{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

lec07_08_fixpriority1

lec07_08_fixpriority1 - Priority-Driven Scheduling of...

This preview shows pages 1–6. Sign up to view the full content.

1 Priority-Driven Scheduling of Periodic Tasks (1) - Chapter 6 - Overview • Reference Model Assumptions • Fixed-priority vs. Dynamic Priority •RM – schedulable utilization bound – time demand analysis •ED F – schedulable utilization bound – time demand analysis – The stability problem of EDF

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
2 Periodic Task Model • A periodic task T i is characterized by – phase: θ i –Pe r iod : p i – Execution time : e i – Relative deadline: D i from the beginning of the period. J 11 θ 1 d 11 θ 1 +p 1 d 12 θ 1 +2*p 1 d 13 θ 1 +3*p 1 J 12 J 13 Default assumption: D i = p i . That is, a periodic task deadline is located at the end of the period 0 (Power On) Assumptions • the tasks are independent – for resource contention, Chapter 8 • there are no aperiodic and sporadic tasks – for integrated scheduling, Chapter 7 • other assumptions – can be preempted at any time – context switch overhead is negligible
3 Classification of Scheduling Algorithms (Review) offline schedule online schedule Clock-driven WRR Priority-driven (Work conserving) fixed-priority (e.g., RM, DM) dynamic-priority (e.g., EDF, LST, FIFO, LIFO) clairvoyant schedule Priority vs. Criticality” • Priority: priority is the order we execute ready jobs. • Criticality (Importance): represents the penalty if a task misses a deadline (one of its jobs misses a deadline). • Quiz: Which task should have higher priority? • Task 1: The most import task in the system: if it does not get done, catastrophic consequences will occur • Task 2: An mp3 player: if it does not get done in time, the played song will have a glitch

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
4 “Priority vs. Criticality” • An important find in real-time computing theory is that importance may or may not correspond to scheduling priority . • In the following example, giving the less important task higher priority results in both tasks meeting their deadlines. • Importance matters only when tasks cannot be scheduled (overload condition), not when they can be scheduled. Important job Less important job Dynamic Priority vs. Fixed Priority •{ T 1 =(p 1 =10, e 1 =4), T 2 =(p 2 =15, e 2 =8), T 3 =(p 3 =30, e 3 =2)} Fixed Priority Schedule (RM) Miss! 01 0 2 0 3 0 Dynamic Priority Schedule (EDF) OK ! 0 2 0 3 0
5 What are advantages of priority- driven schedule over clock-driven? • Scheduling decision is made online, and hence flexible – Jobs of a task doesn’t need to be released at the fixed time (exact periodic) • period = minimum inter-release time – Tasks can dynamically enter and leave the system • Good! BTW, how can we validate the timing behavior? – Predictability: can we say the system is schedulable a priori? – Fortunately, we have sound theory on the schedulability of priority-driven schedule OK, Let’s study such theory - Is it enough to simply memorize important theorems? - Facts – “RM is optimal” – “DM is optimal” – “The system is schedulable if U < n(2 1/n -1) according to RM schedule” – “EDF is optimal” – “The system is schedulable if U < 1 according to EDF schedule” Not that useful!

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 22

lec07_08_fixpriority1 - Priority-Driven Scheduling of...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online