Integrated Scientific Workflow Management for the Emulab Network - - PowerPoint PPT Presentation

Integrated Scientific Workflow Management for the Emulab Network Testbed

Eric Eric Eide Eide, Leigh , Leigh Stoller Stoller, , Tim Stack, Juliana Tim Stack, Juliana Freire Freire, , and Jay and Jay Lepreau Lepreau

University of Utah, University of Utah, School of Computing School of Computing USENIX 2006 / June 3, 2006 USENIX 2006 / June 3, 2006

2

This Talk in One Slide

• Current network

Current network testbeds testbeds

• …manage the “laboratory”

…manage the “laboratory”

• …not the experimentation process.

…not the experimentation process.

• →

→ A big problem for large A big problem for large-

• scale activities!

scale activities!

• Evolve Emulab for experiments based on

Evolve Emulab for experiments based on scientific workflows scientific workflows

• Big mutual benefits:

Big mutual benefits: testbed testbed ↔ ↔ workflow workflow

• Work in progress

Work in progress

3

Example: UAV Simulation

• A distributed, real

A distributed, real-

• time

time application application

• Evaluate improvements

Evaluate improvements to real to real-

• time middleware

time middleware

• vs. CPU load
• vs. CPU load
• vs. network load
• vs. network load
• 4 research groups

4 research groups

• x 19 experiments

x 19 experiments

• x 56 metrics

x 56 metrics

UAV UAV Receiver Receiver ATR ATR

images images → → ← ← images images alerts alerts → →

4

Use Emulab

Concept Concept Experiment Experiment Emulate Emulate

write “ns” file write “ns” file “ “swap in” swap in”

5

Problems Solved

• I get machines!

I get machines!

• 328 PCs, and more

328 PCs, and more

• Time

Time-

• & space

& space-

• shared

shared

• Loads OS and software

Loads OS and software

• I get network!

I get network!

• Config
• Config. topology & quality

. topology & quality

• I get to collaborate!

I get to collaborate!

• Available to researchers

Available to researchers and educators worldwide and educators worldwide

• File storage, email, …

File storage, email, …

6

Problems Not Solved

• “

“Now what?” Now what?”

• Getting off the ground

Getting off the ground

• Run all my software

Run all my software

• Add instrumentation

Add instrumentation

• Collect all my data

Collect all my data

• Analyze it

Analyze it

• Scaling up

Scaling up

• 19 configurations

19 configurations

• Automation

Automation

7

More Problems Not Solved

• “

“How did I get here?” How did I get here?”

• Over the short term…

Over the short term…

• “Where are the results

“Where are the results I got last week?” I got last week?”

• “How did I get those

“How did I get those results anyway?” results anyway?”

• “What if…?”

“What if…?”

• …and the long term

…and the long term

• Reproducing results

Reproducing results

• Reusing artifacts

Reusing artifacts

8

Idea: Scientific Workflow

• Managing activities, inputs, and outputs is the

Managing activities, inputs, and outputs is the job of a job of a scientific workflow system scientific workflow system

• Our approach:

Our approach: evolve Emulab with evolve Emulab with integrated support for scientific workflows integrated support for scientific workflows

• Build on existing abstractions & mechanisms

Build on existing abstractions & mechanisms

• Resource focus

Resource focus → → user & task focus user & task focus

• Users work “within” and “across” experiments

Users work “within” and “across” experiments

9

Contributions

• Address demand + opportunity

Address demand + opportunity

• Users need to manage large

Users need to manage large-

• scale complexity

scale complexity

• A symbiotic combination:

A symbiotic combination: leverage and impact leverage and impact

• Advance the applicability of

Advance the applicability of testbeds testbeds

• Not just Emulab

Not just Emulab — — e.g., e.g., PlanetLab PlanetLab and DETER and DETER

• Advance scientific workflow systems

Advance scientific workflow systems

• Exploit

Exploit testbed testbed capabilities capabilities — — e.g., “total control” e.g., “total control”

• Address

Address testbed testbed requirements requirements — — e.g., flexible use e.g., flexible use

10

Issue: Encapsulation

• Current “experiment” model

Current “experiment” model is not fully encapsulating is not fully encapsulating

• Topology + static events

Topology + static events

• Need everything else!

Need everything else!

• Challenge: specification

Challenge: specification

• Complete and precise…

Complete and precise…

• …w/o huge user burden

…w/o huge user burden

• Approach: be automatic

Approach: be automatic

• E.g., track files used

E.g., track files used

• Snapshot, archive, restore

Snapshot, archive, restore

• User can refine “extent”

User can refine “extent”

ns file ns file OSes OSes packages packages my software my software inputs inputs

• utputs
• utputs

NFS monitors packet monitors AJAX GUI Subversion repo. datapository (DB) research filesystems

11

Issue: Definition vs. Execution

• Current “experiment” has

Current “experiment” has multiple roles multiple roles

• Definition

Definition

• The thing that you run

The thing that you run

• Challenge: representing

Challenge: representing relationships relationships

• Multiple runs of one setup

Multiple runs of one setup

• Similar configurations

Similar configurations

• Approach: a new model of

Approach: a new model of experimentation experimentation

• Separate the roles

Separate the roles

• Evolve the new abstractions

Evolve the new abstractions

12

New Model

• Template

Template

• Swapin

Swapin

• Experiment

Experiment

• Activity

Activity

• Record

Record

n = 2 n = 2 n = 4 n = 4

13

Issue: History

• Research and educational

Research and educational plans are dynamic plans are dynamic

• By design & by discovery

By design & by discovery

• Challenge: safe exploration

Challenge: safe exploration

• Fork

Fork

• Back up

Back up

• Approach: keep history &

Approach: keep history & support temporal navigation support temporal navigation

• Keep template revisions

Keep template revisions

• Track provenance

Track provenance

• Locate, repeat, and reuse

Locate, repeat, and reuse

rev 1.1 rev 1.1 bigger nets bigger nets add add params params

• ops: need new
• ops: need new

measurements measurements what about what about loss? loss?

14

Implementation in Progress

Definition Definition Execution Execution & History & History Data Analysis Data Analysis

15

Conclusion

• Large and powerful

Large and powerful testbeds testbeds

• …enable complex and large

…enable complex and large-

• scale activities

scale activities

• …lead to complex and large

…lead to complex and large-

• scale workflow

scale workflow management problems management problems

• Integrated workflow management can

Integrated workflow management can leverage the strengths of leverage the strengths of testbeds testbeds

• Systems approach

Systems approach — — and systems challenges and systems challenges

• →

→ Better Better testbeds testbeds and workflow systems and workflow systems

http://www.emulab.net/

Thanks! Thanks!

17

Extra Slides After This Point