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-users

Re: [Xen-users] xen-3.2.0 problems with time (and space)

To: xen-users@xxxxxxxxxxxxxxxxxxx
Subject: Re: [Xen-users] xen-3.2.0 problems with time (and space)
From: ein@xxxxxxxxxxxxxx
Date: Mon, 23 Jun 2008 07:39:49 -0700 (PDT)
Delivery-date: Mon, 23 Jun 2008 07:40:25 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
List-help: <mailto:xen-users-request@lists.xensource.com?subject=help>
List-id: Xen user discussion <xen-users.lists.xensource.com>
List-post: <mailto:xen-users@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=unsubscribe>
Sender: xen-users-bounces@xxxxxxxxxxxxxxxxxxx
User-agent: SquirrelMail/1.4.10a
> Hi,
> initially all domUs and dom0s had ntp running, I have disabled it on the
domU and resynced once via ntpdate, but that didn't help. All the domUs
clocks were faster than their dom0.
> I also tried setting /proc/sys/xen/independent_wallclock  to 1 leaving
ntp running but that didn't help either.
> I have the feeling that 3.1 behaves differently, so I was thinking of
downgrading one dom0 and monitor the behavior.
> I remember fighting with clocks with vmware, and funnily enough that was
one of the main reason that made me move to xen.
> Do you think that passing clock=pit  to the domU kerrnel option could
help at all? Also for the record the hardware are HP BL465c blade
servers cpu Dual-Core AMD Opteron(tm) Processor 2216 HE.
> cheers
> M.
>
> [STD]Ein wrote:
>> Have you adjusted any of the clock controls for Xen? (independent
wallclocks)
>> If not, there should be no reason to run ntp in your domU's.  I suspect
that
>> ntp may actually be causing your time skews due to variations
introduced by
>> xen's clock handling.  I would try disabling ntp in domU and see if
your clocks are still moving.
>>
>> -----Original Message-----
>> From: xen-users-bounces@xxxxxxxxxxxxxxxxxxx
>> [mailto:xen-users-bounces@xxxxxxxxxxxxxxxxxxx] On Behalf Of Massimo
Mongardini
>> Sent: June 20, 2008 7:37 AM
>> To: xen-users@xxxxxxxxxxxxxxxxxxx
>> Subject: [Xen-users] xen-3.2.0 problems with time (and space)
>>
>> Hi,
>>     I am experiencing some issues keeping my clock in sync in a series
>> of domU with xen-3.2.0.
>> every node is set to ntpd sync to a central server.
>> (server-0034 is a bare metal server and is in sync with the rest of the
world, while 35-41 are rhel4 domUs)
>>
>> --------- server-0034---------
>> Fri Jun 20 11:49:48 GMT 2008
>> --------- server-0035---------
>> Fri Jun 20 11:50:54 GMT 2008
>> --------- server-0036---------
>> Fri Jun 20 11:49:52 GMT 2008
>> --------- server-0037---------
>> Fri Jun 20 11:49:50 GMT 2008
>> --------- server-0038---------
>> Fri Jun 20 11:49:50 GMT 2008
>> --------- server-0039---------
>> Fri Jun 20 11:50:50 GMT 2008
>> --------- server-0040---------
>> Fri Jun 20 11:50:42 GMT 2008
>> --------- server-0041---------
>> Fri Jun 20 11:49:51 GMT 2008
>>
>> on the logs I see many:
>> Jun 20 11:54:55 server-0041 ntpd[2573]: frequency error -512 PPM
exceeds tolerance 500 PPM
>>
>> Maybe as a side effect to this, the domUs timeout the connection to a
nfs server from time to time
>>
>> Jun 20 09:15:38 server-0036 kernel: nfs: server fs-cluster not
>> responding, still trying
>> Jun 20 09:15:52 server-0036 kernel: nfs: server fs-cluster OK
>> Jun 20 09:16:35 server-0036 kernel: nfs: server fs-cluster not
>> responding, still trying
>> Jun 20 09:16:35 server-0036 kernel: nfs: server fs-cluster OK
>>
>> details:
>> dom0: rhel4
>> xen: 3.2.0 compiled sources
>> domU: rhel4
>>
>> I also have another xen environment that I use for tests with xen 3.1
on a rhel4 dom0 and it doesn't seem to suffer for this issue:
>> --------- server-0002---------
>> Fri Jun 20 12:29:05 GMT 2008
>> --------- server-0012---------
>> Fri Jun 20 12:29:05 GMT 2008
>> --------- server-0040---------
>> Fri Jun 20 12:29:05 GMT 2008
>>
>> any tip?
>>
>> cheers,
>> Massimo
>>
>>
>
>
> --
> Massimo Mongardini
> ~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~
echo
> 'Jg!J!hjwf!zpv!bo!bqqmf!boe!zpv!hjwf!nf!bo!bqqmf-!uifo!xf!xjmm!ibwf!bo!bqqmf!fbdi/!Cvu!jg!J!hjwf!zpv!bo!jefb!boe!zpv!hjwf!nf!bo!jefb-!xf!xjmm!ibwf!uxp!jefbt!fbdi!'
| perl -pe 's/(.)/chr(ord($1)-1)/ge'
> ~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~
http://massimo.mongardini.it
> http://www.getthefacts.it
> http://www.mongardini.it/pizza-howto
> ~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~-.-~
Please avoid sending me Word or PowerPoint attachments.
> See http://www.gnu.org/philosophy/no-word-attachments.html
>
>

Just for the sake of completeness, can you  tell us a bit more about your
platform?
Are you running a ?stock? xen kernel for dom0 and domU, or are these
vendor supplied (rh) kernels?
If it?s vendor supplied, is it possible to test again using the xen
supplied 3.2 2.6.18 kernel?
I?m at a loss, but with a bit more info maybe we can nail it down.




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