Re: [PATCH v1 01/13] docs: create Memory Bandwidth Allocation (MBA) feature document

[Chao Peng <chao.p.peng@linux.intel.com>]

> +     Linear mode: the input precision is defined as 100-(MBA_MAX).
> For instance,
> +     if the MBA_MAX value is 90, the input precision is 10%. Values
> not an even
> +     multiple of the precision (e.g., 12%) will be rounded down
> (e.g., to 10%
> +     delay applied) by HW automatically.

No sure if all people unterstand HW, if not then I prefer Hardware. If
you do this then all places though the document should be replaced.


> +  When context switch happens, the COS ID of VCPU is written to per-
> thread MSR

COS ID is per-domain other than per-vCPU at this time. So 'COS ID of
domain' is more accurate.

> +  `IA32_PQR_ASSOC`, and then hardware enforces bandwidth allocation
> according
> +  to the throttling value stored in the COS register.

There is no COS register in fact. COS exists just a concept.

> +For example:
> +    root@:~$ xl psr-hwinfo --mba
> +    Memory Bandwidth Allocation (MBA):
> +    Socket ID       : 0
> +    Linear Mode     : Enabled
> +    Maximum COS     : 7
> +    Maximum Throttling Value: 90
> +    Default Throttling Value: 0
> +
> +    root@:~$ xl psr-mba-set 1 0xa
> +
> +    root@:~$ xl psr-mba-show 1
> +    Socket ID       : 0
> +    Default THRTL   : 0
> +       ID                     NAME            THRTL
> +        1                 ubuntu14             0xa
> +
> +# Areas for improvement
> +
> +A hexadecimal number is used to show THRTL for a domain now. It may
> not be user-
> +friendly.
> +
> +To improve this, the libxl interfaces can be wrapped in libvirt to
> provide more
> +usr-friendly interfaces to user, e.g. a percentage number to show for
> linear
> +mode.

I suggest we can do this even for 'xl psr-mba-show', as we know we are
in linear mode or not. A hex number is just not easy to understand for
people. And for 'xl psr-mba-set' it is also much straighforward to set a
percentage number in linear mode.

Chao

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel