NetSolve

1
NetSolve

• Henri Casanova and Jack Dongarra
• University of Tennessee and Oak Ridge National
  Laboratory
• http//www.cs.utk.edu/netsolve

2
Objectives

• Harnessing vast computational resources on the
  network
• Hardware
• Software
• Convenient for scientific computing community
• Reducing installation and programming overhead
• Masking complexity related to distributed
  computing

3
Computation-Sharing Models Proxy Computing
4
Computation-Sharing ModelsCode Shipping
Code
Code
Data
Client
Server
Computation on the client
5
Computation-Sharing ModelsRemote Computation
Data
Data
Code
Client
Server
Computation on the server
6
Design issues

• Platform independence to accommodate
  heterogeneity
• User friendly
• Extensibility
• Load balancing
• Fault tolerance

7
NetSolve Architecture
OS
Resources
8
NetSolve Organization and Operation
9
NetSolve Client Interface

• C, Fortran, Java, Matlab, and Mathematica
• gtgt a rand(100) b rand(100,1)
• gtgt x netsolve(ax b, a, b)
• gtgt a rand(100) b rand(100,1)
• gtgt request netsolve_nb (send, ax b, a,
  b)
• gtgt x netsolve_nb(probe, request)
• Not ready
• gtgt x netsolve_nb(wait, request)

10
NetSolve Wrappers

• Problem description file for extensibility
• _at_PROBLEM ipars
• _at_INCLUDE ipars.h
• _at_LIB /home/user/lib/libipars.a
• _at_DECRIPTION
• Parallel Sub-Surface Flow Simulator
• _at_INPUT 2
• _at_OBJECT STRING CHAR model
• _at_OBJECT FILE CHAR infile
• Compiled into wrappers around scientific
  libraries
• XDR for platform-independent data transfer

11
NetSolve Load Balancing

• Assigning a task to the best machine
• Establishing a performance model
• Network delay, server properties, task properties
• Measuring and monitoring dynamic system states
• Load balancing at a finer granularity
• Parallelism through non-blocking interface
• Task migration

12
NetSolve Fault Tolerance

• Inter-server fault tolerance
• Fault tolerance among NetSolve servers
• Intra-server fault tolerance
• Fault tolerance within a NetSolve server

13
NetSolve Fault Tolerance Inter-server Fault
Tolerance

• Performed by NetSolve agents
• Basic approach
• Failure detection task reallocation
• Overload detection task migration
• Introducing NetSolve storage servers
• Store checkpoints or any information related to
  fault tolerance (must be platform-independent)
• No reliance on failed or overloaded server for
  task migration

14
NetSolve Fault ToleranceIntra-server Fault
Tolerance

• Not a new problem
• Could be invisible to NetSolve
• Can take advantage of platform-specific features
  for fault tolerance
• Possible integration with inter-server fault
  tolerance

15
Diskless Checkpointing Checksums and Reverse
Computation

• Diskless checkpointing eliminates the need for
  stable storage
• N servers a checkpointing server
• At any point, consistent checkpoints taken at N
  servers (stored in memory)
• A checksum of checkpoints stored at the
  checkpointing server
• Rollback using reverse computation
• State recovery using the checksum

16
Applications

• MCell with NetSolve
• Large code, small data
• Matlab with NetSolve
• Tradeoffs between parallelism and overhead
• IPARS with NetSolve
• ImageVision with NetSolve

17
(No Transcript)
18
Integration with ScaLAPACK
19
Integration with Condor
20
Integration with Ninf
21
Conclusion

• An interesting infrastructure for sharing
  computational resources
• Both software and hardware
• Convenience, performance, and reliability
• Playground for fault tolerance
• Both general and specific