Conservative Simulation using

1
Conservative Simulation using Distributed-Shared
Memory
Teo, Y. M., Ng, Y. K. and Onggo, B. S.
S. Department of Computer Science National
University of Singapore
2
Objectives

• Improve performance of SPaDES/Java by reducing
  overhead
• Synchronization of events
• Distributed communications
• Study the memory requirements in parallel
  simulations.

3
Presentation Outline

• Parallel Simulation
• Null Message Protocol
• Performance Improvement
• Memory Requirement
• Conclusion

4
Parallel Simulation

• Sequential simulations execute on a single thread
  in one processor.
• Ideally, parallelizing the simulation should
  enhance its real-time performance since the
  workload is distributed.
• The need to maintain causality throughout a
  parallel simulation
• gt Event synchronization protocols.
• gt Adds to inter-process communications.
• gt New bottleneck!

5
Null Message Protocol

• First designed by Chandy and Misra (1979).
• Prevents deadlock situations between LPs.
• LPi sends null messages to each of its neighbours
  at the end of every simulation pass, with
  timestamp local virtual time of LPi.
• Timestamp on null message, T, indicates that the
  source LP will not send any messages to other LPs
  before T.

6
Null Message Protocol
Clock 4 LP
FEL
LP
4
4
4
7
LP
4
LP
4
7
Performance Improvement

• Chandy-Misra-Byrants (CMB) protocol performs
  poorly due to high null message overhead. It
  transmits null msgs on every simulation pass
• NMR gt 1 for nearly all 0, T).
• Optimizations incorporated
• Carrier-null message scheme
• Flushing mechanism
• Demand-driven null message algorithm
• Remote communications using JavaSpace

8
Carrier-Null Message Algorithm

• Problem with cyclic topologies
• Use carrier-null message algorithm (Wood, Turner,
  1996)
• Avoids transmissions of redundant null messages
  in such cycles.

9
Performance Improvement

• Demand driven null messaging flushing

25
20
35
30
35
REQ
Request Channel (B)
10
Performance Evaluation

• Experiments conducted using
• PC cluster of 8 nodes running RedHat Linux
  version 7.0. Each node is a Pentium II 400 MHz
  processor with 256 MB of memory connected through
  100 Mbps switch.
• 2 benchmark programs
• PHOLD system
• Linear Pipeline

11
PHOLD (3x3, m)

• Closed system

12
Linear Pipeline (4, ?)

• Open system

Customer population
Service Center
Service Center
Service Center
Service Center
Depart
13
PHOLD (n x n, m)
14
Linear Pipeline (n, ?)
15
Performance Summary

• tage Reduction in NMR
• PHOLD system
• CMB ? Carrier-null ? 30
• ? Flushing incorporated ? 42
• ? Demand-driven null msg ? 55
• Linear Pipeline
• CMB ? Carrier-null ? 0
• ? Flushing incorporated ? 23
• ? Demand-driven null msg ? 35

16
Distributed Communications

• Originally, SPaDES/Java uses the RMI library to
  transmit messages between remote LPs. But the
  serialization phase presents a bottleneck.
• Previous performance optimization effort message
  deflation.
• Only solution to overcome remote communications
  overhead gt send less messages. How?
• Target at null messages.

17
JavaSpaces

• A special Java-Jini service developed by Sun
  Microsystems, Inc., built on top of Javas RMI,
  mimicking a tuple space.
• Abstract platform for developing complex
  distributed applications.
• Distributed data persistence.
• Holds objects, known as entries, with variable
  attribute types.
• Key concept matching of attribute types/values.

18
JavaSpaces

• 4 generic operations write, read, take and
  notify.

19
Distributed Communications

• Replace the RMI communication module in
  SPaDES/Java with one running on a single
  JavaSpace.
• Use a FrontEndSpace permits crash recovery of
  entries in the space.
• Transmission of processes and null messages
  between remote hosts go through theFrontEndSpace
  as space entries.

20
Space Communications Processes

Time t gt 0
Time 0
SProcess sender 2 receiver 1 ..
SProcess receiver 2
SProcess receiver 1
LP1
LP2
21
Space Communications Null Messages
LP4

NullMsg sender 2 ..
Req sender 2
Req sender 2
LP1
LP2
LP3
22
Performance Evaluation PHOLD(n x n, m)
23
Overall Performance Evaluation PHOLD(n x n, m)
24
Performance Summary

• tage Reduction in NMR
• CMB ? Carrier-null ? 30
• ? Flushing incorporated ? 42
• ? Demand-driven null msg ? 55
• ? JavaSpace (4 processors) ? 63
• ? JavaSpace (8 processors) ? 74

25
Memory Requirement

• Mprob ? ?ni1 MaxQueueSize(LPi)
• Mord ? ?ni1 MaxFELSize(LPi)
• Msync ? ?ni1 MaxNullMsgBufferSize(LPi)

26
Memory Requirement
27
Achievements Conclusion

• Enhanced the performance of SPaDES/Java
  through various synchronization protocols,
  achieving an excellent NMR of lt 30.
• Implemented a brand new discrete-event simulation
  library based on the concept of shared memory in
  a JavaSpace.
• Implemented a TSA into SPaDES/Java that can be
  used as a bench for memory usage studies in
  parallel simulations.

28
Acknowledgments

• Port of Singapore Authority (PSA)
• Ministry of Education, Singapore
• Constructive feed-back from referees

29
References

• SPaDES/Java homepage
• http//www.comp.nus.edu.sg/pasta/spades-java/spad
  esJava.html
• Current project webpage
• http//www.comp.nus.edu.sg/ngyewkwo/HYP.html
• MSG homepage
• http//www.comp.nus.edu.sg/rpsim/MSG