+ All Categories
Home > Documents > Implications of Classical Scheduling Results For Real-Time Systems

Implications of Classical Scheduling Results For Real-Time Systems

Date post: 24-Feb-2016
Category:
Upload: kueng
View: 30 times
Download: 0 times
Share this document with a friend
Description:
Implications of Classical Scheduling Results For Real-Time Systems. John A. Stankovic, Marco Spuri, Marco Di Natale and Giorgo Buttazzo. Introduction. Classical scheduling theory Vast amount of literature Not always directly applicable for RT systems Summarize implications and new results - PowerPoint PPT Presentation
Popular Tags:
52
Implications of Classical Scheduling Results For Real-Time Systems John A. Stankovic, Marco Spuri, Marco Di Natale and Giorgo Buttazzo
Transcript
Page 1: Implications of Classical Scheduling Results For Real-Time Systems

Implications of Classical Scheduling Results For Real-Time Systems

John A. Stankovic, Marco Spuri, Marco Di Natale and Giorgo Buttazzo

Page 2: Implications of Classical Scheduling Results For Real-Time Systems

Introduction

• Classical scheduling theory– Vast amount of literature– Not always directly applicable for RT systems

• Summarize implications and new results• Provide important insight in making good

design choices• Address common problems and design issues

Page 3: Implications of Classical Scheduling Results For Real-Time Systems

Contents• Preliminaries• Uni-processor systems

1. Preemptive vs. Non-preemptive2. Precedence constraints3. Shared resources4. Overload

• Multiprocessor systems1. Static vs. Dynamic2. Preemptive vs. Non-preemtive3. Anomalies4. An analogie

Page 4: Implications of Classical Scheduling Results For Real-Time Systems

Static vs. Dynamic scheduling

• Static– The algorythm has complete preliminary

knowledge regarding the task set, constraints, deadlines, computation times, release times

– i.e. laboratory experiment, process control• Dynamic– The algorythm has complete knowledge on the

current state, but nothing about the future– i.e. multi-agent problems

Page 5: Implications of Classical Scheduling Results For Real-Time Systems

On-line vs. Off-line

• On-line calculating the schedule– Takes the current conditions into account– Decisions are based on the current conditions

• Off-line scheduling is always done– Premilinary analysis (what we should expect)– A scheduling algorithm can be applied to both static

and dynamic scheduling, and can be used on- or off-line

– Dynamic case: static scheduling can be applied to the worst case off-line

Page 6: Implications of Classical Scheduling Results For Real-Time Systems

Metrics• Carefully choose metrics• Minimize the:– Sum of completion time– Weighted sum of completion time– Schedule length– Number of required processors– Maximum lateness (useful)– Number of tasks who miss their deadlines (usually

used)• Deadlines are usually included as constraints

Page 7: Implications of Classical Scheduling Results For Real-Time Systems

Problem with the Lmax property

Page 8: Implications of Classical Scheduling Results For Real-Time Systems

Complexity theory

NP-Complete NP-HardP

NP

NP: a proof can be recognized in polynomial time, but no polynomial algorithm exist to solve the problemP: polynomial algorithm exist to find a proofNP-Complete: R ϵ NP-Complete if all NP problems can be polynomial tranformed to R and R ϵ NPNP-Hard: R ϵ NP-Hard if all NP problems are polynomial transformable to R

Page 9: Implications of Classical Scheduling Results For Real-Time Systems

Uni-processor systems

• Problem definition syntax

α | β | γ

• α: machine environment (number of processors)• β: job characteristics (preemption, constraints...)• γ: optimality criterion (max lateness... etc.)

Page 10: Implications of Classical Scheduling Results For Real-Time Systems

Independent tasks 1. Preemption vs Nonpreemption

• First thing to consider: use of preemption• Problem: 1 | nopmtn | Lmax

• Single machine – no preemption – minimize maximum lateness

• Jackson’s Rule: Any sequence is optimal that puts the jobs in order of nondecreasing due dates

• EDF algorithm: Earliest Deadline First (ϵ P)

Page 11: Implications of Classical Scheduling Results For Real-Time Systems

Independent tasks 2. Release times

• Release time: a task has release time ri if its execution cannot start before time ri

• 1 | nopmtn, rj | Lmax ϵ NP• 1 | pmtn, rj | Lmax ϵ P• Jackson’s Rule Modified: Any sequence that

any instant schedules the job with the earliest due date among all the eligible jobs is optimal with respect to Lmax

Page 12: Implications of Classical Scheduling Results For Real-Time Systems

Independent tasks 3. EDF and LLF

• Proof of Jackson’s rule is the interchange argument (not discussed in the paper)

• Usually allowing preemption decreases complexity

• EDF and LLF algorithms are optimal in these cases

• LLF = Least Laxity First (laxity = „slack time”)– Laxity = d-t-c

tt c Slack time d

Page 13: Implications of Classical Scheduling Results For Real-Time Systems

Independent tasks 4.Rate monotonic approach

• Rate-monotonic approach (Liu and Layland)– Shorter period – higher priority– A set of n independent periodic jobs can be scheduled by

the rate monotonic policy if

– pi: worst case execution time; Ti: period

• 69% utilization can always be achieved• Both rate-monotonic and EDF are broadly used

Page 14: Implications of Classical Scheduling Results For Real-Time Systems

Precendence constraints 1.

• Tasks are not independent anymore• i → j means that task i must precede task j• G(V,E) precedence graph can be constructed

1 | prec, nopmtn | Lmax

• Lawler algorithm solves it in: O(n2) (ϵ P)• But task start times must be identical

Page 15: Implications of Classical Scheduling Results For Real-Time Systems

Precendence constraints 2.

• If we introduce release times, the problem becomes exponential

(1 | prec, nopmtn, ri | Lmax) ϵ NP• The general case cannot be solved• BUT: Polynomial algorithm exists when the

precedence graph is a series-parallel graph

Page 16: Implications of Classical Scheduling Results For Real-Time Systems

Precendence constraints 3.Series-parallel graphs 1.

• Graphs that can beconstruted from an emptygraph with two operators:

• Or if their transitive closure does not contain a Z-graph

Page 17: Implications of Classical Scheduling Results For Real-Time Systems

• Series-parallel graphs only contain intrees OR outrees, but not both of them

• The precedence problem than can than be solved with Lawler’s algorithm in

O(|N| + |A|) ϵ P• |N| - number of nodes; |A| - number of edges

Precendence constraints 4.Series-parallel graphs 2.

Page 18: Implications of Classical Scheduling Results For Real-Time Systems

Precendence constraints 5.

• Bad news: Z-graphs almost always occur in RT systems

• For example: an asyncronous send followed by a syncronous receive

• Preemption again can reduce the complexity of the scheduling problem

(1 | prec, pmtn, ri | Lmax) ϵ O(n2)• Baker’s algorithm (not discussed)

Page 19: Implications of Classical Scheduling Results For Real-Time Systems

Precedence constraints 6.

• Another idea is to encode the precedences into the deadlines, and use EDF

• Blazewicz: EDF is optimal for this case if we revise the deadlines and release dates of tasks according to these formulas:

starting from tasks having no successor step by step

starting from tasks having no predecessor step by step

Page 20: Implications of Classical Scheduling Results For Real-Time Systems

Precedence constraints 7.

• Still no shared resources are taken into account

• The general problem of scheduling tasks with precedence constraints and resource conflicts is still NP-hard

• Solutions usually use heuristic and branch-and-bound methods

Page 21: Implications of Classical Scheduling Results For Real-Time Systems

Shared resources 1.• Problem is solved with mutual exclusion

primitives• Several additional problems arise:• Mok:– When there are mutual exclusion constraints, it is

impossible to find a totally on-line optimal run-time scheduler

– It is even worse: The problem of deciding whether it is possible to schedule a set of periodic processes which use semaphores (only to enforce mutual exclusion) is NP-hard

Page 22: Implications of Classical Scheduling Results For Real-Time Systems

Shared resources 2.

• Even deciding whether a solution exists, is NP-hard

• Proof: polynomial tranformation to the 3-partition problem (a.k.a. Karp-reduction)

• 3 partition problem ϵ NP– A given multiset of integers– Divide it into three equal-sum groups

Page 23: Implications of Classical Scheduling Results For Real-Time Systems

Shared resources 3.

• Mok also points out: the reason for the NP-hardness is the different possible computation times of the mutually exclusive blocks

• Confirmation:1 | nopmtn, rj, pj=1 | Lmax

and 1 | nopmtn, prec, rj, pj=1 | Cmax

ϵ P

Page 24: Implications of Classical Scheduling Results For Real-Time Systems

Shared resources 4.

• Somehow the algorithm should force using same length critical sections

• Sha and Baker found efficient suboptimal solutions guaranteeing minimum level of performance

• Kernelized monitor: Use longer time quantum on the processor, than the longest critical section:

Page 25: Implications of Classical Scheduling Results For Real-Time Systems

Shared resources 5.

• Mok: If a feasible schedule exists for an instance of the process model with precedence constraints and critical sections, then the kernelized monitor scheduler can be used to produce a feasible schedule

Page 26: Implications of Classical Scheduling Results For Real-Time Systems

Shared resources 6.

• Rate-monotonic approach – Priority Ceiling Procotol (PCP)– We assign priority to the mutex object– We prevent accessing all the mutexes based on

this priority– Proved to be deadlock-free– Prevents unbounded priority inversion (a job can

block only once)• Chen and Lin extended PCP to work with EDF

Page 27: Implications of Classical Scheduling Results For Real-Time Systems

Shared resources 7.• Stack Resource Policy (SRP)• A more general solution by Baker• A job should not be permitted to start– until the resources currently available are sufficient

to meet its maximum requirements– until the resources currently available are sufficient

to meet the maximum requirements of any single job that might preempt it

• The first property prevents deadlocks, the second prevents multiple priority inversion

Page 28: Implications of Classical Scheduling Results For Real-Time Systems

Shared resources - summary

• It is very important to deal with the problem of shared resources

• The classical results are usually applicable to RT systems, but only in uniprocessor systems

Page 29: Implications of Classical Scheduling Results For Real-Time Systems

Overload and value 1.

• If transient large overload occur, we still want a suboptimal schedule

• Some tasks should meet their deadlines between all conditions

• We associate values with tasks, so that we can define our preferences

Page 30: Implications of Classical Scheduling Results For Real-Time Systems

Overload and value 2.

• EDF (and LLF) algorithms perform very poorly in overloaded conditions

• EDF gives the highest priority to tasks with the closest deadline, so the „Domino effect” may occur

• For example: all tasks miss their deadline, while a suboptimal solution could have been found

Page 31: Implications of Classical Scheduling Results For Real-Time Systems

Overload and value 3.

• We use different metrics, however Lmax=0 could express that every task should meet its deadline

• Task sets with values: wi

• Smith’s rule: finding an optimal schedule for:

is given by any sequence that puts jobs in order of non-decreasing ratios:

Page 32: Implications of Classical Scheduling Results For Real-Time Systems

Overload and value 4.

• This solution does not work in general• All of these problems are in NP

1 | prec | ΣwjCj 1 | dj | ΣwjCj

1 | prec | Σcj 1 | prec, pj=1| ΣwjCj

• These are solved by a polynomial algorithm:1 | chain | ΣCj 1 | series-parallel | ΣCj

1 | dj | ΣCj

Page 33: Implications of Classical Scheduling Results For Real-Time Systems

Overload and value 5.

• Baruah: there is an upper bound on the performance of any on-line, preemptive algorithm working between overloaded conditions

• Competitve factor: ratio of the cumulative values accomplished by the algorithm and the clairvoyant scheduler

• No on-line scheduling algorithm exists with a competitive factor greater than 0.25

Page 34: Implications of Classical Scheduling Results For Real-Time Systems

Overload and value 6.

• This is the achiveable competitive factor as the function of the load size

Ratio to the clairvoyantscheduler

Load1 2

1

0.250.385

Page 35: Implications of Classical Scheduling Results For Real-Time Systems

Summary of uni-processor results

• Huge amount of theoretical results, • Many used algorithms are based on the EDF or

the rate-monotonic scheduling• Operating in overload and fault-tolerant

scheduling are the fields where additional research is necessary

Page 36: Implications of Classical Scheduling Results For Real-Time Systems

Multi-processor RT scheduling

• Far less results are presented in this field• Almost all of the problems are NP-hard• The most important goal is to develop clever

heuristics• There are serious anomalies that should be

avoided• Processors are considered to be identical

Page 37: Implications of Classical Scheduling Results For Real-Time Systems

Deterministic (static) scheduling 1.Non-preemptive

• Multiprocessor scheduling results usually consider tasks with constant execution time

• Theorems for non-preemptive, partially ordered tasks with resource constraints and one single(!) deadline cases show that they are almost always NP-hard

• The following theorems consider arbitrary partial, forest partial ordered and independent tasks– Forest partial order: in terms of the precedence graph

Page 38: Implications of Classical Scheduling Results For Real-Time Systems

Deterministic (static) scheduling 2.Non-preemptive

Processors Resources Ordering Computational time Complexity Theorem

2 0 Arbitrary Unit P Coffmann and Graham

2 0 Independent Arbitrary NP Garey and Johnson

2 0 Arbitrary 1 or 2 Units NP Garey and Johnson

2 1 Forest Unit NP Garey and Johnson

3 1 Independent Unit NP Garey and Johnson

N 0 Forest Unit P Hu

N 0 Arbitrary Unit NP Ulmann

Page 39: Implications of Classical Scheduling Results For Real-Time Systems

Deterministic (static) scheduling 3.Non-preemptive

• These cases are far less complex than a usual embedded system scheduling problem– No unit tasks– More shared resources– Tasks with different deadlines (!)

• Heuristical algorithms must be used

Page 40: Implications of Classical Scheduling Results For Real-Time Systems

Deterministic (static) scheduling 4.Preemptive

• Introducing preemption usually makes the problem easier, but:

P | pmtn | ΣwjCj

• McNaughton: For any instance of the multiproc. Scheduling problem, there exists a schedule with no preemption for which the value of the sum of computation times is as small as for any schedule with a finite number of preemptions

• There is no advantage of preemption in this case• We should rather minimize overhead (such as context

switches) and not use preemption

Page 41: Implications of Classical Scheduling Results For Real-Time Systems

Deterministic (static) scheduling 5.Preemptive

• Lawler: The multiprocessing problem of scheduling P processors, with task preemption allowed and where we try to minimize the number of late tasks is NP-hard.

(P | pmtn | ΣUj) ϵ NP– Uj – late tasks

• Solution always requires heuristics!

Page 42: Implications of Classical Scheduling Results For Real-Time Systems

Dynamic scheduling 1.

• There are very few theoretical results in this field

• Consider the EDF algorithm (which is optimal in the uni-processor case):– Mok: Earlies deadline first scheduling is not

optimal in the multiprocessor case– Example

Page 43: Implications of Classical Scheduling Results For Real-Time Systems

Example of EDF in multiprocess case• Ti(Ci, di): T1(1,1), T2(1,2), T3(3,3.5)

T1

T2

T3

t

P1

P2

1 2 3 43.5

EDF

T1 T2

T3

t

P1

P2

1 2 3 43.5

optimal

Page 44: Implications of Classical Scheduling Results For Real-Time Systems

Dynamic scheduling 2.

• Mok: For two or more processors, no deadline scheduling algorithm can be optimal without complete a priori knowledge of– deadlines– computation times– start times of tasks

• This implies, that none of the classical scheduling algorithms can be optimal when used online

Page 45: Implications of Classical Scheduling Results For Real-Time Systems

Dynamic scheduling 3.

• Possibilities– Analyse the worst case scenario. If a scheduling

exists, than every run-time situation can be schedules– Use well-developed heuristics – this can really

increase computational requirements (sometimes additional hardware required)

• Baruah: No on-line scheduling algorithm can guarantee a cumulative value greater than one-half for the dual-processor case

Page 46: Implications of Classical Scheduling Results For Real-Time Systems

Multiprocessing anomalies 1.

• Richard’s anomalies• Optimal schedule , fixed number of processors,

fixed execution times, precedence constaints• Graham: For the stated problem, changing the

priority list, increasing the number of processors, reducing execution times, or weakening the precedence constraints can increase the schedule length.

Page 47: Implications of Classical Scheduling Results For Real-Time Systems

Multiprocessing anomalies 2.

• Weakening the constaints can ruin the schedule• Example: P1

P2

P1

P2Static allocation:P1: T1; T2P2: T3; T4; T5

↓ We decrease the C1

Page 48: Implications of Classical Scheduling Results For Real-Time Systems

Multiprocessing anomalies 3.

• Richard’s anomalies are the proof of that it is not always sufficient to schedule the worst-case

• We can overcome these anomalies by having tasks simply idle if they finish earlier than their allocated computation time– This can be really inefficient– However their are solution for this [Shen]

Page 49: Implications of Classical Scheduling Results For Real-Time Systems

Similarity to bin-packing

• Bin-packing problem is a famous algorithmic problem

• There are N bins, each have a capacity• There are boxes, and we have to put them into those

bins• Two variations:– What is the minimum number of required bins (same

size)– Fixed number of bins given, minimize the maximum bin

length

Page 50: Implications of Classical Scheduling Results For Real-Time Systems

Bin-packing implications

• Several algorithms can be used, such as: first-fit (FF), best-fit (BF), first-fit decreasing (FFD), best-fit decreasing (BFD)

• Theroetical boundaries exists:– For FF and BF worst case: (17/10) L* (L* = optimal)– FFD >= BFD boundary: (11/9) L* (L* = optimal)

• In RT systems, we have much more constraints than the ones this analogie takes into account, but the implications might still be useful in off-line analysis

Page 51: Implications of Classical Scheduling Results For Real-Time Systems

Summary

• Uniprocessor RT scheduling can use the vast amount of theoretical knowledge from the classical theory

• We do not know too much from multi-processor scheduling, and most of the problems are NP-hard

• We need to develop clever heuristics, and do additional research in these fields

Page 52: Implications of Classical Scheduling Results For Real-Time Systems

Thank you for you attention!


Recommended