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

Dan Drown (abob@psu.edu)
Mon, 20 Sep 1999 14:07:37 -0400

On Mon, Sep 20, 1999 at 08:34:32PM +0400, kuznet@ms2.inr.ac.ru wrote:
> > It is very odd in that it isnt card dependant. It seems to be more like a
> > qdisc problem somehow affected by interfaces going up and down and up again
>
> 1 sec is ping interval. Please, make "ping -i 3" to check this.
> If the time will be 3 sec, the guess is correct.
>
> And make tcpdump both on wire (on ethernet it should be third host)
> and on this host.

I saw this (ping of >1s on a local lan) with 2.2.(>12) and a 3com 3c509. I
don't have the tcpdumps anymore, but what solved the problem for me was to
compile the kernel with gcc 2.7.2.3 instead of pgcc 1.1.2. iirc, tcpdump on
the host showed the packet going out and the response coming back immediatly,
but I'd run the ping program, and the request on tcpdump would show up about
1s later (or maybe it was the ping program got the response about 1s later, I
can't remember which one now.).

-- 
Daniel Drown


-
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/