Hi,

thanks for the suggestions. Media seems to be fine. Async seemed not 
really to matter at all. FTP performance ist fine.
I am quite new to NetBSD and I it seems that I have not installed a 
prober release but a current binary drop named 1.5S (just noticed that, 
uups). Could this be the problem?

server:
ex0: flags=8863<UP,BROADCAST,NOTRAILERS,RUNNING,SIMPLEX,MULTICAST> mtu 
1500
         address: 00:10:5a:39:4c:f0
         media: Ethernet autoselect (100baseTX full-duplex)
         status: active
         inet 192.168.140.2 netmask 0xffffff00 broadcast 192.168.140.255

client;
en0: flags=8863<UP,BROADCAST,b6,RUNNING,SIMPLEX,MULTICAST> mtu 1500
         inet 192.168.140.20 netmask 0xffffff00 broadcast 192.168.140.255
         ether 00:30:65:d5:26:4e
         media: autoselect (100baseTX <full-duplex>) status: active
         supported media: none autoselect 10baseT/UTP <half-duplex> 
10baseT/UTP <full-duplex> 100baseTX <half-duplex> 100baseTX <full-duplex>


NFS mount with -o async
[icebox:/tmp] root# mount -o async boo:/mnt/raid/tmp boo
[icebox:/tmp/boo] root# dd bs=1024k count=32 if=/dev/zero of=tmpfile
32+0 records in
32+0 records out
33554432 bytes transferred in 49 secs (684784 bytes/sec)
[icebox:/tmp/boo] root# dd bs=1024k count=32 of=/dev/null if=tmpfile
32+0 records in
32+0 records out
33554432 bytes transferred in 12 secs (2796202 bytes/sec)

plain ftp server -> client:
boo:/mnt/raid/tmp> get tmpfile
Receiving file: tmpfile
100%  0 ==========================================> 33554432 bytes. 
ETA:  0:00
tmpfile:  33554432 bytes received in 3.35 seconds, 9.55 MB/s.
boo:/mnt/raid/tmp>

plein ftp client -> server:
tmpfile:                                                32.00 MB    8.96 
MB/s


Dominik


On Sunday, May 6, 2001, at 03:46 PM, Frank van der Linden wrote:

> On Fri, May 04, 2001 at 08:40:03PM +0200, Dominik Westner wrote:
>> Hi all,
>>
>> I am having problems with the NFS performance between  a NetBSD1.5
>> (server) and a MacOSX10.0.2 (client) machine.
>>
>> While I get about 6,8MB/s between two MacOSX machines both 
>> read/write. I
>> only get below 1MB/s write and about 6,7MB/s read performance between
>> NetBSD and MacOSX.
>
> To check if it's the raid set that is somehow causing slow NFS write
> performance, you can try to use the async option (mount .. -o async ..)
> to the exported filesystem, and see if performance improves in that
> case. Not recommended in production usage, but just as an indicator.
>
> What I have also seen causing this kind of problem is badly
> negotiated media type. Check if both sides agree that they
> are both using the same media and duplex settings on their
> ethernet interfaces. Also, you could check with UDP/TCP
> benchmarks (or just a plain ftp both ways) if the networking
> speed is ok.
>
> - Frank
>
> --
> Frank van der Linden                           fvdl@wasabisystems.com
> ======================================================================
> Quality NetBSD CDs, Support & Service.   http://www.wasabisystems.com/