Overcoming
Barriers of Scaling
Your Database
+ I currently use ScyllaDB
+ I currently use another NoSQL database
+ I am currently evaluating NoSQL
+ I am interested in learning more about ScyllaDB
+ None of the above
Where are you in your NoSQL database adoption?
Poll Question
2
Peter Corless
+ Listen to customer stories
+ Write blogs & case studies
+ Play (and design) strategy &
roleplaying games
3
Director of Technical Advocacy ScyllaDB
Tomer Sandler
4
+ Lifecycle support: from deployment
to operations
+ Troubleshoots toughest real-time
technical issues
+ Plays a mean saxophone
Head of Customer Success ScyllaDB
5
+ For distributed, data-intensive apps that require high
performance and low latency
+ 400+ users worldwide
+ Results
+ Comcast: Reduced P99 latencies by 95%
+ FireEye: 1500% improvement in throughput
+ Discord: Reduced C* nodes from ~140 to 6
+ iFood: 9X cost reduction vs. DynamoDB
+ Open Source, Enterprise and Cloud options
+ Fully compatible with Apache Cassandra and Amazon
DynamoDB
About ScyllaDB
1ms <1ms
10ms
1M
10M
ScyllaDB Universe of 400+ Users
400+ Companies Use ScyllaDB
Seamless experiences
across content + devices
Fast computation of flight
pricing
Corporate fleet
management
Real-time analytics
2,000,000 SKU -commerce
management
Real-time location tracking
for friends/family
Video recommendation
management
IoT for industrial
machines
Synchronize browser
properties for millions
Threat intelligence service
using JanusGraph
Real time fraud detection
across 6M
transactions/day
Uber scale, mission critical
chat & messaging app
6
Network security threat
detection
Power ~50M X1 DVRs with
billions of reqs/day
Precision healthcare via
Edison AI
Inventory hub for retail
operations
Property listings and
updates
Unified ML feature store
across the business
Cryptocurrency exchange
app
Geography-based
recommendations
Distributed storage for
distributed ledger tech
Global operations- Avon,
Body Shop + more
Predictable performance
for on sale surges
GPS-based exercise
tracking
7
https://www.scylladb.com/summit/
Register Now >
8
How does a company know when
they’ve hit the wall?
Q1:
9
What about throughput limits?
What’s different if you added
more workloads vs. bursty time-
of-day traffic?
Q2:
10
Even with the best up-front
planning you can run into a
stochastic event that can go
beyond your predictive planning?
What then?
Q3:
11
Let’s define “emergency
scalability” as responding to
unplanned demands on your
system. What examples have you
seen of “emergency scaling”
limits in the wild?
Q4:
12
What’s different doing
“emergency scaling” with an on-
premises deployment vs.
a public cloud?
Q5:
13
14
+ <1 terabyte
+ 1 to 50 terabytes
+ 50-100 terabytes
+ >100 terabytes
How much data do you have under management in your own
transactional database systems?
Poll Question
Is the cloud really is just
“someone else’s computer?”
Q6:
15
Is data volume itself a barrier to
scale? “I want a petabyte of
storage fully loaded by 8 AM
tomorrow!”
Q7:
16
What are other real-time limits
you can’t avoid? Like the latency
of the speed of light, or the raw
time to actually stream your data
to the new hardware?
Q8:
17
Can you talk more about latency
issues? You can’t just throw
hardware at it. Because that
could even make latencies
worse.
Q9:
18
What advice can you give to
system architects planning for
data at scale?
Q10:
19
United States
2445 Faber St, Suite #200
Palo Alto, CA USA 94303
Israel
Maskit 4
Herzliya, Israel 4673304
www.scylladb.com
@scylladb
Learn NoSQL for free! university.scylladb.com
Join the community! slack.scylladb.com
Questions?

Overcoming Barriers of Scaling Your Database

  • 1.
  • 2.
    + I currentlyuse ScyllaDB + I currently use another NoSQL database + I am currently evaluating NoSQL + I am interested in learning more about ScyllaDB + None of the above Where are you in your NoSQL database adoption? Poll Question 2
  • 3.
    Peter Corless + Listento customer stories + Write blogs & case studies + Play (and design) strategy & roleplaying games 3 Director of Technical Advocacy ScyllaDB
  • 4.
    Tomer Sandler 4 + Lifecyclesupport: from deployment to operations + Troubleshoots toughest real-time technical issues + Plays a mean saxophone Head of Customer Success ScyllaDB
  • 5.
    5 + For distributed,data-intensive apps that require high performance and low latency + 400+ users worldwide + Results + Comcast: Reduced P99 latencies by 95% + FireEye: 1500% improvement in throughput + Discord: Reduced C* nodes from ~140 to 6 + iFood: 9X cost reduction vs. DynamoDB + Open Source, Enterprise and Cloud options + Fully compatible with Apache Cassandra and Amazon DynamoDB About ScyllaDB 1ms <1ms 10ms 1M 10M ScyllaDB Universe of 400+ Users
  • 6.
    400+ Companies UseScyllaDB Seamless experiences across content + devices Fast computation of flight pricing Corporate fleet management Real-time analytics 2,000,000 SKU -commerce management Real-time location tracking for friends/family Video recommendation management IoT for industrial machines Synchronize browser properties for millions Threat intelligence service using JanusGraph Real time fraud detection across 6M transactions/day Uber scale, mission critical chat & messaging app 6 Network security threat detection Power ~50M X1 DVRs with billions of reqs/day Precision healthcare via Edison AI Inventory hub for retail operations Property listings and updates Unified ML feature store across the business Cryptocurrency exchange app Geography-based recommendations Distributed storage for distributed ledger tech Global operations- Avon, Body Shop + more Predictable performance for on sale surges GPS-based exercise tracking
  • 7.
  • 8.
  • 9.
    How does acompany know when they’ve hit the wall? Q1: 9
  • 10.
    What about throughputlimits? What’s different if you added more workloads vs. bursty time- of-day traffic? Q2: 10
  • 11.
    Even with thebest up-front planning you can run into a stochastic event that can go beyond your predictive planning? What then? Q3: 11
  • 12.
    Let’s define “emergency scalability”as responding to unplanned demands on your system. What examples have you seen of “emergency scaling” limits in the wild? Q4: 12
  • 13.
    What’s different doing “emergencyscaling” with an on- premises deployment vs. a public cloud? Q5: 13
  • 14.
    14 + <1 terabyte +1 to 50 terabytes + 50-100 terabytes + >100 terabytes How much data do you have under management in your own transactional database systems? Poll Question
  • 15.
    Is the cloudreally is just “someone else’s computer?” Q6: 15
  • 16.
    Is data volumeitself a barrier to scale? “I want a petabyte of storage fully loaded by 8 AM tomorrow!” Q7: 16
  • 17.
    What are otherreal-time limits you can’t avoid? Like the latency of the speed of light, or the raw time to actually stream your data to the new hardware? Q8: 17
  • 18.
    Can you talkmore about latency issues? You can’t just throw hardware at it. Because that could even make latencies worse. Q9: 18
  • 19.
    What advice canyou give to system architects planning for data at scale? Q10: 19
  • 20.
    United States 2445 FaberSt, Suite #200 Palo Alto, CA USA 94303 Israel Maskit 4 Herzliya, Israel 4673304 www.scylladb.com @scylladb Learn NoSQL for free! university.scylladb.com Join the community! slack.scylladb.com Questions?

Editor's Notes

  • #2 Hello! Today we’re going to talk to you about “Overcoming Barriers of Scaling Your Database.”
  • #3 But first, I’d like to get to know about you, our audience, and understand your perspective on distributed databases. For some of you will be interested in SQL and some NoSQL and some both. For those interested in NoSQL, where are you in your NoSQL adoption? I currently use ScyllaDB I currently use another NoSQL database I am currently evaluating NoSQL I am interested in learning more about ScyllaDB None of the above [Pause] Alright. We’ll close out this poll and move on.
  • #4 My name is Peter Corless. I’m the Director of Technical Advocacy at ScyllaDB. I listen to our users’ stories and discover wisdom in each to share with our other practitioners in the industry at large, whether through blogs or in technical presentations.
  • #5 Today I am happy to be joined with my colleague Tomer Sandler who, due to his dedication, experience and insight, become head of ScyllaDB’s customer success organization. Before ScyllaDB, Tomer worked at Dell, VERINT and EMC. With twenty years of experience in the industry, Tomer has seen the rise of the public cloud and distributed databases, and brings with him a wealth of knowledge. He also plays a mean saxophone.
  • #6 Now let’s talk about the database we know and love. ScyllaDB is the single most reliable database for data intensive applications which require high performance and low latency. Our universe of user manage game-changing applications which require “monster” scale. Because of its advanced architecture ScyllaDB provides superior system utilization, resulting in higher performance. lower latencies and better ROI on your infrastructure. ScyllaDB is available as pure open source, enterprise edition with value-added features and full enterprise support, plus a fully-managed Database-as-a-Service, Scylla Cloud.
  • #7 Here’s a quick snapshot of some of the many companies using ScyllaDB. As you can see, it’s not just one industry. Anyone looking to run a big, fast, always-on distributed database can use us. You can start small and keep scaling. There’s no barriers to hit as your company or your use cases grow. Start small. Think hugely.
  • #8 Also, if you want to learn more, Scylla Summit 2022 is coming up February 9th and 10th! It is our annual free online user conference. You can find the registration page at ScyllaDB.com slash summit. I am the Content Chair for this year’s Summit, and I have been busy working with our great lineup of speakers. As ever we’ll have our ScyllaDB executives and engineers talking about latest developments in our database, plus industry leaders, and use cases from our open source users and our cloud and enterprise customers. We have some great sessions lined up and I’m sure you’ll love it!
  • #9 Without any further ado, let’s get on with it.
  • #21 With that, thank you. You can always follow up with me at petercorless on Twitter. And if you want to learn more about ScyllaDB, our highly available, monstrously scalable database, again, check out the free online courses at university.scylladb.com. Have yourself a great day, and, as ever, “onwards to adventure!”