RE: Issues concerning 10GbE speed standards
- To: ka@xxxxxxxxxxxxxxxxxxx, "Chang, Edward S" <Edward.Chang@xxxxxxxxxx>, stds-802-3-hssg@xxxxxxxx
- Subject: RE: Issues concerning 10GbE speed standards
- From: "Chang, Edward S" <Edward.Chang@xxxxxxxxxx>
- Date: Tue, 29 Jun 1999 14:24:37 -0400
- Sender: owner-stds-802-3-hssg@xxxxxxxxxxxxxxxxxx
That is the definition of BER without subtracting the corrected errors. One
has to count all errors include corrected. This is the definition of
measuring the reliability of a link.
A week link can add as many error corrections for their users to make it
more reliable -- no one will prevent you from doing that, but that has
nothing to do with BER definition.
From: ka@xxxxxxxxxxxxxxxxxxx [mailto:ka@xxxxxxxxxxxxxxxxxxx]
Sent: Tuesday, June 29, 1999 1:38 PM
To: Edward.Chang@xxxxxxxxxx; stds-802-3-hssg@xxxxxxxx
Subject: RE: Issues concerning 10GbE speed standards
> Thanks for very elaborated explanation related to FEC with which I am not
> quite familiar.
> From you description, quote: " FEC codes are meant for error correction
> only"; therefore, FEC is one of the error correction scheme.
> Usually, the bit error rate is defined without error corrections. The
> purpose of BER is to measure the reliability of the over-all link, which
> should not subtract the errors corrected by the error-correction-codes.
Why is this a requirement to achieve BER without FEC ? Do you mean this a
common practice among vendors or do you mean this is specified in some
WAN standard ?
PHY standards define a BER. A PHY standard should not specify by what means
vendor A or B achieve that spec. If vendor A decides to meet the BER
objective by using error correction, that should be allowed by the standard.
Now vendor B may prefer not to use FEC, and achieve BER without FEC, that's
fine too. It's probably a good thing to have provision for FEC.
I would like to add that when you decode parity bits (if you decide to
do so), you get directly a measurement of the input BER or link quality
(before error correction). If this is an important parameter for WAN
applications, an estimated link quality could be made available at the
output of the decoder at no extra cost. If I understand well your
comment, you are suggesting that link quality (without error correction)
should be made available to the user. That's possible.
> However, users can chose to correct the errors -- one error, or multiple
> errors-- based on the reliability measure, BER, supplied by vendors and
> requirement of the application to implement error corrections. Error
> correction is not free, which will use valuable resources. For very
> unreliable tapes or disks, error correction is a requirement, however for
> well designed semiconductor memory, error correction is not required.
I agree, error correction is not free, say it costs X kgates. It is up
to the system designers then to decide, in which applications (if any)
the overall system cost can be decreased by using error correction.
> The reason I also elaborate the issue is that BER is measured without
> corrections. Error correction can not be used to claim the BER is
> Otherwise, we will not have the universal referencing point in discussing
> the reliability of a link based on BER.
I think my above comment was probably addressing this comment. Error
correction does not prevent from having a measurement of link quality
before error correction. In many schemes you directly get the number
of errors at the input of the FEC decoder, and this measurement can
be made available to the user. Hope I understood and answered your