Название: Consistent Distributed Storage
Автор: Vincent Gramoli, Nicolas Nicolaou, Alexander A. Schwarzmann
Издательство: Morgan & Claypool
Год: 2021
Страниц: 194
Язык: английский
Формат: pdf (true)
Размер: 10.1 MB

Providing a shared memory abstraction in distributed systems is a powerful tool that can simplify the design and implementation of software systems for networked platforms. This enables the system designers to work with abstract readable and writable objects without the need to deal with the complexity and dynamism of the underlying platform. The key property of shared memory implementations is the consistency guarantee that it provides under concurrent access to the shared objects. The most intuitive memory consistency model is atomicity because of its equivalence with a memory system where accesses occur serially, one at a time. Emulations of shared atomic memory in distributed systems is an active area of research and development. The problem proves to be challenging, and especially so in distributed message passing settings with unreliable components, as is often the case in networked systems. We present several approaches to implementing shared memory services with the help of replication on top of message-passing distributed platforms subject to a variety of perturbations in the computing medium.

We begin the presentation in Chapter 1 where we discuss the general landscape of distributed shared storage systems, and introduce the challenges associated with combining replication and consistency in distributed settings. In Chapter 2, we describe the model of computation, define consistency, and assumptions about communication and failure models. When a particular algorithm assumes a specialized model, we present model refinements and additional assumptions in the relevant section before presenting the algorithm.

The rest of the book is divided into two logical parts. In the first part we deal with static systems where the collection of failure-prone object replica servers is known a-priori. In the second part we deal with dynamic systems, where the set of participating servers may change over time as existing participants depart or fail, and as new participants join.