Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 4 Apr 2001 17:21:53 -0400
From:      "Jason T. Luttgens" <>
To:        "'Karsten W. Rohrbach'" <>, "'Mike Smith'" <>
Cc:        "'Doug Hardie'" <>, <>, "'David W. Chapman Jr.'" <>
Subject:   RE: Network performance question
Message-ID:  <000001c0bd4d$45acfc30$0200010a@lucky>
In-Reply-To: <>

Next in thread | Previous in thread | Raw E-Mail | Index | Archive | Help
>-----Original Message-----
>From: Karsten W. Rohrbach []
>Sent: Tuesday, April 03, 2001 8:14 PM
>To: Mike Smith
>Cc: Jason T. Luttgens; 'Doug Hardie';; >'David
>W. Chapman Jr.'
>Subject: Re: Network performance question
>what exactly is the mainboard hardware? in which slot is the card?
>i recall having had severe problems on some bx tyan board with 5 pci
>slots. when i used slot 1 or 5 i had dropped interrupts since they were
>shared with i tink the onboard scsi. using the middle 3 slots the
>problem was gone. linux seems to handle interrupt sharing on pci
>differently from feebsd.

ABIT BE6-II, in the slot marked PCI2 on the motherboard. This is the
computer I was using to listen to the packets.

The computer that is transmitting the packets is an ASUS P2B-D.

After performing more testing at work and home, I am beginning to belive
that what tcpreplay says it transmitted is not what was really transmitted
(not that the listening machine is capturing everything either). I am in the
process of trying to prove this. I'll post my findings as soon as I can
figure anything out.

Some of my testing at work revealed a strange thing. The 3COM card in a
computer I have at work typically received 407-409 packets from another
computer transmitting (a Sony VAIO laptop with builtin Intel Etherexpress
Pro 10/100 card), then stopped seeing packets for some random number
(usually less than 2000), receive 407-409 packets again, and repeat the
cycle. Anyone know what that might mean?

Thanks again for everyone's help and comments - eventually I will figure
this out....


>> Experiments must be reproducible; they should all fail in the same >way.
>KR433/KR11-RIPE -- --

To Unsubscribe: send mail to
with "unsubscribe freebsd-stable" in the body of the message

Want to link to this message? Use this URL: <$45acfc30$0200010a>