6.964 Pervasive Computing Grid: Scalable Ad Hoc Networking

1
6.964 Pervasive Computing Grid Scalable Ad Hoc
Networking

• 1 November 2001
• Douglas S. J. De Couto
• Parallel and Distributed Operating Systems Group
• MIT Laboratory For Computer Science
• http//www.pdos.lcs.mit.edu/grid

2
Who are we?

• Grid project in PDOS
• Professor Robert Morris
• Students
• Douglas De Couto
• Dan Aguayo
• Jinyang Li
• Ben Chambers
• Hu Imm Lee

3
Outline

• Motivation
• Classic ad hoc protocol
• Geographic forwarding
• Grid location service (GLS)
• Location proxies
• The Grid network

4
So you want to build a pervasive network?

• Assumptions
• Wireless, packet-based, mobile
• Bigger than just your living room (multihop)
• Todays approach IEEE 802.11 base stations
• Site survey, measure radio performance
• Channel Allocation
• Inter-base-station network (wiring?)

5
Base-station example
Wired network
B1
B2
3
1
2
4
6
Ad hoc a better way

• Ad hoc means no infrastructure, no planning
• Normally implies wireless, mobile, multihop
• Place devices (nodes) anywhere
• Constraint devices should form connected network
• If not, add relay nodes
• Costs less!

7
Ad hoc example
3
r
1
2
4
8
Ad hoc scenarios

• Temporary, fast setup
• Emergencies
• Social events
• Rooftop networks
• Connect neighborhoods
• No wires, trenches, etc.
• Developing communities
• Ad hoc is cheaper, more incremental
• Automatic protocols ? no technicians needed

9
Other ad hoc benefits

• Better spectrum reuse (spatial)
• Better scalability
• Possibly better power

10
Ad hoc challenges

• How do we find multihop routes?
• Is there enough network capacity?
• Does it use too much device power?
• Span Chen et al., Mobicom 2001

11
Classic protocol

• Dynamic Source Routing (DSR)
• Flooding route discovery finds source routes as
  needed
• Aggressive caching helps performance

12
Why not use DSR?

• Protocol works well with about a hundred nodes
• Simulation results vary with movement, data
  traffic
• Protocols scales poorly
• Propagates topology information throughout
  network
• Overhead grows too fast with network size,
  especially with mobility

13
DSR overhead
Avg. packets transmitted per node per second
Number of nodes
14
Geographic forwarding (GF)
Cs radio range
A
D
F
C
G
B
E

• Packets addressed to ?id,location?
• Next hop is chosen from neighbors to move packet
  geographically closer to destination location
• Routing overhead constant as network size (nodes,
  area) grows

15
GF With a Local Protocol
E
D
C
F
Local protocol is 2-hop distance vector A
sends packets to F dcf dbf but ddf and C is Bs next hop to D
Bs nbrs A, 1 hop (nh A) C, 1 hop (nh C) D, 2
hops (nh C)
B
A
As nbrs B, 1 hop (nh B) C, 2 hops (nh B)
D, 2 hops (nh C)
C, 2 hops (nh B)
16
Geo. forwarding challenges

• How do we find destination locations?
• How do nodes find their own locations?
• Location sensors not always practical
• Topology problems (holes)
• General ad hoc problems
• Power, capacity

17
Grid Location Service (GLS) overview
E
H
L
B
D
J
G
A
D?
I
F
K
C
Each node has a few servers that know its
location. 1. Node D sends location updates to its
servers (B, H, K). 2. Node J sends a query for D
to one of Ds close servers.
18
Grid Node Identifiers

• Each Grid node has a unique identifier.
• Identifiers are numbers.
• Perhaps a hash of the nodes IP address.
• Identifier X is the successor of Y if X is the
  smallest identifier greater than Y.

19
GLSs Spatial Hierarchy
All nodes agree on the global origin of the grid
hierarchy
20
3 servers per node per level

• s is ns successor in that square.
• (Successor is the node with least ID greater
  than n )

21
Queries search for destinations successors
s
n
s
s
s
s
Each query step visit ns successor at
increasing level.
s
s
s1
x
s2
s
s3
22
GF GLS performs well
Biggest network simulated 600 nodes,
2900x2900m (4-level grid hierarchy)
Fraction of data packets delivered successfully

• Geographic forwarding is less fragile than
  source routing.
• DSR queries use too much b/w with 300 nodes.

23
GLS properties

• Spreads load evenly over all nodes
• Degrades gracefully as nodes fail
• Queries for nearby nodes stay local
• Per-node storage and communication costs grow
  slowly as the network size grows O(log n), n
  nodes
• More details Li et al, Mobicom 2000

24
Geo. forwarding challenges

• How do we find destination locations?
• How do nodes find their own locations?
• Location sensors not always practical

25
Location Proxies

• Nodes that know their location can act as
  location proxies
• Location proxies can communicate with each other
  using geographic forwarding and the local routing
  protocol
• Nodes without location select proxies, and
  communicate through them using the local protocol
• Nodes advertise proxy locations as their own
• Proxies not special besides knowing locations

26
Proxies Increase Delivery Rate
27
The Grid network

• Red 5th floor
• Blue 6th floor
• 20 relay nodes
• About 2 to 4 hops across each floor

28
Current Grid services

• IP routing, including Internet gateway
• E.g. supports traceroute
• Grid specific information
• Who can my radio talk to?
• Who do I have routes to?

29
Grid services in progress

• Location service
• Where is node X?
• Geocast
• Send message m to every node in region R
• Position estimation protocol
• I dont have a position sensor
• Where am I?

30
Grid Applications

• What is a Grid application
• Uses unique Grid services
• Under development Grid chat
• Regular text voice chat
• Whos nearby? (ask Grid)
• Whos at the student center? (ask Grid)

31
Grid details

• Protocol software implemented in the Click
  modular router
• Runs at userlevel, easy to interface to
  applications
• Very portable
• Nodes
• Mobile iPaqs 802.11 PCMCIA Linux
• Relay small PCs 802.11 PCI cards OpenBSD
• Global distance vector (DV), or k-hop DV GF

32
Grid Summary

• Grid routing protocols are
• Self-configuring
• Easy to deploy
• Scalable
• http//www.pdos.lcs.mit.edu/grid
• ipkg http//www.pdos.lcs.mit.edu/decouto/grid-fe
  ed
• ipkg install grid