Akamai in Hyperconnected World
Filip Walkowicz – Site Leader & Senior Customer Care Manager
Paweł Kuśmierski – Senior Engi...
What’s Akamai?
 Founded at MIT in 1998 by prof. Tom Leighton and Danny Lewin
 Akamai has the world’s most distributed In...
Who do we serve?








The top 30 media & entertainment companies
All 20 top global eCommerce sites
7 of the top ...
Representative Customers
Adobe
All Nippon Airways (ANA)
Apple (1999)
AUDI
BMW
Department of Defense
Facebook
FedEx
L'Oréal...
Explosive Growth Online

2012

2020

More People 2.2 Billion1

5 Billion2

More
Devices

8 Billion3

50 Billion4

More Mon...
Trends of mobile devices usage voice/data

View on 2007- 2012 towards data usage
©2013 AKAMAI | FASTER FORWARDTM
Leveraging Key Megatrends

Media

Mobile

Cloud

More than 90% of
Internet traffic will
be video by 20151

10:1 devices pe...
10’000 feet view of Akamai

©2013 AKAMAI | FASTER FORWARDTM
Challenges with Cloud Adoption
Akamai Cloud Optimization
The User Always Connects to a Nearby Akamai Server
Akamai Edge Se...
Cloud Optimization: Route Selection
Cloud Datacenter

X

End User

X
Problem 1

Route to datacenter
may perform poorly

©2...
Cloud Optimization: Route Selection
Akamai Edge Servers
Cloud Datacenter

End User

X
Solution

Problem 1

Route to datace...
Akamai SureRoute Makes a Big Difference
Packet loss into India after MidEast cable cut

Packet Loss

50%
40%

30%
20%

10%...
Cloud Optimization: Communication Protocol
Akamai Edge Servers
Cloud Datacenter

End User

Problem 2

Solution

Akamai Com...
Attacks on Akamai Customers
600

• Typical Attack Size: 3-10 Gbps

500

• Attacks are originating from all
geographies and...
The Threat is Varied & Easier to Launch

Attack Methods

Malware
1%

74% of companies
experienced one or more
DDoS attacks...
Web Application With a Perimeter Defense

(Cloud)
Datacenters

End User
Origin
Traffic

Akamai
Traffic

10000

10000

1000...
July 4th – 7th 2009 DDoS Attack
400,000 Korean Bots Attack Key U.S. Government Web Sites

Peak Traffic

Times Above
Normal...
July 4th – 7th 2009 DDoS Attack
400,000 Korean Bots Attack Key U.S. Government Web Sites

Attack Size — Gbps

125

23:00 M...
Under the hood

©2013 AKAMAI | FASTER FORWARDTM
Akamai Platform
•
•
•
•
•
•
•

Various web infrastructure services
Over 150,000 machines
Over 1 million distributed compon...
Query
• Distributed data collection
• Aggregation at several hundred points
• SQL-style interface

©2013 AKAMAI | FASTER F...
A Sample Query
SELECT
c.continent_name,
SUM(l.hits) hits
FROM
load_info l,
region_data r,
continent_data c
WHERE
l.georegi...
Query at the Edge
• Each machine collects its own data
• Many processes may publish
• Snapshots every two minutes

©2013 A...
Cluster proxies
•
•

Collect data for the whole cluster
Include themselves

©2013 AKAMAI | FASTER FORWARDTM
Top-Level Aggregators
• Collect data for the whole network
• Snapshots every two minutes
• Static tables for data that doe...
SQL parsers
• Get tables from 1 TLA
• Only get the ones we need
• Answer queries based on
them

©2013 AKAMAI | FASTER FORW...
Aggregator Sets
• Span different parts of the network
• Designated for different purposes
• Several replicated TLAs & SQLs...
Scale
•
•
•
•

Several hundred TLAs, SQLs, TLA/SQLs
Thousands of queries per minute
Tens of GB in the system
Up to 16 GB p...
Download the Akamai
Internet Visualization
app in the Apple store

Result:

Result:

Result:

2-100X

2-100X

2-100X

comp...
Dziękujemy za uwagę

Filip Walkowicz, fwalkowi@akamai.com
Paweł Kuśmierski, pkusmier@akamai.com

©2013 AKAMAI | FASTER FOR...
Upcoming SlideShare
Loading in …5
×

Akamai in a hyperconnected world

621 views

Published on

Published in: Technology
  • Be the first to comment

  • Be the first to like this

Akamai in a hyperconnected world

  1. 1. Akamai in Hyperconnected World Filip Walkowicz – Site Leader & Senior Customer Care Manager Paweł Kuśmierski – Senior Engineer, Lead, System Operations Akamai Krakow Center of Excellence
  2. 2. What’s Akamai?  Founded at MIT in 1998 by prof. Tom Leighton and Danny Lewin  Akamai has the world’s most distributed Internet platform (over 150.000 servers, deployed in 81 countries)  The Akamai Intelligent Platform is leading cloud platform delivering up to 30% of the worldwide web traffic.  Accelerating Daily Traffic of:  10+ Tbps  20+ million hits per second  2+ trillion deliveries per day  30+ petabytes/day  10+ million concurrent streams ©2013 AKAMAI | FASTER FORWARDTM
  3. 3. Who do we serve?        The top 30 media & entertainment companies All 20 top global eCommerce sites 7 of the top 10 world banks 9 of the top 10 largest newspapers 9 out of 10 top social media sites 6 of the top 7 computer manufacturers All of the top anti-virus companies ©2013 AKAMAI | FASTER FORWARDTM
  4. 4. Representative Customers Adobe All Nippon Airways (ANA) Apple (1999) AUDI BMW Department of Defense Facebook FedEx L'Oréal Marks & Spencer MTV Networks MySpace Microsoft Netflix General Motors Harley-Davidson, Inc Hitachi IBM Intercontinental Hotels Group Qantas Airways Red Hat Inc. Research In Motion (RIM) Sony Computer Entertainment Sony Ericsson Mobile Communications Toyota Motor Sales TrendMicro Victoria's Secret Yahoo! ©2013 AKAMAI | FASTER FORWARDTM
  5. 5. Explosive Growth Online 2012 2020 More People 2.2 Billion1 5 Billion2 More Devices 8 Billion3 50 Billion4 More Money €600 Billion1 €2800 Billion2 Sources: (Global) 1 Internet World Stats 2 Akamai Estimates 3 IMS Research 4 Ericsson ©2013 AKAMAI | FASTER FORWARDTM
  6. 6. Trends of mobile devices usage voice/data View on 2007- 2012 towards data usage ©2013 AKAMAI | FASTER FORWARDTM
  7. 7. Leveraging Key Megatrends Media Mobile Cloud More than 90% of Internet traffic will be video by 20151 10:1 devices per internet user by 20202 One-third of all data will live in or pass through the cloud by 20201 Sources: 1-Cisco, 2-Akamai 3-IAB, 4-McAfee ©2013 AKAMAI | FASTER FORWARDTM Big Data 2.5 exabytes of data are created every day3 Security Cyber attacks cost companies up to $100,000/min4
  8. 8. 10’000 feet view of Akamai ©2013 AKAMAI | FASTER FORWARDTM
  9. 9. Challenges with Cloud Adoption Akamai Cloud Optimization The User Always Connects to a Nearby Akamai Server Akamai Edge Servers Cloud Datacenter End User Cloud servers reside in big data centers, farther away from the end user… ...resulting in decreased performance and security ©2013 AKAMAI | FASTER FORWARDTM
  10. 10. Cloud Optimization: Route Selection Cloud Datacenter X End User X Problem 1 Route to datacenter may perform poorly ©2013 AKAMAI | FASTER FORWARDTM
  11. 11. Cloud Optimization: Route Selection Akamai Edge Servers Cloud Datacenter End User X Solution Problem 1 Route to datacenter may perform poorly Akamai SureRoute to optimize route ©2013 AKAMAI | FASTER FORWARDTM
  12. 12. Akamai SureRoute Makes a Big Difference Packet loss into India after MidEast cable cut Packet Loss 50% 40% 30% 20% 10% 0% Generic Internet ©2013 AKAMAI | FASTER FORWARDTM Akamai
  13. 13. Cloud Optimization: Communication Protocol Akamai Edge Servers Cloud Datacenter End User Problem 2 Solution Akamai Communication Protocol Many round trips for initial large download ©2013 AKAMAI | FASTER FORWARDTM
  14. 14. Attacks on Akamai Customers 600 • Typical Attack Size: 3-10 Gbps 500 • Attacks are originating from all geographies and are moving between geographies during the attack Number of Attacks • Large Attack Size: 100-200 Gbps 400 300 200 100 0 2009 ©2013 AKAMAI | FASTER FORWARDTM 2010 2011
  15. 15. The Threat is Varied & Easier to Launch Attack Methods Malware 1% 74% of companies experienced one or more DDoS attacks in the past year. 31% of these attacks resulted in service disruption. New attack tools such as Low Orbit Ion Cannon Users download the tool, insert the target URL or IP and press GO! Insufficient Authentication 1% DNS Hijacking 1% Abuse of Functionality 1% Content Spoofing 1% OS Commanding 1% Unknown 10% Denial of Service (DoS) 32% Predictable Resource Location 1% Banking Trojan 1% Stolen Credentials 1% Misconfiguration 3% Known Vulnerability 4% Process Automation 4% Cross-Site Request Forgery (CSRF) 4% Brute Force 4% Cross-Site Scripting (XSS) 9% SQL Injection (SQLi) 21% Source: TrustWave - 2010 - Web Hacking Incident Database ©2013 AKAMAI | FASTER FORWARDTM
  16. 16. Web Application With a Perimeter Defense (Cloud) Datacenters End User Origin Traffic Akamai Traffic 10000 10000 1000 1000 100 100 10 10 1 1 COVERED ©2013 AKAMAI | FASTER FORWARDTM
  17. 17. July 4th – 7th 2009 DDoS Attack 400,000 Korean Bots Attack Key U.S. Government Web Sites Peak Traffic Times Above Normal Traffic U.S. Government Customer 1 124 Gbps 598x U.S. Government Customer 2 32 Gbps 369x U.S. Government Customer 3 9 Gbps 39x U.S. Government Customer 4 9 Gbps 19x U.S. Government Customer 5 2 Gbps 9x U.S. Government Customer 6 1.9 Gbps 6x Customer – PROTECTED ©2013 AKAMAI | FASTER FORWARDTM
  18. 18. July 4th – 7th 2009 DDoS Attack 400,000 Korean Bots Attack Key U.S. Government Web Sites Attack Size — Gbps 125 23:00 Mitigation measures engaged 100 July 5, 2009 Unique IPs Spike 1 21:00 Akamai identifies sources 75 20:00 Attack grows rapidly 50 16:00 Customer notified 25 0:00 23:50 Peak pageviews Spike 2 08:00 16:00 0:00 ©2013 AKAMAI | FASTER FORWARDTM 08:00 16:00 Spike 3
  19. 19. Under the hood ©2013 AKAMAI | FASTER FORWARDTM
  20. 20. Akamai Platform • • • • • • • Various web infrastructure services Over 150,000 machines Over 1 million distributed components Over 1000 autonomous systems 24/7/365 operation Failures, usage changes Massive, real-time monitoring ©2013 AKAMAI | FASTER FORWARDTM
  21. 21. Query • Distributed data collection • Aggregation at several hundred points • SQL-style interface ©2013 AKAMAI | FASTER FORWARDTM
  22. 22. A Sample Query SELECT c.continent_name, SUM(l.hits) hits FROM load_info l, region_data r, continent_data c WHERE l.georegion=r.id AND r.continent=c.continent GROUP BY c.continent_name ORDER BY hits DESC; c.continent_name hits ---------------- --------North America 4,620,551 Europe 3,392,102 South America 655,175 Asia 552,258 Africa 106,781 Oceania 39,905 Antarctica 135 ©2013 AKAMAI | FASTER FORWARDTM
  23. 23. Query at the Edge • Each machine collects its own data • Many processes may publish • Snapshots every two minutes ©2013 AKAMAI | FASTER FORWARDTM
  24. 24. Cluster proxies • • Collect data for the whole cluster Include themselves ©2013 AKAMAI | FASTER FORWARDTM
  25. 25. Top-Level Aggregators • Collect data for the whole network • Snapshots every two minutes • Static tables for data that doesn’t change much ©2013 AKAMAI | FASTER FORWARDTM
  26. 26. SQL parsers • Get tables from 1 TLA • Only get the ones we need • Answer queries based on them ©2013 AKAMAI | FASTER FORWARDTM
  27. 27. Aggregator Sets • Span different parts of the network • Designated for different purposes • Several replicated TLAs & SQLs • Combined TLA/SQLs • Shared hostnames • Help meet reliability guarantees • Help tolerate faults & keep localized ©2013 AKAMAI | FASTER FORWARDTM
  28. 28. Scale • • • • Several hundred TLAs, SQLs, TLA/SQLs Thousands of queries per minute Tens of GB in the system Up to 16 GB per TLA (and growing fast) • • • • • Internet usage Network growth Customer growth Data/customer More queries • Age of data typically a few minutes ©2013 AKAMAI | FASTER FORWARDTM
  29. 29. Download the Akamai Internet Visualization app in the Apple store Result: Result: Result: 2-100X 2-100X 2-100X compression compression compression ©2013 AKAMAI | FASTER FORWARDTM
  30. 30. Dziękujemy za uwagę Filip Walkowicz, fwalkowi@akamai.com Paweł Kuśmierski, pkusmier@akamai.com ©2013 AKAMAI | FASTER FORWARDTM

×