20
Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre Department of Computing, Imperial College

Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

Embed Size (px)

Citation preview

Page 1: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

Performance Architecture within ICENI

Dr Andrew Stephen McGoughLaurie Young, Ali Afzal, Steven Newhouse and John Darlington

London e-Science Centre

Department of Computing, Imperial College London

Page 2: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

2

Outline

• Overview of ICENI

• Performance Framework

• Example

• Conclusion

Page 3: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

3

ICENI: Imperial College e-Science Network Infrastructure

• Collect and provide relevant Grid Meta-Data

• Pluggable architecture• Test Architecture for Grid Research• Foundation for higher-level Services

and Autonomous Composition• Integrated Grid Middleware Solution• Interoperability between

architectures, APIs • Added value layer to other

middleware• Usability: Interactive Grid Workflows• Role and policy driven security• ICENI Open Source licence (extended

SISSL)

The Iceni, under Queen Boudicca, united the tribes of South-East England in a revolt against the occupying Roman forces in AD60.

Page 4: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

4

Scheduling Workflows in ICENI

• Applications consist of a number of components linked together in a dataflow manner

• The abstract workflow needs to be mapped down to a set of component implementations which will run on resources

Linear EquationSource

Linear EquationSolver

Display VectorResults

General Equation generato

r

LU Factorisatio

n

Simple Vector Display

Page 5: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

5

The Problem

• We have:– Multiple resources where components can run– Multiple implementations of components– The choice of one resource component

mapping can affect the others

• User wants predictable performance

• How to choose the “best” mapping of workflow over resources to give user predictability?

Page 6: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

6

The Solution

• We need to take into account:– Execution Times of components on Resources

• Performance Data

– Inter-component effects of workflows• Workflow aware Schedulers

– Workload on resources, making sure they are free when we need them

• Reservation systems

Page 7: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

7

The Architecture

Scheduler

ReservationService

PerformanceStore

Launcher

ApplicationService

ReservationEngine

Workflow

Page 8: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

8

Performance Store- Persistent Performance storage

Performance Store- Persistent Performance storage

The Performance Repository Framework:

Performance Framework

Performance Processing- Conversion of raw event times into performance data

Data Collector-Collecting data on currently running applications (event times)

Performance Store- Persistent Performance storage

Page 9: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

9

Collection of Performance Results

Data CollectorLinear EquationSource

Linear EquationSolver

Display VectorResults

Time Event 12:00 Linear Equation Source Start 12:04 Send out Equations 12:03 Linear Equation Solver Start 12:05 Receive Equations 12:12 ………..

Event:Start LinearEquation Source

Performance Processing

Workflow

Performance Store

Page 10: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

10

Storing Performance Data

• Multiple stores can be used in one framework

• The stores may be data stores or analytical models

• All assumed to be persistent• Allows requests for predictions to be made• New Data can be added to the stores• Store data is aggregated together

– based upon reliability of store data• Provided by the store

Performance Store

Page 11: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

11

Using Performance Data

• Scheduler Builds up workflow graph with timings requested from the Performance Repository

• Timings are based on component implementation, resource, co-allocation count and other properties defined by the component implementer

• As the store will not contain all possible combinations of these properties regression is used to provide estimates for the missing values– This is an area of ongoing research

Page 12: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

12

Reservation Engine

ReservationEngine Framework

Reservations Database- Data about upcoming reservations,usedto test if a new reservation can be made

DRM Translation level-Communication with the underlying DRM system for supporting Reservations

Listen out for requests- Launcher services wishing to makereservations

Page 13: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

13

Reservation Service

ReservationService Framework

Reservations Database- Data about upcoming reservations,usedto test if a new reservation can be made

Reservation orchestration-Attempts to reserve all resources for a given workflow. May shift when it runs

Listen out for Services- Launcher with reservation- Scheduling Services

Page 14: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

14

Reservations

time →

time →

ReservationService

Scheduler

Workflow Reserve (workflow)

HOLD

Conflict

HOLD

HOLD

Reserve

Reserve

WS-AgreementRequest interval

Linear EquationSource

Linear EquationSolver

Display VectorResults

Reservations not possible on Users Desktop

Page 15: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

15

Example: Linear Equation Solver

service list composition pane parameters

Page 16: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

16

Inferring Workflow from Dataflow

Page 17: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

17

Conclusion

• Better usage of resources.– Reservations of resources in the future– Determining if co-allocation of components will affect

performance– Late Enactment of components

• Critical Path analysis – can schedule this appropriately

• Provides a framework for experimentation with– Different scheduling algorithms– Different performance models– Different reservation policies

Page 18: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

18

Performance Trinity

Performance Models

Grid Scheduling Reservation Fabric

Page 19: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

19

The Architecture: Showing the Trinity

SchedulerReservation

Service

PerformanceStore

Launcher

ApplicationService

ReservationEngine

Page 20: Performance Architecture within ICENI Dr Andrew Stephen M c Gough Laurie Young, Ali Afzal, Steven Newhouse and John Darlington London e-Science Centre

20

Acknowledgements

• Director: Professor John Darlington• Research Staff:

– Nathalie Furmento, Stephen McGough, William Lee– Jeremy Cohen, Marko Krznaric, Murtaza Gulamali– Asif Saleem, Laurie Young, Jeffrey Hau– David McBride, Ali Afzal

• Support Staff:– Oliver Jevons, Sue Brookes, Glynn Cunin, Keith Sephton

• Alumni:– Steven Newhouse, Yong Xie, Gary Kong– James Stanton, Anthony Mayer, Angela O’Brien

• Contact:– http://www.lesc.ic.ac.uk/ e-mail: [email protected]