On the use of Clocks to Enforce Consistency in the Cloud
On the use of Clocks to Enforce Consistency in the Cloud
复制标题
关于使用时钟来强制云中的一致性
DOI：
--
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
L. Rodrigues
中科院分区：
文献类型：
--
作者：
Manuel Bravo;Nuno Diegues;Jingna Zeng;P. Romano;L. Rodrigues
众所周知，对事件加时间戳、跟踪事件发生的顺序或确保以对应用程序有意义的方式处理事件的能力在分布式系统中至关重要。Leslie Lamport[30]的开创性工作为理解与使用物理和逻辑同步时钟来建立事件顺序相关的权衡奠定了基础。兰波特最初的工作考虑了标量时钟，后来扩展到考虑更丰富形式的逻辑时钟，如向量时钟和矩阵时钟。本文的目的是在为云开发分布式数据存储系统的具体环境中重新审视这些概念。我们将研究如何在实践中应用不同的时钟机制来构建不同的云数据存储，并进行不同的一致性/性能权衡。我们的目标是更好地淡化使用不同技术捕获时间流逝和时间戳事件的具体后果，以及这些选择不仅影响云数据存储的性能，还影响这些系统能够提供的一致性保证。在此过程中，我们进行了一些观察，这些观察可能会为增强下一代云提供机会
It is well known that the ability to timestamp events, to keep track of the order in which they occur, or to make sure they are processed in a way that is meaningful to the application, is of paramount importance in a distributed system. The seminal work by Leslie Lamport[30] has laid the foundations to understand the trade-offs associated with the use of physically and logically synchronized clocks for establishing the order of events. Lamport’s original work considered scalar clocks and has later been extended to consider richer forms of logical clocks such as vector clocks and matrix clocks. The purpose of this paper is to revisit these concepts in the concrete setting of developing distributed data store systems for the cloud. We look at how different clock mechanisms have been applied in practice to build different cloud data stores, with different consistency/performance trade-offs. Our goal is to gain a better understating of what are the concrete consequences of using different techniques to capture the passage of time, and timestamp events, and how these choices impact not only the performance of cloud data stores but also the consistency guarantees that these systems are able to provide. In this process we make a number of observations that may offer opportunities to enhance the next generations of cloud