This document discusses in-memory computing and distributed systems. It provides an overview of Hazelcast, an open-source distributed systems and in-memory data grid platform. Key features highlighted include using standard Java collections and concurrency APIs, transparent data distribution, being a drop-in replacement for caching solutions, and having a disruptively simple design. Distributed computing concepts like data partitioning, parallel processing, and caching evolution are briefly explained.

1. www.hazelcast.com
/**
* In-Memory Computing
* Distributed Systems
*/

2. www.hazelcast.com
Disclaimer
This presentation may include certain forward-looking statements and projections
provided by the Company. Any such statements and projections reflect various
estimates and assumptions by the Company concerning anticipated results. These
statements involve risks, uncertainties and assumptions and are based on the
current estimates and assumptions of the management of the Company as of the
date of this presentation and are subject to uncertainty and changes. No
representations or warranties are made by the Company as to the accuracy of any
such statements or projections. Whether or not any such forward-looking statements
or projections are in fact achieved will depend upon future events some of which are
not within the control of the Company. Accordingly, actual results may vary from the
projected results and such variations may be material. Statements contained herein
describing documents and agreements are summaries only and such summaries
are qualified in their entirety by reference to such documents and agreements.

3. www.hazelcast.com@noctarius2k

4. www.hazelcast.com
Who’s that dude?
• Chris(toph) Engelbert
• Twitter fanatic: @noctarius2k
• Weird 9+ Java-Years
• Performance, GC, Fairytales
• Apache Committer
• Gaming, Travel Management, …

5. www.hazelcast.com
Who’s that dude?
• Chris(toph) Engelbert
• Twitter fanatic: @noctarius2k
• Weird 9+ Java-Years
• Performance, GC, Fairytales
• Apache Committer
• Gaming, Travel Management, …
The www.hazelcast.ninja

6. www.hazelcast.com@noctarius2k
Distributed
Computing…

7. www.hazelcast.com@noctarius2k
Toaster
Server 1
TV-Server 1
Power
CoffeeMaker
Server 1
Kettle
Server 1
Stove
Server 1
Distributed
Computing…

8. www.hazelcast.com@noctarius2k
Toaster
Server 1
TV-Server 1
Power
CoffeeMaker
Server 1
Kettle
Server 1
Stove
Server 1
Power Grid
Server 1, 2
Distributed
Computing…

9. www.hazelcast.com@noctarius2k
… but what means
Distributed Computing?OOO
( )

10. www.hazelcast.com@noctarius2k
Caching? Don’t you mean ‘Wasting Memory’?
L1 Cache Reference
L2 Cache Reference
Main Memory Reference
1K send over 1 Gbps Network
4K read from SSD
Seek on Spinning Disk
Send Packet CA->AMS->CA
0.5 ns
7 ns
100 ns
10,000 ns
150,000 ns
10,000,000 ns
150,000,000 ns
0.01 ms
0.15 ms
10 ms
150 ms

11. www.hazelcast.com@noctarius2k
Evolution of:
- Memory-Price
- Memory-Size

12. www.hazelcast.com

13. www.hazelcast.com
Data Distribution
(Partitioning / Sharding)

14. www.hazelcast.com@noctarius2k
Data Distribution
String code = “sunnytechhub”
Map<String, TShirtDelivery> shirts = Maps.create()
shirts.put(code, new TShirtDelivery(“Your Address”))

15. www.hazelcast.com@noctarius2k
Data Distribution
String code = “sunnytechhub”
Map<String, TShirtDelivery> shirts = Maps.create()
shirts.put(code, new TShirtDelivery(“Your Address”))
// Enter code at http://hazelcast.org/t-shirts :-)>

16. www.hazelcast.com@noctarius2k
Data Distribution
String code = “sunnytechhub”
int hashcode = hash(code)
partitionId = hashcode % partitionCount
cluster.send(partitionId, code, delivery)

17. www.hazelcast.com@noctarius2k
Data Distribution
int hashcode = hash(code)
partitionId = hashcode % partitionCount
cluster.send(partitionId, code, delivery)
Must be a consistent hash function
Partition count must be constant
Can be calculated, smart routing possible

18. www.hazelcast.com@noctarius2k
That was easy!But don’t tell anyone!

19. www.hazelcast.com
Parallelize Processing

20. www.hazelcast.com@noctarius2k
Parallelize Processing
int[] values = [0..100000].map(randomInt())
int[][] blocks = split(values, 10000)
int[] subresult = blocks.foreach(_.sum())
int result = subresult.sum()

21. www.hazelcast.com@noctarius2k
Parallelize Processing
int[][] blocks = split(values, 10000)
int[] subresult = blocks.foreach(_.sum())
int result = subresult.sum()
No mutation, only new values
Independently computable
Might split further down (fork-join, work-stealing)

22. www.hazelcast.com@noctarius2k
I told you:
Easy Peasy!

23. www.hazelcast.com@noctarius2k
Caching!

24. www.hazelcast.com@noctarius2k
http://gadizmo.com/roll-your-own-with-the-ham-dogger.php
Roll Your Own!
Evolution Of Caching

25. www.hazelcast.com@noctarius2k
Caches Are Simple!
public class Cache<K, V> {
private final Map<K, V> cache = new CHM<>();
public void put(K key, V value) { cache.put(key, value); }
public V get(K key) { return cache.get(key); }
}

26. www.hazelcast.com@noctarius2k
Even With TTL!

27. www.hazelcast.com@noctarius2k
And Auto-Cleanup

28. www.hazelcast.com@noctarius2k
What Is Wrong?

29. www.hazelcast.com@noctarius2k
What Is Wrong?
O(n)
5 mio
Entries

30. www.hazelcast.com@noctarius2k

31. www.hazelcast.com@noctarius2k
Evolution Of Caching

32. www.hazelcast.com@noctarius2k
Proprietary Cache!
Evolution Of Caching

33. www.hazelcast.com@noctarius2k
Proprietary Cache!
Evolution Of Caching
Open Source

34. www.hazelcast.com@noctarius2k
Proprietary Cache!
Evolution Of Caching
Open Source
Commercial

35. www.hazelcast.com@noctarius2k
Proprietary Cache!
Evolution Of Caching
Open Source
Commercial
Stupidly Expensive

36. www.hazelcast.com@noctarius2k
JCache?
Luke!
I Am Your
(J)Cache!

37. www.hazelcast.com@noctarius2k
Success!
Feels like

38. www.hazelcast.com@noctarius2k
Going to the
Hazelcast!

39. www.hazelcast.com@noctarius2k
Hazelcast in 5 Facts
• Java Collections API
• Java Concurrency API
• Transparent Data Distribution
• Drop-In Replacement
• Disruptively Simple
(c) Rod Johnson (@springrod)

40. www.hazelcast.com@noctarius2k
http://technoodling.net/mili-power-crystal-battery-pack-review/
Terracotta /
EHcache
Oracle
Coherence
Infinispan
Java
Collections
API
Hazelcast

41. www.hazelcast.com@noctarius2k
No need to ## care about
Proprietary APIs!

42. www.hazelcast.com@noctarius2k
Time to be Happy!

43. www.hazelcast.com@noctarius2k
Time to be Happy!
Apache License 2

44. www.hazelcast.com@noctarius2k
Time to be Happy!
www.hazelcast.org

45. www.hazelcast.com@noctarius2k
You can do it!

46. www.hazelcast.com
Thank You!
Any Questions?
@noctarius2k
http://www.sourceprojects.org
http://github.com/noctarius
@hazelcast
http://www.hazelcast.com
http://www.hazelcast.org
http://github.com/hazelcast