Upload
priscilla-thompson
View
240
Download
2
Embed Size (px)
Citation preview
MapReduce
Theory and Practice
http://net.pku.edu.cn/~course/cs402/2010/彭波
[email protected]北京大学信息科学技术学院
7/15/2010
Some Slides borrow from Jimmy Lin and Aaron Kimball
2
大纲
Functional Language and MapReduce MapReduce Basic MapReduce Algorithm Design Hadoop and Java Practice
Functional Language and MapReduce
4
What is Functional Programming?
In computer science, functional programming is a programming paradigm that treats computation as the evaluation of mathematical functions and avoids state and mutable data. It emphasizes the application of functions, in contrast with the imperative programming style that emphasizes changes in state.[1]
5
Example
Summing the integers 1 to 10 in Java:
total = 0;
for (i = 1; i 10; ++i)
total = total+i;
The computation method is variable assignment.
5
6
Example
Summing the integers 1 to 10 in Haskell:
sum [1..10]
The computation method is function application.
6
7
Why is it Useful?
The abstract nature of functional programming leads to considerably simpler programs;
It also supports a number of powerful new ways to structure and reason about programs.
8
Functional Programming Review
Functional operations do not modify data structures: they always create new ones
Original data still exists in unmodified form Data flows are implicit in program design Order of operations does not matter
9
Functional Programming Review
fun foo(l: int list) = sum(l) + mul(l) + length(l)
Order of sum() and mul(), etc does not matter They do not modify l
10
Functional Updates Do Not Modify Structures
fun append(x, lst) = let lst' = reverse lst in reverse ( x :: lst' )
The append() function above reverses a list, adds a new element to the front, and returns all of that, reversed, which appends an item.
But it never modifies lst!
11
Functions Can Be Used As Arguments
fun DoDouble(f, x) = f (f x)
It does not matter what f does to its argument; DoDouble() will do it twice.
A function is called higher-order if it takes a function as an argument or returns a function as a result
12
Map
map f lst: (’a->’b) -> (’a list) -> (’b list) Creates a new list by applying f to each element of the i
nput list; returns output in order.
f f f f f f
13
Fold
fold f x0 lst: ('a*'b->'b)->'b->('a list)->'b Moves across a list, applying f to each element plus an a
ccumulator. f returns the next accumulator value, which is combined with the next element of the list
f f f f f returned
initial
14
fold left vs. fold right
Order of list elements can be significant Fold left moves left-to-right across the list Fold right moves from right-to-left
SML Implementation:
fun foldl f a [] = a | foldl f a (x::xs) = foldl f (f(x, a)) xs
fun foldr f a [] = a | foldr f a (x::xs) = f(x, (foldr f a xs))
15
Example
fun foo(l: int list) = sum(l) + mul(l) + length(l)
How can we implement this by map and foldl?
16
Example (Solved)
fun foo(l: int list) = sum(l) + mul(l) + length(l)
fun sum(lst) = foldl (fn (a,x)=>a+x) 0 lstfun mul(lst) = foldl (fn (a,x)=>a*x) 1 lstfun length(lst) = foldl (fn (a,x)=>a+1) 0 lst
17
map Implementation
This implementation moves left-to-right across the list, mapping elements one at a time
… But does it need to?
fun map f [] = [] | map f (x::xs) = (f x) :: (map f xs)
18
Implicit Parallelism In map
In a purely functional setting, elements of a list being computed by map cannot see the effects of the computations on other elements
If order of application of f to elements in list is commutative, we can reorder or parallelize execution
This is the “secret” that MapReduce exploits
19
References
http://net.pku.edu.cn/~course/cs501/2008/resource/haskell/functional.ppt
http://net.pku.edu.cn/~course/cs501/2008/resource/haskell/
MapReduce Basic
21
Typical Large-Data Problem
Iterate over a large number of records Extract something of interest from each Shuffle and sort intermediate results Aggregate intermediate results Generate final output
Key idea: provide a functional abstraction for these two operations
Map
Reduce
(Dean and Ghemawat, OSDI 2004)
22
Roots in Functional Programming
g g g g g
f f f f fMap
Fold
23
MapReduce
Programmers specify two functions:map (k, v) → <k’, v’>*reduce (k’, v’) → <k’, v’>* All values with the same key are sent to the
same reducer The execution framework handles
everything else…
mapmap map map
Shuffle and Sort: aggregate values by keys
reduce reduce reduce
k1 k2 k3 k4 k5 k6v1 v2 v3 v4 v5 v6
ba 1 2 c c3 6 a c5 2 b c7 8
a 1 5 b 2 7 c 2 3 6 8
r1 s1 r2 s2 r3 s3
25
MapReduce
Programmers specify two functions:map (k, v) → <k’, v’>*reduce (k’, v’) → <k’, v’>* All values with the same key are sent to the
same reducer The execution framework handles
everything else…
What’s “everything else”?
26
MapReduce “Runtime”
Handles scheduling Assigns workers to map and reduce tasks
Handles “data distribution” Moves processes to data
Handles synchronization Gathers, sorts, and shuffles intermediate data
Handles errors and faults Detects worker failures and restarts
Everything happens on top of a distributed FS (later)
27
MapReduce
Programmers specify two functions:map (k, v) → <k’, v’>*reduce (k’, v’) → <k’, v’>* All values with the same key are reduced together
The execution framework handles everything else…
Not quite…usually, programmers also specify:partition (k’, number of partitions) → partition for k’ Often a simple hash of the key, e.g., hash(k’) mod n Divides up key space for parallel reduce operationscombine (k’, v’) → <k’, v’>* Mini-reducers that run in memory after the map phase Used as an optimization to reduce network traffic
combinecombine combine combine
ba 1 2 c 9 a c5 2 b c7 8
partition partition partition partition
mapmap map map
k1 k2 k3 k4 k5 k6v1 v2 v3 v4 v5 v6
ba 1 2 c c3 6 a c5 2 b c7 8
Shuffle and Sort: aggregate values by keys
reduce reduce reduce
a 1 5 b 2 7 c 2 9 8
r1 s1 r2 s2 r3 s3
c 2 3 6 8
29
Two more details…
Barrier between map and reduce phases But we can begin copying intermediate data
earlier Keys arrive at each reducer in sorted order
No enforced ordering across reducers
30
“Hello World”: Word Count
Map(String docid, String text): for each word w in text: Emit(w, 1);
Reduce(String term, Iterable<Int> values): int sum = 0; for each v in values: sum += v; Emit(term, value);
31
MapReduce can refer to…
The programming model The execution framework (aka “runtime”) The specific implementation
Usage is usually clear from context!
32
MapReduce Implementations
Google has a proprietary implementation in C++ Bindings in Java, Python
Hadoop is an open-source implementation in Java Development led by Yahoo, used in production Now an Apache project Rapidly expanding software ecosystem
Lots of custom research implementations For GPUs, cell processors, etc.
split 0
split 1
split 2
split 3
split 4
worker
worker
worker
worker
worker
Master
UserProgram
outputfile 0
outputfile 1
(1) submit
(2) schedule map (2) schedule reduce
(3) read(4) local write
(5) remote read(6) write
Inputfiles
Mapphase
Intermediate files(on local disk)
Reducephase
Outputfiles
Adapted from (Dean and Ghemawat, OSDI 2004)
MapReduce Algorithm Design
35
“Everything Else”
The execution framework handles everything else… Scheduling: assigns workers to map and reduce tasks “Data distribution”: moves processes to data Synchronization: gathers, sorts, and shuffles intermediate data Errors and faults: detects worker failures and restarts
Limited control over data and execution flow All algorithms must expressed in m, r, c, p
You don’t know: Where mappers and reducers run When a mapper or reducer begins or finishes Which input a particular mapper is processing Which intermediate key a particular reducer is processing
36
Tools for Programmer
Cleverly-constructed data structures Bring partial results together
Sort order of intermediate keys Control order in which reducers process keys
Partitioner Control which reducer processes which keys
Preserving state in mappers and reducers Capture dependencies across multiple keys and valu
es
37
Preserving State
Mapper object
configure
map
close
stateone object per task
Reducer object
configure
reduce
close
state
one call per input key-value pair
one call per intermediate key
API initialization hook
API cleanup hook
38
Scalable Hadoop Algorithms: Themes
Avoid object creation Inherently costly operation Garbage collection
Avoid buffering Limited heap size Works for small datasets, but won’t scale!
39
Importance of Local Aggregation
Ideal scaling characteristics: Twice the data, twice the running time Twice the resources, half the running time
Why can’t we achieve this? Synchronization requires communication Communication kills performance
Thus… avoid communication! Reduce intermediate data via local aggregation Combiners can help
40
Shuffle and Sort
Mapper
Reducer
other mappers
other reducers
circular buffer (in memory)
spills (on disk)
merged spills (on disk)
intermediate files (on disk)
Combiner
Combiner
41
Word Count: Baseline
What’s the impact of combiners?
42
Word Count: Version 1
Are combiners still needed?
43
Word Count: Version 2
Are combiners still needed?
Key: preserve state across
input key-value pairs!
44
Design Pattern for Local Aggregation
“In-mapper combining” Fold the functionality of the combiner into the mapp
er by preserving state across multiple map calls Advantages
Speed Why is this faster than actual combiners?
Disadvantages Explicit memory management required Potential for order-dependent bugs
45
Combiner Design
Combiners and reducers share same method signature Sometimes, reducers can serve as combiners Often, not…
Remember: combiner are optional optimizations Should not affect algorithm correctness May be run 0, 1, or multiple times
Example: find average of all integers associated with the same key
46
Computing the Mean: Version 1
Why can’t we use reducer as combiner?
47
Computing the Mean: Version 2
Why doesn’t this work?
48
Computing the Mean: Version 3
Fixed?
49
Computing the Mean: Version 4
Are combiners still needed?
50
Algorithm Design: Running Example
Term co-occurrence matrix for a text collection M = N x N matrix (N = vocabulary size) Mij: number of times i and j co-occur in some context
(for concreteness, let’s say context = sentence) Why?
Distributional profiles as a way of measuring semantic distance
Semantic distance useful for many language processing tasks
51
MapReduce: Large Counting Problems
Term co-occurrence matrix for a text collection= specific instance of a large counting problem A large event space (number of terms) A large number of observations (the collection itself) Goal: keep track of interesting statistics about the ev
ents Basic approach
Mappers generate partial counts Reducers aggregate partial counts
How do we aggregate partial counts efficiently?
52
First Try: “Pairs”
Each mapper takes a sentence: Generate all co-occurring term pairs For all pairs, emit (a, b) → count
Reducers sum up counts associated with these pairs
Use combiners!
53
Pairs: Pseudo-Code
54
“Pairs” Analysis
Advantages Easy to implement, easy to understand
Disadvantages Lots of pairs to sort and shuffle around (upper
bound?) Not many opportunities for combiners to work
55
Idea: group together pairs into an associative array
Each mapper takes a sentence: Generate all co-occurring term pairs For each term, emit a → { b: countb, c: countc, d: countd … }
Reducers perform element-wise sum of associative arrays
Another Try: “Stripes”
(a, b) → 1 (a, c) → 2 (a, d) → 5 (a, e) → 3 (a, f) → 2
a → { b: 1, c: 2, d: 5, e: 3, f: 2 }
a → { b: 1, d: 5, e: 3 }a → { b: 1, c: 2, d: 2, f: 2 }a → { b: 2, c: 2, d: 7, e: 3, f: 2 }
+
Key: cleverly-constructed data structure
brings together partial results
56
Stripes: Pseudo-Code
57
“Stripes” Analysis
Advantages Far less sorting and shuffling of key-value pairs Can make better use of combiners
Disadvantages More difficult to implement Underlying object more heavyweight Fundamental limitation in terms of size of event
space
58Cluster size: 38 coresData Source: Associated Press Worldstream (APW) of the English Gigaword Corpus (v3), which contains 2.27 million documents (1.8 GB compressed, 5.7 GB uncompressed)
59
60
Relative Frequencies
How do we estimate relative frequencies from counts?
Why do we want to do this? How do we do this with MapReduce?
'
)',(count
),(count
)(count
),(count)|(
B
BA
BA
A
BAABf
Joint Event
Marginal
61
f(B|A): “Stripes”
Easy! One pass to compute (a, *) Another pass to directly compute f(B|A)
a → {b1:3, b2 :12, b3 :7, b4 :1, … }
62
f(B|A): “Pairs”
For this to work: Must emit extra (a, *) for every bn in mapper Must make sure all a’s get sent to same reducer (us
e partitioner) Must make sure (a, *) comes first (define sort order) Must hold state in reducer across different key-value
pairs
(a, b1) → 3 (a, b2) → 12 (a, b3) → 7(a, b4) → 1 …
(a, *) → 32
(a, b1) → 3 / 32 (a, b2) → 12 / 32(a, b3) → 7 / 32(a, b4) → 1 / 32…
Reducer holds this value in memory
63
“Order Inversion”
Common design pattern Computing relative frequencies requires
marginal counts But marginal cannot be computed until you see
all counts Buffering is a bad idea! Trick: getting the marginal counts to arrive at
the reducer before the joint counts Optimizations
Apply in-memory combining pattern to accumulate marginal counts
Should we apply combiners?
64
Synchronization: Pairs vs. Stripes
Approach 1: turn synchronization into an ordering problem
Sort keys into correct order of computation Partition key space so that each reducer gets the
appropriate set of partial results Hold state in reducer across multiple key-value pairs to
perform computation Illustrated by the “pairs” approach
Approach 2: construct data structures that bring partial results together
Each reducer receives all the data it needs to complete the computation
Illustrated by the “stripes” approach
65
Secondary Sorting
MapReduce sorts input to reducers by key Values may be arbitrarily ordered
What if want to sort value also? E.g., k → (v1, r), (v3, r), (v4, r), (v8, r)…
66
Secondary Sorting: Solutions
Solution 1: Buffer values in memory, then sort Why is this a bad idea?
Solution 2: “Value-to-key conversion” design pattern: form
composite intermediate key, (k, v1) Let execution framework do the sorting Preserve state across multiple key-value pairs
to handle processing Anything else we need to do?
67
Recap: Tools for Synchronization
Cleverly-constructed data structures Bring data together
Sort order of intermediate keys Control order in which reducers process keys
Partitioner Control which reducer processes which keys
Preserving state in mappers and reducers Capture dependencies across multiple keys and valu
es
68
Issues and Tradeoffs
Number of key-value pairs Object creation overhead Time for sorting and shuffling pairs across the netwo
rk Size of each key-value pair
De/serialization overhead Local aggregation
Opportunities to perform local aggregation varies Combiners make a big difference Combiners vs. in-mapper combining RAM vs. disk vs. network
69
Debugging at Scale
Works on small datasets, won’t scale… why? Memory management issues (buffering and
object creation) Too much intermediate data Mangled input records
Real-world data is messy! Word count: how many unique words in
Wikipedia? There’s no such thing as “consistent data” Watch out for corner cases Isolate unexpected behavior, bring local
Hadoop and Java Practice
71
Basic Hadoop API*(0.20.0)
Mapper map(KEYIN key, VALUEIN value, Mapper.Context conte
xt) setup(Mapper.Context context) cleanup(Mapper.Context context)
Reducer/Combiner reduce(KEYIN key, Iterable<VALUEIN> values, Reducer.
Context context) Setup/cleanup
Partitioner getPartition(KEY key, VALUE value, int numPartitions)
*Note: forthcoming API changes…
72
Data Types in Hadoop
Writable Defines a de/serialization protocol. Every data type in Hadoop is a Writable.
WritableComprable Defines a sort order. All keys must be of this type (but not values).
IntWritableLongWritableText…
Concrete classes for different data types.
SequenceFiles Binary encoded of a sequence of key/value pairs
73
Complex Data Types in Hadoop
How do you implement complex data types? The easiest way:
Encoded it as Text, e.g., (a, b) = “a:b” Use regular expressions to parse and extract data Works, but pretty hack-ish
The hard way: Define a custom implementation of WritableComprable Must implement: readFields, write, compareTo Computationally efficient, but slow for rapid prototyping
74
Basic Cluster Components
One of each: Namenode (NN) Jobtracker (JT)
Set of each per slave machine: Tasktracker (TT) Datanode (DN)
75
Putting everything together…
datanode daemon
Linux file system
…
tasktracker
slave node
datanode daemon
Linux file system
…
tasktracker
slave node
datanode daemon
Linux file system
…
tasktracker
slave node
namenode
namenode daemon
job submission node
jobtracker
76
Anatomy of a Job
MapReduce program in Hadoop = Hadoop job Jobs are divided into map and reduce tasks An instance of running a task is called a task attempt Multiple jobs can be composed into a workflow
Job submission process Client (i.e., driver program) creates a job, configures it, and sub
mits it to job tracker JobClient computes input splits (on client end) Job data (jar, configuration XML) are sent to JobTracker JobTracker puts job data in shared location, enqueues tasks TaskTrackers poll for tasks Off to the races…
InputSplit
Source: redrawn from a slide by Cloduera, cc-licensed
InputSplit InputSplit
Input File Input File
InputSplit InputSplit
RecordReader RecordReader RecordReader RecordReader RecordReader
Mapper
Intermediates
Mapper
Intermediates
Mapper
Intermediates
Mapper
Intermediates
Mapper
Intermediates
Inp
utF
orm
at
Source: redrawn from a slide by Cloduera, cc-licensed
Mapper Mapper Mapper Mapper Mapper
Partitioner Partitioner Partitioner Partitioner Partitioner
Intermediates Intermediates Intermediates Intermediates Intermediates
Reducer Reducer Reduce
Intermediates Intermediates Intermediates
(combiners omitted here)
Source: redrawn from a slide by Cloduera, cc-licensed
Reducer Reducer Reduce
Output File
RecordWriter
Ou
tpu
tFo
rmat
Output File
RecordWriter
Output File
RecordWriter
80
Input and Output
InputFormat: TextInputFormat KeyValueTextInputFormat SequenceFileInputFormat …
OutputFormat: TextOutputFormat SequenceFileOutputFormat …
81
Shuffle and Sort in Hadoop
Probably the most complex aspect of MapReduce! Map side
Map outputs are buffered in memory in a circular buffer When buffer reaches threshold, contents are “spilled” to dis
k Spills merged in a single, partitioned file (sorted within each pa
rtition): combiner runs here Reduce side
First, map outputs are copied over to reducer machine “Sort” is a multi-pass merge of map outputs (happens in me
mory and on disk): combiner runs here Final merge pass goes directly into reducer
Q&A
83
What is Hugs?
An interpreter for Haskell, and the most widely used implementation of the language;
An interactive system, which is well-suited for teaching and prototyping purposes;
Hugs is freely available from:
www.haskell.org/hugs
84
The Standard Prelude
When Hugs is started it first loads the library file Prelude.hs, and then repeatedly prompts the user for an expression to be evaluated.
For example:
> 2+3*414
> (2+3)*420
85
> length [1,2,3,4]4
> product [1,2,3,4]24
> take 3 [1,2,3,4,5][1,2,3]
The standard prelude also provides many useful functions that operate on lists. For example:
86
Function Application
In mathematics, function application is denoted using parentheses, and multiplication is often denoted using juxtaposition or space.
f(a,b) + c d
Apply the function f to a and b, and add the result to the product of c
and d.
87
In Haskell, function application is denoted using space, and multiplication is denoted using *.
f a b + c*d
As previously, but in Haskell syntax.