Networking

The Windows 2000 Driver Development Kit (DDK) includes a useful LAN testing utility called NTttcp. We used the NTttcp tool to test Ethernet throughput and the CPU utilization of the various Ethernet Controllers used on the Intel motherboards. We set up one machine as the server; in this test, an Intel system with an Intel CSA Gigabit LAN connection. Intel CSA has a reputation for providing fast throughput and is a logical choice for our Gigabit LAN server.

On the server side, we used the following Command Line as suggested by the VIA whitepaper on LAN testing:

Ntttcpr -m 4,0,‹server IP› -a 4 -l 256000 -n 30000

On the client side (the motherboard under test), we used the following Command Line:

Ntttcps -m 4,0,‹client IP› -a 4 -l 256000 -n 30000

At the conclusion of the test, we captured the throughput and CPU utilization figures from the client screen.

Networking Performance - Throughput

Networking Performance - CPU Utilization

Our network throughput test indicates how well a particular controller design from Realtek, Marvell, or Intel performs instead of being indicative of true chipset performance. This also holds true for the CPU utilization results, though this test can also be influenced to certain degree by the BIOS code and chipset interconnect design.

The CPU utilization and throughput numbers favor the Realtek controller on the Gigabyte board, followed closely by the same Realtek chipset on the Foxconn and ASRock boards. In practice, few if any users will notice a difference, even if they have the requisite gigabit hub, as storage performance frequently bottlenecks the actual transfer rates.

For our second series of networking tests we utilize a Promise SmartStor NS4600 NAS unit equipped with two WD Caviar Black 640GB drives in RAID 1 operation. We are using two benchmarks from Intel’s popular NASPT 1.70 testing tool. The Promise NAS unit is connected to each test platform via a NetGear Gigabit Ethernet switch. We left all settings at their defaults on both the motherboard and Promise NAS unit. Our goal was to maximize the performance of the NAS unit to verify our network throughput capabilities on each motherboard.

Networking Performance - File Copy to NAS

Networking Performance - HD Video - Play/Record

Our three P55 test subjects perform almost identically in our actual usage tests.

USB / FireWire Performance

Our USB transfer speed tests are conducted with an USB 2.0/FireWire based Lacie external hard drive unit featuring a 1TB 7200rpm Samsung drive. In the SSD to External test, we transfer a 3.82GB folder containing 2735 files of various sizes from our Kingston 80GB SSD to the Lacie drive. In the next two file tests, we use the same 3.82GB folder to transfer from our WD VRaptor 300GB hard drive to the external Lacie drive utilizing the USB 2.0 and IEEE 1394a interface.

Storage Performance - USB - SSD to External HD

Storage Performance - USB - HD to External HD

Storage Performance - Firewire - HD to External HD

The MSI board performs in the middle of the pack in our USB tests. The VIA Firewire controller on the MSI board has a slightly higher write speed (+3Mb/s) under HDTach/HDTune and it shows up in our file transfer test compared to the Gigabyte/Foxconn boards.

Storage Performance

In our storage test, we utilize the same 3.82GB test folder and transfer it from our WD VRaptor drive to our Kingston 80GB SSD.


Storage Performance - HD to SSD

Once again, our P55 motherboards perform almost identically. The P55 chipset on the MSI board has a 3% advantage over the JMicron controller on the same board. However, any measurable differences were not recognized in actual usage.

Gaming
Comments Locked

43 Comments

View All Comments

  • goinginstyle - Saturday, October 10, 2009 - link

    It's on the front page. A change up in the article layout from all indications. It's different but good in my opinion as there is no need is reading the same stuff twice.
  • Minion4Hire - Sunday, October 11, 2009 - link

    I really liked it. Keeps everything concise. You get a full synopsis on one page, and yet all the benchmarks and hard numbers are still available if you want to compare. It's really a great format for those who just want to get the feel of a product; they don't have to skim page after page looking to compile useful relevant snippets of information.

    Again, I REALLY like this format. And I'm a benchmark junkie! :D
  • Mahomedsmith - Thursday, December 30, 2010 - link

    How to insert and design the board?
    <a href="http://southbeachjava.org/">South Beach Java</a>

Log in

Don't have an account? Sign up now