In message <199806291547.LAA04438@link.link-systems.com>  Ken Wellsch wrote:
> | From peter.bentley@nomura.co.uk Fri Jun 19 10:01:21 1998
> 
> | Ken Wellsch wrote:
> | > | On Jun 18, Ken Wellsch wrote
> | > | > Within what seems like a few seconds I've consumed all my mbuf space,
> | > | > crippling my server system.  netstat claims I've got the expected 16Kb
> | > | > in the queue.
> | > | >
> | > | > The same server to another system, e.g. W95, W/NT, Linux does not have
> | > | > this problem - the NetBSD seems to be properly blocking my writes.
> | 

[..]

> 
> Here is what I hope is useful info (I notice the large ttl value first-off).
> I notice I've got a fair number of mbuf's in use now, but I've not run out.
> 
> ("mac" is a Mac 6400 running MacOS 8.0 and "link" is a large i386/NetBSD box)

I've seen this too.

254 mbufs in use:
        190 mbufs allocated to data
        64 mbufs allocated to socket names and addresses
93/146 mapped pages in use
323 Kbytes allocated to network (67% in use)
0 requests for memory denied
0 requests for memory delayed
0 calls to protocol drain routines

It looks like pages getlost somewhere. It slowly accumulates on my machine and I've to reboot it 
every 30 days (which is still 10 times more than the average NT :-))


> 
> 11:40:00.452641 mac.link-systems.com.2177 > link.link-systems.com.1234: P 168:169(1) ack 1 win 0 (DF) (ttl 255, id 1614)
> 11:40:00.452698 link.link-systems.com.1234 > mac.link-systems.com.2177: . ack 169 win 17287 (ttl 64, id 43601)

For some reason the MAC sends the data byte by byte and even set's the PUSH bit. 

I'll have look at the code today, maybe I spot something. I would
like to have that fixed too ...


Stefan

--
Stefan Grefen                                Tandem Computers Europe Inc.
grefen@hprc.tandem.com                       High Performance Research Center
 --- Hacking's just another word for nothing left to kludge. ---