Parlab Parallel Boot Camp: Cloud Computing With Mapreduce and Hadoop

PARLab Parallel Boot Camp
Cloud Computing with MapReduce

and Hadoop
Matei Zaharia
Electrical Engineering and Computer Sciences
University of California, Berkeley
What is Cloud Computing?
• “Cloud” refers to large Internet services like Google,

Yahoo, etc that run on 10,000’s of machines
• More recently, “cloud computing” refers to services by

these companies that let external customers rent
computing cycles on their clusters
– Amazon EC2: virtual machines at 10¢/hour, billed hourly
– Amazon S3: storage at 15¢/GB/month
• Attractive features:
– Scale: up to 100’s of nodes
– Fine-grained billing: pay only for what you use
– Ease of use: sign up with credit card, get root access
What is MapReduce?
• Simple data-parallel programming model designed for

scalability and fault-tolerance
• Pioneered by Google
– Processes 20 petabytes of data per day
• Popularized by open-source Hadoop project

– Used at Yahoo!, Facebook, Amazon, …
What is MapReduce used for?
• At Google:
– Index construction for Google Search
– Article clustering for Google News
– Statistical machine translation
• At Yahoo!:
– “Web map” powering Yahoo! Search
– Spam detection for Yahoo! Mail
• At Facebook:
– Data mining
– Ad optimization
– Spam detection
Example: Facebook Lexicon
www.facebook.com/lexicon
Example: Facebook Lexicon
www.facebook.com/lexicon
What is MapReduce used for?
• In research:
– Astronomical image analysis (Washington)
– Bioinformatics (Maryland)
– Analyzing Wikipedia conflicts (PARC)
– Natural language processing (CMU)
– Particle physics (Nebraska)
– Ocean climate simulation (Washington)
– <Your application here>
Outline
• MapReduce architecture
• Example applications
• Getting started with Hadoop
• Higher-level languages over Hadoop: Pig and Hive
• Amazon Elastic MapReduce
MapReduce Design Goals
1. Scalability to large data volumes:

– 1000’s of machines, 10,000’s of disks
2. Cost-efficiency:
– Commodity machines (cheap, but unreliable)
– Commodity network
– Automatic fault-tolerance (fewer administrators)
– Easy to use (fewer programmers)
Typical Hadoop Cluster
Aggregation switch
Rack switch
• 40 nodes/rack, 1000-4000 nodes in cluster

• 1 Gbps bandwidth within rack, 8 Gbps out of rack
• Node specs (Yahoo terasort):
8 x 2GHz cores, 8 GB RAM, 4 disks (= 4 TB?)
Image from http://wiki.apache.org/hadoop-data/attachments/HadoopPresentations/attachments/YahooHadoopIntro-apachecon-us-2008.pdf

Typical Hadoop Cluster
Image from http://wiki.apache.org/hadoop-data/attachments/HadoopPresentations/attachments/aw-apachecon-eu-2009.pdf

Challenges
1. Cheap nodes fail, especially if you have many

– Mean time between failures for 1 node = 3 years
– Mean time between failures for 1000 nodes = 1 day
– Solution: Build fault-tolerance into system
1. Commodity network = low bandwidth

– Solution: Push computation to the data
1. Programming distributed systems is hard

– Solution: Data-parallel programming model: users write “map” &
“reduce” functions, system distributes work and handles faults
Hadoop Components
• Distributed file system (HDFS)

– Single namespace for entire cluster
– Replicates data 3x for fault-tolerance
• MapReduce framework
– Executes user jobs specified as “map” and “reduce”
functions
– Manages work distribution & fault-tolerance
Hadoop Distributed File System
• Files split into 128MB blocks

Namenode
• Blocks replicated across several File1
datanodes (usually 3) 1
2
• Single namenode stores 3

4
metadata (file names, block
locations, etc)
• Optimized for large files,
sequential reads
• Files are append-only 1 2 1 3
2 1 4 2
4 3 3 4
Datanodes
MapReduce Programming Model
• Data type: key-value records
• Map function:
(Kin, Vin)  list(Kinter, Vinter)
• Reduce function:
(Kinter, list(Vinter))  list(Kout, Vout)
Example: Word Count
def mapper(line):
foreach word in line.split():
output(word, 1)
def reducer(key, values):

output(key, sum(values))
Word Count Execution
Input Map Shuffle & Sort Reduce Output
the, 1
brown, 1
the quick fox, 1 brown, 2
Map
brown fox fox, 2
Reduce
how, 1
the, 1
fox, 1
now, 1
the, 1 the, 3
the fox ate
Map
the mouse quick, 1
how, 1
ate, 1 ate, 1
now, 1
mouse, 1
brown, 1 Reduce cow, 1
how now mouse, 1
Map cow, 1
brown cow quick, 1
MapReduce Execution Details
• Single master controls job execution on multiple slaves
• Mappers preferentially placed on same node or same

rack as their input block
– Minimizes network usage
• Mappers save outputs to local disk before serving them

to reducers
– Allows recovery if a reducer crashes
– Allows having more reducers than nodes
An Optimization: The Combiner
• A combiner is a local aggregation function for

repeated keys produced by same map
• Works for associative functions like sum, count, max
• Decreases size of intermediate data
• Example: map-side aggregation for Word Count:

def combiner(key, values):
Word Count with Combiner
Input Map & Combine Shuffle & Sort Reduce Output
the, 1
brown, 1
the quick fox, 1 brown, 2
Map
brown fox fox, 2
Reduce
how, 1
the, 2 now, 1
fox, 1
the, 3
the fox ate
Map
the mouse quick, 1
how, 1
ate, 1 ate, 1
now, 1
mouse, 1
brown, 1 Reduce cow, 1
how now mouse, 1
Map cow, 1
brown cow quick, 1
Fault Tolerance in MapReduce
1. If a task crashes:
– Retry on another node
» OK for a map because it has no dependencies
» OK for reduce because map outputs are on disk
– If the same task fails repeatedly, fail the job or ignore
that input block (user-controlled)
 Note: For these fault tolerance features to work,

your map and reduce tasks must be side-effect-free
2. If a node crashes:
– Re-launch its current tasks on other nodes
– Re-run any maps the node previously ran
» Necessary because their output files were lost along
with the crashed node
3. If a task is going slowly (straggler):

– Launch second copy of task on another node
(“speculative execution”)
– Take the output of whichever copy finishes first, and
kill the other
 Surprisingly important in large clusters

– Stragglers occur frequently due to failing hardware,
software bugs, misconfiguration, etc
– Single straggler may noticeably slow down a job
Takeaways
• By providing a data-parallel programming model,

MapReduce can control job execution in useful ways:
– Automatic division of job into tasks
– Automatic placement of computation near data
– Automatic load balancing
– Recovery from failures & stragglers
• User focuses on application, not on complexities of

distributed computing
Outline
1. Search
• Input: (lineNumber, line) records

• Output: lines matching a given pattern
• Map:
if(line matches pattern):
output(line)
• Reduce: identify function

– Alternative: no reducer (map-only job)
2. Sort
• Input: (key, value) records

• Output: same records, sorted by key
ant, bee
• Map: identity function Map
Reduce [A-M]
zebra
• Reduce: identify function
aardvark
ant
cow bee
cow
Map
elephant
pig
• Trick: Pick partitioning aardvark,

Reduce [N-Z]
function h such that elephant pig

sheep
k1<k2 => h(k1)<h(k2) Map sheep, yak yak

zebra
3. Inverted Index
• Input: (filename, text) records

• Output: list of files containing each word
• Map:
foreach word in text.split():
output(word, filename)
• Combine: uniquify filenames for each word
• Reduce:
def reduce(word, filenames):
output(word, sort(filenames))
Inverted Index Example
hamlet.txt
to, hamlet.txt
to be or be, hamlet.txt
not to be or, hamlet.txt afraid, (12th.txt)
not, hamlet.txt be, (12th.txt, hamlet.txt)
greatness, (12th.txt)
not, (12th.txt, hamlet.txt)
of, (12th.txt)
be, 12th.txt or, (hamlet.txt)
12th.txt
not, 12th.txt to, (hamlet.txt)
be not afraid, 12th.txt
afraid of of, 12th.txt
greatness
greatness, 12th.txt
4. Most Popular Words
• Input: (filename, text) records

• Output: top 100 words occurring in the most files
• Two-stage solution:
– Job 1:
» Create inverted index, giving (word, list(file)) records
– Job 2:
» Map each (word, list(file)) to (count, word)
» Sort these records by count as in sort job
• Optimizations:
– Map to (word, 1) instead of (word, file) in Job 1
– Count files in job 1’s reducer rather than job 2’s mapper
– Estimate count distribution in advance and drop rare words
5. Numerical Integration
• Input: (start, end) records for sub-ranges to integrate

– Easy using custom InputFormat
• Output: integral of f(x) dx over entire range
• Map:
def map(start, end):
sum = 0
for(x = start; x < end; x += step):
sum += f(x) * step
output(“”, sum)
• Reduce:
def reduce(key, values):
Outline
Getting Started with Hadoop
• Download from hadoop.apache.org

• To install locally, unzip and set JAVA_HOME
• Details: hadoop.apache.org/core/docs/current/quickstart.html
• Three ways to write jobs:

– Java API
– Hadoop Streaming (for Python, Perl, etc)
– Pipes API (C++)
Word Count in Java
public class MapClass extends MapReduceBase

implements Mapper<LongWritable, Text, Text, IntWritable> {
private final static IntWritable ONE = new IntWritable(1);
public void map(LongWritable key, Text value,

OutputCollector<Text, IntWritable> out,
Reporter reporter) throws IOException {
String line = value.toString();
StringTokenizer itr = new StringTokenizer(line);
while (itr.hasMoreTokens()) {
out.collect(new text(itr.nextToken()), ONE);
}
}
}
Word Count in Java
public class ReduceClass extends MapReduceBase

implements Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterator<IntWritable> values,

OutputCollector<Text, IntWritable> out,
Reporter reporter) throws IOException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
out.collect(key, new IntWritable(sum));
}
}
Word Count in Java
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("wordcount");
conf.setMapperClass(MapClass.class);
conf.setCombinerClass(ReduceClass.class);
conf.setReducerClass(ReduceClass.class);
FileInputFormat.setInputPaths(conf, args[0]);
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
conf.setOutputKeyClass(Text.class); // out keys are words (strings)

conf.setOutputValueClass(IntWritable.class); // values are counts
JobClient.runJob(conf);
}
Word Count in Python with Hadoop Streaming
Mapper.py: import sys

for line in sys.stdin:
for word in line.split():
print(word.lower() + "\t" + 1)
Reducer.py: import sys

counts = {}
for line in sys.stdin:
word, count = line.split("\t”)
dict[word] = dict.get(word, 0) +
int(count)
for word, count in counts:
print(word.lower() + "\t" + 1)
Outline
Motivation
• Many parallel algorithms can be expressed by a series

of MapReduce jobs
• But MapReduce is fairly low-level: must think about

keys, values, partitioning, etc
• Can we capture common “job building blocks”?

Pig
• Started at Yahoo! Research

• Runs about 30% of Yahoo!’s jobs
• Features:
– Expresses sequences of MapReduce jobs
– Data model: nested “bags” of items
– Provides relational (SQL) operators (JOIN, GROUP BY, etc)
– Easy to plug in Java functions
– Pig Pen development environment for Eclipse
An Example Problem
Suppose you have user

Load Users Load Pages
data in one file, page
view data in another, and
Filter by age
you need to find the top
5 most visited pages by
Join on name
users aged 18 - 25.
Group on url
Count clicks
Order by clicks
Take top 5
Example from http://wiki.apache.org/pig-data/attachments/PigTalksPapers/attachments/ApacheConEurope09.ppt

In MapReduce
import java.io.IOException; reporter.setStatus("OK"); lp.setOutputKeyClass(Text.class);
import java.util.ArrayList; } lp.setOutputValueClass(Text.class);
import java.util.Iterator; lp.setMapperClass(LoadPages.class);
import java.util.List; // Do the cross product and collect the values FileInputFormat.addInputPath(lp, new
for (String s1 : first) { Path("/user/gates/pages"));

import org.apache.hadoop.fs.Path; for (String s2 : second) { FileOutputFormat.setOutputPath(lp,
import org.apache.hadoop.io.LongWritable; String outval = key + "," + s1 + "," + s2; new Path("/user/gates/tmp/indexed_pages"));
import org.apache.hadoop.io.Text; oc.collect(null, new Text(outval)); lp.setNumReduceTasks(0);
import org.apache.hadoop.io.Writable; reporter.setStatus("OK"); Job loadPages = new Job(lp);
import org.apache.hadoop.io.WritableComparable; }
import org.apache.hadoop.mapred.FileInputFormat; } JobConf lfu = new JobConf(MRExample.class);
import org.apache.hadoop.mapred.FileOutputFormat; } lfu.setJobName("Load and Filter Users");
import org.apache.hadoop.mapred.JobConf; } lfu.setInputFormat(TextInputFormat.class);
import org.apache.hadoop.mapred.KeyValueTextInputFormat; public static class LoadJoined extends MapReduceBase lfu.setOutputKeyClass(Text.class);
import org.ap ache.hadoop.mapred.Mapper; implements Mapper<Text, Text, Text, LongWritable> { lfu.setOutputValueClass(Text.class);
import org.apache.hadoop.mapred.MapReduceBase; lfu.setMapperClass(LoadAndFilterUsers.class);
import org.apache.hadoop.mapred.OutputCollector; public void map( FileInputFormat.add
InputPath(lfu, new
import org.apache.hadoop.mapred.RecordReader; Text k, Path("/user/gates/users"));

import org.apache.hadoop.mapred.Reducer; Text val, FileOutputFormat.setOutputPath(lfu,
import org.apache.hadoop.mapred.Reporter; OutputColle ctor<Text, LongWritable> oc, new Path("/user/gates/tmp/filtered_users"));
import org.apache.hadoop.mapred.SequenceFileInputFormat; Reporter reporter) throws IOException { lfu.setNumReduceTasks(0);
import org.apache.hadoop.mapred.SequenceFileOutputFormat; // Find the url Job loadUsers = new Job(lfu);
import org.apache.hadoop.mapred.TextInputFormat; String line = val.toString();
import org.apache.hadoop.mapred.jobcontrol.Job; int firstComma = line.indexOf(','); JobConf join = new JobConf( MRExample.class);
import org.apache.hadoop.mapred.jobcontrol.JobC ontrol; int secondComma = line.indexOf(',', first Comma); join.setJobName("Join Users and Pages");
import org.apache.hadoop.mapred.lib.IdentityMapper; String key = line.substring(firstComma, secondComma); join.setInputFormat(KeyValueTextInputFormat.class);
// drop the rest of the record, I don't need it anymore, join.setOutputKeyClass(Text.class);
public class MRExample { // just pass a 1 for the combiner/reducer to sum instead. join.setOutputValueClass(Text.class);
public static class LoadPages extends MapReduceBase Text outKey = new Text(key); join.setMapperClass(IdentityMap per.class);
implements Mapper<LongWritable, Text, Text, Text> { oc.collect(outKey, new LongWritable(1L)); join.setReducerClass(Join.class);
} FileInputFormat.addInputPath(join, new
public void map(LongWritable k, Text val, } Path("/user/gates/tmp/indexed_pages"));
OutputCollector<Text, Text> oc, public static class ReduceUrls extends MapReduceBase FileInputFormat.addInputPath(join, new
Reporter reporter) throws IOException { implements Reducer<Text, LongWritable, WritableComparable, Path("/user/gates/tmp/filtered_users"));
// Pull the key out Writable> { FileOutputFormat.se
tOutputPath(join, new
String line = val.toString(); Path("/user/gates/tmp/joined"));
int firstComma = line.indexOf(','); public void reduce( join.setNumReduceTasks(50);
String key = line.sub string(0, firstComma); Text ke y, Job joinJob = new Job(join);
String value = line.substring(firstComma + 1); Iterator<LongWritable> iter, joinJob.addDependingJob(loadPages);
Text outKey = new Text(key); OutputCollector<WritableComparable, Writable> oc, joinJob.addDependingJob(loadUsers);
// Prepend an index to the value so we know which file Reporter reporter) throws IOException {
// it came from. // Add up all the values we see JobConf group = new JobConf(MRE xample.class);
Text outVal = new Text("1 " + value); group.setJobName("Group URLs");
oc.collect(outKey, outVal); long sum = 0; group.setInputFormat(KeyValueTextInputFormat.class);
} wh ile (iter.hasNext()) { group.setOutputKeyClass(Text.class);
} sum += iter.next().get(); group.setOutputValueClass(LongWritable.class);
public static class LoadAndFilterUsers extends MapReduceBase reporter.setStatus("OK"); group.setOutputFormat(SequenceFi leOutputFormat.class);
implements Mapper<LongWritable, Text, Text, Text> { } group.setMapperClass(LoadJoined.class);
group.setCombinerClass(ReduceUrls.class);
public void map(LongWritable k, Text val, oc.collect(key, new LongWritable(sum)); group.setReducerClass(ReduceUrls.class);
OutputCollector<Text, Text> oc, } FileInputFormat.addInputPath(group, new
Reporter reporter) throws IOException { } Path("/user/gates/tmp/joined"));
// Pull the key out public static class LoadClicks extends MapReduceBase FileOutputFormat.setOutputPath(group, new
String line = val.toString(); implements Mapper<WritableComparable, Writable, LongWritable, Path("/user/gates/tmp/grouped"));
int firstComma = line.indexOf(','); Text> { group.setNumReduceTasks(50);
String value = line.substring( firstComma + 1); Job groupJob = new Job(group);
int age = Integer.parseInt(value); public void map( groupJob.addDependingJob(joinJob);
if (age < 18 || age > 25) return; WritableComparable key,
String key = line.substring(0, firstComma); Writable val, JobConf top100 = new JobConf(MRExample.class);
Text outKey = new Text(key); OutputCollector<LongWritable, Text> oc, top100.setJobName("Top 100 sites");
// Prepend an index to the value so w e know which file
Reporter reporter) throws IOException { top100.setInputFormat(SequenceFileInputFormat.class);
// it came from. oc.collect((LongWritable)val, (Text)key); top100.setOutputKeyClass(LongWritable.class);
Text outVal = new Text("2" + value); } top100.setOutputValueClass(Text.class);
oc.collect(outKey, outVal); } top100.setOutputFormat(SequenceFileOutputF ormat.class);
} public static class LimitClicks extends MapReduceBase top100.setMapperClass(LoadClicks.class);
} implements Reducer<LongWritable, Text, LongWritable, Text> { top100.setCombinerClass(LimitClicks.class);
public static class Join extends MapReduceBase top100.setReducerClass(LimitClicks.class);
implements Reducer<Text, Text, Text, Text> { int count = 0; FileInputFormat.addInputPath(top100, new
public void reduce( Path("/user/gates/tmp/grouped"));
public void reduce(Text key, LongWritable key, FileOutputFormat.setOutputPath(top100, new
Iterator<Text> iter, Iterator<Text> iter, Path("/user/gates/top100sitesforusers18to25"));
OutputCollector<Text, Text> oc, OutputCollector<LongWritable, Text> oc, top100.setNumReduceTasks(1);
Reporter reporter) throws IOException { Reporter reporter) throws IOException { Job limit = new Job(top100);
// For each value, figure out which file it's from and limit.addDependingJob(groupJob);
store it // Only output the first 100 records
// accordingly. while (count < 100 && iter.hasNext()) { JobControl jc = new JobControl("Find top 100 sites for users
List<String> first = new ArrayList<String>(); oc.collect(key, iter.next()); 18 to 25");
List<String> second = new ArrayList<String>(); count++; jc.addJob(loadPages);
} jc.addJob(loadUsers);
while (iter.hasNext()) { } jc.addJob(joinJob);

Text t = iter.next(); } jc.addJob(groupJob);
String value = t.to String(); public static void main(String[] args) throws IOException { jc.addJob(limit);

if (value.charAt(0) == '1') JobConf lp = new JobConf(MRExample.class); jc.run();
first.add(value.substring(1)); lp.se tJobName("Load Pages"); }
else second.add(value.substring(1)); lp.setInputFormat(TextInputFormat.class); }

In Pig Latin
Users = load ‘users’ as (name, age);

Filtered = filter Users by
age >= 18 and age <= 25;
Pages = load ‘pages’ as (user, url);
Joined = join Filtered by name, Pages by user;
Grouped = group Joined by url;
Summed = foreach Grouped generate group,
count(Joined) as clicks;
Sorted = order Summed by clicks desc;
Top5 = limit Sorted 5;
store Top5 into ‘top5sites’;

Ease of Translation
Notice how naturally the components of the job translate into Pig Latin.
Users = load …
Filter by age
Filtered = filter …
Pages = load …
Join on name
Joined = join …
Group on url
Grouped = group …
Summed = … count()…
Count clicks Sorted = order …
Top5 = limit …
Order by clicks
Take top 5

Ease of Translation
Notice how naturally the components of the job translate into Pig Latin.
Users = load …
Filter by age
Filtered = filter …
Pages = load …
Join on name
Joined = join …
Job 1
Group on url
Grouped = group …
Job 2 Summed = … count()…
Count clicks Sorted = order …
Top5 = limit …
Order by clicks
Job 3
Take top 5

Hive
• Developed at Facebook
• Used for majority of Facebook jobs
• “Relational database” built on Hadoop
– Maintains list of table schemas
– SQL-like query language (HQL)
– Can call Hadoop Streaming scripts from HQL
– Supports table partitioning, clustering, complex
data types, some optimizations
Sample Hive Queries
• Find top 5 pages visited by users aged 18-25:
SELECT p.url, COUNT(1) as clicks
FROM users u JOIN page_views p ON (u.name = p.user)
WHERE u.age >= 18 AND u.age <= 25
GROUP BY p.url
ORDER BY clicks
LIMIT 5;
• Filter page views through Python script:

SELECT TRANSFORM(p.user, p.date)
USING 'map_script.py'
AS dt, uid CLUSTER BY dt
FROM page_views p;
Outline
Amazon Elastic MapReduce
• Provides a web-based interface and command-line

tools for running Hadoop jobs on Amazon EC2
• Data stored in Amazon S3
• Monitors job and shuts down machines after use
• Small extra charge on top of EC2 pricing
• If you want more control over how you Hadoop

runs, you can launch a Hadoop cluster on EC2
manually using the scripts in src/contrib/ec2
Elastic MapReduce Workflow
Conclusions
• MapReduce programming model hides the complexity of

work distribution and fault tolerance
• Principal design philosophies:

– Make it scalable, so you can throw hardware at problems
– Make it cheap, lowering hardware, programming and admin costs
• MapReduce is not suitable for all problems, but when it

works, it may save you quite a bit of time
• Cloud computing makes it straightforward to start

using Hadoop (or other parallel software) at scale
Resources
• Hadoop: http://hadoop.apache.org/core/
• Pig: http://hadoop.apache.org/pig
• Hive: http://hadoop.apache.org/hive
• Video tutorials: http://www.cloudera.com/hadoop-training
• Amazon Web Services: http://aws.amazon.com/

• Amazon Elastic MapReduce guide:
http://docs.amazonwebservices.com/ElasticMapReduce/la
test/GettingStartedGuide/
• My email: [email protected]

Parlab Parallel Boot Camp: Cloud Computing With Mapreduce and Hadoop

Uploaded by

Copyright:

Available Formats

Parlab Parallel Boot Camp: Cloud Computing With Mapreduce and Hadoop

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Parlab Parallel Boot Camp: Cloud Computing With Mapreduce and Hadoop

Uploaded by

Copyright:

Available Formats

PARLab Parallel Boot Camp

Cloud Computing with MapReduce

• “Cloud” refers to large Internet services like Google,

• More recently, “cloud computing” refers to services by

• Simple data-parallel programming model designed for

• Popularized by open-source Hadoop project

1. Scalability to large data volumes:

• 40 nodes/rack, 1000-4000 nodes in cluster

Image from http://wiki.apache.org/hadoop-data/attachments/HadoopPresentations/attachments/YahooHadoopIntro-apachecon-us-2008.pdf

Image from http://wiki.apache.org/hadoop-data/attachments/HadoopPresentations/attachments/aw-apachecon-eu-2009.pdf

1. Cheap nodes fail, especially if you have many

1. Commodity network = low bandwidth

1. Programming distributed systems is hard

• Distributed file system (HDFS)

• Files split into 128MB blocks

• Single namenode stores 3

• Data type: key-value records

def reducer(key, values):

Input Map Shuffle & Sort Reduce Output

• Single master controls job execution on multiple slaves

• Mappers preferentially placed on same node or same

• Mappers save outputs to local disk before serving them

• A combiner is a local aggregation function for

• Decreases size of intermediate data

• Example: map-side aggregation for Word Count:

Input Map & Combine Shuffle & Sort Reduce Output

 Note: For these fault tolerance features to work,

3. If a task is going slowly (straggler):

 Surprisingly important in large clusters

• By providing a data-parallel programming model,

• User focuses on application, not on complexities of

• Input: (lineNumber, line) records

• Reduce: identify function

• Input: (key, value) records

• Trick: Pick partitioning aardvark,

function h such that elephant pig

k1<k2 => h(k1)<h(k2) Map sheep, yak yak

• Input: (filename, text) records

• Combine: uniquify filenames for each word

• Input: (filename, text) records

• Input: (start, end) records for sub-ranges to integrate

• Download from hadoop.apache.org

• Three ways to write jobs:

public class MapClass extends MapReduceBase

private final static IntWritable ONE = new IntWritable(1);

public void map(LongWritable key, Text value,

public class ReduceClass extends MapReduceBase

public void reduce(Text key, Iterator<IntWritable> values,

conf.setOutputKeyClass(Text.class); // out keys are words (strings)

Mapper.py: import sys

Reducer.py: import sys

• Many parallel algorithms can be expressed by a series

• But MapReduce is fairly low-level: must think about

• Can we capture common “job building blocks”?

• Started at Yahoo! Research

Suppose you have user

Example from http://wiki.apache.org/pig-data/attachments/PigTalksPapers/attachments/ApacheConEurope09.ppt

Example from http://wiki.apache.org/pig-data/attachments/PigTalksPapers/attachments/ApacheConEurope09.ppt