Archive Home arrow Reviews: arrow Network arrow QNAP TS-259 Pro Turbo NAS Server
QNAP TS-259 Pro Turbo NAS Server E-mail
Reviews - Featured Reviews: Network
Written by Bruce Normann   
Sunday, 02 May 2010
Table of Contents: Page Index
QNAP TS-259 Pro Turbo NAS Server
QNAP Turbo NAS Features
QNAP TS-259 Pro NAS Hardware
QNAP TS-259 Pro Software
QPKG Center Software Expansion
Closer Look: QNAP TS-259 Pro
Insider Details: QNAP TS-259 Pro
QNAP v3 User Interface
NAS Testing Methodology
Basic-Disk Test Results
Windows 7 Disk Test Results
NAS Server Final Thoughts
QNAP TS-259 Pro Conclusion

Network Terminology

Benchmark Reviews has decided to abandon our effort to educate readers on the difference between a Gigabyte, and a Gibibyte. This article will use the common metric terminology for data measurement, instead of the binary units we've used in past articles. Sadly, too many people are more interested in comfortable reading, even if it means being technically inaccurate. But for anyone who might still be interested in learning real technical terms relevant to the industry, I've added a small explanation below:

The basic unit data measurement is called a bit (one single binary digit). Computers use these bits, which are composed of ones and zeros, to communicate their contents. All files are stored as binary files, and translated into working files by the Operating System. This two number system is called a "binary number system". In comparison, the decimal number system has ten unique digits consisting of zero through nine. Essentially it boils down to differences between binary and metric measurements, because testing is deeply impacted without carefully separating the two. For example, the difference between the transfer time of a one-Gigabyte (1000 Megabytes) file is going to be significantly better than a true binary Gigabyte (referred to as a Gibibyte) that contains 1024 Megabytes. The larger the file used for data transfer, the bigger the difference will be.

Have you ever wondered why your 500 GB hard drive only has about 488 GB once it has been formatted? Most Operating Systems utilize the binary number system to express file data size, however the prefixes for the multiples are based on the metric system. So even though a metric "Kilo" equals 1,000, a binary "Kilo" equals 1,024. Are you confused yet? Don't be surprised, because even the most tech savvy people often mistake the two. Plainly put, the Kilobyte is expressed as 1000 bytes, but it is really comprised of 1,024 bytes.

Most network engineers (myself included) are not fully aware that the IEC changed the way we calculate and name data chunks when they published the new International Standards back in December 1998. The International Electrotechnical Commission (IEC) removed the old metric prefixes for multiples in binary code with new prefixes for binary multiples made up of only the first two letters of the metric prefixes and adding the first two letters of the word "binary". For example, instead of Megabyte (MB) or Gigabyte (GB), the new terms would be Mebibyte (MiB) or Gibibyte (GiB). While this is the new official IEC International Standard, it has not been widely adopted yet because it is either still unknown by institutions or not commonly used.

Personally, I think the IEC took a confusing situation and simply made it more of a mess. As I mentioned earlier, the Kilobyte was previously expressedas 1000 bytes, even though it was really comprised of 1,024 bytes. Now, the Kilobyte really is expressed correctly as 1000 bytes, and the Kibibyte is the item comprised of 1,024 bytes. In essence, the IEC just created a new name for the binary item and left the existing name for the metric item. Hopefully that clears things up, and you can thank Benchmark Reviews for training the next generation of Network Engineers.

NAS Testing Methodology

Although the device we tested can accommodate several different disk configurations, all of our current test data has been with basic (single) disk and RAID-5 configurations. Since this two-bay device cannot support RAID-5, I tested only the single disk mode.

Connected directly to the Realtek RTL8112B PCIe Gigabit Ethernet NIC in the test-bench system by a ten-foot CAT6 patch cable, the NAS product receives one test transfer followed by three timed transfers. Each test file was sent to the Western Digital Caviar Black 750GB (WD7501AALS) hard drives installed in the NAS for a timed write test, and that same file was sent back to a Western Digital VelociRaptor 150GB 10,000 RPM (WD1500HLFS) hard drive in the test system to perform a read test. Each test was repeated, and the first three identical results were recorded and charted.

QNAP_TS-259-Pro_NAS_Left_Front_High.jpg

The two transfer tests: read and write, were conducted on each NAS appliance using the 1 GB file and then the 10 GB file. Additionally, a second set of tests were conducted with Jumbo Frame enabled. While the Synology Disk Station DS209, DS408, Cube Station CS407, and QNAP TS-409 Pro/TS-209 Pro each offered 9000K MTU Jumbo Frame settings available, the D-Link DNS-323 and QNAP TS-509 Pro do not. In some Jumbo Frame tests the Realtek RTL8112B Gigabit NIC was limited to a maximum of 4074 for the MTU value, with Jumbo Frame enabled.

NAS Comparison Products

Support Equipment

  • (2) Western Digital Caviar Black 750GB SATA-II 7200 RPM HDD
  • 10-Foot Category-6 Solid Copper Shielded Twisted Pair Patch Cable
  • 1 metric Gigabyte Test File (1 GB = 1,000,000,000 bytes)
  • 10 metric Gigabyte Test File (10 GB = 10,000,000,000 bytes)

Test System

  • Motherboard: ASUS M4A79T Deluxe (AMD 790FX Chipset)
  • Realtek RTL8112B PCI-E Gigabit LOM Ethernet Controller (Driver Version 5.702.0806.2008)
  • Processor: AMD Phenom II 720 Black Edition (Overclocked to 3.6 GHz)
  • System Memory: 2X 2GB OCZ Reaper HPC DDR3 1600MHz (7-7-7-24)
  • Disk Drive 1: OCZ Summit SSD, 60GB (OCZSSD2-1SUM60G)
  • Disk Drive 2: Western Digital VelociRaptor 150GB, 10,000 RPM (WD1500HLFS)
  • Operating System 1: Windows XP Home, SP3
  • Operating System 2: Windows 7 Ultimate Version 6.1 (Build 7600)



 

Comments 

 
# Test with bonding gbit lan ?^-Super_Treje-^ 2010-05-03 23:34
No test with the network in "bonding" ?
Report Comment
 
 
# I did, but....BruceBruce 2010-05-04 07:15
I repeated the tests with IEEE 802.3ad Link Aggregation Control Protocol, using two Intel Gigabit CT Desktop Adapters in the test bench system. The problem with that test scenario and Teaming or Bonding or whatever you want to call it, is that the network speed stays exactly the same. The bandwidth is increased by widening the data path, not increasing the speed. I.e. it?s analogous to two fully loaded trucks driving the speed limit instead of one truck delivering your data. Yes, you get twice the data, but you get it in the same time frame, which is what our testing measures.

I think the way to test this feature is to have two or more transfers occurring at the same time. With one transfer already under way, another could be started and timed, and the speed of the second transfer should be relatively unaffected by the continued activity of the first one. Your thoughts, suggestions?
Report Comment
 
 
# 802.3ad is NOT your solutionscavenger 2012-11-30 12:01
YES this is it. Load balancing is made only on multiple file transfers.

If you can read french, I posted a lot about it on #lafibre.info/iperf/gs108t-nc360t-n5550-load-balancing-33mbs/new/#new but the result is this one :
Conclusion is 802.3ad is ONLY failover. ABSOLUTELY NOT load balancing.
If you want to do what I dreamed of, choose on each side the Balance-SLB (or Balance-ALB) + round robin transmit load balancing method.
Then you will have a smooth repartition of the packets on each port, but you will notice a strong down bandwidth due to the fact that "Packet order is NOT guaranteed"
Load balancing for a one file transfer on many cables is just a dream... right now...
Report Comment
 

Comments have been disabled by the administrator.

Search Benchmark Reviews
QNAP Network Storage Servers

Follow Benchmark Reviews on FacebookReceive Tweets from Benchmark Reviews on Twitter