Thread Links Date Links
Thread Prev Thread Next Thread Index Date Prev Date Next Date Index

Re: [RE] Overprovisioning (was Re: [RE] CE applications)



Henry,

I agree. If the objective is as you describe, we've got some network
engineering to do.

Although I am an engineer and I am anxious to get to work on a solution, I
think we should be sure our technical objective is driven by application
requirements. I would like to review the applications that have imposed this
objective on us.

Kevin

-----Original Message-----
From: owner-stds-802-3-re@IEEE.ORG [mailto:owner-stds-802-3-re@IEEE.ORG] On
Behalf Of Henry Sariowan
Sent: Wednesday, September 01, 2004 12:09 PM
To: STDS-802-3-RE@listserv.ieee.org
Subject: Re: [RE] Overprovisioning (was Re: [RE] CE applications)

Things are different, if the objective of Residential Ethernet include
(as I mentioned before)
        - constant, sub-millisecond latency for real-time traffic
        - zero jitter for real-time traffic
        - zero packet loss for real-time traffic

Such objectives will be very difficult, if not impossible, to achieve
with only a combination of admission control, ingress traffic/rate
shaping, and priority queuing.  I think this group need to highlight
these objectives in order to justify works for enhancement of layer 2
protocols by some iso/sync-chronous schemes.

Henry