CMPE 257 - Wireless and Mobile Networking 1 CMPE 257 Spring 2006 End-to-End Protocols 2 Wireless and Mobile Networks.

Slides:



Advertisements
Similar presentations
Comparison between DSR and AODV DSR Overview AODV Overview Similarity Difference Consequence.
Advertisements

A feedback–based scheme for improving TCP performance in Ad Hoc Wireless Networks Group : Manish Mehta Aditya Barve.
1 Improving TCP Performance over Mobile Networks HALA ELAARAG Stetson University Speaker : Aron ACM Computing Surveys 2002.
Improving TCP over Wireless by Selectively Protecting Packet Transmissions Carla F. Chiasserini Michele Garetto Michela Meo Dipartimento di Elettronica.
A study of Cross layer work of University of Trento folk A ResiliNet Group Presentation Sarvesh Kumar Varatharajan.
CMPE 257 Spring CMPE 257: Wireless and Mobile Networking Spring 2005 E2E Protocols (point-to-point)
Improving TCP Performance over Mobile Ad Hoc Networks by Exploiting Cross- Layer Information Awareness Xin Yu Department Of Computer Science New York University,
Improving TCP Performance over MANETs by Exploiting Cross-Layer Information Awareness Xin Yu NYU Presented by: David Choffnes.
Special Topics on Wireless Ad-hoc Networks
6/3/ Improving TCP Performance over Mobile Ad Hoc Networks by Exploiting Cross-Layer Information Awareness CS495 – Spring 2005 Northwestern University.
CMPE 257: Wireless and Mobile Networking
CMPE 257 Spring CMPE 257: Wireless and Mobile Networking Spring 2002 Week 7.
Internet Networking Spring 2003 Tutorial 12 Limited Transmit RFC 3042 Long Thin Networks RFC 2757.
Ruy de Oliveira December 05, 2001
CMPE 257 Spring CMPE 257: Wireless and Mobile Networking Spring 2002 Week 6.
TCP over ad hoc networks Ad Hoc Networks will have to be interfaced with the Internet. As such backward compatibility is a big issue. One might expect.
CS 268: Wireless Transport Protocols Kevin Lai Feb 13, 2002.
Improving TCP Performance over Ad-hoc Network 11/28/2000 Xuanming Dong, Duke Lee, and Jin Wang Course Project for EE228A --- Fall 2000 (Professor Jean.
1 TCP over Wireless (II) Based on a presentation by Nitin Vaidya.
CS 552 Wireless TCP slides by B. Nath. Wireless TCP Packet loss in wireless networks may be due to –Bit errors –Handoffs –Congestion (rarely) –Reordering.
CMPE 257 Spring CMPE 257: Wireless and Mobile Networking Spring 2005 E2E Protocols (point-to-point) E2E Protocols (multipoint)
Transport Protocols for Wireless Networks CMPE Spring 2001 Marcelo M. de Carvalho.
Reliable Transport Layers in Wireless Networks Mark Perillo Electrical and Computer Engineering.
TCP performance in Wireless Networks Ehsan Hamadani July 2004.
CMPE 257 Spring CMPE 257: Wireless and Mobile Networking Spring 2005 E2E Protocols (point-to-point)
1 A Comparison of Mechanisms for Improving TCP Performance over Wireless Links Course : CS898T Instructor : Dr.Chang - Swapna Sunkara.
Wireless TCP February 22, 2002 © 2002 Yongguang Zhang CS 395T - Mobile Computing and Wireless Networks Department of Computer SciencesTHE UNIVERSITY OF.
1 TCP over Wireless (I) some slides adapted, notably from tutorial by Nitin Vaidya.
CIS 725 Wireless networks. Low bandwidth High error rates.
Transport Layer Issue in Wireless Ad Hoc and Sensor Network
Spring 2000Nitin BahadurAdvanced Computer Networks A Comparison of Mechanisms for Improving TCP Performance over Wireless Links By: Hari B., Venkata P.
Qian Zhang Department of Computer Science HKUST Advanced Topics in Next- Generation Wireless Networks Transport Protocols in Ad hoc Networks.
Mobile Communications: Mobile Transport Layer Mobile Communications Chapter 10: Mobile Transport Layer  Motivation  TCP-mechanisms  Indirect TCP  Snooping.
Asstt. Professor Adeel Akram.  Motivation  TCP mechanisms  Indirect TCP  Snooping TCP  Mobile TCP  Fast retransmit/recovery  Transmission freezing.
Improving TCP Performance over Mobile Networks Zahra Imanimehr Rahele Salari.
TCP PERFORMANCE OVER AD HOC NETWORKS Presented by Vishwanee Raghoonundun Assisted by Maheshwarnath Behary MSc Computer Networks Middlesex University.
TRANSPORT PROTOCOLS FOR WLANs and AD HOC NETWORKS Ian F. Akyildiz Broadband & Wireless Networking Laboratory School of Electrical and Computer Engineering.
1 Transport Layer for Mobile Ad Hoc Networks (MANETs) Cyrus Minwalla Maan Musleh COSC 6590.
Wireless TCP Prasun Dewan Department of Computer Science University of North Carolina
1 Impact of transmission errors on TCP performance (Nitin Vaidya)
Obile etworking M-TCP : TCP for Mobile Cellular Networks Kevin Brown and Suresh Singh Department of Computer Science Univ. of South Carolina.
Transport over Wireless Networks Myungchul Kim
ECE 695 Sp 2006 Jim Catt TCP Functions TCP is a connection oriented protocol Primary functions  TCP sets up and maintains end-to-end connection between.
Wireless TCP. References r Hari Balakrishnan, Venkat Padmanabhan, Srinivasan Seshan and Randy H. Katz, " A Comparison of Mechanisms for Improving TCP.
Transport layer protocols The objectives of a transport layer protocol include the setting up of an end-to-end connection, end-to- end delivery of data.
Improving TCP Performance over Wireless Networks
Challenges to Reliable Data Transport Over Heterogeneous Wireless Networks.
TCP on Wireless Ad Hoc Networks CS 218 Oct 22, 2003 TCP overview Ad hoc TCP : mobility, route failures and timeout TCP and MAC interaction study TCP fairness.
1 CS 4396 Computer Networks Lab TCP – Part II. 2 Flow Control Congestion Control Retransmission Timeout TCP:
Outline Wireless introduction Wireless cellular (GSM, CDMA, UMTS) Wireless LANs, MAC layer Wireless Ad hoc networks – routing: proactive routing, on-demand.
Transport Protocols for Wireless Ad Hoc Networks 1.
TCP OVER ADHOC NETWORK. TCP Basics TCP (Transmission Control Protocol) was designed to provide reliable end-to-end delivery of data over unreliable networks.
MOBILE TCP.
Ασύρματες και Κινητές Επικοινωνίες Ενότητα # 11: Mobile Transport Layer Διδάσκων: Βασίλειος Σύρης Τμήμα: Πληροφορικής.
ECE 4110 – Internetwork Programming
Prof. Younghee Lee 1 Computer networks u Lecture 10: TCP: wireless network Prof. Younghee Lee.
TCP continued. Discussion – TCP Throughput TCP will most likely generate the saw tooth type of traffic. – A rough estimate is that the congestion window.
2005/12/14 1 Improving TCP Performance over Mobile Ad Hoc Networks by Exploiting Cross-Layer Information Awareness Xin Yu Department of Computer Science.
TCP/IP1 Address Resolution Protocol Internet uses IP address to recognize a computer. But IP address needs to be translated to physical address (NIC).
1 Ad-hoc Transport Layer Protocol (ATCP) EECS 4215.
Mobile Transport Layer  Motivation  TCP-mechanisms  Indirect TCP  Snooping TCP  Mobile TCP  Fast retransmit/recovery  Transmission freezing  Selective.
Tailoring TCP for Wireless Networks. Credits Nitin Vaidya –Tutorial on TCP for Wireless and Mobile Hosts, MobiCom ’99 Balakrishnan, et al. –A Comparison.
TCP over Wireless PROF. MICHAEL TSAI 2016/6/3. TCP Congestion Control (TCP Tahoe) Only ACK correctly received packets Congestion Window Size: Maximum.
UNIT-V Transport Layer protocols for Ad Hoc Wireless Networks
Wireless Transport.
Ad-hoc Transport Layer Protocol (ATCP)
TCP - Part II Relates to Lab 5. This is an extended module that covers TCP flow control, congestion control, and error control in TCP.
TCP in Wireless Ad-hoc Networks
TCP for Wireless Networks
Impact of transmission errors on TCP performance
Presentation transcript:

CMPE Wireless and Mobile Networking 1 CMPE 257 Spring 2006 End-to-End Protocols 2 Wireless and Mobile Networks

CMPE Wireless and Mobile Networking 2 Announcements Exam: –June 7 th in class. Project presentations and demos: –June 12 th. 4-7pm. Homework 4 (routing) is up.

CMPE Wireless and Mobile Networking 3 Today E2E protocols continued.

CMPE Wireless and Mobile Networking 4 E2E Protocols Reliable point-to-point. Reliable multipoint.

CMPE Wireless and Mobile Networking 5 Reliable Point-to-Point Transport: Outline TCP/IP basics. Impact of transmission errors on TCP performance. Approaches to improve TCP performance on wireless networks. –Classification. TCP on single-hop infrastructure-based wireless networks. TCP on MANETs.

CMPE Wireless and Mobile Networking 6 Classification E2E versus cross-layer approaches. –E2E approaches: connection end points try to distinguish between congestion and non- congestion losses. –Cross-layer approaches: combination of e2e and intermediate node participation.

CMPE Wireless and Mobile Networking 7 Cross-Layer Approaches Link layer error recovery. Link layer retransmission. TCP-awareness: Snoop [Balakrishnan95] –TCP-unawareness. Split connection.

CMPE Wireless and Mobile Networking 8 TCP-Aware Link Layer Retransmission

CMPE Wireless and Mobile Networking 9 Snoop Protocol [Balakrishnan95] More sophisticated link-level retransmission scheme. End-to-end semantics retained. Soft state at base station.

CMPE Wireless and Mobile Networking 10 Snoop Protocol FHMHBS wireless physical link network transport application physical link network transport application physical link network transport application rxmt Per TCP-connection state TCP connection

CMPE Wireless and Mobile Networking 11 Snoop Protocol Buffers data packets at base station. –Data sent by FH not yet ack’d by MH. –Allow link layer retransmission. When dupacks received by BS from MH (or local timeout), retransmit on wireless link, if packet in buffer. Prevents fast retransmit by TCP sender at FH by suppressing dupacks at BS.

CMPE Wireless and Mobile Networking 12 Snoop : Example FHMHBS Example assumes delayed ack - every other packet ack’d TCP state maintained at link layer

CMPE Wireless and Mobile Networking 13 Snoop : Example

CMPE Wireless and Mobile Networking 14 Snoop : Example Duplicate acks are not delayed 36 dupack

CMPE Wireless and Mobile Networking 15 Snoop : Example Duplicate acks

CMPE Wireless and Mobile Networking 16 Snoop : Example FHMHBS Discard dupack Dupack triggers retransmission of packet 37 from base station BS needs to be TCP-aware to be able to interpret TCP headers

CMPE Wireless and Mobile Networking 17 Snoop : Example

CMPE Wireless and Mobile Networking 18 Snoop : Example TCP sender does not fast retransmit

CMPE Wireless and Mobile Networking 19 Snoop : Example TCP sender does not fast retransmit 45

CMPE Wireless and Mobile Networking 20 Snoop : Example FHMHBS

CMPE Wireless and Mobile Networking 21 Performance 2 Mbps Wireless link

CMPE Wireless and Mobile Networking 22 Snoop Protocol: Advantages Snoop prevents fast retransmit from sender despite transmission errors and out-of-order delivery on the wireless link. If wireless link delay-bandwidth product less than 4 packets: simple (TCP-unaware) link level retransmission scheme can suffice. –Since delay-bandwidth product is small, retransmission scheme can deliver lost packet without causing MH to send 3 dupacks.

CMPE Wireless and Mobile Networking 23 Snoop Protocol: Advantages Higher throughput can be achieved. Local recovery from wireless losses. Fast retransmit not triggered at sender despite out-of-order link layer delivery. End-to-end semantics retained. Soft state at base station. –Loss of the soft state affects performance, but not correctness.

CMPE Wireless and Mobile Networking 24 Snoop Protocol:Disadvantages Link layer at base station needs to be TCP- aware. Not useful if TCP headers are encrypted (IPsec). Cannot be used if TCP data and TCP ACKs traverse different paths.

CMPE Wireless and Mobile Networking 25 Delayed Dupacks Approach TCP-unaware approximation of TCP-aware link layer. Attempts to imitate Snoop without making BS TCP- aware. Snoop implements two features at BS: –Link layer retransmission. –Dupack handling: reduced interference between TCP and link layer retransmissions (drop dupacks).

CMPE Wireless and Mobile Networking 26 Delayed Dupacks Implements same two features: –at BS : link layer retransmission. –at MH : reducing interference between TCP and link layer retransmissions (by delaying dupacks).

CMPE Wireless and Mobile Networking 27 Delayed Dupacks Protocols TCP receiver delays dupacks (third and subsequent) for interval D, when out-of-order packets received. Dupack delay intended to give link level retransmit time to succeed. Benefit: Delayed dupacks can result in recovery from a transmission loss without triggering a response from the TCP sender. Disadvantage: Recovery from congestion losses delayed.

CMPE Wireless and Mobile Networking 28 Delayed Dupacks Protocols Delayed dupacks released after interval D, if missing packet not received. Link layer maintains state to allow retransmission.

CMPE Wireless and Mobile Networking 29 Delayed Dupacks: Example Example assumes delayed ack - every other packet ack’d Link layer acks are not shown Link layer state

CMPE Wireless and Mobile Networking 30 Delayed Dupacks: Example BS Removed from BS link layer buffer on receipt of a link layer ack (LL acks not shown in figure)

CMPE Wireless and Mobile Networking 31 Delayed Dupacks: Example Duplicate acks are not delayed 36 dupack

CMPE Wireless and Mobile Networking 32 Delayed Dupacks: Example Duplicate acks Original ack

CMPE Wireless and Mobile Networking 33 Delayed Dupacks: Example Base station forwards dupacks dupackdupacks Delayed dupack

CMPE Wireless and Mobile Networking 34 Delayed Dupacks: Example dupacks Delayed dupacks 43

CMPE Wireless and Mobile Networking 35 Delayed Dupacks : Example TCP sender does not fast retransmit 44 Delayed dupacks are discarded if lost packet received before delay D expires

CMPE Wireless and Mobile Networking 36 Delayed Dupacks [Vaidya99] 2 Mbps wireless duplex link with 20 ms delay No congestion losses 20 ms 10 Mbps2 Mbps

CMPE Wireless and Mobile Networking 37 Delayed Dupacks [Vaidya99] 5% packet loss due to congestion 20 ms 10 Mbps2 Mbps

CMPE Wireless and Mobile Networking 38 Delayed Dupacks: Advantages Link layer need not be TCP-aware. Can be used even if TCP headers are encrypted. Works well for relatively small wireless RTT (compared to end-to-end RTT). –Relatively small D sufficient in such cases.

CMPE Wireless and Mobile Networking 39 Delayed Dupacks: Disadvantages Right value of dupack delay D dependent on wireless link properties. Mechanisms to determine D needed. Delays dupacks for congestion losses too, delaying congestion loss recovery.

CMPE Wireless and Mobile Networking 40 Cross-Layer Approaches Link layer error recovery. Link layer retransmission. –TCP-awareness. –TCP-unawareness. Split connection.

CMPE Wireless and Mobile Networking 41 Split Connection Approach

CMPE Wireless and Mobile Networking 42 Split Connection Approach End-to-end TCP connection is broken into one connection on the wired part of route and one over wireless part.

CMPE Wireless and Mobile Networking 43 Split Connection Approach Connection between wireless host MH and fixed host FH goes through base station BS. FH-MH = FH-BS + BS-MH FHMHBS Base StationMobile Host Fixed Host

CMPE Wireless and Mobile Networking 44 Split Connection Approach Split connection results in independent control for the two parts. –Congestion/error control protocols, packet size, time-outs, may be different for each part. FHMHBS Base StationMobile Host Fixed Host

CMPE Wireless and Mobile Networking 45 Split Connection Approach wireless physical link network transport application physical link network transport application physical link network transport application rxmt Per-TCP connection state TCP connection

CMPE Wireless and Mobile Networking 46 Split Connection Approach : Classification Hides transmission errors from sender Primary responsibility at base station If specialized transport protocol used on wireless, then wireless host also needs modification

CMPE Wireless and Mobile Networking 47 Split Connection Approach: Example Indirect TCP [Bakre94] –FH - BS connection : Standard TCP. –BS - MH connection : Standard TCP.

CMPE Wireless and Mobile Networking 48 Split Connection: Advantages BS-MH connection can be optimized independent of FH-BS connection. –Different congestion/error control. Local recovery of errors. –Faster recovery due to relatively shorter RTT on wireless link. Good performance achievable using appropriate BS-MH protocol. –Standard TCP on BS-MH performs poorly when multiple packet losses per window. –Selective ACKs improve performance.

CMPE Wireless and Mobile Networking 49 Split Connection: Disadvantages End-to-end semantics violated. –ACK may be delivered to sender before data delivered to receiver. FHMHBS

CMPE Wireless and Mobile Networking 50 Split Connection: Disadvantages BS retains hard state. –BS failure can result in loss of data. If BS fails, packets 39 and 40 will be lost. Both ack’d to sender;sender does not buffer. FHMHBS

CMPE Wireless and Mobile Networking 51 Split Connection: Disadvantages BS retains hard state. Hand-off latency increases due to state transfer –Data that has been ack’d to sender must be moved to new base station.

CMPE Wireless and Mobile Networking 52 Handoff FHMHBS MH New base station Hand-off 40 39

CMPE Wireless and Mobile Networking 53 Split Connection: Disadvantages Buffer space needed at BS for each TCP connection. –BS buffers tend to get full, when wireless link slower (one window worth of data on wired connection could be stored at the base station for each split connection). Extra copying of data at BS –Copying from FH-BS socket buffer to BS-MH socket buffer. –Increases end-to-end latency.

CMPE Wireless and Mobile Networking 54 Split Connection: Disadvantages May not be useful if data and acks traverse different paths. –Example: data on a satellite wireless hop, acks on a dial-up channel. FHMH data ack BS

CMPE Wireless and Mobile Networking 55 E2E Approaches Strict E2E versus E2E with intermediate node involvement. E2E with intermediate node involvement: –Explicit notifications.

CMPE Wireless and Mobile Networking 56 Explicit Notification Schemes General Philosophy Approximate ideal TCP behavior. –Ideally, TCP sender should simply retransmit a packet lost due to transmission errors without taking any congestion control actions. A node determines whether packets are lost due to errors and informs sender using an “explicit notification”. Sender, on receiving the notification, does not reduce congestion window, but retransmits lost packet.

CMPE Wireless and Mobile Networking 57 Explicit Notification Schemes Motivated by Explicit Congestion Notification (ECN) proposals [Floyd94]. Variations proposed in literature differ in: Who sends explicit notification. How they decide to send explicit notification. What sender does on receiving notification.

CMPE Wireless and Mobile Networking 58 Explicit Loss Notification [Balakrishnan98] MH is the TCP sender. Wireless link first on path from sender to receiver. Base station keeps track of holes in packet sequence. When a dupack is received from the receiver, BS compares the dupack sequence number with recorded holes. –If there is a match, an ELN bit is set in dupack.

CMPE Wireless and Mobile Networking 59 ELN When sender receives dupack with ELN set, it retransmits packet, but does not reduce congestion window. MHFHBS wireless Record hole at TCP sender TCP receiver Dupack with ELN bit set

CMPE Wireless and Mobile Networking 60 Explicit Loss Notification [Biaz99thesis] Adapts ELN proposed in [Balakrishnan98] for the case when MH is receiver. Caches TCP sequence numbers at base station, similar to Snoop. But does not cache data packets, unlike Snoop. Duplicate acks are tagged with ELN bit before being forwarded to sender if sequence number for the lost packet is cached at BS. Sender takes appropriate action on receiving ELN.

CMPE Wireless and Mobile Networking 61 ELN [Biaz99thesis] Sequence numbers cached at base station 37 Dupack with ELN TCP sender TCP receiver

CMPE Wireless and Mobile Networking 62 Explicit Bad State Notification [Bakshi97] MH is TCP receiver. BS attempts to deliver packets to MH using link layer retransmission scheme. If packet cannot be delivered using small number of retransmissions, BS sends a Explicit Bad State Notification (EBSN) message to TCP sender. When TCP sender receives EBSN, it resets RTO. –Timeout delayed when wireless channel in bad state.

CMPE Wireless and Mobile Networking 63 Partial Ack Protocols [Cobb95][Biaz97] Send two types of acknowledgements. Partial ACK informs sender that a packet was received by an intermediate host (typically, base station). Normal TCP cumulative ACK needed by sender for reliability purposes.

CMPE Wireless and Mobile Networking 64 Partial Ack Protocols When packet for which partial ack is received detected to be lost, sender does not reduce its congestion window –Loss assumed to be due to wireless errors Partial ack 37 Cumulative ack

CMPE Wireless and Mobile Networking 65 Variations Base station may or may not locally buffer and retransmit lost packets.

CMPE Wireless and Mobile Networking 66 Announcements Today: –Finish E2E protocols (including multicast). –Course evaluations. Exam on Wed –Topics: everything up to E2E protocols. –Includes: Models and Architectures. MAC. Routing (unicast and multicast). Wireless Internetworking. Bluetooth. DTR. E2E Protocols Project: –Project reports. –Project presentations.

CMPE Wireless and Mobile Networking 67 Recap’ing: Transport Protocols Reliable point-to-point transport. –TCP on single-hop infrastructure-based wireless networks. Cross-layer schemes. Strict E2E schemes. –TCP on MANETs. Reliable multipoint transport.

CMPE Wireless and Mobile Networking 68 Strict E2E Schemes

CMPE Wireless and Mobile Networking 69 Receiver-Based Scheme [Biaz98Asset] MH is TCP receiver. Receiver uses heuristics to “guess” cause of packet loss. When receiver believes that packet loss is due to errors, it sends notification to sender. TCP sender, on receiving notification, retransmits lost packet, without reducing congestion window.

CMPE Wireless and Mobile Networking 70 Heuristics Receiver uses inter-arrival time between consecutively received packets to guess cause of packet loss. On determining a packet loss as being due to errors, the receiver may: –Tag corresponding dupacks with an ELN bit, or –Send an explicit notification to sender.

CMPE Wireless and Mobile Networking 71 Receiver-Based Scheme Packet loss due to congestion: FHMHBS FHMHBS T Congestion loss

CMPE Wireless and Mobile Networking 72 Receiver-Based Scheme Packet loss due to transmission error: FHMHBS FHMHBS Error loss 2 T

CMPE Wireless and Mobile Networking 73 Sender-Based Discrimination Scheme

CMPE Wireless and Mobile Networking 74 Sender-Based Discrimination [Biaz98ic3n,Biaz99techrep] Sender can attempt to determine cause of a packet loss. If packet loss determined to be due to errors, do not reduce congestion window. Sender can only use statistics based on round-trip times, window sizes, and loss pattern. –Unless network provides more information (example: explicit loss notification)

CMPE Wireless and Mobile Networking 75 Heuristics for Congestion Avoidance Define condition C as a function of congestion window size and observed RTTs. Condition C evaluated for new RTT. If (C == True), reduce congestion window.

CMPE Wireless and Mobile Networking 76 Heuristics for Congestion Avoidance: Some proposals TCP Vegas [Brakmo94] expected throughput ET = W(i) / RTTmin actual throughput AT = W(i) / RTT(i) Condition C = ( ET-AT > beta)

CMPE Wireless and Mobile Networking 77 Sender-Based Heuristics Record latest value evaluated for condition C. When a packet loss is detected: –If last evaluation of C is TRUE, assume packet loss due to congestion. –Else assume packet loss due to transmission errors. If packet loss determined to be due to errors, do not reduce congestion window

CMPE Wireless and Mobile Networking 78 Sender-Based Heuristics: Disadvantage Does not work quite well enough!! Reason Not much correlation between observed short-term statistics, and onset of congestion.

CMPE Wireless and Mobile Networking 79 Sender-Based Heuristics: Advantages Only sender needs to be modified. Needs further investigation to develop better heuristics. –Investigate longer-term heuristics.

CMPE Wireless and Mobile Networking 80 TCP in Multi-Hop Ad Hoc Networks (MANETs)

CMPE Wireless and Mobile Networking 81 Issues Route changes due to mobility. –Frequent route changes may cause OOO delivery. Wireless transmission errors. –Problem compounded due to multiple hops. MAC –MAC protocol can impact TCP performance.

CMPE Wireless and Mobile Networking 82 Throughput over Multi-Hop Wireless Paths [Gerla99] When contention-based MAC protocol is used, connections over multiple hops are at a disadvantage compared to shorter connections. –They have to contend for wireless access at each hop. –Delay or drop probability increases with number of hops.

CMPE Wireless and Mobile Networking 83 Improving TCP Performance in MANETs Classification: –Cross-layer. –Strictly end-to-end. First, we’ll look at cross-layer approaches…

CMPE Wireless and Mobile Networking 84 Analysis of TCP Performance over MANETs [Holland99] Impact of mobility. Simulation study. Performance metric: throughput. –Baseline: ideal (expected) throughput. Upper bound. Static network.

CMPE Wireless and Mobile Networking 85 Throughput versus Hops TCP throughput over 2 Mbps MAC, fixed, linear MANET.

CMPE Wireless and Mobile Networking 86 Expected Throughput Ti is measured throughput for i hops using static linear chain topology. ti time duration of TCP connection containing i hops.

CMPE Wireless and Mobile Networking 87 Throughput versus speed Speed (m/s) Average Throughput (Over 50 runs) Expected Actual Throughput decreases with speed…

CMPE Wireless and Mobile Networking 88 Throughput versus Speed Mobility pattern # Actual throughput 20 m/s 30 m/s But not always…

CMPE Wireless and Mobile Networking 89 Impact of Mobility TCP Throughput Ideal throughput (Kbps) Actual throughput 2 m/s10 m/s

CMPE Wireless and Mobile Networking 90 Impact of Mobility Ideal throughput Actual throughput 20 m/s 30 m/s

CMPE Wireless and Mobile Networking 91 mobility causes link breakage, resulting in route failure TCP data and acks en route discarded Why Throughput Degrades TCP sender starts sending packets again Route is repaired No throughput despite route repair

CMPE Wireless and Mobile Networking 92 mobility causes link breakage, resulting in route failure TCP data and acks en route discarded Why Throughput Degrades? TCP sender times out. Backs off timer. Route is repaired TCP sender resumes sending Larger route repair delays especially harmful No throughput despite route repair

CMPE Wireless and Mobile Networking 93 Why Throughput Improves? Low Speed Scenario C B D A C B D A C B D A 1.5 second route failure Route from A to D is broken for ~1.5 second. When TCP sender times out after 1 second, route still broken. TCP times out after another 2 seconds, and only then resumes.

CMPE Wireless and Mobile Networking 94 Why Throughput Improves? Higher Speed Scenario C B D A C B D A C B D A 0.75 second route failure Route from A to D is broken for ~ 0.75 second. Before TCP sender times (after 1 second), route is repaired.

CMPE Wireless and Mobile Networking 95 Why Throughput Improves? General Principle TCP timeout interval somewhat independent of speed. Network state at higher speed, when timeout occurs, may be more favorable than at lower speed. Network state: –Link/route status. –Route caches. –Congestion.

CMPE Wireless and Mobile Networking 96 How to Improve Throughput Network feedback. Inform TCP of route failure explicitly. Let TCP know when route is repaired. –Probing. –Explicit notification. Reduce repeated TCP timeouts and backoff.

CMPE Wireless and Mobile Networking 97 ELFN Explicit Link Failure Notification. Piggyback notification onto DSR’s route failure message to sender. TCP sender responds by disabling congestion control until route is fixed. –Disable retransmission timers. –When ACK is received, TCP restores state and resumes normal operation. TCP sender probes the network until it gets an ACK, which indicates it can resume normal operation.

CMPE Wireless and Mobile Networking 98 Performance Improvement Without network feedback Ideal throughput 2 m/s speed With feedback Actual throughput

CMPE Wireless and Mobile Networking 99 Performance Improvement Without network feedback With feedback Ideal throughput 30 m/s speed Actual throughput

CMPE Wireless and Mobile Networking 100 Performance with Explicit Notification

CMPE Wireless and Mobile Networking 101 Issues: Network Feedback Network knows best (why packets are lost). + Network feedback beneficial. - Need to modify transport & network layer to receive/send feedback Need mechanisms for information exchange between layers.

CMPE Wireless and Mobile Networking 102 Impact of Caching Route caching has been suggested as a mechanism to reduce route discovery overhead (e.g., DSR). Each node may cache one or more routes to given destination. When route from S to D detected as broken, node S may: –Use another cached route from local cache, or –Obtain a new route using cached route at another node.

CMPE Wireless and Mobile Networking 103 To Cache or Not to Cache Average speed (m/s) Actual throughput (as fraction of expected throughput)

CMPE Wireless and Mobile Networking 104 Why Performance Degrades With Caching When a route is broken, route discovery returns cached route from local cache or from nearby node. Cached routes may also be broken. timeout due to route failure timeout, cached route is broken timeout, second cached route also broken

CMPE Wireless and Mobile Networking 105 To Cache or Not to Cache Caching can result in faster route “repair”. But, faster does not necessarily mean correct. If incorrect repairs occur often enough, caching performs poorly. Need mechanisms for determining when cached routes are stale.

CMPE Wireless and Mobile Networking 106 Caching and TCP Performance Caching can reduce overhead of route discovery even if cache accuracy is not very high. But if cache accuracy is not high enough, gains in routing overhead may be offset by loss of TCP performance due to multiple timeouts.

CMPE Wireless and Mobile Networking 107 Window Size After Route Repair When route breaks: may be too optimistic or may be too conservative. Better be conservative than overly optimistic –Reset window to small value after route repair. –TCP needs to be aware of route repair (Route Failure and Route Re-establishment Notifications). –Impact low on paths with small delay-bw product.

CMPE Wireless and Mobile Networking 108 RTO After Route Repair If new route longer, RTO may be too small, leading to timeouts. New RTO = function of old RTO, old route length, and new route length. –Example: new RTO = old RTO * new route length / old route length –Not evaluated yet.

CMPE Wireless and Mobile Networking 109 TCP-Feedback [Chandran01] TCP-F. Similar to ELFN. Relies on notification from routing layer. –When route breakage is detected, a Route Failure Notification (RFN) sent to TCP sender. TCP sender goes to “Snooze” state when RFN received. –Freezes all timers and congestion control. –Stops sending data. TCP sender resumes normal operation when it gets a Route Re-establishment Notification (RRN). –If it does not get RRN within a certain time interval, leaves snooze state. –It invokes congestion control before transmitting data.

CMPE Wireless and Mobile Networking 110 Ad Hoc TCP [Liu01] ATCP also uses network-layer feedback. Implemented as a layer between TCP and network layer. –Listens to ECNs and ICMP (e.g., destination unreachable) messages. TCP ATCP Network Layer

CMPE Wireless and Mobile Networking 111 ATCP (Cont’d) Depending on network notification, TCP sender switches to different states. E.g., “destination unreachable” causes TCP sender to enter “persist” state, during which no packets are sent until route is mended. ECNs invoke TCP congestion control. 3 Dupacks are used as indication of transmission errors. –New ACK resumes TCP’s normal operation.

CMPE Wireless and Mobile Networking 112 Improving TCP Performance in MANETs Classification: –Cross-layer. –Strictly end-to-end.

CMPE Wireless and Mobile Networking 113 TCP Over Different Routing Protocols [Dyer2001] Impact of routing algorithm on TCP performance. –Metrics: connect time, throughput and overhead. On-demand routing. –AODV and DSR. –ADV: adaptive on-demand with proactive updates. Sender-based heuristic to improve TCP’s performance.

CMPE Wireless and Mobile Networking 114 Fixed-RTO TCP does not exponentially backoff the RTO. Uses sender-based heuristic to distinguish between congestion and “route failure” losses. –Route failure assumed if 2 consecutive timeouts. –Unack’d packet retransmitted. –No RTO backoff in the second (and +) timeout. –RTO remains fixed until retransmission is ack’d.

CMPE Wireless and Mobile Networking 115 Improving TCP under OOO Delivery [Wang02]

CMPE Wireless and Mobile Networking 116 Out-of-Order Packet Delivery Route changes may result in out-of-order (OOO) delivery. Significantly OOO delivery confuses TCP, triggering congestion control. Potential solutions: –Avoid OOO delivery by ordering packets before delivering to IP layer –Turn off fast retransmit. Can result in poor performance in presence of congestion

CMPE Wireless and Mobile Networking 117 TCP DOOR Detect and respond to out-of-order (OOO) packets. –Differentiate between OOO and congestion losses. OOO delivery caused by: –Retransmissions. –Route changes.

CMPE Wireless and Mobile Networking 118 Detecting OOO OOO delivery can happen in either direction. Sender detects OOO (duplicate) ACKs. Receiver detects OOO data packets.

CMPE Wireless and Mobile Networking 119 OOO ACKs Sequence number of packet being ACKed: monotonically increasing. –Why? ACKs are not re-transmitted. For DUPACKs, add 1-byte to count DUPACKs. ADSN: ACK duplication sequence number. TCP header option. Each DUPACK carries different ADSN.

CMPE Wireless and Mobile Networking 120 OOO Data Packets At receiver. Why comparing sequence numbers doesn’t work? –Retransmissions: higher sequence #’s can arrive earlier. –Out-of-sequence event. Use extra sequence number: incremented with every data packet, including retransmissions. –2-byte TCP packet sequence number (TPSN) as TCP option. –Or timestamp. Sender needs to be notified.

CMPE Wireless and Mobile Networking 121 OOO Response At sender. 2 types of response: –Temporarily disable congestion control for fixed time interval T1. –If in congestion avoidance mode in the last T2 time interval, go back to prior state.

CMPE Wireless and Mobile Networking 122 Evaluation Simulation environment: –ns-2 + CMU extensions. –Mobility: random way-point. –Workload: single TCP between fixed S and R with and without congestion.

CMPE Wireless and Mobile Networking 123 Results Significant goodput improvement (~50%) when 2 response mechanisms used. Sender versus receiver detection. –Seem to perform the same. –Correlation between OOO ACKs and data. Response mechanisms. –Both in place show better performance.