The Beobot2.0 software system uses ICE to communicate between computers in the cluster.

However, we would like to improve it and add tools that can evaluate how the individual modules are performing, or whether the network is congested by which data packets.

Distributed system features that are important:

• Performance optimization tools:

   timers on modules (evolve, updateMessage)
   latency information of when the packets arrive 
   The amount of data in the **network** to if it is **congested** 

• Packet synchronization

   * only evoke updateMessage if a set of packets with the **same index number** is received.
   * Be able to set the policy for packet dropping for individual message queues

All comes down to serialization.

Real Time Robotics OS research at the kernel level down the line.

• Does not put too much priority in answering user inputs.
• Knows and Prioritize jobs that are the most critical to the survival of the robot.
• Can allocate resources properly to satisfy all the modules.

MOSIX and Scyld Beowulf operating systems that encapsulates all the individual nodes that does all the job distribution internally.

General notes to work your way around Mandriva 2009 and Ubuntu 9.10..