BuddyFS: A File-System to Improve Data Deduplication in Virtualization Environments
Nirandika Wanigasekara, Chamath I. Keppittiyagama · 2014
Most virtualization environments demand users to download complete disk images to create virtual machines. However, since system data hardly varies from user to user there is a possibility to have common data blocks amongst the disk images and the hosting environment. Our research evaluates whether deduplication of these common data blocks can rectify existing problems in virtualization environments. Using a new file-system, BuddyFS we have identified these common data blocks and reused them to create disk images. We have also discussed how semantic information can be used to optimize the data deduplication process. Our results show that data deduplication in virtualization environments can improve transfer times and storage space. It can be used to reduce the overhead of managing virtual devices in now rapidly expanding virtualization environments such as clouds.