A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang...

23
A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University of Notre Dame Sponsored by NSF/ITR-DEB

Transcript of A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang...

Page 1: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

A Self-Manageable Infrastructure for Supporting Web-based

Simulations

Yingping HuangXiaorong XiangGregory Madey

Computer Science & Engineering University of Notre Dame

Sponsored by NSF/ITR-DEB

Page 2: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Outline

Introduction Autonomic Computing Web-based Simulations

Self-manageable infrastructure Self-Configuring Self-Healing Self-Optimizing Self-Protecting

Conclusion and future work

Page 3: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Autonomic Computing

Motivation What’s next? – A dozen

information technology research goals (J. Gray, Microsoft Research)

Goal The SysAdmin sets

system goals and high level polocies

System takes care of itself

http://www.ibm.com/autonomic

Page 4: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Autonomic Computing (cont)

Self-Configuring New simulations, new simulation

servers Self-Healing

Completed simulations Self-Optimizing

Efficient usage of system resources Self-Protecting

No unauthorized access

Page 5: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Web-based Simulations

Features of Web-based simulations Simulations run on the simulation servers Simulation data is downloadable for users Simulation reports are generated dynamically Simulation status is sent to users by email Collaboration among users

Challenges Reliability Availability Efficiency Security

Page 6: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Motivation: NOMSIM

Simulate natural organic matter (NOM) evolution behavior

Agent-based stochastic simulation method Multi-disciplinary project that involves

chemists, biologists, environmental scientists, geologists and computer scientists

Collaboration is essential Funded by NSF-ITR

Page 7: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Outline

Introduction Autonomic Computing Web-based Simulations

Self-manageable infrastructure Self-Configuring Self-Healing Self-Optimizing Self-Protecting

Conclusion and future work

Page 8: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

The Infrastructure

Page 9: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Features of the Infrastructure

Scalability Web server tier: new application servers can

be added to the balanced application server cluster

Simulation server tier: can be scaled almost linearly by installing new simulation servers running identical simulations

Database server tier: real application cluster (RAC) enables all active instances executing transactions against a shared database

Page 10: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Features of the Infrastructure (cont)

Availability Web server tier: eliminates single point

of failure by redundancy and failover, and session state is maintained in the database server tier

Simulation server tier: simulation checkpointing and resuming

Database server tier: eliminates single point of failure by redundancy and failover

Page 11: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Simulation Metadata

<simulation name="nomsim"> <db_url> <url>jdbc:oracle:thin:username/password@hostname:port:sid</url> <username>dbusername</username> <password>dbpassword</password> </db_url> <input_part> <input name="time" type="number" /> <input name="temperature" type="number" /> <input name="granted" type="char(1)" /> <input name="molecule_name" type="varchar2(50)" /> </input_part></simulation>

Page 12: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Simulation Manager and Intelligent Agents

One intelligent agent runs on one simulation server Functionalities of intelligent agents

Register new simulation servers to simulation manager Reports metrics of simulation servers to simulation manager Deploy new simulation models Check for simulation jobs Transport data from simulation servers to database servers Cancel simulation jobs as directed by the simulation

manager Functionalities of simulation manager

Dispatch and manage simulation jobs Notify users simulation job status

Page 13: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Self-Configuring

<simulation name="nomsim"> <db_url> <url>jdbc:oracle:thin:username/password@hostname:port:sid</url> <username>dbusername</username> <password>dbpassword</password> </db_url> <input_part> <input name="time" type="number" /> <input name="temperature" type="number" /> <input name="granted" type="char(1)" /> <input name="molecule_name" type="varchar2(50)" /> </input_part></simulation>

HTML form

JavaScript Form Validation Database Table

JSP Code

Page 14: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Self-Configuring (cont)

On simulation servers Intelligent agents must run Install simulation software

(To simplify: the simulation software is installed on an NFS server and which is mounted on the simulation servers)

On simulation manager Email masquerading

Page 15: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Self-Healing

Self-Healing Web servers Clustered application server instances Automatic recovery of failed instance

Self-Healing simulation servers Simulation checkpointing Simulation resuming

Self-Healing database servers Clustered database instances Automatic recovery of failed instance Raid 0+1

Page 16: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Self-Healing (cont)

Simulation RDBMS

Simulation Server Tier Database Server Tier

Checkpointing

Resuming

Page 17: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Self-Protecting

Role based access control Public Owner Grant

Firewall Port scan IPTABLES

Log messages scanning Network traffic monitoring, Intrusion

Detection (Future work)

Page 18: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Self-Optimizing

Self-Optimizing web server tier Load balanced application server

cluster Self-Optimizing database servers

Database parameter self-tuning Online index rebuilding Summary and aggregation

Page 19: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Self-Optimizing (cont)

Time

Simulation Server 1 Simulation Server 2

Checkpoint

Migrate

DBMS

Page 20: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Implementation of self-*

Tools IBM’s ABLE (agent

building and learning environment)

Oracle Data Mining

Unix Crontab

Languages Java SQL and PL/SQL Bourne shell

scripts

Page 21: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Outline

Introduction Autonomic Computing Web-based Simulations

Self-manageable infrastructure Self-Configuring Self-Healing Self-Optimizing Self-Protecting

Conclusion and future work

Page 22: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Conclusions and Future Work

Conclusions Self-Manageable infrastructure

Intelligent agents Simulation manager

Future work Applying data mining

“Intelligent agents” Proactive critical event prediction Job completion time prediction

Page 23: A Self-Manageable Infrastructure for Supporting Web-based Simulations Yingping Huang Xiaorong Xiang Gregory Madey Computer Science & Engineering University.

Questions?

Thank You