Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 12 Oct 2006 10:38:54 +0200
From:      Danny Braniss <danny@cs.huji.ac.il>
To:        Mike Tancsa <mike@sentex.net>
Cc:        freebsd-net@freebsd.org
Subject:   Re: em blues 
Message-ID:  <E1GXw5e-000O7H-ID@cs1.cs.huji.ac.il>
In-Reply-To: <il5qi256p6ks5dl9kks4hd4u00kekrtokn@4ax.com> 
References:  <E1GXeiv-0007hw-4u@cs1.cs.huji.ac.il> <il5qi256p6ks5dl9kks4hd4u00kekrtokn@4ax.com>

next in thread | previous in thread | raw e-mail | index | archive | help
> On Wed, 11 Oct 2006 16:06:17 +0200, in sentex.lists.freebsd.net you
> wrote:
>=20
>=20
>the box is a bit old (Intel Pentium III (933.07-MHz 686-class CPU)
>=20
>dual cpu.
>=20
>
>
>running iperf -c (receiving):
>freebsd-4.10	0.0-10.0 sec    936 MBytes    785 Mbits/sec
>freebsd-5.4	0.0-10.0 sec    413 MBytes    346 Mbits/sec
>freebsd.6.1	0.0-10.0 sec    366 MBytes    307 Mbits/sec
>freebsd-6.2	0.0-10.0 sec    344 MBytes    289 Mbits/sec
>
>btw, iperf -s (xmitting) is slightly better
>freebsd-4.10	0.0-10.0 sec    664 MBytes    558 Mbits/sec
>freebsd-5.4	0.0-10.0 sec    390 MBytes    327 Mbits/sec
>freebsd-6.1	0.0-10.0 sec    495 MBytes    415 Mbits/sec
>freebsd-6.2	0.0-10.0 sec    487 MBytes    408 Mbits/sec
>so, it seems that as the release number increases, the em
>throughput gets worse - or iperf is.
>
> Hi,
> 	What is your setup for testing ?  For me, with a couple of em
> NICs back to back I get
>  iperf -c 1.1.1.2
> ------------------------------------------------------------
> Client connecting to 1.1.1.2, TCP port 5001
> TCP window size: 32.5 KByte (default)
> ------------------------------------------------------------
> =5B  3=5D local 1.1.1.1 port 57584 connected with 1.1.1.2 port 5001
> =5B  3=5D  0.0-10.0 sec  1.06 GBytes    914 Mbits/sec
>=20
> 6.2-PRERELEASE FreeBSD 6.2-PRERELEASE =230: Mon Oct  9 23:22:10 EDT 200=
6
>=20
> One is a Pentium(R) 4 CPU 3.00GHz and the other an AMD 3800 X2
>=20
> Going the other way is about the same (900Mb)
>=20
> 	---Mike

no back to back, regular production infrastructure,
Nortel Passport 8010 router as a backbone.
one host, as mentioned, is a PIII, the other is an
Intel(R) Xeon(TM) CPU 3.06GHz (3056.82-MHz 686-class CPU)
running FreeBSD 6.2-PRERELEASE =239: Wed Oct 11 09:05:49 IST 2006
which gives nicer numbers, if for example the client is of the same hardw=
are,
and at the moment running 6.1-STABLE:
	0.0-10.0 sec  1.08 GBytes    928 Mbits/sec

short version:
the point im trying to make, is that the same setup, where I only change
the release, is going downhill - with this particular MB.

the long version:
Before I send this box to pasture, i decided to use it as a dns/dhcp/tfpt=

server, and i also upgraded it to the latest/greatest version of freebsd,=

before it becomes eol.
as soon as it became production, i noticed that booting a class of some
60 ws was somewhat slower.=20

danny


danny





Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?E1GXw5e-000O7H-ID>