Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 1 Feb 2023 15:29:37 -0500
From:      Paul Mather <paul@gromit.dlib.vt.edu>
To:        David <2yt@gmx.com>
Cc:        freebsd-stable@freebsd.org
Subject:   Re: Slow WAN traffic to FreeBSD hosts but not to Linux hosts---how to debug/fix?
Message-ID:  <31816EF8-7516-45F9-8584-A649F0011E3D@gromit.dlib.vt.edu>
In-Reply-To: <f4f2dfa5-92fd-91be-8f7d-b4aa13683ac3@gmx.com>
References:  <95EDCFCA-7E3F-458F-85A6-856D606B9D98@gromit.dlib.vt.edu> <4ed8b724-041f-f561-ae60-ab966aefbb68@plan-b.pwste.edu.pl> <282AF730-E5E0-4A50-9F47-E7301B36E5C8@gromit.dlib.vt.edu> <2ed582b9-b544-74bb-2047-99d04924b46b@plan-b.pwste.edu.pl> <f4f2dfa5-92fd-91be-8f7d-b4aa13683ac3@gmx.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Jan 31, 2023, at 9:46 PM, David <2yt@gmx.com> wrote:

> On 1/31/23 13:38, Marek Zarychta wrote:
>> W dniu 31.01.2023 o 19:31, Paul Mather pisze:
>>>> While playing with different mod_cc(4) might bring some =
improvement, to get a real boost I'd suggest enabling tcp_rack(4) if =
feasible.
>>>=20
>>> I am interested in trying this out, but believe it is more feasible =
in my case for the -STABLE and -CURRENT systems I am using, not so much =
for the -RELEASE systems that are kept up to date via binary =
freebsd-update updates.  My reading of the tcp_rack(4) man page is that =
you have to build a custom kernel as, unlike the cc_* congestion control =
algorithms, the loadable tcp_rack module is not built by default.  Is =
that an accurate reading?
>>>=20
>> Yes, this gift from Netflix is probably better suited for -STABLE and =
-CURRENT as easier to set up there. There is an excellent, up-to-date =
article about it by Klara Systems writers[1]. =46rom my experience =
tcp_rack(4) is well suited for congested, lossy or redundant network =
paths where loses, duplicated packets or races between packets occur. =
Not a panacea, but very performant TCP stack based on the _fair_ =
algorithm. In some instances, it might help you to saturate the =
bandwidth of the link. TCP algo can be loaded/unloaded/changed on the =
fly. In FreeBSD 14-CURRENT you can change it on an active socket with =
tcpsso(8) utility, in FreeBSD 12 and 13 you have to restart the app =
bound to the socket.
>> Please feel free to play with TCP stacks and congestion algos with =
the help of benchmarks/iperf3 to find out what prevents the link from =
being saturated and give us some feedback here.
>> [1] =
https://klarasystems.com/articles/using-the-freebsd-rack-tcp-stack/
>> Cheers
>=20
> I compiled a custom kernel (releng/13.1) and followed Klara Systems =
instructions. The results are quite good. I would hope the RACK stack =
will be included in the upcoming 13.2 release as it is a significant =
upgrade.


I heartily concur with this.  It would be very nice if the extra TCP =
stacks were available and able to be loaded in the upcoming 13.2 =
release.

As I mentioned recently in this thread, I built and enabled the extra =
TCP stacks on a -CURRENT system and got much better performance than =
with the default "freebsd" stack.  I've just done the same on a =
13-STABLE system and get the same result.  Using the tcp_bbr stack =
appears to solve the problem I was having.

It would be great if the TCPHPTS and RATELIMIT options could be added to =
the GENERIC kernel and WITH_EXTRA_TCP_STACKS default to enabled for =
building in src.conf.  That way, the tcp_rack and tcp_bbr modules would =
get built by default and people would have the option of loading them on =
-RELEASE systems without having to build their own kernel when doing =
updates via freebsd-update.

Cheers,

Paul.




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?31816EF8-7516-45F9-8584-A649F0011E3D>