Apache Spark: Lightning Fast Cluster Computing
Download as PPTX, PDF1 like763 views
Apache Spark is an open-source cluster computing framework for fast and large-scale data processing. It uses an in-memory data abstraction called resilient distributed datasets (RDDs) that allow parallel operations on large datasets across a cluster. Spark also provides APIs in Java, Scala, Python and R for interactive data analysis through its core engine as well as high-level libraries for SQL, streaming, machine learning and graph processing.
![Page8 © Hortonworks Inc. 2011 – 2015. All Rights Reserved
lines = spark.textFile(“hdfs://...”)
errors = lines.filter(lambda s: s.startswith(“ERROR”))
messages = errors.map(lambda s: s.split(‘t’)[2])
messages.cache()
messages.filter(lambda s: “foo” in s).count()
messages.filter(lambda s: “bar” in s).count()
. . .
Base RDD
Transformed RDD
Action
Result: full-text search of Wikipedia in <1 sec
(vs 20 sec for on-disk data)
Result: scaled to 1 TB data in 5-7 sec
(vs 170 sec for on-disk data)
Example: Mining Console Logs
Load error messages from a log into memory, then
interactively search for patterns](https://image.slidesharecdn.com/sparkato-151120140438-lva1-app6892/85/Apache-Spark-Lightning-Fast-Cluster-Computing-8-320.jpg)
Apache Spark: Lightning Fast Cluster Computing
- 1. Apache Spark Lightening Fast Cluster Computing Eric Mizell – Director, Solution Engineering
- 2. Page2 © Hortonworks Inc. 2011 – 2015. All Rights Reserved What is Apache Spark? Apache Open Source Project Distributed Compute Engine for fast and expressive data processing Designed for Iterative, In-Memory computations and interactive data mining Expressive Multi-Language APIs for Java, Scala, Python, and R Powerful Abstractions Enable data workers to rapidly iterate over data for: • ETL, Machine Learning, SQL, Stream Processing, and Graph Processing Scala Java Python APIs Spark Core EngineSpark Core Engine GraphX Spark SQL Spark Streaming MLlib
- 3. Page3 © Hortonworks Inc. 2011 – 2015. All Rights Reserved Why Spark? Elegant Developer APIs • Data Frames/SQL, Machine Learning, Graph algorithms and streaming • Scala, Python, Java and R • Single environment for pre-processing and Machine Learning In-memory computation model • Effective for iterative computations and machine learning Machine Learning On Hadoop • Implementation of distributed ML-algorithms • Pipeline API (Spark ML) Runs on Hadoop on YARN, Mesos, standalone
- 4. Page4 © Hortonworks Inc. 2011 – 2015. All Rights Reserved Interactions with Spark Command Line • Scala shell – Scala/Java (./bin/spark-shell) • Python - (./bin/pyspark) Notebooks • Apache Zeppelin Notebook • Juptyer/IPython Notebook • IRuby Notebook ODBC/JDBC (Spark SQL only via Thrift) • Simba driver • DataDirect driver
- 5. Page5 © Hortonworks Inc. 2011 – 2015. All Rights Reserved Introducing Apache Zeppelin Web-based Notebook for interactive analytics Features Ad-hoc experimentation Deeply integrated with Spark + Hadoop Supports multiple language backends Incubating at Apache Use Case Data exploration and discovery Visualization Interactive snippet-at-a-time experience “Modern Data Science Studio”
- 6. Page6 © Hortonworks Inc. 2011 – 2015. All Rights Reserved Fundamental Abstraction: Resilient Distributed Datasets RDD Work with distributed collections as primitives RDD Properties • Immutable collections of objects spread across a cluster • Built through parallel transformations (map, filter, etc.) • Automatically rebuilt on failure • Controllable persistence (e.g. caching in RAM) Multiple Languages broad developer, partner and customer engagement RDD Partition 1 RDD Partition 2 RDD Partition 3Worker Node Worker Node Worker Node RDD LogicalSpark Driver sc = new SparkContext rDD =sc.textfile(“hdfs://…”) rDD.filter(…) rDD.Cache rDD.Count rDD.map … Developer Physical Writes RDD RDDs are collections of objects distributed across a cluster, cached in RAM or on disk. They are built through parallel transformations, automatically rebuilt on failure and immutable (each transformation creates a new RDD).
- 7. Page7 © Hortonworks Inc. 2011 – 2015. All Rights Reserved What can developers do with RDDs? RDD Operations Transformations • e.g. map, filter, groupBy, join • Lazy operations to build RDDs from other RDDs Actions • e.g. count, collect, save • Return a result or write it to storage Other primitives • Accumulator • Broadcast Variables Developer Writes RDD Operations Writes Accumulator s Actions Broadcast Variables Transformations
- 8. Page8 © Hortonworks Inc. 2011 – 2015. All Rights Reserved lines = spark.textFile(“hdfs://...”) errors = lines.filter(lambda s: s.startswith(“ERROR”)) messages = errors.map(lambda s: s.split(‘t’)[2]) messages.cache() messages.filter(lambda s: “foo” in s).count() messages.filter(lambda s: “bar” in s).count() . . . Base RDD Transformed RDD Action Result: full-text search of Wikipedia in <1 sec (vs 20 sec for on-disk data) Result: scaled to 1 TB data in 5-7 sec (vs 170 sec for on-disk data) Example: Mining Console Logs Load error messages from a log into memory, then interactively search for patterns
- 9. Page9 © Hortonworks Inc. 2011 – 2015. All Rights Reserved RDD Demo
- 10. Page10 © Hortonworks Inc. 2011 – 2015. All Rights Reserved SQL SQL Access and Data Frames YARN HDFS Scala Java Python APIs Spark Core EngineSpark Core Engine GraphX Spark Streaming MLlib Spark SQL
- 11. Page11 © Hortonworks Inc. 2011 – 2015. All Rights Reserved YARN HDFS Spark SQL Table Structure integrated to work with tables and rows Hive Queries via Spark by Spark SQL Context can connect to Hive and query Hive Bindings to Python, Scala, Java, and R Data Frames new abstractions simplifies and speeds up SQL processing Spark Core Engine Spark SQL Data Frame DSL Spark SQL Data Frame API Data Source API
- 12. Page12 © Hortonworks Inc. 2011 – 2015. All Rights Reserved Storage What are Data Frames? Data Frames represent data in RDDs as a Table RDD is a low level abstraction –Think of RDD as bytecode and DataFrame as the Java Program Data Frame Properties –Data Frames attach schema to RDDs –Allows users to perform aggressive query optimizations –Brings the power of SQL to RDDs! dept name age Bio H Smith 48 CS A Turing 54 Bio B Jones 43 Phys E Witten 61 Tuple Relational View Columnar Storage ORCFile Parquet Unstructured Data JSON CSV Text Avro Custom Weblog
- 13. Page13 © Hortonworks Inc. 2011 – 2015. All Rights Reserved Data Frames are intuitive RDD Example Equivalent Data Frame Example dept name age Bio H Smith 48 CS A Turing 54 Bio B Jones 43 Phys E Witten 61 Find average age by department?
- 14. Page14 © Hortonworks Inc. 2011 – 2015. All Rights Reserved DataFrame Demo YARN HDFS Scala Java Python APIs Spark Core EngineSpark Core Engine GraphX Spark Streaming MLlib Spark SQL
- 15. Page15 © Hortonworks Inc. 2011 – 2015. All Rights Reserved MLlib Machine Learning Library YARN HDFS Scala Java Python APIs Spark Core EngineSpark Core Engine GraphX Spark SQL Spark Streaming MLlib
- 16. Page16 © Hortonworks Inc. 2011 – 2015. All Rights Reserved What is Machine Learning? Machine learning is the study of algorithms that learn concepts from data. A key aspect of learning is generalization: how well a learning algorithm is able to predict on unseen examples.
- 17. Page17 © Hortonworks Inc. 2011 – 2015. All Rights Reserved Machine Learning Primitives Unsupervised Learning Clustering (K-means) Recommendation Collaborative Filtering - alternating least squares Dimensionality Reductions - Principal component analysis (PCA) and singular value decomposition (SVD) Supervised Learning Classification - Naïve Bayes, Decision Tree, Random Forest, Gradient Boosted Trees Regression - linear, logistic and Support Vector Machines (SVMs)
- 18. Page18 © Hortonworks Inc. 2011 – 2015. All Rights Reserved ML Workflows are complex Q-Q Q-A similarit y Log Parsing, Cleanin g Ad category mapping Query category mapping Poly Exp (Q-A) Feature s Model Linear Solver train test Metrics • Feature Extraction Feature Extraction Ad Server Sponsored Search Advertising Pipeline Challenges: -> specify pipeline -> inspect and debug -> tune hyperparameters -> productionize HDFS
- 19. Page19 © Hortonworks Inc. 2011 – 2015. All Rights Reserved ML Pipeline makes ML workflows easier Transformer Transforms one dataset into another Estimator Fits model to data Pipeline Sequence of stages, consisting of estimators or transformers Parameters Trait for components that take parameters
- 20. Page20 © Hortonworks Inc. 2011 – 2015. All Rights Reserved Streaming Real Time Stream Processing YARN HDFS Scala Java Python APIs Spark Core EngineSpark Core Engine GraphX Spark SQL MLlib Spark Streaming
- 21. Page21 © Hortonworks Inc. 2011 – 2015. All Rights Reserved Spark Streaming • Spark Streaming is an extension of Spark-core API that supports scalable, high throughput and fault-tolerant streaming applications. • Data can be ingested from many data sources like Kafka, Flume, Twitter, ZeroMQ or TCP sockets • Data is processed using the now-familiar API: map, filter, reduce, join and window • Processed data can be stored in databases, filesystems, or live dashboards
- 22. Page22 © Hortonworks Inc. 2011 – 2015. All Rights Reserved GraphX Graph Processing YARN HDFS Scala Java Python APIs Spark Core EngineSpark Core Engine Spark SQL Spark Streaming MLlib GraphX
- 23. Page23 © Hortonworks Inc. 2011 – 2015. All Rights Reserved Spark GraphX Graph API on Spark Seamlessly work with graphs and collections Growing library of graph algorithms • SVD++, Connected Components, Triangle Count, … Iterative Graph Computations using Pregel Implements Valiant’s Bulk Synchronous Parallel (BSP) model for distributing graph algorithms. Use Case Social Media: Suggest new connections based on existing relationships Networking: Best routing through a given network
- 24. Page24 © Hortonworks Inc. 2011 – 2015. All Rights Reserved Part. 2 Part. 1 Vertex Table (RDD) B C A D F E A D Distributed Graphs as Tables (RDDs) D Property Graph B C D E AA F Edge Table (RDD) A B A C C D B C A E A F E F E D B C D E A F Routing Table (RDD) B C D E A F 1 2 1 2 1 2 1 2 2D Vertex Cut Heuristic
- 25. Page25 © Hortonworks Inc. 2011 – 2015. All Rights Reserved How to Get Started with Spark
- 26. Page26 © Hortonworks Inc. 2011 – 2015. All Rights Reserved Try Spark Today Download the Hortonworks Sandbox http://hortonworks.com/products/hortonworks-sandbox/ Go to the Apache Spark Website http://spark.apache.org/ Learn Spark Build a Proof of Concept Test New Functionality
- 27. Page27 © Hortonworks Inc. 2011 – 2015. All Rights Reserved © Hortonworks Inc. 2013 Thank You! Eric Mizell - Director, Solutions Engineering [email protected]
Editor's Notes
- #3: NEED SPEAKER NOTES
- #4: NEED SPEAKER NOTES
- #5: NEED SPEAKER NOTES
- #6: TALK TRACK Ad-hoc experimentation Spark, Hive, Shell, Flink, Tajo, Ignite, Lens, etc Deeply integrated with Spark + Hadoop Can be managed via Ambari Stacks Supports multiple language backends Pluggable “Interpreters” Incubating at Apache 100% open source and open community [NEXT SLIDE]
- #7: TALK TRACK Ensuring Spark is well integrated with YARN, Ambari, and Ranger enables enterprise to deploy Spark apps with confidence, and since HDP is available across Windows, Linux, on-premises and cloud deployment environments, it just makes it that much easier for enterprises to adopt it. [NEXT SLIDE] http://www.cs.berkeley.edu/~matei/papers/2010/hotcloud_spark.pdf http://www.cs.berkeley.edu/~matei/papers/2012/nsdi_spark.pd
- #8: TALK TRACK Ensuring Spark is well integrated with YARN, Ambari, and Ranger enables enterprise to deploy Spark apps with confidence, and since HDP is available across Windows, Linux, on-premises and cloud deployment environments, it just makes it that much easier for enterprises to adopt it. [NEXT SLIDE] http://www.cs.berkeley.edu/~matei/papers/2010/hotcloud_spark.pdf http://www.cs.berkeley.edu/~matei/papers/2012/nsdi_spark.pd
- #9: Key idea: add “variables” to the “functions” in functional programming
- #10: NEED SPEAKER NOTES
- #11: NEED SPEAKER NOTES
- #12: NEED SPEAKER NOTES
- #14: Spark DataFrames represent tabular Data
- #15: NEED SPEAKER NOTES
- #16: NEED SPEAKER NOTES
- #17: NEED SPEAKER NOTES
- #18: TALK TRACK Ensuring Spark is well integrated with YARN, Ambari, and Ranger enables enterprise to deploy Spark apps with confidence, and since HDP is available across Windows, Linux, on-premises and cloud deployment environments, it just makes it that much easier for enterprises to adopt it. [NEXT SLIDE]
- #20: TALK TRACK [NEXT SLIDE]
- #21: NEED SPEAKER NOTES
- #23: NEED SPEAKER NOTES
- #24: TALK TRACK Ensuring Spark is well integrated with YARN, Ambari, and Ranger enables enterprise to deploy Spark apps with confidence, and since HDP is available across Windows, Linux, on-premises and cloud deployment environments, it just makes it that much easier for enterprises to adopt it. [NEXT SLIDE] [RESOURCES] A vertex is an entity that can bring a bag of data (generally small) An edge connects vertices and can also own a bag of data https://amplab.cs.berkeley.edu/wp-content/uploads/2013/05/grades-graphx_with_fonts.pdf
- #28: Takeaways Change order of interoperability slide Flush out no lock-in slide to talk about “proprietary open source”