Streaming Analytics with Spark, Kafka, Cassandra and Akka by Helena Edelson
-
Upload
spark-summit -
Category
Data & Analytics
-
view
5.414 -
download
1
Transcript of Streaming Analytics with Spark, Kafka, Cassandra and Akka by Helena Edelson
Streaming Analytics with Spark, Kafka, Cassandra, and Akka
Helena Edelson VP of Product Engineering @Tuplejump
• 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
[email protected]/helena
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
3
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
THE PROBLEM DOMAINDelivering Meaning From A Flood Of Data
5
The Problem DomainNeed to build scalable, fault tolerant, distributed data processing systems that can handle massive amounts of data from disparate sources, with different data structures.
6
TranslationHow to build adaptable, elegant systems for complex analytics and learning tasks to run as large-scale clustered dataflows
7
How Much Data
Yottabyte = quadrillion gigabytes or septillion bytes
8
We all have a lot of data • Terabytes • Petabytes...
https://en.wikipedia.org/wiki/Yottabyte
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
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 loose data?
And stay within our AWS / Rackspace budget
EXAMPLE CASE: CYBER SECURITY
Hunting The Hunter
12
13
• 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
14
• 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
Data Requirements & Description• Streaming event data
• Log messages • User activity records • System ops & metrics data
• Disparate data sources • Wildly differing data structures
15
Massive Amounts Of Data
16
• One machine can generate 2+ TB per day • Tracking millions of devices • 1 million writes per second - bursty • High % writes, lower % reads • TTL
RETHINKING ARCHITECTURE
17
WE DON'T HAVE TO LOOK FAR TO LOOK BACK
18
Rethinking Architecture
19
Most batch analytics flow from several years ago looked like...
STREAMING & DATA SCIENCE
20
Rethinking Architecture
StreamingI need fast access to historical data on the fly for predictive modeling with real time data from the stream.
21
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 data22
Which Translates To• Do it fast • Do it cheap • Do it at scale
23
Challenges• Code changes at runtime • Distributed Data Consistency • Ordering guarantees • Complex compute algorithms
24
Oh, and don't lose data
25
Strategies• Partition For Scale & Data Locality • Replicate For Resiliency • Share Nothing • Fault Tolerance • Asynchrony • Async Message Passing • Memory Management
26
• Data lineage and reprocessing in runtime • Parallelism • Elastically Scale • Isolation • Location Transparency
AND THEN WE GREEKED OUT
27
Rethinking Architecture
Lambda ArchitectureA data-processing architecture designed to handle massive quantities of data by taking advantage of both batch and stream processing methods.
28
Lambda ArchitectureA 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
29
30https://www.mapr.com/developercentral/lambda-architecture
Implementing Is Hard
32
• 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
Performance Tuning & Monitoring: on so many systems
33
Also hard
Lambda ArchitectureAn immutable sequence of records is captured and fed into a batch system and a stream processing system in parallel.
34
WAIT, DUAL SYSTEMS?
35
Challenge Assumptions
Which Translates To• Performing analytical computations & queries in dual
systems • Implementing transformation logic twice • Duplicate Code • Spaghetti Architecture for Data Flows • One Busy Network
36
Why Dual Systems?• Why is a separate batch system needed? • Why support code, machines and running services of
two analytics systems?
37
Counter productive on some level?
YES
38
• 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
ANOTHER ASSUMPTION: ETL
39
Challenge Assumptions
Extract, Transform, Load (ETL)
40
"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
Extract, Transform, Load (ETL)
41
ETL involves • Extraction of data from one system into another • Transforming it • Loading it into another system
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
42
Also unnecessarily redundant and often typeless
ETL
43
• Each ETL step can introduce errors and risk • Can duplicate data after failover • Tools can cost millions of dollars • Decreases throughput • Increased complexity
ETL
• Writing intermediary files • Parsing and re-parsing plain text
44
And let's duplicate the pattern over all our DataCenters
45
46
These are not the solutions you're looking for
REVISITING THE GOAL & THE STACK
47
Removing The 'E' in ETLThanks 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
48
Removing The 'L' in ETLIf 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
49
#NoMoreGreekLetterArchitectures
50
NoETL
51
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
52
SMACK• Scala/Spark • Mesos • Akka • Cassandra • Kafka
53
Spark Streaming
54
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
55
How do I merge historical data with data in the stream?
56
Join Streams With Static Dataval 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()
57
Training Data
Feature Extraction
Model Training
Model Testing
Test Data
Your Data Extract Data To Analyze
Train your model to predict
Spark MLLib
58
Spark Streaming & ML
59
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))
Apache MesosOpen-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.
60
AkkaHigh performance concurrency framework for Scala and Java • Fault Tolerance • Asynchronous messaging and data processing • Parallelization • Location Transparency • Local / Remote Routing • Akka: Cluster / Persistence / Streams
61
Akka ActorsA distribution and concurrency abstraction • Compute Isolation • Behavioral Context Switching • No Exposed Internal State • Event-based messaging • Easy parallelism • Configurable fault tolerance
62
63
Akka Actor Hierarchy
http://www.slideshare.net/jboner/building-reactive-applications-with-akka-in-scala
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) } }
64
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 65
Apache Cassandra• Very flexible data modeling (collections, user defined
types) and changeable over time • Perfect for ingestion of real time / machine data • Huge community
66
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
67
http://github.com/datastax/spark-cassandra-connector
KillrWeather
68
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
• 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
Spark Streaming & Kafkaval 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
70
71
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 LocalitySpark 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
/** 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 }}
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
73
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.
FiloDBDistributed, 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
75
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
76
WRAPPING UP
77
Architectyr?
78"This is a giant mess"
- Going Real-time - Data Collection and Stream Processing with Apache Kafka, Jay Kreps
79
Simplified
80
82
@helenaedelsongithub.com/helenaslideshare.net/helenaedelson
THANK YOU!
I'm speaking at QCon SF on the broader topic of Streaming at Scale
http://qconsf.com/sf2015/track/streaming-data-scale
83