EMC's Data Domain storage division came out April 12 with a speedy
new inline deduplication storage system for enterprise backup
applications.
The numbers shout for themselves. Data Domain claims this new system,
dubbed the Global Deduplication Array, is capable of backing up 12.8TB
of data per hour (which computes to a 3.5G bps I/O rate), has a top-end
usable capacity of 280TB, and can handle up to 270 concurrent write
streams.
Now those are true large enterprise-type specifications, but how does
one system move all those bits so quickly and keep everything going to
the right place? By doubling up on Data Domain's high-end DD880 data
storage controllers, it turns out.
"This is an entirely new product offering for Data Domain, in terms of
using multiple controllers to be able to expand performance capacity,"
Ed Reidenbach, senior director of product marketing, told eWEEK.
"There are a lot of organizations -- large Fortune 1000s, for example
-- that are backing up 40, 50TB per day, given their backup policies.
They have really large databases that they back up in full, even if
there are minor changes to the database. It's too complex, error-prone
to do incremental backups in these cases. This array solves that
problem."
The new inline array distributes parts of the deduplication process to
the backup servers in order to reduce network load and increase
throughput performance of the GDA controllers, Reidenbach said.
Using EMC Data Domain's Replicator software option, the Global
Deduplication Array also can automate wide area network (WAN) vaulting
for use in disaster recovery, remote office backup, or multisite tape
consolidation, Reidenbach said.
"Figuring out how to get backups done within the allotted period of
time in the face of data growth is still the biggest data protection
challenge that organizations face according to our research," said
Brian Babineau, Senior Consulting Analyst with Enterprise Strategy
Group.
"With their Data Domain Global Deduplication Array, EMC has far
exceeded the inline deduplication performance benchmark it set with its
previous top-of-line Data Domain system, but more importantly, the
company has given customers a way to protect more of their data in a
shorter period of time.
"We expect more companies to evaluate integration between backup
software and deduplication storage to maximize these performance levels
and data reduction results while consolidating administrative tasks."
EMC also announced enhanced features for the regular DD880 arrays,
including a new encryption software option designed for data at rest
and new replicator features for systems with thin wires.
The DD880, Data Domain's top-of-the-line array, now features a doubled
top capacity (142.5TB usable from 71TB previously), Reidenbach said.
The EMC Data Domain Global Duplication Array will be generally available in Q2 2010.
For more information about these storage systems, see the EMC Data Domain site.
 |