On the Robustness of Soft- State Protocols John Lui, CUHK Vishal Misra, Columbia U. Dan Rubenstein, Columbia U.

Slides:



Advertisements
Similar presentations
Nick Feamster CS 4251 Computer Networking II Spring 2008
Advertisements

COS 461 Fall 1997 Group Communication u communicate to a group of processes rather than point-to-point u uses –replicated service –efficient dissemination.
Chorus: Collision Resolution for Efficient Wireless Broadcast Xinyu Zhang, Kang G. Shin University of Michigan 1.
Cisco S3 C5 Routing Protocols. Network Design Characteristics Reliable – provides mechanisms for error detection and correction Connectivity – incorporate.
Jump to first page A. Patwardhan, CSE Digital Fountains Main Ideas : n Distribution of bulk data n Reliable multicast, broadcast n Ideal digital.
24-1 Chapter 24. Congestion Control and Quality of Service (part 1) 23.1 Data Traffic 23.2 Congestion 23.3 Congestion Control 23.4 Two Examples.
1 Transport Protocols & TCP CSE 3213 Fall April 2015.
Computer Networks Transport Layer. Topics F Introduction (6.1)  F Connection Issues ( ) F TCP (6.4)
Chi-Cheng Lin, Winona State University CS 313 Introduction to Computer Networking & Telecommunication Chapter 6 Transport Layer.
Receiver-driven Layered Multicast S. McCanne, V. Jacobsen and M. Vetterli University of Calif, Berkeley and Lawrence Berkeley National Laboratory SIGCOMM.
Improving TCP Performance over Mobile Ad Hoc Networks by Exploiting Cross- Layer Information Awareness Xin Yu Department Of Computer Science New York University,
CS 408 Computer Networks Congestion Control (from Chapter 05)
Receiver-driven Layered Multicast S. McCanne, V. Jacobsen and M. Vetterli SIGCOMM 1996.
Random Access MAC for Efficient Broadcast Support in Ad Hoc Networks Ken Tang, Mario Gerla Computer Science Department University of California, Los Angeles.
Analyzing Multi-channel MAC Protocols for Underwater Sensor Networks Presenter: Zhong Zhou.
Transport Layer 3-1 Transport Layer r To learn about transport layer protocols in the Internet: m TCP: connection-oriented protocol m Reliability protocol.
SYN Flooding: A Denial of Service Attack Shivani Hashia CS265.
RCS: A Rate Control Scheme for Real-Time Traffic in Networks with High B X Delay and High error rates J. Tang et al, Infocom 2001 Another streaming control.
E-ODMRP: Enhanced ODMRP with Motion Adaptive Refresh Soon Y. Oh, Joon-Sang Park, Mario Gerla Computer Science Dept. UCLA.
TAPAS: A Research Paradigm for the Modeling, Prediction and Analysis of Non-stationary Network Behavior Almudena Konrad PhD Candidate at UC Berkeley
Experiment: Step by Step Author: Anna Bekkerman
Toward Optimal Network Fault Correction via End-to-End Inference Patrick P. C. Lee, Vishal Misra, Dan Rubenstein Distributed Network Analysis (DNA) Lab.
TCP performance in Wireless Networks Ehsan Hamadani July 2004.
Ns Simulation Final presentation Stella Pantofel Igor Berman Michael Halperin
Error Checking continued. Network Layers in Action Each layer in the OSI Model will add header information that pertains to that specific protocol. On.
Multicast Transport Protocols: A Survey and Taxonomy Author: Katia Obraczka University of Southern California Presenter: Venkatesh Prabhakar.
CSE679: Multicast and Multimedia r Basics r Addressing r Routing r Hierarchical multicast r QoS multicast.
Receiver-driven Layered Multicast Paper by- Steven McCanne, Van Jacobson and Martin Vetterli – ACM SIGCOMM 1996 Presented By – Manoj Sivakumar.
Network Topologies.
Basic Concepts of Computer Networks
Mapping Internet Addresses to Physical Addresses (ARP)
Communication Networks
Firewall and Internet Access Mechanism that control (1)Internet access, (2)Handle the problem of screening a particular network or an organization from.
NETWORK TOPOLOGIES HNC COMPUTING - Network Concepts 1 Network Concepts Topologies.
Chapter 12 Transmission Control Protocol (TCP)
7/26/ Design and Implementation of a Simple Totally-Ordered Reliable Multicast Protocol in Java.
Computer Networks with Internet Technology William Stallings
جلسه هشتم شبکه های کامپیوتری به نــــــــــــام خدا.
Network Concepts Topologies
1 TCP - Part II Relates to Lab 5. This is an extended module that covers TCP data transport, and flow control, congestion control, and error control in.
IETF78 Multimob Masstricht1 Proposal for Tuning IGMPv3/MLDv2 Protocol Behavior in Wireless and Mobile networks draft-wu-multimob-igmp-mld-tuning-02 Qin.
Push Technology Humie Leung Annabelle Huo. Introduction Push technology is a set of technologies used to send information to a client without the client.
a/b/g Networks Routing Herbert Rubens Slides taken from UIUC Wireless Networking Group.
EE689 Lecture 13 Review of Last Lecture Reliable Multicast.
TCP OVER ADHOC NETWORK. TCP Basics TCP (Transmission Control Protocol) was designed to provide reliable end-to-end delivery of data over unreliable networks.
Ασύρματες και Κινητές Επικοινωνίες Ενότητα # 11: Mobile Transport Layer Διδάσκων: Βασίλειος Σύρης Τμήμα: Πληροφορικής.
Prepared by:Ronnel P. Agulto, CpE Objectives Different types of topologies; Their advantages & disadvantages How to choose an appropriate topologies in.
Reliable Client-Server Communication. Reliable Communication So far: Concentrated on process resilience (by means of process groups). What about reliable.
Transport Layer: Sliding Window Reliability
© 2005 Cisco Systems, Inc. All rights reserved. BGP v3.2—7-1 Optimizing BGP Scalability Improving BGP Convergence.
Failure detection The design of fault-tolerant systems will be easier if failures can be detected. Depends on the 1. System model, and 2. The type of failures.
Data Link Layer Flow and Error Control. Flow Control Flow Control Flow Control Specifies the amount of data can be transmitted by sender before receiving.
Networks, Part 2 March 7, Networks End to End Layer  Build upon unreliable Network Layer  As needed, compensate for latency, ordering, data.
CS/EE 145A Reliable Transmission over Unreliable Channel II Netlab.caltech.edu/course.
4343 X2 – The Transport Layer Tanenbaum Ch.6.
EE 122: Integrated Services Ion Stoica November 13, 2002.
1 Sheer volume and dynamic nature of video stresses network resources PIE: A lightweight latency control to address the buffer problem issue Rong Pan,
Reliable Adaptive Lightweight Multicast Protocol Ken Tang, Scalable Network Technologies Katia Obraczka, UC Santa Cruz Sung-Ju Lee, Hewlett-Packard Laboratories.
Chi-Cheng Lin, Winona State University CS412 Introduction to Computer Networking & Telecommunication Data Link Layer Part II – Sliding Window Protocols.
TCP/IP1 Address Resolution Protocol Internet uses IP address to recognize a computer. But IP address needs to be translated to physical address (NIC).
LAN Topologies Part 1. What is topology? Topology is the physical or logical interconnection of communicating devices Physical Topology: LANtopology,
Network Topology Computer network topology is the way various components of a network (like nodes, links, peripherals, etc) are arranged. Network topologies.
draft-ietf-simple-message-sessions-00 Ben Campbell
Design Principles: Hard vs Soft State
EE 122: Lecture 16/17 (Integrated Services)
Chapter 6: Transport Layer (Part I)
Congestion Control, Internet transport protocols: udp
Staged Refresh Timers for RSVP
Advanced Computer Networks
Presentation transcript:

On the Robustness of Soft- State Protocols John Lui, CUHK Vishal Misra, Columbia U. Dan Rubenstein, Columbia U.

State To operate correctly, network protocols require that communicating nodes share state, e.g., –Connection is “active” –The largest sequence # received was … Q: In networks with a lossy/unpredictable control channel, how is state information kept consistent across nodes?

Keeping State Consistent Two very different approaches / philosophies / mantras to how the signaling is performed: –Hard-state: The “Telephony Philosophy”? –Soft-state: The “Internet Philosophy” [Clark’89] The difference: –Easy to describe philosophically –Hard to define precisely

Soft-state signaling Signaling plane Communication plane SenderReceiver Best effort signaling Refresh timer: state needs periodic refresh State only removed by time-out Failure to communicate  go to safe (default) state

Soft-state signaling Signaling plane Communication plane SenderReceiver Best effort signaling Refresh timer: state needs periodic refresh State only removed by time-out Failure to communicate  go to safe (default) state

Hard-state signaling Signaling plane Communication plane SenderReceiver Install ack State is explicitly added and removed Assumes very reliable communication channel Failure to communicate  special recovery procedure removal error X

So Why is Soft State Design “Better”? Some common responses: It’s more robust –To what? Packet loss? High delays? It’s better at handling really bizarre network conditions –Like what? Really high loss rates? Really high delays? Recovery is part of soft state’s normal operating process (no separate recovery operations needed) –So what?

Prior work examining Soft State [Raman,McCanne ’99] –Queueing model of SS signaling system –Showed SS/HS hybrid improves protocol performance [Ji et al ’03] –Performance comparison between SS, HS, and SS/HS hybrids –Conclusion: Hard State beats Soft State, but hybrid SS/HS protocols are best So Why is Soft State Design “Better”?

What’s Wrong with Traditional Performance Evaluations Tradition: “Given some network conditions, design the best protocol.” Input: Conditions Protocol Parameters

Input: Conditions Output: Best Solution What’s Wrong with Traditional Performance Evaluations Tradition: “Given some network conditions, design the best protocol.” Protocol Parameters

The “Traditional” Conclusion For any network condition, hard state protocols can be configured for that condition to out-perform their soft state counterparts

A more “practical” performance evaluation Don’t really know what the conditions will be when configuring the protocol Protocol Parameters Input: Conditions Output: (Best?) Solution Is Hard State best in this setting?

Performance-Oriented View of Protocol Designer Intuition Suppose protocols are “tuned” to operate most efficiently under “normal” conditions Claim: HS performance worsens more rapidly than SS as conditions vary from norm Network Condition Performance Normal Operating Regime Hard State Protocol Soft State Protocol good bad

Our Comparison Study We choose 3 network scenarios –DoS Attack –Correlated, Lossy Feedback Channel –Broadcast Communication Environment For each scenario: –Pick a HS and SS protocol used in the scenario –Choose protocol parameters (timeout lengths, # attempts) to work well for “expected network conditions” –Vary the network conditions –Watch how the protocol performs (w/o rechoosing protocol parameters!!)

A Generic Signaling Protocol Model L = Lifetime that a “state” should exist R = Refresh interval T = Timeout interval (e.g., 3R for SS many protocols) p = Channel loss probability K 1, K 2, etc. = Various Costs (described later)

Refresh Cost Signaling plane Communication plane SenderReceiver Cost = 3K 1 Cost = K 1 Total Cost ~ L/R K 1 Cost = 2K 1 Cost to keep state consistent

(Re)Initialization Cost Signaling plane Communication plane SenderReceiver # of drops ~ pL/R, Cost = K 2 pL/R p Cost to recover from accidental timeout

Stale state cost Signaling plane Communication plane SenderReceiver Stale state lifetime ~ R, Cost = K 3 pR p State Removal Signal Cost of enacting an actual timeout

Total Cost C(R) = K 2 p L/R+ K 1 L/R + K 3 p R E[C(R)] = K 2 p E[L]/R+ K 1 E[L]/R + K 3 p R What is the optimal R to minimize total cost? K 2 K 1 >> K 3, R K 2 K 1 << K 3, R

Optimal R implications K 2,K 1 large  Performance emphasis –Fewer refresh pings, bad to tear down state accidentally K 3 large  Robustness emphasis –Bad to miss tearing down state Higher R, “Harder” the protocol, Lower R, “Softer” the protocol

Cost Comparison Results match previous robustness intuition

Resource Blocking (DoS) Attacks Good Traffic: uses and releases resource Attacker: doesn’t release resource until timeout Hard state more susceptible to attacks

Correlated, Lossy Feedback Channel Client connects to a server If loss rate from server too high, client chooses to disconnect – Soft State: receiver stops sending refresh messages –Hard State: receiver tries to push a “disconnect” message through the lossy channel Channel losses (in both directions) are equal

The Hard-State Dilemma STOP! Feedback loop: Inability to terminate induces greater losses, making it more difficult to terminate

Results of Markov Model Formulation As session expected lifetime (1/μ) decreases, HS zombie sessions grow large Soft State has many fewer zombie sessions

Robust Multicast Feedback Scenario: sender broadcasts transmission as long as some receiver listening Q: How does sender know if a receiver is listening?

Hard State Approach Each “interested” receiver explicitly notifies sender of join and leave S R R R I’m interested I’m no longer interested

Soft State Approach Some receiver must ping sender about interest within time period T or broadcast stops receiver pings randomly delayed and broadcast so other receivers can suppress their pings propagation delays can induce multiple pings per interval TTTT S R R R XXXXX

Optimized Versions Prefix-matching methods [Bolot’93] can be used to reduce receiver communication costs –Hard-state: used to choose a leader –Soft-sate: used to reduce feedback rate

Heavy Arrival Rate Comparison = arrival rate of interested clients Soft State designs exhibit better scalability with large for both versions of polling protocols

Heavy Departure Rate Comparison μ = departure rate of interested clients Soft State designs exhibit better scalability with large μ for both versions of polling protocols

Conclusions Hard state protocols can often outperform soft state protocols when network conditions are known What makes soft state “better” design is its ability to provide “acceptable” performance over a larger variety of network conditions