Scala like distributed collections - dumping time-series data with apache spark

Scala-like Distributed Collections:
Dumping Time-Series Data With
Apache Spark
Demi Ben-Ari - CTO @ Panorays

About Me
Demi Ben-Ari, Co-Founder & CTO @ Panorays
●  BS’c Computer Science – Academic College Tel-Aviv Yaffo
●  Co-Founder “Big Things” Big Data Community
In the Past:
●  Sr. Data Engineer - Windward
●  Team Leader & Sr. Java Software Engineer,
Missile defense and Alert System - “Ofek” – IAF
Interested in almost every kind of technology – A True Geek

Agenda
●  Scala and Spark analogies
●  Data flow and Environment
●  What’s our time series data like?
●  Where we started from - where we got to
○  Problems and our decisions
●  Conclusions

Scala is...
●  Functional
●  Object Oriented
●  Statically typed
●  Interoperates well with Java and Javascript
○  JVM based

DSLs on top of Scala
SBT
Spiral
Scalaz
Slick
Dispatch
Chisel
Specs
Opti{X}
shapeless
ScalaTest
Squeryl

Scala & Spark (Architecture)
Scala REPL Scala Compiler
Spark Runtime
Scala Runtime
JVM
File System
(eg. HDFS,
Cassandra, S3..)
Cluster Manager
(eg. Yarn, Mesos)

What kind of DSL is Apache Spark
●  Centered around Collections
●  Immutable data sets equipped with functional transformations
●  These are exactly the Scala collection operations
map
flatMap
filter
...
reduce
fold
aggregate
...
union
intersection
...

Spark vs. Scala Collections
●  So, Spark is exactly Scala Collections, but running in a Cluster?
●  Not quite. There are Two main differences:
○  Spark is Lazy, Scala collections are strict
○  Spark has added functionality, eg. PairRDDs.
■  Gives us the power doing lots of operations in the NoSQL distributed
world

Collections Design Choices
Imperative Functional
Strict Lazy
VS
VS
java.util scala.collections.immutable
Scala
OCaml
Spark
C#
Scala Streams, views

Spark is A Multi-Language Platform
●  Why to use Scala instead of
Python?
○  Native to Spark, Can use
everything without
translation
○  Types help

So Bottom Line…
What’s Spark???

United Tools Platform - Single Framework
Batch
InteractiveStreaming
Single Framework

Spark Standalone Cluster - Architecture
●  Master
●  History
Server
●  etc
Master
Core 3
Core 4
Core 2
Worker Memory
Core 1Slave
Slave
Slave
Slave
Core 3
Core 4
Core 2
Worker Memory
Core 1
Core 3
Core 4
Core 2
Worker Memory
Core 1
Slave
Core 3
Core 4
Core 2
Worker Memory
Core 1
Core 3
Core 4
Core 2
Worker Memory
Core 1
Slave
Slave
Slave

Data flow and Environment
(Our Use Case)

Structure of the Data
●  Geo Locations + Metadata
●  Arriving over time
●  Different types of messages being reported by sattelites
●  Encoded
●  Might arrive later than acttually transmitted

Data Flow Diagram
Externa
l Data
Source
Analytics
Layers
Data Pipeline
Parsed
Raw
Entity Resolution
Process
Building insights
on top of the entities
Data
Output
Layer
Anomaly
Detection
Trends

Environment Description
Cluster
Dev Testing
Live
Staging
ProductionEnv
OB1K
RESTful Java
Services

Basic Terms
●  Idempotence
is the property of certain operations in mathematics and computer
science, that can be applied multiple times without changing the
result beyond the initial application.
●  Function: Same input => Same output

Basic Terms
●  Missing Parts in Time Series Data
◦  Data arriving from the satellites
⚫  Might be causing delays because of bad transmission
◦  Data vendors delaying the data stream
◦  Calculation in Layers may cause Holes in the Data
●  Calculating the Data layers by time slices

Basic Terms
●  Partitions == Parallelizm
◦  Physical / Logical partitioning
●  Resilient Distributed Datasets (RDDs) == Collections
◦  fault-tolerant collection of elements that can be operated on in
parallel.
◦  Applying immutable transformations and actions over RDDs

The Problem - Receiving
DATA
Beginning state, no data, and the timeline
begins
T = 0
Level 3
Entity
Level 2
Entity
Level 1
Entity

DATA
T = 10
Level 3
Entity
Level 2
Entity
Level 1
Entity
Computation sliding window size
Level 1 entities data
arrives and gets stored

DATA
T = 10
Level 3
Entity
Level 2
Entity
Level 1
Entity
Level 3 entities are created
on top of Level 2’s Data
(Decreased amount of data)
Level 2 entities are
created on top of Level 1’s
Data
(Decreased amount of
data)

DATA
T = 20
Level 3
Entity
Level 2
Entity
Level 1
Entity
Because of the sliding window’s
back size, level 2 and 3 entities
would not be created properly
and there would be “Holes” in the
Data
Level 1 entity's
data arriving late

Solution to the Problem
●  Creating Dependent Micro services forming a data pipeline
◦  Mainly Apache Spark applications
◦  Services are only dependent on the Data - not the previous
service’s run
●  Forming a structure and scheduling of “Back Sliding Window”
◦  Know your data and it’s relevance through time
◦  Don’t try to foresee the future – it might Bias the results

Starting point & Infrastructure

How we started?
●  Spark Standalone – via ec2 scripts
◦  Around 5 nodes (r3.xlarge instances)
◦  Didn’t want to keep a persistent HDFS – Costs a lot
◦  100 GB (per day) => ~150 TB for 4 years
◦  Cost for server per year (r3.xlarge):
●  On demand: ~2900$
●  Reserved: ~1750$
●  Know your costs: http://www.ec2instances.info/

Decision
●  Working with S3 as the persistence layer
◦  Pay extra for
●  Put (0.005 per 1000 requests)
●  Get (0.004 per 10,000 requests)
◦  150TB => ~210$ for 4 years of Data
●  Same format as HDFS (CSV files)
◦  s3n://some-bucket/entity1/201412010000/part-00000
◦  s3n://some-bucket/entity1/201412010000/part-00001
◦  ……

MongoDB for Serving
Worker 1
Worker 2
….
….
…
…
Worker N
MongoDB
Replica
Set
Spark
Cluster
Master
Write
Read

Spark Slave - Server Specs
●  Instance Type: r3.xlarge
●  CPU’s: 4
●  RAM: 30.5GB
●  Storage: ephemeral
●  Amount: 10+

MongoDB - Server Specs
●  MongoDB version: 2.6.1
●  Instance Type: m3.xlarge (AWS)
●  CPU’s: 4
●  RAM: 15GB
●  Storage: EBS
●  DB Size: ~500GB
●  Collection Indexes: 5 (4 compound)

The Problem
●  Batch jobs
◦  Should run for 5-10 minutes in total
◦  Actual - runs for ~40 minutes
●  Why?
◦  ~20 minutes to write with the Java mongo driver – Async
(Unacknowledged)
◦  ~20 minutes to sync the journal
◦  Total: ~ 40 Minutes of the DB being unavailable
◦  No batch process response and no UI serving

Alternative Solutions
●  Sharded MongoDB (With replica sets)
◦  Pros:
●  Increases Throughput by the amount of shards
●  Increases the availability of the DB
◦  Cons:
●  Very hard to manage DevOps wise (for a small team of
developers)
●  High cost of servers – because each shared need 3 replicas

Workflow with MongoDB
Worker 1
Worker 2
….
….
…
…
Worker N
Spark
Cluster
Master
Write
Read
Master

Our DevOps – After that solution
We had no
DevOps guy at
that time at all
☹

Alternative Solutions
●  Apache Cassandra
◦  Pros:
●  Very large developer community
●  Linearly scalable Database
●  No single master architecture
●  Proven working with distributed engines like Apache Spark
◦  Cons:
●  We had no experience at all with the Database
●  No Geo Spatial Index – Needed to implement by ourselves

The Solution
●  Migration to Apache Cassandra
●  Create easily a Cassandra cluster using DataStax Community AMI
on AWS
◦  First easy step – Using the spark-cassandra-connector
(Easy bootstrap move to Spark ⬄ Cassandra)
◦  Creating a monitoring dashboard to Cassandra

Workflow with Cassandra
Worker 1
Worker 2
….
….
…
…
Worker N
Cassandr
a
Cluster
Spark
Cluster
Write
Read

Result
●  Performance improvement
◦  Batch write parts of the job run in 3 minutes instead of ~ 40
minutes in MongoDB
●  Took 2 weeks to go from “Zero to Hero”, and to ramp up a running
solution that work without glitches

So what’s the problem
(Again)?

Transferring the Heaviest Process
●  Micro service that runs every 10 minutes
●  Writes to Cassandra 30GB per iteration
◦  (Replication factor 3 => 90GB)
●  At first took us 18 minutes to do all of the writes
◦  Not Acceptable in a 10 minute process

Transferring the Heaviest Process
●  Solutions
◦  We chose the i2.xlarge
◦  Optimization of the Cluster
◦  Changing the JDK to Java-8
●  Changing the GC algorithm to G1
◦  Tuning the Operation system
●  Ulimit, removing the swap
◦  Write time went down to ~5 minutes (For 30GB RF=3)
Sounds good right? I don’t think so

The Solution
●  Taking the same Data Model that we held in Cassandra (All of the
Raw data per 10 minutes) and put it on S3
◦  Write time went down from ~5 minutes to 1.5 minutes
●  Added another process, not dependent on the main one, happens
every 15 minutes
◦  Reads from S3, downscales the amount and Writes them to
Cassandra for serving

How it looks after all?
Parsed
Raw
Static /
Aggregated
Data
Spark Analytics Layers
UI Serving
Downscale
d Data
Heavy
Fusion
Process

Conclusion
●  Always give an estimate to your data
◦  Frequency
◦  Volume
◦  Arrangement of the previous phase
●  There is no “Best” persistence layer
◦  There is the right one for the job
◦  Don’t overload an existing solution

Conclusion
●  Spark is a great framework for distributed collections
◦ Fully functional API
◦ Can perform imperative actions
● “With great power,
comes lots of partitioning”
◦ Control your work and
data distribution via partitions
●  https://www.pinterest.com/pin/155514993354583499/ (Thanks)

Thanks! my contact:
—Demi Ben-Ari
●  LinkedIn
●  Twitter: @demibenari
●  Blog: http://progexc.blogspot.com/
●  Email: demi.benari@gmail.com
●  “Big Things” Community
–Meetup, YouTube, Facebook, Twitter

Scala like distributed collections - dumping time-series data with apache spark

More Related Content

What's hot (20)

Similar to Scala like distributed collections - dumping time-series data with apache spark (20)

More from Demi Ben-Ari (20)

Recently uploaded (20)

Scala like distributed collections - dumping time-series data with apache spark