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

Scott Henry (scotth@sgi.com)
20 Sep 1999 11:56:57 -0700


>>>>> "D" == David S Miller <davem@redhat.com> writes:

D> Date: Mon, 20 Sep 1999 10:49:19 -0500 (CDT)
D> From: Oliver Xymoron <oxymoron@waste.org>

D> On Mon, 20 Sep 1999, Stephen D. WIlliams wrote:

>> It has been pointed out that it might be my pcmcia drivers, I'm
>> using pcmcia-cs-3.0.13, or the fact that I'm using pump (which
>> apparently has bugs compared to dhcpcd, the client daemon).

D> I've seen this after restarting networking with
D> /etc/rc.d/init.d/network restart. Redhat 6, hand-compiled
D> 2.2.1[012] kernel, with nothing fancy except firewalling. I'v also
D> seen multiples of seconds up to 5 and 6.

D> Do I sense that the common denominator in this problem is that some
D> form of DHCP/pump/whatever is being used? If that is common amongst
D> everyone seeing this problem, it would be nice to know.

I get it on my laptop, with PCMCIA card, no DHCP/pump/whatever.
(what's pump?) I will occasionally get really backed-up pings, a
flood of replies all at once, with ~1000msec intervals. I'll try to
get a snoop from another host the next time I see it. usually,
though, the pings are 1000msec + what it should really be, not just
"1000msec".

Even stranger is to see pings from laptop getting 1000+msec, and in
an ssh-ed window to the other system, see sub-msec pings to the
laptop...

-- 
 Scott Henry <scotth@sgi.com> /  Help! My disclaimer is missing!
 IRIX MTS,                   /  GIGO *really* means: Garbage in, Gospel Out
 Silicon Graphics, Inc      /  http://reality.sgi.com/scotth/

- 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/