Re: 1000ms delay in networking stack or driver, new bug?

Arjan van de Ven (root@fenrus.demon.nl)
Sun, 19 Sep 1999 08:11:30 +0200


In article <37E469CC.C8087C65@lig.net> you wrote:
> I periodically notice that all or most network traffic is taking exactly 1000
> ms. No matter where I check traffic, most roundtrips seem to take 1000ms.
> This includes pings, traceroutes, and apparently TCP traffic since connections
> are running very slowly. Downing/upping the interface cures the problem.

I saw this too, once. The most likely cause was the NIC (a RTL8139 in my
case) not responding to "data sent" events, so only "data received" events
made progress. Hence the 1000ms ping-time, as the secoond ping-packed causes
the first ping-packet to be transmitted.

No solution though.

Greetings,
Arjan van de Ven

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/