首页    期刊浏览 2025年05月24日 星期六
登录注册

文章基本信息

  • 标题:The Hekaton Memory-Optimized OLTP Engine
  • 本地全文:下载
  • 作者:Per-Ake Larson ; Mike Zwilling ; Kevin Farlee
  • 期刊名称:Bulletin of the Technical Committee on Data Engineering
  • 出版年度:2013
  • 卷号:36
  • 期号:2
  • 出版社:IEEE Computer Society
  • 摘要:Hekaton is a new OLTP engine optimized for memory resident data and fully integrated into SQL Server;a database can contain both regular disk-based tables and in-memory tables. In-memory (a.k.a.Hekaton)tables are fully durable and accessed using standard T-SQL. A query can reference both Hekaton tablesand regular tables and a transaction can update data in both types of tables. T-SQL stored proceduresthat reference only Hekaton tables are compiled into machine code for further performance improve-ments. To allow for high concurrency the engine uses latch-free data structures and optimistic, multi-version concurrency control. This paper gives an overview of the design of the Hekaton engine andreports some initial results
国家哲学社会科学文献中心版权所有