[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-users] Dom0 issue

  • To: "Fajar A. Nugraha" <list@xxxxxxxxx>
  • From: "Grinberg, Vitaly" <Vitaly.Grinberg@xxxxxxxxxxxx>
  • Date: Fri, 13 Jan 2012 10:41:55 -0500
  • Cc: xen-users@xxxxxxxxxxxxxxxxxxx
  • Delivery-date: Fri, 13 Jan 2012 15:44:09 +0000
  • List-id: Xen user discussion <xen-users.lists.xensource.com>
  • Thread-index: AczRei/okFzZI4ygTua5a9LZ4Cj9zQAj4iiQ
  • Thread-topic: [Xen-users] Dom0 issue

If it is correct, the Dom0 which is pinned to this CPU is not available.

-----Original Message-----
From: Fajar A. Nugraha [mailto:list@xxxxxxxxx] 
Sent: Thursday, January 12, 2012 5:33 PM
To: Grinberg, Vitaly
Cc: xen-users@xxxxxxxxxxxxxxxxxxx
Subject: Re: [Xen-users] Dom0 issue

On Fri, Jan 13, 2012 at 4:36 AM, Grinberg, Vitaly
<Vitaly.Grinberg@xxxxxxxxxxxx> wrote:
> We are running HP ProLiant DL580 G7 E7540 with four sockets.
> The Dom0 VCPU0 is pinned to the CPU 0 on the socket 0.
> What is going to happen if socket 0 starts malfunctioning?

Your server will be dead. Or at least crashed and needs to be
restarted, and then (in the case of multi-socket servers) it would
have less available CPU than before.

Regardless of whether it's using xen, windows, linux, or whatever,
there are no x86 server that I know of that can keep functioning in
the case of a failed cpu socket.


Xen-users mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.