In Memory Data Pipeline And Warehouse At Scale - BerlinBuzzwords 2015
3 likes•1,153 views
The document describes an in-memory data pipeline and warehouse using Spark, Spark SQL, Tachyon and Parquet. It involves ingesting financial transaction data from S3, transforming the data through cleaning and joining steps, and building a data warehouse using Spark SQL and Parquet for querying. Key aspects covered include distributing metadata lookups, balancing data partitions, broadcasting joins to avoid skew, caching data in Tachyon and Jaws for a RESTful interface to Spark SQL.
In Memory Data Pipeline And Warehouse At Scale - BerlinBuzzwords 2015
- 1. Radu Chilom [email protected] In-memory data pipeline and warehouse at scale using Spark, Spark SQL, Tachyon and Parquet Buzzwords Berlin - 2015 Ema Iancuta [email protected]
- 2. ‹#› • Big data analytics / machine learning • 6+ years with Hadoop ecosystem • 2 years with Spark • http://atigeo.com/ • A research group that focuses on the technical problems that exist in the big data industry and provides open source solutions • http://bigdataresearch.io/
- 3. ‹#› • Intro • Use Case • Data pipeline with Spark • Spark Job Rest Service • Spark SQL Rest Service (Jaws) • Parquet • Tachyon • Demo Agenda
- 4. ‹#› • Build an in memory data pipeline for millions financial transactions used downstream by data scientists for detecting fraud • Ingestion from S3 to our Tachyon/HDFS cluster • Data transformation • Data warehouse Use Case
- 5. ‹#› • “fast and general engine for large-scale data processing” • Built around the concept of RDD • API for Java/Scala/Python (80 operators) • powers a stack of high level tools including Spark SQL, MLlib, Spark Streaming. Apache Spark
- 6. ‹#› Public S3 Bucket: public-financial-transactions public-financial- transactions (s3-bucket) scheme scheme.csv data input-0.csv data2 input-1.csv . . . . . .
- 7. ‹#› • Download from S3 1. Ingestion • Resolving the wildcards means listing files metadata • Listing the metadata for a large number of files from external sources can take a long time
- 8. ‹#› Listing the metadata (distributed) Driver Worker Worker Worker folder1 folder2 folder3 folder4 folder5 folder6 folder1 folder2 folder3 folder4 folder5 folder6 file-11 file-12 file-21 file-22 file-23 file-31 file-32 file-41 file-42 file-43 file-44 file-51 file-52 file-61
- 9. ‹#› Listing the metadata (distributed) • For fine tuning, specify the number of partitions
- 10. ‹#› • Unbalanced partitions Download Files
- 11. ‹#› Unbalanced partitions Partition 0 transactions.csv Partition 1 input.csv data.csv values.csv buzzwords.csv buzzwords.txt
- 12. ‹#› Balancing partitions Partition 0 (0, transactions.csv) (2, data.csv) (4, buzzwords.csv) Partition 1 (1, input.csv) (3, values.csv) (5, buzzwords.txt)
- 13. ‹#› • Balancing partitions Keep in mind that repartitioning your data is a fairly expensive operation. Balancing partitions
- 14. ‹#› • Data cleaning is the first step in any data science project • For this use-case: - Remove lines that don't match the structure - Remove “useless” columns - Transform data to be in a consistent format 2. Data Transformation
- 15. ‹#› • Join Find Country char code Numeric Format Alpha 2 Format 276 DE Name Germany • Problem with skew in the key distribution
- 17. ‹#› • Broadcast Country Codes Map Find Country char code
- 18. ‹#› Metrics
- 19. ‹#› Transformation with Join vs Broadcasted Map (skewed key) Seconds 0 60 120 180 240 300 Rows 1 Million 2 Million 3 Million Join Broadcasted Map
- 20. ‹#› • Supports multiple contexts • Launches a new process for each Spark context • Inter-process communication with Akka actors • Easy context creation & job runs • Supports Java and Scala code • Friendly UI Spark-Job-Rest https://github.com/Atigeo/spark-job-rest
- 21. ‹#› • Hive • Apache Pig • Impala • Presto • Stinger (Hive on Tez) • Spark SQL Build a data warehouse
- 22. ‹#› Spark SQL • Support for multiple input formats • Rich language interfaces • RDD-aware optimizer RDD DataFrame / SchemaRDD JDBC HIVE QL SQL
- 23. ‹#› Creating a data frame
- 24. ‹#› Perform a simple query: Explore data > Directly on the data frame > Registering a temporary table - select - filter - join - groupBy - agg - join - count - sort - where ..etc.
- 25. ‹#› Creating a data warehouse https://github.com/Atigeo/xpatterns-spark-parquet
- 26. ‹#› • TextFile • SequenceFile • RCFile (RowColumnar) • ORCFile (OptimizedRowColumnar) • Avro • Parquet File Formats > columnar format > good for aggregation queries > only the required columns are read from disk > nested data structures > schema with the data > spark sql supports schema evolution > efficient compression
- 27. ‹#› Tachyon • memory-centric distributed file system enabling reliable file sharing at memory-speed across cluster frameworks • Pluggable underlayer file system: hdfs, S3,…
- 28. ‹#› Caching in Spark SQL • Cache data in columnar format • Automatically compression tune
- 29. ‹#› • spark context might crash Spark cache vs Tachyon • GC kicks in • share data between different applications
- 30. ‹#› - Highly scalable and resilient data warehouse - Submit queries concurrently and asynchronously - Restful alternative to Spark SQL JDBC having a interactive UI - Since Spark 091 with Shark - Support for Spark SQL and Hive - MR (and more to come) https://github.com/Atigeo/jaws-spark-sql-rest Jaws spark sql rest
- 31. ‹#› - Akka actors to communicate through instances - Support cancel queries - Supports large results retrieval - Parquet in memory warehouse - returns persisted logs, results, query history - provides a metadata browser - configuration file to fine tune spark Jaws main features
- 33. ‹#› Q & A
- 34. © 2013 Atigeo, LLC. All rights reserved. Atigeo and the xPatterns logo are trademarks of Atigeo. The information herein is for informational purposes only and represents the current view of Atigeo as of the date of this presentation. Because Atigeo must respond to changing market conditions, it should not be interpreted to be a commitment on the part of Atigeo, and Atigeo cannot guarantee the accuracy of any information provided after the date of this presentation. ATIGEO MAKES NO WARRANTIES, EXPRESS, IMPLIED OR STATUTORY, AS TO THE INFORMATION IN THIS PRESENTATION.