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

Re: [Xen-devel] [RFC Patch v4 8/8] x86/hvm: bump the maximum number of vcpus to 512

On Fri, Feb 23, 2018 at 06:11:39PM +0000, Roger Pau Monné wrote:
>On Wed, Dec 06, 2017 at 03:50:14PM +0800, Chao Gao wrote:
>> Signed-off-by: Chao Gao <chao.gao@xxxxxxxxx>
>> ---
>>  xen/include/public/hvm/hvm_info_table.h | 2 +-
>>  1 file changed, 1 insertion(+), 1 deletion(-)
>> diff --git a/xen/include/public/hvm/hvm_info_table.h 
>> b/xen/include/public/hvm/hvm_info_table.h
>> index 08c252e..6833a4c 100644
>> --- a/xen/include/public/hvm/hvm_info_table.h
>> +++ b/xen/include/public/hvm/hvm_info_table.h
>> @@ -32,7 +32,7 @@
>>  #define HVM_INFO_PADDR       ((HVM_INFO_PFN << 12) + HVM_INFO_OFFSET)
>>  /* Maximum we can support with current vLAPIC ID mapping. */
>> -#define HVM_MAX_VCPUS        128
>> +#define HVM_MAX_VCPUS        512
>Wow, that looks like a pretty big jump. I certainly don't have access
>to any box with this number of vCPUs, so that's going to be quite hard
>to test. What the reasoning behind this bump?

There are 288 cpus on some Intel XEON-phi platform. Bumping this value to
288 would be weird because I think if I do that there would be some
questions -- why it should be 288 and why the number of vCPUs should be the
same with the number of pCPUs. I choose 512, just because it is the nearest
next power of 2 number.

>Is hardware with 512 ways expected soon-ish?


>Also osstest is not even able to test the current limit, so I would

Do we have any plan to test guest with 128 vCPUs on osstest?

>maybe bump this to 256, but as I expressed in other occasions I don't
>feel comfortable with have a number of vCPUs that the current test
>system doesn't have hardware to test with.

If we only test functionality (osstest doesn't test performance,
right?), hardware needn't have so many pCPUs.

Could we declare that more than 128 vCPUs support is only
experimental feature? Once some regular tests are available, we can
announce that On x86, Xen supports HVM with, for example, 128 vCPUs or
512 vCPUs. It seems Geroge's work on SUPPORT.md is for this kind of propose.


Xen-devel mailing list



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