3

I'm working on compiling some information about network latency and designing tests to help our support folks troubleshoot problems. In order to do this, I need some basic information that I don't really have access to (and can't find via a Google search). I'm looking for the following specific numbers:

  • What is the maximum throughput across dark fiber that is leased?
  • What is the most common throughput across modern implementation of copper lines?
  • What technology do modern transoceanic lines use and are there any specific considerations to including them as part of a latency test?

Feel free to ask for clarification, I'm looking for hard numbers (specifically the mode or median) in order to better understand what to expect when looking at various client site numbers.

11

Signal travels roughly same speed in copper and fibre, copper being slightly faster. Fibre is determined by refractive index, typically speed being about 0.65c, i.e 200km per 1ms (single direction, not RTT).

Maximum theoretical throughput is hard to determine, maybedivide wavelengths to Planck length difference and light each up, so absurd amount. But in practice about 128 waves by 100G each in optical fibre.

For copper we're now doing 40G commercially, 100G will happen and is 400G the table. Obviously distances are very short.

  • 1
    Copper also as 40g commercially available if you think broader than cat6/7. Twinax or 'Direct Attached Copper' cables are widely used at those speeds, but they have a very short distance limitation (10m). – Kelly McDowell May 29 '13 at 19:22
  • Thanks Kelly. 40G is important and often ignored. Answer updated. – ytti May 29 '13 at 20:49
  • I'm pretty confused by this answer. You're saying that a signal will travel through copper at a faster speed than fiber? Can you please sight your source for this? – user3629081 Aug 9 '18 at 17:10
  • The optical wave propagation speed is the speed of light divided by the refractive index (ca. 1.48) -> ca. .68c. The electrical wave propagation speed is the speed of light divided by the square root of the dielectric constant for the material the wave passes through which includes the insulation -> ca. .65c for Cat5/6 and .75c for Cat7. Check en.wikipedia.org/wiki/Velocity_factor – Zac67 Aug 9 '18 at 18:13
4

In terms of maximum throughput through fibre there isn't really a limit you can put on it as it changes year by year.

If you use a DWDM device on the end of a piece of fibre you will get multitudes more throughput down a single strand compared to a single wavelength.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.