On 04/16/2013 10:20 PM, address@hidden 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.