Re: UDP packet handling weird behaviour of various operating systems
From: Jarno Huuskonen (Jarno.Huuskonen@uku.fi)Date: 07/27/01
- Previous message: Juergen P. Meier: "Re: UDP packet handling weird behaviour of various operating systems"
- In reply to: Stefan Laudat: "Re: UDP packet handling weird behaviour of various operating systems"
- Next in thread: Jake Luck: "solaris in.lpd patch where/when?"
- Next in thread: Boyan Krosnov: "RE: UDP packet handling weird behaviour of various operating systems"
- Reply: Jake Luck: "solaris in.lpd patch where/when?"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]
Date: Fri, 27 Jul 2001 15:36:36 +0300 From: Jarno Huuskonen <Jarno.Huuskonen@uku.fi> To: bugtraq@securityfocus.com Subject: Re: UDP packet handling weird behaviour of various operating systems Message-ID: <20010727153636.A109558@messi.uku.fi>
On Thu, Jul 26, Stefan Laudat wrote:
> Identical network cards for Win2k, Linux SMP and OpemBSD processor (Intel
> Pro 100). Linux was run on dual p3/1Ghz(SMP), Pentium2/400Mhz and P3/800Mhz
> (UP). Windows 2000 was run on p3/1Ghz UP. I've made tests with same results
> against Linux UP boxes running on Celeron/600 with 3com Vortex and realtek
> 8139 NICs. I've outlined that the result is the same no matter if you hit
> via 1Gbit or 100Mbit.
Could you test the pro100 adapter with the intel e100 driver with
cpu-saver enabled (insmod e100.o ucode=1) ? (Also playing around with
other parameters like IntDelay, BundleMax and Tx/RxDescriptors might
make a difference). The 'cpu-saver' option should limit the number of
interrupts the nic generates (this might help if the interrupts bring
the machine to halt) (read the e100 driver manual for more information).
-Jarno
-- Jarno Huuskonen <Jarno.Huuskonen@uku.fi>
- Previous message: Juergen P. Meier: "Re: UDP packet handling weird behaviour of various operating systems"
- In reply to: Stefan Laudat: "Re: UDP packet handling weird behaviour of various operating systems"
- Next in thread: Jake Luck: "solaris in.lpd patch where/when?"
- Next in thread: Boyan Krosnov: "RE: UDP packet handling weird behaviour of various operating systems"
- Reply: Jake Luck: "solaris in.lpd patch where/when?"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]