Task%20Migration%20for%20Fault-Tolerance%20in%20Mixed-Criticality%20Embedded%20Systems

1
Task Migration for Fault-Tolerance in
Mixed-Criticality Embedded Systems

• Prabhat Kumar Saraswat
• Paul Pop
• Jan Madsen

Workshop on Adaptive and Reconfigurable Embedded
Systems (at ESWeek09) October 11, 2009,
Grenoble, France
2
Problem Formulation
Mapping?
Soft Task
?
?
?
?
Hard Task
?
Utilization?

• Given Implementation and fault occurrence
• Determine Mapping and Utilization
• Such that
• Deadlines for all hard real-time tasks are
  satisfied
• Graceful degradation for soft tasks

Online task migration and utilization allocation
algorithm
3
Example

• Embedded Applications
• Timing Requirements
• Hard
• Soft
• Safety Requirements
• Permanent Faults
• Transient Faults
• No fault tolerance
• Example
• Automotive Applications

ABS (Antilock Breaking) Engine
Control Steering Wheel Transmission Control
Audio Climate Control Power Seat Sun
Roof Drivers Info. panel

• Same platform
• Economic Pressures
• Multicore

FAULTS!
Hard Constraints
Soft Constraints
4
Outline

• Application Model
• Platform Model
• Example
• Task Migration and Bandwidth Allocation (TMBA)
• Experimental results
• Conclusions

5
Application Model

• Safety-criticality
• Permanent faults
• Transient faults

6
Platform Model
7
Constant Bandwidth Server

• Each soft task is assigned a CBS with parameters
• Qi maximum server budget (bandwidth)
• Ti server period (equal to the period of the
  soft task)
• A soft task is allowed to execute for only Qi
  units of time every period Ti
• Probability of meeting the deadline (QoS) depends
  on Qi

Soft
Hard
Processor
Util.
8
CBS Example Abeni 98
Hard WCET2 Period3
Soft Requests
CBS Bandwidth 2 Period 7
18
20
2
4
10
12
22
6
8
14
16
9
Stochastic Analysis Example
How does Q affects the QoS? (Probability of
meeting the deadline for soft tasks)
Important to choose right Q!
10
Example
PE3 Fails!
PE2
PE3
PE1
Offline Solution
99.54
QoS 72.21
Q (Deadline) Period
ti
72.21
QoS
WCET Period
ti
Offline
11
Example
PE3 Fails!
PE2
PE3
PE1
Proposed Solution
Time Proposed ltltOffline
99.54
QoS 70.58
Q (Deadline) Period
ti
70.58
QoS
WCET Period
ti
Proposed
12
Greedy based Task Migration and Bandwidth
Allocation (TMBA)
Iteration System QoS Decision
Tryingt4 on PE1 X Cant be mapped Tryingt4
on PE1 84.11 Tryingt9 on PE1 78.54 Tryingt9
on PE2 56.32 Tryingt10 on PE1
70.58 Tryingt10 on PE2 59.20

• Greedy
• Hard tasks considered first
• Tasks ordered according to their Utilizations
• CBS parameters are adjusted proportionally to
  their means.

Failed Processor
t5 (0.19)
t6 (0.18)
t1 (0.4)
t7 (0.16)
t10 (0.15)
t8 (0.10)
t9 (0.16)
t3 (0.4)
t4 (0.32)
t3 (0.32)
13
Experimental Results
Case Study Portable media player QoS reported
by TMBA 73.42 Optimal QoS
74.19

• QoS resulted by TMBA is quite close to the
  offline. (difference of only 0.66)
• TMBA runs in polynomial time
• Hard deadlines were satisfied for all cases

14
Conclusion

• A greedy-based online heuristic is proposed for
  migration of safety-critical tasks to tolerate
  permanent faults on a mixed hard/soft real-time
  system.
• Better design choices can be made by taking
  stochastic execution times of soft tasks into
  consideration.
• Proposed heuristic provides very good quality
  solutions.

15
Thanks Questions?