1. Big Data-Driven Applications
with Cassandra and Spark
Artem Chebotko, Ph.D.
Solution Architect

2. 1 Modern Big Data and Cloud Applications
2 Cassandra and Spark Highlights
3 Architecture Overview
4 Languages and APIs
5 Live Demo
2

3. Modern Application Requirements
• Numerous Endpoints
• Geographically Distributed
• Continuously Available
• Instantaneously Responsive
• Immediately Decisive
• Predictably Scalable
3

4. Applications by Response Time and Workload
4
Analytical (OLAP)Operational (OLTP)

5. Applications by Response Time and Workload
5
Real-time transactions
Analytical (OLAP)Operational (OLTP)
• Web and IoT apps
• Financial transactions

6. Applications by Response Time and Workload
6
Real-time transactions
Real-time analytics
Analytical (OLAP)Operational (OLTP)
• Web and IoT apps
• Financial transactions
• Recommendations

7. Applications by Response Time and Workload
7
Real-time transactions
Real-time analytics
Streaming analytics
Analytical (OLAP)Operational (OLTP)
• Web and IoT apps
• Financial transactions
• Recommendations
• Fraud prevention

8. Applications by Response Time and Workload
8
Real-time transactions
Real-time analytics
Streaming analytics
Batch analytics
Analytical (OLAP)Operational (OLTP)
• Web and IoT apps
• Financial transactions
• Recommendations
• Fraud prevention
• Predictive models
• Fraud detection

9. Roles of Cassandra and Spark
9
Real-time transactions
Real-time analytics
Streaming analytics
Batch analytics
Analytical (OLAP)Operational (OLTP)
• Web and IoT apps
• Financial transactions
• Recommendations
• Fraud prevention
• Predictive models
• Fraud detection
Numerous Endpoints
Geographically Distributed
Continuously Available
Instantaneously Responsive
Immediately Decisive
Predictably Scalable

10. 1 Modern Big Data and Cloud Applications
2 Cassandra and Spark Highlights
3 Architecture Overview
4 Languages and APIs
5 Live Demo
10

11. Cassandra – Operational Database
• Millions of concurrent users
• Millisecond response time
• Linear scalability
• Always on
11

12. Cassandra – Operational Database
12

13. Spark – Analytics Platform
• Real-time, streaming and batch analytics
• Up to 100x faster than Hadoop
• Scalability, fault-resilience
• Versatile and rich API
13

14. Spark – Analytics Platform
14
SQL Streaming MLlib GraphX
Cluster Manager
Standalone YARN Mesos

15. Spark-Cassandra Connector
Open-Source Package for Spark
• Routine Spark-Cassandra interactions
– Read from and write into Cassandra
• Profound optimizations
– Predicate pushdown
– Data locality
– Cassandra-optimized joins
– Cassandra-aware partitioning
– Shuffle-free grouping
15

16. 1 Modern Big Data and Cloud Applications
2 Cassandra and Spark Highlights
3 Architecture Overview
4 Languages and APIs
5 Live Demo
16

17. C*: Distributed, Shared Nothing, Peer-to-Peer
17
C* Client
C*
C*
C*
-263
+263
-1
Driver
C* Client Driver
transaction
transaction
transaction
transaction

18. C*: Partitioning and Replication
18
replica 2
replica 1
replica 3
coordinator
partitioner
partition
partition
key
write request
acknowledgment
CL=QUORUM
RF=3
......
TABLE

19. C*: Partitioning and Replication
19
replica 2
replica 1
replica 3
partition
partition
key
result
CL=ONE
RF=3
coordinator
partitioner
read request

20. Spark: Master-Worker, Failover Masters
20
Spark
Client
Driver
Master
Worker
SparkContext
Spark
Client
Driver
SparkContext
Worker
Worker
Executor Executor
Executor Executor
Executor Executor

21. Spark: Computation Scheduling
21
Driver
SparkContext
DAG Job 0
Stage 1
task task
task
Stage 0
task task
task
Stage 2
task task
task
Job 1
Stage 4
task task
task
Stage 3
task task
task
Stage 5
task task
task
Executor
task
cache
task
Executor
task
cache
task
Executor
task
cache
task

22. Spark-Cassandra Connector
22
C*
C*
C*
Master Worker
Executor
Executor
Spark-Cassandra Connector
Worker
Executor
Executor
Spark-Cassandra
Connector
Worker
Executor
Executor
Spark-Cassandra
Connector

23. Spark-Cassandra Connector
23
C*
C*
C*
Master Worker
Executor
Executor
Spark-Cassandra Connector
Worker
Executor
Executor
Spark-Cassandra
Connector
Worker
Executor
Executor
Spark-Cassandra
Connector
ClusterNode
Spark Node
Master JVM
Connector.jar
Worker JVM
Executor JVM
Executor JVM
C* Node
C* JVM

24. Multi-DC Deployment and Workload Separation
24
C* Client Driver Spark
Client
Driver
SparkContextC* Client Driver
C*
C*
C*
Master
Worker
Executor
WorkerWorker
C*
C*
C*
Executor
Executor
Executor
Executor Executor
Executor
C*C*
C*
Data
Replication
C* Client Driver
Spark
Client
Driver
SparkContext
real-time
transactions
interactive and
batch analytics
DC
Operations
DC
Analytics

25. 1 Modern Big Data and Cloud Applications
2 Cassandra and Spark Highlights
3 Architecture Overview
4 Languages and APIs
5 Live Demo
25

26. Getting Started with Cassandra and Spark Applications
• Data Model and Cassandra Query Language
• Core Spark and Spark-Cassandra Connector
26

27. Keyspace and Replication
27
CREATE KEYSPACE iot
WITH replication = {'class': 'NetworkTopologyStrategy',
'DC-Kyiv-Operations' : 3,
'DC-Houston-Analytics': 2};
USE iot;

28. Table with Single-Row Partitions
28
username age address
Alice 28 Santa Clara, CA
Alex 37 Austin, TX
users CREATE TABLE users (
username TEXT,
age INT,
address TEXT,
PRIMARY KEY(username)
);
SELECT * FROM users
WHERE username = ?;

29. Table with Single-Row Partitions
29
id type settings owner
1 phone {gps ⇒ on,
pedometer ⇒ on}
Alice
2 wristband {heart rate ⇒ on, …} Alice
3 thermostat {temp ⇒ 75, …} Alice
4 security {…} Alex
5 phone {…} Alex
sensors CREATE TABLE sensors (
id INT,
type TEXT,
settings MAP<TEXT,TEXT>,
owner TEXT,
PRIMARY KEY(id)
);
SELECT * FROM sensors
WHERE id = ?;

30. Table with Multi-Row Partitions
30
username id type settings age address
Alice 1 phone {gps ⇒ on, …} 28 Santa Clara, CA
Alice 2 wristband {heart rate ⇒ on, …} 28 Santa Clara, CA
Alice 3 thermostat {temp ⇒ 75, …} 28 Santa Clara, CA
Alex 4 security … 37 Austin, TX
Alex 5 phone … 37 Austin, TX
sensors_by_user
ASCASC

31. Table with Multi-Row Partitions
CREATE TABLE sensors_by_user (
username TEXT, age INT STATIC, address TEXT STATIC,
id INT, type TEXT, settings MAP<TEXT,TEXT>,
PRIMARY KEY(username, id)
) WITH CLUSTERING ORDER BY (id ASC);
SELECT * FROM sensors_by_user WHERE username = ?;
SELECT * FROM sensors_by_user WHERE username = ? AND id = ?;
SELECT * FROM sensors_by_user WHERE username = ? AND id > ?
ORDER BY id DESC;
31

32. Retrieving Data from C*
• SparkContext, RDD, Connector
32
val rdd = sc.cassandraTable("iot","sensors_by_user")
.select("username","id","type")

33. Predicate Pushdown
33
sc.cassandraTable("iot","sensors_by_user")
.select("username","id","type")
.filter(row => row.getString("username") == "Alice")
• Suboptimal code

34. Predicate Pushdown
34
sc.cassandraTable("iot","sensors_by_user")
.select("username","id","type")
.filter(row => row.getString("username") == "Alice")
.where("username = 'Alice'")
• Predicate pushed down to C*

35. Data Locality
input.split.size_in_mb input.consistency.level input.fetch.size_in_rows
35
Cassandra Spark
Node
(64) (LOCAL_ONE) (1000)

36. • Standard Spark join = shuffle + shuffle
Cassandra-Optimized Joins
36
val s = sc.cassandraTable("iot","sensors")
.keyBy(row => row.getString("owner"))
val u = sc.cassandraTable("iot","users")
.keyBy(row => row.getString("username"))
s.join(u)

37. Cassandra-Optimized Joins
37
• Shuffle
B
Partition 1
A C D
Map Task
Partition A
Reduce Task
B
Partition 2
A C D
Map Task
Partition B
Reduce Task
B
Partition 3
A C D
Map Task
Partition D
Reduce Task
Partition C
Reduce Task
Buckets:
memory
memory
Shuffle write
Shuffle read
disk
disk
Aggregation Aggregation Aggregation
Aggregation AggregationAggregationAggregation

38. • Connector join = no shuffle + no data locality
Cassandra-Optimized Joins
38
sc.cassandraTable("iot","sensors")
.select("id","type","owner".as("username"))
.joinWithCassandraTable("iot","users")
.on(SomeColumns("username"))

39. Cassandra-Optimized Joins
39
id type owner 
username
1 … Alice
4 … Alex
3 ... Alice
2 … Alice
5 … Alex
username age address
Alex 37 …
username age address
Alice 28 …

40. • Connector join + CAP = shuffle + data locality
Cassandra-Aware Partitioning
40
sc.cassandraTable("iot","sensors")
.select("id","type","owner".as("username"))
.repartitionByCassandraReplica("iot","users")
.joinWithCassandraTable("iot","users")
.on(SomeColumns("username"))

41. Cassandra-Aware Partitioning
41
id type owner 
username
1 … Alice
2 … Alice
3 ... Alice
username age address
Alex 37 …
username age address
Alice 28 …
id type owner 
username
4 … Alex
5 … Alex

42. • Suboptimal code
Shuffle-Free Grouping
42
sc.cassandraTable("iot","sensors_by_user")
.select("username","id","type")
.as((u:String,i:Int,t:String)=>(u,(i,t)))
.groupByKey

43. • Shuffling eliminated at no extra cost
Shuffle-Free Grouping
43
sc.cassandraTable("iot","sensors_by_user")
.select("username","id","type")
.as((u:String,i:Int,t:String)=>(u,(i,t)))
.groupByKeyspanByKey

44. Saving Data to C*
44
rdd.saveToCassandra("iot","users",
SomeColumns("username", "age"))
output.consistency.level (LOCAL_QUORUM)
output.batch.grouping.key (Partition)
output.batch.size.bytes (1024)
output.batch.grouping.buffer.size (1000)
output.concurrent.writes (5)

45. 1 Modern Big Data and Cloud Applications
2 Cassandra and Spark Highlights
3 Architecture Overview
4 Languages and APIs
5 Live Demo
45

46. Artem Chebotko
achebotko@datastax.com
www.linkedin.com/in/artemchebotko
46