Excellent, thanks: I had forgotten the &@%^#$##!$!!!!! pass-through
switch that we had a few years ago, that didn't have enough buffer and
threw a jam signal whenever it got busy.

--dave

On 01/17/2014 07:44 PM, Joe Touch wrote:
>
>
> On 1/17/2014 3:51 PM, David Collier-Brown wrote:
>> I'm going to suggest that these are queues and associated physical
>> buffers that do two things:
>>
>>  1. hold packets that arrive at a bottleneck for a long as it takes to
>>     send them out a slower link that they came in on, and
>>  2. hold bursts of packets that arrive adjacent to each other until they
>>     can be sent out in a normal spacing, with some small amount of time
>>     between them
>
> That's one thing:
>
>     hold packets that have already arrived until they can depart
>
> If you're talking about rate changes, then the queue might absorb a
> burst of packets then emit them, i.e., you need a queue that can
> handle several packets.
>
> If you're taking about scheduling, then a queue might need as little
> as one packet to adjust the outgoing time based on the incoming time.
>
> However, they're both queues, and they both absorb "bursts" (in the
> latter case, it's a 'burst' of 1 that needs to wait until a scheduled
> slot is available).
>
> Joe
> _______________________________________________
> aqm mailing list
> [email protected]
> https://www.ietf.org/mailman/listinfo/aqm
>


-- 
David Collier-Brown,         | Always do right. This will gratify
System Programmer and Author | some people and astonish the rest
[email protected]           |                      -- Mark Twain
(416) 223-8968

_______________________________________________
aqm mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/aqm

Reply via email to