A QoS Assurance Framework for Distributed Infrastructures Andr Lage - - PowerPoint PPT Presentation

▶
a qos assurance framework for distributed infrastructures
SMART_READER_LITE
LIVE PREVIEW

A QoS Assurance Framework for Distributed Infrastructures Andr Lage - - PowerPoint PPT Presentation

Dec 08, 2022 362 likes •755 views

A QoS Assurance Framework for Distributed Infrastructures Andr Lage Freitas , Nikos Parlavantzas, Jean-Louis Pazat {Andre.Lage,Nikos.Parlavantzas,Jean-Louis.Pazat}@irisa.fr Universit Europenne de Bretagne INSA, INRIA, IRISA, UMR 6074

slide-1
SLIDE 1

A QoS Assurance Framework for Distributed Infrastructures

André Lage Freitas, Nikos Parlavantzas, Jean-Louis Pazat

{Andre.Lage,Nikos.Parlavantzas,Jean-Louis.Pazat}@irisa.fr Université Européenne de Bretagne INSA, INRIA, IRISA, UMR 6074 F-35708 Rennes, France Myriads Team - INRIA–IRISA 3rd International Workshop on Monitoring, Adaptation and Beyond (MONA+) Ayia Napa, Cyprus

December 1, 2010

slide-2
SLIDE 2

Outline

1

Context Service-Oriented Architecture (SOA) The Problem Challenges

2

QU4DS: Quality Assurance for Distributed Services Architecture Use Cases Implementation Preliminary Evaluation

3

Conclusions

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 2 / 32

slide-3
SLIDE 3

Outline

1

Context Service-Oriented Architecture (SOA) The Problem Challenges

2

QU4DS: Quality Assurance for Distributed Services Architecture Use Cases Implementation Preliminary Evaluation

3

Conclusions

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 3 / 32

slide-4
SLIDE 4

Service-Oriented Architecture (SOA) [5]

Service abstraction

Distributed business applications Re-usability Interoperability Loose-coupling

Service-Based Applications (SBA)

Composition of services Service-Level Agreements (SLA)

Functional Non-functional

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 4 / 32

slide-5
SLIDE 5

Service-Oriented Architecture (SOA) [5]

Quality of Service (QoS)

Promotes business Differentiates service providers Influences directly on contract establishments

Examples:

Request response time Request throughput Service availability

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 5 / 32

slide-6
SLIDE 6

The Problem

To ensure the agreed QoS Prevent SLA violations

Avoid penalties Reduce costs Improve service reputation

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 6 / 32

slide-7
SLIDE 7

The Problem: Scope

Atomic service on large-scale distributed infrastructures

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 7 / 32

slide-8
SLIDE 8

Goal

Provide QoS assurance for atomic service on large-scale distributed infrastructures

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 8 / 32

slide-9
SLIDE 9

Goal

Provide QoS assurance for atomic service on large-scale distributed infrastructures

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 9 / 32

slide-10
SLIDE 10

Goal

Provide QoS assurance for atomic service on large-scale distributed infrastructures

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 10 / 32

slide-11
SLIDE 11

Goal

Provide QoS assurance for atomic service on large-scale distributed infrastructures

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 11 / 32

slide-12
SLIDE 12

Goal

Provide QoS assurance for atomic service on large-scale distributed infrastructures

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 12 / 32

slide-13
SLIDE 13

Raised Issues

What can the underlying infrastructure provide? How to match QoS requirements to service instantiation and resource configurations? How to deal with the dynamic environment?

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 13 / 32

slide-14
SLIDE 14

What can the underlying infrastructure provide?

Trade-off

Simplicity Control

A Uniform Infrastructure Usage SAGA [3] easy + accounting Separation of two distinct managements

Job Resource

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 14 / 32

slide-15
SLIDE 15

What can the underlying infrastructure provide?

Trade-off

Simplicity Control

A Uniform Infrastructure Usage SAGA [3] easy + accounting Separation of two distinct managements

Job Resource

Simple and high-level

Job

create(jobDescription) run() cancel() checkpoint() suspend() resume() migrate() registerCallback()

Accounting

Pricing model

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 14 / 32

slide-16
SLIDE 16

How to match QoS requirements to service instantiation and resource configurations?

QoS ↔ service instance and resource configurations

E.g.: response time ↔ instantiation requirements + number of resources

It is not trivial High-level infrastructures interfaces are not enough

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 15 / 32

slide-17
SLIDE 17

How to match QoS requirements to service instantiation and resource configurations?

QoS ↔ service instance and resource configurations

E.g.: response time ↔ instantiation requirements + number of resources

It is not trivial High-level infrastructures interfaces are not enough Representation of such a translation

Application profiling Analytical models Implementation details

The more knowledge, the more accurate

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 15 / 32

slide-18
SLIDE 18

How to deal with the dynamic environment?

Unpredictability of service demand

New customers Provision changes

Infrastructure dynamism

Availability Requirements fluctuations

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 16 / 32

slide-19
SLIDE 19

How to deal with the dynamic environment?

Unpredictability of service demand

New customers Provision changes

Infrastructure dynamism

Availability Requirements fluctuations

Self-Adaptation

Adaptation at runtime Autonomic control loop [4] Dynaco [1]

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 16 / 32

slide-20
SLIDE 20

The Pieces Together

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 17 / 32

slide-21
SLIDE 21

The Pieces Together

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 18 / 32

slide-22
SLIDE 22

The Pieces Together

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 19 / 32

slide-23
SLIDE 23

Outline

1

Context Service-Oriented Architecture (SOA) The Problem Challenges

2

QU4DS: Quality Assurance for Distributed Services Architecture Use Cases Implementation Preliminary Evaluation

3

Conclusions

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 20 / 32

slide-24
SLIDE 24

QU4DS: Quality Assurance for Distributed Services

QU4DS is a framework for ensuring QoS for distributed services

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 21 / 32

slide-25
SLIDE 25

QU4DS: Quality Assurance for Distributed Services

QU4DS is a framework for ensuring QoS for distributed services Translate QoS parameters to service instance and resource configurations in a bi-directional way Automatically deploy the service on appropriate resources Ensure the agreed QoS by reacting to underlying infrastructures changes while keeping compliant to the QoS objectives

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 21 / 32

slide-26
SLIDE 26

QU4DS – Architecture

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 22 / 32

slide-27
SLIDE 27

QU4DS – Use Case 1: SLA Negotiation

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 23 / 32

slide-28
SLIDE 28

QU4DS – Use Case 2: QoS Assurance

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 24 / 32

slide-29
SLIDE 29

Implementation Overview

Prototype implemented in Java Support for Master/Worker applications Management of service tasks

Workers wrapped as jobs Master can focus on its main concern

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 25 / 32

slide-30
SLIDE 30

Implementation Overview

Prototype implemented in Java Support for Master/Worker applications Management of service tasks

Workers wrapped as jobs Master can focus on its main concern

Infrastructure: simple, high-level API and based on XOSAGA

Backend: XtreemOS [2] Customized metrics

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 25 / 32

slide-31
SLIDE 31

Implementation Details

QoS Translator: application profiling

QoS ↔ # of workers

E.g.: 1 min response time ↔ 4 workers

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 26 / 32

slide-32
SLIDE 32

Implementation Details

QoS Translator: application profiling

QoS ↔ # of workers

E.g.: 1 min response time ↔ 4 workers

Self-Adaptation: QoS Assurance Controller

Implements a simple control loop Monitor

Job: state, elapsed time, CPU usage, number of threads, command QoS: response time

Decider

Event-condition-action

Planning

Sequence of XOSAGA methods

Executor

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 26 / 32

slide-33
SLIDE 33

Case Study: The flac2ogg Service

An audio encoder

Encodes Flac to Ogg Master/Worker service

QoS

Response time Translation

Degree of parallelization t = 23 sec/MB ↔ 12 workers

Adaptation strategy

Single Replacement for Late Jobs (SRLJ)

Policies Conditions Actions j: jobETimeThreshold rt: respTimeThreshold if (jobETime > j) AND (requestETime < rt) 1) create a job to replace the late job 2) cancel the late job 3) submit the job replacement André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 27 / 32

slide-34
SLIDE 34

Preliminary Evaluation

Emulated environment (virtual machine)

2.4 GHz CPU 1.5 GB memory XtreemOS core and resource

Two faulty scenarios

NA-F: Non-Adaptable A-F: Adaptable QoS translation

response time 500 secs ↔ 12 workers

30 requests

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 28 / 32

slide-35
SLIDE 35

Preliminary Evaluation

Emulated environment (virtual machine)

2.4 GHz CPU 1.5 GB memory XtreemOS core and resource

Two faulty scenarios

NA-F: Non-Adaptable A-F: Adaptable QoS translation

response time 500 secs ↔ 12 workers

30 requests

Experiment Violated requests NA-F 12 (40%) A-F 6 (20%)

Table: QU4DS reduced to half the number of SLA violations.

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 28 / 32

slide-36
SLIDE 36

Outline

1

Context Service-Oriented Architecture (SOA) The Problem Challenges

2

QU4DS: Quality Assurance for Distributed Services Architecture Use Cases Implementation Preliminary Evaluation

3

Conclusions

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 29 / 32

slide-37
SLIDE 37

Conclusions

QU4DS: a framework for quality assurance of distributed services

Prevents SLA violations Re-negotiates agreements Eases the development of distributed and QoS-aware services

Self-Adaptation

Autonomic control loop Single Replacement for Late Jobs (SRLJ)

Prototype

XtreemOS Early results are promising

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 30 / 32

slide-38
SLIDE 38

Current and Future Directions

On-going work

Uniform infrastructure interface under XOSAGA and Grid’5000 Improvements on integrating monitoring mechanisms and the infrastructure Manage distinct contracts in parallel

Challenges for future work

QoS Translation accuracy

Service provider knowledge

Support beyond Master/Worker applications

E.g.: workflow management

Negotiate resource usage with the infrastructure

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 31 / 32

slide-39
SLIDE 39

Questions?

Thank you!

References

[1]

  • J. Buisson, F

. André, and J.-L. Pazat. Dynamic adaptation for Grid computing. In EGC ’05: Proceedings of The European Grid Conference, pages 538–547, Amsterdam, June 2005. [2]

  • T. Cortes, C. Franke, Y. Jégou, T. Kielmann, D. Laforenza, B. Matthews, C. Morin, L. P

. Prieto, and A. Reinefeld. XtreemOS: a Vision for a Grid Operating System. Technical report, XtreemOS Consortium, May 2008. [3]

  • T. Goodale, S. Jha, H. Kaiser, T. Kielmann, P

. Kleijer, A. Merzky, J. Shalf, and C. Smith. A Simple API for Grid Applications (SAGA). Global Grid Forum, January 2008. [4]

  • J. O. Kephart and D. M. Chess.

The Vision of Autonomic Computing. Computer, 36(1):41–50, January 2003. [5]

  • M. P

. Papazoglou and D. Georgakopoulos. Service-Oriented Computing, Introduction.

  • Commun. ACM, 46(10):24–28, 2003.

André Lage Freitas (INRIA - Myriads Team) Quality Assurance for Distributed Services December 2010 32 / 32