensors, and only store additional deltas for tensors within a predefined similarity threshold to ensure tensor-level deduplication. Second, we propose a delta quantization algorithm that effectively compresses delta tensors, thus achieving a superior compression ratio with controllable model accuracy loss. Finally, we devise a compression-aware model loading mechanism, which improves model utilization performance by enabling direct computation on compressed tensors. Experimental evaluations demonstrate that NeurStore achieves superior compression ratios and competitive model loading throughput compared to state-of-the-art approaches.

With increasing demands for privacy, it becomes necessary to protect sensitive user query data when accessing public key-value databases. Existing Private Information Retrieval (PIR) schemes provide full security but suffer from poor scalability, limiting their applicability in large-scale deployment. We argue that in many real-world scenarios, a more practical solution should allow users to flexibly determine the privacy levels of their queries in a theoretically guided way, balancing security and performance based on specific needs. To formally provide provable guarantees, we introduce a novel concept of distance-based indistinguishability, which can facilitate users to comfortably relax their security requirements. We then design Femur, an efficient framework to securely query public key-value stores with flexible security and performance trade-offs. It uses a space-efficient learned index to convert query keys into storage locations, obfuscates these locations with extra noise provably derived by the distance-based indistinguishability theory, and sends the expanded range to the server. The server then adaptively utilizes the best scheme to retrieve data. We also propose a novel variable-range PIR scheme optimized for bandwidth-constrained environments. Experiments show that Femur outperforms the state-of-the-art designs even when ensuring the same full security level. When users are willing to relax their privacy requirements, Femur can further improve the performance gains to up to 163.9X, demonstrating an effective trade-off between security and performance.

Trusted execution environment (TEE) has provided an isolated and secure environment for building cloud-based analytic systems, but it still suffers from access pattern leakages caused by side-channel attacks. To better secure the data, computation inside TEE enclave should be made oblivious, which introduces significant overhead and severely slows down the computation. A natural way to speed up is to build the analytic system with multiple servers in the distributed setting. However, this setting raises a new security concern—the volumes of the transmissions among these servers can leak sensitive information to a network adversary. Existing works have designed specialized algorithms to address this concern, but their supports for equi-join, one of the most important but nontrivial database operators, are either inefficient, limited, or under a weak security assumption. In this paper, we present Jodes, an efficient oblivious join algorithm in the distributed setting. Jodes prevents the leakage on both the network and enclave sides, supports a general equi-join operation, and provides a high security level protection that only publicizes the input sizes and the output size. Meanwhile, it achieves both communication cost and computation cost asymptotically superior to existing algorithms. To demonstrate the practicality of Jodes, we conduct experiments in the distributed setting comprising 16 servers. Empirical results show that Jodes achieves up to a sixfold performance improvement over state-of-the-art join algorithms.

In contemporary database applications, the demand for memory resources is intensively high. To enhance adaptability to varying resource needs and improve cost efficiency, the integration of diverse storage technologies within heterogeneous memory architectures emerges as a promising solution. Despite the potential advantages, there exists a significant gap in research related to the security of data within these complex systems. This paper endeavors to fill this void by exploring the intricacies and challenges of ensuring data security in object-oriented heterogeneous memory systems. We introduce the concept of Unified Encrypted Memory (UEM) management, a novel approach that provides unified object references essential for data management platforms, while simultaneously concealing the complexities of physical scheduling from developers. At the heart of UEM lies the seamless and efficient integration of data encryption techniques, which are designed to ensure data integrity and guarantee the freshness of data upon access. Our research meticulously examines the security deficiencies present in existing heterogeneous memory system designs. By advancing centralized security enforcement strategies, we aim to achieve efficient object-centric data protection. Through extensive evaluations conducted across a variety of memory configurations and tasks, our findings highlight the effectiveness of UEM. The security features of UEM introduce low and acceptable overheads, and UEM outperforms conventional security measures in terms of speed and space efficiency.

In response to escalating concerns about data privacy in the Large Language Model (LLM) domain, we demonstrate EncChain , a pioneering solution designed to bolster data security in LLM applications. EncChain presents an all-encompassing approach to data protection, encrypting both the knowledge bases and user interactions. It empowers confidential computing and implements stringent access controls, offering a significant leap in securing LLM usage. Designed as an accessible Python package, EncChain ensures straightforward integration into existing systems, bolstered by its operation within secure environments and the utilization of remote attestation technologies to verify its security measures. The effectiveness of EncChain in fortifying data privacy and security in LLM technologies underscores its importance, positioning it as a critical advancement for the secure and private utilization of LLMs.

The Sparse Vector Technique (SVT) is one of the most fundamental tools in differential privacy (DP). It works as a backbone for adaptive data analysis by answering a sequence of queries on a given dataset, and gleaning useful information in a privacy-preserving manner. Unlike the typical private query releases that directly publicize the noisy query results, SVT is less informative---it keeps the noisy query results to itself and only reveals a binary bit for each query, indicating whether the query result surpasses a predefined threshold. To provide a rigorous DP guarantee for SVT, prior works in the literature adopt a conservative privacy analysis by assuming the direct disclosure of noisy query results as in typical private query releases. This approach, however, hinders SVT from achieving higher query accuracy due to an overestimation of the privacy risks, which further leads to an excessive noise injection using the Laplacian or Gaussian noise for perturbation. Motivated by this, we provide a new privacy analysis for SVT by considering its less informative nature. Our analysis results not only broaden the range of applicable noise types for perturbation in SVT, but also identify the exponential noise as optimal among all evaluated noises (which, however, is usually deemed non-applicable in prior works). The main challenge in applying exponential noise to SVT is mitigating the sub-optimal performance due to the bias introduced by noise distributions. To address this, we develop a utility-oriented optimal threshold correction method and an appending strategy, which enhances the performance of SVT by increasing the precision and recall, respectively. The effectiveness of our proposed methods is substantiated both theoretically and empirically, demonstrating significant improvements up to 50% across evaluated metrics.

In the Internet of Vehicle (IoV) systems, intelligent vehicles generate huge amounts of data that supports diverse services and applications. In practice, database systems are deployed in the cloud to manage data uploaded from the vehicle side and provide real-time query capacities. However, existing database systems are ill-suited because IoV data contains a large number of metrics and is written at an extremely high throughput. To better understand IoV data and corresponding challenges to underlying database systems, we conduct the first extensive empirical study of real-world IoV workloads. According to our findings from the study, we design Lindorm-UWC as a superior database for IoV systems. It implements a distributed architecture and a cold/hot data separation mechanism to accommodate massive amounts of IoV data. In each data partition, it deploys an ultra-wide-column storage engine to efficiently handle the query and ingestion of multi-metric data. We evaluate Lindorm-UWC under different data scales and various types of query. Our experimental results show that it can always achieve higher write throughput (over 79% increase) and competitive query performance compared to various alternative solutions. Lindorm-UWC has been serving IoV enterprise customers on Alibaba Cloud since 2019, managing tens of petabytes of IoV data.

Numerous studies have underscored the significant privacy risks associated with various leakage patterns in encrypted data stores. While many solutions have been proposed to mitigate these leakages, they either (1) incur substantial overheads, (2) focus on specific subsets of leakage patterns, or (3) apply the same security notion across various workloads, thereby impeding the attainment of fine-tuned privacy-efficiency trade-offs. In light of various detrimental leakage patterns, this paper starts with an investigation into which specific leakage patterns require our focus in the contexts of key-value, range-query, and dynamic workloads, respectively. Subsequently, we introduce new security notions tailored to the specific privacy requirements of these workloads. Accordingly, we propose and instantiate Swat, an efficient construction that progressively enables these workloads, while provably mitigating system-wide leakage via a suite of algorithms with tunable privacy-efficiency trade-offs. We conducted extensive experiments and compiled a detailed result analysis, showing the efficiency of our solution. Swat is about an order of magnitude slower than an encryption-only data store that reveals various leakage patterns and is two orders of magnitude faster than a trivial zero-leakage solution. Meanwhile, the performance of Swat remains highly competitive compared to other designs that mitigate specific types of leakage.

In cloud computing, remote accesses over the cloud data inevitably bring the issue of trust. Despite strong encryption schemes, adversaries can still learn sensitive information from encrypted data by observing data access patterns. Oblivious RAMs (ORAMs) are proposed to protect against access pattern attacks. However, directly deploying ORAM constructions in an encrypted database brings large computational overhead. In this work, we focus on oblivious joins over a cloud database. Existing studies in the literature are restricted to either primary-foreign key joins or binary equi-joins. Our major contribution is to support general band joins and multiway equi-joins. For oblivious join without ORAMs, we extend the existing binary equi-join algorithm to support general band joins obliviously. For oblivious join with ORAMs, we integrate$B$-tree indices into ORAMs for each input table and retrieve blocks through the indices in join processing. The key point is to avoid retrieving tuples that make no contribution to the final join result and bound the number of accesses to each$B$-tree index. The effectiveness and efficiency of our algorithms are demonstrated through extensive evaluations over real-world datasets. Our method shows orders of magnitude speedup for oblivious multiway equi-joins in comparison with baseline algorithms.

Leader-based Byzantine fault-tolerant (BFT) consensus protocols used by permissioned blockchains have limited scalability and robustness. To alleviate the leader bottleneck in BFT consensus, we introduce Stratus, a robust shared mempool protocol that decouples transaction distribution from consensus. Our idea is to have replicas disseminate transactions in a distributed manner and have the leader only propose transaction ids. Stratus uses a provably available broadcast (PAB) protocol to ensure the availability of the referenced transactions. To deal with unbalanced load across replicas, Stratus adopts a distributed load balancing protocol.We implemented and evaluated Stratus by integrating it with state-of-the-art BFT-based blockchain protocols. Our evaluation of these protocols in both LAN and WAN settings shows that Stratus-based protocols achieve 5× to 20× higher throughput than their native counterparts in a network with hundreds of replicas. In addition, the performance of Stratus degrades gracefully in the presence of network asynchrony, Byzantine attackers, and unbalanced workloads.

Functional dependencies (FDs) have been extensively employed in discovering inferential relationships in databases, which provide feasible approaches for many data mining tasks, such as data obfuscation, query optimization, and schema normalization. Since the explosive growth of data leads to a rapid increase of FDs on large datasets, existing algorithms that pay more attention to the exact FD discovery cannot extract FDs efficiently. To bridge this gap, we propose an Efficient double-cycle approximation of Functional Dependency (EulerFD) discovery algorithm, which ensures both efficiency and accuracy of FD discovery. EulerFD induces FDs from invalid ones as invalidating an FD only requires comparing and verifying some pairs of tuples (that violate the dependency) while validating an FD requires examining and verifying all tuples. Considering the abundant tuple pairs in large datasets, a novel sampling strategy is employed in EulerFD to quickly extract invalid FDs by revising the sampling range according to previous sampling results. Furthermore, EulerFD evaluates the stopping criteria in a double-cycle structure as feedback for further sampling. The sampling strategy and the double-cycle structure complement each other to achieve a more efficient sampling effect. Experimental results on real-world and synthetic datasets, especially the massive datasets from DMS of Alibaba Cloud, justify the design and verify the efficiency and effectiveness of the proposed EulerFD.

Learned indexes have been proposed to replace classic index structures like B-Tree with machine learning (ML) models. They require to replace both the indexes and query processing algorithms currently deployed by the databases, and such a radical departure is likely to encounter challenges and obstacles. In contrast, we propose a fundamentally different way of using ML techniques to build a better R-Tree without the need to change the structure or query processing algorithms of traditional R-Tree. Specifically, we develop reinforcement learning (RL) based models to decide how to choose a subtree for insertion and how to split a node when building and updating an R-Tree, instead of relying on hand-crafted heuristic rules currently used by the R-Tree and its variants. Experiments on real and synthetic datasets with up to more than 100 million spatial objects show that our RL based index outperforms the R-Tree and its variants in terms of query processing time.

We study the problem of random sampling in the secure multi-party computation (MPC) model. In MPC, taking a sample securely must have a cost Ω(n) irrespective to the sample size s. This is in stark contrast with the plaintext setting, where a sample can be taken in O(s) time trivially. Thus, the goal of approximate query processing (AQP) with sublinear costs seems unachievable under MPC. To get around this inherent barrier, in this paper we take a two-stage approach: In the offline stage, we generate a batch of n/s samples with (n) total cost, which can then be consumed to answer queries as they arrive online. Such an approach allows us to achieve an Õ(s) amortized cost per query, similar to the plaintext setting. Based on our secure batch sampling algorithms, we build MASQUE, an MPC-AQP system that achieves sublinear online query costs by running an MPC protocol to evaluate the queries on pre-generated samples. MASQUE achieves the strong security guarantee of the MPC model, i.e., nothing is revealed beyond the query result, which itself can be further protected by (amplified) differential privacy

The increasing prevalence of data breaches necessitates robust data protection measures in computational tasks. Secure computation outsourcing (SCO) presents a viable solution by safeguarding the confidentiality of inputs and outputs in data processing without disclosure. Nonetheless, this approach assumes the existence of a trustworthy coordinator to orchestrate and oversee the process, typically implying that data owners must fulfill this role themselves. In this paper, we consider secure delegated data processing (SDDP), an expanded data processing scenario wherein data owners simply delegate their data to SDDP providers for subsequent value mining or other downstream applications, eliminating the necessary involvement of data owners or trusted entities to dive into data processing deeply. However, general-purpose SDDP poses significant challenges in permitting the discretionary execution of computational tasks by SDDP providers on sensitive data while ensuring confidentiality. Existing approaches are insufficient to support SDDP in either efficiency or universality. To tackle this issue, we propose TGCB, a TEE-based General-purpose Computational Backend, designed to endow general-purpose computation with SDDP capabilities from an engineering perspective, powered by TEE-based code integrity and data confidentiality. Central to TGCB is the Encryption Programming Language (EPL) that defines computational tasks in SDDP. Specifically, SDDP providers can express arbitrary computable functions as EPL scripts, processed by TGCB's interfaces, securely interpreted and executed in TEE, ensuring data confidentiality throughout the process. As a universal computational backend, TGCB extensively bolsters data security in existing general-purpose computational tasks, allowing data owners to leverage SDDP without privacy concerns.

Internet services supported by large-scale distributed systems have become essential for our daily life. To ensure the stability and high quality of services, diverse metric data are constantly collected and managed in a time-series database to monitor the service status. However, when the number of metrics becomes massive, existing time-series databases are inefficient in handling high-rate data ingestion and queries hitting multiple metrics. Besides, they all lack the support of machine learning functions, which are crucial for sophisticated analysis of large-scale time series. In this paper, we present Lindorm TSDB, a distributed time-series database designed for handling monitoring metrics at scale. It sustains high write throughput and low query latency with massive active metrics. It also allows users to analyze data with anomaly detection and time series forecasting algorithms directly through SQL. Furthermore, Lindorm TSDB retains stable performance even during node scaling. We evaluate Lindorm TSDB under different data scales, and the results show that it outperforms two popular open-source time-series databases on both writing and query, while executing time-series machine learning tasks efficiently.

Due to the increasing demand for scalable and interactive data analytics, column stores have become the de-facto choice in many analytical databases. As a common and fundamental operation in column stores, expression evaluation has a remarkable effect on many queries. To speed up expression evaluation, vectorized techniques such as Single-Instruction-Multiple-Data (SIMD) instructions are widely used. However, there are few works concerning dedicated optimizations for SIMD-based expression evaluation for column stores. In this paper, we propose a runtime optimization framework named ROVEC that enables effective optimizations for SIMD-based expression evaluation. The key idea is to optimize logical expression at execution time, by leveraging lightweight compression and fine-grained statistics associated with the compressed data. ROVEC removes unnecessary type casting and finds the tightest type during evaluation, which maximizes the concurrent operands in SIMD instructions. ROVEC can be applied to many expression-evaluation-intensive operators (e.g., table scan and theta join) for different data types (e.g., numeric, time and string). To validate the effectiveness of ROVEC, we integrate it into a columnar database PolarDB-C. Our evaluation results show that ROVEC improves up to 120% (60% on average) throughput of table scan and up to 50% (30% on average) latency of theta join.

Cloud computing is on the rise, which promotes new breeds of database systems to accommodate the cloud environment. The development of cloud-native databases reveals three trends. One is the adoption of multi-datacenter (DC) deployment to survive the downtime of any single site. Another is the separation of computation and storage resources to achieve higher elasticity and scalability. The last is the support of HTAP to eliminate data redundancy and system complexity from heterogeneous databases. To cater to these trends, we design a distributed relational database called PolarDB-X, which is built on top of the cloud-native database PolarDB. It hence inherits many cloud-native features, such as multi-datacenter deployment and elasticity. To achieve cross-DC capability, it leverages Paxos and hybrid logical clock to achieve durability and snapshot-isolation consistency with low coordination costs. For resource elasticity, since the underlying PolarDB supports rapid migration of tenants between nodes, PolarDB-X can quickly scale the cluster to cope with a sudden traffic increase. For HTAP support, with the help of read replicas and a HTAP executor, PolarDB-X can improve the latency and parallelism of analytical queries without impacting concurrently-running TP workloads. Using its MPP engine and an in-memory column index, the efficiency of analytical queries can be further enhanced. PolarDB-X is now a cloud database service at Alibaba Cloud. We have learned many useful lessons from its development and operation, and have incorporated those into our design and analysis.

Verifiability is the backbone of most ledger systems to realize credible authentication. However, existing permissioned blockchains and centralized ledger databases lack rigorous verifiability to authenticate all facts (i.e., what-when-who validation). Besides, they suffer from high verification cost to a continually growing immutable storage. In this paper, we introduce verification principles behind LedgerDB, a centralized ledger database that achieves both strong external auditability and fast verification. We coin a novel concept called Dasein Verification that composes of three validation factors what-when-who to formalize ledger auditing. Regarding what, LedgerDB devises fam (fractal accumulating model) to accelerate existence verification, and CM-Tree for efficient lineage verification. Veri-fiable data mutations are also supported. For when, we discuss attacks on existing time pegging protocols that compromise the authenticity of timestamps, and propose a time notary protocol to resolve those threats. Evaluations show that fam and CM- Tree significantly outperform traditional approaches. Compared to Hyperledger Fabric, LedgerDB achieves 23x higher verification throughput with 500 x lower latency in notarization applications, and 3 x higher throughput with 300 x lower latency in lineage tracking applications. As a public-cloud ledger service, the end-to-end verification latencies of LedgerDB are on average 50 x and 1000x lower than that of QLDB in the above applications, respectively.

Many individuals and companies choose the public cloud as their data and IT infrastructure platform. But remote accesses over the data inevitably bring the issue of trust. Despite strong encryption schemes, adversaries can still learn sensitive information from encrypted data by observing data access patterns. Oblivious RAMs (ORAMs) are proposed to protect against access pattern attacks. However, directly deploying ORAM constructions in an encrypted database brings large computational overhead.

With the rapid growth of cloud computing, efficient management of multi-tenant databases has become a vital challenge for cloud service providers. It is particularly important for Alibaba, which hosts a distributed multi-tenant database supporting one of the world's largest e-commerce platforms. It serves tens of millions of sellers as tenants, and supports transactions from hundreds of millions of buyers. The inherent imbalance of shopping preferences from the buyers essentially generates a drastically skewed workload on the database, which could create unpredictable hotspots and consequently large throughput decline and latency increase. In this paper, we present the architecture and implementation of ESDB (ElasticSearch Database), a cloud-native document-oriented database which has been running on Alibaba Cloud for 5 years as the main transaction database behind Alibaba's e-commerce platform. ESDB provides strong full-text search and retrieval capability, and proposes dynamic secondary hashing as the solution for processing extremely skewed workloads. We evaluate ESDB with both simulated workloads and real-world workloads, and demonstrate that ESDB significantly enhances write throughput and reduces the completion time of writes without sacrificing query throughput.

There has been an increasing interest in building cloud-native databases that decouple computation and storage for elasticity. A cloud-native database often adopts a cloud storage underneath its storage engine, leveraging another layer of virtualization and providing a high-performance and elastic storage service without exposing complex storage details. It helps reduce the maintenance cost and expedite development cycles for the database kernels. We have observed that there are significant differences between the local and the cloud storage that invalid many designs inside existing databases when they are ported to the cloud storage. In this paper, we analyze the challenges and opportunities of both B-tree and LSM-tree-based storage engines when they are deployed on a cloud storage. We propose an optimization framework that guides database developers to transform on-premise databases into their cloud-native counterparts. We use a B+-tree-based InnoDB as a demonstration vehicle where we have implemented a suite of optimizations using the proposed framework and extend such efforts to the LSM-tree-based RocksDB. On both engines, our evaluations show significant performance improvements on the cloud storage.

In-memory databases (IMDBs) have been the backbone of modern systems that demand high throughput and low latency. Because of the cost and volatility of DRAM, IMDBs become incompetent when dealing with workloads that require large data volume and strict durability. The emergence of non-volatile memory (NVM) brings new opportunities for IMDBs to tackle this situation. However, it is non-trivial to build an NVM-based IMDB, due to performance degradation, NVM programming complexity, and other challenges. In this paper, we present Tair-PMem , an NVM-based enterprise-strength database atop Redis, the most popular IMDB. Tair-PMem adopts a well-controlled data layout and a log-as-user-data design to mitigate NVM overheads. It eases the NVM programming complexity by providing a hybrid memory programming toolkit. To better leverage the enterprise-strength features and implementations from Redis, Tair-PMem retrofits it in a less intrusive way to achieve full compatibility and stability, while retaining its advanced features. With all of the above techniques elaborately implemented, Tair-PMem satisfies full durability, high throughput, and low latency at the same time. Tair-PMem has now been publicly available as a cloud service on Alibaba Cloud. To the best of our knowledge, Tair-PMem is the first cloud service that makes good use of the persistence capability of NVM.

Managing massive trajectory data from various moving objects has always been a demanding task. A desired trajectory data system should be versatile in its supported query types and distance functions, of low storage cost, and be consistently efficient on processing trajectory data of different properties. Unfortunately, none of the existing systems can meet the above three criteria at the same time. To this end, we propose VRE, aversatile,robust, andeconomical trajectory data system.VRE separates the storage from the processing. In the storage layer, we propose a novel segment-based storage model that takes advantage of the strengths of both point-based and trajectory-based storage models. VRE supports these three storage models and ten storage schemas upon them. With the secondary index, VRE reduces the storage cost up to 3x. In the processing layer, we first propose a two-stage processing framework and a pushdown strategy to alleviate full trajectory transmission cost. Then, we design a unified pruning strategy for five widely used trajectory distance functions and numerous tailored processing algorithms for five advanced queries. Extensive experiments are conducted to verify the design choice and efficiency of VRE, from which we present some key insights that are crucial to both VRE and future trajectory system's design.

Recent years have witnessed the rapid development of the encrypted database, due to the increasing number of data privacy breaches and the corresponding laws and regulations that caused millions of dollars in loss. These encrypted databases may rely on different techniques, such as cryptographic primitives and trusted execution environments. In this work, we investigate the feasibility of utilizing fully homomorphic encryption (FHE) to support unbounded database aggregation queries, which typically involve comparisons as filtering predicates and a final aggregation. These operators are theoretically supported by FHE, but need careful algorithm design to maximize the efficiency and have not been explored before. We creatively use two types of FHE schemes, i.e. , one for numerical and one for binary value, to enjoy their advantages respectively. To bridge the encrypted values between these two schemes for seamless query processing without client-server interaction, we propose a novel ciphertext transformation mechanism, which is of independent research interest, to close this gap. We further implement our system and test it over three TPC-H queries and a query over a real social media e-commerce database. Evaluation results show that, to process an aggregation query over 8 k encrypted rows takes about 430 seconds. Although it is slower than plaintext processing in magnitudes and still has much room for improvement, as the very first work in this domain, our system demonstrates the feasibility of using FHE to process OLAP queries.

The past decade has witnessed the rapid development of cloud computing and data-centric applications. While these innovations offer numerous attractive features for data processing, they also bring in new issues about the loss of data ownership. Though some encrypted databases have emerged recently, they can not fully address these concerns for the data owner. In this paper, we propose an ownership-preserving database (OPDB), a new paradigm that characterizes different roles' responsibilities from nowadays applications and preserves data ownership throughout the entire application. We build Operon to follow the OPDB paradigm, which utilizes the trusted execution environment (TEE) and introduces a behavior control list (BCL). Different from access controls that merely handle accessibility permissions, BCL further makes data operation behaviors under control. Besides, we make Operon practical for real-world applications, by extending database capabilities towards flexibility, functionality and ease of use. Operon is the first database framework with which the data owner exclusively controls its data across different roles' subsystems. We have successfully integrated Operon with different TEEs, i.e. , Intel SGX and an FPGA-based implementation, and various database services on Alibaba Cloud, i.e. , PolarDB and RDS PostgreSQL. The evaluation shows that Operon achieves 71% - 97% of the performance of plaintext databases under the TPC-C benchmark while preserving the data ownership.

\beginabstract The trend in the DBMS market is to migrate to the cloud for elasticity, high availability, and lower costs. The traditional, monolithic database architecture is difficult to meet these requirements. With the development of high-speed network and new memory technologies, disaggregated data center has become a reality: it decouples various components from monolithic servers into separated resource pools (e.g., compute, memory, and storage) and connects them through a high-speed network. The next generation cloud native databases should be designed for disaggregated data centers. In this paper, we describe the novel architecture of \name, which follows thedisaggregation design paradigm: the CPU resource on compute nodes is decoupled from remote memory pool and storage pool. Each resource pool grows or shrinks independently, providing \revon-demand provisoning at multiple dimensions while improving reliability. We also design our system to mitigate the inherent penalty brought by resource disaggregation, and introduce optimizations such as optimistic locking and index awared prefetching. Compared to the architecture that uses local resources, \name achieves better dynamic resource provisioning capabilities and 5.3 times faster failure recovery speed, while achieving comparable performance. \endabstract

The emergence of trusted hardwares (such as Intel SGX) provides a new avenue towards verifiable database. Such trust hardwares act as an additional trust anchor, allowing great simplification and, in turn, performance improvement in the design of verifiable databases. In this paper, we introduce the design and implementation of VeriDB, an SGX-based verifiable database that supports relational tables, multiple access methods and general SQL queries. Built on top of write-read consistent memory, VeriDB provides verifiable page-structured storage, where results of storage operations can be efficiently verified with low, constant overhead. VeriDB further provides verifiable query execution that supports general SQL queries. Through a series of evaluation using practical workload, we demonstrate that VeriDB incurs low overhead for achieving verifiability: an overhead of 1-2 microseconds for read/write operations, and a 9% - 39% overhead for representative analytical workloads.

Data confidentiality is one of the biggest concerns that hinders enterprise customers from moving their workloads to the cloud. Thanks to the trusted execution environment (TEE), it is now feasible to build encrypted databases in the enclave that can process customers' data while keeping it confidential to the cloud. Though some enclave-based encrypted databases emerge recently, there remains a large unexplored area in between about how confidentiality can be achieved in different ways and what influences are implied by them. In this paper, we first provide a broad exploration of possible design choices in building encrypted database storage engines, rendering trade-offs in security, performance and functionality. We observe that choices on different dimensions can be independent and their combination determines the overall trade-off of the entire storage. We then propose Enclage , an encrypted storage engine that makes practical trade-offs. It adopts many enclave-native designs, such as page-level encryption, reduced enclave interaction, and hierarchical memory buffer, which offer high-level security guarantee and high performance at the same time. To make better use of the limited enclave memory, we derive the optimal page size in enclave and adopt delta decryption to access large data pages with low cost. Our experiments show that Enclage outperforms the baseline, a common storage design in many encrypted databases, by over 13x in throughput and about 5x in storage savings.

Data collaboration activities typically require systematic or protocol-based coordination to be scalable. Git, an effective enabler for collaborative coding, has been attested for its success in countless projects around the world. Hence, applying the Git philosophy to general data collaboration beyond coding is motivating. We call it Git for data. However, the original Git design handles data at the file granule, which is considered too coarse-grained for many database applications. We argue that Git for data should be co-designed with database systems. To this end, we developed ForkBase to make Git for data practical. ForkBase is a distributed, immutable storage system designed for data version management and data collaborative operation. In this demonstration, we show how ForkBase can greatly facilitate collaborative data management and how its novel data deduplication technique can improve storage efficiency for archiving massive data versions.

The explosion of time series advances the development of time series databases. To reduce storage overhead in these systems, data compression is widely adopted. Most existing compression algorithms utilize the overall characteristics of the entire time series to achieve high compression ratio, but ignore local contexts around individual points. In this way, they are effective for certain data patterns, and may suffer inherent pattern changes in real-world time series. It is therefore strongly desired to have a compression method that can always achieve high compression ratio in the existence of pattern diversity. In this paper, we propose a two-level compression model that selects a proper compression scheme for each individual point, so that diverse patterns can be captured at a fine granularity. Based on this model, we design and implement AMMMO framework, where a set of control parameters is defined to distill and categorize data patterns. At the top level, we evaluate each sub-sequence to fill in these parameters, generating a set of compression scheme candidates (i.e., major mode selection). At the bottom level, we choose the best scheme from these candidates for each data point respectively (i.e., sub-mode selection). To effectively handle diverse data patterns, we introduce a reinforcement learning based approach to learn parameter values automatically. Our experimental evaluation shows that our approach improves compression ratio by up to 120% (with an average of 50%), compared to other time-series compression methods.

With the increasing demand for real-time system monitoring and tracking in various contexts, the amount of time-stamped event data grows at an astonishing rate. Analytics on time-stamped events must be real time and the aggregated results need to be accurate even when data arrives out of order. Unfortunately, frequent occurrences of out-of-order data will significantly slow down the processing, and cause a large delay in the query response. Timon is a timestamped event database that aims to support aggregations and handle late arrivals both correctly (i.e., upholding the exactly-once semantics) and efficiently. Our insight is that a broad range of applications can be implemented with data structures and corresponding operators that satisfy associative and commutative properties. Records arriving after the low watermark are appended to Timon directly, allowing aggregations to be performed lazily. To improve query efficiency, Timon maintains a TS-LSM-Tree, which keeps the most recent data in memory and contains a time-partitioning tree on disk for high-volume data accumulated over long time span. Besides, Timon supports materialized aggregation views and correlation analysis across multiple streams. Timon has been successfully deployed at Alibaba Cloud and is a critical building block for Alibaba cloud's continuous monitoring and anomaly analysis infrastructure.

In emerging applications such as blockchains and collaborative data analytics, there are strong demands for data immutability, multi-version accesses, and tamper-evident controls. To provide efficient support for lookup and merge operations, three new index structures for immutable data, namely Merkle Patricia Trie (MPT), Merkle Bucket Tree(MBT), and Pattern-Oriented-Split Tree (POS-Tree), have been proposed. Although these structures have been adopted in real applications, there is no systematic evaluation of their pros and cons in the literature, making it difficult for practitioners to choose the right index structure for their applications. To alleviate the above problem, we present a comprehensive analysis of the existing index structures for immutable data, and evaluate both their asymptotic and empirical performance. Specifically, we show that MPT, MBT, and POS-Tree are all instances of a recently proposed framework, dubbed Structurally Invariant and Reusable Indexes (SIRI). We propose to evaluate the SIRI instances on their index performance and deduplication capability. We establish the worst-case guarantees of each index, and experimentally evaluate all indexes in a wide variety of settings. Based on our theoretical and empirical analysis, we conclude that POS-Tree is a favorable choice for indexing immutable data.

With the growing market of cloud databases, careful detection and elimination of slow queries are of great importance to service stability. Previous studies focus on optimizing the slow queries that result from internal reasons (e.g., poorly-written SQLs). In this work, we discover a different set of slow queries which might be more hazardous to database users than other slow queries. We name such queries Intermittent Slow Queries (iSQs), because they usually result from intermittent performance issues that are external (e.g., at database or machine levels). Diagnosing root causes of iSQs is a tough but very valuable task. This paper presents iSQUAD, Intermittent Slow QUery Anomaly Diagnoser, a framework that can diagnose the root causes of iSQs with a loose requirement for human intervention. Due to the complexity of this issue, a machine learning approach comes to light naturally to draw the interconnection between iSQs and root causes, but it faces challenges in terms of versatility, labeling overhead and interpretability. To tackle these challenges, we design four components, i.e., Anomaly Extraction, Dependency Cleansing, Type-Oriented Pattern Integration Clustering (TOPIC) and Bayesian Case Model. iSQUAD consists of an offline clustering & explanation stage and an online root cause diagnosis & update stage. DBAs need to label each iSQ cluster only once at the offline stage unless a new type of iSQs emerges at the online stage. Our evaluations on real-world datasets from Alibaba OLTP Database show that iSQUAD achieves an iSQ root cause diagnosis average F1-score of 80.4%, and outperforms existing diagnostic tools in terms of accuracy and efficiency.

With the explosive growth of unstructured data (such as images, videos, and audios), unstructured data analytics is widespread in a rich vein of real-world applications. Many database systems start to incorporate unstructured data analysis to meet such demands. However, queries over unstructured and structured data are often treated as disjoint tasks in most systems, where hybrid queries ( i.e. , involving both data types) are not yet fully supported. In this paper, we present a hybrid analytic engine developed at Alibaba, named AnalyticDB-V (ADBV), to fulfill such emerging demands. ADBV offers an interface that enables users to express hybrid queries using SQL semantics by converting unstructured data to high dimensional vectors. ADBV adopts the lambda framework and leverages the merits of approximate nearest neighbor search (ANNS) techniques to support hybrid data analytics. Moreover, a novel ANNS algorithm is proposed to improve the accuracy on large-scale vectors representing massive unstructured data. All ANNS algorithms are implemented as physical operators in ADBV, meanwhile, accuracy-aware cost-based optimization techniques are proposed to identify effective execution plans. Experimental results on both public and in-house datasets show the superior performance achieved by ADBV and its effectiveness. ADBV has been successfully deployed on Alibaba Cloud to provide hybrid query processing services for various real-world applications.

The emergence of Blockchain has attracted widespread attention. However, we observe that in practice, many applications on permissioned blockchains do not benefit from the decentralized architecture. When decentralized architecture is used but not required, system performance is often restricted, resulting in low throughput, high latency, and significant storage overhead. Hence, we propose LedgerDB on Alibaba Cloud, which is a centralized ledger database with tamper-evidence and non-repudiation features similar to blockchain, and provides strong auditability. LedgerDB has much higher throughput compared to blockchains. It offers stronger auditability by adopting a TSA two-way peg protocol, which prevents malicious behaviors from both users and service providers. LedgerDB supports verifiable data removals demanded by many real-world applications, which are able to remove obsolete records for storage saving and hide records for regulatory purpose, without compromising its verifiability. Experimental evaluation shows that LedgerDB's throughput is 80X higher than state-of-the-art permissioned blockchain (i.e., Hyperledger Fabric). Many blockchain customers (e.g., IP protection and supply chain) on Alibaba Cloud have switched to LedgerDB for its high throughput, low latency, strong auditability, and ease of use.

GPS coordinates are fine-grained location indicators that are difficult to be effectively utilized by classifiers in geo-aware applications. Previous GPS embedding methods are mostly tailored for specific problems that are taken place within areas of interest. When it comes to the scale of the entire planet, existing approaches always suffer from extensive computational cost and significant information loss. To solve these issues, we present a novel two-level grid based framework to learn semantic embeddings for geo-coordinates worldwide. The Earth's surface is first discretized by the Universal Transverse Mercator (UTM) coordinate system. Each UTM zone is next processed as a local area of interest that is further divided into fine-grained cells to perform the initial GPS encoding. We train a neural network in each UTM zone to learn the semantic embeddings from the initial GPS encoding. The training labels can be automatically derived from large-scale geotagged documents such as tweets, check-ins, and images that are available from social sharing platforms. We evaluate the effectiveness of our proposed GPS embeddings in geotagged image classification. Improved classification results have been obtained based on a simple early feature fusion technique.

Alibaba runs the largest e-commerce platform in the world serving more than 600 million customers, with a GMV (gross merchandise value) exceeding USD 768 billion in FY2018. Online e-commerce transactions have three notable characteristics: (1) drastic increase of transactions per second with the kickoff of major sales and promotion events, (2) a large number of hot records that can easily overwhelm system buffers, and (3) quick shift of the "temperature'' (hot v.s. warm v.s. cold) of different records due to the availability of promotions on different categories over different short time periods. For example, Alibaba's OLTP database clusters experienced a 122 times increase of transactions on the start of the Singles' Day Global Shopping Festival in 2018, processing up to 491,000 sales transactions per second which translate to more than 70 million database transactions per second. To address these challenges, we introduce X-Engine, a write-optimized storage engine of POLARDB built at Alibaba, which utilizes a tiered storage architecture with the LSM-tree (log-structured merge tree) to leverage hardware acceleration such as FPGA-accelerated compactions, and a suite of optimizations including asynchronous writes in transactions, multi-staged pipelines and incremental cache replacement during compactions. Evaluation results show that X-Engine has outperformed other storage engines under such transactional workloads.

With data explosion in scale and variety, OLAP databases play an increasingly important role in serving real-time analysis with low latency (e.g., hundreds of milliseconds), especially when incoming queries are complex and ad hoc in nature. Moreover, these systems are expected to provide high query concurrency and write throughput, and support queries over structured and complex data types (e.g., JSON, vector and texts). In this paper, we introduce AnalyticDB, a real-time OLAP database system developed at Alibaba. AnalyticDB maintains all-column indexes in an asynchronous manner with acceptable overhead, which provides low latency for complex ad-hoc queries. Its storage engine extends hybrid row-column layout for fast retrieval of both structured data and data of complex types. To handle large-scale data with high query concurrency and write throughput, AnalyticDB decouples read and write access paths. To further reduce query latency, novel storage-aware SQL optimizer and execution engine are developed to fully utilize the advantages of the underlying storage and indexes. AnalyticDB has been successfully deployed on Alibaba Cloud to serve numerous customers (both large and small). It is capable of holding 100 trillion rows of records, i.e., 10PB+ in size. At the same time, it is able to serve 10m+ writes and 100k+ queries per second, while completing complex queries within hundreds of milliseconds.

Recent advancements in high-performance networking interconnect significantly narrow the performance gap between intra-node and inter-node communications, and open up opportunities for distributed memory platforms to enforce cache coherency among distributed nodes. To this end, we propose GAM, an efficient distributed in-memory platform that provides a directory-based cache coherence protocol over remote direct memory access (RDMA). GAM manages the free memory distributed among multiple nodes to provide a unified memory model, and supports a set of user-friendly APIs for memory operations. To remove writes from critical execution paths, GAM allows a write to be reordered with the following reads and writes, and hence enforces partial store order (PSO) memory consistency. A light-weight logging scheme is designed to provide fault tolerance in GAM. We further build a transaction engine and a distributed hash table (DHT) atop GAM to show the ease-of-use and applicability of the provided APIs. Finally, we conduct an extensive micro benchmark to evaluate the read/write/lock performance of GAM under various workloads, and a macro benchmark against the transaction engine and DHT. The results show the superior performance of GAM over existing distributed memory platforms.

Existing data storage systems offer a wide range of functionalities to accommodate an equally diverse range of applications. However, new classes of applications have emerged, e.g., blockchain and collaborative analytics, featuring data versioning, fork semantics, tamper-evidence or any combination thereof. They present new opportunities for storage systems to efficiently support such applications by embedding the above requirements into the storage. In this paper, we present ForkBase , a storage engine designed for blockchain and forkable applications. By integrating core application properties into the storage, ForkBase not only delivers high performance but also reduces development effort. The storage manages multiversion data and supports two variants of fork semantics which enable different fork worklflows. ForkBase is fast and space efficient, due to a novel index class that supports efficient queries as well as effective detection of duplicate content across data objects, branches and versions. We demonstrate ForkBase 's performance using three applications: a blockchain platform, a wiki engine and a collaborative analytics application. We conduct extensive experimental evaluation against respective state-of-the-art solutions. The results show that ForkBase achieves superior performance while significantly lowering the development effort.

Big data analytics is gaining massive momentum in the last few years. Applying machine learning models to big data has become an implicit requirement or an expectation for most analysis tasks, especially on high-stakes applications. Typical applications include sentiment analysis against reviews for analyzing on-line products, image classification in food logging applications for monitoring user's daily intake, and stock movement prediction. Extending traditional database systems to support the above analysis is intriguing but challenging. First, it is almost impossible to implement all machine learning models in the database engines. Second, expert knowledge is required to optimize the training and inference procedures in terms of efficiency and effectiveness, which imposes heavy burden on the system users. In this paper, we develop and present a system, called Rafiki, to provide the training and inference service of machine learning models. Rafiki provides distributed hyper-parameter tuning for the training service, and online ensemble modeling for the inference service which trades off between latency and accuracy. Experimental results confirm the efficiency, effectiveness, scalability and usability of Rafiki.

Sensing devices generate tremendous amounts of data each day, which include large quantities of multi-dimensional measurements. These data are expected to be immediately available for real-time analytics as they are streamed into storage. Such scenarios pose challenges to state-of-the-art indexing methods, as they must not only support efficient queries but also frequent updates. We propose here a novel indexing method that ingests multi-dimensional observational data in real time. This method primarily guarantees extremely high throughput for data ingestion, while it can be continuously refined in the background to improve query efficiency. Instead of representing collections of points using Minimal Bounding Boxes as in conventional indexes, we model sets of successive points as line segments in hyperspaces, by exploiting the intrinsic value continuity in observational data. This representation reduces the number of index entries and drastically reduces "over-coverage" by entries. Experimental results show that our approach handles real-world workloads gracefully, providing both low-overhead indexing and excellent query efficiency.

Locality Sensitive Hashing (LSH) and its variants, are generally believed to be the most effective radius search methods in high-dimensional spaces. However, many applications involve finding the k nearest neighbors (k-NN), where the k-NN distances of different query points may differ greatly and the performance of LSH suffers. We propose a novel indexing scheme called Selective Hashing, where a disjoint set of indices are built with different granularities and each point is only stored in the most effective index. Theoretically, we show that k-NN search using selective hashing can achieve the same recall as a fixed radius LSH search, using a radius equal to the distance of the c1kth nearest neighbor, with at most c2 times overhead, where c1 and c2 are small constants. Selective hashing is also easy to build and update, and outperforms all the state-of-the-art algorithms such as DSH and IsoHash.

Huge amounts of data are being generated by sensing devices every day, recording the status of objects and the environment. Such observational data is widely used in scientific research. As the capabilities of sensors keep improving, the data produced are drastically expanding in precision and quantity, making it a write-intensive domain. Log-structured storage is capable of providing high write throughput, and hence is a natural choice for managing large-scale observational data. In this paper, we propose an approach to indexing and querying observational data in log-structured storage. Based on key traits of observational data, we design a novel index approach called the CR-index (Continuous Range Index), which provides fast query performance without compromising write throughput. It is a lightweight structure that is fast to construct and often small enough to reside in RAM. Our experimental results show that the CR-index is superior in handling observational data compared to other indexing techniques. While our focus is scientific data, we believe our index will be effective for other applications with similar properties, such as process monitoring in manufacturing.

In crowdsourcing database, human operators are embedded into the database engine and collaborate with other conventional database operators to process the queries. Each human operator publishes small HITs (Human Intelligent Task) to the crowdsourcing platform, which consists of a set of database records and corresponding questions for human workers. The human workers complete the HITs and return the results to the crowdsourcing database for further processing. In practice, published records in HITs may contain sensitive attributes, probably causing privacy leakage so that malicious workers could link them with other public databases to reveal individual private information. Conventional privacy protection techniques, such asK-Anonymity, can be applied to partially solve the problem. However, after generalizing the data, the result of standard K-Anonymity algorithms may render uncontrollable information loss and affects the accuracy of crowdsourcing. In this paper, we first study the tradeoff between the privacy and accuracy for the human operator within data anonymization process. A probability model is proposed to estimate the lower bound and upper bound of the accuracy for general K-Anonymity approaches. We show that searching the optimal anonymity approach is NP-Hard and only heuristic approach is available. The second contribution of the paper is a general feedback-based K-Anonymity scheme. In our scheme, synthetic samples are published to the human workers, the results of which are used to guide the selection on anonymity strategies. We apply the scheme on Mondrian algorithm by adaptively cutting the dimensions based on our feedback results on the synthetic samples. We evaluate the performance of the feedback-based approach on U.S. census dataset, and show that given a predefined$K$, our proposal outperforms standard K-Anonymity approaches on retaining the effectiveness of crowdsourcing.

Numerous applications such as financial transactions (e.g., stock trading) are write-heavy in nature. The shift from reads to writes in web applications has also been accelerating in recent years. Write-ahead-logging is a common approach for providing recovery capability while improving performance in most storage systems. However, the separation of log and application data incurs write overheads observed in write-heavy environments and hence adversely affects the write throughput and recovery time in the system. In this paper, we introduce LogBase -- a scalable log-structured database system that adopts log-only storage for removing the write bottleneck and supporting fast system recovery. It is designed to be dynamically deployed on commodity clusters to take advantage of elastic scaling property of cloud environments. LogBase provides in-memory multiversion indexes for supporting efficient access to data maintained in the log. LogBase also supports transactions that bundle read and write operations spanning across multiple records. We implemented the proposed system and compared it with HBase and a disk-based log-structured record-oriented system modeled after RAMCloud. The experimental results show that LogBase is able to provide sustained write throughput, efficient data access out of the cache, and effective system recovery.