Technology - The Ocarina ECOsystem

The Ocarina ECOsystem

The Ocarina ECOsystem is a patented, three-step solution that enables you to reclaim 30 to 75 percent more capacity on your existing storage. Typical Ocarina customers free up two-thirds more disk space, saving OpEx and CapEx for storage. This award-winning solution utilizes unique, “content-aware” dedupe and compression algorithms that have the intelligence to extract and analyze the component parts of virtually any file.

The Ocarina ECOsystem involves three sequential steps:

Extract:
First, we extract data from each file, seeking out any objects that could be compressed or deduplicated. We break down the file to its sub-file level. This often requires delayering compound documents, decoding already-compressed files, and other procedures to get to the fundamental storage objects in a given file.

C is for Correlate:
Once the storage objects have been identified, Ocarina can correlate them within and across files. We look for exact matches and similar storage objects at the information level and remove redundant information. The Ocarina correlation process is able to identify the relationships between objects which, at byte level, may share no duplicate patterns. A block-level dedupe product, on the other hand, could never identify such connections.

This process draws boundaries at the natural object level, in a way that is comparable to the human eye. Examples include: an image in a PowerPoint file, a page in Word document, or a JPEG file in a zipped archive. Because Ocarina is content aware, we are able, for example, to find files within larger file containers such as Zip files, and intelligently recognize them. If there are any duplicates within these files—even if they are not within another Zip file—we’ll find them and dedupe them. Where the data set is something we do not have specific algorithms for, we’ll treat each file as an opaque object.

Optimize:
Finally, we optimize the remaining storage objects, employing patent-pending content-aware algorithms to get the best possible space savings for each fundamental data type. Routing each part of each document to the specific file-aware optimizer best for that data type, we achieve compression results beyond plain dedupe.


Results are impressive. In Ocarina’s content-aware storage optimization solution, initial space savings range from 40% for complex image files to well over 70% for common office file mixes. It is not unreasonable to expect that almost any company could reduce the space they need to store their user and application files by 2/3rds or more—on storage they already have, from vendors they are already work with, on networks that are already in place.