Divergence control algorithms for epsilon serializability

The paper presents divergence control methods for epsilon serializability (ESR) in centralized databases. ESR alleviates the strictness of serializability (SR) in transaction processing by allowing for limited inconsistency. The bounded inconsistency is automatically maintained by divergence control (DC) methods in a way similar to SR is maintained by concurrency control (CC) mechanisms. However, DC for ESR allows more concurrency than CC for SR. The authors first demonstrate the feasibility of ESR by showing the design of three representative DC methods: two-phase locking, timestamp ordering and optimistic approaches. DC methods are designed by systematically enhancing CC algorithms in two stages: extension and relaxation. In the extension stage, a CC algorithm is analyzed to locate the places where it identifies non-SR conflicts of database operations. In the relaxation stage, the non-SR conflicts are relaxed to allow for controlled inconsistency. They then demonstrate the applicability Of ESR by presenting the design of DC methods using other most known inconsistency specifications, such as absolute value, age and total number of nonserializably read data items. In addition, they present a performance study using an optimistic divergence control algorithm as an example to show that a substantial improvement in concurrency can be achieved in ESR by allowing for a small amount of inconsistency     

基于全局目录的分布式数据库数据一致性算法

针对分布式数据库中数据的分布性、事务执行的分布性和一些不可预测的软件错误和硬件故障等原因导致的数据不一致性问题,指出解决这些问题尚存在的困难,分析了消息队列法、事务控制法、复制控制法等分布式数据库中维护数据一致性的三种主要方法的缺点。在全局目录和分布式两阶段提交协议的基础上,提出了基于全局目录的分布式数据库数据一致性控制算法。该算法增强了分布式数据库中数据的一致性,节省了网络带宽,也提高了事务处理能力。     

A non-two-phase locking protocol for global concurrency control indistributed heterogeneous database systems

A concurrency control method is proposed for global transactions in a distributed heterogeneous database system. This method is applicable when the database sites are interconnected in a rooted tree fashion. It guarantees deadlock freedom in addition to serializability. A general architecture of a heterogeneous system is given. The global transaction manager (GTM) decomposes the global transactions initiated at a site and the subtransactions received from other sites into smaller subtransactions, some of which are sent to the GTMs of the other sites, and those remaining, called g-local transactions, are to be executed by the local transaction manager (LTM) at that site. A concurrency control mechanism ensures serializability among: the local transactions (including the g-local transactions of the global ones) at each site, the global transactions and the global and local transactions together     

一种改进的分布式并行事务处理策略研究

目前,XML技术在基于因特网的复杂分布式系统事务处理中的应用已成为国内外研究的热点,尤其是如何提高分布式系统的并行事务处理能力,同时使系统具有高度容错能力,是一个具有挑战性的课题。本文提出了一种对XML文档进行DOM树划分、将复杂长事务划分成可并行执行的子事务的并行事务处理策略,从而在不影响其容错性能的情况下进一步提高分布式系统的并行运算性能和处理复杂长事务的能力,同时做到负载均衡。     

P2P多数据库系统中的事务并发控制研究

P2P多数据库系统是一种分布式的数据库系统,它是P2P计算系统和传统数据库系统的结合体.P2P计算系统的动态性使得P2P多数据库系统的事务管理缺少全局控制机制.在事务传播过程不存在循环的前提下,文章提出了一种保证P2P多数据库系统中事务全局串行化的并发控制协议,它通过控制一系列全局事务传播过程中每个熟识关系的两级串行化来实现.     

嵌套事务可序列化调度中的隐式约束

嵌套事务模型在现代数据库及分布式对象系统并发控制的理论研究和应用中具有重要地位。而父子事务之间的同步能力则是其中必不可少的组成部分之一。通常做法中，父事务对（指定的）单个子事务的同步可能触发可序列化调度的隐式约束，从而导致调度不可操作。通过分析隐式约束的产生原因，并将具有一定拓扑结构的嵌套事务定义为良构的，可以避免上述不可操作性。最后给出算法以控制良构的嵌套事件中的隐式约束及保证调度的可序列化。     

Application Specific Transaction Management in Multidatabase Systems

We present a transaction model for multidatabase systems with autonomous component systems, coined heterogeneous 3-level transactions. It has become evident that in such a system the requirements of guaranteeing full ACID properties and full local autonomy can not be reconciled. In the heterogeneous 3-level transaction model, semantics of actions and specific properties of the architecture of multidatabase systems and of applications are utilized to define application specific compromises between these competing goals. We consider different definitions of conflicts between actions together with application specific sets of allowed (autonomous) local transactions and global subtransactions. A formal model for serializability is given. It is proven that heterogeneous 3-level transactions guarantee all consistency constraints that are ensured in serial executions. In contrast to most other models, we do not require data to be partitioned into global and local data. In particular, heterogeneous 3-level transactions even allow the same data to be updated by local and global transactions in parallel, if these updates are found to be semantically non-conflicting. Recovery is handled by inverse actions. We present a formal framework for this approach which is fully integrated into serializability theory by considering inverse actions as ordinary actions. This has an important impact on the relationship of concurrency control and recovery in our model: By changing the definition of conflicts between actions in order to tailor the model according to application needs, recovery is implicitly affected and no further explicit adaptation of recovery algorithms is necessary. The heterogeneous 3-level transaction model assumes component database systems to support ACID transaction properties. Further properties of local transactions or interfaces of the component database systems are not required. We describe a prototype implementation of heterogeneous 3-level transactions in the object-oriented database system VODAK.     

多数据库系统中的一致性维护

在多数据库环境中存在着全局事务和局部事务,它们必须相互协作,从而为应用程序提供一致性的数据。为了维护多数据库系统（MDBS）的一致性,提出一种事务管理机制。该机制基于扩展事务的原理,对全局子事务和局部事务进行扩展,并为各个局部数据库引进一些控制表。局部数据库管理系统（LDBMS）和局部数据库和控制表之上执行扩展务,这些扩展事务负一局可串行性及事务的恢复。由于它不依赖于LDBMS的各种特征,因此该方法易于实现,是实用的。     

面向用户的移动实时事务并发控制策略

-可串行化、 可串行化、准一致性可串行化等现有面向事务的放松可串行化正确性准则虽能帮助更多无线通信事务满足其截止期要求，但会导致数据的受限不一致。该文针对移动实时环境和应用，形式化定义并分析了 可串行化和 可串行化2种新的面向用户的并发控制策略，它们都比冲突可串行化宽松，但都能始终保证移动用户读取数据的一致性。     

网格数据库事务管理策略

网格技术的本质就是提高资源的共享能力和实现计算资源的协同处理能力.网格数据库就是使传统数据库能够充分利用网格平台的这种优势,实现传统数据库的存储、管理、处理、分析等能力的共享和协同.网格数据库中的事务也存在全局事务和局部事务之分,对全局事务要保证得到正确的执行结果,其串行化是关键.给出了网格数据库全局事务的形式化定义,以及全局事务实现串行化的条件,并进行了相关证明.     

安全数据库系统中的事务

在多级安全数据库系统中经典的BLP模型的“向上写”违反了数据库的完整性,并产生隐通道和带来多实例问题,事务间的提交和回退依赖也会产生隐通道,在对事务安全性分析的基础上提出了安全事务模型和安全事务正确性标准一安全冲突可串行化(SCSR),最后给出了一个避免隐通道的安全并发控制算法．     

支持分布式合作实时事务处理的协同检验点方法

在实时事务执行时，事务故障或数据竞争会导致事务重启，为减少事务重启损失的工作量，可以采用检验点技术保证事务的时间正确性．在一类分布式实时数据库应用中，不同结点的事务通过消息交换形成合作关系，为保证合作事务间的全局一致性，当某一事务记检验点时，相关事务也要记检验点．传统协同检验点方法没有考虑应用的定时约束，不能很好地支持分布式合作实时事务处理．该文提出了一种基于图论的协同检验点方法，利用在每个计算结点上为每个合作事务集维护的局部有向图，使用一个基于图论的计算过程标识出应记检验点的事务，该方法既具有最小协同检验点特性，又使全局检验点的时延最小．实验表明该算法减少了全局检验点时延，有利于实时事务截止期的满足．     

多副本分布式事务处理关键技术及典型数据库系统综述

数据复制是分布式数据库提高可用性的重要手段,通过在不同区域放置数据库的部分副本,还可以提高本地读写操作的响应速度,增加副本数量也会提升读负载的线性扩展能力.考虑到这些优良特性,近年来国内外都出现了众多多副本分布式数据库系统,包括Google Spanner、CockroachDB、TiDB、OceanBase等一系列主流的工业界系统,也出现了包括Calvin、Aria、Berkeley Anna等一系列优秀的学术界系统.然而,多副本数据库带来诸多收益的同时,也带来了一致性维护、跨节点事务、事务隔离等一系列挑战.总结分析现有的复制架构、一致性维护策略、跨节点事务并发控制等技术,对比几个代表性多副本数据库系统之间在分布式事务处理方面上的差异与共同点,并在阿里云环境下搭建跨区域的分布式集群环境,对几个代表性系统的分布式事务处理能力进行了实验测试分析.     

Large scale interoperability and distributed transaction processing

This article integrates an interoperability architecture, the OSCA^TM architecture, and a distributed transaction processing protocol, the X/Open^® Distributed Transaction Processing model, into a unified model of large scale interoperability and distributed transaction processing. Applications supporting different business operations are often deployed in heterogeneous environments in which applications are stand alone islands and operations are fragmented. But in order to have integrated operations, a loosely coupled system of autonomous applications is required often bound together via a distributed transaction processing protocol. This article describes a model for this configuration. It will propose that the span of control of a transaction manager defines the transaction environment for a single application. Any two applications need not conform to the same supplier's transaction environment nor reside in the same environment. Interoperability must be provided among applications, since any one application cannot assume that any other application is under the control of the same transaction manager. Requirements are imposed upon the interactions of applications to support interoperability. The interface between transaction managers must be compatible with these requirements. Other distributed architecture standards must define the requirements for release independence, resource independence, accessibility transparency, location transparency, contract interfaces, and secure environment.     

Coordinator log transaction execution protocol

The coordinator log transaction execution protocol proposed in this paper centralizes logging on a per transaction basis and exploits piggybacking to provide the semantics of a distributed atomic commit at a minimal cost. The protocol eliminates two rounds of messages (one phase) from the presumed commit protocol and dramatically reduces the number of log forces needed for distributed atomic commit. We compare the coordinator log transaction execution protocol to existing protocols, explain when it is desirable, and discuss how it affects the write ahead log protocol and the database crash recovery algorithm. Recommended by: Tamer Ozsu     

A Storage Optimization Scheme for Blockchain Transaction Databases

As the typical peer-to-peer distributed networks, blockchain systems require each node to copy a complete transaction database, so as to ensure new transactions can by verified independently. In a blockchain system (e.g., bitcoin system), the node does not rely on any central organization, and every node keeps an entire copy of the transaction database. However, this feature determines that the size of blockchain transaction database is growing rapidly. Therefore, with the continuous system operations, the node memory also needs to be expanded to support the system running. Especially in the big data era, the increasing network traffic will lead to faster transaction growth rate. This paper analyzes blockchain transaction databases and proposes a storage optimization scheme. The proposed scheme divides blockchain transaction database into cold zone and hot zone using expiration recognition method based on Least Recently Used (LRU) algorithm. It can achieve storage optimization by moving unspent transaction outputs outside the in-memory transaction databases. We present the theoretical analysis on the optimization method to validate the effectiveness. Extensive experiments show our proposed method outperforms the current mechanism for the blockchain transaction databases.     

MDBS中一种改进的并发事务调度算法

MDBS中并发事务的调度策略必须满足可串行化准则,论文主要分析以事务提交图为中心的调度算法TM2,虽然保证了全局事务提交顺序的可串行化,但在提交时才进行冲突检测方式存在缺点,提出改进后的事务调度算法TM3不仅保证了全局事务的可串行化和防止了全局死锁的发生,还提高了全局事务执行的并发度。最后通过实验在数据库加速引擎中进行模拟,对比了两种调度算法的性能。     

Revisiting Transaction Management in Multidatabase Systems

A lot of research efforts have focused on global serializability, global atomicity, and global deadlocks in multidatabase systems. Surprisingly, however, very few transaction processing model exists that ensures global serializability, global atomicity, and freedom from global deadlocks in a uniform manner. In this paper, we examine previous transaction processing models and propose a new transaction processing model that generates globally serializable and deadlock-free schedules in failure-prone multidatabase systems. A new transaction processing model adopts rigid conflict serializability as a correctness criterion on global serializability, and follows an emulated 2PC, criteria for global commitment, and an abort-based multidatabase recovery scheme for global serializability in failure-prone multidatabase systems. In addition, a deadlock-free policy is suggested where rigid conflict serializability is enforced when each subtransaction, including redo transactions, begins its execution. To practically support a new transaction processing model, Rigid Ticket Ordering (RTO) methods are designed. The proposed transaction processing model has the following improvements: (a) it resolves abnormal direct conflicts identified in this paper, (b) it imposes no restrictions on the execution of local transactions, and (c) it relaxes the restrictions on the execution of global transactions.     

一种基于补偿代价的长事务调度算法

服务组合应用中的事务具有较长的生命周期,一个事务被划分成多个分布的子事务.补偿机制是保证长事务原子性的一种有效方法,允许在语义上逆转一个已提交子事务的结果.然而,补偿的代价可能是巨大的.针对该问题,在分析并定义事务补偿代价的基础上,提出一种子事务延迟提交算法――STCD(subtransactions committingdelay)算法,与传统子事务执行后立即提交的方法相比,STCD 算法允许某个全局事务的子事务在提交前根据自身的补偿代价和全局事务的运行状态动态确定提交时间,使可能的补偿操作变更为回滚操作.算法的正确性得以证明.模拟实验结果表明,在事务失败时,STCD 算法可以有效地减少补偿活动的数目,降低补偿代价.