SGI with Linux server

SGI with Linux server

Post by Guy Premon » Sat, 11 Sep 1999 04:00:00



Hi,

I have a LAN of 8 SGIs (Indy, O2, Octane, Onyx RE2) and I'm trying to
set up a disk server with an intel box running RedHat Linux 6.0 with
kernel 2.2.5-22. The intel box also have a second network interface that
leads to a mainly PC LAN with very small traffic.

When the SGIs don't do large and constant access to the server,
everything works fine. But at some point (which I haven't discovered
yet) all network traffic stops. This happens usually under heavy load,
when several users simultaneously request file from the server, but
sometimes for no apparent reasons.

The only messages on the SGIs are
  NFS2 read failed for server dupont: Timed out
or
  NFS2 write failed for server dupont: Timed out

The only peculiar message given by dmesg on the linux box is
  eth0: Transmit error, Tx status register 82.

I tried using NFS3 instead, using async NFS, I checked all cables,
plugs, other machines, patches, etc., but I couldn't find anything that
made it work correctly.

For all I know, it could be a problem with the SCSI cards inside the PC
but the only symptoms are related to network.

If anybody as an idea, or if someone has a configuration similar, i
would be happy to hear any suggestion.

Thanks,
Guy Premont

--
===========================================
          Silicon Worlds S.A.  
12, rue de Chatillon    75014 Paris  France
       Tel: +33 (01) 53.90.11.11
       Fax: +33 (01) 53.90.11.12
===========================================

 
 
 

SGI with Linux server

Post by irinak7.. » Fri, 08 Oct 1999 04:00:00




Quote:> Hi,

> I have a LAN of 8 SGIs (Indy, O2, Octane, Onyx RE2) and I'm trying to
> set up a disk server with an intel box running RedHat Linux 6.0 with
> kernel 2.2.5-22. The intel box also have a second network interface
that
> leads to a mainly PC LAN with very small traffic.

> When the SGIs don't do large and constant access to the server,
> everything works fine. But at some point (which I haven't discovered
> yet) all network traffic stops. This happens usually under heavy load,
> when several users simultaneously request file from the server, but
> sometimes for no apparent reasons.

> The only messages on the SGIs are
>   NFS2 read failed for server dupont: Timed out
> or
>   NFS2 write failed for server dupont: Timed out

> The only peculiar message given by dmesg on the linux box is
>   eth0: Transmit error, Tx status register 82.

> I tried using NFS3 instead, using async NFS, I checked all cables,
> plugs, other machines, patches, etc., but I couldn't find anything
that
> made it work correctly.

> For all I know, it could be a problem with the SCSI cards inside the
PC
> but the only symptoms are related to network.

> If anybody as an idea, or if someone has a configuration similar, i
> would be happy to hear any suggestion.

> Thanks,
> Guy Premont

> --
> ===========================================
>           Silicon Worlds S.A.
> 12, rue de Chatillon    75014 Paris  France
>        Tel: +33 (01) 53.90.11.11
>        Fax: +33 (01) 53.90.11.12
> ===========================================

I would like to let you know that I have the same problem with my SGI
(Indy) machine. Since I updated it from 6.2 to 6.5. I keep getting the
 following message
NFS2 write failed for server .... : Can't encode arguments
NFS write error 5
Our NFS server is not Linux but freeBSD. Were you ever able to solve
you problem?

 Thank you ,

Irina Kaliman, University of Miamia, Florida

Sent via Deja.com http://www.deja.com/
Before you buy.

 
 
 

1. FTP problem: linux>>win/SGI slow win/SGI>>linux fast

The machine is on a Novell 4.2 network and uses an Intel
Ether Express 16 card. It is possible to be on another
machine and transfer a file FROM the linux box at a rate of
about 600kB/s.
However, transferring to the linux machine gives rates of
about 18kB/s.  Similarly if one is
on the Linux box using ftp, transfer both from and
to another machine and
from another machine is slow - around 18Kb / sec.

It is a dual boot system - when tranferring/receiving files
using windoze ftp (QVFTP or WS_FTP) the transfer rates in
both direction are 600kB/s.

At installation time, linux was set up to use the
'eexpress' driver and the bootp protocol.

There are no packet overflows, packets lost or errors generally.

Visualising the transfer using the 'hash' function of ftp
shows that transfer progresses at the expected speed for
10-30kB, then stalls or slows down to a snail pace, then
starts again, slow, stall, slow, etc...

I have tried
- explicitly stating the IRQ=10, I/O base address 0x300
- turning on/off IPX
- making the MTU smaller
- manually configuring (i.e no bootp) the ip address etc.
- playing with the routing window as suggested in the
HOWTO-Ethernet file.

The only effect I have been able to achieve is a reduction
in performance to 13kB/s.

Checking usenet a number of people seem to have had a
similar problem but no relevant solutions suggested.  One
person claimed they started having this problem when
they upgraded their motherboard.

I have no idea what to do next... help...

2. newbie problem creating a kernel with isdn

3. FTP problem: Linux->Win/SGI slow Win/SGI->Linux fast

4. Overriding system calls

5. SGI CEO Resigns, joins Microsoft (was Re: SGI switching gears: NT -> Linux)

6. Linux Quake Howto - feedback requested

7. PPP: SGI-server Linux-client.Need help!

8. I want to burn my own RedHat 5.0 CD Help!

9. Failsafe servers... SGI and/or Linux

10. Web Server: SGI vs. Linux Box

11. Display SGI GL on non-SGI box

12. I need to copy all SGI(indy) to new SGI(O2)IRIX 6.3