Hi Roger,
We are testing the indirect feature of xen-blkfront module these days.
And we found that, after VM live-migrate a couple of times, the "%util" of
iostat keeps being 100%, and there are several requests stock in "avgqu-sz".
We have checked some later version of Linux, and it happens on U
On 2015.1.23 19:15, Roger Pau Monné wrote:
> Hello,
>
> El 23/01/15 a les 8.59, Ouyang Zhaowei (Charles) ha escrit:
>> Hi Roger,
>>
>> We are testing the indirect feature of xen-blkfront module these days.
>> And we found that, after VM live-migrate a couple of
If a PVOPS VM has multi-cpu the vcpu_info of cpu0 is the member of the
structure HYPERVISOR_shared_info,
and the others is not, but after 'xl save -c/restore' the vcpu_info will be
reinitialized,
the vcpu_info of all the vcpus will be considered as the member of
HYPERVISOR_shared_info.
This will
If the VM has multi-cpu the vcpu_info of cpu0 is the member of the structure
HYPERVISOR_shared_info,
and the others is not, but after hold/release the VM, the vcpu_info will be
reinitialized,
the vcpu_info of all the vcpus will be considered as the member of
HYPERVISOR_shared_info.
This will cau
On 2015.4.26 7:31, Boris Ostrovsky wrote:
>
> On 04/24/2015 05:30 AM, Ouyang Zhaowei (Charles) wrote:
>> If a PVOPS VM has multi-cpu the vcpu_info of cpu0 is the member of the
>> structure HYPERVISOR_shared_info,
>> and the others is not, but after 'xl save -c/r
On 2015.4.29 5:31, Boris Ostrovsky wrote:
> On 04/28/2015 08:30 AM, Ouyang Zhaowei (Charles) wrote:
>>
>> On 2015.4.26 7:31, Boris Ostrovsky wrote:
>>> On 04/24/2015 05:30 AM, Ouyang Zhaowei (Charles) wrote:
>>>> If a PVOPS VM has multi-cpu the vc
Hi all,
It's been a long time, I don't know whether this patch is OK or not. Or does it
somewhere need to be improved a little bit?
thanks
On 2015.5.6 9:47, Ouyang Zhaowei (Charles) wrote:
> vcpu_info would be reset to wrong place on canceled suspend on PVOPS VM which
> has mu
On 2015.5.28 19:07, David Vrabel wrote:
> On 06/05/15 02:47, Ouyang Zhaowei (Charles) wrote:
>> vcpu_info would be reset to wrong place on canceled suspend on PVOPS VM
>> which has multi-cpu
>>
>> The hypervisor continues assuming that vcpu_info is stored in per-cpu d
On 2015.5.5 17:09, David Vrabel wrote:
> On 04/05/15 03:56, Ouyang Zhaowei (Charles) wrote:
>> The hypervisor continues assuming that vcpu_info is stored in per-cpu data
>> which was set up by xen_vcpu_setup(),
>> while on canceled suspend, the call to xen_hvm_init_s
On 2015.5.6 1:21, David Vrabel wrote:
> On 05/05/15 14:19, Ouyang Zhaowei (Charles) wrote:
>>
>>
>> On 2015.5.5 17:09, David Vrabel wrote:
>>> On 04/05/15 03:56, Ouyang Zhaowei (Charles) wrote:
>>>> The hypervisor continues assuming that vcpu_info is sto
vcpu_info would be reset to wrong place on canceled suspend on PVOPS VM which
has multi-cpu
The hypervisor continues assuming that vcpu_info is stored in per-cpu data
which was set up by xen_vcpu_setup(),
while on canceled suspend, the call to xen_hvm_init_shared_info() will make the
guest thin
On 2015.5.2 2:55, Boris Ostrovsky wrote:
> On 04/30/2015 03:27 AM, Ouyang Zhaowei (Charles) wrote:
>>
>> On 2015.4.29 5:31, Boris Ostrovsky wrote:
>>> On 04/28/2015 08:30 AM, Ouyang Zhaowei (Charles) wrote:
>>>> On 2015.4.26 7:31, Boris Ostrovsky wrote:
The hypervisor continues assuming that vcpu_info is stored in per-cpu data
which was set up by xen_vcpu_setup(),
while on canceled suspend, the call to xen_hvm_init_shared_info() will now make
the guest think that vcpu_info
is in the shared page, so we do not call xen_hvm_init_shared_info() on su
On 2015.1.26 10:30, Ouyang Zhaowei (Charles) wrote:
>
> On 2015.1.23 19:15, Roger Pau Monné wrote:
>> Hello,
>>
>> El 23/01/15 a les 8.59, Ouyang Zhaowei (Charles) ha escrit:
>>> Hi Roger,
>>>
>>> We are testing the indirect feature of xe
14 matches
Mail list logo
