Ethernet Performance

The current motherboard test suite includes LAN performance measurements. All of these boards utilize PCI Express controllers with the only difference being the supplier of the core logic.

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 nForce4 Ultra motherboards.

We set up one machine as the server; in this case, an Intel box with an Intel CSA Gigabit LAN connection. Intel CSA has a reputation for providing fast throughput and seemed a reasonable choice to serve our Gigabit LAN clients.

At the server side, we used the following Command Line as suggested by the VIA whitepaper on LAN testing:
Ntttcps - m 4,0, -a 4 - l 256000 - n 30000
On the client side (the motherboard under test), we used the following Command Line:
Ntttcpr - m 4,0, -a 4 - l 256000 - n 30000
At the conclusion of the test, we captured the throughput and CPU utilization figures from the client screen.

Ethernet Throughput

Ethernet Throughput

The Agere ET1310 and NVIDIA on-chip PCI Express LAN solutions exhibit slightly higher throughput, but their CPU utilization is slightly more than the PCI Express Broadcom solution on the Gigabyte and Foxconn boards. The Marvell 88E8053 options on the Epox and Asus boards offer excellent throughput, but at the price of having almost double the CPU utilization of the other solutions. The additional PCI-only Broadcom solution on the Foxconn board exhibits lower throughput and higher CPU utilization than the PCI Express solutions.

All standard Ethernet tests were performed with standard frames and the NVIDIA Active Armor suite disabled unless otherwise noted. Gigabit Ethernet supports Jumbo frames as well and can provide a further reduction in CPU overhead.

Firewire and USB Performance Audio Performance
Comments Locked

26 Comments

View All Comments

  • Houdani - Tuesday, November 15, 2005 - link

    The other reviewers here at Anandtech offer their own style, thereby providing the "mix it up" factor. I personally don't think you need to adjust your style, as I happen to like the cultural infusion supplied by your literary quotes.
  • Furen - Tuesday, November 15, 2005 - link

    Fair enough, I was just giving my personal opinion on the matter.
  • bersl2 - Tuesday, November 15, 2005 - link

    What's wrong with being exposed to what the author believes to be wisdom? Surely you don't read these articles simply for the technical specifications; otherwise, you would read the spec sheet. Why, then, do you object to the author trying to relate an idea to you?
  • Furen - Tuesday, November 15, 2005 - link

    I read the articles for their technical merits. Spec sheets do not show how the different components interact with one another nor can they show performance, stability, etc; and, most importantly of all, they're made by the manufacturer, who is hardly to be considered an unbiased source. The problem with throwing a strong idea in front of the reader before giving him article is that this idea becomes the filter through which the rest of the article is viewed. This is, of course, very effective if you are trying to persuade the user to reach the same conclusions as you, but it skews the reader's ability to analize the purely technical merits of the products.
  • mbhame - Tuesday, November 15, 2005 - link

    What makes you so sure Conroe is the last P4? ;)
    quote:

    The Pentium 4 will never die!
    Long Live the Pentium 4!!!
  • JarredWalton - Tuesday, November 15, 2005 - link

    Conroe isn't a P4. It's the next generation architecture that Intel has not yet named - also referred to as the NGATIHNYN. :p

Log in

Don't have an account? Sign up now