Networking

1
Networking

• Kihong ParkAssistant ProfessorDepartment of
  Computer SciencesPurdue University

2
Team

• K. Park (CS)
• D. Yau (CS)
• W. Szpankowski (CS)
• N. Shroff (ECE)
• S. Fahmy (CS)

3
Related Faculty

• B. Bhargava (CS)
• D. Comer (CS)
• E. Houstis (CS)
• D. Marinescu (CS)
• V. Rego (CS)

4
Funding (1)

• Network Scheduling
• NSF ANI-9875789 (Park, CAREER)
• NSF ANI-9714707 (Park)
• End System Scheduling
• NSF CCR-9875742 (Yau, CAREER)
• NSF ESS-9806741 (Grama, Park, Yau)

5
Funding (2)

• Related
• NSF ANI-9729721 (vBNS, Purdue-wide)
• NSF NCR-9415491 (Szpankowski)
• NSF CCR-9804760 (Szpankowski)
• NSF NCR-9624525 (Shroff, CAREER)
• NSF ANI-9805441 (Shroff, Schwartz)
• Sprint (Park, Spafford)

6
Labs

• Network Systems Lab (Park)
• Systems Software Arch. Lab (Yau)
• NEWS (Shroff)
• Multimedia Compression (Szpankowski)
• BOND, COAST, Internetworking Lab, Multimedia DB,
  RAID

7
Components

• End-to-End QoS
• Network Scheduling
• Packet scheduling
• End-to-end control
• End System Scheduling
• Real-time OS
• Distributed scheduling

8
Research Goal (1)

• Network Environment

9
Research Goal (2)

• Diverse QoS requirements
• Shared network resources
• facilitate QoS-sensitive sharing of network
  resources

10
Research Issues

• Diverse user QoS requirements
• Bursty traffic
• Scalability
• Efficiency
• Resource contention resolution
• Selfishness

11
State-of-the-Art (1)

• Resource Reservation Admission Control
• On-demand leasing of bandwidth
• QoS guarantees
• GPS routers
• IETF Int-Serv (e.g., RSVP)

12
State-of-the-Art (2)

• Drawbacks
• Wasteful
• self-similar bursty traffic
• overprovisioning
• Scales poorly with system size
• per-flow control
• admission control policing

13
(No Transcript)
14
State-of-the-Art (3)

• Overkill for many applications
• Soft QoS
• Graded service levels
• Resource contention resolution
• Who should get what
• Noncooperative environment

15
State-of-the-Art (4)

• IETF Diff-Serv
• Assured service (Clark)
• 2-bit marking bit RIO gateways
• Premium service (Jacobson)
• Leaky-bucket with priority gateways
• aggregate flow control with weak protection

16
State-of-the-Art (5)

• Drawbacks
• Differentiated service
• not QoS-sensitive
• Admission control policing/shaping
• impediment to scalability
• Weak complexity trade-off
• Lack of resource contention resolution

17
SBS Approach (1)

• Dual Architecture
• Guaranteed service (GS)
• Reservation-based QoS
• Small fraction of most stringent apps
• Stratified best-effort service (SBS)
• Graded service
• Large spectrum of QoS-sensitive apps

18
SBS Approach (2)

• Architectural Features
• Compatible with reservation scheme
• Common substrate of GPS routers
• Amortize cost of overprovisioning for GS
• Aggregate flow control
• Per-flow QoS control
• Zero per-flow state at routers
• Distributed protocol

19
SBS Approach (3)

• SBS Router

20
SBS Approach (4)

• SBS Control Path

21
SBS Approach (5)

• Properties
• Graded services
• Beyond differentiated services
• QoS-sensitivity
• Scalability
• No resource reservation
• No admission control
• Aggregate flow control
• Simple user/network interface

22
SBS Approach (6)

• Resource contention resolution
• Selfish user behavior
• Stability, optimality, efficiency
• Pricing
• WAN implementation
• User-centric ? networking-centric mechanism
• Simple user/simple network realization
• Distributed QoS Control

23
Distributed QoS Control (1)

• Component Services
• Guaranteed service (GS)
• Stratified best-effort service (SBS)
• SBS Protocol
• Packet scheduling at routers
• End-to-end control

24
Distributed QoS Control (2)

• WAN QoS Control GS

25
Distributed QoS Control (3)

• WAN QoS Control SBS GS

26
Distributed QoS Control (4)

• Self-Optimization Procedure
• Select service class s.t.
• . QoS requirement is satisfied
• . Least cost, i.e., minimum resource service
  class
• User optimal
• Selfishness emulation

27
Distributed QoS Control (5)

• GPS Switch Multi-Class QoS

28
Distributed QoS Control (6)

• Service Class-QoS Association Table
• Ca lt Cb ? Pa gt Pb

29
System Operation (1)

• Service Access Point
• Direct user access
• Access by DB Security modules
• Export API
• (GS/SBS, QoS Requirement Vector)

30
System Operation (2)

• Interface with DB Security Modules

31
QoS Parameters Translation (1)

• Network QoS
• Traffic characterization
• Mean/peak/minimum data rates
• Reliable/unreliable transport
• QoS requirements
• Packet loss rate
• Delay
• Jitter

32
QoS Parameters Translation (2)

• Application QoS
• QoP other user requirements
• Video frame rate (f/s)
• Hit rate
• Hit rate jitter
• Reliability
• Security services

33
QoS Parameters Translation (3)

• Hit Rate
• Probability of timely arrival

34
QoS Parameters Translation (4)

• QoS Translation

35
QoS Parameters Translation (5)

• Example (hit rate)
• if Measured Hit Rate lt Target Hit Rate then
• increase allocated resources
• else
• decrease resources
• QoS translation control loop

36
System Performance (1)

• vBNS Benchmarking

37
System Performance (2)

• Traffic Configuration

38
System Performance (3)

• SBS Performance

39
System Performance (4)

• Performance Comparison

40
End-to-End QoS Control (1)

• SBS Exports Graded Services
• QoS amplification using end-to-end control

41
End-to-End QoS Control (2)

• Real-Time Traffic
• Adaptive forward error-correction
• Inject redundancy adaptively (network state)
• Maintain invariant target QoS
• Optimal control problem
• AFEC protocol

42
End-to-End QoS Control (3)

• QoS-Redundancy Curve

43
End-to-End QoS Control (4)

• Real-Time MPEG Video Transport

44
End-to-End QoS Control (5)

• Benchmark Experiments

45
End-to-End QoS Control (6)

• Benchmark Data

46
End-to-End QoS Control (7)

• Performance Measurements

47
End-to-End QoS Control (8)

• Redundancy Trace

48
End-to-End QoS Control (9)

• Self-Similar Traffic Control
• Exploit long-range dependence
• Multiple time scale congestion control (MTSC)
• Throughput (SAC, TCP-MT)
• Real-time traffic (AFEC-MT)

49
End-to-End QoS Control (10)

• Multiple time scale congestion control

50
Proposed Research (1)

• Implementation of GS/SBS Architecture
• Experimental network
• Purdue Infobahn
• Testbed substrate for MSI
• User/network API
• 2-Tier network
• Backbone Cisco 72xx routers
• LANs ATM Gigabit Ethernet

51
Proposed Research (2)

• Purdue Infobahn

52
Proposed Research (3)

• Performance Comparison Diff-Serv
• Assured service
• Premium service
• SBS Optimization
• End-to-end QoS control ? switch architecting
• Cooperative control
• Refinements (e.g., SBS Light)
• Deployability experiments

53
Proposed Research (4)

• Measurement Collection/Dissemination
• Traffic characterization
• User behavior characterization
• INDEX project (Berkeley, NSF ANIR)
• Limitations
• Outdated applications
• ISDN line rates
• Infinite supply/overprovisioning

54
Proposed Research (5)

• User behavior characterization (cont.)
• Next generation resource sharing behavior
• high-bandwidth, multimedia applications
• extend to direct user pool
• diverse QoS requirements
• token/pricing-based resource contention
  resolution
• stability, robustness, fairness
• vBNS/Abilene peering traffic

55
Proposed Research (6)

• End-to-End QoS Control Experiments
• QoS amplification trade-off
• Quality vs. quantity
• QoS tunneling
• Protocol stack interaction
• Self-similar traffic control
• Long-range dependence delay-bandwidth
• Variable compression traffic control

56
Proposed Research (7)

• Integrated DB Security Experiments
• Extended QoS specification API
• QoS translation
• Integrated scheduling
• Component analysis
• Hybrid scheduling
• Application benchmarking

57
Proposed Research (8)

• QoS, Security, and Fault-Tolerance
• Security/QoS trade-off overhead
• Reactive security (vs. proactive)
• Fault-tolerance and QoS
• Impact of fault-tolerance on QoS
• Hierarchical fault-tolerance self-healing
• Network management
• Availability