1. Klara Nahrstedt Spring 2011
CS 414 – Multimedia Systems Design Lecture 32 – Process Management (Part 2)
Klara Nahrstedt
Spring 2011
CS Spring 2011

2. Administrative
MLC application ‘mi-clicker’ is published on the Android Market under “MLC Edu App”.
Check the class website for a document “Getting Started” with the mi-clicker!!!
Starting Monday, we will use the phones at the beginning of each class, so bring phones to the class.
CS Spring 2011

3. Outline EDF vs RMS Dynamic Soft Real Time Scheduling
CPU service classes
Probing concept
Overrun- adaptation concept
CS Spring 2011

4. Admission Control (for preemptive tasks)
Schedulability test for RMS
Schedulability test for EDF
CS Spring 2011

5. Example
Consider the following preemptive RT tasks and their characteristics
T1: p1 = 50ms, e1=10ms
T2: p2 = 100ms, e2=20ms
T3: p3 = 200ms, e3=50ms
T4: p4 = 100ms, e4=20ms
Are these tasks schedulable via RMS?
If yes, what is the feasible schedule?
Are these tasks schedulable via EDF?
CS Spring 2011

6. DSRT (Dynamic Soft Real-Time Scheduling) – Example of a Multimedia CPU Scheduler
Multiple CPU Service Classes
Schedule real-time and not real-time tasks in an integrated fashion
Execution Flow of a SRT Process
Possible Mapping CPU Service Classes into a Multiprocessor Partitioning Design
Source: Hao-hua Chu 1999
CS Spring 2011

7. CPU Service Classes Service Classes Specification Parameters
Guaranteed
PCPT
(Periodic Constant
Processing Time)
P = Period
PPT = Peak Processing Time
PPT
PVPT
(Periodic Variable
Processing Time)
P = Period
SPT = Sustainable Processing
Time
PPT = Peak Processing Time
BT = Burst Tolerance
SPT
ACPU
(Aperiodic Constant
Processor Utilization)
PPU
PPU = Peak Processor
Utilization
Relative Deadline
PPT = Peak Processing Time
Event
PPT
CS Spring 2011

8. Periodic Constant Processing Time Class
Example Usage Pattern:
Peak Processing Time=10ms
Period = 100ms 10
110
210
100
200
Time(ms)
Processing IIIIIIIIIII frames
CS Spring 2011

9. Periodic Variable Processing Time Class
Example Usage Pattern:
Period = 100ms
Peak Processing Time = 30ms
Sustainable Processing
Time = 15ms
Burst Tolerance = 7ms 15
120
210
100
200
Time(ms)
Processing of IPBBPI frames
CS Spring 2011

10. Execution Flow of a SRT Process
Probing Phase
Execution Phase
Reservation Phase
Scheduling
Probe
Admission
Control
Extract
Reservation
Monitor/
Conformance
Test
Contract
Processor Binding
Adaptation
SRT Process
Adjusted Contract
CS Spring 2011

11. C++ APIs CpuApi cpu; CpuReservation reservation; // Probing Phase;
cpu.probe();
cpu.start();
for (int i=0; i<numProbeIterations; i++) {
doJob();
cpu.yield(); }
cpu.stop();
cpu.probeEnd();
cpu.probeMatch(&reservation);
// Reservation Phase
cpu.reserve(reservation);
cpu.setAdaptStrategy(strategy);
// Execution Phase
cpu.start();
for (;;) {
doJob();
cpu.yield(); }
cpu.stop();
cpu.free();
CS Spring 2011

12. Smart Offline Probing (1)
Goal: Extract a reservation.
Determine the most suitable Service Class and Parameters.
Avoid over/under reserve resources.
Needed because:
Processor usage is hardware platform dependent.
Processor usage is input dependent.
CS Spring 2011

13. Smart Probing (2)
DSRT runs a few iterations of SRT applications without reservation.
DSRT monitors the usage iteration by iteration.
DSRT analyzes the usage history.
Estimate a Reservation
Processor Usage
Iteration Number
CS Spring 2011

14. Smart Probing (3) It is Periodic Variable Processing Time (PVPT)
Compute average processor usage = 50ms
Compute peak processor usage = 62ms.
Max Burst = 12ms
It is Periodic Variable Processing Time (PVPT)
40ms
50ms
62ms
43ms
55ms
12ms
40ms
50ms
62ms
55ms
60ms
10ms
5ms
50ms
50ms
50ms
50ms
50ms

15. Multiprocessor Partitioning Design
Guaranteed Part
Non-guaranteed Part
PCPT Processes
Reserved Run
Overrun
PVPT Processes
Reserved Run
Burst
Overrun
TS Processes
RT Scheduler
Overrun Scheduler
TS Scheduler
Processor #1
RT Partition
Overrun Partition
TS Partition
Processor #2
RT Partition
Overrun Partition
TS Partition
CS Spring 2011

16. Admission Control Test
Given a reservation request, determine
Resource Availability. (1) + (2)
Processor Binding. (2)
Preemptive Earliest Deadline First:
CS Spring 2011

17. Partition Scheduling Processor #1 RT Partition Overrun Partition
Top-Level Scheduler
Proportional Sharing
RT Scheduler
Overrun Scheduler
TS Scheduler
Multi-Level
Round Robin
Priority Queues
Preemptive
EDF
Kernel
Scheduler
Processor #1
RT Partition
Overrun Partition
TS Partition
Processor #2
RT Partition
Overrun Partition
TS Partition
CS Spring 2011

18. RT Partition Scheduler
Processor #1
Waiting Queue:
(Sorted with the
earliest released
time) p
(2a) finished one
iteration
(3) released for
next iteration p
(1) admitted p
Runnable Queue:
(Sorted with the
earliest deadline)
(2b) overrunning
Overrun Partition Queues
CS Spring 2011

19. Overrun Partition Scheduler
Highest Priority
Burst Queue (FIFO)
(2) Miss Deadline p
(1a) Conformed?
Overrun Queue (FIFO)
(1b) Nonconformed? p
Permanent Non-conforming Queue (FIFO)
(1c) Nonconformed frequently?
Lowest Priority
CS Spring 2011

20. Adaptation Adjust Reservation. Adaptive Strategy Exponential Average
Scene #1
Scene #2
Adjust Reservation.
Adaptive Strategy
Exponential Average
CS Spring 2011
Frame 275

21. Exponential Average Adaptation Strategy
...
Xws-1
Xws
Xws+1
...
X2ws
...
X3ws
Iteration Number
Adaptation Points
Specification:
Window Size (ws).
Alpha ()
Xi= Guaranteed Parameter in a reservation.
Xi-1 = Actual Usage.
CS Spring 2011

22. User-level Priority Dispatch
Highest Priority
(5) Dispatched
Process runs
for T ms.
(4) Scheduler
sleeps.
Fixed RT
Priority
(3) Scheduler
sets Timer for
T ms. N
DSRT Scheduler Process
(6) Timer
interrupts
Scheduler
N-1
Dispatched Process .
(2) Set
Processor
Affinity. .
Time Sharing Processes
(5) Decrease
Priority .
(1) Increase
Priority.
Dynamic TS
Priority
RT Process Pool
Lowest Priority
CS Spring 2011

23. Experiment Setup Run 8 TS processes and 5 SRT processes concurrently.
TS1-6: Computational intensive programs.
TS7-8: Compilation programs.
SRT1: A MPEG player at 10 FPS.
Probing (PVPT class, P=100ms,
SPT=28ms, PPT=40ms, BT=11ms).
Adaptation Strategy: (Statistical,
f = 20%, ws = 20).
CS Spring 2011

24. Experimental Setup (Cont.)
SRT2: A MPEG player at 20 FPS.
Probing (PVPT class, P=50ms,
SPT=14ms, PPT=21ms, BT=6ms)
SRT3: A sampling program.
Probing(PCPT class, P=50ms,
PPT=10ms)
SRT4: A Java RocksInSpace game.
(PCPT class, P=100ms, PPT=30ms).
SRT5: Misbehaving greedy program.
(PCPT class, P=500ms, PPT=10ms).
CS Spring 2011

25. Experimental Result SRT2: MPEG player with P=50ms.
CS Spring 2011

26. Experimental Result (Cont.)
SRT3: Sampling program with P=50ms.
SRT4: Java game with P=100ms.
CS Spring 2011

27. Conclusion (Over-provisioning Approach)
Current Approach:
To achieve throughput - overprovision of resources (fast processors, large disks, fast I/O bus, high-speed networks), and exclusive usage of resources
To achieve timing - overprovision CPU, exclusive usage of resources, application-dependent scheduling
Current Thesis: With over-provisioning we get
Quality of Service !!
CS Spring 2011

28. Conclusion (Problems with Over-provisioning)
Violation of Timing Guarantees in Exclusive Case (head-of-line blocking)
Sensory and Video Data Processing/Transmission
Violation of Timing/Throughput Guarantees in Shared Case (greedy applications, flows)
UDP flows versus TCP Flows
Last Mile Problem (not everywhere is over-provisioning possible)
Telescopes, University Campus
Need support of QoS in OS towards multimedia tasks
CS Spring 2011