1. Scheduling for MW applications
E. Heymann, M.A. Senar and E. Luque
Computer Architecture and Operating Systems Group
Universitat Autònoma of Barcelona
SPAIN

2. Contents Statement of the problem. Simulation framework.
Simulation results.
Implementation on MW.
Future work.

3. Objective
To develop and evaluate efficient scheduling policies for parallel applications with the following MW model:
for i=1 to M
for j=1 to NTasks
do F(j)
end
[computation]
In an opportunistic environment
Expectation
Variance
The expectation of the execution time of F(j) is the same (with some variance) for all the executions of the external loop.

4. Objective How many workers ? How to assign tasks to workers ?
Efficiency without forgetting performance.
How sensitive is efficiency with respect to variance changes.
To optimize the use of the processor resource to get the best efficiency, but considering the efficiency/execution time ratio.

5. Example 6 8 1 8 5 4 5 4 1 1 4 8 5 Without preoccupation LPTF Policy
Efficiency = = 3 8 5 4 1 8 5 4 1
LPTF Policy
Efficiency = = 1
9 + 9

6. Platforms Dedicated homogeneous machines.
Non-dedicated (such as Condor) homogeneous machines.
Non-dedicated (such as Condor) heterogeneous machines.
1) Fixed number of machines
2) 3) In an opportunistic environment like Condor.

7. Policies Simulated LPTF: Largest processing time first LPTF on Average
Random
Random and Average

8. LPTF => Implies sorting the tasks
Rand&Avg => Implies the computation of the average of the previous
execution times of task i. And sorting

9. Simulation
Response Variables:
Efficiency
Execution Time

10. Simulation. Factors. Variation6 24 7 40 8
(5)
Simulation Factors Variation 35
(4) 28
20% deviation
(1) 9
(1) 6 6

11. Simulation. Factors. Workload

12. Simulation. Factors Processor Number 31, 100, 300
Standard Deviation , 10, 30, 60, 100
External Loop , 35, 50, 100
Workload %load: 30, 40, 50, 60, 70, 80, 90
20%dist: equal, decreasing
80%dist: equal, decreasing

13. Simulation Results Dedicated homogeneous machines
Efficiency:
few big tasks and lots of machines => waste of resources.
Loop: does not matter.
Deviation: separates the curves when there are many big tasks.
Few big tasks: Nothing to do

14. Simulation Results Dedicated homogeneous machines

15. Simulation Results Dedicated homogeneous machines

16. Simulation Results Dedicated homogeneous machines

17. Simulation Results Dedicated homogeneous machines

18. Simulation Conclusions Dedicated homogeneous machines
Rough analysis:
Variance does not seem to make efficiency significantly worse.
External loop does not affect efficiency.
To achieve an efficiency > 80% and an execution time < 1.1 respect to LPTF execution time, the number of workers should range between 15% of the tasks number (90% load) and 40% (30% load).
Few big tasks and lots of machines => Waste of resources.
With 30% load, about 33% of the tasks number is needed. With 90% load only 16% is needed.

19. Simulation Non-dedicated homogeneous machines
Factors:
Processor Number
Standard Deviation
External Loop Only 35
Workload
Probability of loosing and getting machines
Checkpoint Always
Never
Only for “big” tasks that have
been “a long time” in execution
The response variables are the same as (A): Efficiency & execution time
checkpoint times:
SAVE_OVERHEAD = Minute / 2
RESTORE_OVERHEAD = Minute / 2
CHECK_MACHINE_STATE = 2 * Minute
(loose a machine with p=15%, win a machine with p=15%)

20. Simulation Results Non-dedicated homogeneous machines
Biggest task =
Smaller task =

21. Simulation Results Non-dedicated homogeneous machines
This is only an example, we haven’t done lots of execution and average yet.
Probability of getting a machine = Probability of loosing a machine == 15%
Ckpt time to save == ckpt time to restore = 30 segs.
Dist : Bigger task = 285
Smaller tasks = 3

22. Implementation on MW Support to the desired Program Model.
Computation of the Efficiency.
Scheduling policies Random
Random & Average
Efficiency: Always with the master clock

23. Implementation on MW Statistics S to get Eff. Policy: Rand ||
iteration 1
iteration 2
iteration M
Statistics
to get Eff. S
Policy: Rand ||
Rand & Avg S

24. Future Non-dedicated homogeneous machines:
Complete the simulations.
Duplication of large tasks. (?)
Non-dedicated heterogeneous machines:
Use dynamic load information (provided by Condor) to rank machines.
Implementation on MW:
Test the MW scheduling policies with large applications.
Lo de tener etiquetas de seguridad en las maquinas, lo tendria que
proveer condor.
To ask Condor for getting information about machines safety.
Complete simulation includes doing proofs with different CKPT_OVERHEAD time, and when loosing more machines than winning machines, and trying some other winning/loosing machine probability.