RAMCube is a datacenter oriented design for RAM-based key-value store that supports thousands or tens of thousands of servers to offer up to hundreds of terabytes of RAM storage. Here's the PDF Paper describing the system and here's a video of the presentation given at HotCloud.

The big idea is: RAMCube exploits the proximity of a BCube network to construct a symmetric MultiRing structure, restricting all failure detection and recovery traffic within a one-hop neighborhood, which addresses problems including false failure detection and recovery traffic congestion. In addition, RAMCube leverages BCube’s multiple paths between any pairs of servers to handle switch failures.

A few notes:

• 75% of Facebook data is stored in memcache.
• RAM is 1000 time faster than disk
• RAM is used in caches, but this increases application complexity as applications are responsible for cache consistency.
• Under a high work load a 1% cache miss rate can lead to a 10x performance penalty.
• So store data directly in RAM instead of using a cache. 
• Storing all data in RAM requires replication to multiple nodes for safety, which brings in datacenter networking issues.
• The unhappy reality of datacenter networks must be considered to maximize the benefits of RAM.
  • False failure detection. It's difficult to quickly tell temporary network problems from real node failures.
  • Given the high levels of traffic fast failure recovery is difficult.
• Utilizes the global topology information of BCube and leverage network proximity to restrict all failure detection and recovery traffic within an one-hop neighborhood. 

Related Articles

• Building Super Scalable Systems: Blade Runner Meets Autonomic Computing In The Ambient Cloud
• Changing Architectures: New Datacenter Networks Will Set Your Code And Data Free