[TriLUG] Xen HVM guest has severe clock drift

[Joseph S. Tate]

Ugh, who's it with so we know to stay far away?  Xen does not have an
independent time source, it's clock is controlled by the hypervisor.
NTP can't keep up because a xen guest cannot set the clock.

The only decent VPS I've had is with slicehost/rackspace.  All the
other ones have sucked in one way or another, even Linode.

On Thu, Mar 10, 2011 at 9:02 AM, Warren Myers <volcimaster at gmail.com> wrote:
> Sounds like the host is severely overloaded. I personally haven't seen this
> kind of clock drift since the early days of VMware Server trying to run too
> many guests at once on a laptop, or a light physical machine trying to run
> ESX with some heavy-lift VMs
>
> -WMM
>
> On Thu, Mar 10, 2011 at 07:06, Igor Partola <igor at igorpartola.com> wrote:
>
>> Good morning.
>>
>> I recently rented a VPS from a provider that runs on a Xen HVM
>> platform. I am running Ubuntu 10.10 i686 (2.6.35-22-generic-pae) on
>> it. I continuously run ntpd, but the clock drifts by as much as 30
>> seconds in 5 minutes and NTP cannot keep up. Has anyone experienced
>> this? What could be the root cause of this problem?
>>
>> Here are some details:
>>
>> $ dmesg | grep clock
>> [    0.160000] Measured 347 cycles TSC warp between CPUs, turning off TSC
>> clock.
>> [    0.396000] * this clock source is slow. Consider trying other clock
>> sources
>> [    0.550448] Switching to clocksource acpi_pm
>> [    0.653135] rtc_cmos 00:05: setting system clock to 2011-03-09
>> 02:45:40 UTC (1299638740)
>>
>> $ cat /sys/devices/system/clocksource/clocksource0/available_clocksource
>> acpi_pm
>>
>> $ cat /sys/devices/system/clocksource/clocksource0/current_clocksource
>> acpi_pm
>>
>> So far I've tried the following things:
>>
>> 1. I tried disabling ACPI.
>> 2. I replaced openntpd with ntp and added "tinker panic 0" to the top
>> of my /etc/ntp.conf file
>> 3. I read up about xen.independent_wallclock flag, which from what I
>> can tell applies only to Xen PV.
>> 4. Contacted the hosting provider who had little useful advice, aside
>> from "you should install an ntp deamon."
>>
>> What could be the root cause of this problem? Is there any sort of
>> remedy aside from just running an ntp daemon and losing lots of clock
>> time?
>> --
>> This message was sent to: Warren <volcimaster at gmail.com>
>> To unsubscribe, send a blank message to trilug-leave at trilug.org from that
>> address.
>> TriLUG mailing list : http://www.trilug.org/mailman/listinfo/trilug
>> Unsubscribe or edit options on the web  :
>> http://www.trilug.org/mailman/options/trilug/volcimaster%40gmail.com
>> TriLUG FAQ          :
>> http://www.trilug.org/wiki/Frequently_Asked_Questions
>>
>
>
>
> --
> Warren Myers
> http://warrenmyers.com
> http://twitter.com/volcimaster
> http://www.linkedin.com/in/warrenmyers
> --
> This message was sent to: Joseph Tate <dragonstrider at gmail.com>
> To unsubscribe, send a blank message to trilug-leave at trilug.org from that address.
> TriLUG mailing list : http://www.trilug.org/mailman/listinfo/trilug
> Unsubscribe or edit options on the web  : http://www.trilug.org/mailman/options/trilug/dragonstrider%40gmail.com
> TriLUG FAQ          : http://www.trilug.org/wiki/Frequently_Asked_Questions
>



-- 
Joseph Tate
Personal e-mail: jtate AT dragonstrider DOT com
Web: http://www.dragonstrider.com