Scheduling of Distributed Real-Time Systems

courseware

Scheduling of Distributed Real-Time Systems

Jan Madsen

Informatics and Mathematical ModellingTechnical University of Denmark

Richard Petersens Plads, Building 321DK2800 Lyngby, Denmark

[email protected]

(c) Jan Madsen 2SoC-MOBINET courseware

Multi-processor scheduling

1

34

2

a memb

b

os

3

4

mema

os

2

1

scheduling


Characteristics to be handled

Processes: preemptive and non-preemptive periodic and aperidoic processes with multiple levels of importance group of processes with single deadline

Constraints and requirements: end-to-end timing precedence relations communication shared resources placement hard and soft deadlines fault tolerance


Handling interfaces between

CPU scheduling and resource allocation IO scheduling and CPU scheduling CPU scheduling and communication scheduling Local and distributed scheduling Static scheduling of critical processes and dynamic

scheduling of other processes

Comprehensive results will not exist for many years!


Phases of real-time distributed systems scheduling

Allocation assigning processes and resources to processors in the

system Scheduling

Ordering the execution of processes and communications to meet timing and resource constraints

Dispatching Executing the processes in conformance with the

scheduler’s decisions


Approaches to embedded system scheduling

deterministic (static) scheduling Allocating and static scheduling all periodic processes

off-line Allocate time-slots for handling non-periodic processes

Distributed scheduling Each CPU runs its own scheduler Set of processes is distributed, statically allocated but

dynamically activated


Static distributed scheduling

Typical approach

– Construct a comprehensive graph containing all process instances that executes in an interval of length T (T is the least common multiple of all process periods)

– Cluster communicating processes– Allocate clusters of processes to PEs

and schedule processes and communications


ArchitectureSpecification

Characterization Scheduling

A Simple Example

t1

t3t2

PE1 PE2

bus

t1

t2

t3

PE1 PE2 PE1

PE2


First solution

t1

t3t2

PE1 PE2

bus



t1

t2

t3

PE1 PE2 PE1

PE215 15

10 20

5 -

t1 t2

t3

20


Introducing communication

t1

t3t2

PE1 PE2

bus



t1

t2

t3

PE1 PE2 PE1

PE215 15

10 20

5 -

50 10

t1 t2

t3

25

bus

Can transfer2 data unitsper time unit

5


Introducing interfaces

t1

t3t2

PE1 PE2

bus



t1

t2

t3

PE1 PE2 PE1

PE215 15

10 20

5 -

50 10

i1 i2

t1 t2

t3

27

bus

i1

i2

Can buffer10 data unitsper time unit


PE

Memory?

t1

Memory contributions:program

data

data to be transferred

Memory utilization:

time

Me

mor

y si

zePE t1


Introducing memory

t1

t3t2

PE1 PE2

bus



t1

t2

t3

PE1 PE2 PE1

15 5,5 15 10,5

10 5,5 20 10,5

5 10,2 -

50 10

i1 i2

t1 t2 Peak memory

1052

50

10 = 77


Dynamic multi-processor scheduling

Primary objective is to ensure that all timing constraints are met

Serious difficulties in validating hard timing constraints

Assumptions: Each processor has its own scheduler The scheduler uses a uni-processor scheduling

algorithm Schedulers on different processors need not use the

same algorithm


Multi-processor scheduling

Task assignment Most real-time systems are static, tasks are partitioned

and statically bound to processors

Inter-processor synchronization Ensuring that precedence constraints of tasks on

different processors are always satisfied


Task assignment

Often done off-line NP-hard problem Assignment based on:

Execution times Resource requirements Data dependencies Timing constraints Communication cost ...

b

os

a

os

3

42

1


Task assignment - RMFF

1

34

2Assume zero communication overhead

Scheduling based on fixed priorities

A synchronization signal makes sure that is released as soon as has completed

3 2

Example:

1 a

i k i

k

Rate-Monotonic First-Fit algorithm:1. Sort tasks in increasing order according to their period

2. Assign tasks one by one is assigned to is assigned to if the total utilization of and the tasks

already assigned to < URM


Example

1

34

2

ri Ti ei

0 4 2

0 6 2+2

4 6 3

1

2

4

3

b

os

4

a

os

1

2

3


Dynamic scheduling

b

os

4

a

os

1

2

3

0 4 6 8 102 14 1612

1

2a

0 4 6 8 102 14 1612

3

4b

RM RM


Changing synchronization protocol

0 4 6 8 102

0 4 6 8 102

14 1612

14 1612

b

os

4

a

os

1

2

31

3

2

4

a

b

RM EDF


Multi-processing anomalies

Assume a set of tasks optimally scheduled on a multiprocessor system with: fixed number of processors fixed execution times (ei)

precedence constraints Then

changing the priority list increasing the number of processor reducing execution times weakening the precedence constraints

May increase the scheduling length!


Example of anomalies

1

3

2

4 5

1

3

2

4 5

Reduce e1 of task 1

a

b

a

b

Task 2 and 4 are sharing a resource, i.e. mutually exclusion

1 3

42

5


Consequences of anomalies

Tasks may complete before their WCETs So most on-line scheduling algorithms are

subject to experience anomalies Simple but inefficient solution:

Have tasks completing early idle


Summary

Introduction to classical uni-processor multi-task scheduling

illustration of multi-processor scheduling Not covered:

Priority inversion when having shared resources Context switching and cache overhead Overload conditions Low power scheduling,

Increasing idle periods on processors Voltage scaling

Communication

Documents

Scheduling of Distributed Real-Time Systems