UVA HPC & BIG DATA COURSE

Introduction to Big Data

Adam Belloum
 Content

•  General Introduction
•  Definitions
•  Data Analytics
•  Solutions for Big Data Analytics
•  The Network (Internet)
•  When to consider BigData solution
•  Scientific e-infrastructure – some challenges to
overcome
 Jim Gray Vision in 2007
•  “ We have to do better at producing tools to support the whole research cycle—
from data capture and data curation to data analysis and data visualization. Today, the
tools for capturing data both at the mega-scale and at the milli-scale are just dreadful.
After you have captured the data, you need to curate it before you can start doing
any kind of data analysis, and we lack good tools for both data curation and data
analysis.”

•  “Then comes the publication of the results of your research, and the published
literature is just the tip of the data iceberg. By this I mean that people collect a lot of
data and then reduce this down to some number of column inches in Science or
Nature—or 10 pages if it is a computer science person writing. So what I mean by
data iceberg is that there is a lot of data that is collected but not curated or published
in any systematic way. “
Based on the transcript of a talk given by Jim Gray
to the NRC-CSTB1 in Mountain View, CA, on January 11, 2007
 Data keep on growing
•  Google processes 20 PB a day (2008)
•  Wayback Machine has 3 PB + 100 TB/month (3/2009)
•  Facebook has 2.5 PB of user data + 15 TB/day (4/2009)
•  eBay has 6.5 PB of user data + 50 TB/day (5/2009)
•  CERN’s Large Hydron Collider (LHC) generates 15 PB a
year

4  
BigData.pptx  -­‐  Computer  Science  www.cs.kent.edu/~jin/Cloud12Spring/BigData.pptx  
Data is Big If It is Measured in MW

•  A good sweet spot for a data center is 15 MW

•  Facebook’s leased data centers are typically
between 2.5 MW and 6.0 MW.
•  Facebook’s Pineville data center is 30 MW
•  Google’s computing infrastructure uses 260 MW

Robert  Grossman,  Collin  BenneC  University  of  Chicago  Open  Data  Group  
 Big data was big news in 2012

•  and probably in 2013 too.

•  The Harvard Business Review talks about it as

“The Management Revolution”.

•  The Wall Street Journal

“Meet the New Big Data”,
“Big Data is on the Rise,
Bringing Big Questions”.
 BigData is the new hype

By  the  end  of  2011  

the  world  had  an  es7mated  1.8  ze<abytes  (trillion  gigabytes)  of  data  and  it  is  es7mated  to  
7  
grow  to  35  ze<abytes  in  the  next  few  years  
 Where Big Data Comes From?
•  Big Data is not Specific application
type, but rather a trend –or even
a collection of Trends- napping
multiple application types
•  Data growing in multiple ways
–  More data (volume of data )
–  More Type of data (variety of data)
–  Faster Ingest of data (velocity of
data)
–  More Accessibility of data (internet,
instruments , …)
–  Data Growth and availability exceeds
organization ability to make
intelligent decision based on it

Addison  Snell  CEO.  Intersect360,  Research    

 How to deal with Big Data
Advice From Jim Gray

1.  Analysing Big data requires scale‐out solutions not

scale-up solutions
2.  Move the analysis to the data.
3.  Work with scientists to find the most common “20
queries” and make them fast.
4.  Go from “working to working.”

Source:  Robert  Grossman,  Collin  Bennec  University  of  Chicago  Open  Data  Group  
 content

•  General Introduction
•  Definitions
•  Data Analytics
•  Solutions for Big Data Analytics
•  The Network (Internet)
•  When to consider BigData solution
•  Scientific e-infrastructure – some challenges to
overcome
 How do We Define Big Data

•  Big in Big Data refers to:

–  Big size is the primary definition.
–  Big complexity rather than big
volume. it can be small and not all
large datasets are big data
–  size matters... but so does
accessibility, interoperability and
reusability.

•  define Big Data using 3 Vs; namely:

–  volume, variety, velocity

Big  Data  -­‐  Back  to  mine   11  

 volume, variety, and velocity

•  Aggregation that used to be measured

in petabytes (PB) is now referenced by
a term: zettabytes (ZB).
–  A zettabyte is a trillion gigabytes (GB)
–  or a billion terabytes

•  in 2010, we crossed the 1ZB marker,

and at the end of 2011 that number
was estimated to be 1.8ZB
 volume, variety, and velocity

•  The variety characteristic of Big

Data is really about trying to
capture all of the data that pertains
to our decision-making process.

•  Making sense out of unstructured

data, such as opinion, or analysing
images.
 volume, variety, and velocity
(Type of Data)
•  Relational Data (Tables/Transaction/Legacy Data)
•  Text Data (Web)
•  Semi-structured Data (XML)
•  Graph Data
–  Social Network, Semantic
Web (RDF), …
•  Streaming Data
–  You can only scan the data
once
 volume, variety, and velocity

•  velocity is the rate at which

data arrives at the enterprise
and is processed or well
understood

•  In other terms “How long does

it take you to do something
about it or know it has even
arrived?”
volume, variety, and velocity

Today,  it  is  possible  using  real-­‐Rme  analyRcs  to  

opRmize  Like  ()        buWons  across  both  website  
and  on  Facebook.    
FaceBook  use  anonymised  data  to  show    the  
number  of  Rmes  people:  
•   saw  Like  buWons,    
•  clicked  Like  buWons,    
•  saw  Like  stories  on  Facebook,    
•  and  clicked  Like  stories  to  visit  a  given  
website.  
 
 volume, variety, velocity, and veracity

•  Veracity refers to the quality or trustworthiness of

the data.

•  A common complication is that the data is

saturated with both useful signals and lots of noise
(data that can’t be trusted)

LHC ATLAS detector generates about 1 Petabyte raw data per

second, during the collision time (about 1 ms)
Big Data platform must include the six
key imperatives

The  Big  Data  plaYorm  manifesto:  imperaRves  and  underlying  technologies  

 content

•  General Introduction
•  Definitions
•  Data Analytics
•  Solutions for Big Data Analytics
•  The Network (Internet)
•  When to consider BigData solution
•  Scientific e-infrastructure – some challenges to
overcome
 Data Analytics

Analytics Characteristics are not new

•  Value: produced when the analytics output is put into
action
•  Veracity: measure of accuracy and timeliness
•  Quality:
–  well-formed data
–  Missing values
–  cleanliness
•  Latency: time between measurement and availability
•  Data types have differing pre-analytics needs
 The Real Time Boom..
Facebook  Real  Time     SaaS Real Time Google Real Time
Social  AnalyRcs     User Tracking Web Analytics

Twitter paid tweet analytics New Real Time Google Real Time Search
Analytics Startups..

® Copyright 2011 Gigaspaces Ltd. All Rights

21   Reserved
 Example of Analytics 
(from Analytics @ Twitter )

•  Counting
–  How many request/day?
–  What’s the average latency?
–  How many signups, sms, tweets?

•  Correlating
–  Desktop vs Mobile user ?
–  What devices fail at the same time?
–  What features get user hooked?

•  Researching
–  What features get re-tweeted
–  Duplicate detection
–  Sentiment analysis

® Copyright 2011 Gigaspaces Ltd. All Rights

Reserved
 Skills required for Big Data Analytics
(A.K.A Data Science)
•  Store and process
–  Large scale databases
–  Software Engineering
–  System/network Engineering

•  Analyse and model

–  Reasoning
–  Knowledge Representation
–  Multimedia Retrieval
–  Modelling and Simulation
–  Machine Learning
–  Information Retrieval

•  Understand and design

–  Decision theory
–  Visual analytics
–  Perception Cognition

Nancy  Grady,  PhD,  SAIC  Co-­‐Chair  DefiniRons  and  Taxonomy  Subgroup  NIST  Big  Data  Working  
Group  
 content

•  General Introduction
•  Definitions
•  Data Analytics
•  Solutions for Big Data Analytics
•  The Network (Internet)
•  When to consider BigData solution
•  Scientific e-infrastructure – some challenges to
overcome
Traditional analytics applications

•  Scale-up Database
–  Use traditional SQL database
–  Use stored procedure for event driven reports
–  Use flash-based disks to reduce disk I/O
–  Use read only replica to scale-out read queries

•  Limitations
–  Doesn’t scale on write
–  Extremely expensive (HW + SW)
® Copyright 2011 Gigaspaces Ltd. All Rights
25 Reserved
 CEP – Complex Event Processing

•  Process the data as it comes

•  Maintain a window of the data in-memory
•  Pros:
–  Extremely low-latency
–  Relatively low-cost

•  Cons
–  Hard to scale (Mostly limited to scale-up)
–  Not agile - Queries must be pre-generated
–  Fairly complex
26
 In Memory Data Grid

•  Distributed in-memory
database
–  Scale out (Horizontal scaling)

•  Pros
–  Scale on write/read
–  Fits to event driven (CEP style) , ad-hoc query model

•  Cons
-  Cost of memory vs disk
-  Memory capacity is limited

® Copyright 2011 Gigaspaces Ltd. All Rights

27 Reserved
In Memory Data Grid products

•  Hazelcast
hazelcast.org
•  JBOSS Infinispan
www.infinispan.org
•  IBM eXtreme Scale:
ibm.com/software/products/en/websphere-extreme-scale
•  Gigaspace XAP Elastic caching edition:
www.gigaspaces.com/xap-in-memory-caching-scaling/datagrid
•  Oracle Coherence
www.oracle.com/technetwork/middleware/coherence
•  Terracotta entreprise suite
www.terracotta.org/products/enterprise-suite
•  Pivotal Gemfire
pivotal.io/big-data/pivotal-gemfire
 NoSQL

•  Use distributed database

–  Hbase, Cassandra, MongoDB

•  Pros
–  Scale on write/read
–  Elastic

•  Cons
–  Read latency
–  Consistency tradeoffs are hard
–  Maturity – fairly young technology

® Copyright 2011 Gigaspaces Ltd. All Rights

29 Reserved
NoSQL

Bill  Howe,  UW    

 Hadoop MapReudce

•  Distributed batch
processing
•  Pros
–  Designed to process
massive amount of data
–  Mature
–  Low cost

•  Cons
–  Not real-time

31
 Sorting 1 TB of DATA
•  Estimate:
–  read 100MB/s, write 100MB/s
–  no disk seeks, instant sort
–  341 minutes → 5.6 hours

•  The terabyte benchmark

winner (2008):
–  209 seconds (3.48 minutes)
–  910 nodes x (4 dual-core
processors, 4 disks, 8 GB
memory)

•  October 2012
–  ? see
http://www.youtube.com/watch?
v=XbUPlbYxT8g&feature=youtu.be

32  
 MapReduce vs. Databases

•  A. Pavlo, et al. "A comparison of approaches to

large-scale data analysis," in SIGMOD ’09:
Proceedings of the 35th SIGMOD international
conference on Management of data, New York, NY,
USA, 2009, pp. 165-178
•  Conclusions: … at the scale of the experiments we
conducted, both parallel database systems
displayed a significant performance advantage over
Hadoop MR in executing a variety of data intensive
analysis benchmarks.
 Hadoop Map/Reduce – Reality
check..
“With  the  paths  that  go  through  Hadoop  [at  Yahoo!],  the  
latency  is  about  fieeen  minutes.  …  [I]t  will  never  be  true  
real-­‐Rme..”  (Yahoo  CTO  Raymie  Stata)

Hadoop/Hive..Not  realRme.  Many  dependencies.  Lots  of  

points  of  failure.  Complicated  system.  Not  dependable  
enough  to  hit  realRme  goals  (  Alex  Himel,  Engineering  
Manager  at  Facebook.)
The image cannot be displayed. Your computer may not have
enough memory to open the image, or the image may have
been corrupted. Restart your computer, and then open the
file again. If the red x still appears, you may have to delete
the image and then insert it again.

"MapReduce  and  other  batch-­‐processing  systems  cannot  

process  small  updates  individually  as  they  rely  on  creaRng  
large  batches  for  efficiency,“    (Google  senior  director  of  
engineering  Eisar  Lipkovitz)

® Copyright 2011 Gigaspaces Ltd. All Rights

34 Reserved
 Map Reduce

R  
M   E  
Very     ParRRoning  
A   D   Result  
big   FuncRon  
P   U  
data  
C  
E  

•  Map: •  Reduce :
–  Accepts –  Accepts
•  input key/value pair •  intermediate key/value* pair
–  Emits –  Emits
•  intermediate key/value pair •  output key/value pair

35  
WING  Group  MeeRng,  13  Oct  2006  Hendra  SeRawan  
 Apache Spark 
Lightning-fast cluster computing

•  Generality
–  Combine SQL, streaming, complex analytics.
•  Runs Everywhere
–  Spark runs on Hadoop, Mesos, standalone,
or in the cloud. It can access diverse data
sources (HDFS, Cassandra, HBase, and S3)
•  Ease of Use
–  Write applications quickly in Java, Scala,
Python, R.
 Apache Storm
By  Nathan  Marz  

•  Storm is a distributed real-time

computation system that solves
typical
–  downsides of queues & workers
systems.
–  Built with Big Data in mind (the
“Hadoop of realtime”).
•  Storm Trident (high level
abstraction over Storm core)
–  Micro-batching (~ streaming)
 Apache Kafka
A high-throughput distributed messaging system

•  Apache Kafka is publish-subscribe messaging

rethought as a distributed commit log.

•  Kafka maintains feeds of messages in

categories called topics.
–  Processes can publish messages to a Kafka (topic
producers).

–  processes can subscribe to topics and process

the feed of published messages consumers.

•  Kafka is run as a cluster comprised of one or

more servers each of which is called a broker.
Performance
 content

•  General Introduction
•  Definitions
•  Data Analytics
•  Solutions for Big Data Analytics
•  The Network (Internet)
•  When to consider BigData solution
•  Scientific e-infrastructure – some challenges to
overcome
 The problem

•  TCP Was never designed to move large datasets

over wide area high Performance Networks.

•  For loading a webpage, TCP is great.

•  For sustained data transfer, it is far from ideal.
–  Most of the time even though the connection itself is
good (let say 45Mbps), transfers are much slower.
–  There are two reason for a slow transfer over fast
connections:
•  Latency
•  and packet loss bring TCP-based file transfer to a crawl.

Robert  Grossman  University  of  Chicago  Open  Data  Group,  November  14,  2011  
 TCP Throughput vs RTT and Packet
Loss
LAN US US-EU US-ASIA
1000

800

600
Throughput (Mb/s)

400

200
1000

800 0.01%

600 0.05%

0.1%
400

0.5%
200

1%

1 10 100 200 400

Round Trip Time (ms)

Source:  Yunhong  Gu,    2007,  experiments  over  wide  area  1G.  
 The solutions

•  Use parallel TCP streams

–  GridFTP

•  Use specialized network protocols

–  UDT, FAST, etc.

•  Use RAID to stripe data across disks to improve

throughput when reading
•  These techniques are well understood in HEP,
astronomy, but not yet in biology

Robert  Grossman  University  of  Chicago  Open  Data  Group,  November  14,  2011  
 Moving 113GB of Bio-mirror Data

Site   RTT   TCP   UDT   TCP/UDT   Km  

•  Site
NCSA  
RTT TCP
10  
UDT TCP/UDT
139  
Km
139   1   200  
NCSA 10 139 139 1 200
Purdue  
Purdue 17 17  125 125125  1 125  
500 1   500  
ORNL 25 361 120 3 1,200
ORNL  
TACC 37
25   616 361  
120 5.5
120  
2,000
3   1,200  
SDSC
TACC   65 37   750 475
616   1.6 3,300
120   55   2,000  
CSTNET 274 3722 304 12 12,000
SDSC   65   750   475   1.6   3,300  
CSTNET   274   3722   304   12   12,000  

•  GridFTP TCP and UDT transfer times for 113 GB from

gridip.bio-­‐mirror.net/biomirror/ blast/ (Indiana USA).
–  All TCP and UDT times in minutes.
–  Source: http://gridip.bio-mirror.net/biomirror/

Robert  Grossman  University  of  Chicago  Open  Data  Group,  November  14,  2011  
 Case study: CGI 60 genomes

•  Trace by Complete Genomics showing performance of moving 60

complete human genomes from Mountain View to Chicago using the
open source Sector/UDT.
•  Approximately 18 TB at about 0.5 Mbs on 1G link.

Robert  Grossman  University  of  Chicago  Open  Data  Group,  November  14,  2011  
 How FedEx Has More Bandwidth Than
the Internet—and When That'll Change
•  If you're looking to transfer hundreds of
gigabytes of data, it's still—weirdly—faster to
ship hard drives via FedEx than it is to transfer
the files over the internet.
•  “ Cisco  esRmates  that  total  internet  traffic  currently  averages  167  terabits  per  
second.  FedEx  has  a  fleet  of  654  aircrae  with  a  lie  capacity  of  26.5  million  pounds  
daily.  A  solid-­‐state  laptop  drive  weighs  about  78  grams  and  can  hold  up  to  a  
terabyte.  That  means  FedEx  is  capable  of  transferring  150  exabytes  of  data  per  
day,  or  14  petabits  per  second—almost  a  hundred  7mes  the  current  throughput  
of  the  internet.  

hWp://gizmodo.com/5981713/how-­‐fedex-­‐has-­‐more-­‐bandwidth-­‐than-­‐the-­‐internetand-­‐when-­‐
thatll-­‐change  
 content

•  General Introduction
•  Definitions
•  Data Analytics
•  Solutions for Big Data Analytics
•  The Network (Internet)
•  When to consider BigData solution
•  Scientific e-infrastructure – some challenges to
overcome
When to Consider a Big Data Solution
User point of view
•  You’re limited by your current platform or
environment because you can’t process the
amount of data that you want to process

•  You want to involve new sources of data in the

analytics, but you can’t, because it doesn’t fit into
schema-defined rows and columns without
sacrificing fidelity or the richness of the data
When to Consider a Big Data Solution

•  You need to ingest data as quickly as possible and

need to work with a schema-on-demand
–  You‘re forced into a schema-on-write approach (the
schema must be created before data is loaded),
–  but you need to ingest data quickly, or perhaps in a
discovery process, and want the cost benefits of a
schema-on-read approach (data is simply copied to the
file store, and no special transformation is needed) until
you know that you’ve got something that’s ready for
analysis?
 When to Consider a Big Data Solution

•  You want to analyse not just raw structured data,

but also semi-structured and unstructured data
from a wide variety of sources

•  you’re not satisfied with the effectiveness of your

algorithms or models
–  when all, or most, of the data needs to be analysed
–  or when a sampling of the data isn’t going to work
When to Consider a Big Data Solution

•  you aren’t completely sure where the

investigation will take you, and you want elasticity
of compute, storage, and the types of analytics
that will be pursued—all of these became useful
as we added more sources and new methods

If your answers to any of these questions are “yes,” you

need to consider a Big Data solution.
 content

•  General Introduction
•  Definitions
•  Data Analytics
•  Solutions for Big Data Analytics
•  The Network (Internet)
•  When to consider BigData solution
•  Scientific e-infrastructure – some challenges to
overcome
 Scientific e-infrastructure – some
challenges to overcome

•  Collection
–  How can we make sure that data are collected together with
the information necessary to re- use them?

•  Trust
–  How can we make informed judgements about whether
certain data are authentic and can be trusted?

–  How can we judge which repositories we can trust? How

can appropriate access and use of resources be granted or
controlled

Riding  the  wave,  How  Europe  can  gain  from  the  rising  Rde  of  scienRfic  data  
 Scientific e-infrastructure – some
challenges to overcome

•  Usability
–  How can we move to a situation where non-specialists can
overcome the barriers and be able to start sensible work on
unfamiliar data

•  Interoperability
–  How can we implement interoperability within disciplines and move to an
overarching multi-disciplinary way of understanding and using data?
–  How can we find unfamiliar but relevant data resources beyond simple
keyword searches, but involving a deeper probing into the data
–  How can automated tools find the information needed to tackle data

Riding  the  wave,  How  Europe  can  gain  from  the  rising  Rde  of  scienRfic  data  
 Scientific e-infrastructure – some
challenges to overcome
•  Diversity
–  How do we overcome the problems of diversity –
heterogeneity of data, but also of backgrounds and data-
sharing cultures in the scientific community?

–  How do we deal with the diversity of data repositories and

access rules – within or between disciplines, and within or
across national borders?

•  Security
–  How can we guarantee data integrity?
–  How can we avoid data poisoning by individuals or groups
intending to bias them in their interest?

Riding  the  wave,  How  Europe  can  gain  from  the  rising  Rde  of  scienRfic  data  
 Scientific e-infrastructure – a wish list

• Open deposit, allowing user-community centres

to store data easily
• Bit-stream preservation, ensuring that data
authenticity will be guaranteed for a specified
number of years
• Format and content migration, executing CPU-
intensive transformations on large data sets at
the command of the communities

Riding  the  wave,  How  Europe  can  gain  from  the  rising  Rde  of  scienRfic  data  
 Scientific e-infrastructure – a wish list

• Persistent identification, allowing data centres to

register a huge amount of markers to track the
origins and characteristics of the information
• Metadata support to allow effective
management, use and understanding
•  Maintaining proper access rights as the basis of
all trust
• A variety of access and curation services that will
vary between scientific disciplines and over time

Riding  the  wave,  How  Europe  can  gain  from  the  rising  Rde  of  scienRfic  data  
 Scientific e-infrastructure – a wish list

• Execution services that allow a large group of

researchers to operate on the stored date
• High reliability, so researchers can count on its
availability
• Regular quality assessment to ensure adherence to
all agreements
• Distributed and collaborative authentication,
authorisation and accounting
• A high degree of interoperability at format and
semantic level

Riding  the  wave,  How  Europe  can  gain  from  the  rising  Rde  of  scienRfic  data  
 Google BigQuery

•  Google BigQuery is a web service that lets you

do interactive analysis of massive datasets—up
to billions of rows. Scalable and easy to use,
BigQuery lets developers and businesses tap
into powerful data analytics on demand

–  http://www.youtube.com/watch?v=P78T_ZDwQyk
 IBM BigInsights

•  BigInsights = analytical platform for persistent

“big data”
–  Based on open sources & IBM technologies

•  Distinguishing characteristics
–  Built-in Analytics

Big  Data:  Frequently  Asked  QuesRons  for  IBM  InfoSphere  BigInsights  

hWp://www.youtube.com/watch?v=I4hsZa2jwAs    
 References
•  T. Hey, S. Tansley, and K. Tolle, The Fourth Paradigm: Data-Intensive
Scientific Discovery, T. Hey, S. Tansley, and K. Tolle, Eds. Microsoft, 2009.   
Available:
http://research.microsoft.com/en-us/collaboration/fourthparadigm/
•  Enabling knowledge creation in data-driven science
https://sciencenode.org/feature/enabling-knowledge-creation-data-
driven-science.php
•  Science as an open enterprise: open data for open science
http://royalsociety.org/uploadedFiles/Royal_Society_Content/policy/
projects/sape/2012-06-20-SAOE.pdf
•  Realtime Analytics for Big Data: A Facebook Case Study
http://www.youtube.com/watch?v=viPRny0nq3o