[Bloat] RED 13 years later

[Bloat] RED 13 years later

[Dave Taht]

And I still have never seen anyone give me a packet capture of juniper
or cisco´s red
implementation.

https://lkml.kernel.org/netdev/CAA93jw7wAL75pVrB-q+xGAcpQtiZz4iVW0Z2W9E8VGSyUFOo-w@mail.gmail.com/

-- 
40 years of net history, a couple songs:
https://www.youtube.com/watch?v=D9RGX6QFm5E
Dave Täht CSO, LibreQos

Re: [Bloat] RED 13 years later

[Kenneth Porter]

I didn't know what RED was and had to look it up. For others new to the 
lingo:

https://en.wikipedia.org/wiki/Random_early_detection

Re: [Bloat] RED 13 years later

[Kathleen Nichols]

A big issue is that "average queue length" was and is a terrible 
indicator of congestion. But I think the first "bug" Van was referring 
to was the original RED "control law" - I asked him why he thought it 
would work as it really ends up looking like a step function which your 
first control theory course will show is rather primitive. The thing is, 
that TCP is really robust and almost anything will "work" on long-lived 
TCP connections. Which is what everyone used for testing.

On 2/10/24 9:10 AM, Kenneth Porter via Bloat wrote:
> I didn't know what RED was and had to look it up. For others new to the 
> lingo:
> 
> https://en.wikipedia.org/wiki/Random_early_detection
> 
> 
> _______________________________________________
> Bloat mailing list
> Bloat@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/bloat