ExaGrid

ExaGrid Product Line

ExaGrid Product Line

ExaGrid offers a highly scalable disk-based backup system that works with your existing backup application and combines high quality SATA storage, compression and byte-level data de-duplication with a virtualized GRID architecture. This unique approach reduces the disk space required for backup by a range of 10 to 50:1, delivering unparalleled cost savings and performance at a fraction of the price of standard SATA disk storage.

Scalable GRID Architecture

There are five core ExaGrid disk-based backup servers. These servers include GRID computing software. When plugged into a switch they virtualize into one another. As a result, any of the five configurations can be mixed and matched into a single GRID system, with capacities up to 60TB, in 1TB increments. Once virtualized, they appear as a single system to the backup server. Load balancing of all data across servers is automatic and multiple GRID systems can be combined for additional capacity.

Five Core ExaGrid Server Configurations

  • 1TB EX1000
  • 2TB EX2000
  • 3TB EX3000
  • 4TB EX4000
  • 5TB EX5000

For example, a 5TB ExaGrid server can store a 5TB full backup (5TB of primary data) plus up to 16 weeks of retention/history, while a 2TB server can take in a 2TB full backup (2TB of primary data) plus up to 16 weeks of retention. If a 20TB system is required, then four EX5000s are plugged into the switch and virtualize into a single system.

 

Five Mix and Match Servers

ExaGrid Model

Primary Data Capacity

Capacity for Weekly Fulls

Capacity for Daily Fulls

Backup throughput

 

 

Copies

Total backup data

Copies

Total backup data

 

EX1000

1 TB

16

16 TB

75

75 TB

360 GB/hr

EX2000

2 TB

16

32 TB

75

150 TB

360 GB/hr

EX3000

3 TB

16

48 TB

75

225 TB

360 GB/hr

EX4000

4 TB

16

64 TB

75

300 TB

540 GB/hr

EX5000

5 TB

16

80 TB

75

375 TB

540 GB/hr

 

Examples of several common ExaGrid system GRID configurations between 5TB and 20TB

Configuration Models Used

Primary Data Capacity

Capacity for Weekly Fulls

Capacity for Daily Fulls

Backup throughput

 

 

Copies

Total backup data

Copies

Total backup data

 

7 TB
1 x EX4000
1 x EX3000

7 TB

16

112 TB

75

525 TB

1.08 TB/hr

10 TB
2 x EX5000

10 TB

16

160 TB

75

750 TB

1.08 TB/hr

12 TB
3 x EX4000

12 TB

16

192 TB

75

900 TB

1.62 TB/hr

15 TB
3 x EX5000

15 TB

16

240 TB

75

1125 TB

1.62 TB/hr

20 TB
4 x EX5000

20 TB

16

320 TB

75

1500 TB

2.1 TB/hr

 

Scalability and Performance

A 1TB to 5TB ExaGrid server in combination with the virtualized GRID architecture allows for the following:

  • Start with the appropriate initial capacity and add capacity in 1TB to 5TB increments as needed

  • "Right size" capacity up front and over time by adding only the required capacity
  • As servers are added, additional memory, processor disk and GigE are also added resulting in no loss of performance. As data grows the appropriate amount of system resources are added.

Core Server Components

ExaGrid servers are comprised of the following:

  • Intel Dual Core XEON processors
  • Intel motherboard
  • Seagate SATA drives
  • RAID 6 hot Spare
  • ExaGrid Software

Each server includes the appropriate amount of processor, memory, disk and GigE for the amount of data. As each server is plugged into the switch and virtualized into the GRID it brings not only disk capacity but also processor, memory and GigE such that performance is maintained as data is added.

 

Summary

ExaGrid’s unique approach to scalability provides the following benefits:

  • Performance is maintained as your data grows – each additional ExaGrid server added to a system provides disk, processor, memory and GigE

  • Capacity utilization is load-balanced across servers – as a single server reaches full utilization, it can leverage space available on other servers in the GRID

  • Plug and play expansion – adding an additional ExaGrid server is as simple as plugging it in and letting ExaGrid’s automatic virtualized GRID software do the rest

  • Cost-effective, system "right-sizing" – acquire just what you need now, add more later as data grows