A Na Native C Content Di Discover ery Mechan anism f for or - - PowerPoint PPT Presentation

a na native c content di discover ery mechan anism f for
SMART_READER_LITE
LIVE PREVIEW

A Na Native C Content Di Discover ery Mechan anism f for or - - PowerPoint PPT Presentation

A Na Native C Content Di Discover ery Mechan anism f for or NDN Onur Ascigil , Vasilis Sourlas, Ioannis Psaras, and George Pavlou Department of Electronic and Electrical Engineering, University College London, UK 1 Outlin line


slide-1
SLIDE 1

A Na Native C Content Di Discover ery Mechan anism f for

  • r NDN

Onur Ascigil, Vasilis Sourlas, Ioannis Psaras, and George Pavlou Department of Electronic and Electrical Engineering, University College London, UK

1

slide-2
SLIDE 2

Outlin line

  • Content discovery
  • Opportunistic Off-path Content Discovery
  • Forwarding Strategies
  • Results
  • Future Work &Conclusions

2

slide-3
SLIDE 3

Cont ntent nt D Discovery

3

slide-4
SLIDE 4

Content Discovery

  • Goal: Retrieve a nearby (ideally the nearest!) copy of the content
  • Difficult to achieve without significant ``overhead’’ in practice
  • Why?
  • Placement of Data into the Content Stores happens frequently
  • What does NDN/CCN do?
  • Route Interests to content origins
  • Search content opportunistically on-path (i.e., along the default path)
  • Existing Solutions for Content Discovery:
  • Opportunistic on-path
  • Coordinated off-path

4

slide-5
SLIDE 5

Content Discovery

  • Opportunistic on-path: limited gain, without overhead
  • Coordinated off-path: coordination and communication overhead
  • Using control plane: Advertise content names
  • Using a function: A Hash function determines the placement and routing
  • What do we propose?
  • integrate an “opportunistic off-path content discovery mechanism” to the existing

Interest/Data processing pipeline of NDN

  • With minimal changes to NDN packet processing
  • Without introducing excessive overhead

5

slide-6
SLIDE 6

Opportunistic Of Off-path C Content Discovery

6

slide-7
SLIDE 7

Opportunistic off-path Content Discovery

  • Satisfied Interest Table (SIT): Caches trails of Data packets

Interest /ndn/xyz R S T U Prefix Next-hop /ndn T Prefix Next-hop /ndn U

Data /ndn/xyz Interest /ndn/xyz Name Next-hop

/ndn/xyz

T Name Next-hop

/ndn/xyz

S H1 H2 Prefix Next-hop /ndn T FIB FIB SIT SIT FIB

7

slide-8
SLIDE 8

For

  • rwarding St

g Strategi egies es with F FIB & B & SI SIT

8

slide-9
SLIDE 9

Forwarding Strategies with FIB & SIT

  • Breadcrumb

R S T U Prefix Next-hop /ndn U

Data /ndn/xyz Name Next-hop

/ndn/xyz

S H1 H2 FIB SIT Interest /ndn/xyz Interest /ndn/xyz CS /ndn/xyz Wait in the PIT

9

Name Next-hop

/ndn/xyz

S, R

slide-10
SLIDE 10

Forwarding Strategies with FIB & SIT

  • Breadcrumb

R S T U Prefix Next-hop /ndn U

NACK /ndn/xyz Name Next-hop

/ndn/xyz

S H1 H2 FIB SIT Interest /ndn/xyz Interest /ndn/xyz CS Wait in the PIT

10

Name Next-hop

slide-11
SLIDE 11

Forwarding Strategies with FIB & SIT

  • Multicast

R S T U Prefix Next-hop /ndn U

Name Next-hop

/ndn/xyz

S H1 H2 FIB SIT Interest /ndn/xyz Interest /ndn/xyz CS /ndn/xyz Data /ndn/xyz Data /ndn/xyz

11

Name Next-hop

/ndn/xyz

S, R

slide-12
SLIDE 12

Forwarding Strategies with FIB & SIT

  • Multicast: Once forwarded downstream, an Interest follows a single SIT trail
  • Forwarding Strategy: Pick the freshest matching SIT entry

R S T U Prefix Next-hop /ndn U

Name Next-hop

/ndn/xyz

S H1 H2 FIB SIT Interest /ndn/xyz Interest /ndn/xyz CS

12

slide-13
SLIDE 13

Forwarding Strategies with FIB & SIT

  • Multicast: Once forwarded downstream, an Interest follows a single SIT trail
  • Forwarding Strategy: Pick the freshest matching SIT entry

R S T U Prefix Next-hop /ndn U

Name Next-hop

/ndn/xyz

S H1 H2 FIB SIT Interest /ndn/xyz CS

13

NACK /ndn/xyz Name Next-hop

slide-14
SLIDE 14

Res esul ults - Multicast and Br Brea eadc dcrumb St Strategi egies es

14

slide-15
SLIDE 15

Results- Settings

  • Topology: Rocketfuel ISP topology
  • Content Providers: Attached to 16 egress nodes are randomly chosen
  • Link Latencies: Penalty for leaving ISP network: extra 50-100 msec
  • Network Cache Capacity: %80 of content can be cached in the network
  • Request Rate: 100 Requests/sec (origins selected randomly)
  • Popularity Distribution: Zipf Parameter 0.7
  • Experiment Duration: 1 Hour warm-up and 3 hours of experiment

AS 3257

15

slide-16
SLIDE 16

Results with Breadcrumb & Multicast

Overlap

16

slide-17
SLIDE 17

Results

  • Modified Multicast Strategy:
  • Each Interest is associated with a Forwarding Budget
  • spend the budget on:
  • sending a copy upstream (following FIB)
  • sending a copy downstream (following SIT)
  • spend it on both
  • Cost of sending Interest upstream/downstream
  • Static: Deduct one unit per each copy sent downstream.
  • Dynamic: Deduct variable amount per each copy sent downstream

17

slide-18
SLIDE 18

Multicast with Forwarding Budget (Static)

Name Next- hops /x/y/z Y Q Y R S T N Interest: /x/y/z

Budget = 6

Interest: /x/y/z

Budget = 7

Interest: /x/y/z OFF-PATH SIT Interest: /x/y/z Interest: /x/y/z

Budget = 5

18

slide-19
SLIDE 19

Res esul ults - Multicas ast with F Forwar arding B g Budget

19

slide-20
SLIDE 20

Res esul ults - Multicas ast with F Forwar arding B g Budget

20

Overlap Satisfaction

slide-21
SLIDE 21

Conclus usions ns

  • Opportunistic content discovery using SIT table
  • Significant increase in the percentage of requests satisfied from

the caches

  • Forwarding strategies using SIT/FIB are introduced
  • Possible to limit the overhead with a Forwarding Budget and Dynamic Costs
  • Requires minimal changes to the packet processing of NDN
  • Security
  • End-user/host caches are not exploited by the mechanism
  • Exclude field can be used to ignore matching SIT entries
  • Our scheme inherits the existing cache poisoning problems with NDN

21

slide-22
SLIDE 22

Thank you! Questions?

22