BRRL: a recovery library for main-memory applications in the cloud

In this demonstration we present BRRL, a library for making distributed main-memory applications fault tolerant. BRRL is optimized for cloud applications with frequent points of consistency that use data-parallelism to avoid complex concurrency control mechanisms. BRRL differs from existing recovery libraries by providing a simple table abstraction and using schema information to optimize checkpointing. We will demonstrate the utility of BRRL using a distributed transaction processing system and a platform for scientific behavioral simulations. Categories and Subject Descriptors H.2.2 [Information Systems]: Database Management—Recovery and restart General Terms Performance, Reliability

• Type: Journal
• Year: 2011
• Where: SIGMOD
• Authors: Tuan Cao, Benjamin Sowell, Marcos Antonio Vaz Salles, Alan J. Demers, Johannes Gehrke
• Keywords: Concurrency Control Mechanisms, Data Parallelism, Database, SIGMOD 2011, Transaction Processing System