Periodic tasks

Arrival time C: computing time F: finishing/response time time

SCHEDULING PERIODIC TASKS

R: release time

T:period D: deadline

Periodic tasks (the simplified case)

Scheduled to run Arrival time computing Finishing/response time

Assumptions on task sets

Each task is released at a given constant rate

Given by the period T The same worst case execution time: C The same relative deadline: D=T (not a restriction) The same relative arrival time: A=0 (not a restriction) The same release time, released as soon as they arrive No sharing resources (consider this later) E.g context switch etc (consider this later)
4

All instances of a task have:

time T:period R: release time D: deadline

All tasks are independent

All overheads in the kernel are assumed to be zero

Periodic task model

CPU utilization

A task = (C, T)

C: worst case execution time/computing time (C<=T!) T: period (D=T)

C/T is the CPU utilization of a task U= Ci/Ti is the CPU utilization of a task set Note that the CPU utilization is a measure on how busy the processor could be during the shortest repeating cycle: T1*T2*...*Tn

A task set: (Ci,Ti)

All tasks are independent The periods of tasks start at 0 simultaneously

U>1 (overload): some task will fail to meet its deadline no matter what algorithms you use! U<=1: it will depend on the scheduling algorithms

If U=1 and the CPU is kept busy (non idle algorithms e.g. EDF), all deadlines will be met

Scheduling Algorithms

Static cyclic scheduling

Static Cyclic Scheduling (SCS) Earliest Deadline First (EDF) Rate Monotonic Scheduling (RMS) Deadline Monotonic Scheduling (DMS)

Shortest repeating cycle = least common multiple (LCM) Within the cycle, it is possible to construct a static schedule i.e. a time table Schedule task instances according to the time table within each cycle Synchronous programming languages: Esterel, Lustre, Signal
8

Example: the Car Controller

Activities of a car control system. Let
1. 2. 3.

The car controller: static cyclic scheduling

C= worst case execution time T= (sampling) period D= deadline

The shortest repeating cycle = 80ms All task instances within the cycle:
0 Speed ABS Fuel 20 Speed 40 Speed ABS 60 Speed 80

Speed measurment: C=4ms, T=20ms, D=20ms ABS control: C=10ms,T=40ms, D=40ms Fuel injection: C=40ms,T=80ms, D=80ms Other software with soft deadlines e.g audio, air condition etc

Try any method to schedule the tasks

10

The car controller: time table constructed with EDF

76
FUEL-4

Static cyclic scheduling: + and

80 0
Soft RT tasks speed

4
ABS

14
FUEL-1

Deterministic: predictable (+) Easy to implement (+) Inflexible (-)

64
speed

20

Difficult to modify, e.g adding another task Difficult to handle external events
Huge memory-usage Difficult to construct the time table

A feasible Schedule!
FUEL-3

speed

The table can be huge (-)

24
Fuel-2

60

54

ABS

44

speed

40

11

12

Example: shortest repeating cycle

Earliest Deadline First (EDF)

OBS: The LCM determines the size of the time table

Task model

LCM =50ms for tasks with periods: 5ms, 10ms and 25ms LCM =7*13*23=2093 ms for tasks with periods: 7ms, 13ms and 23ms (very much bigger)

a set of independent periodic tasks (not necessarily the simplified task model) Whenever a new task arrive, sort the ready queue so that the task closest to the end of its period assigned the highest priority Preempt the running task if it is not placed in the first of the queue in the last sorting EDF can schedule the task set if any one else can Ci/Ti <= 1 iff the task set is schedulable
14

EDF:

So if possible, manipulate the periods so that they are multiples of each other

Easier to find a feasible schedule and Reduce the size of the static schedule, thus less memory usage

FACT 1: EDF is optimal

FACT 2 (Scedulability test):

13

Example

EDF: + and

Task set: {(2,5),(4,7)} U = 2/5 + 4/7= 34/35 ~ 0.97 (schedulable!)

Note that this is just the simple EDF algorithm; it works for all types of tasks: periodic or non periodic

It is simple and works nicely in theory (+) Simple schedulability test: U <= 1 (+) Optimal (+) Best CPU utilization (+)

10

15

35

14

35

Difficult to implement in practice. It is not very often adopted due to the dynamic priority-assignment (expensive to sort the ready queue on-line), which has nothing to do with the periods of tasks. Note that Any task could get the highest priority (-) Non stable: if any task instance fails to meet its deadline, the system is not predictable, any instance of any task may fail (-)

We use periods to assign static priorities: RMS

15 16

Rate Monotonic Scheduling: task model

Assume a set of periodic tasks: (Ci,Ti) Di=Ti Tasks are always released at the start of their periods Tasks are independent

RMS: fixed/static-priority scheduling

Rate Monotonic Fixed-Priority Assignment:

Tasks with smaller periods get higher priorities

Run-Time Scheduling:

Preemptive highest priority first

FACT: RMS is optimal in the sense:

If a task set is schedulable with any fixed-priority scheduling algorithm, it is also schedulable with RMS

17

18

Example
{(20,100),(40,150),(100,350)} T1 20 0 20 100 Pr(T1)=1, Pr(T2)=2, Pr(T3)=3 20 200 20 300

Example

Task set: T1=(2,5), T2=(4,7) U = 2/5 + 4/7= 34/35 ~ 0.97 (schedulable?) RMS priority assignment: Pr(T1)=1, Pr(T2)=2

T2

40

40 150

300

40

0 2

10 15 Missing the deadline! 14

35

T3 0

40

30

10

20 350
19

5 7

35

20

RMS: schedulability test

The famous Utilization Bound test (UB test) [by Liu and Layland, 1973: a classic result]

U<1 doesnt imply schedulable with RMS

Assume a set of n independent tasks:

OBS: the previous example is schedulable by EDF, not RMS

S= {(C1,T1)(C2,T2)...(Cn,Tn)} and U = Ci/Ti

FACT: if U<= n*(21/n-1), then S is schedulable by RMS Note that the bound depends only on the size of the task set

Idea: utilization bound

Given a task set S, find X(S) such that U<= X(S) if and only if S is schedulable by RMS (necessary and sufficient test) Note that the bound X(S) for EDF is 1

21

22

Example: Utilization bounds

B(1)=1.0 B(2)=0.828 B(3)=0.779 B(4)=0.756 B(5)=0.743 B(6)=0.734 B(7)=0.728 B(8)=0.724 U()=0.693

Example: applying UB Test

C Task 1 20 T (D=T) 100 C/T 0.200

Task 2
Task 3

40
100

150
350

0.267
0.286

Note that U()=0.693 !

Total utilization: U=0.2+0.267+0.286=0.753<B(3)=0.779! The task set is schedulable

23

24

Example: RM Scheduling
{(20,100),(40,150),(100,350)} 20 0 20 100 20 200 20 300

UB test is only sufficient, not necessay!

Let U= Ci/Ti and B(n) = n*(21/n-1) Three possible outcomes:

0<= U<= B(n): B(n)<U<=1: 1< U :

schedulable no conclusion overload

40

40 150

300

40

Thus, the test may be too conservative (exact test will be given later)

40

30

10

20 350
25 26

Example: UB test is sufficient, not necessary

Assume a task set: {(1,3),(1,5),(1,6),(2,10)} CPU utilization U= 1/3+1/5+1/6+2/10=0.899 The utilization bound B(4)=0.756 The task set fails in the UB test due to U>B(4) Question: is the task set schedulable? Answer: YES

{(1,3),(1,5),(1,6),(2,10)}
0 0 0 3 5 6 6 9 10 12 12 15 15

Response times? Worst case? First period? Why?

18 20 18

0
27

10

20
28

This is only for the first periods! But we will see that this is enough to tell that the task set is schedullable.

How to deal with tasks with the same period

RMS: Summary

What should we do if tasks have the same period? Should we assign the same priority to the tasks? How about the UB test? Is it still sufficient? What happens at run time?

Task model:

priodic, independent, D=T, and a task= (Ci,Ti)

Fixed-priority assignment:

smaller periods = higher priorities

Run time scheduling: Preemptive HPF Sufficient schedulability test: U<= n*(21/n-1) Precise/exact schedulability test exists

29

30

RMS: + and

Critical instant: an important observation

Simple to understand (and remember!) (+) Easy to implement (static/fixed priority assignment)(+) Stable: though some of the lower priority tasks fail to meet deadlines, others may meet deadlines (+) lower CPU utilization (-) Requires D=T (-) Only deal with independent tasks (-) Non-precise schedulability analysis (-) But these are not really disadvantages;they can be fixed (+++)

Note that in our examples, we have assumed that all tasks are released at the same time: this is to consider the critical instant (the worst case senario)

If tasks meet the first deadlines (the first periods), they will do so in the future (why?)

We can solve all these problems except lower utilization

Critical instant of a task is the time at which the release of the task will yield the largest response time. It occurs when the task is released simultaneously with higher priority tasks Note that the start of a task period is not necessarily the same as any of the other periods: but the delay between two releases should be equal to the constant period (otherwise we have jitters)

31

32

Sufficient and necessary schedulability analysis

Worst case response time calculation: example

{(1,3),(1,5),(1,6),(2,10)}
0 0 0 3 5 6 6 9 10 12 12 15 15 18
Response times? Worst case? First period? Why?

Simple ideas [Mathai Joseph and Paritosh Pandya, 1986]:

Critical instant: the worst case response time for all tasks is given when all tasks are released at the same time Calculate the worst case response time R for each task with deadline D. If R<=D, the task is schedulable/feasible. Repeat the same check for all tasks If all tasks pass the test, the task set is schedulable If some tasks pass the test, they will meet their deadlines even the other dont (stable and predictable) how to calculate the worst case response times?

18 20

Question:

We did this before!

0
33

10

20
34

Worst case response time calculation: example

{(1,3),(1,5),(1,6),(2,10)}
0 0 0 3 5 6 6 9 10 12 12 15 15
Response times? Worst case? First period? Why?

Calculation of worst case response times

[Mathai Joseph and Paritosh Pandya, 1986]

Let Ri stand for the response time for task i. Then Ri= Ci + j I(i,j)

18 20

W CR=1

Ci is the computing time I(i,j) is the so-called interference of task j to i I(i,j) = 0 if task i has higher priority than j x denotes the least integer larger than x E.g 3.2 = 4, 3 =3, 1.9 =2

WCR=2

You dont have to Check this area!

I(i,j) = Ri/Tj*Cj if task i has lower priority than j

18

WCR=3

Ri= Ci + j HP(i) Ri/Tj*Cj

0
What to do if too many?

10

20

WCR=9
35 36

Intuition on the equation Ri= Ci + j HP(i) Ri/Tj*Cj

Equation solving and schedulability analysis

Ri/Tj is the number of instances of task j during Rj Ri/Tj*Cj is the time needed to execute all instances of task j released within Rj j HP(i) Ri/Tj*Cj is the time needed to execute instances of tasks with higher priorities than task i, released during Rj Rj is the sum of the time required for executing task instances with higher priorities than task j and its own computing time

We need to solve the equation: Ri= Ci + j HP(i) Ri/Tj*Cj This can be done by numerical methods to compute the fixed point of the equation e.g. By iteration: let

Ri0 = Ci + j HP(i) Cj = C1+C2+...+Ci (the first guess) Rik+1 = Ci + j HP(i) Rik/Tj*Cj (the (k+1)th guess) Rim+1>Ti or non schedulable Rim<Ti and Rim+1 = Rim schedulable

The iteration stops when either

This is the so called Precise test

38

37

Example

Combine UB and Precise tests

Assume a task set: {(1,3),(1,5),(1,6),(2,10)} Question: is the task set schedulable? Answer: YES Because R11 = R10 = C1=1 (done) R20 = C2 + C1=2, R21 = C2 + R20/T1*C1=1+ 2/3*1=2 (done)

Order tasks according to their priorities (periods) Use UB test as far as you can until you find the first non-schedulable task Calculate response time for the task and all the tasks with lower priority

39

40

Example (combine UB test and precise test)

Example

Consider the same task set: {(1,3),(1,5),(1,6),(3,10)} CPU utilization U= 1/3+1/5+1/6+3/10=0.899> B(4)= 0.756

Fail the UB test!

But U(3)= 1/3+1/5+1/6=0.699<B(3)=0.779

C Task 1 Task 2 Task 3 40 40 100

T 100 150 350

C/T 0.400 0.267 0.286

This means that the first 3 tasks are schedulable

R40 = C1+C2+C3+C4= 6 R41 = C4+R40/T1*C1+R40/T2*C2+R40/T3*C3 = 3 + 6/3*1+6/5*1+6/6*1=8 R42 = C4+R41/T1*C1+R41/T2*C2+R41/T3*C3 = 3 + 8/3*1+8/5*1+8/6*1 = 3+3+2+2 = 10 3 R4 = C4+R42/T1*C1+R42/T2*C2+R42/T3*C3 = 3+ 4 + 2 + 2 = 11 (task 4 is non schedulable!

Question: is task 4 set schedulable?

Total utilization: U=0.4+0.267+0.286= 0.953>B(3)=0.779! UB test is inclusive: we need Precise test but we do have U(T1)+U(T2)= 0.4+0.267= 0.667<U(2)=0.828 so we need to calculate R3 only!
41 42

Calculate response time for task 3

Question: other priority-assignments

R30 =

C1+C2+C3= 180 R31 = C3+R30/T1*C1+R30/T2*C2 =100+ 180/100*40+180/150*40 =100+2*40+2*40=260 R32 =C3+R31/T1*C1+R31/T2*C2 =100+ 260/100*40+260/150*40=300 R33 =C3+R32/T1*C1+R32/T2*C2 =100+ 300/100*40+300/150*40=300 (done)

Could we calculate the response times by the same equation for different priority assignment?

Task 3 is schedulable and so are the others!

43

44

Precedence constraints
How to handle precedence constraints?

Summary: Three ways to check schedulability

1. 2. 3.

We can always try the old method: static cyclic scheduling! Alternatively, take the precedence constraints (DAG) into account in priority assignment: the priority-ordering must satisfy the precedence constraints

UB test (simple but conservative) Response time calculation (precise test) Construct a schedule for the first periods

Precise schedulability test is valid: use the same method as beforee to calculate the response times.

assume the first instances arrive at time 0 (critical instant) draw the schedule for the first periods if all tasks are finished before the end of the first periods, schedulable, otherwise NO

45

46

Extensions to the basic RMS

RMS for tasks with D <= T

Deadline <= Period Interrupt handling Non zero OH for context switch Non preemptive sections Resource Sharing

RMS is no longer optimal (example?) Utilization bound test must be modified Response time test is still applicable

Assuming that fixed-priority assignment is adopted But considering the critical instant and checking the first deadlines principle are still applicable

47

48

Deadline Monotonic Scheduling (DMS) [Leung et al, 1982]

Example
C Task 1 Task 2 Task 3 Task 4 1 1 2 1 T 4 5 6 D 3 5 4
5 6 10 12 11 R1=1 R2=4 R3=3 R4=10 15 4 8 12 16

Task model: the same as for RMS but Di<=Ti Priority-Assignment: tasks with shorter deadline are assigned higher priorities Run-time scheduling: preemptive HPF FACTS:

11 10

DMS is optimal RMS is a special case of DMS

DMS is often refered as Rate Monotonic Scheduling for historical reasons and they are so similar
49

50

DMS: Schedulability analysis

Summary: 3 ways for DMS schedulability check

UB test (sufficient):
Ci/Di <= n*(21/n-1) implies schedulable by DMS

Prescise test (exactly the same as for RMS):

Response time calculation: Ri= Ci + j HP(i) Ri/Tj*Cj Ri0 = Ci + j HP(i) Cj = C1+C2+...+Ci the first guess Rik+1 = Ci + j HP(i) Rik/Tj*Cj the (k+1)th guess The iteration stops when either

UB test (sufficient, inconclusive) Response time calculation Draw the schedule for the first periods

Rim+1>Di or non schedulable Rim<Di and Rim+1 = Rim schedulable

51

52

EDF for tasks with D <= T

Summary: schedulability analysis

Di=Ti Static/Fixed- RMS priority Sufficient test Ci/Ti <= n*(21/n-1) Precise test
Ri= Ci + j HP(i) Ri/Tj *Cj Ri<=Ti

You can always use EDF and it is always optimal to schedule tasks with deadlines

Di<=Ti DMS Sufficient test Ci/Di <= n*(21/n-1) Precise test

Ri= Ci + j HP(i) Ri/Tj *Cj Ri<=Di

We have a precise UB test for EDF for tasks with Di=Ti: U<=1 iff task set is schedulable Unfortunately, for tasks with Di<=Ti, schedulability analysis is more complicated (out of scope of the course, further reading [Giorgio Buttazzos book])

We can always check the whole LCM

Dynamic priority
53

EDF Precise test Ci/Ti <=1

EDF ?
54

Handling context switch overhands in schedulability analysis

Handling context switch overheads ?

Assume that

Cl is the extra time required to load the context for a new task (load contents of registers etc from TCB) Cs is the extra time required to save the context for a current task (save contents of registers etc to TCB) Note that in most cases, Cl=Cs, which is a parameter depending on hardware Cl Cs Task 1 Task 2
55

Thus, the real computing time for a task should be Ci= Ci+Cl+Cs The schedulability analysis techniques we studied so far are applicable if we use the new computing time C.

Unfortunately this is not right

Dispatch/context switch

56

Handling context switch

Handling interrupts: problem and example

Task 0 Task 0 is the interrupt handler with highest priority 0

Ri= Ci+ j H P (i) Ri/Tj * Cj = Ci+ 2Ccs + j H P (i) Ri/Tj*(Cj + 2Ccs)

60

100

200 Missing deadline = 50 Response time = 70

This is wrong!

T=D 200 50 250

Task 1 0

Released here

Ri= Ci+ 2Ccs + j HP(i) Ri/Tj*Cj + j H P (i) Ri/Tj*4Ccs

(each preemption 2 context switches)

IH, task 0

60 10 40

Task 1 Task 2

50 60

= Ci+ 2Ccs + j H P (i) Ri/Tj*(Cj +4Ccs)

Task 2

This is right

57

58

Handling interrupts: solution

Handling interrupts: example

IH Task 0 is the interrupt handler with highest priority 200

Whenever possible: move code from the interrupt handler to a special application task with the same rate as the interrupt handler to make the interrupt handler (with high priority) as shorter as possible Interrupt processing can be inconsistent with RM priority assignment, and therefore can effect schedulability of task set (previous example)

C IH Task 1 Task 2 Task 3 10 10 40 50

T=D 200 50 150 200

Task 1 50 100 150

Interrupt handler runs with high priority despites its period Interrupt processing may delay tasks with shorter periods (deadlines) how to calculate the worst case response time ?

Task 2 150 Task 3

59

60

10

Handling non-preemtive sections

Handling non preemptive sections: Problem and Example

Task 3 is an interrupt handler with highest priority Task 4 has a non preemptive section of 20 sec C Task 1 Task 2 20 40
T=D blocking

So far, we have assumed that all tasks are preemptive regions of code. This not always the case e.g code for context switch though it may be short, and the short part of the interrupt handler as we considered before

blocked 20 20

100 150

0 0

Task 3
Task 4

60
40

200
350

0
20

20
0

Some section of a task is non preemptive

Missing deadline 150 60

In general, we may assume an extra parameter B in the task model, which is the computing time for the non preemtive section of a task.

IH Task 3 Task 1 Task 2 Task 4 20

60

100

200

Bi = computing time of non preemptive section of task i

150 20
Non preemptive/non interruptible section of 20
62

61

Handling non-preemtive sections: Response time calculation

So now, we have an equation:

The equation for response time calculation: Ri= Bi + Ci + j HP(i) Ri/Tj*Cj Where Bi is the longest time that task i can be blocked by lower-priority tasks with non preemptive section

Ri= Bi + Ci+2Ccs + j HP(i) Ri/Tj*(Cj +4*Ccs)

Note that a task preempts only one task with lower priority within each period

63

64

The Jitter Problem

Jitter: Example
{(20,100),(40,150),(20, T3)}
T1 20 0 40 0 T3 0 20 100 40 150 20 200 20 300 40 300

So far, we have assumed that tasks are released at a constant rate (at the start of a constant period) This is true in practice and a realistic assumption However, there are situations where the period or rather the release time may jitter or change a little, but the jitter is bounded with some constant J The jitter may cause some task missing deadline

T2

130
20

170

150

300

T3 is activated by T2 when it finishes within each period Note that because the response time for T2 is not a constant, the period between two instances of T3 is not a constant: 170, 130
65 66

11

Jitter: Definition

Jitter: Example
{(20,100),(40,150),(20, T3)}
T1 T2 0 T3 0 20 0 40 20 100 40 150

J(biggest)=maximal delay from period-start J(smallest)=minimal delay from period-start Jitter= J(biggest)-J(smallest) Jitter = the maximal length of the interval in which a task may be released non-deterministically If J(biggest)=J(smallest), then NO JITTER and therefore no influence on the other tasks with lower priorities
67

Pr(T1)=1, Pr(T2)=2, Pr(T3)=3

20 200 20 300 40 300

130
20

170

150

300

T3 is activated by T2 by the end of each instance J(biggest)= R2(worst case), J(smallest)= R2(best case) Jitter = J(biggest)- J(smallest)=60-40=20
68

Jitter: Example
{(20,100),(40,150),(20, T3)}
T1
T2 0 T3 0 20 0 40 20 100 40 150 20 200 20 300 40

The number of preemptions due to Jitter

Task L will be preempted at least 2 times if Rlow > Thigh -Jhigh

Rlow
One release Task L 0

90
20

210

300

Tlow Jhigh
One more release due to the jitter W hich preempts L, one more time

150

300

Task H 0

T3 is activated by T2 at any time during its execution of an instance J(biggest)= R2(worst case), J(smallest)= R2(best case)-C2 Jitter = J(biggest)- J(smallest)=60-0=60
69

Thigh

70

The number of preemptions/blocking when jitters occur

Task L will be preempted at least 3 times if Rlow > 2Thigh -Jhigh

Rlow
One release Task L 0

Tlow

Jhigh
Task H 0

One more release due to the jitter Which preempts L, one more time

Thigh

2Thigh

Task L will be preempted at least 2 times if Rlow > Thigh -Jhigh Task L will be preempted at least 3 times if Rlow > 2 *T high -Jhigh ... Task L will be preempted at least n times if Rlow > (n-1)* Thigh Jhigh Thus (Rlow +J high)/Tj > n-1 the largest n satisfying the condition is given by n= (Rlow + Jhigh)/ Thigh

71

72

12

Handling Jitters in schedulability analysis

Ri= Ci + j HP(i) number of preemptions *Cj

Handling Jitters in schedulability analysis

Ri* = Ri + Ji(biggest)

Ri= Ci + j HP(i)

Ri* = Ri + J i(biggest) why Ri+Ji(biggest) ?

(Ri+Jj)/Tj*C

if Ri* < Di, task i is schedulable otherwise no

if Ri* < Di, task i is schedulable, otherwise no

73

74

Now, we have an equation:

Ri= Ci+ 2Ccs + Bi + j HP(i) (Ri+J j)/Tj*(Cj +4Ccs)

Reource Sharing with HLP and PCP (and BIP)

Let

CS(k,S) denote the computing time for the critical section that task k uses semaphore S. Use(S) is the set of tasks using S

The response time for task i

Then for HLP and PCP, the maximal blocking time RSi and response time Ri for task i is as follows:

Ri* = Ri+Ji(biggest) Ji(biggest) is the biggest jitter for task i

RSi = max{CS(k,S)| i,k in Use(S), pr(k)<pr(i)<=C(S)}

How about BIP?

RSi = Sum{CS(k,S)| i,k in Use(S), pr(k)<pr(i)<=C(S)}

Ri= RSi + Ci + j HP(i) Ri/Tj *Cj

76

75

Finally, we have an equation (why?):

Ri= Ci+ 2Ccs + Bi + RSi + j HP(i) (Ri+Jj)/Tj*(Cj +4Ccs)

Summary: + and

Static Cyclic Scheduling (SCS)

Simple, and reliable, may be difficult to construct the time table and difficult to modify and (inflexible)

Earliest Deadline First (EDF)

Simple in theory, but difficult to implement, non-stable no precise analysis for tasks D<T
Simple in theory and practice, and easy to implement Similar to RMS

Rate Monotonic Scheduling (RMS)

Deadline Monotonic Scheduling (DMS)

Handling overheads, blocking, resource sharing (priority ceiling protocols)

77

78

13