|
|
|
|
|
|
|
|
|
|
xen-devel
Re: [Xen-devel] xm mem-set causes kernel panic
To: |
"Ian Pratt" <m+Ian.Pratt@xxxxxxxxxxxx> |
Subject: |
Re: [Xen-devel] xm mem-set causes kernel panic |
From: |
Keir Fraser <Keir.Fraser@xxxxxxxxxxxx> |
Date: |
Thu, 4 May 2006 11:03:59 +0100 |
Cc: |
xen-devel@xxxxxxxxxxxxxxxxxxx, "Krysan, Susan" <KRYSANS@xxxxxxxxxx>, "Puthiyaparambil, Aravindh" <aravindh.puthiyaparambil@xxxxxxxxxx>, "Subrahmanian, Raj" <raj.subrahmanian@xxxxxxxxxx>, "Vessey, Bruce A" <Bruce.Vessey@xxxxxxxxxx>, "Carb, Brian A" <Brian.Carb@xxxxxxxxxx> |
Delivery-date: |
Thu, 04 May 2006 03:04:09 -0700 |
Envelope-to: |
www-data@xxxxxxxxxxxxxxxxxx |
In-reply-to: |
<A95E2296287EAD4EB592B5DEEFCE0E9D4BA56D@xxxxxxxxxxxxxxxxxxxxxxxxxxx> |
List-help: |
<mailto:xen-devel-request@lists.xensource.com?subject=help> |
List-id: |
Xen developer discussion <xen-devel.lists.xensource.com> |
List-post: |
<mailto:xen-devel@lists.xensource.com> |
List-subscribe: |
<http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe> |
List-unsubscribe: |
<http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe> |
References: |
<A95E2296287EAD4EB592B5DEEFCE0E9D4BA56D@xxxxxxxxxxxxxxxxxxxxxxxxxxx> |
Sender: |
xen-devel-bounces@xxxxxxxxxxxxxxxxxxx |
On 3 May 2006, at 22:15, Ian Pratt wrote:
We did run using unstable. We installed sles10 beta11 but we
pulled and built xen-unstable changeset 9903 from xensource
repository. We have not tried with PAE hypervisor. It is
not our focus. How desperately would you need us to try PAE?
Interesting. If you boot with dom0_mem=512 and then start a 15GB guest,
do you see problems shrinking the guest's memory?
I'd certainly be interested in hearing whether the problem exists on
PAE.
I don't think this behaviour is surprising. The kernel is probably
taking about 1% of memory to track memory usage. So trying to balloon
down to 1-2% of your initial memory reservation is rather harsh.
The 'fix' here is to stop users being able to shoot their feet off, by
setting a lower bound on ballooning that is related to the initial
memory size of the guest, and/or quiesce the balloon driver when
low-memory and out-of-memory code paths are executed in the guest.
-- Keir
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
|
|
|
|