Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 25 Oct 2015 20:37:37 +0100
From:      Kristof Provost <kp@FreeBSD.org>
To:        James Lodge <James@Lodge.me.uk>
Cc:        "freebsd-net@freebsd.org" <freebsd-net@freebsd.org>
Subject:   Re: Jail - PF - NAT - Network Performance
Message-ID:  <BB154E57-A6B2-49D7-9EEA-8AEAE1134C75@FreeBSD.org>
In-Reply-To: <VI1PR06MB10378E0DC73518F6A4571531F9240@VI1PR06MB1037.eurprd06.prod.outlook.com>
References:  <VI1PR06MB1037187D07A9C500B3E4E791F9240@VI1PR06MB1037.eurprd06.prod.outlook.com> <DF61454E-408E-432F-8822-39353632CA90@FreeBSD.org> <VI1PR06MB10378E0DC73518F6A4571531F9240@VI1PR06MB1037.eurprd06.prod.outlook.com>

next in thread | previous in thread | raw e-mail | index | archive | help

> On 25 Oct 2015, at 18:47, James Lodge <James@Lodge.me.uk> wrote:
>=20
>> On 25 Oct 2015, at 17:46, James Lodge <James@Lodge.me.uk> wrote:
>> I currently have a FreeBSD 10.1 host running on Digital Ocean. I have =
multiple jails and I'm not using vimage.
>>=20
>>=20
>> I'm using PF on the host to NAT traffic from said jails and all is =
working as expected. I have a jail running OpenVPN and clients can =
connect and traffic is routed to the Internet down the tunnel via =
PF/NAT. The issue I'm seeing is download speeds to the client from the =
Internet on the external side on PF. Upload always seem reasonable, but =
download is always woeful. I'm using a Windows machine as the client if =
that make any odds.
>>=20
>> Yeah, there=92s an issue with checksums and pf/Xen.
>> Disabling TSO should work for you (sudo sysctl net.inet.tcp.tso=3D0), =
and the problem should be completely fixed in the >next release (10.3 or =
11.0)
>>=20
>> Regards,
>> Kristof
>=20
>=20
> Thanks Kristof for the quick reply,
>=20
> I was hoping it would be that simple, but Digital Ocean use KVM (from =
what I know) as their hypervisor so disabling TSO and LRO seems to have =
no noticed increase in performance.=20
>=20
Can you run a tcpdump while you=92re seeing the problem?
The issue I know about is related to the TCP checksum, so I=92d expect =
to see many invalid checksums.

Regards,
Kristof




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?BB154E57-A6B2-49D7-9EEA-8AEAE1134C75>