摘要：Wojciech Golab, University of Waterloo Muntasir R. Rahman, University of Illinois at Urbana-Champaign Alvin AuYoung, HP Labs, Palo Alto Kimberly Keeton, HP Labs, Palo Alto Xiaozhou (Steve) Li, Google Storage systems continue to lay the foundation for modern Internet services such as Web search, e-commerce, and social networking. Pressures caused by rapidly growing user bases and data sets have driven system designs away from conventional centralized databases and toward more scalable distributed solutions, including simple NoSQL key-value storage systems, as well as more elaborate NewSQL databases that support transactions at scale. Distributed key-value storage systems are among the simplest and most scalable specimens in the modern storage ecosystem. Such systems forgo many of the luxuries of conventional databases, including ACID (atomicity, consistency, isolation, durability) transactions, joins, and referential integrity constraints, but retain fundamental abstractions such as tables and indexes. As a result, application developers are sheltered from technicalities such as normalizing the relational schema, selecting the optimal transaction isolation level, and dealing with deadlocks.
