Paper: The Case for RAMClouds: Scalable High-Performance Storage Entirely in DRAM

Stanford Info Lab is taking pains to document a direction we've been moving for a while now, using RAM not just as a cache, but as the primary storage medium. Many quality products have built on this model. Even if the vision isn't radical, the paper does produce a lot of data backing up the transition, which is in itself helpful. From the The Abstract:

Disk-oriented approaches to online storage are becoming increasingly problematic: they do not scale grace-fully to meet the needs of large-scale Web applications, and improvements in disk capacity have far out-stripped improvements in access latency and bandwidth. This paper argues for a new approach to datacenter storage called RAMCloud, where information is kept entirely in DRAM and large-scale systems are created by aggregating the main memories of thousands of commodity servers. We believe that RAMClouds can provide durable and available storage with 100-1000x the throughput of disk-based systems and 100-1000x lower access latency. The combination of low latency and large scale will enable a new breed of data-intensive applications.

Related Articles

• Hacker News Thread
• Are Cloud Based Memory Architectures the Next Big Thing?
• Stanford Info Lab
• The SSD Relapse: Understanding and Choosing the Best SSD
• Put that database in memory by Greg Linden 
• Randy Shoup & John Ousterhout at HPTS 2009 by James Hamilton

Comments

[sensei]

So Standford Info labs are coming after you.
This shows How good jobs you have performed.
Regards.

[Mark Robson]

How can we achieve durability with a ram-cloud?

Even with the best will in the world, datacentres seem to have a habit of occasionally turning the power off. Not just on one server, or one rack, but the whole caboodle. They usually leave it off for a few minutes before turning it back on. Do we need battery backup? Do we checkpoint stuff / transaction log it to disc or ssd?

[Hisyam]

it reminds me of Object Prevalence...

An introduction to object prevalence :
http://www.ibm.com/developerworks/library/wa-objprev/

3251 Times Faster than MySQL, 9983 Times Faster than ORACLE :
http://www.advogato.org/article/479.html

[Lennie]

The video on YouTube explains it very well:

http://www.youtube.com/watch?v=lcUvU3b5co8