CASPaxos: Replicated State Machines without logs

نویسنده

  • Denis Rystsov
چکیده

CASPaxos is a replicated state machine (RSM) protocol, an extension of Synod. Unlike Raft and Multi-Paxos, it doesn’t use leader election and log replication, thus avoiding associated complexity. Its symmetric peer-to-peer approach achieves optimal commit latency in wide-area networks and doesn’t cause transient unavailability when any bN−1 2 c of N nodes crash. The lightweight nature of CASPaxos allows new combinations of RSMs in the designs of distributed systems. For example, a representation of key-value storage as a hashtable with independent RSM per key increases fault tolerance and improves performance on multi-core systems compared with a hashtable behind a single RSM. This paper describes CASPaxos protocol, formally proves its safety properties, covers cluster membership change and evaluates the benefits of CASPaxos-based key-value storage.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

SALSA: Analyzing Logs as StAte Machines

SALSA examines system logs to derive state-machine views of the sytem’s execution, along with controlflow, data-flow models and related statistics. Exploiting SALSA’s derived views and statistics, we can effectively construct higher-level useful analyses. We demonstrate SALSA’s approach by analyzing system logs generated in a Hadoop cluster, and then illustrate SALSA’s value by developing visua...

متن کامل

Stoppable Paxos

A stoppable state machine is one whose execution can be terminated by a special stopping command. Stoppable state machines can be used to implement reconfiguration in a replicated state machine; a reconfigurable state machine is implemented by a sequence of stoppable state machines, each running in a fixed configuration. Stoppable Paxos, a variant of the ordinary Paxos algorithm, implements a r...

متن کامل

Discrete Algorithms for Mobile and Wireless Networks Lecture 12 : Thursday , 22 nd February 2007 Instructor : Soma Chaudhuri Scribe : Aaron Sterling

This class period focused on a theoretical application of collision-detectors to solve the consensus problem; and the implementation of replicated state machines, to produce fault-tolerant wireless networks. We reviewed two papers: “Consensus and Collision Detectors in Wireless Ad Hoc Networks” by G. Chockler, M. Demirbas and S. Gilbert; and “Replicated State Machines” by G. Chockler and S. Gil...

متن کامل

Fast Replicated State Machines Over Partitionable Networks

This paper presents an implementationof replicated state machines in asynchronous distributed environments prone to node failures and network partitions. This implementation has several appealing properties: It guarantees that progress will be made whenever a majority of replicas can communicate with each other; it allows minority partitions to continue providing service for idempotent requests...

متن کامل

Tolerating Latency in Replicated State Machines Through Client Speculation

Replicated state machines are an important and widelystudied methodology for tolerating a wide range of faults. Unfortunately, while replicas should be distributed geographically for maximum fault tolerance, current replicated state machine protocols tend to magnify the effects of high network latencies caused by geographic distribution. In this paper, we examine how to use speculative executio...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1802.07000  شماره 

صفحات  -

تاریخ انتشار 2018