Bugtraq mailing list archives
RE: UDP packet handling weird behaviour of various operating systems
From: "David LeBlanc" <dleblanc () mindspring com>
Date: Thu, 26 Jul 2001 22:08:00 -0700
-----Original Message----- From: Michal Zalewski [mailto:lcamtuf () gis net]
3. Windows 2000 Server UP. - the system graphs jump from 2%cpu usage(in a calm evening with no ongoing backups and domain synchronizations) to approx. 35% and holds it steady.
Windows are usually impacted by high-ratio packet floods.
Depends on the NIC, the driver, and the OS version. Very old versions of NDIS weren't as efficient as more recent versions. Driver quality tends to dominate the results.
I believe you are actually testing link layer performance, PCI bus speed and network cards, not operating systems ;)
And NIC driver. I've seen this happen more than once - Attacker is fast box tester writes flood code on. Victim is some dilapidated system that should have been retired. CPU gets pegged on victim, as it has a cheap NIC with bad drivers. Person thinks they've found a new exploit. Some NICs work better than others, and some drivers work better than others.
Current thread:
- Re: UDP packet handling weird behaviour of various operating systems, (continued)
- Re: UDP packet handling weird behaviour of various operating systems Michal Zalewski (Jul 26)
- Re: UDP packet handling weird behaviour of various operating systems Kevin Day (Jul 26)
- Re: UDP packet handling weird behaviour of various operating systems Cade Cairns (Jul 26)
- Re: UDP packet handling weird behaviour of various operating systems Michal Zalewski (Jul 26)
- Re: UDP packet handling weird behaviour of various operating systems Cade Cairns (Jul 27)
- Re: UDP packet handling weird behaviour of various operating systems aland (Jul 27)
- Re: UDP packet handling weird behaviour of various operating systems Stefan Laudat (Jul 26)
- Re: UDP packet handling weird behaviour of various operating systems Michal Zalewski (Jul 26)
- Re: UDP packet handling weird behaviour of various operating systems Stefan Laudat (Jul 26)
- Re: UDP packet handling weird behaviour of various operating systems Niels Bakker (Jul 27)
- RE: UDP packet handling weird behaviour of various operating systems David LeBlanc (Jul 26)
- Re: UDP packet handling weird behaviour of various operating systems Radu-Adrian Feurdean (Jul 27)
- Re: UDP packet handling weird behaviour of various operating systems Michal Zalewski (Jul 26)
- Re: UDP packet handling weird behaviour of various operating systems trop (Jul 26)
- Re: UDP packet handling weird behaviour of various operating systems Paul Sack (Jul 26)
- Re: UDP packet handling weird behaviour of various operating systems Stefan Laudat (Jul 26)
- Re: UDP packet handling weird behaviour of various operating systems Sean Hunter (Jul 27)
- Re: UDP packet handling weird behaviour of various operating systems Sean Hunter (Jul 28)
- Re: UDP packet handling weird behaviour of various operating systems Adrian Chadd (Jul 27)
- Re: UDP packet handling weird behaviour of various operating systems Jarno Huuskonen (Jul 27)
- solaris in.lpd patch where/when? Jake Luck (Jul 28)
- Re: UDP packet handling weird behaviour of various operating systems Stefan Laudat (Jul 26)