Building Apps with Distributed In-Memory Computing Using Apache Geode
3 likes1,221 views
The document provides an overview of Apache Geode, a distributed, memory-based data management platform designed for high performance, scalability, and continuous availability in data-oriented applications. It discusses Geode's architecture, key features, advanced concepts like persistence, functions, and event-driven architectures, as well as hands-on examples and community resources. It highlights Geode's capability to handle significant data volumes and concurrent users while maintaining low latency and high availability.
![• Clone & Build
•
• Start Services
• Create & Monitor Region
How to START? Easy as !!
20
git clone https://github.com/apache/incubator-geode
cd incubator-geode
./gradlew build -Dskip.tests=true
cd gemfire-assembly/build/install/apache-geode
./bin/gfsh
gfsh> start locator --name=locator
gfsh> start server --name=server
gfsh> create region --name=myRegion —type=REPLICATE
gfsh> start [pulse | jconsole]
1
2
3
'
1 2 3](https://image.slidesharecdn.com/geodemeetup2016-03-v2-160310205437/85/Building-Apps-with-Distributed-In-Memory-Computing-Using-Apache-Geode-20-320.jpg)
![• Register Interest
• Individual Keys OR RegEx for Keys
• Updates Local Copy
• Examples:
• region.registerInterest(“key-1”);
• region1.registerInterestRegex(“[a-z]+“);
• Continuous Query
• Receive Notification when Query condition met on server
• Example:
• SELECT * FROM /tradeOrder t WHERE t.price > 100.00
Can be DURABLE
Events & Notifications
34](https://image.slidesharecdn.com/geodemeetup2016-03-v2-160310205437/85/Building-Apps-with-Distributed-In-Memory-Computing-Using-Apache-Geode-34-320.jpg)
Building Apps with Distributed In-Memory Computing Using Apache Geode
- 1. Building Apps with Distributed In-Memory Computing using Apache Geode Nitin Lamba @nlamba9 (incubating) William Markito @william_markito
- 2. Introduction (Nitin) • WHAT? Overview & history • WHY? Relevance & Differentiators • HOW? Features & Basic Concepts • SEE! Quick start Hands-on (William) • LEARN: Advanced Concepts - Persistence, f(x), PDX, … • SHOW: Demos (Docker, PDX) Resources Q & A Agenda 2
- 4. From GEM to GEODE… 4
- 5. A distributed, memory-based data management platform for data oriented apps that need: • high performance, scalability, resiliency and continuous availability • fast access to critical data sets • location-aware distributed data processing • event-driven data architecture What is GEODE? 5
- 6. High-level Architecture 6 Powerful app development kit • APIs: Java & REST • Adapters: Redis, Lucene*, Spark*, … Multiple persistence options • Filesystem, RDBMS or HDFS* • Sync: read-through, write-through • Async: write-behind Durable <K,V> cache/ store • Data replicated or partitioned • Redundant storage in-memory/ disk • Flexible data retention policiesÎ ! Locator Server Server Server Server +"""" " $ % % % && & % % % % % % % % && A Peer-2-Peer Distributed System REST ! * Experimental and waiting community feedback
- 7. • 1000+ systems in production (real customers) • Cutting edge use cases Incubating but ROCK solid… 7 <2000 2004 2008 2012 2016 Early drivers • Data Volumes • Margins/ transactions • IT maintenance costs • Elasticity needs Real-time needs • Real-time response • Time to market needs • Flexible Data Models • Persistent+In-memory Global Data • Visibility across DC • Fast Ingest • Device to enterprise • Uptime (always on) Open Source! • Apache Incubation • Gemfire > Geode • M1 release • 1st Geode Summit Financial Services US DoD Trade Clearing Travel Portal Online Gambling Telcos Manufacturing Auto Insurance Payroll processing Rail systems
- 8. …with both SCALE and SPEED, … 8 40K Transactions per second 3TB Data in-memory 17B Records in-memory 120K Concurrent users
- 9. … and impacting a LOT of people! 9 China Railway Corporation Indian Railways 19% 17% 36% of the world population
- 10. Built for PERFORMANCE… 10 Operationspersecond 0 200,000 400,000 600,000 800,000 YCSB Workloads AReads AUpdates BReads BUpdates CReads DInserts DReads FReads FUpdates Cassandra Geode
- 11. …and horizontal, consistent SCALABILITY! 11 Horizontal scaling for reads, consistent latency and CPU 0 4.5 9 13.5 18 Speedup 0 1.25 2.5 3.75 5 Server Hosts 2 4 6 8 10 speedup latency (ms) CPU % • Scaled from 256 clients and 2 servers to 1280 clients and 10 servers • Partitioned region with redundancy and 1K data size
- 12. • Minimize copying • Minimize contention points • Run user code in-process • Partitioning & parallelism • Avoid disk seeks • Automated benchmarks What makes it go FAST? 12
- 13. • Cache • Region • Member • Client Cache • Persistence • Functions • Events & Listeners • High Availability • Serialization Let’s talk about a few (basic) CONCEPTS… 13
- 14. • In-memory storage and management for your data • Configurable through XML, Java API or CLI • Collection of Region What is a CACHE? 14 Region Region Region Cache JVM
- 15. • Distributed java.util.Map on steroids (Key/Value) • Consistent API regardless of where or how data is stored • Observable (reactive) • Highly available, redundant on cache Member (s). What is a REGION? 15 Region Cache java.util.Map JVM Key Value K01 May K02 Tim
- 16. • Local, Replicated or Partitioned • In-memory or persistent • Redundant • LRU • Overflow Region: Types & Options 16 Region Cache java.util.Map JVM Key Value K01 May K02 Tim Region Cache java.util.Map JVM Key Value K01 May K02 Tim LOCAL LOCAL_HEAP_LRU LOCAL_OVERFLOW LOCAL_PERSISTENT LOCAL_PERSISTENT_OVERFLOW PARTITION PARTITION_HEAP_LRU PARTITION_OVERFLOW PARTITION_PERSISTENT PARTITION_PERSISTENT_OVERFLOW PARTITION_PROXY PARTITION_PROXY_REDUNDANT PARTITION_REDUNDANT PARTITION_REDUNDANT_HEAP_LRU PARTITION_REDUNDANT_OVERFLOW PARTITION_REDUNDANT_PERSISTENT PARTITION_REDUNDANT_PERSISTENT_OVERFLOW REPLICATE REPLICATE_HEAP_LRU REPLICATE_OVERFLOW REPLICATE_PERSISTENT REPLICATE_PERSISTENT_OVERFLOW REPLICATE_PROXY
- 17. • Durability • WAL for efficient writing • Consistent recovery • Compaction Persistent Regions 17 Modify k1->v5 Create k6->v6 Create k2->v2 Create k4->v4 Oplog2.crf Member 1 Modify k4->v7Oplog3.crf Put k4->v7 Region Cache java.util.Map JVM Key Value K01 May K02 Tim Region Cache java.util.Map JVM Key Value K01 May K02 Tim Server 1 Server N
- 18. • A process that has a connection to the system • A process that has created a cache • Embeddable within your application What is a MEMBER? 18 Client Locator Server
- 19. • A process connected to the Geode server(s) • Can have a local copy of the data • Run OQL queries on local data • Can be notified about events on the servers What is a CLIENT CACHE? 19 Application GemFire Server Region Region RegionClient Cache
- 20. • Clone & Build • • Start Services • Create & Monitor Region How to START? Easy as !! 20 git clone https://github.com/apache/incubator-geode cd incubator-geode ./gradlew build -Dskip.tests=true cd gemfire-assembly/build/install/apache-geode ./bin/gfsh gfsh> start locator --name=locator gfsh> start server --name=server gfsh> create region --name=myRegion —type=REPLICATE gfsh> start [pulse | jconsole] 1 2 3 ' 1 2 3
- 22. • Cache • Region • Member • Client Cache • Persistence • Functions • Events & Listeners • High Availability • Serialization More (advanced) CONCEPTS… 22
- 23. Persistence - Shared Nothing 23 Server 3Server 2Server 1
- 24. Persistence - Shared Nothing 24 Server 3Server 2Server 1 B1 B3 B2 B1 B3 B2 Primary Secondary
- 25. Persistence - Shared Nothing 25 Server 3Server 2Server 1 B1 B3 B2 B1 B3 B2 Primary Secondary
- 26. Persistence - Shared Nothing 26 Server 3Server 2Server 1 B1 B3 B2 B1 B3 B2 Primary Secondary
- 27. Persistence - Shared Nothing 27 Server 3Server 2Server 1 B1 B3 B2 B1 B3 B2 Primary Secondary
- 28. Persistence - Shared Nothing 28 Server 3Server 2Server 1 B1 B3 B2 B1 B3 B2 Primary Secondary B3 B2 Server 1 waits for others when it starts
- 29. Persistence - Shared Nothing 29 Server 3Server 2Server 1 B1 B3 B2 B1 B3 B2 Primary Secondary Fetches missed operations on restart
- 30. Persistence - Operational Logs 30 Create k1->v1 Create k2->v2 Modify k1->v3 Create k4->v4 Modify k1->v5 Create k6->v6 Member 1 Put k6->v6 Oplog2.crf Oplog1.crf Append to operation log
- 31. Persistence - Operational Logs: Compaction 31 Create k1->v1 Create k2->v2 Modify k1->v3 Create k4->v4 Modify k1->v5 Create k6->v6 Member 1 Put k6->v6 Oplog2.crf Oplog1.crf Append to operation log Copy live data forward
- 32. • Used for distributed concurrent processing (Map/Reduce, stored procedure) • Highly available • Data oriented • Member oriented Functions 32 Submit (f1) f1 , f2 , … fn Execute Functions
- 33. Functions 33 Server Server FunctionService.onRegion.withFilter.execute ResultCollector.getResult Server Distributed System execute Server Server 6 1 result execute execute result result 2 5 3 4 3 4 Server Partitioned Region Data Store - X Partitioned Region Data Store - Y Partitioned Region Data Store - Z Partitioned Region Data Accessor Partitioned Region Data Accessor filter = Keys X, Y Client Region
- 34. • Register Interest • Individual Keys OR RegEx for Keys • Updates Local Copy • Examples: • region.registerInterest(“key-1”); • region1.registerInterestRegex(“[a-z]+“); • Continuous Query • Receive Notification when Query condition met on server • Example: • SELECT * FROM /tradeOrder t WHERE t.price > 100.00 Can be DURABLE Events & Notifications 34
- 35. • CacheWriter / CacheListener • AsyncEventListener (queue / batch) • Parallel or Serial • Conflation Listeners 35
- 37. Fixed or Flexible schema? 37 id name age pet_id or { id : 1, name : “Fred”, age : 42, pet : { name : “Barney”, type : “dino” } }
- 38. Portable Data eXchange (PDX) 38 C#, C++, Java, JSON No IDL, no schemas, no hand-coding Schema evolution (Forward and Backward Compatible) * domain object classes not required | header | data | | pdx | length | dsid | typeid | fields | offsets |
- 39. Efficient for queries 39 { id : 1, name : “Fred”, age : 42, pet : { name : “Barney”, type : “dino” } } SELECT p.name FROM /Person p WHERE p.pet.type = “dino” single field deserialization
- 40. But HOW to serialize data? 40 Benchmark: https://github.com/eishay/jvm-serializers
- 41. Schema Evolution 41 Member A Member B Distributed Type Definitions v2v1 Application #1 Application #2 v2 objects preserve data from missing fields v1 objects use default values to fill in new fields PDX provides forwards and backwards compatibility, no code required
- 43. Code • New features • Bug fixes • Writing tests Documentation • Wiki • Web site • User guide How to CONTRIBUTE? 43 Community • Join the mailing list • Ask or answer • Join our HipChat • Become a speaker • Finding bugs • Testing an RC/Beta