2. How much digital data are
we creating every second?
www.symform.com
3. It’s all about the data
➡58 Gigabytes of data
created every second
➡35 Zettabytes of digitally
stored data by 2020
➡ That’s enough data to fill a
stack of DVDs reaching
from the Earth to the
moon and back — about
240,000 miles each way.
33
5. Only one problem
Cloud is powered by massive centralized
infrastructure
5
6. Cloud driving massive data center build out
Over 500,000 data
centers worldwide
covering 290m sqft or
6,000 football fields
66
7. What percentage of North
American energy consumption do
those data centers account for?
www.symform.com
8. Issues with over centralization
➡ Have to build for peak usage; excess capacity lying idle
➡ Power consumption issues
• 2% of North American energy consumption goes to servers and data
centers
• 2% of global carbon footprint is data centers used to power cloud
computing
• Google uses 260 million watts continuously across the globe --
equivalent to the power used by all the homes and businesses in a city of
200,000 people.
➡ Energy grid management
➡ Potential security and physical vulnerabilities (e.g. fire)
➡ Costs - data centers are expensive to build and maintain
➡ Bandwidth bottlenecks
8 8
10. Good news . . .
The Internet is already highly distributed
Internet Users by Country
Billions of devices sitting on the edge
Data distributed across devices,
10
networks, data centers, and geos
11. You are already using distributed systems
Cloud Computing is driving distributed models:
➡ Multi-tenant architecture
➡ Distributed database
➡ Virtualization
➡ Multi-threading
➡ Multi-core CPUs
➡ Parallel processing
➡ Distributed file systems
➡ Distributed Load Balancing
➡ RAID algorithms
11
12. And we’re realizing benefits
➡ System or process optimization
➡ Improved performance - faster
➡ Increased reliability & fault tolerance
➡ Lower costs
➡ Increased efficiencies
➡ Easier scalability or expansion
➡ Continuous or near continuous operations
12
12
13. What’s the largest distributed &
decentralized system
in the world?
www.symform.com
14. Distributed alone is not enough . . .
Distributed only will not keep up with our data growth
Still heavily
based on
centralized
models with
distributed
components
14
15. Need to go beyond distributed to decentralized
Why?
Unused instances
Over provisioning
Under use of reserved instances
Orphaned services
Millions of dollars invested and wasted
Contributing source: Mat Ellis
15
16. How to think about Decentralization
➡ No central hub or owner
➡ Power of large numbers
➡ Organic, demand driven growth in capacity
➡ Leverages existing infrastructure and devices on edge
➡ Shared information
➡ Concept of ―Contribution‖ to the community
➡ Assume everyone / every node is ―untrusted‖
➡ Geographic spread of:
• Ownership & participation
• Costs
• Management overhead
• Risks
16 16
17. Good news . . .
There are good
examples of
decentralization
today
17 17
18. Do you have an example of
a decentralized system?
www.symform.com
19. Decentralized Development
Open Source Movement
Programmers who support the
➡ Linux – a Unix-Based operating system open source movement philosophy
contribute to the open
➡ Apache — a leading server software and
scripting language on the web source community by voluntarily
writing and exchanging
➡ MySQL — a database management system
programming code for software
➡ PHP — a widely used open source general- development.
purpose scripting language
➡ Blender — a 3D graphics and animation
software
➡ OpenOffice.org – an office suite software
with word processor, spreadsheet, and
presentation capabilities
➡ Mozilla — a web browser and e-mail client
➡ Perl — a programming/scripting language
➡ Wikipedia — Online encyclopedia open for
anyone to update and revise content
19 19
20. Decentralized Communications
Skype is the largest telephone
company in the world but has
almost no centralized infrastructure
20
21. Decentralized Processing
Search for
extraterrestrial
intelligence (SETI)
World
Community
Grid
21
22. Decentralized Cloud Storage
What if we aggregated all the unused capacity across servers,
desktops and storage devices on the edge of the Internet to build a
global storage network?
22
23. Decentralized IT budgets
Alas . . . Also already here
➡ CMOs often have as much IT purchasing power as CIOs
➡ Employees are buying rogue platforms, applications and devices
23 23
24. Whoa! . . . ―This is chaos for enterprise IT‖
24 24
25. Doesn’t mean loss of centralized control or IT power
What Stays Centralized?
➡ IT Policy and governance
➡ Security and compliance mandates
➡ Definition of ―trust‖
➡ API management
➡ Shared services (SOA)
➡ Vendor evaluation guidelines
➡ Data analysis aggregation (search, e-discovery & reporting)
25 25
26. We are still in early stages
Issues with decentralization
➡ Desire for Control
➡ Geo-political differences
➡ Random expertise
➡ Data security and encryption
➡ Integration
➡ Need more open API’s
➡ Consistent Quality of Service
26 26
28. We still need data centers
Data centers are ideal for:
➡ High volume, low latency
transactions
➡ Data warehousing
➡ Search
28 28
29. But we can look for opportunities
To Leverage Distributed & Decentralized Models
➡ Assumption of ―untrusted‖ should be your security
principle today
➡ Worry less about where the data is and on how to control
access
➡ Be the source of centralized policy and governance
29
33. Thank You
margaret@symform.com
praerit@symform.com
CloudNOW Cloud Connect
Advisory Council Advisory Council
www.symform.com
Editor's Notes
Do we have enough data centers to fit? Can we build them fast enough to stay ahead of demand?Simple back of the envelope math shows the problem. If we were to store the 0.8 ZB of storage today in Google (assuming their 1M servers) we would need a 160 Google’s. In 2015, Google will obviously grow, but even if they quadrupled we would need 450 Google’s.This approach is just not sustainable.
Reduce function: Chopping something into pieces: data, processes, applicationsDistribution function: Spreading those pieces across multiple systemsResource sharingParallel executions