Re: [Qemu-devel] [PATCH QEMU 5/5] migration: Add the interface for cache drop control

[Eric Blake <eblake@redhat.com>]

[-- Attachment #1: Type: text/plain, Size: 1633 bytes --]

On 04/19/2016 08:20 AM, Liang Li wrote:
> Whether drop the cache and drop what kind of cache depend on the

Whether to drop the cache, and what kind of cache drop to perform,
depend ...

> user, add the related qmp and hmp interface to query and set the
> cache control value.
> 
> Signed-off-by: Liang Li <liang.z.li@intel.com>
> ---

> +++ b/qapi-schema.json
> @@ -612,11 +612,21 @@
>  # @x-cpu-throttle-increment: throttle percentage increase each time
>  #                            auto-converge detects that migration is not making
>  #                            progress. The default value is 10. (Since 2.5)
> +# @x-drop-cache: drop guest's page cache during live migration, the value can
> +#         be set to 0, 1, 2, 3. 1 means drop the clean page cache, 2 means
> +#         drop the slab cache, 3 means to drop both clean page cache, 0 means
> +#         do not drop any cache. Drop cache can speed up live migration
> +#         process and reduce the network traffic, the side affect is the
> +#         performance impact to the guest, 1 is the recommended value for
> +#         proper balance between speed and performance. The value only takes
> +#         affect when the virtio-balloon device are enabled and the guest
> +#         has the related driver. The default value is 0. (Since 2.7)

Absolutely not this interface.  Make this an enum type, not a raw
magic-number integer type, where the user requests
"x-drop-cache":"clean", "x-drop-cache":"slab", and so on.

-- 
Eric Blake   eblake redhat com    +1-919-301-3266
Libvirt virtualization library http://libvirt.org


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 604 bytes --]