mapreduce and hadoop Distributed File sysytem

K. MADURAI AND B. RAMAMURTHY
MapReduce and Hadoop
Distributed File System
B.Ramamurthy & K.Madurai
1
Contact:
Dr. Bina Ramamurthy
CSE Department
University at Buffalo (SUNY)
bina@buffalo.edu
http://www.cse.buffalo.edu/faculty/bina
Partially Supported by
NSF DUE Grant: 0737243
CCSCNE 2009 Palttsburg, April 24 2009

The Context: Big-data
 Man on the moon with 32KB (1969); my laptop had 2GB RAM (2009)
 Google collects 270PB data in a month (2007), 20000PB a day (2008)
 2010 census data is expected to be a huge gold mine of information
 Data mining huge amounts of data collected in a wide range of domains
from astronomy to healthcare has become essential for planning and
performance.
 We are in a knowledge economy.
 Data is an important asset to any organization
 Discovery of knowledge; Enabling discovery; annotation of data
 We are looking at newer
 programming models, and
 Supporting algorithms and data structures.
 NSF refers to it as “data-intensive computing” and industry calls it “big-
data” and “cloud computing”
2

Purpose of this talk
 To provide a simple introduction to:
 “The big-data computing” : An important
advancement that has a potential to impact
significantly the CS and undergraduate curriculum.
 A programming model called MapReduce for
processing “big-data”
 A supporting file system called Hadoop Distributed
File System (HDFS)
 To encourage educators to explore ways to infuse
relevant concepts of this emerging area into their
curriculum.
3

The Outline
 Introduction to MapReduce
 From CS Foundation to MapReduce
 MapReduce programming model
 Hadoop Distributed File System
 Relevance to Undergraduate Curriculum
 Demo (Internet access needed)
 Our experience with the framework
 Summary
 References
4

MapReduce
CCSCNE 2009 Palttsburg, April 24 2009 B.Ramamurthy & K.Madurai
5

What is MapReduce?
 MapReduce is a programming model Google has used
successfully is processing its “big-data” sets (~ 20000 peta
bytes per day)
 Users specify the computation in terms of a map and a
reduce function,
 Underlying runtime system automatically parallelizes the
computation across large-scale clusters of machines, and
 Underlying system also handles machine failures,
efficient communications, and performance issues.
-- Reference: Dean, J. and Ghemawat, S. 2008. MapReduce:
simplified data processing on large clusters. Communication of
ACM 51, 1 (Jan. 2008), 107-113.
6

From CS Foundations to MapReduce
Consider a large data collection:
{web, weed, green, sun, moon, land, part, web, green,
…}
Problem: Count the occurrences of the different words
in the collection.
Lets design a solution for this problem;
 We will start from scratch
 We will add and relax constraints
 We will do incremental design, improving the solution for
performance and scalability
7

Word Counter and Result Table
Data
collection
web 2
weed 1
green 2
sun 1
moon 1
land 1
part 1
8
ResultTable
Main
DataCollection
WordCounter
parse( )
count( )
{web, weed, green, sun, moon, land, part,
web, green,…}

Multiple Instances of Word Counter
web 2
weed 1
green 2
sun 1
moon 1
land 1
part 1
9
Thread
DataCollection ResultTable
WordCounter
parse( )
count( )
Main
1..*
1..*
Data
collection
Observe:
Multi-thread
Lock on shared data

Improve Word Counter for Performance
10
Data
collection
WordList
Thread
Main
1..*
1..*
DataCollection
Parser
1..*
Counter
1..*
ResultTable
KEY web weed green sun moon land part web green …….
VALUE
web 2
weed 1
green 2
sun 1
moon 1
land 1
part 1
N
o
No need for lock
Separate counters

Peta-scale Data
11
Data
collection
WordList
Thread
Main
1..*
1..*
DataCollection
Parser
1..*
Counter
1..*
ResultTable
VALUE
web 2
weed 1
green 2
sun 1
moon 1
land 1
part 1

Addressing the Scale Issue
12
 Single machine cannot serve all the data: you need a distributed
special (file) system
 Large number of commodity hardware disks: say, 1000 disks 1TB
each
 Issue: With Mean time between failures (MTBF) or failure rate of
1/1000, then at least 1 of the above 1000 disks would be down at a
given time.
 Thus failure is norm and not an exception.
 File system has to be fault-tolerant: replication, checksum
 Data transfer bandwidth is critical (location of data)
 Critical aspects: fault tolerance + replication + load balancing,
monitoring
 Exploit parallelism afforded by splitting parsing and counting
 Provision and locate computing at data locations

Peta-scale Data
13
Data
collection
WordList
Thread
Main
1..*
1..*
DataCollection
Parser
1..*
Counter
1..*
ResultTable
VALUE
web 2
weed 1
green 2
sun 1
moon 1
land 1
part 1

Peta Scale Data is Commonly Distributed
14
Data
collection
WordList
Thread
Main
1..*
1..*
DataCollection
Parser
1..*
Counter
1..*
ResultTable
VALUE
web 2
weed 1
green 2
sun 1
moon 1
land 1
part 1
Data
collection
Data
collection
Data
collection
Data
collection Issue: managing the
large scale data

Write Once Read Many (WORM) data
15
Data
collection
WordList
Thread
Main
1..*
1..*
DataCollection
Parser
1..*
Counter
1..*
ResultTable
VALUE
web 2
weed 1
green 2
sun 1
moon 1
land 1
part 1
Data
collection
Data
collection
Data
collection
Data
collection

WORM Data is Amenable to Parallelism
16
Data
collection
WordList
Thread
Main
1..*
1..*
DataCollection
Parser
1..*
Counter
1..*
ResultTable
Data
collection
Data
collection
Data
collection
Data
collection
1. Data with WORM
characteristics : yields
to parallel processing;
2. Data without
dependencies: yields
to out of order
processing

Divide and Conquer: Provision Computing at Data Location
17
WordList
Thread
Main
1..*
1..*
DataCollection
Parser
1..*
Counter
1..*
ResultTable
Data
collection
WordList
Thread
Main
1..*
1..*
DataCollection
Parser
1..*
Counter
1..*
ResultTable
Data
collection
Data
collection
WordList
Thread
Main
1..*
1..*
DataCollection
Parser
1..*
Counter
1..*
ResultTable
WordList
Thread
Main
1..*
1..*
DataCollection
Parser
1..*
Counter
1..*
ResultTable
Data
collection
For our example,
#1: Schedule parallel parse tasks
#2: Schedule parallel count tasks
This is a particular solution;
Lets generalize it:
Our parse is a mapping operation:
MAP: input  <key, value> pairs
Our count is a reduce operation:
REDUCE: <key, value> pairs reduced
Map/Reduce originated from Lisp
But have different meaning here
Runtime adds distribution + fault
tolerance + replication + monitoring +
load balancing to your base application!
One node

Mapper and Reducer
18
Remember: MapReduce is simplified processing for larger data sets:
MapReduce Version of WordCount Source code

Map Operation
MAP: Input data  <key, value> pair
Data
Collection: split1
web 1
weed 1
green 1
sun 1
moon 1
land 1
part 1
web 1
green 1
… 1
KEY VALUE
Split the data to
Supply multiple
processors
Data
Collection: split 2
Data
Collection: split n
Map
……
Map
19
…

Reduce
Reduce
Reduce
Reduce Operation
MAP: Input data  <key, value> pair
REDUCE: <key, value> pair  <result>
Data
Collection: split1 Split the data to
Supply multiple
processors
Data
Collection: split 2
Data
Collection: split n Map
Map
……
Map
20
…

Count
Count
Count
Large scale data splits
Parse-hash
Parse-hash
Parse-hash
Parse-hash
Map <key, 1> Reducers (say, Count)
P-0000
P-0001
P-0002
, count1
, count2
,count3
21

Cat
Bat
Dog
Other
Words
(size:
TByte)
map
map
map
map
split
split
split
split
combine
combine
combine
reduce
reduce
reduce
part0
part1
part2
MapReduce Example in my operating systems class
22

MapReduce Programming
Model
23

MapReduce programming model
 Determine if the problem is parallelizable and solvable using
MapReduce (ex: Is the data WORM?, large data set).
 Design and implement solution as Mapper classes and
Reducer class.
 Compile the source code with hadoop core.
 Package the code as jar executable.
 Configure the application (job) as to the number of mappers
and reducers (tasks), input and output streams
 Load the data (or use it on previously available data)
 Launch the job and monitor.
 Study the result.
 Detailed steps.
24

MapReduce Characteristics
 Very large scale data: peta, exa bytes
 Write once and read many data: allows for parallelism without
mutexes
 Map and Reduce are the main operations: simple code
 There are other supporting operations such as combine and partition
(out of the scope of this talk).
 All the map should be completed before reduce operation starts.
 Map and reduce operations are typically performed by the same
physical processor.
 Number of map tasks and reduce tasks are configurable.
 Operations are provisioned near the data.
 Commodity hardware and storage.
 Runtime takes care of splitting and moving data for operations.
 Special distributed file system. Example: Hadoop Distributed File
System and Hadoop Runtime.
25

Classes of problems “mapreducable”
 Benchmark for comparing: Jim Gray’s challenge on data-
intensive computing. Ex: “Sort”
 Google uses it (we think) for wordcount, adwords, pagerank,
indexing data.
 Simple algorithms such as grep, text-indexing, reverse
indexing
 Bayesian classification: data mining domain
 Facebook uses it for various operations: demographics
 Financial services use it for analytics
 Astronomy: Gaussian analysis for locating extra-terrestrial
objects.
 Expected to play a critical role in semantic web and web3.0
26

Scope of MapReduce
Pipelined Instruction level
Concurrent Thread level
Service Object level
Indexed File level
Mega Block level
Virtual System Level
Data size: small
Data size: large
27

Hadoop
28

What is Hadoop?
 At Google MapReduce operation are run on a special
file system called Google File System (GFS) that is
highly optimized for this purpose.
 GFS is not open source.
 Doug Cutting and Yahoo! reverse engineered the
GFS and called it Hadoop Distributed File System
(HDFS).
 The software framework that supports HDFS,
MapReduce and other related entities is called the
project Hadoop or simply Hadoop.
 This is open source and distributed by Apache.
29

Basic Features: HDFS
 Highly fault-tolerant
 High throughput
 Suitable for applications with large data sets
 Streaming access to file system data
 Can be built out of commodity hardware
30

Hadoop Distributed File System
31
Application
Local file
system
Master node
Name Nodes
HDFS Client
HDFS Server
Block size: 2K
Block size: 128M
Replicated
More details: We discuss this in great detail in my Operating
Systems course

Hadoop Distributed File System
32
Application
Local file
system
Master node
Name Nodes
HDFS Client
HDFS Server
Block size: 2K
Block size: 128M
Replicated
More details: We discuss this in great detail in my Operating
Systems course
heartbeat
blockmap

Relevance and Impact on Undergraduate courses
 Data structures and algorithms: a new look at traditional
algorithms such as sort: Quicksort may not be your
choice! It is not easily parallelizable. Merge sort is better.
 You can identify mappers and reducers among your
algorithms. Mappers and reducers are simply place
holders for algorithms relevant for your applications.
 Large scale data and analytics are indeed concepts to
reckon with similar to how we addressed “programming
in the large” by OO concepts.
 While a full course on MR/HDFS may not be warranted,
the concepts perhaps can be woven into most courses in
our CS curriculum.
33

Demo
 VMware simulated Hadoop and MapReduce demo
 Remote access to NEXOS system at my Buffalo office
 5-node HDFS running HDFS on Ubuntu 8.04
 1 –name node and 4 data-nodes
 Each is an old commodity PC with 512 MB RAM,
120GB – 160GB external memory
 Zeus (namenode), datanodes: hermes, dionysus,
aphrodite, athena
34

Summary
 We introduced MapReduce programming model for
processing large scale data
 We discussed the supporting Hadoop Distributed
File System
 The concepts were illustrated using a simple example
 We reviewed some important parts of the source
code for the example.
 Relationship to Cloud Computing
35

References
1. Apache Hadoop Tutorial: http://hadoop.apache.org
http://hadoop.apache.org/core/docs/current/mapred_tu
torial.html
2. Dean, J. and Ghemawat, S. 2008. MapReduce:
simplified data processing on large clusters.
Communication of ACM 51, 1 (Jan. 2008), 107-113.
3. Cloudera Videos by Aaron Kimball:
http://www.cloudera.com/hadoop-training-basic
4. http://www.cse.buffalo.edu/faculty/bina/mapreduce.html
36

mapreduce and hadoop Distributed File sysytem

More Related Content

Similar to mapreduce and hadoop Distributed File sysytem (20)

Recently uploaded (20)

mapreduce and hadoop Distributed File sysytem