CAT 5e or CAT 6 cables for server gigabit speeds

Lately, we have been testing our server environment and setting up our Linux powered lab where all servers are connected to 1Gbps managed switches.

One of the first tests we had was testing Ethernet cables – CAT 5e and CAT 6 category cables. CAT 6 is the standard for Gigabit Ethernet and backward compatible with CAT 5 and CAT 5e. CAT 6 provides performance of up to 250 Mhz.

In our tests we will review data transfers between two servers each connected to 1Gbps switch. Our maximum data throughput for these boxes are at around 350Mbps due to network card drivers, depending how we tune network stack and MTU size. You should not pay attention to the maximum bandwidth throughput, but the bandwidth difference between CAT 5e and CAT 6 cables.

CAT 6 cable:
————————————————————
Server listening on TCP port 5001
TCP window size: 260 KByte (WARNING: requested 130 KByte)
————————————————————
[ 4] local 192.168.3.10 port 5001 connected with 192.168.3.20 port 38899
[ 4] 0.0- 1.0 sec 37.6 MBytes 315 Mbits/sec
[ 4] 1.0- 2.0 sec 37.6 MBytes 315 Mbits/sec
[ 4] 2.0- 3.0 sec 37.6 MBytes 315 Mbits/sec
[ 4] 3.0- 4.0 sec 37.6 MBytes 315 Mbits/sec
[ 4] 4.0- 5.0 sec 37.6 MBytes 315 Mbits/sec
[ 4] 5.0- 6.0 sec 37.6 MBytes 315 Mbits/sec
[ 4] 6.0- 7.0 sec 37.6 MBytes 315 Mbits/sec
[ 4] 7.0- 8.0 sec 37.6 MBytes 315 Mbits/sec
[ 4] 8.0- 9.0 sec 37.6 MBytes 315 Mbits/sec
[ 4] 9.0-10.0 sec 37.6 MBytes 315 Mbits/sec
[ 4] 0.0-10.0 sec 376 MBytes 315 Mbits/sec

CAT 5e cable:

————————————————————
Server listening on TCP port 5001
TCP window size: 260 KByte (WARNING: requested 130 KByte)
————————————————————
[ 4] local 192.168.3.10 port 5001 connected with 192.168.3.20 port 4192
[ 4] 0.0- 1.0 sec 37.5 MBytes 315 Mbits/sec
[ 4] 1.0- 2.0 sec 37.5 MBytes 315 Mbits/sec
[ 4] 2.0- 3.0 sec 37.5 MBytes 315 Mbits/sec
[ 4] 3.0- 4.0 sec 37.5 MBytes 315 Mbits/sec
[ 4] 4.0- 5.0 sec 37.5 MBytes 315 Mbits/sec
[ 4] 5.0- 6.0 sec 37.5 MBytes 315 Mbits/sec
[ 4] 6.0- 7.0 sec 37.5 MBytes 315 Mbits/sec
[ 4] 7.0- 8.0 sec 37.5 MBytes 315 Mbits/sec
[ 4] 8.0- 9.0 sec 37.5 MBytes 315 Mbits/sec
[ 4] 9.0-10.0 sec 37.5 MBytes 315 Mbits/sec
[ 4] 0.0-10.0 sec 376 MBytes 315 Mbits/sec

There is no real difference – the speed is the same 315 MBits/sec using CAT 5e or CAT 6 cables.

We tested bandwidth throughput using iperf and CAT 6 cable length was 1.6m (5.24 feet) and CAT 5e cable was 0.6m (1.96 feet). In the future, we will try a few tests more, but we need to get better NIC cards with better drivers for much higher throughput.


Comments

  1. Kai says:

    The test architecture was as follows:

    Server1 -> Switch -> Server2

  2. Etherealmind says:

    Your cables will not impact your testing at this level. The extra spectral bandwidth provided by Cat6 is not relevant to Ethernet throughput since it is defined at Layer 2 of the OSI model, and cabling will only be relevant at Layer 1.

    Unless you have a poor electrical environment, in which case, Cat6 is more likely to sustain throughput.

  3. Gunnar says:

    People tend to forget research – the gigabit standard is based on the cat5e cabeling std, all network cards supporting Gbit are therefore also based on this.

    I agree that cat6 may give you better margines in the signaling scheme (osi level 1) but that makes a difference only when you have a sloppy installation

    since an installation of cat5e should include a test protocol – just like cat6, one might ask, why accept a sloppy installation?

    I find it more interesting comparing the physical comparison:
    cat6 cabeling often includes a plastic core and has a minimum bend radius of 5 – 10 cm ( 2 – 4 inches) -depending on brand

    cat5e cabeling has a more reasonable bend radius 1-2 inches

    pls visualize which std is easiest to install correctly

  4. aj says:

    Previous comments are true, but even still, would you not want to use cables that are much, much longer. No way you can get recordable results to compare with a 5ft cable.

    Seriously though, good luck with you trials and learning. It’s fun.

  5. Jason says:

    yes, at least 90m Ethernet cables should be tested with cat5e and cat6e connectors. etc. cannot do tests like that.

  6. Steve says:

    Quote:CAT 6 cable length was 1.6m (5.24 feet) and CAT 5e cable was 0.6m (1.96 feet)?
    —————————————————————————
    In that short distance, there wil not be any big difference between Cat 4 and Cat 6 either. Try to test100 feet and give us a conclusion. :)

  7. arash says:

    cat6 is better than cat 5

  8. trolley says:

    cat 6 >> cat 5 for so many reasons that I am not going to mention.

  9. Jeff says:

    I would suggest testing with a 100 meter (300) foot cable also BUNDLED with some other cables also running dummy test transmissions, this test crosstalk. The crosstalk is another factor of Cat5e vs Cat6. Also try running the long cable run over some florescent light fixtures or parallel to electrical wire (simulating a “bad” installation).

  10. Andy says:

    I am having difficulty making my own cables from “Cat 6e” cable and “cat 6” RJ45 plugs. They will NOT run at gigabit speed! This is true of our short cables and long cables – we seem to have narrowed it down to the plugs, but there is no visible difference between these and the ones that are on the pre-made cables (which do run at a gig). I tried forcing Gigabit in the NIC driver config, and that just drops out. Best my cables can get is 100Mbps full duplex.

    First of all, could it be the crimping tool we are using?
    Secondly, has anyone else experienced such problems?
    Thirdly, if anyone has, how did you get around it?

    Many thanks in anticipation of any helpful responses!

  11. Kene says:

    There are 2 distinct plugs that you can get. Make sure the cat6 plugs you’re using match the conductor type of the cable. Plugs made for stranded conductors pierce the conductor jacket with a straight pins, whereas a plug made for solid conductors have the pins slighlty bent to “hug” the conductor.

  12. a raccoon says:

    Hmm.

    So you’re going to compare a Ford Focus to a Ferrari Enzo and say both are just as fast, because you only drive the speed limit?

    So you’re going to compare a Ford Focus to a Jeep Wrangler and say they can both handle the same extreme terrain, but you never take them off-roading?

    So you’re going to compare a Ford Focus to a Tanker Truck and say they can both drive the same distance without refueling, but you only take a spin around the block?

    So you’re going to compare a Ford Focus to an Armored Truck and say they are both as strong, but never attempt to fire a gun at either?

    Cat6 beats out Cat5/e in speed, environment, distance and mechanical strength. Your test only demonstrates that Cat6 is backward compatible with Cat5/e.

  13. Tom Massey says:

    a raccoon is somewhat correct. The Cat5e and the Cat6 are both carrying the maximum 315Mbits/sec that the undersized and underperforming 350MBps network cards will push. But I can’t see anywhere that shows we should expect a Cat6 cable to carry 10X more data than a Cat5e, as some people seem to believe. Better shielding. What else?

Leave a Reply