1. 7th Biennial Ptolemy Miniconference Berkeley, CA February 13, 2007 PTIDES: A Programming Model for Time- Synchronized Distributed Real-time Systems Yang Zhao, EECS, UC Berkeley Edward A. Lee, EECS, UC Berkeley Jie Liu, Microsoft Research

2. Zhao, Berkeley 2Ptolemy Miniconference, February 13, 2007 Distributed Real-Time Systems Multiple computers, comprising of sensors and actuators, connected on a network that act and react on events to meet timing constraints.

3. Zhao, Berkeley 3Ptolemy Miniconference, February 13, 2007 Related Work RTOS: prioritize tasks and trigger computation. Languages: synchronous languages: Esterel, Scade, Luster, Signal time-triggered languages and the concept of logical execution time: Simulink (RTW), Giotto. Real-Time Networking Time Triggered Protocol (MARS project) FlexRay (BMW, etc.) SAFEbus (Honeywell) deterministic message sending or guaranteed message latency clock synchronization requiring special bus-architecture

4. Zhao, Berkeley 4Ptolemy Miniconference, February 13, 2007 Related Work Time synchronization over standard network NTP (~ms): internet RBS (~ms): wireless network IEEE1588(~ns): Ethernet Provides a useful common notion of time for general distributed real- time systems. How to design such systems leveraging time synchronization? Event-triggered approach: more dynamic environment. PTIDES (Programming Time-Integrated Distributed Embedded Systems): Discrete-event semantics Carefully chosen relations between model time and real time. Efficient execution based on causality analysis that guarantees determinacy is preserved at runtime. Does not depends on domain specific network architectures

5. Zhao, Berkeley 5Ptolemy Miniconference, February 13, 2007 Discrete Event Modeling in Ptolemy II DE Director implements timed semantics to make sure ordering of time stamps be respected. Event source Time line Reactive actors Signal

6. Zhao, Berkeley 6Ptolemy Miniconference, February 13, 2007 Discrete Event Models DE models have been primarily used in performance modeling and simulation: Hardware systems (VHDL, Verilog) Manufacturing systems Communication networks (OPNET, NS-2) Transportation systems Stock market DDE is usually to accelerate simulation, not to implement distributed real-time systems. PTIDES uses DE as a application specification language which serves as a semantic basis for obtaining determinism in distributed real-time systems. Applications are given as distributed DE models. Certain events have their model time mapped to real time.

7. Zhao, Berkeley 7Ptolemy Miniconference, February 13, 2007 Example: Networked Cameras Camera has computer-controlled zoom and focus capabilities. Zoom and focus take time to set up, and the camera should not take picture during this period. The video of each camera is synchronized and time stamped All the views of some interesting moment can be played back in sequence How often a camera takes picture is also controlled by the computer. e: zoom camera at t e’: take picture at t’ If t – t’ <, then e should be dropped.

8. Zhao, Berkeley 8Ptolemy Miniconference, February 13, 2007 DE Model for the Example

9. Zhao, Berkeley 9Ptolemy Miniconference, February 13, 2007 DE Model on the Central Computer zoom in all t r = 2 tmtm v 1 2 132 v = 2: zoom in camera.

10. Zhao, Berkeley 10Ptolemy Miniconference, February 13, 2007 DE Model on the Central Computer double period t r = 5.5 tmtm v 1 2 132 v = 2: zoom in camera. 3 4 465 v > 2: change period p to (v-2)*p.

11. Zhao, Berkeley 11Ptolemy Miniconference, February 13, 2007 DE Model for the Cameras tmtm v 1 2 132 3 4 465 135624 tmtm 1 v 109 7 8

12. Zhao, Berkeley 12Ptolemy Miniconference, February 13, 2007 DE Model for the Cameras tmtm v 1 2 132 3 4 465 tmtm v 1 2 132 3 4 465 Assume d = 1

13. Zhao, Berkeley 13Ptolemy Miniconference, February 13, 2007 DE Model for the Cameras tmtm v 1 2 132 3 4 465 Assume d = 1 tmtm v 1 2 132 3 4 465 tmtm 1 2 132 v

14. Zhao, Berkeley 14Ptolemy Miniconference, February 13, 2007 DE Model for the Cameras 135624 tmtm 1 v 109 7 8 tmtm 1 2 132 v 135624 tmtm 1 v 9 7 8 2 e: zoom camera at t e’: take picture at t’ If t – t’ < =1, then e should be dropped.

15. Zhao, Berkeley 15Ptolemy Miniconference, February 13, 2007 DE Model for the Cameras 135624 tmtm 1 v 109 7 8 2 Ex. v = 1, t m = 1: take a picture at t r = 1. v = 2, t m = 3: zoom in camera at t r = 3.

16. Zhao, Berkeley 16Ptolemy Miniconference, February 13, 2007 Actors bind model time to real time double period t r = 5.5 tmtm v 1 2 132 3 4 465 producing an event with model time corresponding to the real time when the user input happens.

17. Zhao, Berkeley 17Ptolemy Miniconference, February 13, 2007 Actors bind model time to real time 135624 tmtm 1 v 109 7 8 2 The Device actor producing an physical action at the real time corresponding to the model time of each input event. Input events must be made available for processing at real time strictly earlier than the model time.

18. Zhao, Berkeley 18Ptolemy Miniconference, February 13, 2007 Challenges in Executing the Model Not be practical nor efficient to use a centralized event queue to sort events in chronological order. Do the techniques developed for distributed DE simulation work? Conservative (Chandy and Misra) Optimistic (Time warp, Jefferson) Our approach: events only need to be processed in time-stamp order when they are causally related.

19. Zhao, Berkeley 19Ptolemy Miniconference, February 13, 2007 Conservative Execution of the Example tmtm 1 132 v Assure no event with time stamp t m <= 3 at t r = 3 Received at real time t r > 3 Deadline missed!

20. Zhao, Berkeley 20Ptolemy Miniconference, February 13, 2007 Challenges in Executing the Model Not be practical nor efficient to use a centralized event queue to sort events in chronological order. Do the techniques developed for distributed DE simulation work? Conservative (Chandy and Misra) Optimistic (Time warp, Jefferson) Our approach: events only need to be processed in time-stamp order when they are causally related.

21. Zhao, Berkeley 21Ptolemy Miniconference, February 13, 2007 Intuition on Out of Order Execution tmtm 1 132 v If there is an event with time stamp t m <= 3-d at t r <= 3-d Received by real time t r < 3-d+D tmtm 1 132 ? tmtm 1 13-d ? D : is the up bound of network delay; d > D

22. Zhao, Berkeley 22Ptolemy Miniconference, February 13, 2007 Intuition on Out of Order Execution tmtm 1 132 v D : is the up bound of network delay; d > D We can always safely process an event e at the first input of Merge by t r > t m - d + D, no matter whether there are events received at s 1 or not! (If some sub-system fails, the rest of the system can continue without being blocked.)

23. Zhao, Berkeley 23Ptolemy Miniconference, February 13, 2007 Relevant Dependency Analysis Relevant dependency analysis gives a formal framework for analyzing causality relationships to determine the minimal ordering constraints on processing events. It capture the idea that events only need to be processed in time-stamp order when they are causally related. Can preserve the deterministic behaviors specified in DE models without paying the penalty of totally ordered executions. Yang Zhao, Jie Liu and Edward A. Lee, "A Programming Model for Time- Synchronized Distributed Real-Time Systems", in Proceedings of the 13th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS 07), Bellevue, WA, United States, April 3-6, 2007.A Programming Model for Time- Synchronized Distributed Real-Time Systems

24. Zhao, Berkeley 24Ptolemy Miniconference, February 13, 2007 Causality Interface [Zhou--Lee] Causality interface of a component declares the dependency between input and output.

25. Zhao, Berkeley 25Ptolemy Miniconference, February 13, 2007 Causality Interface Composition

26. Zhao, Berkeley 26Ptolemy Miniconference, February 13, 2007 Relevant Dependency Relevant dependency on any pair of input ports p1 and p2 specifies whether an event at p1 will affect an output signal that may also depend on an event at p2.

27. Zhao, Berkeley 27Ptolemy Miniconference, February 13, 2007 Relevant Dependency d( p 1, p 6 ) = d means any event with time stamp t at p 2 can be processed when all events at p 1 are known up to time stamp t − d.

28. Zhao, Berkeley 28Ptolemy Miniconference, February 13, 2007 Relevant Order Relevant dependencies induce a partial order, called the relevant order, on events. e 1 < r e 2 means that e1 must be processed before e2. If neither e 1 < r e 2, nor e 2 < r e 1, i.e. e 1 || r e 2, then e 1, e 2 can be processed in any order. This technique can be adapted to distributed execution.

29. Zhao, Berkeley 29Ptolemy Miniconference, February 13, 2007 Conclusion Time synchronization can greatly change the way distributed systems are designed. Discrete-event model can be used as a programming model to explicitly specify and manipulate time relations between events. It is challenging to design distributed systems to make sure they are executable. Causality analysis can be used to determine when events can be processed out of order to improve executability and reliability. Work in progress: statically check whether a system design is executable. Implementing a runtime environment on P1000 by Agilent.