nanog mailing list archives
Re: Forward Erasure Correction (FEC) and network performance
From: Matthew Kaufman <matthew () eeph com>
Date: Fri, 10 Apr 2009 11:47:25 -0700
Lamar Owen wrote:
On Friday 10 April 2009 13:43:26 Matthew Kaufman wrote:The bit error rate of copper is better than 1 error in 10^9 bits. The bit error rate of fiber is better than 1 error in 10^12 bits. So the packet loss rate of the transport media is approximately zero.*This sounds pretty good, until you realize that it means you can expect 36 errors in 10 hours on a 100% utilized gigabit fiber link.
That *still* sounds good to me. There's a reason reliable transport protocols work the way they do... and integrity protection better than simple checksums is well-understood these days as well.
Matthew Kaufman
Current thread:
- Forward Erasure Correction (FEC) and network performance Marshall Eubanks (Apr 10)
- Re: Forward Erasure Correction (FEC) and network performance Patrick W. Gilmore (Apr 10)
- Re: Forward Erasure Correction (FEC) and network performance Mikael Abrahamsson (Apr 10)
- [SPAM] Re: Forward Erasure Correction (FEC) and network performance Jean-Michel Planche (Apr 10)
- Re: Forward Erasure Correction (FEC) and network performance Matthew Kaufman (Apr 10)
- Re: Forward Erasure Correction (FEC) and network performance Lamar Owen (Apr 10)
- Re: Forward Erasure Correction (FEC) and network performance Matthew Kaufman (Apr 10)
- Re: Forward Erasure Correction (FEC) and network performance Mikael Abrahamsson (Apr 10)
- Re: Forward Erasure Correction (FEC) and network performance Lamar Owen (Apr 10)