软件事务内存的动态竞争管理策略

软件事务内存是为了简化并行程序设计而出现的一种新的程序设计技术.为了降低软件事务内存系统中事务冲突的发生频率以提升系统整体性能,提出了一种新的基于动态控制和队列调度的竞争管理策略.定义了竞争强度的概念和系统总体框架,并在此基础上给出了利用运行时反馈信息动态调节竞争强度的方法.同时给出了事务序列化的设计方法与实现中应注意的问题,通过将冲突概率大的事务序列化以达到避免相同冲突再次发生的目的.结合常用的基准数据结构,对模型和算法进行了实验,最后结果表明了算法的正确性和有效性.     

面向多核的基于RSTM系统的冲突管理策略

程序并行化是充分发挥多核处理器性能的有效手段。现有编程模型受锁、管道等同步方式的约束,并行度很难提高。针对上述问题,提出一种面向多核的基于Rochester软件事务存储(RSTM)系统的冲突管理策略,在现有编程语言中提供接口,通过事务方式提高程序并行度,以优先级方式解决2个事务发生冲突时的裁决问题,减少不必要的一致性验证,减小系统开销。     

基于冲突相关性检测的竞争管理模型

在无干扰特性下的软件事务存储系统中,竞争管理策略直接应用于冲突事务的消解,对具有整个系统的性能有直接的影响。针对现有竞争管理决策方式相对单一而产生的性能不稳定问题,提出了基于冲突相关性检测的竞争管理模型。该方法可以从过去的仲裁记录中分析冲突事务中存在的关联性,并把检测到的关联性作为当前冲突的决策依据,从而得到较优的冲突处理结果。在仿真平台采用该方法对部分基准数据结构的测试数据表明,该方法检测到并且帮助提交的冲突关联事务最多可占系统吞吐量的30%,其事务吞吐总量比其他参照对象的平均值高出约11%,具有较好的灵活度和适用性。     

STM多事务竞争冲突下竞争管理策略的研究

事务存储系统是一种高层次抽象并行编程模型,目的为方便开发并行程序。事务存储系统中的竞争管理模块用于解决事务之间的冲突。传统的事务竞争管理策略只负责仲裁两个冲突事务之间的冲突．提出将多个事务及事务冲突关联转换成一张无向图,基于全局事务冲突情景,利用图顶点着色技术求解无向图中最大独立集。最大独立集中事务相互不冲突,CM仲裁处理并发执行,实现系统并发最大化。     

混合实时事务的接纳控制机制ACMHRTT

提出了一种含有实时和非实时两部分的混合实时事务接纳控制机制ACMHRTT(Admission Control Mechamsm for Hybrid Real-Time Transactions)。ACMHRTT将混合事务分为真实时和非实时两部分，综合考虑混合事务的执行需求和价值，目的是为保留系统资源，有效控制负载，减少了被系统接纳执行后而又不能满足截止期的事务，提高实时数据库系统事务处理的成功率和可靠性，使系统收益最大化。着重分析了ACMHRTT的模型，对ACMHRTT与传统的ACM作了分析比较，说明了比传统的ACM协议更优，并提出了须进一步研究的问题。     

移动实时数据库QoS管理和更新事务调度算法

分布式环境下的移动实时数据库服务应用逐渐广泛,但系统负载的不可预测甚至可能的超载使得应用受到限制.系统中事务在低带宽移动环境下竞争有限的系统资源导致重启或夭折,从而给系统带来损失甚至灾难.通过结合时间有效性和值域的有效性提出基于的一种新的衡量系统性能的参数标准,如错过截止期事务的比率、数据新鲜度、CPU利用率去保证QoS,同时提出一种更新事务调度新算法和基于反馈控制的架构去实现.通过仿真实验评估,算法可以从稳定性能和暂态性能保证系统的性能指标不会超过由数据库管理员事先提出的QoS规范.     

taTHP: 一种THP的改进事务模型

随着电子商务的迅速崛起,Web服务逐渐成为Web领域一个崭新的分布式计算模型.在自治的、松耦合的Web服务事务环境中,由于事务参与者不能提供长时排它的资源锁定模式,因而无法继续采用传统的ACID事务结构.换而言之,Web服务事务处理必须具备针对松散耦合事务环境及自治资源提供策略的协调能力.本文在THP(TentativeHoldProtocol)事务模型的基础上,进一步发展了资源的“准”占用思想,提出了一种具备“事务意识”的新型资源协调算法,从而使系统性能有了较大提升.     

taTHP：一种THP的改进事务模型

随着电子商务的迅速崛起,Web服务逐渐成为Web领域一个崭新的分布式计算模型.在自治的、松耦合的Web服务事务环境中,由于事务参与者不能提供长时排它的资源锁定模式,因而无法继续采用传统的ACID事务结构.换而言之,Web服务事务处理必须具备针对松散耦合事务环境及自治资源提供策略的协调能力.本文在THP(TentativeHoldProtocol)事务模型的基础上,进一步发展了资源的“准”占用思想,提出了一种具备“事务意识”的新型资源协调算法,从而使系统性能有了较大提升.     

基于MVCC的嵌套事务研究与实现

探讨了用保存点模拟嵌套事务的思想,给出了基于多版本并发控制技术的保存点实现方法,并在PostgreSQL系统上,通过改进其日志管理器、内存管理器和版本选择算法,成功地实现了嵌套事务。     

分布事务监控器集群框架研究

介绍了在分布事务监控器OnceTX中采用的服务器/集群管理器/应用域管理器的三层集群结构,并给出了两级负载平衡策略和自适应的域间拓扑结构管理算法.它们已在OnceTX中实现,并达到了预期的目的.     

Performance considerations for an operating system transactionmanager

Results of a previous comparison study (A. Kumar and M. Stonebraker, 1987) between a conventional transaction manager and an operating system (OS) transaction manager indicated that the OS transaction manager incurs a severe performance penalty and appears to be feasible only in special circumstances. Three approaches for enhancing the performance of an OS transaction manager are considered. The first strategy is to improve performance by reducing the cost of lock acquisition and by compressing the log. The second strategy explores the possibility of still further improvements from additional semantics to be built into an OS transaction system. The last strategy is to use a modified index structure that makes update operations less expensive to perform. The results show that the OS will have to implement essentially all of the specialized tactics for transaction management that are currently used by a database management system (DBMS) in order to match DBMS performance     

Transaction Scheduling Using Dynamic Conflict Avoidance

Software transaction memory (STM) systems have been used as an approach to improve performance, by allowing the concurrent execution of atomic blocks. However, under high-contention workloads, STM-based systems can considerably degrade performance, as transaction conflict rate increases. Contention management policies have been used as a way to select which transaction to abort when a conflict occurs. In general, contention managers are not capable of avoiding conflicts, as they can only select which transaction to abort and the moment it should restart. Since contention managers act only after a conflict is detected, it becomes harder to effectively increase transaction throughput. More proactive approaches have emerged, aiming at predicting when a transaction is likely to abort, postponing its execution. Nevertheless, most of the proposed proactive techniques are limited, as they do not replace the doomed transaction by another or, when they do, they rely on the operating system for that, having little or no control on which transaction to run. This article proposes LUTS, a lightweight user-level transaction scheduler. Unlike other techniques, LUTS provides the means for selecting another transaction to run in parallel, thus improving system throughput. We discuss LUTS design and propose a dynamic conflict-avoidance heuristic built around its scheduling capabilities. Experimental results, conducted with the STAMP and STMBench7 benchmark suites, running on TinySTM and SwissTM, show how our conflict-avoidance heuristic can effectively improve STM performance on high contention applications.     

Transactional Contention Management as a Non-Clairvoyant Scheduling Problem

The transactional approach to contention management guarantees consistency by making sure that whenever two transactions have a conflict on a resource, only one of them proceeds. A major challenge in implementing this approach lies in guaranteeing progress, since transactions are often restarted. Inspired by the paradigm of non-clairvoyant job scheduling, we analyze the performance of a contention manager by comparison with an optimal, clairvoyant contention manager that knows the list of resource accesses that will be performed by each transaction, as well as its release time and duration. The realistic, non-clairvoyant contention manager is evaluated by the competitive ratio between the last completion time (makespan) it provides and the makespan provided by an optimal contention manager.     

Hardware transactional memory architecture with adaptive version management for multi-processor FPGA platforms

Multiprocessor embedded systems integrates diverse dedicated processing units to handle high performance applications such as in multimedia and network processing. However, lock-based synchronization limits the efficiency of such heterogeneous concurrent systems. Hardware Transactional Memory (HTM) is a promising approach in creating an abstraction layer for multi-threaded programming. However, HTM performance is application-specific and determined by version and conflict management configurations. Most previous HTM implementations for embedded system in literature were built on fixed version management that result in significant performance loss when transaction behaviour changes. In this paper, we propose a HTM targeted for embedded applications which is able to adapt its version management based on application behaviour at runtime. It is prototyped and analysed on Altera Cyclone IV platform. Random requests at different contention levels and different transaction sizes are used to verify the performance of the proposed HTM. Based on our experiments, lazy version management is able to obtain up to 12.82% speed-up compared to eager version management at high contention level. Meanwhile, eager version management obtains up to 37.84% speed-up compared to lazy version management at low contention. The adaptive mechanism is able to switch configuration at runtime based on applications behaviour for maximum performance.     

Scalable and adaptive log manager in distributed systems

On-line transaction processing (OLTP) systems rely on transaction logging and quorum-based consensus protocol to guarantee durability, high availability and strong consistency. This makes the log manager a key component of distributed database management systems (DDBMSs). The leader of DDBMSs commonly adopts a centralized logging method to writing log entries into a stable storage device and uses a constant log replication strategy to periodically synchronize its state to followers. With the advent of new hardware and high parallelism of transaction processing, the traditional centralized design of logging limits scalability, and the constant trigger condition of replication can not always maintain optimal performance under dynamic workloads. In this paper, we propose a new log manager named Salmo with scalable logging and adaptive replication for distributed database systems. The scalable logging eliminates centralized contention by utilizing a highly concurrent data structure and speedy log hole tracking. The kernel of adaptive replication is an adaptive log shipping method, which dynamically adjusts the number of log entries transmitted between leader and followers based on the real-time workload. We implemented and evaluated Salmo in the open-sourced transaction processing systems Cedar and DBx1000. Experimental results show that Salmo scales well by increasing the number of working threads, improves peak throughput by 1.56\times and reduces latency by more than 4\times over log replication of Raft, and maintains efficient and stable performance under dynamic workloads all the time.     

Using Discrete Event Simulation to Analyze Contention Managers

Understanding the behavior and benefits of contention managers is important for designing transactional memory implementations. Contention manager design is closely tied to other design decisions in a transaction memory implementation, and therefore experiments to compare the behaviors of contention managers are difficult. This paper presents a discrete event simulator that allows researchers to explore the behavior of contention managers and even to perform experiments that compare lazy conflict detection without contention management to eager detection combined with a contention manager. For our benchmarks, we found that lazy conflict detection was competitive with the best contention managers. Our experiments confirm that contention management design is critical for transactional memories that use eager validation. We used the simulator to explore new tiered contention managers that combine livelock-prone contention managers with livelock-free contention managers to provide the benefits of the livelock-prone contention manager while avoiding its pathological behaviors under contention.     

On the impact of serializing contention management on STM performance

Transactional memory (TM) is an emerging concurrent programming abstraction. Numerous software-based transactional memory (STM) implementations have been developed in recent years. STM implementations must guarantee transaction atomicity and isolation. In order to ensure progress, an STM implementation must resolve transaction collisions by consulting a contention manager (CM).     

On transaction boundaries in active databases: a performanceperspective

A performance model designed for studying active DBMS performance issues is described. The authors present the results of simulation experiments in which system performance was studied as a function of transaction boundary semantics for varying levels of data contention, rule complexity, and data sharing between externally submitted tasks and rule management tasks. The results demonstrate that the way in which transaction boundaries are imposed can have a major impact on the performance of an active DBMS. It is therefore concluded that this aspect of rule semantics must be carefully considered at the time that rules are specified     

并行实时数据库系统中的一种自适应并发控制模式

根据事务的实时性及关键性分类,事务分为硬实时、固实时、软实时和非实时事务。传统的并发控制仅考虑其中一到两种事务,且将固／软实时事务统一为软实时事务考虑,带有很大的不精确性,这将降低系统吞吐率。为此,本文提出了一种自适应并发控制模式。该模式采用两级并发控制体系,一级是主并发控制器,探测不同类事务间可能存在
在的类间数据冲突;二级是从并发控制器,探测同类事务间可能存在的类内数据冲突,由四类从并发控制器实现。根据各类事务的不同特征,各控制器采用的策略不同,因而具有极大的自适应性并能最终提高系统的吞吐率,但需要增加额外的硬件开销。