RAMCloud Papers

This page lists all of the papers that have been published about RAMCloud and related topics, in reverse chronological order (most recent papers first).

• Implementing Linearizability at Large Scale and Low Latency: describes a general purpose design for providing exactly once semantics and its use in implementing transactions.  Appeared in SOSP in October 2015.
• The RAMCloud Storage System: a comprehensive paper describing RAMCloud, including the log-structured storage mechanism, RAMCloud's thread architecture and approach to low latency, and its crash recovery mechanisms. Published in ACM TOCS in September 2015.
• SLIK: Scalable Low-Latency Indexes for a Key-Value Store: describes how SLIK adds secondary indexing to RAMCloud without sacrificing latency or scalability. An earlier version appeared in ATC'16.
• Experience with Rules-Based Programming for Distributed, Concurrent, Fault-Tolerant Code describes a common approach for building DCFT (distributed, concurrent, fault-tolerant) modules in RAMCloud and other distributed systems. Appeared in ATC'15.
• In Search of an Understandable Consensus Algorithm (Extended Version): describes the Raft consensus protocol. Slightly shorter version (PDF) published in ATC'14; won Best Paper Award.
• Memory and Object Management in RAMCloud: PhD dissertation, Steve Rumble, March 2014.
• Log-Structured Memory for DRAM-based Storage: describes how RAMCloud manages the storage of objects both in DRAM and on disk. Appeared in FAST in February 2014; won Best Paper Award.
• Durability and Crash Recovery in Distributed In-memory Storage Systems: PhD dissertation, Ryan Stutsman, November 2013.
• Toward Common Patterns for Distributed, Concurrent, Fault-Tolerant Code: HotOS XIV (2013) workshop paper arguing the need for common patterns for developing fault-tolerant code
• Fast Crash Recovery in RAMCloud: describes RAMCloud's mechanism for recovering crashed servers in 1-2 seconds. Appeared in SOSP in October 2011.
• It's Time for Low Latency: HotOS 2011 workshop paper arguing for the OS community to focus on network latency.
• The Case for RAMCloud: a position paper that discusses the motivation for RAMCloud, the new kinds of applications it may enable, and some of the research issues that will have to be addressed to create a working system. Appeared in CACM in July 2011. An earlier and a slightly longer version appeared in Operating Systems Review in December 2009.