Mobile Grid Computer Science Major Area Examination

1
Mobile Grid Computer Science Major Area
Examination

• Ye Wen
• Nov 13, 2002

2
Introduction Grid Computing

• The Grid Computing ProblemCoordinated resource
  sharing and problem solving in dynamic,
  heterogeneous environment.
• Characteristics of current Grid system
• Large-scale
• Heterogeneous
• Dynamic resource sharing relationship
• Pros and Cons
• Pros large-scale, heterogeneity, flexibility
• Cons static availability of resources,
  infrequent change

3
Introduction Mobile Computing

• What is mobile computing about?Build a
  distributed system for a network in which mobile
  devices and static hosts connected via wireless
  links.
• Characteristics of mobile computing
• Versatile communication (no wire constraints)
• Ubiquitous computation
• Flexible usability
• Pros and Cons
• Pros ubiquity, availability, productivity
• Cons constraints of wireless network
• Unpredictable network quality
• Lowered trust and robustness
• Limited local resources and battery lifetime for
  mobile devices

4
Mobile Grid Grid in mobile environment

• Mobile Grid Sharing both advantages
• Powerful computation capability of Grid system
• Ubiquitous and flexible availability of mobile
  system
• A scenario
• Other scenarios scientific application,
  commercial business

5
Exploring Mobile Grid (Outline)

• Overview of GridGrid architecture
• Performancescheduling scheme, scheduling
  algorithm
• Energy awarenessdynamic power management,
  computation offloading
• Adaptationdisconnected operation, adaptive
  application
• Securitymobile authentication
• Address mobility and location independent
  namingmobile IP, ad hoc protocols
• Distributed, reliable and scalable
  storagepeer-to-peer resource routing

6
Overview of Grid Architecture

• Many ways to look at the Grid
• Open Grid Services Architecture (OGSA)
• Virtual Organization (VO) a set of individuals
  or institutions that provide or request
  resources.
• Service orientation everything is service.
• Service virtualization definition separated from
  implementation.
• Service semantics -- the Grid Service standard
  interfaces of interoperability
• Discovery service data, service registration,
  service data retrieving
• Dynamic service creation service factory
• Lifetime management service destroy and
  termination, keep alive
• Notification

Ian Foster, Carl Kesselman, Jeffrey M. Nick,
Steven Tuecke, "The Physiology of the Grid An
Open Grid Services Architecture for Distributed
Systems Integration." Open Grid Service
Infrastructure WG, Global Grid Forum, June 2002.
7
Scheduling Application Level Scheduling

• Goal of scheduling maximize application
  performance.
• Application Level Scheduling (AppLeS)
• An application-specific approach to build
  scheduler for parallel applications on
  heterogeneous systems.
• Comprehensive system and application information
• Static information
• User-specified application parameters
• Application performance model
• Dynamic information Network Weather Service
• Performance prediction Network Weather Service
• Experience the system from the point view of
  application
• Run-time scheduling Information is applied to
  application model to estimate application
  performance and choose an optimal resource
  allocation from a set of viable configurations.
• Goodness accurate

F. Berman, R. Wolski, S. Figueira, J. Schopf, and
G. Shao, "Application-Level Scheduling on
Distributed Heterogeneous Networks." In
Proceedings of Supercomputing 96, Pittsburgh, PA,
Nov. 1996.
8
Scheduling Algorithms host-satellite systems

• Host-satellite system
• A powerful host and many less-powerful satellites
• Offloading computation from satellite to host to
  maximize overall performance
• Fit the scenario of mobile environment
• Partitioning algorithm
• Requirements
• Serial program
• Pipeline processing
• Chain structure
• Construct assignment graph for the partition
  problem.
• Weight for edges (Wh, Ws)
• Find the optimal sum-bottleneck path in the
  assignment graph
• Complexity O(n2loge)

Shahid H. Bokhari, "Partitioning problems in
parallel, pipelined and distributed computing."
IEEE Transactions on Computers, 37(1)48-57,
1988.
9
Energy saving

• Energy crisis of mobile devices
• Performance also concerns energy
• Energy consumption estimation
• Simulation SimplePower, Wattch
• Empirical methods
• Ways to save energy
• Dynamic power management (DPM) policies tradeoff
  between energy and performance
• Spin down disks
• Turn off screen
• Network interface hibernation
• Processor voltage scaling
• Comprehensive stochastic model
• Computation offloading

10
Policy optimization of DPM

• Policy optimization
• Most aggressive policy is not acceptable.
• Find the balance of aggressiveness to optimize
  performance and energy consumption.
• Stochastic model Discrete-time Markov decision
  processes
• Model service provider, service requestor, queue
• Power manager makes random decision according to
  current state of SP, SR, Q, at each time period.
• Minimize performance penalty while keeping
  average energy consumption and request loss below
  some levels specified by users.
• Advantages generality, abstraction,
  non-determinism

G. A. Paleologo, L. Benini, A. Bogliolo, G. De
Micheli, "Policy Optimization for Dynamic Power
Management." Design Automation Conference, pp.
182-187, June 1998.
11
Computation offloading

• Scheduling in terms of energy
• Offloading can reduce computation, but
  communication also consumes energy
• Optimize energy consumption by offloading part of
  computation
• Model a program
• Task definition each call site (statically)
  each invocation (dynamically)
• Cost graph
• Relationship between tasks and data
• Node weight indicating power consumption of
  computation and communication
• Edge weight indicating mean number of times for
  tasks accessing data
• Aggregate the consumption from the cost graph and
  optimize

Zhiyuan Li, Cheng Wang, Rong Xu, "Computation
offloading to save energy on handheld devices a
partition scheme." In Proceedings of the
international conference on compilers,
architecture, and synthesis for embedded systems,
Atlanta, Georgia, USA, 2001.
12
Disconnected operation

• Another fact affects performance unpredictable
  network link quality
• Solution adaptation
• Disconnected operation in Coda file system
• Definitiona mode of operation that enables a
  client to continue accessing critical data during
  temporary failures of a shared data repository.
• Solution proxy cache
• Venus client-side proxy
• Three working states
• Hoarding
• Emulation
• Reintegration

James J. Kistler, M. Satyanarayanan,
"Disconnected Operation in the Coda File System."
ACM Transactions on Computer Systems, Feb. 1992,
Vol. 10, No. 1, pp. 3-25.
13
Application-aware adaptation

• Application-aware adaptation model
• System notifies application of relevant changes
• Application decides how to adapt to the changes
• Design of Odyssey proxy again
• Typed data
• Working model
• Application requests data within a range of
  availability
• Odyssey returns data or notify change
• Application re-request data of different quality
  using different range
• Implemented as VFS in NetBSD system
• Requests are intercepted as system call
• Advantages agility, smooth running, support of
  concurrency

Brian D. Noble, M. Satyanarayanan, Dushyanth
Narayanan, James Eric Tilton, Jason Flinn, Kevin
R. Walker, "Agile Application-Aware Adaptation
for Mobility." In Proceedings of the 16th ACM
Symposium on Operating System Principles, St.
Malo, France, Oct 1997.
14
Mobile security

• Difficulties of security in wireless mobile
  environment
• Inherent vulnerability of wireless media
• Performance impact!
• Charon indirect authentication using Kerberos
• Extend Kerberos by inserting a remote proxy
  (again!!) between client and other servers
• Secure channel is built by first granting the
  proxy service to client
• Proxy interacts with other servers on clients
  behalf
• Client can be very small only need DES
  encryption/decryption
• No compromise of security
• The communication between client and proxy is
  encrypted
• Proxy believes the identity of user
• Proxy does not possess clients session key and
  private key

Armando Fox, Steven D. Gribble, "Security on the
move indirect authentication using Kerberos." In
Proceedings of the second annual international
conference on Mobile computing and networking
(MobiCom'96), Rye, New York, United States, 1996.
15
Address mobility and location independent naming

• Wireless mobile networks
• Nomadic network Mobile IP
• Ad hoc network ad hoc routing protocols

16
Mobile IP

• Problems
• stable connection requires stable IP ? stable
  routing ? no mobility
• Solution associate two IPs with one host (one
  for identification, one for routing)
• Mobile IP

Charles E. Perkins, "Mobile IP", IEEE
Communications Magazine, May 1997.
17
Ad hoc routing protocol

• Ad hoc network
• No static or centralized infrastructure
• Packet relay routing
• Ad-hoc On-Demand Distance Vector Routing (AODV)
• Pure on-demand route acquisition
• Discover and maintain a route to another node
  only when
• Need to communicate with the node
• Current node acts as an intermediate forwarding
  node
• Timeout to purge outdated path
• Only reinitiate path discovery when moving node
  lying along active path
• Monotonic increasing sequence number to supercede
  stale path
• Goodness scalability, efficiency, responsiveness
  to change

C. E. Perkins, E. M. Royer, "Ad-hoc On-Demand
Distance Vector Routing." In Proceedings of the
2nd IEEE Workshop on Mobile Computing Systems and
Applications, New Orleans, LA, February 1999, pp.
90-100.
18
Peer-to-Peer resource routing

• Difference with Grid
• No distinguished server anywhere (scalability)
• Unstable nodes join/leave (reliability)
• Problems how to find resource in peer-to-peer
  network?
• Keep each resource location at each node not
  scalable
• Flooding (Gnutella) not scalable
• Centralized index server (Napster) single
  failure
• P2P routing algorithms (distributed hash table)
• Content Addressable Network (CAN) distributed 2D
  hash table
• Chord ring-based structure
• Pastry Plaxton-tree based
• Tapestry Plaxton-tree based
• Similarities and differences between ad hoc
  routing and P2P routing
• Sims high mobility and low reliability of nodes,
  hop by hop connection, flat network topology,
  etc.
• Diffs purpose of usage, node-node connection,
  abstraction level, routing table, etc.

19
Pastry

• Plaxton-tree-like structure
• Hashed ID for both node and document
• Routing table (O(logN)) digit similarity
• Leaf set numerically closest nodes
• Routing (O(logN) hops)
• First check leaf set
• Then use routing table to forward message (1
  more digit)
• Finally check ID with longest prefix and closest
  value
• Goodness
• Highly distributed (reliability)
• Scalability
• Efficiency

A. Rowstron, P. Druschel, "Pastry Scalable,
distributed object location and routing for
large-scale peer-to-peer systems." IFIP/ACM
International Conference on Distributed Systems
Platforms (Middleware), Heidelberg, Germany,
pages 329-350, November, 2001.
20
Conclusions

• Incorporating mobility into Grid architecture is
  necessary and beneficial.
• Problems arise since meaning of performance is
  extended
• Computational performance scheduling
• Energy power management and offloading
• Unstable network adaptation
• Security
• Addressing and naming
• Scalability Reliability
• A lot can be borrowed from other research areas,
  but they should be put into a real Mobile Grid
  framework for inspection.
• Future focus comprehensive scheduling
• Thanks