Brokering Techniques for Managing Three- Tier Applicatjons in - - PowerPoint PPT Presentation

▶
brokering techniques for managing three tier applicatjons
SMART_READER_LITE
LIVE PREVIEW

Brokering Techniques for Managing Three- Tier Applicatjons in - - PowerPoint PPT Presentation

Jan 09, 2024 393 likes •980 views

Brokering Techniques for Managing Three- Tier Applicatjons in Distributed Cloud Computjng Environments Nikolay Grozev Supervisor: Prof. Rajkumar Buyya 7 th October 2015 PhD Completjon Seminar 1 2 3 Cloud Computjng Cloud computjng ...

slide-1
SLIDE 1

Brokering Techniques for Managing Three- Tier Applicatjons in Distributed Cloud Computjng Environments

Nikolay Grozev

Supervisor: Prof. Rajkumar Buyya

7th October 2015 PhD Completjon Seminar

1

slide-2
SLIDE 2

2

slide-3
SLIDE 3

3

slide-4
SLIDE 4

Cloud Computjng

  • Cloud computjng ...
  • is a model for delivering virtualized

computjng resources over the Internet;

  • is supported by large scale data centres

aggregatjng commodity hardware;

  • is subscriptjon based (pay-as-you-go);
  • Challenges - outages, security, etc.

www.google.com/datacenters/

4

slide-5
SLIDE 5

Inter-Cloud Computjng

  • Motjvatjon:
  • Mitjgate efgects of cloud outage;
  • Diversify geographical locatjons;
  • Avoid vendor lock-in;
  • Latency.
  • Solutjon - use multjple clouds

5

slide-6
SLIDE 6

Inter-Cloud Computjng: Architectures

6

slide-7
SLIDE 7

Inter-Cloud Computjng: Architectures

7

slide-8
SLIDE 8

3-Tier applicatjons in cloud

8

slide-9
SLIDE 9

3-Tier applicatjons in a Multj-Cloud

9

slide-10
SLIDE 10

Research Questjon

  • How to broker 3-Tier applicatjons in a Multj-Cloud environment,

considering Quality of Service (QoS) requirements in terms of:

  • Network Latency Awareness — end users should be served near their

geographical locatjon to experience betuer responsiveness;

  • Pricing Awareness— the overall costs for hostjng should be minimized;
  • Legislatjon/Policy Awareness — legal and politjcal consideratjons about

where individual users are served should be honoured;

  • Code Re-usability — few changes to existjng 3-Tier applicatjons should be
  • made. The technical overhead of moving an existjng 3-Tier system to a Multj-

Cloud should be minimal.

10

slide-11
SLIDE 11

Research Questjon

  • How to broker 3-Tier applicatjons in a Multj-Cloud environment,

considering Quality of Service (QoS) requirements in terms of:

  • Network Latency Awareness — end users should be served near their

geographical locatjon to experience betuer responsiveness;

  • Pricing Awareness— the overall costs for hostjng should be minimized;
  • Legislatjon/Policy Awareness — legal and politjcal consideratjons about

where individual users are served should be honoured;

  • Code Re-usability — few changes to existjng 3-Tier applicatjons should be
  • made. The technical overhead of moving an existjng 3-Tier system to a Multj-

Cloud should be minimal.

11

?

slide-12
SLIDE 12

12

slide-13
SLIDE 13

13

slide-14
SLIDE 14

Background and Objectjves

  • Distributed systems simulatjon has already fostered the research

efgorts;

  • Existjng simulators can be used to simulate batch processing and

infrastructure utjlisatjon workloads only;

  • Previous works on multj-tjer applicatjon modelling have series of

shortcomings;

  • Goal – defjne a fmexible and coarse grained model and simulator

for 3-Tier applicatjons in one and multjple clouds.

14

slide-15
SLIDE 15

Target Scenario

15

slide-16
SLIDE 16

Session Performance Model

  • AS Memory Load -
  • AS CPU Load -
  • DB Memory Load -
  • DB CPU Load -
  • DB Disk I/O Load -
  • Step Size –
  • Session arrival model:
  • Model each session type separately
  • Poison distributjon of a frequency

functjon -

16

slide-17
SLIDE 17

Simulator Implementatjon

17

slide-18
SLIDE 18

Validatjon Environment

  • 3-Tier app. designed afuer ebay;
  • Client applicatjon, generatjng requests;
  • Transitjon table;
  • "Think tjmes“;
  • Experiments;
  • Benchmarking;
  • Experiment 1 - statjc workload on local infrastructure;
  • Experiment 2 - dynamic workload on local infrastructure (DC1) and

EC2(DC2);

18

slide-19
SLIDE 19

Model Extractjon - Example

  • Execute 2 Experiments:
  • With 1 user;
  • With 100 users;
  • Compute the “average” session

behavior;

  • Standard Linux utjlisatjon

measurement tools.

19

slide-20
SLIDE 20

Experiment 1: Statjc Workload in 1 cloud

Predicted and actual disk I/O utjlisatjon of the DB server with 50, 300, and 600 simultaneous sessions in Experiment 1.

20

slide-21
SLIDE 21

21

slide-22
SLIDE 22

22

slide-23
SLIDE 23

Background and Objectjves

  • Current Multj-Cloud 3-Tier have limitatjons manage resources and

workload suboptjmally;

  • They do not consider essentjal regulatory requirements;
  • Goal: propose a general and fmexible architecture that honours key

non-functjonal requirements and optjmises cost and latency.

23

slide-24
SLIDE 24

Overall Architecture

24

slide-25
SLIDE 25

Overall Architecture

25

slide-26
SLIDE 26

Load Balancing and Autoscaling

  • Load balancing algorithm – stjcky or not?
  • Monitor VM utjlizatjon;
  • Free underutjlized VMs.
  • Autoscaling algorithm:
  • Repeated periodically;
  • Number of pre-provisioned instances;
  • Do not terminate before billing tjme is over;

26

slide-27
SLIDE 27

Load Balancing and Autoscaling

  • Load balancing algorithm – stjcky or not?
  • Monitor VM utjlizatjon;
  • Free underutjlized VMs.
  • Autoscaling algorithm:
  • Repeated periodically;
  • Number of pre-provisioned instances;
  • Do not terminate before billing tjme is over;

27

slide-28
SLIDE 28

Load Balancing and Autoscaling

  • Load balancing algorithm – stjcky or not?
  • Monitor VM utjlizatjon;
  • Free underutjlized VMs.
  • Autoscaling algorithm:
  • Repeated periodically;
  • Number of pre-provisioned instances;
  • Do not terminate before billing tjme is over;

28

slide-29
SLIDE 29

Load Balancing and Autoscaling

  • Load balancing algorithm – stjcky or not?
  • Monitor VM utjlizatjon;
  • Free underutjlized VMs.
  • Autoscaling algorithm:
  • Repeated periodically;
  • Number of pre-provisioned instances;
  • Do not terminate before billing tjme is over;

29

slide-30
SLIDE 30

Load Balancing and Autoscaling

  • Load balancing algorithm – stjcky or not?
  • Monitor VM utjlizatjon;
  • Free underutjlized VMs.
  • Autoscaling algorithm:
  • Repeated periodically;
  • Number of pre-provisioned instances;
  • Do not terminate before billing tjme is over;

30

slide-31
SLIDE 31

Cloud Selectjon Algorithm

  • Ensure users are served in

eligible clouds;

  • Timeout;
  • Estjmate network latency;
  • Estjmate potentjal cost;
  • Overloaded infrastructure;
  • Optjmise latency and cost.

31

slide-32
SLIDE 32

Performance Evaluatjon

  • Previous simulatjon env.;
  • Clouds of AWS and Google

in the US and Europe;

  • Baseline:
  • AWS Route 53;
  • AWS Elastjc LB;
  • AWS Autoscaling;

32

slide-33
SLIDE 33

33

slide-34
SLIDE 34

34

slide-35
SLIDE 35

Background and Objectjves

  • Current autoscaling approaches select

VMs statjcally:

  • Applicatjons change over tjme;
  • Workload changes over tjme;
  • Infrastructure capacity changes over

tjme.

  • Goal: propose a fmexible approach to

VM selectjon that adapts to such changes.

35

slide-36
SLIDE 36

Background and Objectjves

  • Current autoscaling approaches select

VMs statjcally:

  • Applicatjons change over tjme;
  • Workload changes over tjme;
  • Infrastructure capacity changes over

tjme.

  • Goal: propose a fmexible approach to

VM selectjon that adapts to such changes.

36

slide-37
SLIDE 37

Approach Overview

37

slide-38
SLIDE 38

Capacity Estjmatjon and Normalisatjon

  • Linux kernel fjle: /proc/cpuinfo;
  • Mpstat: %steal, %idle, actjve_memory;
  • Frequencies: fr1, ... frn;
  • nmax_cores, frmax, RAMmax;

ramLoadN orm active memory RAM

  • .
  • .
  • .
  • .

38

slide-39
SLIDE 39

ANN based online regression

  • Learning rate and Momentum;
  • Increase learning rate in the

beginning and when anomaly is detected;

  • Increase momentum at later

stages and when no anomaly is detected;

  • Online training and fjltering;

39

slide-40
SLIDE 40

VM type selectjon algorithm

  • For each VM type:
  • Estjmate its capacity;
  • Estjmate how many users it can

serve;

  • Choose best VM type in terms of

cost per user;

40

slide-41
SLIDE 41

Experimental setup and workload

  • CloudStone in AWS EC2;
  • Choose best VM type in terms of cost per user;
  • Increasing workload for 5 hours;
  • Workload change afuer 3.5 hours;
  • Baseline – AWS-like autoscaling;

41

slide-42
SLIDE 42

Experimental Results

42

slide-43
SLIDE 43

43

slide-44
SLIDE 44

44

slide-45
SLIDE 45

Background and Objectjves

  • How to implement the system from Chapter 4 with

modern sofuware technologies;

  • How to easily model user redirectjon requirements;

45

slide-46
SLIDE 46

Scope

46

slide-47
SLIDE 47

Entry Point – Admission Controller interactjon

  • Restgul web servers;
  • Entry Point bufgers and sends

requests in batch;

  • Admission Controller uses a rule

inference engine;

  • Entry Point choses optjmal cloud

site.

47

slide-48
SLIDE 48

Admission rules

  • Drools rule inference engine;
  • 3 layers of rules;
  • Polymorphism and rules;
  • Admission through

contradictjon.

48

slide-49
SLIDE 49

Experimental setup and workload

  • 24 hours, 2 users per second;
  • 50% of users require PCI-DSS compliant clouds;
  • Random citjzenship: Germany, USA, Australia, or Canada;
  • 50% of US citjzens are government offjcials.

49

slide-50
SLIDE 50

Results: dispatch tjmes and destjnatjons

50

slide-51
SLIDE 51

Results: dispatch tjmes and destjnatjons

51

slide-52
SLIDE 52

52

slide-53
SLIDE 53

53

slide-54
SLIDE 54

Summary

  • Proposed a performance model and a simulator for 3-Tier apps in

clouds;

  • Defjned a generic architecture for such applicatjons that honors the

key functjonal and non-functjonal requirements;

  • Proposed a method for VM type selectjon during autoscaling;
  • Proposed and implemented a user redirectjon approach in Multj-

Clouds.

54

slide-55
SLIDE 55

Future Directjons

  • Provisioning Techniques Using A Mixture of VM Pricing Models;
  • Dynamic Replacement of Applicatjon Server VMs;
  • VM Type Selectjon In Private Clouds;
  • Regulatory Requirements Specifjcatjon Using Industry Standards;
  • Generalisatjon to Multj-Tier Applicatjons.

55

slide-56
SLIDE 56

List of publicatjons

  • Nikolay Grozev and Rajkumar Buyya, “Inter-cloud Architectures and Applicatjon Brokering: Taxonomy and

Survey”, Sofuware: Practjce and Experience, John Wiley & Sons, Ltd, vol. 44, no. 3, pp. 369–390, 2014;

  • Nikolay Grozev and Rajkumar Buyya, “Performance Modelling and Simulatjon of Three-Tier Applicatjons

in Cloud and Multj-Cloud Environments”, The Computer Journal, Oxford University Press, vol. 58, no. 1,

  • pp. 1–22, 2015;
  • Nitjsha Jain, Nikolay Grozev, J. Lakshmi, Rajkumar Buyya , “PriDynSim: A Simulator for Dynamic Priority Based I/O Scheduling

for Cloud Applicatjons”, Proceedings of the IEEE Internatjonal Conference on Cloud Computjng for Emerging Markets, 2015 (In Press);

  • Nikolay Grozev and Rajkumar Buyya, “Multj-Cloud Provisioning and Load Distributjon for Three-tjer

Applicatjons”, ACM Transactjons on Autonomous and Adaptjve Systems, vol. 9, no. 3, pp. 13:1–13:21, 2014;

  • Nikolay Grozev and Rajkumar Buyya, “Dynamic Selectjon of Virtual Machines for Applicatjon Servers in

Cloud Environments”, Technical Report, CLOUDS Laboratory, The University of Melbourne, CLOUDS-TR- 2016-1

  • Nikolay Grozev and Rajkumar Buyya, “Regulatjons and Latency Aware Load Distributjon of Web

Applicatjons in Multj-Clouds”, Journal of Supercomputjng (Under Review), 2015;

56

slide-57
SLIDE 57

Acknowledgements

  • Supervisor: Professor Rajkumar Buyya;
  • Commituee: Professor James Bailey, Dr. Rodrigo Calheiros;
  • Dr. Amir Vahid and Dr. Anton Beloglazov;
  • Past and Present CLOUDS Lab members and CIS Department;
  • Microsofu;
  • Amazon Inc;
  • Family and Friends.

57

slide-58
SLIDE 58

Q&A

Thank you!

58