CSS434:%20Parallel%20

1
CSS490 Grid Computing Textbook No Corresponding
Chapter
Instructor Munehiro Fukuda These slides were
compiled from The Grid Blueprint for a New
Computer Infrastructure.
2
Network Infrastructure

• Users login their organizational systems first
  locally or remotely.
• If they are affiliated with other organizations,
• They can login from the system of their main use
  to some other systems. (They are given an
  opportunity to use those resources in parallel).
• Problems
• They must orchestrate job execution among the
  resources they use.
• Should those resources be limited to such a
  handful number of researchers?

3
The Computational Grid

• Use computing resource connected to high-speed
  information highway as if we use electric power
  grid
• Only 30 utilization in academic/commercial
  environments.
• Many applications have only episodic
  requirements. So, why don稚 we share computation
  resource?
• Computational results and data should be also
  made available to all users.
• Users
• Computational scientists and engineers
• Experimental scientists
• Association and corporations
• Training and education
• Consumers (E-commerce)

4
Grid Applications
Category Examples Characteristics
Distributed supercomputing DIS and Stellar dynamics Very large problems needing lots of computing resource at a time
High throughput Chip design and parameter studies Harnessing many idle resources to increase aggregate throughput
On demand Medical instrumentation Allocating special resource dynamically
Data intensive Sky survey Using distributed data and needing high-volume data flows
Collaborative Collaborative design Education Support communication or collaborative work
5
ExampleDistributed Interactive Simulation
Fighter simulator
Tank simulator
Observer/Analyst
Small unit (company, platoon) commander
Software agents (automated enemy)
6
Grid Services Architecture(from www.globus.org
slide)
High-energy physics data analysis
Collaborative engineering
On-line instrumentation
Applications
Regional climate studies
Parameter studies
Distributed computing
Collab. design
Remote control
Application Toolkit Layer
Data- intensive
Remote viz
Information
Resource mgmt
. . .
Grid Services Layer
Security
Data access
Fault detection
Transport
Multicast
. . .
Grid Fabric Layer
Instrumentation
Control interfaces
QoS mechanisms
7
Grid Systems/Tools

• NetSolve
• http//icl.cs.utk.edu/netsolve/
• RPC-based approach
• Legion
• http//legion.virginia.edu/
• Object-based approach
• Globus Toolkit
• http//www.globus.org/
• Tool-based approach

8
NetSolve
Network of servers
Client

• RPC-based approach
• Clients
• Include a set of APIs called as (asynchronous)
  RPCs
• Agents
• Match client痴 requests for services with servers
• Servers
• Encapsulates remotely accessed numerical libraries

Agent
Agent
choice
Scalar server
Client
request
reply
MPP servers
9
Legion

• Legion classes
• Act as managers and make policy
• Core objects
• Provide mechanisms that classes use to implement
  policies hosts (processors), vaults(memory),
  context, binding agents, etc.
• Per-Program Scheduling
• Participating sites can assure their local
  policies.
• User can choose a scheduling policy.

Prog
request
Enactor
Scheduler
Converted Legion object ID By context objects
reserve
search
Converted Logion object address By binding agents
Resource database
Class
Host
collection
tty
Host
Host
tty
Resources
Class
tty
10
Globus
Resource brokers and resource co-allocators MPI, HPC, CORBA Arch. Type, OS, memory, bandwidth
GRAM (RSL-based management) Nexus (Remote execution by thread migration) MDS (Directory info. Tree)
Condor NQE Load Sharing Facility IP, Message passing, ATM, shared mem. LDAP

• A collection of tools
• GRAM Resource allocation and process management
• Nexus Communication services
• MDS Directory services
• GSI Authentication/security services

11
CoordAgents(The CSS490 Instructor痴 New Research
Project)

• Mobile-agent-based approach
• Resources
• Server resources and client requests are all
  described in XML.
• Servlet
• Launches a mobile agent on behalf of a client.
• Maintains a server resources.
• Mobile agents
• Carries a client program, executes it remotely,
  and reports its results to the client.

Each Server
Client
Outgoing
Web
Launcher servlet
Incoming
Rsc Mgmt servlet
Agent engine
Jave DB
Resource XML
OS
12
CoordAgents Cont壇(The CSS490 Instructor痴 New
Research Project)

• PCs
• Most PCs are idle
• PC Grid
• Why don稚 PC users get together to use each
  other痴 idle PCs?
• Challenges
• PCs may be powered on and off suddenly.
• Network bandwidth may change suddenly.
• Using CoordAgents
• Dispatches a user job.
• Performs check-pointing.
• Migrate a process dynamically.