EMC Data Domain
Technology
Data Domain technology optimizes deduplication storage.
EMC Data Domain Stream-Informed Segment Layout (SISL™) scaling architecture: Optimizes deduplication throughput scalability and minimizes disk footprint by minimizing disk accesses. System throughput is CPU-centric, not “spindle bound.” Inline deduplication throughput speeds leverage the continued advancement in CPU performance. SISL technology first identifies 99 percent of duplicate, variable-length data segments in RAM, inline, before storing to disk. Then it stores related segments and fingerprints together, so large groups can be read at once. EMC Data Domain systems can use the capacity of large SATA disks for data protection and—without increasing RAM—minimize the number of disks needed to deliver high throughput.
EMC Data Domain Data Invulnerability Architecture: Advanced data verification and data integrity, including RAID 6 protection. Continuous fault detection, healing, and write verification ensure that backup and archive data is accurately stored, available, and recoverable. The no-overwrite, log-structured architecture of the EMC Data Domain filesystem, with insistence on full-stripe writes, ensures that old backups are always safe even after software errors during new backups. Meanwhile, a simple and robust implementation reduces the chance of software errors in the first place.

Hardware
EMC® Data Domain® deduplication storage systems dramatically reduce the amount of disk storage needed to retain and protect enterprise data. By identifying redundant files and data as they are being stored, Data Domain systems require a storage footprint that is 10x-30x smaller, on average, than the original dataset. Backup data can then be efficiently replicated and retrieved over existing networks for streamlined disaster recovery and consolidated tape operations.



