Analyzing Cross-layer Interaction in Overlay Networks

53
Analyzing Cross-layer Interaction in Overlay Networks Srinivasan Seetharaman September 2007

description

Analyzing Cross-layer Interaction in Overlay Networks. Srinivasan Seetharaman September 2007. Overlay Networks. Overlay networking helps overcome functionality limitations of the Internet by forming a virtual network over the native IP network that is: Independent Customizable. - PowerPoint PPT Presentation

Transcript of Analyzing Cross-layer Interaction in Overlay Networks

Page 1: Analyzing Cross-layer Interaction in Overlay Networks

Analyzing Cross-layer Interaction

in Overlay Networks

Srinivasan SeetharamanSeptember 2007

Page 2: Analyzing Cross-layer Interaction in Overlay Networks

22

Overlay Networks

Overlay networking helpsovercome functionalitylimitations of the Internetby forming a virtual networkover the native IP networkthat is:

Independent Customizable

Page 3: Analyzing Cross-layer Interaction in Overlay Networks

33

Service Overlay Networks

Offer enhanced or new services by deploying intelligent routing schemes.

Relaying

Overlay link

Page 4: Analyzing Cross-layer Interaction in Overlay Networks

44

Service Overlay Networks (contd.)

Characteristics: Nodes and links are persistent Perform overlay routing independent of native layer

routing Each Overlay path comprises one or more Overlay

links, based on a certain selfish objective

Many types of services can be offered Multicast (e.g. ESM, Overcast) QoS (e.g. OverQoS, SON) Security (e.g. DynaBone, SOS) Better routes (e.g. RON, Detour, X-Bone)… and much more

Page 5: Analyzing Cross-layer Interaction in Overlay Networks

55

Cross-Layer Interaction

Performing dynamic routing at both overlay and native IP layers leads to:

Conflict due to mismatch or misalignment of routing objectives

Contention for limited physical resources

Functionality overlap (Both overlay layer and IP layer perform similar set of functions)

Page 6: Analyzing Cross-layer Interaction in Overlay Networks

66

Cross-Layer Interaction (contd.)

These issues are amplified in the presence of

Selfish motives and aggressive behavior

Lack of information about other layer

Increasing impact ( #overlays |Traffic| )

Page 7: Analyzing Cross-layer Interaction in Overlay Networks

77

Context

Native network topology Intra-domain Inter-domain

Attitude of native network Restrictive Oblivious Cooperative

Page 8: Analyzing Cross-layer Interaction in Overlay Networks

88

Thesis Organization

. Oblivious Restrictive Cooperative

Intra-domain

Interaction with failure recovery

[Chapter III]

OR vs Load balancing

[Chapter V]

Overlay-friendly native

network[Chapter VII]

Inter-domain

OR vs Policy constraints[Chapter IV]

BT vs Load balancing

[Chapter VI]

Page 9: Analyzing Cross-layer Interaction in Overlay Networks

INTERACTION BETWEEN FAILURE RECOVERY IN THE NATIVE

AND OVERLAY LAYERS

Chapter III

Page 10: Analyzing Cross-layer Interaction in Overlay Networks

1212

Dual Rerouting

A

OVERLAY1

LAYER

NATIVE IP

LAYER

X

A

D

E F H

FH

GA

EC

C

BD

B

G

Each layer performs rerouting, with no knowledge of which layer leads to optimal restoration

Overlay reroutin

g

Native rerouting

Failure

Page 11: Analyzing Cross-layer Interaction in Overlay Networks

1515

1. Overlap of functionality between layers causing Unnecessary route changes (esp when connectivity in

native network is very dynamic) Increased probing overhead

2. Unawareness of other layer’s decisions leading to Multiple simultaneous failures

3. Lack of flexibility and control

Downside to Dual Rerouting

Page 12: Analyzing Cross-layer Interaction in Overlay Networks

1717

Tuning Dual Rerouting

Intra-domain (keepAlive-time = 1 sec, hold-time = 3 secs)

Dual Rerouting

Suppress overlay rerouting at 0.5 prob.

Defer overlay rerouting by 0.375 secs

Native-only rerouting

Average route changes 125.08% 101.59% 109.85% 1.567

Stabilized inflation 100% 108.32% 100% 1.202

Time when stable 113.7% 100.48% 107.33% 2.481

Peak inflation 114.22% 109.98% 110.73% 1.202

Page 13: Analyzing Cross-layer Interaction in Overlay Networks

1919

Further Improving Recovery

Adjust the functioning of native layer:

Tuning the native layer keepAlive-time:

This produces the best tradeoff

between # of route changes,

stabilization time and recovery time

keep

Alive

-tim

e

keep

Alive

-tim

e

Tuning

Page 14: Analyzing Cross-layer Interaction in Overlay Networks

INTERACTION BETWEEN OVERLAY ROUTING AND TRAFFIC ENGINEERING

Chapter V

Page 15: Analyzing Cross-layer Interaction in Overlay Networks

2121

Repeated Non-Cooperative Game

Player1: Overlay Routing - Latency-optimized paths between nodes

Player2: Traffic Engineering - Optimal load-balanced routes

OverlayRoutingOverlay Link

Latencies

Overlay layertraffic

Overlay routes

TrafficEngineerin

g

Traffic on each overlay

link

Background traffic

Nativeroutes

Native linkdelays

TM

Page 16: Analyzing Cross-layer Interaction in Overlay Networks

2626

Simulation Results

TEobjective

Overlayobjective

Overallstability

Round

Page 17: Analyzing Cross-layer Interaction in Overlay Networks

2828

Our goal

.. is to propose strategies that

obtain the best possible performance for a particular layerwhile steering the system towards a stable state.

Page 18: Analyzing Cross-layer Interaction in Overlay Networks

3131

Assume: Each layer has a general notion of the other layer’s selfish objective

Designate leader / follower

Operate leader such thata. Follower has no desire to change Friendlyb. Follower has no alternative to pick Hostile

Use history to learn desired action gradually.

Resolving Conflict – Our Approach

Page 19: Analyzing Cross-layer Interaction in Overlay Networks

3636

Performance of Preemptive Strategies

We proposed four strategies that improve performance for one layer and achieve a stable operating point

Inflation factor= Steady state obj value with strategy

Best obj value achievedLeader Strategy Overlay TE

Overlay Friendly: Load-constrained LPHostile: Dummy traffic injection

1.0821.023

1.1221.992

Native Friendly: Hopcount-constrained LPHostile: Load-based Latency tuning

1.0271.938

1.1841.072

Inflation

Page 20: Analyzing Cross-layer Interaction in Overlay Networks

Chapter VI

CROSS-LAYER INTERACTION OF PERFORMANCE-AWARE OVERLAY

APPLICATIONS

Page 21: Analyzing Cross-layer Interaction in Overlay Networks

3939

BitTorrent File-Sharing

Popular file-sharing application that generates a large volume of Internet traffic

Characteristics: Service capacity increases with demand Centralized tracker regulating neighborhood Dynamically change active peers by

choke/unchoke protocol

Page 22: Analyzing Cross-layer Interaction in Overlay Networks

4040

Comparison to Overlay Routing

AX

Data1

BY

Data2

A2

A1

B2B1A3

Page 23: Analyzing Cross-layer Interaction in Overlay Networks

4141

BitTorrent Protocol

Tit-for-tat based incentive for uploading decisions Leecher: Unchoke the fastest uploaders Seed: Unchoke the fastest downloaders

Popular strategy to improve performance Optimistic unchoke: periodically look for faster

peers

Page 24: Analyzing Cross-layer Interaction in Overlay Networks

4343

UnchokeRequest

BitTorrent Dynamics

B

X

A

L1

L2

ED

C

When bottlenecked on link L1

ChokeChoke

Load distribution across links is balanced

BitTorrent apps use all available b/wPeer TFT

Upload stats Download stats

Status Opt? Interested Pieces? Status My interest

Unchoke

Page 25: Analyzing Cross-layer Interaction in Overlay Networks

4444

BitTorrent Dynamics

B

X

A

L1

L2

ED

C

When NOT bottlenecked on link L1

ChokeChoke

Load distribution across links is unbalanced

Unchoke

Page 26: Analyzing Cross-layer Interaction in Overlay Networks

4545

Cross-Layer Interaction

Operating BitTorrent disrupts load balance and can result in high max util: This can be a problem for background traffic

Objective of native layer: Minimize ( Max Util.)

Objective of BitTorrent: Minimize (Overall finish time)

Page 27: Analyzing Cross-layer Interaction in Overlay Networks

4949

Simulation Setup

Pick 100 ASes with 60% of them being non-stub ASes

Page 28: Analyzing Cross-layer Interaction in Overlay Networks

5050

Simulation Setup

A

B

C

D

E

F

Generate 1-50 peers. Each associating with 1-3 torrents

F

L1

L2

Page 29: Analyzing Cross-layer Interaction in Overlay Networks

5353

Simulation Performance Metrics

Max util across access links

= MaxaE ( Xa/Ca ), E is set of all links

X is the load, C is the capacity

Average finish time inflation of leechers

= 1/Nl ( ’i / i ) Nl is # of leechers

’ is finish time after strategy

Nl

i=1

Page 30: Analyzing Cross-layer Interaction in Overlay Networks

5454

Reducing Impact – Traffic Engg

TE can be performed across inter-domain access links, in order to minimize (Max util)

Two flavors: Ingress / Egress

Determines which access link to pick for a certain destination or source IP address

Page 31: Analyzing Cross-layer Interaction in Overlay Networks

5555

Reducing Impact – Traffic Engg (contd.)

Applying TE does not make much difference

Performance of a random AS (Focus AS)

Page 32: Analyzing Cross-layer Interaction in Overlay Networks

5757

Alter certain BitTorrent protocol components or tune the associated parameters Minimal reduction of the max util Significant inflation of finish time

Specifically, we tried each of the following: Make peer selection random Make piece selection random Reduce duration of optimistic unchoking Freeze list of unchoked peers after 10 mins Tune the unchoking timers

Reducing Impact – Tuning BitTorrent

Page 33: Analyzing Cross-layer Interaction in Overlay Networks

5959

Reducing Impact – Locality-awareness

Locality-based traffic management Give priority to peers within AS No change to BitTorrent clients Also try caching of requests sent outside AS

Page 34: Analyzing Cross-layer Interaction in Overlay Networks

6060

Reducing Impact – Bandwidth Throttling

Limit bandwidth consumed by BT traffic Popular strategy among most ASes Involves lesser infrastructure cost

Page 35: Analyzing Cross-layer Interaction in Overlay Networks

6161

Cross-layer Conflict

Native layer and BitTorrent layer constantly retaliate to other layer’s disruptive behavior

Peers deploy BitTorrent Protocol Encryption to avoid detection by native layer

We develop two “friendly” BitTorrent strategies that achieve a mutually agreeable point by reducing peak load

Page 36: Analyzing Cross-layer Interaction in Overlay Networks

6262

A. Limit # of parallel downloads

The unchoking protocol and their timeline is uncoordinated across neighborsA

vera

ge

Page 37: Analyzing Cross-layer Interaction in Overlay Networks

6363

A. Limit # of parallel downloads (contd.)

Reduces peak load from 0.94 to 0.852Finish time inflation is 1.1501

Page 38: Analyzing Cross-layer Interaction in Overlay Networks

6464

B. Avoiding common neighbors

Problem is that two peers in same AS often contact same peer outside AS

Algorithm Perform bilateral info exchange where each

peer A finds out if its neighbor B has a neighbor C inside its own AS

If yes, toss a coin to determine if we can download from this peer B (Randomization acts as a load balancing strategy)

Page 39: Analyzing Cross-layer Interaction in Overlay Networks

6565

B. Avoiding common neighbors (contd.)

Reduces max util from 0.94 to 0.85Finish time inflation is 1.187

Page 40: Analyzing Cross-layer Interaction in Overlay Networks

ANALYZING INTER-DOMAIN POLICY VIOLATIONS IN OVERLAY

ROUTES

Chapter IV

Page 41: Analyzing Cross-layer Interaction in Overlay Networks

7070

Inter-Domain Policy Violations

Two types of violations exist

Provider 1

Provider 1

Client 1Client 1

A

Client 2

Client 2

BClient

3Client

3C

Provider 2

Provider 2Peer

Legitimate native route

Overlay route

Exit violation

$

Transitviolation

$$

Page 42: Analyzing Cross-layer Interaction in Overlay Networks

7575

Each transit violation has a corresponding exit violation upstream

Extent of exit policy violations in multihop paths

Measurement Results

Violation Type % paths

Next hop AS violated 72.05

Exit point violated 15.63

Total 87.68

Page 43: Analyzing Cross-layer Interaction in Overlay Networks

7676

Policy Enforcement by Native Layer

As ISPs become aware of the negative impact of overlays and commence filtering, this leads to

drastic deterioration in overlay route performance commensurate with the number of ASes enforcing policy

Page 44: Analyzing Cross-layer Interaction in Overlay Networks

7777

Overlay Service Provider (OSP) adopts a combination of the following strategies for achieving good legitimate paths:

1. Obtain transit permit from certain AS for $T

2. Add new node to certain provider AS for $N

3. Obtain exit permit from certain AS for $E

Resolving Conflict

Page 45: Analyzing Cross-layer Interaction in Overlay Networks

7878

With no filtering,

Illustration of Mitigation Strategy

31

21

32

22

11 13

23

33

Cust-Prov relation

Peering relation

Transitviolation

AS hosting overlay node

Tier-1 provider

Tier-2 provider

Stub customer

Page 46: Analyzing Cross-layer Interaction in Overlay Networks

7979

With filtering, we have no multi-hop paths

Illustration of Mitigation Strategy (contd.)

31

21

32

22

11 13

23

33

Cust-Prov relation

Peering relation

AS hosting overlay node

Tier-1 provider

Tier-2 provider

Stub customer

Page 47: Analyzing Cross-layer Interaction in Overlay Networks

8080

Option 1: Add new overlay node to provider AS 22

Option 2: Obtain transit permit from stub AS 32

Illustration of Mitigation Strategy (contd.)

31

21

32

22

11 13

23

33

Cust-Prov relation

Peering relation

AS hosting overlay node

Tier-1 provider

Tier-2 provider

Stub customer

22

Page 48: Analyzing Cross-layer Interaction in Overlay Networks

8181

Objective of Mitigation Strategy

For a certain budget, determine which ASes to obtain transit permit from to add new node to to obtain exit permit from

… so as to achieve the best possible gainGain = Native route latency – Overlay path

latency Native route latency

Page 49: Analyzing Cross-layer Interaction in Overlay Networks

8383

Mitigation Results

When all permit fee = P, new node fee = N

Add new node

Permit

Page 50: Analyzing Cross-layer Interaction in Overlay Networks

9090

Summary of Cross-Layer Interaction

Overlays offer valuable services needed by end-systems. But, lead to complex cross-layer interaction with potentially detrimental effects

Layer awareness is essential to reduce negative effects and to improve performance of both layers. We propose simple strategies that achieve this goal in an effective manner.

Page 51: Analyzing Cross-layer Interaction in Overlay Networks

9191

Contributions of Thesis

Knobs for better control over the cross-layer interaction

Analysis and mitigation of the conflict in objective between native and overlay layers:

inter-domain: OR vs Policy enforcement intra-domain: OR vs Traffic engg

Ways to improve coexistence between BitTorrent file-sharing and native layer

Framework for network layer support of overlay services

Page 52: Analyzing Cross-layer Interaction in Overlay Networks

9292

Future of Overlays

Overlays are essential as… Means for end-systems to collaborate Environment for testing future innovations (GENI) Architecture for Future Internet in the form of Network

Virtualization

Cross-layer interaction will affect performance. How best to design protocols and services in the future?

Page 53: Analyzing Cross-layer Interaction in Overlay Networks

9393

Future Work

Need to address the network impasse. How to tune the network for

.. the new breed of Internet applications? (e.g., file sharing) …and new paradigms of communication? (e.g., wireless)

Which layer to implement a service at? For example, a service like multicast can be performed at both native layer and overlay layer!

Which layer to use for a particular scenario? How can the other layer support this service?