Clearpath’s Blog on IT Infrastructure, Hybrid Clouds and IT Security

EMC Data Domain Boost: What is it and Why it's Beneficial

Posted by Judson Weinsheimer on Thu, Jan 29, 2015 @ 09:39 AM

Over the years I’ve had quite a few Data Domain customers ask, “Just what is Data Domain Boost?” followed by “Do I need Boost?” - Chances are you’ve come across this article with the same two questions. With any luck, by the time you’re through reading, I’ll have answered the first question and helped you along the way to answering the second.

Contact Clearpath's Dell EMC Professional Services Team

What is Data Domain (DD) Boost? Simply put DD Boost is software that enhances how backup servers and clients interact with a Data Domain backup appliance. It is based on Symantec’s OST (Open Storage Technology) protocol, and is a means to extend Data Domain features back to the source. This API integration adds three distinct benefits:

  • It distributes the data deduplication process, resulting in faster data throughput and decreased server CPU utilization
  • It allows the backup application to natively control deduplicated replication of backup sets
  • It provides advanced load balancing and link failover, eliminating the need for link aggregation

Using non-Boost access protocols (CIFS, NFS, VTL) the Data Domain performs inline data deduplication. As files and data sets are sent over the network, the DD uses RAM and CPU to deduplicate common data, writing only unique data segments to disk. By adding DD Boost, a large part of the deduplication work can take place before the data is sent over the network to the Data Domain. The backup source takes the data, segments it out, compares it with segments already on the Data Domain, and only sends over new, unique segments. This distributed deduplication allows for greatly reduced network utilization. A backup set of 500GB traversing your network may be shrunk down to a tenth of that size. This is of particular value to congested networks or backups being sent over a WAN. Using distributed deduplication also frees up resources on the Data Domain allowing it to ingest data at a higher rate. With Boost, Data Domain systems can effectively double their max throughput.

 

Without DD Boost

With DD Boost

DD160

667 GB/hr

1.1 TB/hr

DD2500

5.3 TB/hr

13.4 TB/hr

DD4200

10.2 TB/hr

22.0 TB/hr

DD990

15.0 TB/hr

31.0 TB/hr

Source: EMC Data Domain Deduplication Storage Systems Spec Sheet

Data Domain’s integrated replication, while fantastic, is a second pane of glass for administrators trying to keep track of their environment. With DD Boost, replication tasks between appliances are managed within the backup application (replica traffic is still deduplicated).  Having the backup application aware of the second appliance provides two useful benefits - you can restore data from the second appliance in the event the local appliance is unavailable and it allows for different retention policies between appliances.

Do I need Data Domain Boost?  The first thing you should ask yourself is are you encountering bottlenecks during your backup window? In a lot of small to medium environments sending backup data to a single Data Domain, a CIFS or NFS share provides more than enough flexibility and throughput. Environments with large or distributed datasets are more likely to immediately benefit from Boost integration.

Second, would you prefer to manage replication through the backup application? In many cases, the native replication features within Data Domain will suit your needs. However, if you want to be able to restore directly from the second appliance without reconfiguring the application or you want different retention periods between sites, then you’ll want Boost.

You can’t handle the Boost. While not every backup application currently integrates with DD Boost, there are many that do.  EMC Networker and Avamar both integrate, as does Symantec products, vRanger, Veeam, HP, and many others.  Check with your backup application provider (or give us a call) if you’d like additional help in determining compatibility.

So there you have it, some very quick and dirty information on DD Boost. With any luck I’ve answered some questions and got some gears moving. For more information check out EMC’s Slow Backups Got You Down? The Business Value of Data Domain Boost whitepaper, or the latest Data Domain Administration Guide. 

Topics: EMC, Data Domain, Deduplication, DataDomain, Backup & Recovery Solutions, Backup & Replication

Subscribe to Email Updates

Recent Posts

Posts by Topic

see all
Live Chat Support Software