using schedflow for performance evaluation of workflow applications
DESCRIPTION
Using SchedFlow for Performance Evaluation of Workflow Applications. Elisa Heyman Gustavo Martínez Miquel Angel Senar Emilio Luque Universitat Aut ònoma de Barcelona [email protected]. Barton P. Miller University of Wisconsin [email protected]. 1. T1. T2. T3. T4. T5. - PowerPoint PPT PresentationTRANSCRIPT
1
Using SchedFlow for Performance Evaluation of Workflow Applications
Barton P. Miller
University of Wisconsin
Elisa HeymanGustavo Martínez
Miquel Angel Senar Emilio Luque
Universitat Autònoma de Barcelona
2
Our Problem
T1
T2 T3
T4 T5 T6
T7
Scheduling Policies
Workflow Engines
3
Our Solution
T1
T2 T3
T4 T5 T6
T7
Scheduling Policies
Workflow Engines
SchedFlow
4
Outline› Introduction› SchedFlow› Experimental Study› Conclusions
5
Introduction› For executing a workflow on a
distributed environment, we need:› Scheduling policy integrated into a› Workflow engine
› Reduce makespan› Factors
› Workload size› Inaccurate computing and
communication times› Machines appearing/disappering
dynamically
6
Introduction› With SchedFlow, we assessed the
influence of the workload on the makespan considering:› Different scheduling policies › Different workflow engines
SchedFlowT1
T2 T3
T4 T5 T6
T7
User PolicyAPI
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
T1
T2 T3
T4
The user submits a workflow
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
User PolicyAPI
T1
T2
T3
The Scheduler uses the specified scheduling policy on the available resources discovered by the Observer.
M1
M2
M3
T4 M4
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
T1
T2
T3
The Controller receives the first task-machine pairs
M2
M3
T4 M4
M1
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
T1
T2
T3
The Controller tells the adaptor which engine to use. The adaptor deals with formatting and enqueues the task.
M2
M3
T4 M4
M1
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
T2
T3
M2
M3
T4 M4
M1
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logsT1
T2
T3
The Engine sends the task to the assigned machine. The Observer checks the Engine log for finished tasks.
M2
M3
T4 M4
SchedFlow
M1T1
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
T2
T3
When the task finishes, the Observer notifies the Scheduler.
M2
M3
T4 M4
SchedFlow
M1
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
T2 T3
T4 M4
The Scheduler finds the tasks that have their dependencies satisfied and sends them to the Controller.
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
M2
M3
T2 T3
T4 M4
M2
M3
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
T4 M4
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
M2
M3
T2 T3
T4 M4
M2
M3
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
M2
M3
T2
T3
T2 finishes OK.M3 is claimed.
T4 M4
M2
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
M2
M3T3
The Observer detects the problem and T3 is removed from M3 and dynamcally rescheduled.
T4 M4
M2
M3
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
M2
M3T3
T3 is rescheduled. The Observer does not include M3 as an available resource.
T4 M4
T3
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
M2
M3
T4 M4
T3 M2
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
M2
M3
T4 M4
T3
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
M2
M3
T4 M4
T3
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
M2
M3
T4 M4
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
M2
M3
T3
T4 M4
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
M2
M3
T3
T4 M4
T3 finishes OK. The Observer notifies the Scheduler, and it releases T4.
SchedFlow
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
M2
M3
T4
SchedFlow
M4
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
T4
SchedFlow
M4
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
SchedFlow
M4
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logsT4
SchedFlow
M4
queue
Task manager
Controller Observer
SchedulerScheduler
SchedulerScheduler
Adaptor
Scheduler
Adaptor
Workflow Engine
logs
T4
When T4 finishes the Observer computes the makespan.
32
Experimental Study› Execution environment:
– 140 machines› Workflow applications:
– Montage (53 tasks) – LIGO (81 tasks)
› Workflow engines:– Condor-DAGMan 7.0– Taverna 1.4.8– Karajan 4_0_a1
33
Experimental Study› Scheduling policies:
– Default– Min-min– HEFT– BMCT
34
Experimental Study› Input workload:
– 400 MB– 1024 MB
› We studied the effect of the scheduling policies.
› We measured application makespan› Real executions
35
Results› Mantage ran on Taverna, DAGMan,
Karajan› 400 MB input workload› 120 executions› Default scheduling policy
Taverna DAGMan Karajan0
2000
4000
6000
8000
10000
12000
14000
Worflow engine with default Scheduling Policies
Mak
espa
n av
erag
e (s
ec.)
36
Results› Same experiments but using SchedFlow› Min-min, HEFT, BMCT› Rescheduling
Taverna DAGMan Karajan0
2000
4000
6000
8000
10000
12000
14000
Default min-min HEFT BMCT
Worflow engine with differents Scheduling Policies
Mak
espa
n av
erag
e (s
ec.)
37
Results› Mantage ran on Taverna, DAGMan,
Karajan› 1024 MB input workload› 120 executions› Default scheduling policy
Taverna DAGMan Karajan0
4000
8000
12000
16000
20000
24000
28000
Worflow engine with default Scheduling Policies
Mak
espa
n av
erag
e (s
ec.)
38
Results› Same experiments but using SchedFlow› Min-min, HEFT, BMCT› Rescheduling
Taverna DAGMan Karajan0
4000
8000
12000
16000
20000
24000
28000
Default min-min HEFT BMCT
Worflow engine with differents Scheduling Policies
Mak
espa
n av
erag
e (s
ec.)
39
Results› LIGO ran on Taverna, DAGMan, Karajan› 400 MB input workload› 120 executions› Default scheduling policy
Taverna DAGMan Karajan0
4000
8000
12000
16000
20000
24000
28000
Worflow engine with default Scheduling Policies
Mak
espa
n av
erag
e (s
ec.)
40
Results› Same experiments but using SchedFlow› Min-min, HEFT, BMCT› Rescheduling
Taverna DAGMan Karajan0
4000
8000
12000
16000
20000
24000
28000
Default min-min HEFT BMCT
Worflow engine with differents Scheduling Policies
Mak
espa
n av
erag
e (s
ec.)
41
Results› LIGO ran on Taverna, DAGMan, Karajan› 1024 MB input workload› 120 executions› Default scheduling policy
Taverna DAGMan Karajan0
10000
20000
30000
40000
50000
60000
Worflow engine with default Scheduling Policies
Mak
espa
n av
erag
e (s
ec.)
42
Results› Same experiments but using SchedFlow› Min-min, HEFT, BMCT› Rescheduling
Taverna DAGMan Karajan0
10000
20000
30000
40000
50000
60000
Default min-min HEFT BMCT
Worflow engine with differents Scheduling Policies
Mak
espa
n av
erag
e (s
ec.)
43
Conclusions› No single scheduling policy is the best for
all scenarios› SchedFlow allows us to obtain better
performance providing:– Flexibility regarding scheduling policies– Support for rescheduling– Integration with Workflow Engines
44
Using SchedFlow for Performance Evaluation of Workflow Applications
Barton P. Miller
University of Wisconsin
Elisa HeymanGustavo Martínez
Miquel Angel Senar Emilio Luque
Universitat Autònoma de Barcelona