+ All Categories
Home > Education > ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

Date post: 03-Jul-2015
Category:
Upload: georgiana-copil
View: 840 times
Download: 1 times
Share this document with a friend
Description:
Presentation given at ICSOC 2014, describing ADVISE framework for estimating elasticity behavior, in time, for different cloud service parts. BEST PAPER AWARD - http://link.springer.com/chapter/10.1007/978-3-662-45391-9_19 ADVISE webpage: http://tuwiendsg.github.io/ADVISE/
19
ADVISE: a Framework for Evaluating Cloud Service Elasticity Behavior Georgiana Copil 1 , Demetris Trihinas 2 , Hongβˆ’Linh Truong 1 , Daniel Moldovan 1 , George Pallis 2 , Schahram Dustdar 1 , Marios Dikaiakos 2 1 Distributed Systems Group, Vienna University of Technology 2 Computer Science Department, University of Cyprus 12 th International Conference on Service Oriented Computing
Transcript
Page 1: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ADVISE: a Framework for Evaluating

Cloud Service Elasticity Behavior

Georgiana Copil1, Demetris Trihinas

2, Hongβˆ’Linh Truong1, Daniel Moldovan

1,

George Pallis2, Schahram Dustdar

1, Marios Dikaiakos

2

1Distributed Systems Group, Vienna University of Technology

2Computer Science Department, University of Cyprus

12th International Conference on Service Oriented Computing

Page 2: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 2

Overview

Motivation

Evaluating Cloud Service Behavior

– Learning process

– Determining expected elasticity behavior

Experiments

Conclusions and Future Work

Page 3: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 3

Motivation – Cloud service runtime evolution

Complex

Cloud

Service

Elastic

Cloud

Service

(running)Deployment

process

Elasticity

control

process

Elasticity Control

Processes

What would be

the elasticity

behavior?

Elasticity

requirements

Elasticity controller

Page 4: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 4

Motivation – Cloud service runtime evolution

Elasticity control

process enforced

now

Which will be the behavior?

Page 5: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 5

Motivation – Cloud service runtime evolution

Possible requirements

violations

Elasticity control

process enforcedExpected impact

Expected cool-off

period

now

Which will be the behavior?

Which elasticity control process is most appropriate?

How a control process will affect metrics, e.g., throughput, of the

overall service and individually on each part of the cloud service?

Page 6: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 6

Motivation – Cloud service behavior

Cloud service behavior is complex and can depend on:

– The structure of the cloud service

– The runtime resources used

– The workload of the cloud service

– The control processes enforced, e.g., by the controller

Capturing & using these types of information for

evaluating elasticity behavior

Service

Topology 1

Unit 1

Unit 2

Topology 2

Unit 3

Unit 4

𝑉𝑀π‘₯1 𝑉𝑀π‘₯2𝑉𝑀π‘₯3 𝑉𝑀π‘₯𝑛

Page 7: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 7

Approach

Input:

– Cloud service structure

– Monitoring information of different service parts (e.g., service

units, service topologies)

– Elasticity control process 𝐸𝐢𝑃𝑖

Expected output:

– Metrics evolution, in time, for different service parts and 𝐸𝐢𝑃𝑠

Main mechanism:

– Creating behavior clusters

– Computing closest behavior centroids

Page 8: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 8

Gathering information

Select relevant timeseries where 𝐸𝐢𝑃𝑖 was enforced before

𝐸𝐢𝑃𝑖 enforcement

Metric measurement

Relevant timeseries

Page 9: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 9

Clustering elasticity behaviors

Transform relevant timeseries to multi-dimensional

points

Time𝑑1 𝑑2 𝑑𝑛…

Metric

π‘šπ‘₯

π‘€π‘’π‘‘π‘Ÿπ‘–π‘π‘‰π‘Žπ‘™ (𝑑1)

π‘€π‘’π‘‘π‘Ÿπ‘–π‘π‘‰π‘Žπ‘™ (𝑑2)

π‘€π‘’π‘‘π‘Ÿπ‘–π‘π‘‰π‘Žπ‘™ (𝑑3)

π‘€π‘’π‘‘π‘Ÿπ‘–π‘π‘‰π‘Žπ‘™ (𝑑4)

…

π‘€π‘’π‘‘π‘Ÿπ‘–π‘π‘‰π‘Žπ‘™ (𝑑𝑛)

Behavior Point

BP

K-meansπΆπ‘™π‘’π‘ π‘‘π‘’π‘Ÿ1π‘šπ‘₯

πΆπ‘™π‘’π‘ π‘‘π‘’π‘Ÿ2π‘šπ‘₯

πΆπ‘™π‘’π‘ π‘‘π‘’π‘Ÿπ‘ π‘šπ‘₯𝐢1π‘šπ‘₯

𝐢2π‘šπ‘₯

𝐢𝑐 π‘šπ‘₯

Page 10: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 10

Computing expected behavior

πΆπ‘™π‘’π‘ π‘‘π‘’π‘Ÿ1π‘šπ‘₯

𝐢1π‘šπ‘₯

πΆπ‘™π‘’π‘ π‘‘π‘’π‘Ÿ2π‘šπ‘₯

𝐢2π‘šπ‘₯

πΆπ‘™π‘’π‘ π‘‘π‘’π‘Ÿ1π‘šπ‘¦

𝐢1π‘šπ‘¦

πΆπ‘™π‘’π‘ π‘‘π‘’π‘Ÿπ‘ π‘šπ‘¦

πΆπ‘π‘šπ‘¦

πΆπ‘™π‘’π‘ π‘‘π‘’π‘Ÿ1π‘šπ‘₯ πΆπ‘™π‘’π‘ π‘‘π‘’π‘Ÿ2π‘šπ‘₯πΆπ‘™π‘’π‘ π‘‘π‘’π‘Ÿπ‘Ÿ π‘šπ‘₯

πΆπ‘™π‘’π‘ π‘‘π‘’π‘Ÿ1π‘šπ‘¦a b -

πΆπ‘™π‘’π‘ π‘‘π‘’π‘Ÿπ‘ π‘šπ‘¦c - d

Co-occurrence matrix

Current values

π΅π‘ƒπ‘šπ‘¦π΅π‘ƒπ‘šπ‘₯

Compute centroids

closest to the 𝐡𝑃𝑖

πΆπ‘π‘šπ‘¦

𝐢1π‘šπ‘₯

Transform

to timeseries

π‘šπ‘₯π‘šπ‘¦

πΆπ‘™π‘’π‘ π‘‘π‘’π‘Ÿπ‘Ÿ π‘šπ‘₯

πΆπ‘Ÿ π‘šπ‘₯

Page 11: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 11

Experiment Settings [1/3]

Setting:

– M2M service

– Video Service

Page 12: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 12

Experiment Settings [2/3]

Setting:

– Running on public Flexiant cloud FCO

– MELA & JCatascopia for monitoring cloud services

– Randomly apply ECPs of random type for collecting behavioral

information

– β€œInteresting” metrics

Page 13: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 13

Experiment Settings [3/3]

Page 14: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 14

Experiments – Video Service

Video Service – effect of 𝐸𝐢𝑃1 on Application Server

𝐸𝐢𝑃1 - scale in application server tier – select instance to remove,

stop the video streaming service, remove instance from load

balancer, stop JCatascopia monitoring agent, delete instance

Page 15: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 15

Experiments – M2M Service [1/2]

M2M Service – effect of 𝐸𝐢𝑃7 on the entire cloud service

𝐸𝐢𝑃7 - scale in data node service unit – copy data from the instance

to be removed, remove recursively virtual machine

Page 16: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 16

Experiments – M2M Service [2/2]

M2M Service – effect on Data End Controller of enforcing 𝐸𝐢𝑃8𝐸𝐢𝑃8 - scale out data node service unit – create new network

interface, create new instance, assign token to node, set cluster

controller

Page 17: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 17

Experiments –

Quality of Results

π‘‰π‘Žπ‘Ÿπ‘–π‘Žπ‘›π‘π‘’π‘š

= π‘›π‘πΈπ‘ π‘‘π‘–π‘šπ‘Žπ‘‘π‘–π‘œπ‘›π‘  π‘’π‘ π‘‘π‘–π‘šπ‘Žπ‘‘π‘–π‘œπ‘›π‘†π‘–π‘§π‘’(π‘’π‘ π‘‘π‘–π‘šπ‘Žπ‘‘π‘’π‘‘π‘€π‘’π‘‘π‘Ÿπ‘–π‘π‘š βˆ’ π‘œπ‘π‘ π‘’π‘Ÿπ‘£π‘’π‘‘π‘€π‘’π‘‘π‘Ÿπ‘–π‘π‘š)

2

π‘›π‘πΈπ‘ π‘‘π‘–π‘šπ‘Žπ‘‘π‘–π‘œπ‘›π‘  βˆ’ 1

The more random the workload, of the service,

the more difficult to estimate the behavior Lower abstraction layer

=> better estimations

Complex,

unpredictable

metrics => very low

degree of accuracy

Page 18: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 18

Conclusions and Future Work

Conclusions

– When controlling a complex cloud service, we need to consider

the impact elasticity control processes have on different service

parts

– ADVISE is indeed able to "advise" elasticity controllers about

cloud service behavior

Future work

– Integrating with rSYBL (https://github.com/tuwiendsg/rSYBL)

– Adapting the control mechanisms of rSYBL to use such

information

ADVISE

– More experiments available at http://tuwiendsg.github.io/ADVISE

– Prototype https://github.com/tuwiendsg/ADVISE

Page 19: ADVISE - a Framework for Evaluating Cloud Service Elasticity Behavior - Best paper award

ICSOC 2014, 5 November, Paris 19

Thank you!

Georgiana Copil

[email protected]://dsg.tuwien.ac.at/staff/ecopil/

Distributed Systems GroupVienna University of Technology

Austria


Recommended