Networked systems and their users

Size: px
Start display at page:

Download "Networked systems and their users"

Transcription

1 Networked systems and their users q The expansion of the Google serving infrastructure q A personalized livestreaming system q A platform for crowdsourcing web QoE measurements

2 Mapping the expansion of Google s serving infrastructure M. Calder, X. Fan, Z. Hu, E. Katz- Bassett, J. Heidemann, R. Govindan IMC 2013

3 Why study Google? Content providers dominate Internet traffic Google serves an estimated 25% of North American Internet Traffic (Wired, July 2013) Google goes down for 5 minutes, Internet traffic drops 40% (CNET, August 2013) Complex infrastructure for performance Unique and valuable view of the Internet Properties of content serving infrastructure Improve new and existing systems 3

4 Google infrastructure Designed to reduce latency Datacenter 4

5 Google infrastructure Designed to reduce latency Public interface for web services Users interact directly with front-ends Relay between user and datacenter Datacenter Front-end 5

6 The work map front-ends Google s or ISP network More control from front-end to datacenter Financial motivation to map clients to nearby front-ends Front-end 6

7 Goal: Map content serving infrastructure Geographical and topological scope Client-server mapping Tracking expansion Client impact of expansion 7

8 Challenges and approach Insufficient vantage points limit mapping Existing geolocations inaccurate for servers Differentiate physical sites in metro area 8

9 Challenges and approach Use the fact that Google works hard to direct clients to nearby front-ends Insufficient vantage points limit mapping Complete enumeration using EDNS client subnet-prefix Existing geolocations inaccurate for servers Geolocate server based on its clients Differentiate physical sites in metro area Clustering technique 9

10 Background: Client to front-end mapping Hard case: Distributed users Google server A Google.com? Google server A Google server B Local DNS resolver 10

11 Background: Client to front-end mapping Solution: EDNS Client-subnet-prefix Google server A Google.com? /24 Google server B Google server B Local DNS resolver /24 11

12 Enumeration methodology Daily, we query from all routable prefixes using EDNS and find which front-end Google is directing it to For DNS, equivalent to having a vantage point in 10 million /24s 12

13 Client-Centric Geolocation Geolocates a server from the geographic mean of the (possibly noisy) locations for clients associated with that server Intuition If the provider is doing a good job, clients will be send to network and probably geographically close servers so if you know where clients are, you can approximate the server s location 13

14 Geolocation methodology Geolocate a front-end IP based on the location of the clients it serves 1. Given a front-end IP

15 Geolocation methodology Geolocate a front-end IP based on the location of the clients it serves 1. Given a front-end IP 2. Identify the client prefixes directed to it / / /24 15

16 Geolocation methodology Geolocate a front-end IP based on the location of the clients it serves 1. Given a front-end IP 2. Identify the client prefixes directed to it 3. Geolocate all client prefixes using MaxMind database /24 Sydney, Auz /24 Auckland, NZ /24 Sydney, Aus 16

17 Geolocation methodology Geolocate a front-end IP based on the location of the clients it serves 1. Given a front-end IP 2. Identify the client prefixes directed to it 3. Geolocate all client prefixes using MaxMind database 4. Discard outliers to improve accuracy 5. Location is geographic mean of remaining prefix locations /24 Sydney, Auz /24 Auckland, NZ /24 Sydney, Aus 17

18 Geolocation example ? 18

19 Geolocation example Sydney, AUS Ground truth from airport code sysd01s13-in-f16.1e100.net 19

20 Geolocation example All prefix locations 12944, error 580 Km Actual Estimated 20

21 Geolocation example All prefix locations 12944, error 580 Km Remove low confidence location -2227, error 320 Km Remove prefixes far from front-ends -7257, error 12 Km Actual Estimated 21

22 Speed of light filtering 1. Measure RTT 2. Establish feasibility region based on RTT 3. Discard locations outside intersection region Target front-end Vantage point 22

23 Geolocation example All prefix locations 12944, error 580 Km Remove low confidence locations -2227, error 320 Km Remove prefixes far from front-ends -7257, error 12 Km Additional filtering details in paper Actual Estimated 23

24 Validation: Geolocation accuracy Ground truth are Google IPs with airport codes MaxMind places everything in Mountain View, CA Speed of light needs nearby vantage points Our geolocation approach median error is 26Km 24

25 Overview Overcome infrastructure mapping challenges Limited vantage points Inaccurate geolocation for servers Enable longitudinal study of Google Expansion results 25

26 Results: Expansion 1,400+ serving sites as of Aug

27 Google.com servers in Oct sites in 60 countries and 100 ASes Large % are in Google s AS 27

28 Google.com servers in October sites (7x) In 130+ countries (2.3x) 800+ ASes (8x) Growth is outside Google s AS 28

29 Results: What is different for ASes? AS size 2012/11 ASes 2013/08 ASes Google 2 2 (+0%) Tier (+100%) Large (+310%) Small (+811%) Stub (+1133%) Most front-ends in low end of AS hierarchy 29

30 Results: What is different for users? AS size 2012/11 ASes 2013/08 ASes 2012/11 Clients 2013/08 Clients Google 2 2 (+0%) 9856K 9067K (-8%) Tier (+100%) K (+7278%) Large (+310%) 111K 410K (+270%) Small (+811%) 37K 359K (+870%) Stub (+1133%) 52K 180K (+240%) Most front-ends in low end of AS hierarchy 90% of prefixes still directed to servers in Google network Most prefixes directed to front ends in larger ASes 30

31 Results: Client Front-end distance Of prefixes now served by ISP-hosted sites Median Km to Google-hosted front-end Median within ~45 Km of ISP-hosted front-end 31

32 Expansion strategy Moving infrastructure closer to clients Reduce latency Split-TCP proxies Persistent, multiplexed connections Serve static content immediately Advanced error recovery Repurposing of Google Global Cache YouTube video caches 32

33 Client impact (ongoing work) PlanetLab node at Christchurch, NZ Nearest Google-hosted front-end in Sydney Query response time to ISP and Google hosted 33

34 Conclusion New techniques for mapping the content serving infrastructures for a major content provider, Google Longitudinal study of expansion of Google s infrastructure Shows shift in Google s strategy for reducing client latency Data available mappinggoogle.cs.usc.edu 34

35 Today The expansion of the Google serving infrastructure A personalized livestreaming system A platform for crowdsourcing web QoE measurements 35

Mapping the Expansion of Google s Serving Infrastructure

Mapping the Expansion of Google s Serving Infrastructure Mapping the Expansion of Google s Serving Infrastructure Matt Calder University of Southern California Ethan Katz-Bassett University of Southern California Xun Fan USC/ISI John Heidemann USC/ISI Zi Hu

More information

BROAD AND LOAD-AWARE ANYCAST MAPPING WITH VERFPLOETER

BROAD AND LOAD-AWARE ANYCAST MAPPING WITH VERFPLOETER BROAD AND LOAD-AWARE ANYCAST MAPPING WITH VERFPLOETER WOUTER B. DE VRIES, RICARDO DE O. SCHMIDT, WES HARDAKER, JOHN HEIDEMANN, PIETER-TJERK DE BOER AND AIKO PRAS London - November 3, 2017 INTRODUCTION

More information

PinPoint: A Ground-Truth Based Approach for IP Geolocation

PinPoint: A Ground-Truth Based Approach for IP Geolocation PinPoint: A Ground-Truth Based Approach for IP Geolocation Brian Eriksson Network Mapping and Measurement Conference 2010 Paul Barford Robert Nowak Bruce Maggs Introduction Consider some resource in the

More information

John S. Otto Mario A. Sánchez John P. Rula Fabián E. Bustamante

John S. Otto Mario A. Sánchez John P. Rula Fabián E. Bustamante John S. Otto Mario A. Sánchez John P. Rula Fabián E. Bustamante Northwestern, EECS http://aqualab.cs.northwestern.edu ! DNS designed to map names to addresses Evolved into a large-scale distributed system!

More information

End-user mapping: Next-Generation Request Routing for Content Delivery

End-user mapping: Next-Generation Request Routing for Content Delivery Introduction End-user mapping: Next-Generation Request Routing for Content Delivery Fangfei Chen, Ramesh K. Sitaraman, Marcelo Torres ACM SIGCOMM Computer Communication Review. Vol. 45. No. 4. ACM, 2015

More information

KillTest ᦝ䬺 䬽䭶䭱䮱䮍䭪䎃䎃䎃ᦝ䬺 䬽䭼䯃䮚䮀 㗴 㓸 NZZV ]]] QORRZKYZ PV ٶ瀂䐘މ悹伥濴瀦濮瀃瀆ݕ 濴瀦

KillTest ᦝ䬺 䬽䭶䭱䮱䮍䭪䎃䎃䎃ᦝ䬺 䬽䭼䯃䮚䮀 㗴 㓸 NZZV ]]] QORRZKYZ PV ٶ瀂䐘މ悹伥濴瀦濮瀃瀆ݕ 濴瀦 KillTest Exam : 1Y0-A21 Title : Basic Administration for Citrix NetScaler 9.2 Version : Demo 1 / 5 1.Scenario: An administrator is working with a Citrix consultant to architect and implement a NetScaler

More information

Chapter 2 Content Delivery Networks and Its Interplay with ISPs

Chapter 2 Content Delivery Networks and Its Interplay with ISPs Chapter 2 Content Delivery Networks and Its Interplay with ISPs This chapter surveys measurement studies on Content Delivery Networks (CDNs) in real world. Several representative CDNs with different architecture

More information

Adaptive Bit Rate (ABR) Video Detection and Control

Adaptive Bit Rate (ABR) Video Detection and Control OVERVIEW Adaptive Bit Rate (ABR) Video Detection and Control In recent years, Internet traffic has changed dramatically and this has impacted service providers and their ability to manage network traffic.

More information

CONTENT-AWARE DNS. IMPROVING CONTENT-AWARE DNS RESOLUTION WITH AKAMAI DNSi CACHESERVE EQUIVALENCE CLASS. AKAMAI DNSi CACHESERVE

CONTENT-AWARE DNS. IMPROVING CONTENT-AWARE DNS RESOLUTION WITH AKAMAI DNSi CACHESERVE EQUIVALENCE CLASS. AKAMAI DNSi CACHESERVE AKAMAI DNSi CACHESERVE CONTENT-AWARE DNS IMPROVING CONTENT-AWARE DNS RESOLUTION WITH AKAMAI DNSi CACHESERVE EQUIVALENCE CLASS. CacheServe is the telecommunication industry s gold standard for caching DNS.

More information

Investigating Transparent Web Proxies in Cellular Networks

Investigating Transparent Web Proxies in Cellular Networks Investigating Transparent Web Proxies in Cellular Networks Xing Xu, Yurong Jiang, Tobias Flach, Ethan Katz-Bassett, David Choffnes, Ramesh Govindan USC & Northeastern University March 20, 2015 Introduction

More information

Diagnosing Path Inflation of Mobile Client Traffic

Diagnosing Path Inflation of Mobile Client Traffic Diagnosing Path Inflation of Mobile Client Traffic Kyriakos Zarifis, Tobias Flach, Srikanth Nori, David Choffnes, Ramesh Govindan, Ethan Katz- Bassett, Z. Morley Mao, Matt Welsh University of Southern

More information

Revealing the Load-balancing Behavior of YouTube Traffic on Interdomain Links

Revealing the Load-balancing Behavior of YouTube Traffic on Interdomain Links Revealing the Load-balancing Behavior of YouTube Traffic on Interdomain Links Ricky K. P. Mok, Vaibhav Bajpai, Amogh Dhamdhere, and kc claffy CAIDA/UCSD, San Diego, USA cskpmok amogh kc@caida.org Technische

More information

Cell Spotting: Studying the Role of Cellular Networks in the Internet. John Rula. Fabián E. Bustamante Moritz Steiner 2017 AKAMAI FASTER FORWARD TM

Cell Spotting: Studying the Role of Cellular Networks in the Internet. John Rula. Fabián E. Bustamante Moritz Steiner 2017 AKAMAI FASTER FORWARD TM Cell Spotting: Studying the Role of Cellular Networks in the Internet * John Rula * Fabián E. Bustamante Moritz Steiner * 1 Understanding cellular growth is critical Growing dominance of mobile On subscriptions

More information

Studying Black Holes on the Internet with Hubble

Studying Black Holes on the Internet with Hubble Studying Black Holes on the Internet with Hubble Ethan Katz-Bassett, Harsha V. Madhyastha, John P. John, Arvind Krishnamurthy, David Wetherall, Thomas Anderson University of Washington RIPE, May 2008 This

More information

Characterizing the Deployment and Performance of Multi-CDNs

Characterizing the Deployment and Performance of Multi-CDNs ABSTRACT Characterizing the Deployment and Performance of Multi-CDNs Rachee Singh rachee@cs.umass.edu UMass Amherst Pushing software updates to millions of geographically diverse clients is an important

More information

Network infrastructure, routing and traffic. q Internet inter-domain traffic q Traffic estimation for the outsider

Network infrastructure, routing and traffic. q Internet inter-domain traffic q Traffic estimation for the outsider Network infrastructure, routing and traffic q Internet inter-domain traffic q Traffic estimation for the outsider Internet Inter-Domain Traffic C. Labovitz, S. Lekel-Johnson, D. McPherson, J. Oberheide,

More information

Factors Affecting Performance of Web Flows in Cellular Networks

Factors Affecting Performance of Web Flows in Cellular Networks in Cellular Networks Ermias A. Walelgne, Kim Setälä, Vaibhav Bajpai, Stefan Neumeier, Jukka Manner, Jörg Ott October 17, 2018 - RIPE 77, Amsterdam Introduction Introduction Introduction Motivation 99%

More information

Internet Anycast: Performance, Problems and Potential

Internet Anycast: Performance, Problems and Potential Internet Anycast: Performance, Problems and Potential Zhihao Li, Dave Levin, Neil Spring, Bobby Bhattacharjee University of Maryland 1 Anycast is increasingly used DNS root servers: All 13 DNS root servers

More information

Internet Inter-Domain Traffic. C. Labovitz, S. Iekel-Johnson, D. McPherson, J. Oberheide, F. Jahanian, Proc. of SIGCOMM 2010

Internet Inter-Domain Traffic. C. Labovitz, S. Iekel-Johnson, D. McPherson, J. Oberheide, F. Jahanian, Proc. of SIGCOMM 2010 Internet Inter-Domain Traffic C. Labovitz, S. Iekel-Johnson, D. McPherson, J. Oberheide, F. Jahanian, Proc. of SIGCOMM 2010 Motivation! Measuring the Internet is hard! Significant previous work on Router

More information

Reverse Traceroute. NSDI, April 2010 This work partially supported by Cisco, Google, NSF

Reverse Traceroute. NSDI, April 2010 This work partially supported by Cisco, Google, NSF Reverse Traceroute Ethan Katz-Bassett, Harsha V. Madhyastha, Vijay K. Adhikari, Colin Scott, Justine Sherry, Peter van Wesep, Arvind Krishnamurthy, Thomas Anderson NSDI, April 2010 This work partially

More information

Peering at the Internet s Frontier:

Peering at the Internet s Frontier: Peering at the Internet s Frontier: A First Look at ISP Interconnectivity in Africa Arpit Gupta Georgia Tech Matt Calder (USC), Nick Feamster (Georgia Tech), Marshini Chetty (Maryland), Enrico Calandro

More information

Odin: Microsoft s Scalable Fault-

Odin: Microsoft s Scalable Fault- Odin: Microsoft s Scalable Fault- Tolerant CDN Measurement System Matt Calder Manuel Schröder, Ryan Gao, Ryan Stewart, Jitendra Padhye, Ratul Mahajan, Ganesh Ananthanarayanan, Ethan Katz-Bassett NSDI,

More information

Domain Name System.

Domain Name System. Domain Name System http://xkcd.com/302/ CSCI 466: Networks Keith Vertanen Fall 2011 Overview Final project + presentation Some TCP and UDP experiments Domain Name System (DNS) Hierarchical name space Maps

More information

IP Geolocation. Doxa Chatzopoulou Computer Science and Engineering Dept UC Riverside

IP Geolocation. Doxa Chatzopoulou Computer Science and Engineering Dept UC Riverside IP Geolocation Doxa Chatzopoulou Computer Science and Engineering Dept UC Riverside Email: chatzopd@cs.ucr.edu Marios Kokkodis Computer Science and Engineering Dept UC Riverside Email: kokkodim@cs.ucr.edu

More information

Web Content Cartography. Georgios Smaragdakis Joint work with Bernhard Ager, Wolfgang Mühlbauer, and Steve Uhlig

Web Content Cartography. Georgios Smaragdakis Joint work with Bernhard Ager, Wolfgang Mühlbauer, and Steve Uhlig Web Content Cartography Georgios Smaragdakis Joint work with Bernhard Ager, Wolfgang Mühlbauer, and Steve Uhlig Cartography Cartography (from Greek Χάρτης, chartes or charax = sheet of papyrus (paper)

More information

A Look at Router Geolocation in Public and Commercial Databases

A Look at Router Geolocation in Public and Commercial Databases A Look at Router Geolocation in Public and Commercial Databases Manaf Gharaibeh 1, Anant Shah 1, Bradley Huffaker 2, Han Zhang 1, Roya Ensafi 3, Christos Papadopoulos 1 1 Colorado State University 2 CAIDA

More information

A Learning-based Approach for IP Geolocation

A Learning-based Approach for IP Geolocation A Learning-based Approach for IP Geolocation Brian Eriksson, Paul Barford, Joel Sommers, and Robert Nowak University of Wisconsin - Madison, Colgate University bceriksson@wisc.edu, pb@cs.wisc.edu, jsommers@colagate.edu,

More information

IPv6 at Google. a case study. Angus Lees Site Reliability Engineer. Steinar H. Gunderson Software Engineer

IPv6 at Google. a case study. Angus Lees Site Reliability Engineer. Steinar H. Gunderson Software Engineer IPv6 at Google a case study Angus Lees Site Reliability Engineer Steinar H. Gunderson Software Engineer 1 A Brief History 14 March 2005 Register with ARIN 2001:4860::/32 August 2007 Network architecture

More information

Distributed Systems. 21. Content Delivery Networks (CDN) Paul Krzyzanowski. Rutgers University. Fall 2018

Distributed Systems. 21. Content Delivery Networks (CDN) Paul Krzyzanowski. Rutgers University. Fall 2018 Distributed Systems 21. Content Delivery Networks (CDN) Paul Krzyzanowski Rutgers University Fall 2018 1 2 Motivation Serving web content from one location presents problems Scalability Reliability Performance

More information

Democratizing Content Publication with Coral

Democratizing Content Publication with Coral Democratizing Content Publication with Mike Freedman Eric Freudenthal David Mazières New York University www.scs.cs.nyu.edu/coral A problem Feb 3: Google linked banner to julia fractals Users clicking

More information

Democratizing Content Publication with Coral

Democratizing Content Publication with Coral Democratizing Content Publication with Mike Freedman Eric Freudenthal David Mazières New York University NSDI 2004 A problem Feb 3: Google linked banner to julia fractals Users clicking directed to Australian

More information

Quantifying Violations of Destination-based Forwarding on the Internet

Quantifying Violations of Destination-based Forwarding on the Internet Quantifying Violations of Destination-based Forwarding on the Internet Tobias Flach, Ethan Katz-Bassett, and Ramesh Govindan University of Southern California November 14, 2012 Destination-based Routing

More information

Mobile Content Hosting Infrastructure in China: A View from a Cellular ISP. Zhenhua Li Chunjing Han Gaogang Xie

Mobile Content Hosting Infrastructure in China: A View from a Cellular ISP. Zhenhua Li Chunjing Han Gaogang Xie Mobile Content Hosting Infrastructure in China: A View from a Cellular ISP Zhenyu Li Donghui Yang Zhenhua Li Chunjing Han Gaogang Xie Continuous increase of mobile data CISCO projected: the mobile data

More information

Achieving scale: Large scale active measurements from PlanetLab

Achieving scale: Large scale active measurements from PlanetLab Achieving scale: Large scale active measurements from PlanetLab Marc-Olivier Buob, Jordan Augé (UPMC) 4th PhD School on Traffic Monitoring and Analysis (TMA) April 15th, 2014 London, UK OneLab FUTURE INTERNET

More information

PoP Level Mapping And Peering Deals

PoP Level Mapping And Peering Deals PoP Level Mapping And Peering Deals Mapping Internet Methodology Data Collection IP Classification to PoP PoP Geolocation PoP locations on Peering estimations Outline Internet Service Providers ISPs are

More information

The Flattening Internet Topology:

The Flattening Internet Topology: The Flattening Internet Topology: Natural Evolution, Unsightly Barnacles or Contrived Collapse? Phillipa Gill Martin Arlitt Zongpeng Li Anirban Mahanti U of Calgary HP Labs/ U of Calgary IIT Delhi U of

More information

Network Forensics Prefix Hijacking Theory Prefix Hijacking Forensics Concluding Remarks. Network Forensics:

Network Forensics Prefix Hijacking Theory Prefix Hijacking Forensics Concluding Remarks. Network Forensics: Network Forensics: Network OS Fingerprinting Prefix Hijacking Analysis Scott Hand September 30 th, 2011 Outline 1 Network Forensics Introduction OS Fingerprinting 2 Prefix Hijacking Theory BGP Background

More information

Understanding and Characterizing Hidden Interception of the DNS Resolution Path

Understanding and Characterizing Hidden Interception of the DNS Resolution Path Who Is Answering My Queries? Understanding and Characterizing Hidden Interception of the DNS Resolution Path Baojun Liu, Chaoyi Lu, Haixin Duan, YingLiu, ZhouLi, ShuangHaoand MinYang ISP DNS Resolver DNS

More information

Enabling and Configuring DNS Traffic Control in NIOS 7.x

Enabling and Configuring DNS Traffic Control in NIOS 7.x DEPLOYMENT GUIDE Enabling and Configuring DNS Traffic Control in NIOS 7.x 2016 Infoblox Inc. All rights reserved. Infoblox-DG-0141-00 Enabling and Configuring DNS Traffic Control May 2016 Page 1 of 20

More information

YouLighter: An Unsupervised Methodology to Unveil YouTube CDN Changes

YouLighter: An Unsupervised Methodology to Unveil YouTube CDN Changes YouLighter: An Unsupervised Methodology to Unveil YouTube CDN Changes Danilo Giordano, Stefano Traverso, Luigi Grimaudo, Marco Mellia, Elena Baralis Politecnico di Torino Alok Tongankar, Sabyasachi Sasha

More information

Dynamic Design of Cellular Wireless Networks via Self Organizing Mechanism

Dynamic Design of Cellular Wireless Networks via Self Organizing Mechanism Dynamic Design of Cellular Wireless Networks via Self Organizing Mechanism V.Narasimha Raghavan, M.Venkatesh, Divya Sridharabalan, T.Sabhanayagam, Nithin Bharath Abstract In our paper, we are utilizing

More information

ddos-guard.net Protecting your business DDoS-GUARD: Distributed protection against distributed attacks

ddos-guard.net Protecting your business DDoS-GUARD: Distributed protection against distributed attacks ddos-guard.net Protecting your business DDoS-GUARD: Distributed protection against distributed attacks 2 WHAT IS A DDOS-ATTACK AND WHY ARE THEY DANGEROUS? Today's global network is a dynamically developing

More information

draft-moura-dnsop-authoritativerecommendations-03

draft-moura-dnsop-authoritativerecommendations-03 draft-moura-dnsop-authoritativerecommendations-03 Giovane C. M. Moura 1,2, Wes Hardaker 3, John Heidemann 3, Marco Davids 1 DNSOP IETF 104 Prague, CZ 2019-03-26 1 SIDN Labs, 2 TU Delft, 3 USC/ISI 1 Draft

More information

Scaling Internet TV Content Delivery ALEX GUTARIN DIRECTOR OF ENGINEERING, NETFLIX

Scaling Internet TV Content Delivery ALEX GUTARIN DIRECTOR OF ENGINEERING, NETFLIX Scaling Internet TV Content Delivery ALEX GUTARIN DIRECTOR OF ENGINEERING, NETFLIX Inventing Internet TV Available in more than 190 countries 104+ million subscribers Lots of Streaming == Lots of Traffic

More information

Partitioning the Internet

Partitioning the Internet Partitioning the Internet Matthias Wachs Christian Grothoff 1 Ramakrishna Thurimella 2 Technische Universität München 1 University of Denver 2 CRiSIS 2012, Cork, Ireland FSNSG (TUM) Partitioning the Internet

More information

George Nomikos

George Nomikos George Nomikos gnomikos@ics.forth.gr To appear in IMC, Boston, 2018 V. Kotronis, P. Sermpezis, P. Gigis, L. Manassakis, C. Dietzel, S. Konstantaras, X. Dimitropoulos, V. Giotsas *Jane Coffin and Christian

More information

Factors Affecting Performance of Web Flows in Cellular Networks

Factors Affecting Performance of Web Flows in Cellular Networks in Cellular Networks Ermias A. Walelgne, Kim Setälä, Vaibhav Bajpai, Stefan Neumeier, Jukka Manner, Jörg Ott May 15, 2018 - FP Networking, Zurich ntroduction ntroduction ntroduction Motivation 99% of the

More information

BraindumpsQA. IT Exam Study materials / Braindumps

BraindumpsQA.  IT Exam Study materials / Braindumps BraindumpsQA http://www.braindumpsqa.com IT Exam Study materials / Braindumps Exam : 70-532 Title : Developing Microsoft Azure Solutions Vendor : Microsoft Version : DEMO Get Latest & Valid 70-532 Exam's

More information

CSE 124: CONTENT-DISTRIBUTION NETWORKS. George Porter December 4, 2017

CSE 124: CONTENT-DISTRIBUTION NETWORKS. George Porter December 4, 2017 CSE 124: CONTENT-DISTRIBUTION NETWORKS George Porter December 4, 2017 ATTRIBUTION These slides are released under an Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0) Creative Commons

More information

List of measurements in rural area

List of measurements in rural area List of measurements in rural area Network Distance / Delay / HOP! Tool " ICMP Ping and UDP Ping (traceroute)! Targets / Tests " VSAT Gateways / Earth Station # Testing distance to VSAT FTP server at the

More information

Measuring IPv6 Adoption

Measuring IPv6 Adoption Measuring IPv6 Adoption Presenter: Johannes Zirngibl Technische Universität München Munich, 18. May 2017 Author: Jakub Czyz (University of Michigan) Mark Allman (International Computer Science Institute)

More information

CS November 2017

CS November 2017 Distributed Systems 21. Delivery Networks () Paul Krzyzanowski Rutgers University Fall 2017 1 2 Motivation Serving web content from one location presents problems Scalability Reliability Performance Flash

More information

Tracing the Path to YouTube: A Quantification of Path Lengths and Latencies Toward Content Caches

Tracing the Path to YouTube: A Quantification of Path Lengths and Latencies Toward Content Caches ACCEPTED FROM OPEN CALL Tracing the Path to YouTube: A Quantification of Path Lengths and Latencies Toward Content Caches Trinh Viet Doan, Ljubica Pajevic, Vaibhav Bajpai, and Jörg Ott Quantifying the

More information

Data and measurement tools from the RIPE NCC. Robert Kisteleki RIPE NCC R&D

Data and measurement tools from the RIPE NCC. Robert Kisteleki RIPE NCC R&D Data and measurement tools from the RIPE NCC Robert Kisteleki RIPE NCC R&D Table of Contents Today s topics: RIPEstat to know more about resources RIPE Atlas to run Internet measurements yourself, and

More information

Building an Internet-Scale Publish/Subscribe System

Building an Internet-Scale Publish/Subscribe System Building an Internet-Scale Publish/Subscribe System Ian Rose Mema Roussopoulos Peter Pietzuch Rohan Murty Matt Welsh Jonathan Ledlie Imperial College London Peter R. Pietzuch prp@doc.ic.ac.uk Harvard University

More information

CS November 2018

CS November 2018 Distributed Systems 21. Delivery Networks (CDN) Paul Krzyzanowski Rutgers University Fall 2018 1 2 Motivation Serving web content from one location presents problems Scalability Reliability Performance

More information

Vivaldi: : A Decentralized Network Coordinate System

Vivaldi: : A Decentralized Network Coordinate System Vivaldi: : A Decentralized Network Coordinate System Frank Dabek, Russ Cox, Frans Kaashoek, Robert Morris MIT CSAIL Presenter: Yi-Chao Chen 1 Introduction Design Issues Idea Algorithm Evaluation Model

More information

From Internet Data Centers to Data Centers in the Cloud

From Internet Data Centers to Data Centers in the Cloud From Internet Data Centers to Data Centers in the Cloud This case study is a short extract from a keynote address given to the Doctoral Symposium at Middleware 2009 by Lucy Cherkasova of HP Research Labs

More information

DailyCatch: A Provider-centric View of Anycast Behaviour

DailyCatch: A Provider-centric View of Anycast Behaviour DailyCatch: A Provider-centric View of Anycast Behaviour Stephen McQuistin University of Glasgow Sree Priyanka Uppu Marcel Flores Verizon Digital Media Services What is IP anycast? 2 What is IP anycast?

More information

Diffusing Your Mobile Apps: Extending In-Network Function Virtualisation to Mobile Function Offloading

Diffusing Your Mobile Apps: Extending In-Network Function Virtualisation to Mobile Function Offloading Diffusing Your Mobile Apps: Extending In-Network Function Virtualisation to Mobile Function Offloading Mario Almeida, Liang Wang*, Jeremy Blackburn, Konstantina Papagiannaki, Jon Crowcroft* Telefonica

More information

CONTENT-DISTRIBUTION NETWORKS

CONTENT-DISTRIBUTION NETWORKS CONTENT-DISTRIBUTION NETWORKS George Porter June 1, 2018 ATTRIBUTION These slides are released under an Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0) Creative Commons license These

More information

Chapter 2 Application Layer

Chapter 2 Application Layer Chapter 2 Application Layer A note on the use of these Powerpoint slides: We re making these slides freely available to all (faculty, students, readers). They re in PowerPoint form so you see the animations;

More information

A First Look at QUIC in the Wild

A First Look at QUIC in the Wild A First Look at QUIC in the Wild Jan Rüth 1, Ingmar Poese 2, Christoph Dietzel 3, Oliver Hohlfeld 1 1 : RWTH Aachen University 2 : Benocs GmbH 3 : TU Berlin / DE-CIX http://comsys.rwth-aachen.de/ London

More information

Table of Contents. Cisco How NAT Works

Table of Contents. Cisco How NAT Works Table of Contents How NAT Works...1 This document contains Flash animation...1 Introduction...1 Behind the Mask...2 Dynamic NAT and Overloading Examples...5 Security and Administration...7 Multi Homing...9

More information

AP-atoms: A High-Accuracy Data-Driven Client Aggregation for Global Load Balancing

AP-atoms: A High-Accuracy Data-Driven Client Aggregation for Global Load Balancing AP-atoms: A High-Accuracy Data-Driven Client Aggregation for Global Load Balancing Yibo Pi, Sugih Jamin Univerisity of Michigian Ann Arbor, MI {yibo, sugih}@umich.edu Peter Danzig Panier Analytics Menlo

More information

Characterizing a Meta-CDN

Characterizing a Meta-CDN Characterizing a Meta-CDN Oliver Hohlfeld, Jan Rüth, Konrad Wolsing, http://comsys.rwth-aachen.de/ Berlin / PAM 2018 Motivation - What is a Meta-CDN? Content Delivery Networks Key component in the Internet,

More information

Updates and Case Study

Updates and Case Study Archipelago Measurement Infrastructure Updates and Case Study Young Hyun CAIDA ISMA 2010 AIMS Workshop Feb 9, 2010 2 Outline Introduction Monitor Deployment Measurements & Collaborations Tools Development

More information

Authors: Rupa Krishnan, Harsha V. Madhyastha, Sridhar Srinivasan, Sushant Jain, Arvind Krishnamurthy, Thomas Anderson, Jie Gao

Authors: Rupa Krishnan, Harsha V. Madhyastha, Sridhar Srinivasan, Sushant Jain, Arvind Krishnamurthy, Thomas Anderson, Jie Gao Title: Moving Beyond End-to-End Path Information to Optimize CDN Performance Authors: Rupa Krishnan, Harsha V. Madhyastha, Sridhar Srinivasan, Sushant Jain, Arvind Krishnamurthy, Thomas Anderson, Jie Gao

More information

IXP economic aspect and benefits

IXP economic aspect and benefits IXP economic aspect and benefits M. Sall modou.sall@orange-sonatel.com Slide 1 ITU IXP Workshop September 28 th, 2015 Copyright Sonatel. All rights reserved Outline Context Content Distribution and Hosting

More information

Citrix SD-WAN for Optimal Office 365 Connectivity and Performance

Citrix SD-WAN for Optimal Office 365 Connectivity and Performance Solution Brief Citrix SD-WAN for Optimal Office 365 Connectivity and Performance Evolving Needs for WAN Network Architecture Enterprise networks have historically been architected to provide users access

More information

INFERRING PERSISTENT INTERDOMAIN CONGESTION

INFERRING PERSISTENT INTERDOMAIN CONGESTION INFERRING PERSISTENT INTERDOMAIN CONGESTION Amogh Dhamdhere with David Clark, Alex Gamero-Garrido, Matthew Luckie, Ricky Mok, Gautam Akiwate, Kabir Gogia, Vaibhav Bajpai, Alex Snoeren, k Claffy Problem:

More information

Where are the anycasters?

Where are the anycasters? NANOG 66 Where are the anycasters? (Lightning version) Danilo Cicalese danilo.cicalese@telecom- paristech.fr h>p://www. telecom- paristech.fr/~drossi/anycast GA n. 318627 Joint work with Dario Rossi, Diana

More information

Flooding Attacks by Exploiting Persistent Forwarding Loops

Flooding Attacks by Exploiting Persistent Forwarding Loops Flooding Attacks by Exploiting Persistent Forwarding Jianhong Xia, Lixin Gao, Teng Fei University of Massachusetts at Amherst {jxia, lgao, tfei}@ecs.umass.edu ABSTRACT In this paper, we present flooding

More information

IPv6 at Google. Lorenzo Colitti

IPv6 at Google. Lorenzo Colitti IPv6 at Google Lorenzo Colitti lorenzo@google.com Why? IPv4 address space predictions (G. Huston) To put it into perspective... Iljitsch van Beijnum, Ars Technica Why IPv6? Cost Buying addresses will be

More information

Validation of a LISP Simulator

Validation of a LISP Simulator Validation of a LISP Simulator Albert Cabellos-Aparicio, Jordi Domingo-Pascual Technical University of Catalonia Barcelona, Spain Damien Saucez, Olivier Bonaventure Université catholique de Louvain Louvain-La-Neuve,

More information

Evaluating path diversity in the Internet: from an AS-level to a PoP-level granularity

Evaluating path diversity in the Internet: from an AS-level to a PoP-level granularity Evaluating path diversity in the Internet: from an AS-level to a PoP-level granularity Evaluation de la diversité de chemins sur Internet: d une granularité au niveau des AS à une vision au niveau des

More information

Internet Inter-Domain Traffic

Internet Inter-Domain Traffic Internet Inter-Domain Traffic Craig Labovitz, Scott Iekel-Johnson, Danny McPherson, Jon Oberheide, Farnam Jahanian Presented by: Mario Sanchez Instructor: Fabian Bustamante Date: 01/10/2011 Page 2 Goals

More information

THE WORLD S BEST- CONNECTED DATA CENTERS EQUINIX MIDDLE EAST & NORTH AFRICA (MENA) Equinix.com

THE WORLD S BEST- CONNECTED DATA CENTERS EQUINIX MIDDLE EAST & NORTH AFRICA (MENA) Equinix.com THE WORLD S BEST- CONNECTED DATA CENTERS EQUINIX MIDDLE EAST & NORTH AFRICA (MENA) Equinix.com PLATFORM EQUINIX A PLATFORM FOR GROWTH As the world s largest data center company, Equinix brings global leaders

More information

Internet Technology 2/18/2016

Internet Technology 2/18/2016 Internet Technology 04r. Assignment 4 & 2013 Exam 1 Review Assignment 4 Review Paul Krzyzanowski Rutgers University Spring 2016 February 18, 2016 CS 352 2013-2016 Paul Krzyzanowski 1 February 18, 2016

More information

LASTor: A Low-Latency AS-Aware Tor Client

LASTor: A Low-Latency AS-Aware Tor Client 22 IEEE Symposium on Security and Privacy LASTor: A Low-Latency AS-Aware Tor Client Masoud Akhoondi, Curtis Yu, and Harsha V. Madhyastha Department of Computer Science and Engineering University of California,

More information

A Scalable, Commodity Data Center Network Architecture

A Scalable, Commodity Data Center Network Architecture A Scalable, Commodity Data Center Network Architecture B Y M O H A M M A D A L - F A R E S A L E X A N D E R L O U K I S S A S A M I N V A H D A T P R E S E N T E D B Y N A N X I C H E N M A Y. 5, 2 0

More information

Oracle PeopleSoft 9.2 with NetScaler for Global Server Load Balancing

Oracle PeopleSoft 9.2 with NetScaler for Global Server Load Balancing Oracle PeopleSoft 9.2 with NetScaler for Global Server Load Balancing This solution guide focuses on defining the deployment process for Oracle PeopleSoft with Citrix NetScaler for GSLB (Global Server

More information

A Tale of Three CDNs

A Tale of Three CDNs A Tale of Three CDNs An Active Measurement Study of Hulu and Its CDNs Vijay K Adhikari 1, Yang Guo 2, Fang Hao 2, Volker Hilt 2, and Zhi-Li Zhang 1 1 University of Minnesota - Twin Cities 2 Bell Labs,

More information

DETECTING RESOLVERS AT.NZ. Jing Qiao, Sebastian Castro DNS-OARC 29 Amsterdam, October 2018

DETECTING RESOLVERS AT.NZ. Jing Qiao, Sebastian Castro DNS-OARC 29 Amsterdam, October 2018 DETECTING RESOLVERS AT.NZ Jing Qiao, Sebastian Castro DNS-OARC 29 Amsterdam, October 2018 BACKGROUND DNS-OARC 29 2 DNS TRAFFIC IS NOISY Despite general belief, not all the sources at auth nameserver are

More information

Performance Characterization of a Commercial Video Streaming Service

Performance Characterization of a Commercial Video Streaming Service Performance Characterization of a Commercial Video Streaming Service Mojgan Ghasemi, Princeton University P. Kanuparthy, 1 A. Mansy, 1 T. Benson, 2 J. Rexford 3 1 Yahoo, 2 Duke University, 3 Princeton

More information

The DNS of Things. A. 2001:19b8:10 1:2::f5f5:1d Q. WHERE IS Peter Silva Sr. Technical Marketing

The DNS of Things. A. 2001:19b8:10 1:2::f5f5:1d Q. WHERE IS  Peter Silva Sr. Technical Marketing The DNS of Things Peter Silva Sr. Technical Marketing Manager @psilvas Q. WHERE IS WWW.F5.COM? A. 2001:19b8:10 1:2::f5f5:1d Advanced threats Software defined everything SDDC/Cloud Internet of Things Mobility

More information

Chapter The LRU* WWW proxy cache document replacement algorithm

Chapter The LRU* WWW proxy cache document replacement algorithm Chapter The LRU* WWW proxy cache document replacement algorithm Chung-yi Chang, The Waikato Polytechnic, Hamilton, New Zealand, itjlc@twp.ac.nz Tony McGregor, University of Waikato, Hamilton, New Zealand,

More information

Using MySQL for Distributed Database Architectures

Using MySQL for Distributed Database Architectures Using MySQL for Distributed Database Architectures Peter Zaitsev CEO, Percona SCALE 16x, Pasadena, CA March 9, 2018 1 About Percona Solutions for your success with MySQL,MariaDB and MongoDB Support, Managed

More information

A Survey on Research on the Application-Layer Traffic Optimization (ALTO) Problem

A Survey on Research on the Application-Layer Traffic Optimization (ALTO) Problem A Survey on Research on the Application-Layer Traffic Optimization (ALTO) Problem draft-rimac-p2prg-alto-survey-00 Marco Tomsu, Ivica Rimac, Volker Hilt, Vijay Gurbani, Enrico Marocco 75 th IETF Meeting,

More information

Microclouds for Fragmented Markets Getting OpenStack everywhere!

Microclouds for Fragmented Markets Getting OpenStack everywhere! Microclouds for Fragmented Markets Getting OpenStack everywhere! Benjamin Diaz - Cloud Engineer at Whitestack 1 What are fragmented markets? A marketplace where there is no one company that can exert enough

More information

Performance Characterization of a Commercial Video Streaming Service. Mojgan Ghasemi, Akamai Technologies - Princeton University

Performance Characterization of a Commercial Video Streaming Service. Mojgan Ghasemi, Akamai Technologies - Princeton University Performance Characterization of a Commercial Video Streaming Service Mojgan Ghasemi, Akamai Technologies - Princeton University MGhasemi,PKanuparthy,AMansy,TBenson,andJRexford ACM IMC 2016 1 2 First study

More information

Administering View Cloud Pod Architecture. VMware Horizon 7 7.0

Administering View Cloud Pod Architecture. VMware Horizon 7 7.0 Administering View Cloud Pod Architecture VMware Horizon 7 7.0 You can find the most up-to-date technical documentation on the VMware Web site at: https://docs.vmware.com/ The VMware Web site also provides

More information

BGP. Daniel Zappala. CS 460 Computer Networking Brigham Young University

BGP. Daniel Zappala. CS 460 Computer Networking Brigham Young University Daniel Zappala CS 460 Computer Networking Brigham Young University 2/20 Scaling Routing for the Internet scale 200 million destinations - can t store all destinations or all prefixes in routing tables

More information

Two days in The Life of The DNS Anycast Root Servers

Two days in The Life of The DNS Anycast Root Servers Two days in The Life of The DNS Anycast Root Servers Ziqian Liu Beijing Jiaotong Univeristy Bradley Huffaker, Marina Fomenkov Nevil Brownlee, and kc claffy CAIDA PAM2007 Outline DNS root servers DNS anycast

More information

Dig into MPLS: Transit Tunnel Diversity

Dig into MPLS: Transit Tunnel Diversity January 2015 Dig into MPLS: Transit Tunnel Diversity Yves VANAUBEL Pascal MÉRINDOL Jean-Jacques PANSIOT Benoit DONNET Summary Motivations MPLS Background Measurement Campaign Label Pattern Recognition

More information

Network Virtualization Business Case

Network Virtualization Business Case SESSION ID: GPS2-R01 Network Virtualization Business Case Arup Deb virtual networking & security VMware NSBU adeb@vmware.com I. Data center security today Don t hate the player, hate the game - Ice T,

More information

Diagnosing Path Inflation of Mobile Client Traffic

Diagnosing Path Inflation of Mobile Client Traffic Diagnosing Path Inflation of Mobile Client Traffic Kyriakos Zarifis 1, Tobias Flach 1, Srikanth Nori 1, David Choffnes 2, Ramesh Govindan 1, Ethan Katz-Bassett 1, Z. Morley Mao 3, and Matt Welsh 4 1 University

More information

Mapping PoP-Level Connectivity of Large Content Providers

Mapping PoP-Level Connectivity of Large Content Providers Mapping PoP-Level Connectivity of Large Content Providers Amir Farzad Reza Rejaie ABSTRACT Large content providers (CPs) are responsible for a large fraction of injected traffic to the Internet. They maintain

More information

Measuring the IPv6 Internet by active DNS and HTTP measurements (work in progress)

Measuring the IPv6 Internet by active DNS and HTTP measurements (work in progress) Measuring the IPv6 Internet by active DNS and HTTP measurements (work in progress) emile.aben@ripe.net Early 21st centry http://www.ripe.net 1 The 2 Internets The IPv4 Internet The IPv6 Internet How are

More information

Open Connect Everywhere: A Glimpse at the Internet Ecosystem through the Lens of the Netflix CDN

Open Connect Everywhere: A Glimpse at the Internet Ecosystem through the Lens of the Netflix CDN Open Connect Everywhere: A Glimpse at the Internet Ecosystem through the Lens of the Netflix CDN Timm Böttger, Felix Cuadrado, Gareth Tyson, Ignacio Castro, Steve Uhlig steve.uhlig@qmul.ac.uk Queen Mary

More information