More Related Content Similar to There are 250 Database products, are you running the right one? (20) There are 250 Database products, are you running the right one?1. © 2015 Aerospike. All rights reserved. Confidential 1
Webinar:
There are 250+ database products,
are you running the right one?
SPEED at SCALE
Featuring:
2. © 2015 Aerospike. All rights reserved. Confidential 2
Featured Speakers
Noel Yuhanna, Principal Analyst,
Forrester
Peter Goldmacher, VP of Strategy,
Aerospike
Alvin Richards, VP of Product,
Aerospike
3. © 2015 Aerospike. All rights reserved. Confidential 3
Agenda
• Industry overview and trends
• Choosing the right database
• Evolution of Data
• Real world use cases where speed at scale matters
• Architecture Overview
• Wrap up and Q&A
5. Business growth and speed are
driving new apps and data
requirements that are changing
the way we store, process, and
access data.
6. © 2015, Forrester Research, Inc. .
Data Volume has grown out of control…..
What about your organization?
How are you managing your data?
Terabytes
Petabytes Zetabytes
7. © 2015 Forrester Research, Inc. Reproduction Prohibited 7
Database management challenges have grown
DB
DB
DB
DB
DB
DBDB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DBDB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DBDB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DBDB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB DB
DB
DB
DB
DB
DB
DB
DB DB
DB
DB
DB
DB
DB
DB
DBDB
DB
DB
DB
DB
DB
DB
DB
DBDB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DBDB
DB
DBDB
DB
DB
DB
DB
DB
DB
DB
DB
DB
DB
So many physical database instances!
So many heterogeneous database technologies, architectures, models, and schemas!
So many database applications, workloads, deployment roles, and content types!
So many database policies, rules, and SLAs!
How do we
architect all this?
How do we
implement this?
How do we scale
and optimize all
this?
What database
do we need?
HELP!!!!!!!
DBAs
8. © 2015 Forrester Research, Inc. Reproduction Prohibited 8
DB
Analytics
DB
OLTP
DB
IOT
DB
Mobile
100%
CPU
50%
100%
CPU
50%
100%
CPU
50%
100%
CPU
50%
DB
DB DB
DB
DB
DB
DB
DB DB
DB
DB
DB
When you use the wrong DBMS.. You waste
resources, increase cost and slow down new
application deployment…
9. Data management
• Growing data volume
• Need for real-time information
• Security concerns
• Growing complexity of systems
• Increased HA requirements
• Underutilized servers and
storage
• Drive toward enhanced SLAs
Distributed data management
• Integration issues
• Administration
• Data duplication
• Security concerns
• Performance and scalability
• Synchronizing repositories
• Content, unstructured data
Data management pain points intensify . . .
10. © 2013 Forrester Research, Inc. Reproduction Prohibited 10
Four key trends that are impacting
database strategy
Social network apps
Real-time apps
LOB apps
Big data apps
Mobile apps
Collaboration
TBs into TBs
Larger EDW
Unstructured data
Admin challenges
Performance issues
Scale — unpredictable workload
Budget concern remains.
Doing more with less
Automation is the key.
Need for optimized
system
Subscription model
Ensure security.
Need for 24x7 availability
Deliver high performance.
Ensure on-demand scale.
Minimize planned downtime.
Next-
generation
apps
Budget
issues
Data
volume,
variety,
velocity
Global
apps
Database
© 2015 Forrester Research, Inc. Reproduction Prohibited.
11. © 2015 Forrester Research, Inc. Reproduction Prohibited 11
New business requirements are making older
database approaches inadequate…
› Business challenges:
• Need for real-time data has grown
• Delivering solutions more quickly
• Delivering more scalable solution
• Ensuring cost effectiveness
› Technology challenges:
• Increasing data volume
• Ensuring 24x7 global availability
• Increasing number of users
12. © 2014, Forrester Research, Inc. .
New business applications demand more
optimized databases…
Age of the Customer – personalization
IOT – machine analysis, proactive maintenance
Real-time Analytics
360-degree view of the business, product
Global transactional Apps
Gaming – scores, ratings, store
Fraud Detection – risk management, online trading
Mobile Apps – Hotel reservations, inventory tracking
And others…
13. © 2013 Forrester Research, Inc. Reproduction Prohibited 13
Age of the customer is driving the need for
integrated customer data…
› Age of the customer — a 20-year business cycle in which
the most successful enterprises will reinvent themselves
to systematically understand and serve increasingly
powerful customers
© 2015, Forrester Research, Inc. .
15. How can you provide a perfect and
individual recommendation?
Individual
Recommendation
16. © 2014 Forrester Research, Inc. Reproduction Prohibited 16
Engines
Machines Factories
IOT drives new types of use cases but
requires a real-time data platform
Cisco predicts 50 billion
devices will be connected
by 2020.
Forrester estimates 30%
usage of IIOT in
manufacturing, will double
by 2019.
IOT
© 2015 Forrester Research, Inc.
17. © 2013 Forrester Research, Inc. Reproduction Prohibited 17
Amazon uses data to predict everything in
its delivery process.. even Xmas orders!
Image source: Digits (http://blogs.wsj.com/digits/2014/01/17/amazon-wants-to-ship-your-package-before-you-buy-it/)
Prediction
18. © 2013 Forrester Research, Inc. Reproduction Prohibited 18
We are gaining a deeper view of the
world by digitizing everything . . .
Image source: Github (http://seeread.github.com/canopy/)
DATA SCIENTISTS PARTICIPATED IN A DATA DIVE TO HELP THE NYC PARKS
DEPARTMENT BETTER MANAGE STORM RISK AND OPTIMIZE PRUNING
SCHEDULES OF THE CITY’S TREES
Advanced Analytics
19. Supermarket predicts the exact date
customers will return and what they will spend
within $10 for 19% of their customers?
Complex
Prediction
20. © 2015 Forrester Research, Inc. Reproduction Prohibited 20
What does this mean? Your Database strategy
needs to include NoSQL besides RDBMS
New App Requirements NoSQL RDBMS
Optimized for unstructured data Yes Partial
Scale to petabytes Yes Partial
Millions of users Yes Partial
Complex data relationships Yes Partial
Flexible schema Yes No
Extreme performance Yes No
Easy to deploy and use Yes Partial
Lower Cost Yes No/Partial
Horizontal scale-out Yes No
22. © 2015 Aerospike. All rights reserved. Confidential 22
Evolution of Data
&
Architecture Overview
Peter Goldmacher, VP of Strategy
Alvin Richards, VP of Product
SPEED at SCALE
23. © 2015 Aerospike. All rights reserved. Confidential 23
Evolution of Data
DATA VOLUME
1970
1985
2010
2015
IMS
RDBMS
NoSQL
NoSQL
at Scale
TPS
24. © 2015 Aerospike. All rights reserved. Confidential 24
Our Users Have the Following Requirements
Mission critical apps that require near 100% up-time
AdTech
Risk/Fraud
Telco
Mandate for response times measured in milliseconds
10 milliseconds for AdTech
750 milliseconds for Fraud
Very large data sets
50TB+
Sophisticated and robust decision algorithms
2M+ transactions per second
Best in class price/performance
Proven 10 to 1 savings versus other NoSQL vendors
25. © 2015 Aerospike. All rights reserved. Confidential 25
AdTech – Real-Time Bidding
Challenge
• Low read latency (milliseconds)
• 100K to 5M operations/second
• Ensure 100% uptime
• Provide global data replication
Performance achieved
• 1 to 6 billion cookies tracked
• 5.0M auctions per second
• 100ms ad rendering, 50ms real-time bidding,
1ms database access
• 1.5KB median object size
Selected Aerospike NoSQL over competition
• 10X fewer nodes
• 10X better TCO
• 20X better read latency
• High throughput at low latency
Ads is Displayed
Publishers
Ad Networks & SSPs
Ad Exchanges
Demand Side
Platform
Data Management
Platforms
Brands Agencies Buyers
0 ms 100 ms
26. © 2015 Aerospike. All rights reserved. Confidential 26
Challenge
• Overall SLA 750 ms
• Loss of business due to latency
• Every credit card transaction requires
hundreds of DB reads/writes
Need to Scale Reliably
• 10 100 TB
• 10B 100 B objects
• 200k I Million+ TPS
Selected Aerospike In-Memory NoSQL
• Built for Flash
• Predictable low latency at high throughput
• Immediate consistency, no data loss
• Cross data center (XDR) support
• 20 server cluster
• Dell 730xd w/ 4NVMe SSDs
Credit Card Processing System
Fraud Detection & Protection App
Rules
Rule 1
Rule 2
Rule 3
Historical Data
Rule 1-Passed
Rule 2-Passed
Rule 3-Failed
Account Behavior
Static Data
Account Statistics
Fraud Prevention
27. © 2015 Aerospike. All rights reserved. Confidential 27
Telco – Real-Time Billing and Usage Systems
Challenge
• Edge access to regulate traffic
• Accessible using provisioning applications
(self-serve and through support personnel)
Need for extremely high availability,
reliably, low latency
• > TBs of data
• 10-100M objects
• 10-200K TPS
Selected Aerospike in-Memory NoSQL
• Clustered system
• Predictable low latency at high throughput
• Highly-available and reliable on failure
• Cross data center (XDR) support
SOURCE
DEVICE/USER DESTINATIONReal-Time
Auth. QoS Billing
Request Execute
Request
Real-Time ChecksConfig Module App
Update Device
User Setting
Hot-Standby
XDR
28. © 2015 Aerospike. All rights reserved. Confidential 28
Speed
0
50,000
100,000
150,000
200,000
250,000
300,000
350,000
Balanced Read-Heavy
Aerospike Cassandra
MongoDB Couchbase 2.0*
0
2.5
5
7.5
10
0 50,000 100,000 150,000 200,000
AverageLatency,ms
Throughput, ops/sec
Balanced Workload Read Latency
Aerospike
Cassandra
MongoDB
0
4
8
12
16
0 50,000 100,000 150,000 200,000
AverageLatency,ms
Throughput, ops/sec
Balanced Workload Update Latency
Aerospike
Cassandra
MongoDB
• Flash / SSD Optimized
• Primary Index in DRAM
29. © 2015 Aerospike. All rights reserved. Confidential 29
Scale
• RIPE MD160 Hashing & Partitioning
• Dynamically Add/Remove Nodes
• Auto Rebalance
• Auto Heal
31. © 2015 Aerospike. All rights reserved. Confidential 31
Vertical Focus / Horizontal Opportunity
FINANCIAL
ECOMMERCE
ADTECH
HORIZONTAL
GAMING
TELECOM
Confidential #1
Confidential #2
32. © 2015 Aerospike. All rights reserved. Confidential 32
Takeaways
• Focused on real-time, mission critical applications
• Enables companies to leverage speed at scale
• Scales up and out to accelerate real-time applications
in Retail, FinServ, Telecom, Adtech and Internet
• Greater than 10x performance improvements at a
materially lower cost per transaction
33. © 2015 Aerospike. All rights reserved. Confidential 33
High Performance
NoSQL Database
Powering New
Opportunities at Scale
@aerospikedb
NEXT STEPS:
See how much you can save with Aerospike:
http://www.aerospike.com/tco-calculator/
Ready to get started?
http://www.aerospike.com/quick-start/
If you have any questions or want to further
explore if Aerospike is right for you, contact
us:
info@aerospike.com