Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 26 Nov 2011 16:39:03 +0200
From:      Nikolay Denev <ndenev@gmail.com>
To:        freebsd-net@freebsd.org
Subject:   Re: Possible sge(4)/atphy(4) regression on RELENG_9?
Message-ID:  <D4802FF0-5AB3-4322-9AA5-271E15C00CD2@gmail.com>
In-Reply-To: <0DF73F37-3E46-4F7D-AA6B-B7EB2F2276AB@gmail.com>
References:  <C9E571B9-DD8E-40D7-A3D2-5D461E3ABB5B@gmail.com> <20111024175252.GB4663@michelle.cdnetworks.com> <0DF73F37-3E46-4F7D-AA6B-B7EB2F2276AB@gmail.com>

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

On Oct 24, 2011, at 9:18 PM, Nikolay Denev wrote:

>=20
> On Oct 24, 2011, at 8:52 PM, YongHyeon PYUN wrote:
>=20
>> On Mon, Oct 24, 2011 at 04:43:57PM +0300, Nikolay Denev wrote:
>>> Hello,
>>>=20
>>> I've recently upgraded a box running RELENG_8 to RELENG_9 and =
immediately I noticed much slower network connection.
>>> Running iperf shows about 20-30Mbits which was almost full GigE =
(~900Mbits) speed before.
>>>=20
>>> I'm noticing interface errors :
>>>=20
>>> [16:37]ndenev@nas:~% netstat -I sge0
>>> Name    Mtu Network       Address              Ipkts Ierrs Idrop    =
Opkts Oerrs  Coll
>>> sge0   1500 <Link#4>      00:0a:e4:86:62:fa 76114295 42197     0 =
103559806 10324     0
>>> sge0   1500 10.0.0.0      nas               76109575     -     - =
119109557     -     -
>>>=20
>>> Both the switch and the card show 1000 full-duplex.
>>> I've tried playing with rxcsum,txcsum,vlanhwtag,tso but disabling =
even all of them do not change anything.
>>> I've tried different switch port and changed the cable.
>>>=20
>>> Here is devinfo for my hardware :
>>>=20
>>> sge0 pnpinfo vendor=3D0x1039 device=3D0x0191 subvendor=3D0x103c =
subdevice=3D0x2a70 class=3D0x020000
>>> atphy0 pnpinfo oui=3D0xc82e model=3D0x1 rev=3D0x6 at phyno=3D0
>>>=20
>>> Of course all of this can mean hardware problem, I just want to ask =
if somebody is seeing something similar, since
>>> there are quite a lot minibus related changes as far as I can see.
>>>=20
>>> I'll boot RELENG_8 again tomorrow and do a quick test again to =
verify that this is not a hardware issue.
>>>=20
>>=20
>> I don't have sge(4) controller so it would be better to let us know
>> which revision introduced the regression.  Just looking over the
>> code change didn't reveal the possible cause.
>> BTW, I thought sge(4) shall use rgephy(4). Can you also verify
>> whether sge(4) in stable/8 also use atphy(4)?
>=20
> I've just checked my logs and I can confirm that it was atphy(4) even =
in stable/8.
>=20
> Sep 26 15:55:19 nas kernel: atphy0: <Atheros F1 10/100/1000 PHY> PHY 0 =
on miibus0
> Sep 26 15:55:19 nas kernel: atphy0:  none, 10baseT, 10baseT-FDX, =
100baseTX, 100baseTX-FDX, 1000baseT-FDX, 1000baseT-FDX-master, auto
>=20
> I'll post more info when I try again stable/8 on this hardware.
>=20
> Thanks!
>=20

Just for the sake of completeness I'm reporting that the problem turned =
out to be not hardware related.
The thread "TCP Reassembly Issues" in freebsd-stable list describes the =
issue.

Thanks.=



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?D4802FF0-5AB3-4322-9AA5-271E15C00CD2>