On Fri, Mar 31, 2017 at 10:51 PM, Joe Touch <[email protected]> wrote:
>
>
> On 3/31/2017 4:30 PM, Jim Gettys wrote:
>
>
>
> On Fri, Mar 31, 2017 at 6:18 PM, Joe Touch <[email protected]> wrote:
>
>>
>>
>> On 3/31/2017 7:47 AM, Jim Gettys wrote:
>> > One full size packet @ 1mbps == 13 milliseconds.
>> That sort of blocking is its own problem and the only solution is to use
>> smaller packets.
>>
>> It can be solved at TCP by pushing the MSS down, but for UDP that's
>> another good reason for considering UDP options as a TSVWG WG item!
>>
>
> Yes, but without better packet scheduling such as fq_codel at the
> bottleneck, it won't help. But I'm decently optimistic that that
> fq_codel/cake/other things will be deploying widely, since we're seeing
> fq_codel appear in commercial products at this date.
>
>
> No amount of scheduling overcomes a limit on the unit of scheduling - the
> packet size, which has increasing impact as link bandwidth decreases.
>
> Better scheduling is important necessary too, but by itself insufficient.
>
Agree entirely. Both are necessary, and either by itself insufficient.
- Jim
>
>
> Joe
>
> _______________________________________________
> iccrg mailing list
> [email protected]
> https://www.irtf.org/mailman/listinfo/iccrg
>
>
