As you can see, we use a pretty strong test system with an ultra-fast OCZ Vertex 4 SSD off of which all tests are executed. This ensures that there is no bottleneck due to the PC since the specified SSD can achieve up to 560 MB/s read and 510 MB/s write speeds (sequential).
NAS Configuration
Internal Disks:
6x Seagate ST500DM005 500 GB (HD502HJ, Serial ATA III, 7200 RPM, 16 MB)
External Disks:
OCZ Agility 2 (64 GB) in USB 3.0 enclosure
Firmware:
ADM 1.0.4.RBU2
Ethernet Switch:
TL-SG3216 16-port Gigabit managed switch (LACP and Jumbo frames support)
Ethernet Cabling:
CAT 6e, 2 m
Methodology
We use three different programs to evaluate the performance of the NAS. The first is Intel's NAS Performance Toolkit. Intel was kind enough to build a NAS performance toolkit, and not only did they release it for free to the public, but they also provided its source code. The only problem of this toolkit is that the results of two tests ("HD Video Record" and "File Copy to NAS") are heavily skewed on a client PC with more than 2 GB of memory since these tests actually measure the client's RAM buffer speed and not the network speed, which is why we set the maximum memory to 2GB via msconfig's advanced options. During these tests, we exploit the batch run function: it repeats the selected tests for five turns and takes the average reading as the final result.
The second program is a custom-made program that performs ten basic file-transfer tests, taking the average MB/s speed for each transfer. We run the selected tests ten times and use the average as a final result to extract results that are as accurate as possible.
The third program we use in our test sessions is ATTO: a well-known program for storage benchmarks. ATTO cannot directly access network drives, and we are, in order to use ATTO for benchmarking, forced to map a shared folder of the NAS to a local drive.