We would like to thank the following companies for supplying and supporting us with our test system hardware and equipment: AVADirect, GIGABYTE, Cooler Master, LSI, Corsair and Phanteks.
You can read more about TweakTown's Storage Product Testing Workstation and the procedures followed to test products in this article.
The new 2012 TweakTown Storage Test system is in full effect after a short validation period. I was very surprised at how quickly the system passed our tests for stability, performance and reliability. AVADirect came through again and supplied us with Intel's flagship processor, a true beast of engineering.
On the motherboard side GIGABYTE supplied us with two boards to get the system up and running. Our main requirement for 2012 was the need for four full length PCIe slots. We are now testing NAS servers with 10GbE Ethernet that is capable of delivering up to 800-1000MB/s of bandwidth. To reach those speeds on the client side we also require a RAID controller, the LSI 9265-8i is the best in class product for this purpose.
Reaching 1000MB/s for the OS is easier than it used to be with solid state drives. Running SSDs in RAID and keeping the performance high is another story all together. For this we chose to run eight Corsair Performance 3 drives. The Performance 3 Series use a very aggressive background garbage collection algorithm so performance stays constant even after an abusive cycle of tests.
For the first time in six years I'm not running a Noctua CPU cooler. The Phanteks orange CPU cooler matches the orange on the motherboard and I wanted to see what other companies have to offer. I'm not disappointed in the cooler or its performance, but I did need to modify the cooler to fit the taller Corsair Vengeance memory.
ATTO Baseline Performance
Version and / or Patch Used: 2.34
ATTO is used by many disk manufacturers to determine the read and write speeds that will be presented to customers.
Using ATTO we achieved a marketing speed of nearly 470MB/s read and 205MB/s write. That is a fairly wide gap between read and write performance, but common on this type of architecture in smaller capacity drives. Peak performance is hardly the best way to judge performance as you will see in the fill testing today.