[Bloat] HardenedBSD implementation of CAKE

[Bloat] HardenedBSD implementation of CAKE

[Mark D.]

[-- Attachment #1: Type: text/plain, Size: 610 bytes --]

Hello all,
I am wondering if anyone is working on implementing fq_codel or CAKE on the
HardenedBSD network stack? A few popular firewall and router distributions
use this OS, and I believe that it would be beneficial for it to have AQM.
If this work has already been done, please point me to the documentation
for it. I loved what fq_codel was able to do on my OpenWRT flashed
off-the-shelf router, and I would love to be able to use it on my x86
OPNSense box. I am not a developer, but am a user that would love to
support both the CAKE project and the HardenedBSD project if possible.

Regards,
Mark Denkert

[-- Attachment #2: Type: text/html, Size: 692 bytes --]

Re: [Bloat] HardenedBSD implementation of CAKE

[Toke Høiland-Jørgensen]

"Mark D." <mark4931@gmail.com> writes:

> Hello all,
> I am wondering if anyone is working on implementing fq_codel or CAKE on the
> HardenedBSD network stack? A few popular firewall and router distributions
> use this OS, and I believe that it would be beneficial for it to have AQM.
> If this work has already been done, please point me to the documentation
> for it. I loved what fq_codel was able to do on my OpenWRT flashed
> off-the-shelf router, and I would love to be able to use it on my x86
> OPNSense box. I am not a developer, but am a user that would love to
> support both the CAKE project and the HardenedBSD project if possible.

Not aware of any effort in this direction. However, the code in the
Linux kernel is dual-licensed GPL/BSD so at least there should be no
licensing impediments to porting. I believe that is how fq_codel ended
up in BSD.

CAKE does rely on quite a few kernel internals, though, so it would take
someone with integral BSD kernel knowledge to port it to their
equivalents there; in that sense it's not a trivial project...

-Toke

Re: [Bloat] HardenedBSD implementation of CAKE

[Dave Taht]

to clarify fq_codel has been in freebsd for quite some time. I know
nothing about that bsd or other bsds, as soon as I saw a mbuf my brain
melted. But my hope would be it ports over to all the other bsds.

I would LOVE a cake dev (not me!) to partner up with a BSD dev or
three to port cake. It would take $ though. From somewhere.

cake is actually, in it's own way, more modular that fq_codel is, aside
from the nat hooks.  The 5 tuple hashing code can be leveraged from
BSD, as one example. My major doubting point about a port was the
resolution of the kernel clock. Linux has a high quality hirres clock,
BSDs didn't seem capable of scheduling on less than a 1ms tick at the
time I last paid attention.

but I could be wrong. Kept hoping that an implementation of packet
pacing would emerge from netflix's attempt to port BBR, at least.

Even more important in my mind for BSD is an implementation of BQL or
equivalent.

I think.

Even a version of cake without the integral shaper or BQL would be
interesting for bsd, and if someone could merely start the project,
well, who knows where it would lead... certainly I didn't know where
cake would end up when we started it, all I wanted was a faster
fq_codel....

On Tue, Feb 16, 2021 at 3:17 AM Toke Høiland-Jørgensen via Bloat
<bloat@lists.bufferbloat.net> wrote:
>
> "Mark D." <mark4931@gmail.com> writes:
>
> > Hello all,
> > I am wondering if anyone is working on implementing fq_codel or CAKE on the
> > HardenedBSD network stack? A few popular firewall and router distributions
> > use this OS, and I believe that it would be beneficial for it to have AQM.
> > If this work has already been done, please point me to the documentation
> > for it. I loved what fq_codel was able to do on my OpenWRT flashed
> > off-the-shelf router, and I would love to be able to use it on my x86
> > OPNSense box. I am not a developer, but am a user that would love to
> > support both the CAKE project and the HardenedBSD project if possible.
>
> Not aware of any effort in this direction. However, the code in the
> Linux kernel is dual-licensed GPL/BSD so at least there should be no
> licensing impediments to porting. I believe that is how fq_codel ended
> up in BSD.
>
> CAKE does rely on quite a few kernel internals, though, so it would take
> someone with integral BSD kernel knowledge to port it to their
> equivalents there; in that sense it's not a trivial project...
>
> -Toke
> _______________________________________________
> Bloat mailing list
> Bloat@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/bloat



-- 
"For a successful technology, reality must take precedence over public
relations, for Mother Nature cannot be fooled" - Richard Feynman

dave@taht.net <Dave Täht> CTO, TekLibre, LLC Tel: 1-831-435-0729

Re: [Bloat] HardenedBSD implementation of CAKE

[Jonathan Morton]

> On 2 Mar, 2021, at 2:59 am, Dave Taht <dave.taht@gmail.com> wrote:
> 
> My major doubting point about a port was the
> resolution of the kernel clock. Linux has a high quality hirres clock,
> BSDs didn't seem capable of scheduling on less than a 1ms tick at the
> time I last paid attention.

This is actually something Cake's shaper can already cope with.  I did some testing on an ancient PC that didn't have HPET hardware, so timer interrupts only had 1ms resolution even on Linux.  This merely results in small bursts of traffic at 1ms intervals, which collectively add up to the configured rate.

 - Jonathan Morton