Forerunner: Constraint-based Speculative Transaction Execution for Ethereum

Q3 Computer Science
Yang Chen, Zhongxin Guo, Runhuai Li, Shuo Chen, Lidong Zhou, Yajin Zhou, Xian Zhang
{"title":"Forerunner: Constraint-based Speculative Transaction Execution for Ethereum","authors":"Yang Chen, Zhongxin Guo, Runhuai Li, Shuo Chen, Lidong Zhou, Yajin Zhou, Xian Zhang","doi":"10.1145/3477132.3483564","DOIUrl":null,"url":null,"abstract":"Ethereum is an emerging distributed computing platform that supports a decentralized replicated virtual machine at a large scale. Transactions in Ethereum are specified in smart contracts, disseminated through broadcast, accepted into the chain of blocks, and then executed on each node. In this new Dissemination-Consensus-Execution (DiCE) paradigm, the time interval between when a transaction is known (during the dissemination phase) to when the transaction is executed (after the consensus phase) offers a window of opportunity to accelerate transaction processing through speculative execution. However, the traditional speculative execution, which hinges on the ability to predict the future accurately, is inadequate because of DiCE's many-future nature. Forerunner proposes a novel constraint-based approach for speculative execution on Ethereum. In contrast to the traditional approach of predicting a single future and demanding it to be perfectly accurate, Forerunner speculates on multiple futures and can leverage speculative results based on imperfect predictions whenever certain constraints are satisfied. Under these constraints, a transaction execution is substantially accelerated through a novel multi-trace program specialization enhanced by a new form of memoization. The fully implemented Forerunner is evaluated as a node connected to the worldwide Ethereum network. When processing 13 million transactions live in real time, Forerunner achieves an effective average speedup of 8.39x on the transactions that it hears during the dissemination phase, which accounts for 95.71% of all the transactions. The end-to-end speedup over all the transactions is 6.06x. The code and data sets are publicly available.","PeriodicalId":38935,"journal":{"name":"Operating Systems Review (ACM)","volume":"22 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"18","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Operating Systems Review (ACM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3477132.3483564","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Computer Science","Score":null,"Total":0}
引用次数: 18

Abstract

Ethereum is an emerging distributed computing platform that supports a decentralized replicated virtual machine at a large scale. Transactions in Ethereum are specified in smart contracts, disseminated through broadcast, accepted into the chain of blocks, and then executed on each node. In this new Dissemination-Consensus-Execution (DiCE) paradigm, the time interval between when a transaction is known (during the dissemination phase) to when the transaction is executed (after the consensus phase) offers a window of opportunity to accelerate transaction processing through speculative execution. However, the traditional speculative execution, which hinges on the ability to predict the future accurately, is inadequate because of DiCE's many-future nature. Forerunner proposes a novel constraint-based approach for speculative execution on Ethereum. In contrast to the traditional approach of predicting a single future and demanding it to be perfectly accurate, Forerunner speculates on multiple futures and can leverage speculative results based on imperfect predictions whenever certain constraints are satisfied. Under these constraints, a transaction execution is substantially accelerated through a novel multi-trace program specialization enhanced by a new form of memoization. The fully implemented Forerunner is evaluated as a node connected to the worldwide Ethereum network. When processing 13 million transactions live in real time, Forerunner achieves an effective average speedup of 8.39x on the transactions that it hears during the dissemination phase, which accounts for 95.71% of all the transactions. The end-to-end speedup over all the transactions is 6.06x. The code and data sets are publicly available.
先驱:以太坊基于约束的投机交易执行
以太坊是一个新兴的分布式计算平台,支持大规模的分散复制虚拟机。以太坊中的交易在智能合约中指定,通过广播传播,被接受到区块链中,然后在每个节点上执行。在这种新的传播-共识-执行(DiCE)范式中,事务已知(在传播阶段)到事务执行(在共识阶段之后)之间的时间间隔为通过推测执行加速事务处理提供了机会。然而,传统的投机执行依赖于准确预测未来的能力,由于DiCE的多未来性质,这是不够的。先驱提出了一种新的基于约束的方法,用于以太坊的投机执行。与传统预测单一未来并要求其完全准确的方法不同,vanguard对多个未来进行投机,并且可以在满足某些约束条件的情况下利用基于不完美预测的投机结果。在这些约束下,事务执行通过一种新的多跟踪程序专门化(由一种新的记忆形式增强)得到了极大的加速。完全实现的先驱被评估为连接到全球以太坊网络的节点。在实时处理1300万笔交易时,在传播阶段听到的交易的有效平均加速达到8.39倍,占所有交易的95.71%。所有事务的端到端加速是6.06倍。代码和数据集是公开的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Operating Systems Review (ACM)
Operating Systems Review (ACM) Computer Science-Computer Networks and Communications
CiteScore
2.80
自引率
0.00%
发文量
10
期刊介绍: Operating Systems Review (OSR) is a publication of the ACM Special Interest Group on Operating Systems (SIGOPS), whose scope of interest includes: computer operating systems and architecture for multiprogramming, multiprocessing, and time sharing; resource management; evaluation and simulation; reliability, integrity, and security of data; communications among computing processors; and computer system modeling and analysis.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信