Distributed Systems 19. Content Delivery Networks (CDN) Paul Krzyzanowski pxk@cs.rutgers.edu

Similar documents
Distributed Systems. 24. Content Delivery Networks (CDN) 2013 Paul Krzyzanowski. Rutgers University. Fall 2013

Distributed Systems. 23. Content Delivery Networks (CDN) Paul Krzyzanowski. Rutgers University. Fall 2015

Distributed Systems. 25. Content Delivery Networks (CDN) 2014 Paul Krzyzanowski. Rutgers University. Fall 2014

Web Caching and CDNs. Aditya Akella

Measuring the Web: Part I - - Content Delivery Networks. Prof. Anja Feldmann, Ph.D. Dr. Ramin Khalili Georgios Smaragdakis, PhD

Indirection. science can be solved by adding another level of indirection" -- Butler Lampson. "Every problem in computer

How To Understand The Power Of A Content Delivery Network (Cdn)

DATA COMMUNICATOIN NETWORKING

Content Distribu-on Networks (CDNs)

DNS, CDNs Weds March Lecture 13. What is the relationship between a domain name (e.g., youtube.com) and an IP address?

Getting Started with AWS. Hosting a Static Website

CSC2231: Akamai. Stefan Saroiu Department of Computer Science University of Toronto

Internet Content Distribution

ICP. Cache Hierarchies. Squid. Squid Cache ICP Use. Squid. Squid

Content Delivery Networks. Shaxun Chen April 21, 2009

Content Delivery Networks (CDN) Dr. Yingwu Zhu

COMP 631: COMPUTER NETWORKS. How to distribute content without requiring centralized, heavy-duty servers? Peer-to-peer content distribution

Overview. Tor Circuit Setup (1) Tor Anonymity Network

Lecture 3: Scaling by Load Balancing 1. Comments on reviews i. 2. Topic 1: Scalability a. QUESTION: What are problems? i. These papers look at

1. Comments on reviews a. Need to avoid just summarizing web page asks you for:

CDN and Traffic-structure

Comparative Performance Report

Demand Routing in Network Layer for Load Balancing in Content Delivery Networks

Analysing the impact of CDN based service delivery on traffic engineering

Getting Started with AWS. Hosting a Static Website

CSCI-1680 CDN & P2P Chen Avin

Content Delivery Networks

THE MASTER LIST OF DNS TERMINOLOGY. v 2.0

Overlay Networks. Slides adopted from Prof. Böszörményi, Distributed Systems, Summer 2004.

Dynamic Content Acceleration: Lightning-Fast Web Apps with Amazon CloudFront and Amazon Route 53

John S. Otto Fabián E. Bustamante

EE 7376: Introduction to Computer Networks. Homework #3: Network Security, , Web, DNS, and Network Management. Maximum Points: 60

How To Model The Content Delivery Network (Cdn) From A Content Bridge To A Cloud (Cloud)

Cisco Videoscape Distribution Suite Service Broker

Making the Internet fast, reliable and secure. DE-CIX Customer Summit Steven Schecter <schecter@akamai.com>

How To Understand The Power Of Icdn

From Internet Data Centers to Data Centers in the Cloud

Getting Started with AWS. Static Website Hosting

ExamPDF. Higher Quality,Better service!

Creating "Origin Pull" on Akamai (1)

Distributed Systems. 09. Naming. Paul Krzyzanowski. Rutgers University. Fall 2015

High volume Internet data centers. MPLS-based Request Routing. Current dispatcher technology. MPLS-based architecture

Content Delivery Network. Version 0.95

Amazon Web Services Yu Xiao

LAN TCP/IP and DHCP Setup

Rapid IP redirection with SDN and NFV. Jeffrey Lai, Qiang Fu, Tim Moors December 9, 2015

Request Routing, Load-Balancing and Fault- Tolerance Solution - MediaDNS

The old Internet. Software in the Network: Outline. Traditional Design. 1) Basic Caching. The Arrival of Software (in the network)

THE MASTER LIST OF DNS TERMINOLOGY. First Edition

BGP and Traffic Engineering with Akamai. Christian Kaufmann Akamai Technologies MENOG 14

Wikimedia Architecture Doing More With Less. Asher Feldman Ryan Lane Wikimedia Foundation Inc.

Dynamic Load Balancing and Node Migration in a Continuous Media Network

Department of Computer Science Institute for System Architecture, Chair for Computer Networks. Caching, Content Distribution and Load Balancing

The importance of Drupal Cache. Luis F. Ribeiro Ci&T Inc. 2013

Fundamentals of Windows Server 2008 Network and Applications Infrastructure

The Effectiveness of Request Redirection on CDN Robustness

Data Center Content Delivery Network

BGP and Traffic Engineering with Akamai. Caglar Dabanoglu Akamai Technologies AfPIF 2015, Maputo, August 25th

Web Application Deployment in the Cloud Using Amazon Web Services From Infancy to Maturity

CONTENT DELIVERY WHITE PAPER proinity GmbH 1

Demystifying CDNs: Building Video Enabled Networks That Maintain Your Network Integrity And Meet User Demand

Carnegie Mellon Computer Science Department Spring 2007 Theory Problem Set 2

Transport and Network Layer

Chapter 4: Networking and the Internet

high-quality steaming over the Internet

Global Server Load Balancing

IP addressing and forwarding Network layer

Load Balancing and Sessions. C. Kopparapu, Load Balancing Servers, Firewalls and Caches. Wiley, 2002.

Web Application Hosting Cloud Architecture

The Effect of Caches for Mobile Broadband Internet Access

Savvius Insight Initial Configuration

Essential Ingredients for Optimizing End User Experience Monitoring

CS101 Lecture 19: Internetworking. What You ll Learn Today

Learning Management Redefined. Acadox Infrastructure & Architecture

A Taxonomy of CDNs. Chapter Introduction. Mukaddim Pathan and Rajkumar Buyya

The Value of Content Distribution Networks Mike Axelrod, Google Google Public

The Application Front End Understanding Next-Generation Load Balancing Appliances

Azure Media Service Cloud Video Delivery KILROY HUGHES MICROSOFT AZURE MEDIA

Introduction to Network Operating Systems

How Comcast Built An Open Source Content Delivery Network National Engineering & Technical Operations

Peer-to-Peer Networks. Chapter 6: P2P Content Distribution

Deliuery Networks. A Practical Guide to Content. Gilbert Held. Second Edition. CRC Press. Taylor & Francis Group

The Domain Name System

Claudio Jeker. RIPE 41 Meeting Amsterdam, 15. January Using BGP topology information for DNS RR sorting

Transcription:

Distributed Systems 19. Content Delivery Networks (CDN) Paul Krzyzanowski pxk@cs.rutgers.edu 1

Motivation Serving web content from one location presents problems Scalability Reliability Performance Flash crowd problem What if everyone comes to you at once? Cache content and serve requests from multiple servers at the network edge (close to the user) Reduce demand on site s infrastructure Provide faster service to users Content comes from nearby servers 2

Focus on Content Computing is still done by the site host s server(s) Offload the static parts Images Video CSS files Static pages 3

Serving & Consuming Web server Internet 4

Caching Proxy Caching Proxy Caching Proxies Web server Internet 5

Load Balancer Load Balancing Web server Web server Web server Internet 6

Internet End-to-End Packet Delivery Network edge: applications & hosts Web server Local ISP Tier 2 ISP Tier 1 ISP Tier 1 ISP Local ISP Tier 2 ISP Network core: routers 7

Multihoming Get links from multiple ISPs 1 IP address but multiple links Announce address to upstream routers via BGP Local ISP Web server Tier 2 ISP Tier 1 ISP Tier 1 ISP Local ISP Tier 2 ISP 8

copy Mirroring Synchronize multiple servers Web server Local ISP Tier 2 ISP Tier 1 ISP Tier 1 ISP Web server Local ISP Tier 2 ISP 9

Improving scalability, availability, & performance Scalability Load balance among multiple servers Multiple ISPs if network congestion is a concern Availability Replicate servers Multiple data centers & ISPs Performance Replicate servers for load balancing Cache content and serve requests from multiple servers at the network edge (close to the user) Reduce demand on site s infrastructure Provide faster service to users Content comes from nearby servers 10

Akamai Distributed Caching Company evolved from MIT research "Invent a better way to deliver Internet content" Tackle the "flash crowd" problem Akamai runs on 95,000 servers in 1,900 networks across 71 countries 11

Traditional approaches to web scaling Local balancing Data center or ISP can fail Multihoming IP protocols (BGP) are often not quick to find new routes Mirroring at multiple sites Synchronization can be difficult Proxy servers Typically a client-side solution Low cache hit rates All require extra capacity and extra capital costs 12

Akamai s goal Akamai tries to serve clients from servers likely to have the content Nearest: lowest round-trip time Available: server that is not too loaded Likely: server that is likely to have the data 13

Akamai Mapping Akamai does this via Dynamic DNS Customer modifies URLs (akamizes) Direct requests to the right content servers Resolve a host name based on: service requested (e.g., QuickTime, HTML, Windows Media) content requested (is server likely to have it? based on hash) server health server load user location network status load balancing 14

DNS Servers Remember how DNS queries work? Referrals & caching Set short cache time Client DNS queries will get referred to Akamai DNS servers 15

DNS Resolution Resolve a7.g.akamai.net NS resolver contacts root server Root server sends a referral to a name server responsible for.net Resolver queries.net name server Returns a referral for.akamai.net This is the top-level Akamai server Resolver queries a top-level Akamai server Returns a referral for.g.akamai.net Low-level Akamai server (TTL approx 1 hour) Low-level servers are in the same location as edge servers closest to user Resolver queries a low-level Akamai server Returns IP addresses of servers available to satisfy the request Short TTL (several seconds to 1 minute) 16

Akamai needs data to do this Map network topology Based on BGP and traceroute information Estimate hops and transit time Content servers report their load to a monitoring application Monitoring app publishes load reports to a local DNS server DNS server determines which IP addresses to return when resolving names Load shedding: If servers get too loaded, the DNS server will not respond with those addresses 17

Populating the cache If an Akamai server does not have the content Get it from another Akamai server Or get it from the site 18

Types of content Static content Cached depending on original site's requirements (never to forever) Dynamic content Caching proxies cannot do this Akamai uses Edge Side Includes technology (www.esi.org) Assembles dynamic content on edge servers Similar to server-side includes Page is broken into fragments with independent caching properties Assembled on demand Streaming media Live stream is sent to an entry-point server in the Akamai network Stream is delivered from the entry-point server to multiple edge servers Edge servers serve content to end users. 19

Other Things CDNs Do 20

Signed URLs Example: Amazon CloudFront Control access to content via a signed URL URL contains: policy or a reference to a policy Signature = encrypted hash URL cannot be modified Policies include: Validity: start time & expiration time Range of IP addresses that are allowed to access the object 21

LimeLight Reach Video Universal URL Publish Web site Transcoder Content server Content server Content server f(player, device, encoding parameters) 22

Server-side Video Ad Insertion Example, Limelight Reach Ads Ad Server Ad selection Ad call Web site Ad insertion Request context CDN Media with ad Request content 23

The End 24