Re: [Rpm] [Bloat] Relentless congestion control for testing purposes

[Dave Taht <dave.taht@gmail.com>]

On Mon, Oct 4, 2021 at 3:45 PM Matt Mathis via Rpm
<rpm@lists.bufferbloat.net> wrote:
>
> Please don't send this upstream.   It would makesTCP into the evil transport from hell.

You mean it isn't already? :)

There are a lot of test tools in the world (like pktgen) that are
designed to do evil things to the network,
why not evilTCP(tm)? Too many tools synthesize evil one way traffic
and people draw incorrect conclusions
from those....

>  Modern loss recovery is robust enough to run hardcoded cwnd=<blat> and persistent losses, Please don't make this too easy for people who are intent on getting their "fair" share of the network before the greedy people.
>
> Dave overlooked an important detail in relentless TCP:

It had been a while, and it was intended to be a complex point. But
thx for the correction.

>It reduced the window by exactly the losses, such that the presented load was exactly the quantity of data successfully delivered on the previous RTT.   I have forgotten the details of the increase function, but it was something Reno like but only on loss less RTTs.

What I was looking for was a test tool that mimicked enough of tcp's
coupled ack behavior to give more predictable results, when
looking for expected behavior from an AQM (or policer). What I had
been using before was a udp flood, but that was dicy (and very
misleading) on non-duplex wireless.

That, and a small nuclear reactor so I'd never have to put more diesel
in my (still broken) boat.

>
>
> If you want to adapt TCP
> Thanks,
> --MM--
> The best way to predict the future is to create it.  - Alan Kay
>
> We must not tolerate intolerance;
>        however our response must be carefully measured:
>             too strong would be hypocritical and risks spiraling out of control;
>             too weak risks being mistaken for tacit approval.
>
>
> On Fri, Oct 1, 2021 at 11:02 AM Luigi Rizzo via Rpm <rpm@lists.bufferbloat.net> wrote:
>>
>> On Fri, Oct 1, 2021 at 6:33 PM Bob McMahon <bob.mcmahon@broadcom.com> wrote:
>> >
>> > hmm, this looks interesting to a test & measurement guy. Can it be done with a setsockopt? I might want to add this as an iperf2 option, particularly if it's broadly available,
>>
>>
>> I would be happy to submit it as one or two upstream patches --
>> perhaps one to implement
>> the basic "ignore_holes" + setsockopt(), and another mechanism (if
>> there isn't one
>> already) to override defaults sockopts on certain sockets.
>>
>> I do think we need more readily available testing tool,
>>
>> cheers
>> luigi
>> _______________________________________________
>> Rpm mailing list
>> Rpm@lists.bufferbloat.net
>> https://lists.bufferbloat.net/listinfo/rpm
>
> _______________________________________________
> Rpm mailing list
> Rpm@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/rpm



-- 
Fixing Starlink's Latencies: https://www.youtube.com/watch?v=c9gLo6Xrwgw

Dave Täht CEO, TekLibre, LLC