Presentation is loading. Please wait.

Presentation is loading. Please wait.

L ondon e-S cience C entre Application Scheduling in a Grid Environment Nine month progress talk Laurie Young.

Similar presentations


Presentation on theme: "L ondon e-S cience C entre Application Scheduling in a Grid Environment Nine month progress talk Laurie Young."— Presentation transcript:

1 L ondon e-S cience C entre Application Scheduling in a Grid Environment Nine month progress talk Laurie Young

2 L ondon e-S cience C entre 2 Overview Introduction to grid computing Work so far… Imperial College E-Science Networked Infrastructure (ICENI) Scheduling within ICENI Optimisation criteria/Scheduling policy Scheduling/Mapping algorithms

3 L ondon e-S cience C entre 3 What is a Grid? CPU Node Storage Node Scientific Instrument Visulisation/Steering Software

4 L ondon e-S cience C entre 4 What is a Grid Application? Tier2 Centre ~1 TIPS Online System Offline Processor Farm ~20 TIPS CERN Computer Centre FermiLab ~4 TIPS France Regional Centre Italy Regional Centre Germany Regional Centre Institute Institute ~0.25TIPS Physicist workstations ~100 MBytes/sec ~622 Mbits/sec ~1 MBytes/sec There is a bunch crossing every 25 nsecs. There are 100 triggers per second Each triggered event is ~1 MByte in size Physicists work on analysis channels. Each institute will have ~10 physicists working on one or more channels; data for these channels should be cached by the institute server Physics data cache ~PBytes/sec ~622 Mbits/sec or Air Freight (deprecated) Tier2 Centre ~1 TIPS Caltech ~1 TIPS ~622 Mbits/sec Tier 0 Tier 1 Tier 2 Tier 4 1 TIPS is approximately 25,000 SpecInt95 equivalents

5 L ondon e-S cience C entre 5 Current Work Development of Supporting Technologies –Development of EPIC (E-Science IC) GridFTP (High throughput FTP) Grid/Globus submission of jobs to resources Development of test application –Parameter sweep analysis of submarine acoustics –Multithreaded and Component versions –Integration with EPIC

6 L ondon e-S cience C entre 6 ICENI IC e-Science Networked Infrastructure Developed by LeSC Grid Middleware Group Collect and provide relevant Grid meta-data Use to define and develop higher-level services The Iceni, under Queen Boudicca, united the tribes of South-East England in a revolt against the occupying Roman forces in AD60.

7 L ondon e-S cience C entre 7 ICENI Component Applications Each ICENI job is composed of multiple components. Each runs on a different resource Each component is connected to at least one other component. Data is passed along these connections

8 L ondon e-S cience C entre 8 The Scheduling Problem Given a component application and a (large) network of linked computational resources, what is the best mapping of components onto resources?

9 L ondon e-S cience C entre 9 Scheduler in ICENI Resources ICENI App Builder (GUI) Component Repository Performance Models SchedulerBroker

10 L ondon e-S cience C entre 10 Multiple Metrics (1) It is the goal of a scheduler to optimise one or more metrics (Feitelson & Rudolph) Generally one metric is most important –Application Optimisation Execution time Execution cost –Host Optimisation Host utilisation Host throughput Interaction Latency

11 L ondon e-S cience C entre 11 In a Grid Environment there are three application optimisation based important metrics –Start time ( ) –End time ( ) –Cost ( ) Relative importance varies on a user by user and application by application basis Multiple Metrics (2)

12 L ondon e-S cience C entre 12 A Benefit Function maps the metrics we are interested in to a single Benefit Value metric Different benefit functions represent different optimisation preferences Combining Metrics – Benefit Fn

13 L ondon e-S cience C entre 13 Optimisation Preferences Cost Optimisation Time Optimisation Cost/Time Optimisation

14 L ondon e-S cience C entre 14 Graph Oriented Scheduling (1) Applications are described as a graph –Nodes represent application components –Edges represent component communication Resources are described as a graph –Nodes represent resources –Edges represent network connections

15 L ondon e-S cience C entre 15 VOYAGER Microsoft/Dell Intel Cluster 32 processor Giganet Centre Resources SATURN Sun E6800 SMP 24 processors Backplane: 9.6GB/s PIONEER Athlon Cluster 22 processor 100Mb Storage ATLAS Compaq / Quadrics Cluster 32 processor MPI: ~5.7us & >200 MB/s CONDOR POOL ~ 150 PIII processors AP Sparc Ultra II APNet VIKING 1 P4/Linux Cluster 66 dual node Myrinet VIKING 2 P4/Linux Cluster 68 dual node 100Mb 6TB 1.2TB 24TB

16 L ondon e-S cience C entre 16 Graph Oriented Scheduling (2) Condor pool AtlasSaturn Viking DesignAnalyse Scatter Gather Mesh DRACS Mesh DRACS Mesh DRACS Factory

17 L ondon e-S cience C entre 17 Graph Oriented Scheduling (3) Condor pool ScatterGather Design Atlas Factory Analyse Saturn Viking

18 L ondon e-S cience C entre 18 Schedule Benefit Each component and communication has a benefit function Each resource and network connection has a predicted time & cost for each component or communication that could be deployed Fit the task graph onto the resource graph to get the maximum Total Predicted Benefit

19 L ondon e-S cience C entre 19 Future Work Develop benefit maximisation algorithms Test schedulers –On grid simulators such as SimGrid, GridSim and MicroGrid –On grid testbeds, such as IC Testbed and the EUDG Develop brokering methods Define Scheduler-Broker communications

20 L ondon e-S cience C entre 20 Summary Concept of grid computing for HPC/HTC ICENI Middleware for utilization of grids Importance of scheduling metrics Combining metrics Mapping application graphs - resource graphs Optimisation of total benefit Need good mapping algorithms…


Download ppt "L ondon e-S cience C entre Application Scheduling in a Grid Environment Nine month progress talk Laurie Young."

Similar presentations


Ads by Google