Restore Performance On Deduplicated Data Is A Common Challenge. Why?
If deduplication occurs inline, then all of the data on the disk is deduplicated and needs to be put back together, or “rehydrated,” for every restore request. This means that local restores, instant VM recoveries, audit copies, tape copies and all other requests will take hours to days. Most environments need VM boot times of single-digit minutes; however, with a pool of deduplicated data, a VM boot can take hours due to the time it takes to rehydrate the data. All of the deduplication in the backup applications as well as the large-brand deduplication appliances store only deduplicated data. All of these products are very slow for restores, offsite tape copies, and VM boots.
How Does ExaGrid Address Backup And Restore Performance On NetWorker?
When you choose ExaGrid Tiered Backup Storage for NetWorker, each ExaGrid appliance includes a disk-cache Landing Zone. Backup data is written directly to the Landing Zone versus being deduplicated on the way to disk. This avoids inserting the compute-intensive process into the backup – eliminating costly slow down. As a result, ExaGrid achieves backup performance of 488 TB/hr. for a 2.7 petabyte full backup versus Data Domain at 68 TB/hr. using DDBoost for only 1 PB of full backup storage. This is 3 times faster than any traditional inline data deduplication solution, including deduplication performed in backup applications or target side deduplication appliances.
Because ExaGrid’s appliances allow each full backup to first land on the Landing Zone before deduplication, the system maintains the most recent backup in its full, undeduplicated form for fast restores, Instant VM recoveries in seconds to minutes, and fast offsite tape copies. Since over 90% of restores and 100% of instant VM recoveries and tape copies are done from the most recent backup, this approach avoids the overhead incurred from “rehydrating” data during critical restores. As a result, restore, recovery, and copy times from an ExaGrid system are an order of magnitude faster than solutions that only store deduplicated data.
In most cases, ExaGrid is at least 20 times faster than any other solution, including Data Domain, backup applications and target side deduplication appliances.
ExaGrid Scales with Linear Performance Up to a 2.7PB Full Backup
Should you choose fixed-compute media servers or front-end controllers as a storage solution for NetWorker, as data grows, the backup window expands as it takes increasingly longer to perform deduplication. ExaGrid solves this problem by applying a scale-out storage architecture to back up with data deduplication. Each ExaGrid appliance has Landing Zone storage, repository storage, processor, memory, and network ports. As data grows, ExaGrid appliances are added into the scale-out system. This increases all resources linearly. The result is a fixed-length backup window regardless of data growth, versus Data Domain which only scales to a 1PB full backup.
Dell EMC NetWorker users may be surprised at how quickly they can have their first backup running on ExaGrid. Many ExaGrid customers take only a few seconds to configure and are fully operational within 30 minutes.
The Dell EMC NetWorker family is the fastest and most flexible backup and recovery solution in the industry. NetWorker protects your critical enterprise applications at record speed. ExaGrid fits into the NetWorker DiskBackup Option as part of the NetWorker family.