Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 28 Apr 2011 18:47:49 -0400
From:      Adam Stylinski <kungfujesus06@gmail.com>
To:        Jack Vogel <jfvogel@gmail.com>
Cc:        freebsd-net@freebsd.org
Subject:   Re: em0 performance subpar
Message-ID:  <20110428224749.GA47010@freebsdbox.adamsnet>
In-Reply-To: <BANLkTikLb7k36mN3ktRGdm4mQyehHB-ONg@mail.gmail.com>
References:  <20110428141339.GD2800@ossumpossum.geop.uc.edu> <EE019B72D65E417BABD7022E4DF10357@multiplay.co.uk> <20110428144513.GF2800@ossumpossum.geop.uc.edu> <41EE7AB832F24194AC8730544E1C2EB7@multiplay.co.uk> <20110428152141.GA19362@ossumpossum.geop.uc.edu> <11659E32824B4B1E91B6B219BDEF1234@multiplay.co.uk> <20110428160919.GE19362@ossumpossum.geop.uc.edu> <BANLkTimRcAdO33AasTOMb%2BLSOjc1GwFe%2Bg@mail.gmail.com> <20110428180037.GA1889@zephyr.snd-wireless.uc.edu> <BANLkTikLb7k36mN3ktRGdm4mQyehHB-ONg@mail.gmail.com>

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

--LQksG6bCIzRHxTLp
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On Thu, Apr 28, 2011 at 02:22:29PM -0700, Jack Vogel wrote:
> My validation engineer set things up on an 8.2 REL system, testing the
> equivalent of
> HEAD, and he reports performance is fine. This is without any tweaks from
> what's
> checked in.
>=20
> Increasing the descriptors to 4K is way overkill and might actually cause
> problems,
> go back to default.
>=20
> He has a Linux test client, what are you transmitting to?
>=20
> Jack
>=20
>=20
> On Thu, Apr 28, 2011 at 11:00 AM, Adam Stylinski <kungfujesus06@gmail.com=
>wrote:
>=20
> > On Thu, Apr 28, 2011 at 09:52:14AM -0700, Jack Vogel wrote:
> > > Adam,
> > >
> > > The TX ring for the legacy driver is small right now compared to em, =
try
> > > this experiment,
> > > edit if_lem.c, search for "lem_txd" and change EM_DEFAULT_TXD to 1024,
> > see
> > > what
> > > that does, then 2048.
> > >
> > > My real strategy with the legacy code was that it should stable, mean=
ing
> > not
> > > getting
> > > a lot of changes... that really hasn't worked out over time. I suppose
> > I'll
> > > have to try and
> > > give it some tweaks and let you try it. The problem with this code is=
 it
> > > technically supports
> > > a huge range of old stuff we don't test any more, things I do might c=
ause
> > > other regressions :(
> > >
> > > Oh well, let me know if increasing the TX descriptors helps.
> > >
> > > Jack
> > Jack,
> >
> > Is this the same thing as adjusting these values?:
> >
> > hw.em.rxd=3D4096
> > hw.em.txd=3D4096
> >
> > If so I've maxed this out and it's not helping.  I'll give it a shot on=
 my
> > 8-STABLE box as it has a kernel I can play with.
> >
> > Setting the MTU to 1500 gave lower throughput.
> >
> > --
> > Adam Stylinski
> > PGP Key: http://pohl.ececs.uc.edu/~adam/publickey.pub
> > Blog: http://technicallyliving.blogspot.com
> >

I am transmitting to a linux client (kernel 2.6.38, 9000 byte MTU, PCI-Ex b=
ased card).  My sysctl's on the Linux client (apart from the default) look =
like so:

net.ipv4.ip_forward =3D 0
# Enables source route verification
net.ipv4.conf.default.rp_filter =3D 1
# Enable reverse path
net.ipv4.conf.all.rp_filter =3D 1
net.core.rmem_max =3D 16777216
net.core.wmem_max =3D 16777216
net.ipv4.tcp_rmem =3D 4096 87380 16777216
net.ipv4.tcp_wmem =3D 4096 87380 16777216
net.core.wmem_default =3D 87380
net.core.rmem_default =3D 87380
net.ipv4.tcp_mem =3D 98304 131072 196608
net.ipv4.tcp_no_metrics_save =3D 1
net.ipv4.tcp_window_scaling =3D 1
dev.rtc.max-user-freq =3D 1024

The exact troublesome device (as reported by pciconf):=20

em0@pci0:7:5:0: class=3D0x020000 card=3D0x13768086 chip=3D0x107c8086 rev=3D=
0x05 hdr=3D0x00
    vendor     =3D 'Intel Corporation'
    device     =3D 'Gigabit Ethernet Controller (Copper) rev 5 (82541PI)'
    class      =3D network
    subclass   =3D ethernet
Apart from bus saturation (which I don't suspect is the problem) I'm not su=
re what the issue could be.  What should I try next?

--=20
Adam Stylinski
PGP Key: http://pohl.ececs.uc.edu/~adam/publickey.pub
Blog: http://technicallyliving.blogspot.com

--LQksG6bCIzRHxTLp
Content-Type: application/pgp-signature

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.17 (FreeBSD)
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=LzTp
-----END PGP SIGNATURE-----

--LQksG6bCIzRHxTLp--



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20110428224749.GA47010>