Flexibility Driven Scheduling and Mapping for Distributed Real-Time - - PowerPoint PPT Presentation

1 of 14 1 /23

Flexibility Driven Scheduling and Mapping for Distributed Real-Time Systems

Paul Pop, Petru Eles, Zebo Peng

Department of Computer and Information S cience Linköpings universitet, Sweden

2 of 14 2 /23

Outline

Introduction Incremental design process

Mapping and scheduling

Problem formulation Mapping strategy Experimental results Conclusions

3 of 14 3 /23

Introduction

Characteristics:

Incremental design process, engineering change; Distributed real-time embedded systems; Heterogeneous architectures; Fixed priority pre-emptive scheduling for processes;

static cyclic scheduling for messages;

Communications using a time-division multiple-access (TDMA) scheme:

• H. Kopetz, G. Grünsteidl. TTP-A Protocol for Fault-Tolerant Real-Time S
• ystems. IEEE Computer ‘ 94.

Contributions:

Mapping and scheduling considered inside an incremental design process; Two design criteria (and their metrics) that drive our mapping strategies to

solutions supporting an incremental design process;

Two mapping algorithms.

Message:

Engineering change can be successfully addressed at system level.

4 of 14 4 /23

“Classic” Mapping and Scheduling

I/ O Interface

• Comm. Controller

CPU RAM ROM AS IC

S S

1

S

2

S

3

S S

1

S

2

S

3

TDMA Round Cycle of two rounds S lot

5 of 14 5 /23

S

tart from an already existing system with applications:

In practice, very uncommon to start from scratch.

Implement new functionality on this system (increment):

As few as possible modifications of the existing applications,

to reduce design and testing time;

Plan for the next increment:

It should be easy to add functionality in the future.

Incremental Design Process

6 of 14 6 /23

Mapping and Scheduling

No modifications are performed to t he exist ing applications.

Existing applications

N-1

Map and schedule so that the future applications will have a chance to fit.

Current applications

N

Do not exist yet at Version N!

Future applications

Version N+1

7 of 14 7 /23

Mapping and Scheduling Example

Processor Bus

Current apps Future apps Existing applications

P3 P4 m 4 m 5 P1 P2 m 1 m 2 m 3

8 of 14 8 /23

Mapping and Scheduling Example, Cont.

Processor Bus

Current apps Future apps Existing applications

P3 P4 m 4 m 5 P1 P2 m 1 m 2 m 3

9 of 14 9 /23

Mapping and Scheduling Example, Cont.

Processor Bus

Current apps Future apps Existing applications

P4 P3 m 4 m 5 P2 P1 m 1 m 2 m 3

10 of 14 10 /23

Problem Formulation

Input

A set of exist ing applications modelled as process sets. A current application to be mapped. Each process in the application has its own period, priorit y and deadline. Each process has a pot ent ial set of nodes to be mapped to and a WCET. The system architecture is given.

Output

A mapping and scheduling of the current application, so that:

• Requirement a: constraints of the current application are satisfied

and minimal modifications are performed to the exist ing applications.

• Requirement b: new fut ure applications can be mapped
• n the resulted system.

11 of 14 11 /23

Mapping and Scheduling, Requirement a)

Mapping and scheduling of the current application, so that:

Constraints of the current application are satisfied and minimal modifications are performed to the exist ing applications.

∑

Ω ∈ Γ

= Ω

i

i

R R ) (

Subset selection problem

S

elect that subset Ω of existing applications which guarantees that the current application fits and the modification cost R(Ω) is minimized:

12 of 14 12 /23

Characterizing Existing Applications

R({Γ7})=20, R({Γ3})=50, R({Γ3 , Γ7})=70, R({Γ4, Γ7})=90 (the inclusion of Γ4 triggers the inclusion of Γ7), R({Γ2 , Γ3})=120, R({Γ3 , Γ4 , Γ7})=140, R({Γ1})=150, .... The total number of possible subsets is 16.

Γ1 Γ2 Γ4 Γ5 Γ6 Γ7 Γ3 Γ8 Γ9 Γ10 Γ1 Γ2 Γ4 Γ5 Γ6 Γ7 Γ3 Γ8 Γ9 Γ10

150 70 70 50 50 20

13 of 14 13 /23

Mapping and Scheduling, Requirement b)

Mapping and scheduling of the current application, so that:

New fut ure applications can be mapped on the resulted system.

P4 m 5

Design criteria reflect t he degree t o which a design meet s t he requirement b); Design metrics quantify the degree to which the criteria are met; Heuristics to improve the design metrics.

14 of 14 14 /23 10 20 30 40 50 60 70 80 90 100 0.02 0.05 0.1 0.2

Typical ut ilizat ion fact ors Uf=C/ T Probability [% ]

Characterizing Future Applications

S

mallest expected period T min

Expected necessary bandwidth bneed

Probability [% ]

10 20 30 40 50 60 70 80 90 100 2 4 6 8

Typical message sizes [bytes]

15 of 14 15 /23

Mapping and Scheduling: Processes

Design criterion for processes: available ut ilizat ion

How well t he available ut ilizat ion of t he current design alternative accommodate

a family of f ut ure applications that are characterized as outlined before;

Design metrics for the first design criterion

C1

P for processes

How much of the largest f ut ure application (total available utilization),

cannot be mapped on the current design alternative;

Bin-packing algorit hm using t he best -f it policy:

utilization factors of processes as obj ects to be packed, and the slack as cont ainers. C1

P=40%

16 of 14 16 /23

Mapping and Scheduling: Messages

First design criterion for messages: slack sizes

How well t he slack sizes of t he current design alternative accommodate

a family of f ut ure applications that are characterized as outlined before;

Tries to cluster t he available slack: t he best slack would be a cont iguous slack.

a) b) c) contiguous slack

Design metrics for the first design criterion

C1

m for messages;

How much of the largest f ut ure application (contiguous slack),

cannot be mapped on the current design alternative;

Bin-packing algorit hm using t he best -f it policy:

processes as obj ects to be packed, and the slack as containers. C1

m=0%

C1

m=0%

C1

m=75%

17 of 14 17 /23

Mapping and Scheduling: Messages, Cont.

S

econd design criterion: slack distribution for messages

Used for the reduction of design space exploration How well the slack of the current design alternative is distributed in time

to accommodate the messages of a family of fut ure applications;

Tries to dist ribut e the slack so that we periodically (T min) have enough necessary

bandwith bneed for the most demanding future application. a) b) Tmin

Design metrics for the second design criterion

C2

m is the sum of minimum periodic slack inside a T min period on each processor.

C2

m=0 < bneed =40ms

C2

m=40 ms

bneed

18 of 14 18 /23

Mapping and Scheduling Strategy

Initial mapping and scheduling Requirement a)

Minimizing the modification cost R(Ω), subset selection:

Exhaustive Search (ES) Ad-Hoc Solut ion (AH) Subset Selection Heuristic (SH)

) , max( ) ( ) (

2 2 1 1 1 1 m need m m m P P

C b w C w C w C − + + =

Requirement b)

Starting from a valid solution, heuristics to minimize the obj ective function:

Ad-Hoc approach (AH), little support for incremental design. Simulated Annealing (SA), near optimal value for C. Mapping Heuristic (MH):

Iteratively performs design transformations that improve the design; Examines only transformations with the highest pot ent ial to improve the design; Design transformations:

moving a process to a different processor, moving a message to a different slack on the bus.

19 of 14 19 /23

200 400 600 800 1000 1200 160 240 320 400 480 AS S H ES

Average Modification Cost R(Ωmin) How do the subset selection algorithms compare? exist ing applications: 400 Number of processes in the current application

Experimental Results

20 of 14 20 /23

20 40 60 80 100 120 140 160 40 80 160 240 320 AM MH S A

• Avg. %

Deviation from near optimal How does the quality (cost function) of the mapping heuristic (MH) compare to the ad-hoc approach (AM) and the simulated annealing (S A)? exist ing applications: 400 Number of processes in the current application

Experimental Results

21 of 14 21 /23

20 40 60 80 100 40 80 160 240 MH* AM

Experimental Results, Cont.

%

• f fut ure applications mapped

exist ing applications: 400, future application: 80 Number of processes in the current application Are the mapping strategies proposed facilitating the implementation of future applications?

Existing application Current application Future application No modifications allowed

22 of 14 22 /23

20 40 60 80 100 40 80 160 240 AM MH* MH

Experimental Results, Cont.

%

• f fut ure applications mapped

exist ing applications: 400, future application: 80 Number of processes in the current application Are the mapping strategies proposed facilitating the implementation of future applications?

Existing application Current application Future application Modifications allowed

23 of 14 23 /23

Conclusions

Distributed real-time embedded systems

Fixed priority pre-emptive scheduling for processes S

tatic cyclic scheduling for messages (TDMA)

Mapping and scheduling considered inside an incremental design process

Constraints of the current application are satisfied

and minimal modifications are performed to the exist ing applications

New fut ure applications can be mapped on the resulted system

Mapping strategy

Design criteria+metrics which drive mapping strategies to solutions

supporting an incremental design process

Iterative improvement mapping algorithm; subset selection algorithm