1. The Pig Experience: Building High-Level Data flows on top of Map-Reduce The Pig Experience: Building High-Level Data flows on top of Map-Reduce DISTRIBUTED INFORMATION SYSTEMS Presenter: Javeria Iqbal Tutor: Dr.Martin Theobald

2. Outline Map-Reduce and the need for Pig Latin Pig Latin Compilation into Map-Reduce Optimization Future Work

3. Data Processing Renaissance  Internet companies swimming in data TBs/day for Yahoo! Or Google! PBs/day for FaceBook!  Data analysis is “inner loop” of product innovation

4. Data Warehousing …? Scale Often not scalable enough Price Prohibitively expensive at web scale Up to $200K/TB SQL High level declarative approach Little control over execution method

5. Map-Reduce Map : Performs filtering Reduce : Performs the aggregation These are two high level declarative primitives to enable parallel processing BUT no complex Database Operations e.g. Joins

6. Split the Program Master and Worker Threads Worker reads, parses key/value pairs and passes pairs to user-defined Map function Worker reads, parses key/value pairs and passes pairs to user-defined Map function Buffered pairs are written to local disk partitions, Location of buffered pairs are sent to reduce workers Buffered pairs are written to local disk partitions, Location of buffered pairs are sent to reduce workers Execution Overview of Map-Reduce

7. Reduce worker sorts data by the intermediate keys. Reduce worker sorts data by the intermediate keys. Unique keys, values are passed to user’s Reduce function. Output is appended to the output file for this reduce partition. Unique keys, values are passed to user’s Reduce function. Output is appended to the output file for this reduce partition. Execution Overview of Map-Reduce

8. The Map-Reduce Appeal Scale Scalable due to simpler design Explicit programming model Only parallelizable operations Price Runs on cheap commodity hardware Less Administration Procedural Control- a processing “pipe” SQL

9. Disadvantages 1. Extremely rigid data flow Other flows hacked in Join, Union Split M M R R M M M M R R M M Chains 2. Common operations must be coded by hand Join, filter, projection, aggregates, sorting, distinct 3. Semantics hidden inside map-reduce functions Difficult to maintain, extend, and optimize 3. No combined processing of multiple Datasets Joins and other data processing operations

10. Motivation ScalableCheap Control over execution Inflexible Lots of hand coding Semantics hidden Need a high-level, general data flow language

11. Enter Pig Latin ScalableCheap Control over execution Pig Latin Need a high-level, general data flow language

12. Outline Map-Reduce and the need for Pig Latin Pig Latin Compilation into Map-Reduce Optimization Future Work

13. Pig Latin: Data Types Rich and Simple Data Model Simple Types: int, long, double, chararray, bytearray Complex Types: Atom: String or Number e.g. (‘apple’) Tuple: Collection of fields e.g. (áppe’, ‘mango’) Bag: Collection of tuples { (‘apple’, ‘mango’) (ápple’, (‘red’, ‘yellow’)) } Map: Key, Value Pair

14. Example: Data Model Atom: contains Single atomic value ‘alice’ ‘lanker’ ‘ipod’ Atom Tuple Tuple: sequence of fields Bag: collection of tuple with possible duplicates

15. Pig Latin: Input/Output Data Input: queries = LOAD `query_log.txt' USING myLoad() AS (userId, queryString, timestamp); Output: STORE query_revenues INTO `myoutput' USING myStore();

16. Pig Latin: General Syntax Discarding Unwanted Data: FILTER C omparison operators such as ==, eq, !=, neq Logical connectors AND, OR, NOT

17. Pig Latin: Expression Table

18. Pig Latin: FOREACH with Flatten expanded_queries = FOREACH queries GENERATE userId, expandQuery(queryString); ----------------- expanded_queries = FOREACH queries GENERATE userId, FLATTEN(expandQuery(queryString));

19. Pig Latin: COGROUP Getting Related Data Together: COGROUP Suppose we have two data sets result:(queryString, url, position) revenue:(queryString, adSlot, amount) grouped_data = COGROUP result BY queryString, revenue BY queryString;

20. Pig Latin: COGROUP vs. JOIN

21. Pig Latin: Map-Reduce Map-Reduce in Pig Latin map_result = FOREACH input GENERATE FLATTEN(map(*)); key_group = GROUP map_result BY $0; output = FOREACH key_group GENERATE reduce(*);

22. Pig Latin: Other Commands UNION : Returns the union of two or more bags CROSS: Returns the cross product ORDER: Orders a bag by the specified field(s) DISTINCT: Eliminates duplicate tuple in a bag

23. Pig Latin: Nested Operations grouped_revenue = GROUP revenue BY queryString; query_revenues = FOREACH grouped_revenue { top_slot = FILTER revenue BY adSlot eq `top'; GENERATE queryString, SUM(top_slot.amount), SUM(revenue.amount); };

24. Pig Pen: Screen Shot

25. Pig Latin: Example 1 Suppose we have a table urls: (url, category, pagerank) Simple SQL query that finds, For each sufficiently large category, the average pagerank of high-pagerank urls in that category SELECT category, Avg(pagetank) FROM urls WHERE pagerank > 0.2 GROUP BY category HAVING COUNT(*) > 10 6

26. Data Flow Filter good_urls by pagerank > 0.2 Group by category Filter category by count > 10 6 Foreach category generate avg. pagerank Foreach category generate avg. pagerank

27. Equivalent Pig Latin good_urls = FILTER urls BY pagerank > 0.2; groups = GROUP good_urls BY category; big_groups = FILTER groups BY COUNT(good_urls) > 10 6 ; output = FOREACH big_groups GENERATE category, AVG(good_urls.pagerank);

28. Example 2: Data Analysis Task UserUrlTime Amycnn.com8:00 Amybbc.com10:00 Amyflickr.com10:05 Fredcnn.com12:00 Find the top 10 most visited pages in each category UrlCategoryPageRank cnn.comNews0.9 bbc.comNews0.8 flickr.comPhotos0.7 espn.comSports0.9 VisitsUrl Info

29. Data Flow Load Visits Group by url Foreach url generate count Foreach url generate count Load Url Info Join on url Group by category Foreach category generate top10 urls Foreach category generate top10 urls

30. Equivalent Pig Latin visits = load ‘/data/visits’ as (user, url, time); gVisits = group visits by url; visitCounts = foreach gVisits generate url, count(visits); urlInfo = load ‘/data/urlInfo’ as (url, category, pRank); visitCounts = join visitCounts by url, urlInfo by url; gCategories = group visitCounts by category; topUrls = foreach gCategories generate top(visitCounts,10); store topUrls into ‘/data/topUrls’;

31. visits = load ‘/data/visits’ as (user, url, time); gVisits = group visits by url; visitCounts = foreach gVisits generate url, count(urlVisits); urlInfo = load ‘/data/urlInfo’ as (url, category, pRank); visitCounts = join visitCounts by url, urlInfo by url; gCategories = group visitCounts by category; topUrls = foreach gCategories generate top(visitCounts,10); store topUrls into ‘/data/topUrls’; Quick Start and Interoperability Operates directly over files

32. visits = load ‘/data/visits’ as (user, url, time); gVisits = group visits by url; visitCounts = foreach gVisits generate url, count(urlVisits); urlInfo = load ‘/data/urlInfo’ as (url, category, pRank); visitCounts = join visitCounts by url, urlInfo by url; gCategories = group visitCounts by category; topUrls = foreach gCategories generate top(visitCounts,10); store topUrls into ‘/data/topUrls’; Quick Start and Interoperability Schemas optional; Can be assigned dynamically Schemas optional; Can be assigned dynamically

33. visits = load ‘/data/visits’ as (user, url, time); gVisits = group visits by url; visitCounts = foreach gVisits generate url, count(urlVisits); urlInfo = load ‘/data/urlInfo’ as (url, category, pRank); visitCounts = join visitCounts by url, urlInfo by url; gCategories = group visitCounts by category; topUrls = foreach gCategories generate top(visitCounts,10); store topUrls into ‘/data/topUrls’; User-Code as a First-Class Citizen User-defined functions (UDFs) can be used in every construct Load, Store Group, Filter, Foreach User-defined functions (UDFs) can be used in every construct Load, Store Group, Filter, Foreach

34. Pig Latin has a fully nested data model with: – Atomic values, tuples, bags (lists), and maps Avoids expensive joins Nested Data Model yahoo, finance email news

35. Common case: aggregation on these nested sets Power users: sophisticated UDFs, e.g., sequence analysis Efficient Implementation (see paper) Nested Data Model Decouples grouping as an independent operation UserUrlTime Amycnn.com8:00 Amybbc.com10:00 Amybbc.com10:05 Fredcnn.com12:00 groupVisits cnn.com Amycnn.com8:00 Fredcnn.com12:00 bbc.com Amybbc.com10:00 Amybbc.com10:05 group by url I frankly like pig much better than SQL in some respects (group + optional flatten), I love nested data structures).” Ted Dunning Chief Scientist, Veoh 35

36. CoGroup queryurlrank Lakersnba.com1 Lakersespn.com2 Kingsnhl.com1 Kingsnba.com2 queryadSlotamount Lakerstop50 Lakersside20 Kingstop30 Kingsside10 groupresultsrevenue Lakers nba.com1Lakerstop50 Lakersespn.com2Lakersside20 Kings nhl.com1Kingstop30 Kingsnba.com2Kingsside10 resultsrevenue Cross-product of the 2 bags would give natural join

37. Pig Features Explicit Data Flow Language unlike SQL Low Level Procedural Language unlike Map- Reduce Quick Start & Interoperability Mode (Interactive Mode, Batch, Embedded) User Defined Functions Nested Data Model

38. Outline Map-Reduce and the need for Pig Latin Pig Latin Compilation into Map-Reduce Optimization Future Work

39. Pig Process Life Cycle Hadoop Job Manager Logical Optimizer Parser Pig Latin to Logical Plan Map-Reduce Optimizer Map-Reduce Compiler Logical Plan to Physical Plan

40. Pig Latin to Physical Plan A = LOAD ‘file1’ AS (x,y,z); B = LOAD ‘file2’ AS (t,u,v); C = FILTER A by y > 0; D = JOIN C by x,B by u; E = GROUP D by z; F = FOREACH E generate group, COUNT(D); STORE F into ‘output’; LOAD FILTER LOAD JOIN GROUP FOREACH STORE x,y,z x,y,z,t,u,v group, count

41. Logical Plan to Physical Plan LOAD FILTER LOAD JOIN GROUP FOREACH STORE 1 2 3 4 7 6 5 LOCAL REARRANGE GLOABL REARRANGE GLOBAL REARRANGE STORE LOCAL REARRANGE LOAD FILTER LOAD PACKAGE FOREACH PACKAGE FOREACH 1 2 3 44 4 4 5 5 5 6 7

42. Physical Plan to Map-Reduce Plan LOCAL REARRANGE GLOABL REARRANGE GLOBAL REARRANGE STORE LOCAL REARRANGE LOAD FILTER LOAD PACKAGE FOREACH PACKAGE FOREACH 1 2 3 44 4 4 5 5 5 6 7 Filter Local Rearrange Package Foreach Package Foreach

43. Implementation cluster Hadoop Map-Reduce Pig SQL automatic rewrite + optimize or user Pig is open-source. http://hadoop.apache.org/pig Pig is open-source. http://hadoop.apache.org/pig ~50% of Hadoop jobs at Yahoo! are Pig 1000s of jobs per day

44. Compilation into Map-Reduce Load Visits Group by url Foreach url generate count Foreach url generate count Load Url Info Join on url Group by category Foreach category generate top10(urls) Foreach category generate top10(urls) Map 1 Reduce 1 Map 2 Reduce 2 Map 3 Reduce 3 Every group or join operation forms a map-reduce boundary Other operations pipelined into map and reduce phases

45. Nested Sub Plans SPLIT FILTER FOEACHFOREACH FILTER LOCAL REARRANGE GLOBAL REARRANGE SPLIT FOREACH PACKAGE MULTIPLEX

46. Outline Map-Reduce and the need for Pig Latin Pig Latin Compilation into Map-Reduce Optimization Future Work

47. Using the Combiner Input records k1k1 v1v1 k2k2 v2v2 k1k1 v3v3 k2k2 v4v4 k1k1 v5v5 map k1k1 v1v1 k1k1 v3v3 k1k1 v5v5 k2k2 v2v2 k2k2 v4v4 Output records reduce Can pre-process data on the map-side to reduce data shipped Algebraic Aggregation Functions Distinct processing

48. Skew Join Default join method is symmetric hash join. groupresultsrevenue Lakers nba.com1Lakerstop50 Lakersespn.com2Lakersside20 Kings nhl.com1Kingstop30 Kingsnba.com2Kingsside10 cross product carried out on 1 reducer Problem if too many values with same key Skew join samples data to find frequent values Further splits them among reducers

49. Fragment-Replicate Join Symmetric-hash join repartitions both inputs If size(data set 1) >> size(data set 2) – Just replicate data set 2 to all partitions of data set 1 Translates to map-only job – Open data set 2 as “side file”

50. Merge Join Exploit data sets are already sorted. Again, a map-only job – Open other data set as “side file”

51. Multiple Data Flows [1] Load Users Filter bots Group by state Group by state Apply udfs Store into ‘bystate’ Group by demographic Group by demographic Apply udfs Store into ‘bydemo’ Map 1 Reduce 1

52. Multiple Data Flows [2] Load Users Filter bots Group by state Group by state Apply udfs Store into ‘bystate’ Group by demographic Group by demographic Apply udfs Store into ‘bydemo’ Split Demultiplex Map 1 Reduce 1

53. Performance

54. Strong & Weak Points Explicit Dataflow Retains Properties of Map-Reduce Scalability Fault Tolerance Multi Way Processing Open Source Column wise Storage structures are missing Memory Management No facilitation for Non Java Users Limited Optimization No GUI for Flow Graphs +++ The step-by-step method of creating a program in Pig is much cleaner and simpler to use than the single block method of SQL. It is easier to keep track of what your variables are, and where you are in the process of analyzing your data. Jasmine Novak Engineer, Yahoo! With the various interleaved clauses in SQL It is difficult to know what is actually happening sequentially. With the various interleaved clauses in SQL It is difficult to know what is actually happening sequentially. David Ciemiewicz Search Excellence, Yahoo!

55. Hot Competitor Google Map-Reduce System

56. Installation Process 1.Download Java Editor (NetBeans or Eclipse) 2.Create sample pig latin code in any Java editor 3.Install Pig Plugins (JavaCC, Subclipse) 4.Add necessary jar files for Hadoop API in project 5.Run input files in any Java editor using Hadoop API, NOTE: Your system must work as distributed cluster Another NOTE: If you want to run sample as Command Line please install more softwares: -JUNIT, Ant, CygWin -And set your path variables everywhere

57. New Systems For Data Analysis  Map-Reduce  Apache Hadoop  Dryad  Sawzall  Hive...

58. Outline Map-Reduce and the need for Pig Latin Pig Latin Compilation into Map-Reduce Optimization Future Work

59. Future / In-Progress Tasks Columnar-storage layer Non Java UDF and SQL Interface Metadata repository GUI Pig Tight integration with a scripting language – Use loops, conditionals, functions of host language Memory Management & Enhanced Optimization Project Suggestions at: http://wiki.apache.org/pig/ProposedProjects

60. Summary Big demand for parallel data processing – Emerging tools that do not look like SQL DBMS – Programmers like dataflow pipes over static files Hence the excitement about Map-Reduce But, Map-Reduce is too low-level and rigid Pig Latin Sweet spot between map-reduce and SQL Pig Latin Sweet spot between map-reduce and SQL