Re: [Qemu-devel] [PULL v3 7/7] rdma: add documentation

["Michael R. Hines" <mrhines@linux.vnet.ibm.com>]

On 04/17/2013 11:52 AM, Eric Blake wrote:
> On 04/16/2013 10:20 PM, mrhines@linux.vnet.ibm.com wrote:
>
>> +Experimental: Next, decide if you want dynamic page registration.
>> +For example, if you have an 8GB RAM virtual machine, but only 1GB
>> +is in active use, then disabling this feature will cause all 8GB to
>> +be pinned and resident in memory. This feature mostly affects the
>> +bulk-phase round of the migration and can be disabled for extremely
>> +high-performance RDMA hardware using the following command:
>> +
>> +QEMU Monitor Command:
>> +$ migrate_set_capability chunk_register_destination off # enabled by default
> This needs updating to match the QMP capability name (or else the HMP
> command needs some glue logic to map chunk_register_destination into the
> QMP x-chunk-register-destination as a convenience to the user).
>
>> +
>> +TODO:
>> +=====
>> +1. Currently, cgroups swap limits and infinband memory pinning
>> +   are not compatible with each other. We have no plans to unregister
>> +   memory *during* the live migration as the benefit of doing so is not clear.
>> +2. Use of the recent /proc/<pid>/pagemap would likely speed up
>> +   the use of KSM and ballooning while using RDMA.
>> +3. Also, some form of balloon-device usage tracking would also
>> +   help alleviate some issues.
> Maybe also mention that the protocol will be renamed from -incoming
> x-rdma:... to -incoming rdma:... when it has been through more testing
> to stabilize the protocol.
>

Acknowledged. Thanks for the catch.