Power consumption and the management of disk failures have been niche topics in computer science over the past ten years. It takes a nontrivial amount of energy to keep a disk spinning. The costs become significant when we consider the number of personal computers, servers, and notebooks currently in use. More critically, disks fail much more frequently than commonly believed. GreenFS is a system that addresses both the reliability of disks and the cost of constant operation.

The GreenFS architecture begins with the notion that most enterprise computers, of whatever form factor, are networked. Joukov and Sipek introduce the concept of a reverse backup. Typical systems store backup data on the server and use the local disk for daily operations. In GreenFS, they store the backup on the local disk and use the network for daily operations. This inversion allows the local disk to be spun up only a few times a day to retrieve updates from the active network. In case of disconnected operations, the local disk is spun up and used as the main repository.

To provide complete protection and uninterrupted operations, the GreenFS file system uses a local flash disk as an intermediary storage area for items that need to be retained locally, but do not warrant spinning up the local disk. Although necessary, the local flash disk complicates the architecture and its implementation.

I enjoyed reading this paper. It is full of good details and presents a novel file system design.