1. Challenges to Reliable Data Transport Over Heterogeneous Wireless Networks

2. Motivation (Ch 1+2) Everybody went nuts about wireless (cell phones, etc) and the data networks (the internet) in the 90's Then, why are wireless networks not more popular? –Is there no demand? No

3. Then, why are wireless networks not more popular? Poor performance Too large a difference from wired technology

4. Heterogeneity Makes it difficult to identify performance bottlenecks

5. Three Fundamental Challenges Wireless bit errors –TCP assumes losses are due to congestion Asymmetric effects and latency variation –TCP relies on consistent rtt's for good performance Low channel bandwidths –Long range channels are often orders of magnitude slower than the wired alternative

6. Split-Connection Protocols Put a layer under tcp that is error free –Now losses are due to congestion –Asymmetric rtt's lead to poor performance

7. Wireless Testbed (ch 3)

8. Simulation Environment Initially used REAL –Realistic TCP modules –Inflexible –Written in C with parts in assembler –Hard to extend –Simulation written in propriety script language Now use NS-2

9. NS-2 Added LAN object –Formerly only point-to-point link Error Models Tested on real wireless network to determine error behaviour

10. BARWAN WaveLan –2Mb/s DS Throughput between 50k and 1.5M Usually closer to the low end Ricochet –Half-duplex FH Cable –10Mb/s shared up, dialup down

11. Measurement Techniques Wrote netperf –Measures TPC workloads Tcpdump –Detailed packet traces

12. Performance Metrics Throughput –Received bytes /unit time Goodput –Ratio of useful bytes to number transmitted –Always < 1, closer to 1 - more efficient Utilization –How often contended resource is idle Fairness –How evenly shared, Jan's fairness index

13. Jan's Fairness Index n connections x i = throughput for node I f = (  x i ) 2 /(n  x i 2 )

14. Berkeley Snoop Protocol (Ch 4) Significantly improves TCP performance in error-prone cellular networks Uses cross-layer protocol optimisations

15. Topology End node(s) connected to Base station via wireless link Rest of hops over wired network Using TCP Reno a bit error rate of 5% makes a transfer take 4.5 times longer than ideal TCP(2MB transfer)

16. Extra layer Transfer to –Agent at base station Uses info in ACKs Soft state Transport aware link protocol Transfer from –Explicit loss notification Retransmits lost packets No congestion control Link aware transport protocol

17. Design Goals Local solution –Transparent to fixed internet host Eliminate adverse interaction between layers Enable incremental deployment Preserve end-to-end semantics Use soft state

18. Transfer From a Fixed Host Caches data to be forwarded to MH ACKs are forwarded to fixed host if not due to loss –Duplicate ACKs can mean loss Packet is resent with high priority DupACKs after first not forwarded

19. Transfer From Mobile Host Negative ACKs –Built on SACKs Dependant on SACK implementation –Not used ELN –BS keeps list of “holes” Hole is set only when BS is not receiving close to max # of packets –If DupACK corresponds to hole ELN bit is set

20. Mobility Handoffs can lead to packet loss Multi-cast based buffering –Intermediate “home” agent does snoop and sends to each base-station

21. Performance

22. Asymmetry ACK speed on slow link limits throughput on fast link –Compress ACKs –Reduce ACK frequency

23. Small Windows Fast retransmissions are infrequent Most due to timeouts –Results in idle channel Usually fix with SACKs and ELN ER (Enhanced Recovery) –Probe network after <3 Duplicate ACKs