Computer Networking Lecture 18 – TCP over Wireless

Lecture 18: Wireless TCP2 Readings [R.2] Hari Balakrishnan, Srinivasan Seshan, and Randy H. Katz, "Improving Reliable Transport and Handoff Performance in Cellular Wireless Networks." ACM Wireless Networks, Volume 1, Number 4. December Pages Improving Reliable Transport and Handoff Performance in Cellular Wireless Networks [R.3] Ajay Bakre and B. R. Badrinath, "I-TCP: Indirect TCP for Mobile Hosts," Proceedings of the 15th International Conference on Distributed Computing Systems (ICDCS '95), May 30 - June 2, 1995, Vancouver, British Columbia. Pages I-TCP: Indirect TCP for Mobile Hosts [R.6] Analysis of TCP Performance over Mobile Ad Hoc Networks, G. Holland and N. Vaidya, Wireless Networks 8, 2002Analysis of TCP Performance over Mobile Ad Hoc Networks

Lecture 18: Wireless TCP3 Optional Readings [R.1] Ramon Caceres and Liviu Iftode, "Improving the Performance of Reliable Transport Protocols in Mobile Computing Environments." IEEE JSAC, Volume 13, Number 5. June 1995.Improving the Performance of Reliable Transport Protocols in Mobile Computing Environments [R.4] H. Balakrishnan, Venkat Padmanabhan, Srinivasan Seshan, and Randy H. Katz, A Comparison of Mechanisms for Improving TCP Performance over Wireless Links, IEEE/ACM Transactions on Networking, December 1997.A Comparison of Mechanisms for Improving TCP Performance over Wireless Links [R.5] David Eckhardt and Peter Steenkiste, "An Internet-style Approach to Wireless Link Errors", Journal of Wireless Communications and Mobile Computing, Wiley, special issue on "Reliably Transport Protocols for Mobile Computing", Volume 2, Number 1, February [R.7] ATP: A Reliable Transport Protocol for Ad-hoc Networks, Karthikeyan Sundaresan, Vaidyanathan Anantharaman, Hung-Yun Hsieh, Raghupathy Sivakumar, MobiHoc'03.ATP: A Reliable Transport Protocol for Ad-hoc Networks [R.8] Hung-Yun Hsieh, Kyu-Han Kim, Yujie Zhu, and Raghupathy Sivakumar. A Receiver-Centric Transport Protocol for Mobile Hosts with Heterogeneous Wireless Interfaces. MobiCom 2003.A Receiver-Centric Transport Protocol for Mobile Hosts with Heterogeneous Wireless Interfaces.

Lecture 18: Wireless TCP4 TCP Problems Over Noisy Links First reported in [R.1] Wireless links are inherently error-prone Fades, interference, attenuation Errors often happen in bursts TCP cannot distinguish between corruption and congestion TCP unnecessarily reduces window, resulting in low throughput and high latency Burst losses often result in timeouts Sender retransmission is the only option Inefficient use of bandwidth

Lecture 18: Wireless TCP5 Challenge #1: Wireless Bit-Errors Router Computer 2Computer Loss  Congestion Burst losses lead to coarse-grained timeouts Result: Low throughput Loss  Congestion Wireless

Lecture 18: Wireless TCP Performance Degradation Time (s) Sequence number (bytes) TCP Reno (280 Kbps) Best possible TCP with no errors (1.30 Mbps) 2 MB wide-area TCP transfer over 2 Mbps Lucent WaveLAN

Lecture 18: Wireless TCP7 Constraints & Requirements Incremental deployment Solution should not require modifications to fixed hosts If possible, avoid modifying mobile hosts Probably more data to mobile than from mobile Attempt to solve this first

Lecture 18: Wireless TCP8 Proposed Solutions End-to-end protocols Selective ACKs, Explicit loss notification Split-connection protocols Separate connections for wired path and wireless hop Reliable link-layer protocols Error-correcting codes Local retransmission

Lecture 18: Wireless TCP9 Approach Styles (End-to-End) Improve TCP implementations Not incrementally deployable Improve loss recovery (SACK, NewReno) Help it identify congestion (ELN [R.4], ECN) ACKs include flag indicating wireless loss Trick TCP into doing right thing  E.g. send extra dupacks [R.1] Wired linkWireless link

Lecture 18: Wireless TCP End-to-End: Selective Acks Correspondent Host Mobile Host Base Station X 2

Lecture 18: Wireless TCP End-to-End: Selective Acks Correspondent Host Mobile Host Base Station ack 1ack 1,3 ack 1,3-4ack 1,3-5ack 1,3-6

Lecture 18: Wireless TCP12 Approach Styles (Split Connection) Split connections [R.3] Wireless connection need not be TCP Hard state at base station Complicates mobility Vulnerable to failures Violates end-to-end semantics Wired linkWireless link

Lecture 18: Wireless TCP Split Connection Correspondent Host Mobile Host Base Station 2 A B 3 X 1 ack 0 X sack Asack A,B C sack A,B,D D

Lecture 18: Wireless TCP Split-Connection Congestion Window Wired connection does not shrink congestion window But wireless connection times out often, causing sender to stall

Lecture 18: Wireless TCP15 Approach Styles (Link Layer) More aggressive local rexmit than TCP Bandwidth not wasted on wired links Adverse interactions with transport layer Timer interactions Interactions with fast retransmissions Large end-to-end round-trip time variation FEC does not work well with burst losses Wired linkWireless link ARQ/FEC

Lecture 18: Wireless TCP16 Hybrid Approach: Snoop Protocol Described in [R.2] Transport-aware link protocol Modify base station To cache un-acked TCP packets … And perform local retransmissions Key ideas No transport level code in base station When node moves to different base station, state eventually recreated there

Lecture 18: Wireless TCP Snoop Protocol: CH to MH Correspondent Host Mobile Host Base Station Snoop agent: active interposition agent Snoops on TCP segments and ACKs Detects losses by duplicate ACKs and timers Suppresses duplicate ACKs from FH sender Snoop Agent

Lecture 18: Wireless TCP Snoop Protocol: CH to MH Correspondent Host Mobile Host Base Station Transfer of file from CH to MH Current window = 6 packets Snoop Agent

Lecture 18: Wireless TCP Snoop Protocol: CH to MH Correspondent Host Mobile Host Base Station Transfer begins Snoop Agent

Lecture 18: Wireless TCP Snoop Protocol: CH to MH Correspondent Host Mobile Host Base Station Snoop agent caches segments that pass by Difference #1 from pure link-layer – does not add a new header uses existing TCP header to identify losses Snoop Agent

Lecture 18: Wireless TCP Snoop Protocol: CH to MH Correspondent Host Mobile Host Base Station Packet 1 is Lost Snoop Agent 23 1 Lost Packets 1

Lecture 18: Wireless TCP Snoop Protocol: CH to MH Correspondent Host Mobile Host Base Station Packet 1 is Lost Duplicate ACKs generated Snoop Agent 2 3 Lost Packets 1 4 ack 0

Lecture 18: Wireless TCP Snoop Protocol: CH to MH Correspondent Host Mobile Host Base Station Packet 1 is Lost Duplicate ACKs generated Packet 1 retransmitted from cache at higher priority Snoop Agent 2 3 Lost Packets 1 4 ack

Lecture 18: Wireless TCP Snoop Protocol: CH to MH Correspondent Host Mobile Host Base Station Duplicate ACKs suppressed Difference #2 from pure link-layer – tries to prevent sender from noticing loss Sender may still timeout though – fortunately timeouts are typically long (500ms+) Snoop Agent ack ack 0 X

Lecture 18: Wireless TCP Snoop Protocol: CH to MH Correspondent Host Mobile Host Base Station 56 Clean cache on new ACK Snoop Agent ack ack 4

Lecture 18: Wireless TCP Snoop Protocol: CH to MH Correspondent Host Mobile Host Base Station 6 Clean cache on new ACK Snoop Agent ack ack 5 ack 4

Lecture 18: Wireless TCP Snoop Protocol: CH to MH Correspondent Host Mobile Host Base Station Active soft state agent at base station Transport-aware reliable link protocol Preserves end-to-end semantics Snoop Agent ack ack 5

Lecture 18: Wireless TCP28 Other Issues What about mobility? What about mobile-to-fixed communication?

Lecture 18: Wireless TCP29 Handling Mobility Correspondent Host Base Station Mobile Host Base Station Router Send packets to multiple base stations

Lecture 18: Wireless TCP30 Handling Mobility Correspondent Host Base Station Mobile Host Base Station Router Resend missed packets from Snoop cache on handoff

Lecture 18: Wireless TCP Snoop Protocol: MH to CH Mobile Host Correspondent Host Base Station 0 2 Caching and retransmission will not work Losses occur before packet reaches BS Congestion losses should not be hidden Solution: Explicit Loss Notifications (ELN) In-band message to TCP sender

Lecture 18: Wireless TCP Snoop Protocol: MH to CH Mobile Host Base Station MH begins transfer to CH Correspondent Host

Lecture 18: Wireless TCP Snoop Protocol: MH to CH Mobile Host Base Station Packet 1 lost on wireless link Correspondent Host

Lecture 18: Wireless TCP Snoop Protocol: MH to CH Mobile Host Receiver Base Station Add 1 to list of holes after checking for congestion 4 3 Lost Packets 1 1 ack 0

Lecture 18: Wireless TCP Snoop Protocol: MH to CH Mobile Host Base Station Duplicate ACKs sent 4 3 Lost Packets 1 1 ack 0 Correspondent Host

Lecture 18: Wireless TCP Snoop Protocol: MH to CH Mobile Host Base Station ELN information added to duplicate ACKs 4 3 Lost Packets 1 1 ack 0 ack 0 ELN ack 0 Correspondent Host

Lecture 18: Wireless TCP Snoop Protocol: MH to CH Mobile Host Base Station ELN information on duplicate ACKs Retransmit on Packet 1 on dup ACK + ELN No congestion control now 4 3 Lost Packets ack 0 ELN ack 0 Correspondent Host

Lecture 18: Wireless TCP Snoop Protocol: MH to CH Mobile Host Receiver Base Station Clean holes on new ACK Link-aware transport decouples congestion control from loss recovery Technique generalizes nicely to wireless transit links 4 3 ack 6 1

Lecture 18: Wireless TCP39 Snoop Data Processing Yes Packet arrives New pkt? No 1. Forward pkt 2. Reset local rexmit counter In-sequence? Yes 1. Cache packet 2. Forward to mobile 1. Mark as cong. loss 2. Forward pkt Congestion loss Common case Sender retransmission No

Lecture 18: Wireless TCP40 Snoop ACK Processing No Dup ack? No New ack? Yes 1. Free buffers 2. Update RTT estimate Yes Discard > threshold No Discard Retransmit Yes lost packet 3. Propagate ack to sender Common case Spurious ack Next pkt lost Later dup acks for lost packet Ack arrives (from mobile host)

Lecture 18: Wireless TCP41 Discussion Why does Snoop perform well? Hides out-of-order delivery from sender Current reliable MACs do single packet at a time reliability  no out-of-order delivery [R.5]

Lecture 18: Wireless TCP42 [R.6] Analysis of TCP Performance over Mobile Ad Hoc Networks, G. Holland and N. Vaidya, Wireless Networks 8, 2002Analysis of TCP Performance over Mobile Ad Hoc Networks

Lecture 18: Wireless TCP43 TCP ELFN (Explicit Link Failure Notification ) Analysis of TCP performance in static, linear, multi hop wireless network Analysis of TCP in MANETs using expected throughput and measured throughput Suggestion of TCP ELFN Simulation results

Lecture 18: Wireless TCP44 TCP performance in simple, static, linear multi-hop network A simple multi-hop network TCP-Reno throughput over an fixed, linear, multi-hop network of varying length

Lecture 18: Wireless TCP45 Performance metric Expected throughput = Σ i=0 ∞ ∞ t i t i * T i i: # of hops t i: the duration for which the shortest path contains i hops Ti: the throughput obtained “ over a linear chain ” using i hops Expected throughput does not take into account the performance overhead of determining new routes after route failures It serves as a upper bound of throughput in mobile network

Lecture 18: Wireless TCP46 Performance metric : Expected throughput Example SR Δt=toΔt=t1 Δt=t2 Throughput = TH1Throughput = TH3Throughput = TH1 Expected throughput = to + t1 + t2 t 0*TH1 + t1*TH2 + t2*TH1 SRSR Throughput in linear network when # hops is n

Lecture 18: Wireless TCP47 Expected throughput and Measured Throughput Simulation environment ns network simulator TCP-Reno over DSR, BSD’s ARP 30 nodes, 1500X300 m 2, the random waypoint The average throughput of 50 scenarios From 2m/s to 10m/s the throughput drops sharply

Lecture 18: Wireless TCP48 Measured and expected throughput

Lecture 18: Wireless TCP49 Zero Throughput T = 0s, route fail, packet dropped SABC R T = 6s, data packet retransmitted SABC R T = 6.1xxs, ACK dropped, due to stale cached route SABC R T = 18.1xxs, the second retransmission of data packet, dropped again due to stale cached route SABC R T=42,90,120s no ACK from the TCP receiver

Lecture 18: Wireless TCP50 Some facts In previous example, only for 6 s of 120 s the network is partitioned DSR’s stale cached route can degrade TCP throughput significantly DSR does not retransmit dropped packet when it receives Route Error Msg, and the TCP sender or receiver does not know about the packet loss The TCP sender waits for occurring time out Unnecessary RTO back-off of the TCP sender makes problems even worse

Lecture 18: Wireless TCP51 TCP ELFN Explicit Link Failure Notification (ELFN) The objective : To provide the TCP sender with information about link and route failures TCP sender can avoid responding to the failures as if congestion occurred DSR’s route failure message is modified A payload similar to the “host unreachable” ICMP message The sender and receiver’s addresses and ports and seq number SABCD R TCP data DSR ROUTE ERROR + ELFN Probing message

Lecture 18: Wireless TCP52 TCP ELFN Sender reaction When a TCP sender receives an ELFN, It disables its retransmission timers and enters a “stanby” mode While on standby, A packet is sent at periodic intervals to probe the network to see if a route has been established If an acknowledgment is received, Then it leaves standby mode

Lecture 18: Wireless TCP53 Simulation for the 50 different Mobility patterns (2m/s, 10m/s, 20m/s, 30m/s)

Lecture 18: Wireless TCP54 Simulation for the different probing intervals and different window and RTO modification Different probing interval If the interval is too large, it delays the discovery of new routes If the interval is too small, the rapid injection of probes into the network will cause congestion and lower throughput

Lecture 18: Wireless TCP55 [R.7] ATP: A Reliable Transport Protocol for Ad-hoc Networks, Karthikeyan Sundaresan, Vaidyanathan Anantharaman, Hung-Yun Hsieh, Raghupathy Sivakumar, MobiHoc'03.ATP: A Reliable Transport Protocol for Ad-hoc Networks

Lecture 18: Wireless TCP56 Time spent in Slow-Start phase Average time in Slow-Start phase. Total simulation time: 100s TCP New Reno 1.The time spent in Slow-Start increases with the increasing of the mobility. 2.The proportion of time goes above 50% for the higher load situation. 3.The connections spend a large portion of the lifetime probing for the available bandwidth. 50%

Lecture 18: Wireless TCP57 Key design elements of ATP Cross layer coordination Rate based transmissions This is the core of ATP Decoupled congestion control and reliability

Lecture 18: Wireless TCP58 Layer Coordination Similar to TCP-ELFN Utilize explicit feedback from intermediate nodes. ATP uses layer coordination for Path failure notification Initiating a sending-rate estimation for the new route

Lecture 18: Wireless TCP59 Rate based transmissions What is rate based transmission Transmit fixed size of data in each time interval. GSM example, 260bits from speech codec in every 20ms Use timer to clock the new data, not the sending window Avoids drawbacks due to burstiness The need for self-clocking by the arrival of ACKs is eliminated Allows decoupling of congestion control mechanism from the reliability mechanism Timer granularity in low bandwidth MANETS large enough to be realized without significant overheads

Lecture 18: Wireless TCP60 Decoupling of Congestion Control & Reliability For congestion control: Intermediate nodes provide the feedback of available rate. The feedback is piggybacked on forward path and sent back from receiver to sender. The sender adjusts the sending rate accordingly. For reliability: The receiver uses SACK to report any new holes in the data stream.

Lecture 18: Wireless TCP61 [R.8] Hung-Yun Hsieh, Kyu-Han Kim, Yujie Zhu, and Raghupathy Sivakumar. A Receiver-Centric Transport Protocol for Mobile Hosts with Heterogeneous Wireless Interfaces. MobiCom 2003.A Receiver-Centric Transport Protocol for Mobile Hosts with Heterogeneous Wireless Interfaces.

Lecture 18: Wireless TCP62 Core Thesis Behind Proposal The wireless last link is crucial Receiver has accurate knowledge of channel conditions Receiver has knowledge of all its interfaces Receiver can handle functionality without making changes at the sender

Lecture 18: Wireless TCP63 Loss recovery React to non-congestion related losses Sender-centric approach Sender needs feedback from receiver Difficult to provide all types of feedback Receiver-centric approach Avoids feedback overheads and latency

Lecture 18: Wireless TCP64 Congestion Control Discover the point of threshold of packet loss Sender-centric Server might need several congestion control schemes for the different types of connections Receiver-centric Receiver responsible for congestions control Each receiver can implement its own congestion control

Lecture 18: Wireless TCP65 RCP Protocol Overview Data Transfer: REQ-DATA instead of DATA-ACK REQ in 2 modes Cumulative (new data) Pull (retransmission) REQ DATA Sender Receiver 3 out-of-order DATA segments-> Fast Retransmit In CUM or PULL mode

Lecture 18: Wireless TCP66 RCP Protocol Overview Congestion Window maintained at Receiver Receiver can react to packet loss based on its knowledge of channel conditions Window moves forward on DATA receipt