[Ns-developers] ns3 distributed simulation code

[Faker.Moatamri@sophia.inria.fr]

> A functional MPI-based distributed simulation patch has been posted to
> appspot (link below).  The code makes minimal changes to the base and
> is off of revision f4cd995f1718 in ns-3-dev.
>
> http://codereview.appspot.com/97051/show
>
> --
> Josh Pelkey
>
> ----- Original Message -----
> From: "George Riley" <riley at ece.gatech.edu>
> To: "ns-developers" <ns-developers at ISI.EDU>
> Cc: "Josh Pelkey" <jpelkey at gatech.edu>
> Sent: Monday, July 20, 2009 4:43:22 PM GMT -05:00 US/Canada Eastern
> Subject: ns3 distributed simulation code
>
> Tom suggested we post some information regarding the MPI Distributed
> simulation code, in light of the comments below.  First an overview,
> then some details.
>
> Overview.  The distributed simulation code is designed to use allow
> a single topology to be split into "n" sub-topologies, and executed
> on "n" linux boxes in a distributed memory environment.  The current
> implementation only allows packets sent scross point-to-point links
> to be sent across simulator boundaries; the next release will support
> wireless we hope.  We tried to change as little as possible of the
> existing code base and isolate our changes in separate modules where
> possible.  There appears to be no collision or interactions with the
> multi-threaded patch posted recently.
>
> Details.
> point-to-point-channel.[h,cc]  - Made TransmitStart virtual so the
> new subclass (see below) can override.
>
> point-to-point-remote-channel.[h,cc] - new subclass of p2p channel;
> used to connect simulated nodes on one simulator to nodes on a
> separate simulator.  Overrides the TransmitStart function and
> uses MPI to send the packet across simulator processes.
>
> point-to-point-helper.[hcc].  Checks the system id on the two nodes
> being connected, and uses a p2p-remote-channel rather than a p2p-channel
> if the system id's do not match.
>
> node.[h,cc] - Added a "SetSystemId" function, to allow the system id to
> be set after the node is constructed, rather than passing parameter
> to constructor; this exists because there was no way to use
> non-default constructors on object creation.  I believe this might have
> been fixed since then, so perhaps this might not be neded.
>
> global-route-manager.cc - Do not compute routes for any node whose
> system-id
> does not match the simulator's system id.  Clearly, we don't need to
> compute routes in simulator A for nodes modeled in simulator B.
>
> default-simulator-impl.[h.cc] = Added virtual "GetSystemId" method,
> which returns the system id (MPI rank) of this process.   For
> the default-simulator object it always returns zero.
>
> distributed-simulator-impl.[h.cc] - new subclass of default-simulator-
> impl.
> THe meat of this is the overridden "run" method that handles all of
> the time management needed, using MPI.
>
> mpi-interface.[h,cc] - All MPI related processing is here in a single
> spot, rather than across several modules.
>
> packetr.[h,cc] - THis still needs work (Josh is working on it now).
> The existing seriallization code does not meet our needs; it adds
> zero bytes for the dummy payload, making the MPI messages larger, and
> it looses the unique id as packets cross simulator boundaries.  While I
> agree that we no longer truly have "unique" id's because each simulator
> presently starts it's unique id's a zero;  We will change this to
> have a 64-bit UID, with the upper 32 bits being the simulator id and the
> lower being the process-specific UID.
>
> Josh is cleaning up the patch today and will post no later than tomorrow
> for review, excepting the packet serialization that is still being
> worked.
>
> George and Josh
>
>
I did a small review and posted few comments.
Regards
Faker Moatamri