Re: UDP packet handling weird behaviour of various operating systems

From: Kevin Day (toasty@temphost.dragondata.com)
Date: 07/26/01


From: Kevin Day <toasty@temphost.dragondata.com>
Message-Id: <200107262148.f6QLmZL97633@temphost.dragondata.com>
Subject: Re: UDP packet handling weird behaviour of various operating systems
To: lcamtuf@gis.net (Michal Zalewski)
Date: Thu, 26 Jul 2001 16:48:34 -0500 (CDT)


>
> > The flood is performed via a Gigabit link. The packet rate handling of
> > win2k is wonderful, it even beats an OpenBSD 2.8. Kudos to MS guys,
> > this one is a real hit. As I couldn't believe my eyes I ran some
> > applications on it (crunching queries on the local MS SQL2k server
> > etc) and I got timely-fashion responses.
>
> I believe you are actually testing link layer performance, PCI bus speed
> and network cards, not operating systems ;)
>

Actually, you're probably entering a "livelock" situation. Packets were
coming in so fast that the interrupt handler is consuming all your time.
Alot of high speed network devices have special modes to prevent this from
happening. (Only interrupt when a certain number of packets are in the
FIFO, make sure the interrupt isn't asserted for more than x% of the time,
etc).

This is probably possible on 100MBit links on slow CPUs too.

Which network card are you using? I don't ever want to buy one. :)

-- 
Kevin Day
toasty@dragondata.com - kevin@stileproject.com



Relevant Pages

  • RE: More information regarding Etherleak
    ... > I audited our system running under various operating systems. ... I have just tested a HP JetDirect J6035A by pinging with the 1-byte method ... On another note, in CERT's information, they include a statement from Cisco ... A packet typical of those I have logged ...
    (Bugtraq)
  • Re: Block martians with source address 127.0.0.1
    ... > The kernel on the firewall logs these packets as martians ... and ONLY THE FIRST RULE THAT MATCHES IS APPLIED to a packet. ... operating systems and network security. ...
    (Focus-Linux)
  • interface records errors
    ... error for every RX packet. ... UDP communication is impossible, and TCP really slow. ... Please do not send copies of list mail to me; ... micro$oft is to operating systems & security ...
    (Debian-User)
  • Re: UDP packet handling weird behaviour of various operating systems
    ... UDP packet handling weird behaviour of various operating systems ...
    (Bugtraq)
  • Re: bge(4) sysctl tuneables -- a blast from the past.
    ... The real effect of TX coalesce ticks is confusing to me; TX interrupt ... receiving side is Intel 82571). ... The interrupt rate I had got seemed to be related to packet size?! ...
    (freebsd-net)