网站大量收购独家精品文档,联系QQ:2885784924

Exploiting atomic broadcast in replicated databases.pdf

Exploiting atomic broadcast in replicated databases.pdf

  1. 1、本文档共24页,可阅读全部内容。
  2. 2、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
  3. 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载
  4. 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
查看更多
Exploiting atomic broadcast in replicated databases

Exploiting Atomic Broadcast in Replicated Databases Fernando Pedone Rachid Guerraoui Andre Schiper Departement dInformatique Ecole Polytechnique Federale de Lausanne 1015 Lausanne, Switzerland Abstract Database replication protocols have historically been built on top of distributed database systems, and have consequently been designed and implemented using distributed transac- tional mechanisms, such as atomic commitment. We argue in this paper that this approach is not always adequate to eciently support database replication and that more suitable al- ternatives, such as atomic broadcast primitives, should be employed instead. More precisely, we show in this paper that fully replicated database systems, based on the deferred update replication model, have better throughput and response time if implemented with an atomic broadcast termination protocol than if implemented with atomic commitment. 1 Introduction Replication is considered a cheap software based way to increase data availability when compared to hardware based specialised techniques [16]. However, designing a replication scheme that provides reasonable performance and maintains data consistency is still an active area of research both in the database and in the distributed systems communities. In the database context, replication techniques based on the deferred update model have received increasingly attention in the past years [13]. According to the deferred update model, transactions are processed locally at one server (i.e., one replica manager) and, at commit time, are forwarded for certi cation to the other servers (i.e., the other replica managers). Deferred update replication techniques o er many advantages over immediate update techniques, which synchronise every transaction operation across all servers. Among these advantages, one may 1 cite: (a) better performance, by gathering and propagating multiple updates together, and localising the execution at a single, possibly nearby, server (t

文档评论(0)

l215322 + 关注
实名认证
内容提供者

该用户很懒,什么也没介绍

1亿VIP精品文档

相关文档