Commit a5f56b90 authored by Michael R. Hines's avatar Michael R. Hines Committed by Juan Quintela
Browse files

rdma: update documentation to reflect new unpin support 



As requested, the protocol now includes memory unpinning support.
This has been implemented in a non-optimized manner, in such a way
that one could devise an LRU or other workload-specific information
on top of the basic mechanism to influence the way unpinning happens
during runtime.

The feature is not yet user-facing, and is thus can only be enabled
at compile-time.

Reviewed-by: default avatarEric Blake <eblake@redhat.com>
Signed-off-by: default avatarMichael R. Hines <mrhines@us.ibm.com>
Signed-off-by: default avatarJuan Quintela <quintela@redhat.com>
parent 3464700f

docs/rdma.txt

+30 −21
Original line number Diff line number Diff line
@@ -35,7 +35,7 @@ memory tracked during each live migration iteration round cannot keep pace 
with the rate of dirty memory produced by the workload.



RDMA currently comes in two flavors: both Ethernet based (RoCE, or RDMA

over Convered Ethernet) as well as Infiniband-based. This implementation of

over Converged Ethernet) as well as Infiniband-based. This implementation of

migration using RDMA is capable of using both technologies because of

the use of the OpenFabrics OFED software stack that abstracts out the

programming model irrespective of the underlying hardware.
@@ -202,7 +202,7 @@ The maximum number of repeats is hard-coded to 4096. This is a conservative 
limit based on the maximum size of a SEND message along with emperical

observations on the maximum future benefit of simultaneous page registrations.



The 'type' field has 10 different command values:

The 'type' field has 12 different command values:

     1. Unused

     2. Error                      (sent to the source during bad things)

     3. Ready                      (control-channel is available)
@@ -213,6 +213,8 @@ The 'type' field has 10 different command values: 
     8. Register request           (dynamic chunk registration)

     9. Register result            ('rkey' to be used by sender)

    10. Register finished          (registration for current iteration finished)

    11. Unregister request         (unpin previously registered memory)

    12. Unregister finished        (confirmation that unpin completed)



A single control message, as hinted above, can contain within the data

portion an array of many commands of the same type. If there is more than
@@ -243,7 +245,7 @@ qemu_rdma_exchange_send(header, data, optional response header & data): 
   from the receiver to tell us that the receiver

   is *ready* for us to transmit some new bytes.

2. Optionally: if we are expecting a response from the command

   (that we have no yet transmitted), let's post an RQ

   (that we have not yet transmitted), let's post an RQ

   work request to receive that data a few moments later.

3. When the READY arrives, librdmacm will

   unblock us and we immediately post a RQ work request
@@ -293,8 +295,10 @@ librdmacm provides the user with a 'private data' area to be exchanged 
at connection-setup time before any infiniband traffic is generated.



Header:

    * Version (protocol version validated before send/recv occurs), uint32, network byte order

    * Flags   (bitwise OR of each capability), uint32, network byte order

    * Version (protocol version validated before send/recv occurs),

                                               uint32, network byte order

    * Flags   (bitwise OR of each capability),

                                               uint32, network byte order



There is no data portion of this header right now, so there is

no length field. The maximum size of the 'private data' section
@@ -313,7 +317,7 @@ If the version is invalid, we throw an error. 
If the version is new, we only negotiate the capabilities that the

requested version is able to perform and ignore the rest.



Currently there is only *one* capability in Version #1: dynamic page registration

Currently there is only one capability in Version #1: dynamic page registration



Finally: Negotiation happens with the Flags field: If the primary-VM

sets a flag, but the destination does not support this capability, it
@@ -413,3 +417,8 @@ TODO: 
   the use of KSM and ballooning while using RDMA.

4. Also, some form of balloon-device usage tracking would also

   help alleviate some issues.

5. Move UNREGISTER requests to a separate thread.

6. Use LRU to provide more fine-grained direction of UNREGISTER

   requests for unpinning memory in an overcommitted environment.

7. Expose UNREGISTER support to the user by way of workload-specific

   hints about application behavior.