Subject: Re: ARP lockup (arp_drain: locked; punting)
To: None <>
From: Rui Paulo <>
List: tech-net
Date: 03/25/2006 10:54:45
Edgar Fuß <> writes:

> But anyway, even if increasing NMBCLUSTERS really solves the problem
> (and not just makes the server take longer before it happens again)

It may be the case, but I haven't found out what's going on yet.
        1) we changed something and default number of mbufclusters
        isn't enough;
        2) we have an mbuf leakage.

Either way, both are strange and I have no idea what could have

> I would have expected a message suggesting to raise that option
> rather than ARP to lock up.

If it turns out that the best way to fix this problem is to increase,
NMBCLUSTERS, I'll change the message myself.

  Rui Paulo			<rpaulo@{NetBSD{,-PT}.org,}>