WARNING - OLD ARCHIVES

This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
   
 
 
Xen 
 
Home Products Support Community News
 
   
 

xen-ppc-devel

[XenPPC] dom0 boots to nfsroot on JS21

To: xen-ppc-devel@xxxxxxxxxxxxxxxxxxx
Subject: [XenPPC] dom0 boots to nfsroot on JS21
From: Amos Waterland <apw@xxxxxxxxxx>
Date: Thu, 13 Jul 2006 23:34:17 -0400
Delivery-date: Thu, 13 Jul 2006 20:34:45 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
In-reply-to: <20060617041455.GA18150@xxxxxxxxxxxxxxxxxxxxx>
List-help: <mailto:xen-ppc-devel-request@lists.xensource.com?subject=help>
List-id: Xen PPC development <xen-ppc-devel.lists.xensource.com>
List-post: <mailto:xen-ppc-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-ppc-devel>, <mailto:xen-ppc-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-ppc-devel>, <mailto:xen-ppc-devel-request@lists.xensource.com?subject=unsubscribe>
References: <20060617041455.GA18150@xxxxxxxxxxxxxxxxxxxxx>
Sender: xen-ppc-devel-bounces@xxxxxxxxxxxxxxxxxxx
User-agent: Mutt/1.5.9i
With current PPC Xen, dom0 is able to boot and mount an nfsroot on the
JS21 blade I have access to.  I can ssh in and run standard tools like gcc.

There seem to be some questions about the current stability of this
JS21+SLOF+XEN+DOM0 combination, but at least with a NFS root it seems
quite stable.  I ran `stress -c 4 -m 1 --vm-bytes 20M -i 1' for a good
half-hour with no problems.

I then formated the disk drive with an ext2 partition and mounted it
under /mnt/sda1.  I ran the following for a half-hour with no problems:
`while true; do cp /etc/passwd /mnt/sda1 && sync || break; done'

While running `stress -d 1' I did immediately see the kernel's OOM
killer fire, but since dialing back the size of the buffer that stress
writes to the disk with the `--hdd-bytes 20M' option stops it from
triggering, I think it was simply a natural consequence of having only
64MB allocated to the partition.

I am getting random SSH hangups though, usually but not always after
doing something that causes a lot of console output.  The message from
my client looks like `Disconnecting: Bad packet length 3890534716.'
The effect does not seem to be permanent, as I can immediately ssh back in.


_______________________________________________
Xen-ppc-devel mailing list
Xen-ppc-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ppc-devel

<Prev in Thread] Current Thread [Next in Thread>
  • [XenPPC] dom0 boots to nfsroot on JS21, Amos Waterland <=