Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Streaming Analytics with Spark, Kafka, Cassandra and Akka

43,685 views

Published on

This talk will address how a new architecture is emerging for analytics, based on Spark, Mesos, Akka, Cassandra and Kafka (SMACK). Popular architecture like Lambda separate layers of computation and delivery and require many technologies which have overlapping functionality. Some of this results in duplicated code, untyped processes, or high operational overhead, let alone the cost (i.e. ETL). I will discuss the problem domain and what is needed in terms of strategies, architecture and application design and code to begin leveraging simpler data flows. We will cover how the particular set of technologies addresses common requirements and how collaboratively they work together to enrich and reinforce each other.

Published in: Technology

Streaming Analytics with Spark, Kafka, Cassandra and Akka

  1. 1. Streaming Analytics with Spark, Kafka, Cassandra, and Akka Helena Edelson VP of Product Engineering @Tuplejump
  2. 2. • Committer / Contributor: Akka, FiloDB, Spark Cassandra Connector, Spring Integration • VP of Product Engineering @Tuplejump • Previously: Sr Cloud Engineer / Architect at VMware, CrowdStrike, DataStax and SpringSource Who @helenaedelson github.com/helena
  3. 3. Tuplejump Tuplejump Data Blender combines sophisticated data collection with machine learning and analytics, to understand the intention of the analyst, without disrupting workflow. • Ingest streaming and static data from disparate data sources • Combine them into a unified, holistic view • Easily enable fast, flexible and advanced data analysis 3
  4. 4. Tuplejump Open Source github.com/tuplejump • FiloDB - distributed, versioned, columnar analytical db for modern streaming workloads • Calliope - the first Spark-Cassandra integration • Stargate - Lucene indexer for Cassandra • SnackFS - HDFS-compatible file system for Cassandra 4
  5. 5. What Will We Talk About • The Problem Domain • Example Use Case • Rethinking Architecture – We don't have to look far to look back – Streaming – Revisiting the goal and the stack – Simplification
  6. 6. THE PROBLEM DOMAIN Delivering Meaning From A Flood Of Data 6
  7. 7. The Problem Domain Need to build scalable, fault tolerant, distributed data processing systems that can handle massive amounts of data from disparate sources, with different data structures. 7
  8. 8. Translation How to build adaptable, elegant systems for complex analytics and learning tasks to run as large-scale clustered dataflows 8
  9. 9. How Much Data Yottabyte = quadrillion gigabytes or septillion bytes 9 We all have a lot of data • Terabytes • Petabytes... https://en.wikipedia.org/wiki/Yottabyte
  10. 10. Delivering Meaning • Deliver meaning in sec/sub-sec latency • Disparate data sources & schemas • Billions of events per second • High-latency batch processing • Low-latency stream processing • Aggregation of historical from the stream
  11. 11. While We Monitor, Predict & Proactively Handle • Massive event spikes • Bursty traffic • Fast producers / slow consumers • Network partitioning & Out of sync systems • DC down • Wait, we've DDOS'd ourselves from fast streams? • Autoscale issues – When we scale down VMs how do we not lose data?
  12. 12. And stay within our AWS / Rackspace budget
  13. 13. EXAMPLE CASE: CYBER SECURITY Hunting The Hunter 13
  14. 14. 14 • Track activities of international threat actor groups, nation-state, criminal or hactivist • Intrusion attempts • Actual breaches • Profile adversary activity • Analysis to understand their motives, anticipate actions and prevent damage Adversary Profiling & Hunting
  15. 15. 15 • Machine events • Endpoint intrusion detection • Anomalies/indicators of attack or compromise • Machine learning • Training models based on patterns from historical data • Predict potential threats • profiling for adversary Identification • Stream Processing
  16. 16. Data Requirements & Description • Streaming event data • Log messages • User activity records • System ops & metrics data • Disparate data sources • Wildly differing data structures 16
  17. 17. Massive Amounts Of Data 17 • One machine can generate 2+ TB per day • Tracking millions of devices • 1 million writes per second - bursty • High % writes, lower % reads • TTL
  18. 18. RETHINKING ARCHITECTURE 18
  19. 19. WE DON'T HAVE TO LOOK FAR TO LOOK BACK 19 Rethinking Architecture
  20. 20. 20 Most batch analytics flow from several years ago looked like...
  21. 21. STREAMING & DATA SCIENCE 21 Rethinking Architecture
  22. 22. Streaming I need fast access to historical data on the fly for predictive modeling with real time data from the stream. 22
  23. 23. Not A Stream, A Flood • Data emitters • Netflix: 1 - 2 million events per second at peak • 750 billion events per day • LinkedIn: > 500 billion events per day • Data ingesters • Netflix: 50 - 100 billion events per day • LinkedIn: 2.5 trillion events per day • 1 Petabyte of streaming data 23
  24. 24. Which Translates To • Do it fast • Do it cheap • Do it at scale 24
  25. 25. Challenges • Code changes at runtime • Distributed Data Consistency • Ordering guarantees • Complex compute algorithms 25
  26. 26. Oh, and don't lose data 26
  27. 27. Strategies • Partition For Scale & Data Locality • Replicate For Resiliency • Share Nothing • Fault Tolerance • Asynchrony • Async Message Passing • Memory Management 27 • Data lineage and reprocessing in runtime • Parallelism • Elastically Scale • Isolation • Location Transparency
  28. 28. AND THEN WE GREEKED OUT 28 Rethinking Architecture
  29. 29. Lambda Architecture A data-processing architecture designed to handle massive quantities of data by taking advantage of both batch and stream processing methods. 29
  30. 30. Lambda Architecture A data-processing architecture designed to handle massive quantities of data by taking advantage of both batch and stream processing methods. • An approach • Coined by Nathan Marz • This was a huge stride forward 30
  31. 31. 31 https://www.mapr.com/developercentral/lambda-architecture
  32. 32. Implementing Is Hard 33 • Real-time pipeline backed by KV store for updates • Many moving parts - KV store, real time, batch • Running similar code in two places • Still ingesting data to Parquet/HDFS • Reconcile queries against two different places
  33. 33. Performance Tuning & Monitoring: on so many systems 34 Also hard
  34. 34. Lambda Architecture An immutable sequence of records is captured and fed into a batch system and a stream processing system in parallel. 35
  35. 35. WAIT, DUAL SYSTEMS? 36 Challenge Assumptions
  36. 36. Which Translates To • Performing analytical computations & queries in dual systems • Implementing transformation logic twice • Duplicate Code • Spaghetti Architecture for Data Flows • One Busy Network 37
  37. 37. Why Dual Systems? • Why is a separate batch system needed? • Why support code, machines and running services of two analytics systems? 38 Counter productive on some level?
  38. 38. YES 39 • A unified system for streaming and batch • Real-time processing and reprocessing • Code changes • Fault tolerance http://radar.oreilly.com/2014/07/questioning-the-lambda- architecture.html - Jay Kreps
  39. 39. ANOTHER ASSUMPTION: ETL 40 Challenge Assumptions
  40. 40. Extract, Transform, Load (ETL) 41 "Designing and maintaining the ETL process is often considered one of the most difficult and resource- intensive portions of a data warehouse project." http://docs.oracle.com/cd/B19306_01/server.102/b14223/ettover.htm
  41. 41. Extract, Transform, Load (ETL) 42 ETL involves • Extraction of data from one system into another • Transforming it • Loading it into another system
  42. 42. Extract, Transform, Load (ETL) "Designing and maintaining the ETL process is often considered one of the most difficult and resource- intensive portions of a data warehouse project." http://docs.oracle.com/cd/B19306_01/server.102/b14223/ettover.htm 43 Also unnecessarily redundant and often typeless
  43. 43. ETL 44 • Each ETL step can introduce errors and risk • Can duplicate data after failover • Tools can cost millions of dollars • Decreases throughput • Increased complexity
  44. 44. ETL • Writing intermediary files • Parsing and re-parsing plain text 45
  45. 45. And let's duplicate the pattern over all our DataCenters 46
  46. 46. 47 These are not the solutions you're looking for
  47. 47. REVISITING THE GOAL & THE STACK 48
  48. 48. Removing The 'E' in ETL Thanks to technologies like Avro and Protobuf we don’t need the “E” in ETL. Instead of text dumps that you need to parse over multiple systems: Scala & Avro (e.g.) • Can work with binary data that remains strongly typed • A return to strong typing in the big data ecosystem 49
  49. 49. Removing The 'L' in ETL If data collection is backed by a distributed messaging system (e.g. Kafka) you can do real-time fanout of the ingested data to all consumers. No need to batch "load". • From there each consumer can do their own transformations 50
  50. 50. #NoMoreGreekLetterArchitectures 51
  51. 51. NoETL 52
  52. 52. Strategy Technologies Scalable Infrastructure / Elastic Spark, Cassandra, Kafka Partition For Scale, Network Topology Aware Cassandra, Spark, Kafka, Akka Cluster Replicate For Resiliency Spark,Cassandra, Akka Cluster all hash the node ring Share Nothing, Masterless Cassandra, Akka Cluster both Dynamo style Fault Tolerance / No Single Point of Failure Spark, Cassandra, Kafka Replay From Any Point Of Failure Spark, Cassandra, Kafka, Akka + Akka Persistence Failure Detection Cassandra, Spark, Akka, Kafka Consensus & Gossip Cassandra & Akka Cluster Parallelism Spark, Cassandra, Kafka, Akka Asynchronous Data Passing Kafka, Akka, Spark Fast, Low Latency, Data Locality Cassandra, Spark, Kafka Location Transparency Akka, Spark, Cassandra, Kafka My Nerdy Chart 53
  53. 53. SMACK • Scala/Spark • Mesos • Akka • Cassandra • Kafka 54
  54. 54. Spark Streaming 55
  55. 55. Spark Streaming • One runtime for streaming and batch processing • Join streaming and static data sets • No code duplication • Easy, flexible data ingestion from disparate sources to disparate sinks • Easy to reconcile queries against multiple sources • Easy integration of KV durable storage 56
  56. 56. How do I merge historical data with data in the stream? 57
  57. 57. Join Streams With Static Data val ssc = new StreamingContext(conf, Milliseconds(500)) ssc.checkpoint("checkpoint") val staticData: RDD[(Int,String)] = ssc.sparkContext.textFile("whyAreWeParsingFiles.txt").flatMap(func) val stream: DStream[(Int,String)] = KafkaUtils.createStream(ssc, zkQuorum, group, Map(topic -> n)) .transform { events => events.join(staticData)) .saveToCassandra(keyspace,table) ssc.start() 58
  58. 58. Training Data Feature Extraction Model Training Model Testing Test Data Your Data Extract Data To Analyze Train your model to predict Spark MLLib 59
  59. 59. Spark Streaming & ML 60 val context = new StreamingContext(conf, Milliseconds(500)) val model = KMeans.train(dataset, ...) // learn offline val stream = KafkaUtils .createStream(ssc, zkQuorum, group,..) .map(event => model.predict(event.feature))
  60. 60. Apache Mesos Open-source cluster manager developed at UC Berkeley. Abstracts CPU, memory, storage, and other compute resources away from machines (physical or virtual), enabling fault-tolerant and elastic distributed systems to easily be built and run effectively. 61
  61. 61. Akka High performance concurrency framework for Scala and Java • Fault Tolerance • Asynchronous messaging and data processing • Parallelization • Location Transparency • Local / Remote Routing • Akka: Cluster / Persistence / Streams 62
  62. 62. Akka Actors A distribution and concurrency abstraction • Compute Isolation • Behavioral Context Switching • No Exposed Internal State • Event-based messaging • Easy parallelism • Configurable fault tolerance 63
  63. 63. 64 Akka Actor Hierarchy http://www.slideshare.net/jboner/building-reactive-applications-with-akka-in-scala
  64. 64. import akka.actor._ class NodeGuardianActor(args...) extends Actor with SupervisorStrategy { val temperature = context.actorOf( Props(new TemperatureActor(args)), "temperature") val precipitation = context.actorOf( Props(new PrecipitationActor(args)), "precipitation") override def preStart(): Unit = { /* lifecycle hook: init */ } def receive : Actor.Receive = { case Initialized => context become initialized } def initialized : Actor.Receive = { case e: SomeEvent => someFunc(e) case e: OtherEvent => otherFunc(e) } } 65
  65. 65. Apache Cassandra • Extremely Fast • Extremely Scalable • Multi-Region / Multi-Datacenter • Always On • No single point of failure • Survive regional outages • Easy to operate • Automatic & configurable replication 66
  66. 66. Apache Cassandra • Very flexible data modeling (collections, user defined types) and changeable over time • Perfect for ingestion of real time / machine data • Huge community 67
  67. 67. Spark Cassandra Connector • NOSQL JOINS! • Write & Read data between Spark and Cassandra • Compatible with Spark 1.4 • Handles Data Locality for Speed • Implicit type conversions • Server-Side Filtering - SELECT, WHERE, etc. • Natural Timeseries Integration 68 http://github.com/datastax/spark-cassandra-connector
  68. 68. KillrWeather 69 http://github.com/killrweather/killrweather A reference application showing how to easily integrate streaming and batch data processing with Apache Spark Streaming, Apache Cassandra, Apache Kafka and Akka for fast, streaming computations on time series data in asynchronous event-driven environments. http://github.com/databricks/reference-apps/tree/master/timeseries/scala/timeseries-weather/src/main/scala/com/ databricks/apps/weather
  69. 69. 70 • High Throughput Distributed Messaging • Decouples Data Pipelines • Handles Massive Data Load • Support Massive Number of Consumers • Distribution & partitioning across cluster nodes • Automatic recovery from broker failures
  70. 70. Spark Streaming & Kafka val context = new StreamingContext(conf, Seconds(1)) val wordCount = KafkaUtils.createStream(context, ...) .flatMap(_.split(" ")) .map(x => (x, 1)) .reduceByKey(_ + _) wordCount.saveToCassandra(ks,table) context.start() // start receiving and computing 71
  71. 71. 72 class KafkaStreamingActor(params: Map[String, String], ssc: StreamingContext) extends AggregationActor(settings: Settings) {
 import settings._ 
 val kafkaStream = KafkaUtils.createStream[String, String, StringDecoder, StringDecoder](
 ssc, params, Map(KafkaTopicRaw -> 1), StorageLevel.DISK_ONLY_2)
 .map(_._2.split(","))
 .map(RawWeatherData(_))
 
 kafkaStream.saveToCassandra(CassandraKeyspace, CassandraTableRaw)
 /** RawWeatherData: wsid, year, month, day, oneHourPrecip */
 kafkaStream.map(hour => (hour.wsid, hour.year, hour.month, hour.day, hour.oneHourPrecip))
 .saveToCassandra(CassandraKeyspace, CassandraTableDailyPrecip)
 
 /** Now the [[StreamingContext]] can be started. */
 context.parent ! OutputStreamInitialized
 
 def receive : Actor.Receive = {…} } Gets the partition key: Data Locality Spark C* Connector feeds this to Spark Cassandra Counter column in our schema, no expensive `reduceByKey` needed. Simply let C* do it: not expensive and fast.
  72. 72. 73 /** For a given weather station, calculates annual cumulative precip - or year to date. */
 class PrecipitationActor(ssc: StreamingContext, settings: WeatherSettings) extends AggregationActor {
 
 def receive : Actor.Receive = {
 case GetPrecipitation(wsid, year) => cumulative(wsid, year, sender)
 case GetTopKPrecipitation(wsid, year, k) => topK(wsid, year, k, sender)
 }
 
 /** Computes annual aggregation.Precipitation values are 1 hour deltas from the previous. */
 def cumulative(wsid: String, year: Int, requester: ActorRef): Unit =
 ssc.cassandraTable[Double](keyspace, dailytable)
 .select("precipitation")
 .where("wsid = ? AND year = ?", wsid, year)
 .collectAsync()
 .map(AnnualPrecipitation(_, wsid, year)) pipeTo requester
 
 /** Returns the 10 highest temps for any station in the `year`. */
 def topK(wsid: String, year: Int, k: Int, requester: ActorRef): Unit = {
 val toTopK = (aggregate: Seq[Double]) => TopKPrecipitation(wsid, year,
 ssc.sparkContext.parallelize(aggregate).top(k).toSeq)
 
 ssc.cassandraTable[Double](keyspace, dailytable)
 .select("precipitation")
 .where("wsid = ? AND year = ?", wsid, year)
 .collectAsync().map(toTopK) pipeTo requester
 }
 }
  73. 73. A New Approach • One Runtime: streaming, scheduled • Simplified architecture • Allows us to • Write different types of applications • Write more type safe code • Write more reusable code 74
  74. 74. Need daily analytics aggregate reports? Do it in the stream, save results in Cassandra for easy reporting as needed - with data locality not offered by S3.
  75. 75. FiloDB Distributed, columnar database designed to run very fast analytical queries • Ingest streaming data from many streaming sources • Row-level, column-level operations and built in versioning offer greater flexibility than file-based technologies • Currently based on Apache Cassandra & Spark • github.com/tuplejump/FiloDB 76
  76. 76. FiloDB • Breakthrough performance levels for analytical queries • Performance comparable to Parquet • One to two orders of magnitude faster than Spark on Cassandra 2.x • Versioned - critical for reprocessing logic/code changes • Can simplify your infrastructure dramatically • Queries run in parallel in Spark for scale-out ad-hoc analysis • Space-saving techniques 77
  77. 77. WRAPPING UP 78
  78. 78. Architectyr? 79 "This is a giant mess" - Going Real-time - Data Collection and Stream Processing with Apache Kafka, Jay Kreps
  79. 79. 80 Simplified
  80. 80. 81
  81. 81. 82 www.tuplejump.com info@tuplejump.com@tuplejump
  82. 82. 83 @helenaedelson github.com/helena slideshare.net/helenaedelson THANK YOU!
  83. 83. I'm speaking at QCon SF on the broader topic of Streaming at Scale http://qconsf.com/sf2015/track/streaming-data-scale 84

×