How Hadoop Revolutionized Data Warehousing at Yahoo and Facebook
Download as PPT, PDF•63 likes•22,397 views
Hadoop was developed to solve problems with data warehousing systems at Yahoo and Facebook that were limited in processing large amounts of raw data in real-time. Hadoop uses HDFS for scalable storage and MapReduce for distributed processing. It allows for agile access to raw data at scale for ad-hoc queries, data mining and analytics without being constrained by traditional database schemas. Hadoop has been widely adopted for large-scale data processing and analytics across many companies.
![Contact Information If you have further questions or comments: Amr Awadallah CTO, Cloudera Inc. [email_address] 650-362-0488 twitter.com/awadallah twitter.com/cloudera](https://image.slidesharecdn.com/awadallah-final-tdwibiexecsum2009-090805180646-phpapp01/85/How-Hadoop-Revolutionized-Data-Warehousing-at-Yahoo-and-Facebook-22-320.jpg)
How Hadoop Revolutionized Data Warehousing at Yahoo and Facebook
- 1. Amr Awadallah CTO, Cloudera, Inc. August 5, 2009 How Hadoop Revolutionized Data Warehousing at Yahoo and Facebook
- 2. Outline Problems We Wanted to Solve What is Hadoop? HDFS and MapReduce Access Languages for Hadoop Hadoop vs RDBMSes Conclusion
- 3. Our Older Systems Limited Raw Data Access Storage Farm for Unstructured Data (20TB/day) Instrumentation Collection RDBMS (200GB/day) BI / Reports Mostly Append Ad hoc Queries & Data Mining ETL Grid Non-Consumption Filer heads are a bottleneck
- 4. We Needed To Be More Agile (part 1) Data Errors and Reprocessing We encountered data errors that required reprocessing, which could happen a long time after the fact. “Tape Data” was cost prohibitive to reprocess, we needed to retain raw-data online for long time periods Conformation Loss Conversion of data from raw format to conformed dimensions causes some information loss. We needed access to the original data to recover lost information whenever needed (e.g.: a new browser user agent) Shrinking ETL Window The storage filers for raw data started becoming a significant bottleneck as large amounts of data needed to be copied to the ETL grid for processing (e.g. 30 hours to process a day’s worth of data) Ad Hoc Queries on Raw Data We wanted to run ad hoc queries against the original raw event data, but the storage filers only store and can’t compute
- 5. We Needed To Be More Agile (part 2) Data Model Agility: Schema-on-Read vs Schema-on-Write We wanted to access data even if it had no schema yet, e.g. frequently a new product or feature will launch but we can’t get their dashboards since their schemas weren’t defined yet Schema-on-Read is slower in terms of machine time (due to read overhead) but it allows us to evolve in an agile way, then we materialize to relational datamarts when data model stabilizes Consolidated Repository and Ubiquitous Access We wanted to eliminate borders and have a single repository where anybody can store, join, and process any of our data bits Beyond Reporting (Data-As-Product) Last, but not least, we wanted to process the data in ways that feed directly into the product/business (e.g. Email Spam Filtering, Ad Targeting, Collaborative Filtering, Multimedia Processing)
- 6. The Solution: A Store-Compute Grid Storage + Computation Instrumentation Collection RDBMS Interactive Apps “ Batch” Apps Mostly Append ETL and Aggregations Ad hoc Queries & Data Mining
- 7. What is Hadoop? A scalable fault-tolerant grid operating system for data storage and processing Its scalability comes from the marriage of: HDFS: Self-Healing High-Bandwidth Clustered Storage MapReduce: Fault-Tolerant Distributed Processing Operates on unstructured and structured data A large and active ecosystem (many developers and additions like HBase, Hive, Pig, …) Open source under the friendly Apache License http://wiki.apache.org/hadoop/
- 8. Hadoop History 2002-2004: Doug Cutting and Mike Cafarella started working on Nutch (a web-scale crawler-based search system) 2003-2004: Google publishes GFS and MapReduce papers 2004: Cutting adds DFS & MapReduce support to Nutch 2006: Yahoo! hires Cutting, Hadoop spins out of Nutch 2007: NY Times converts 4TB of archives over 100 EC2s 2008: Web-scale deployments at Y!, Facebook, Last.fm April 2008: Fastest sort of a TB, 3.5mins over 910 nodes May 2009: Fastest sort of a TB, 62secs over 1460 nodes Sorted a PB in 16.25hours over 3658 nodes 100s of deployments worldwide ( http://wiki.apache.org/hadoop/PoweredBy ) June 2009: Hadoop Summit 2009 – 750 attendees
- 9. Hadoop Design Axioms System Shall Manage and Heal Itself Performance Shall Scale Linearly Compute Should Move to Data Simple Core, Modular and Extensible
- 10. HDFS: Hadoop Distributed File System Block Size = 64MB Replication Factor = 3 Cost/GB is a few ¢/month vs $/month
- 12. MapReduce Example for Word Count cat *.txt | mapper.pl | sort | reducer.pl > out.txt Split 1 Split i Split N Map 1 (docid, text) (docid, text) Map i (docid, text) Map M Reduce 1 Output File 1 (sorted words, sum of counts) Reduce i Output File i (sorted words, sum of counts) Reduce R Output File R (sorted words, sum of counts) (words, counts) (sorted words, counts) Map (in_key, in_value) => list of (out_key, intermediate_value) Reduce (out_key, list of intermediate_values) => out_value(s) Shuffle (words, counts) (sorted words, counts) “ To Be Or Not To Be?” Be, 5 Be, 12 Be, 7 Be, 6 Be, 30
- 13. Hadoop Is More Than Just Analytics/BI Building the Web Search Index Processing News/Content Feeds Content/Ad Targeting Optimization Fraud Detection and Fighting Email Spam Facebook Lexicon: Trends of words on walls Collaborative Filtering (you might like) Batch Video/Image Transcoding Gene Sequence Alignment
- 14. Apache Hadoop Ecosystem HDFS (Hadoop Distributed File System) HBase (Key-Value store) MapReduce (Job Scheduling/Execution System) Pig (Data Flow) Hive (SQL) BI Reporting ETL Tools Avro (Serialization) Zookeepr (Coordination) Sqoop RDBMS
- 15. Hadoop Development Languages Java MapReduce Gives the most flexibility and performance, but with a potentially longer development cycle Streaming MapReduce Allows you to develop in any language of your choice, but slightly slower performance Pig A relatively new data-flow language contributed by Yahoo, suitable for ETL like workloads (procedural multi-stage jobs) Hive A SQL warehouse on top of MapReduce (contributed by Facebook). It has two main components: A meta-store which keeps the schema for files, and An interpreter which converts the SQL query into MapReduce
- 16. Hive Features A subset of SQL covering the most common statements Agile data types: Array, Map, Struct, and JSON objects User Defined Functions and Aggregates Regular Expression support MapReduce support JDBC support Partitions and Buckets (for performance optimization) In The Works: Indices, Columnar Storage, Views, Microstrategy compatibility, Explode/Collect More details: http://wiki.apache.org/hadoop/Hive
- 17. Relational Databases: An ACID Database system Stores Tables (Schema) Stores 100s of terabytes Processes 10s of TB/query Transactional Consistency Lookup rows using index Mostly queries Interactive response Hadoop: A data grid operating system Stores Files (Unstructured) Stores 10s of petabytes Processes 10s of PB/job Weak Consistency Scan all blocks in all files Queries & Data Processing Batch response (>1sec) Hadoop vs. Relational Databases
- 18. Relational Databases: Hadoop: Use The Right Tool For The Right Job
- 19. Hadoop Criticisms (part 1) Hadoop MapReduce requires Rocket Scientists Hadoop has the benefit of both worlds, the simplicity of SQL and the power of Java (or any other language for that matter) Hadoop is not very efficient hardware wise Hadoop optimizes for scalability, stability and flexibility versus squeezing every tiny bit of hardware performance It is cost efficient to throw more “pizza box” servers to gain performance than hire more engineers to manage, configure, and optimize the system or pay 10x the hardware cost in software Hadoop can’t do quick random lookups HBase enables low-latency key-value pair lookups (no fast joins) Hadoop doesn’t support updates/inserts/deletes Not for multi-row transactions, but HBase enables transactions with row-level consistency semantics
- 20. Hadoop Criticisms (part 2) Hadoop isn’t highly available Though Hadoop rarely loses data, it can suffer from down-time if the master NameNode goes down. This issue is currently being addressed, and there are HW/OS/VM solutions for it Hadoop can’t be backed-up/recovered quickly HDFS, like other file systems, can copy files very quickly. It also has utilities to copy data between HDFS clusters Hadoop doesn’t have security Hadoop has Unix style user/group permissions, and the community is working on improving its security model Hadoop can’t talk to other systems Hadoop can talk to BI tools using JDBC, to RDBMSes using Sqoop, and to other systems using FUSE, WebDAV & FTP
- 21. Conclusion Hadoop is a data grid operating system which augments current BI systems and improves their agility by providing an economically scalable solution for storing and processing large amounts of unstructured data over long periods of time
- 22. Contact Information If you have further questions or comments: Amr Awadallah CTO, Cloudera Inc. [email_address] 650-362-0488 twitter.com/awadallah twitter.com/cloudera
- 23. APPENDIX
- 24. Hadoop High-Level Architecture Name Node Maintains mapping of file blocks to data node slaves Job Tracker Schedules jobs across task tracker slaves Data Node Stores and serves blocks of data Hadoop Client Contacts Name Node for data or Job Tracker to submit jobs Task Tracker Runs tasks (work units) within a job Share Physical Node
Editor's Notes
- #6: Data-As-Product is also referred to as Active DW, Operational BI, Online BI, etc.
- #7: The solution is to *augment* the current RDBMSes with a “smart” storage/processing system. The original event level data is kept in this smart storage layer and can be mined as needed. The aggregate data is kept in the RDBMSes for interactive reporting and analytics.
- #8: The system is self-healing in the sense that it automatically routes around failure. If a node fails then its workload and data are transparently shifted some where else. The system is intelligent in the sense that the MapReduce scheduler optimizes for the processing to happen on the same node storing the associated data (or co-located on the same leaf Ethernet switch), it also speculatively executes redundant tasks if certain nodes are detected to be slow. One of the key benefits of Hadoop is the ability to just upload any unstructured files to it without having to “schematize” them first. You can dump any type of data into Hadoop then the input record readers will abstract it out as if it was structured (i.e. schema on read vs on write) Open Source Software allows for innovation by partners and customers. It also enables third-party inspection of source code which provides assurances on security and product quality. 1 HDD = 75 MB/sec, 1000 HDDs = 75 GB/sec, the “head of fileserver” bottleneck is eliminated.
- #9: http://developer.yahoo.net/blogs/hadoop/2009/05/hadoop_sorts_a_petabyte_in_162.html
- #10: Speculative Execution, Data rebalancing, Background Checksumming, etc.
- #11: Pool commodity servers in a single hierarchical namespace. Designed for large files that are written once and read many times. Example here shows what happens with a replication factor of 3, each data block is present in at least 3 separate data nodes. Typical Hadoop node is eight cores with 16GB ram and four 1TB SATA disks. Default block size is 64MB, though most folks now set it to 128MB
- #12: Differentiate between MapReduce the platform and MapReduce the programming model. The analogy is similar to the RDBMs which executes the queries, and SQL which is the language for the queries. MapReduce can run on top of HDFS or a selection of other storage systems Intelligent scheduling algorithms for locality, sharing, and resource optimization.
- #13: Think: SELECT word, count(*) FROM documents GROUP BY word Checkout ParBASH: http://cloud-dev.blogspot.com/2009/06/introduction-to-parbash.html
- #14: Other uses like face recognition, document discovery, OCR, gene sequence alignment, etc. Data Mining: ** Search and Text Analytics ** Clustering/Categorization ** Modeling/Machine Learning ** Optimization/Operations Research ** Response Prediction/Forecasting ** Simulation, Monte-Carlo like. ** Random Walks of Connectivity Graphs
- #15: HBase: Low Latency Random-Access with per-row consistency for updates/inserts/deletes
- #16: First bullet is like assembly, then it gets higher level from there.
- #17: Query: SELECT, FROM, WHERE, JOIN, GROUP BY, SORT BY, LIMIT, DISTINCT, UNION ALL Join: LEFT, RIGHT, FULL, OUTER, INNER DDL: CREATE TABLE, ALTER TABLE, DROP TABLE, DROP PARTITION, SHOW TABLES, SHOW PARTITIONS DML: LOAD DATA INTO, FROM INSERT Types: TINYINT, INT, BIGINT, BOOLEAN, DOUBLE, STRING, ARRAY, MAP, STRUCT, JSON OBJECT Query: Subqueries in FROM, User Defined Functions, User Defined Aggregates, Sampling (TABLESAMPLE) Relational: IS NULL, IS NOT NULL, LIKE, REGEXP Built in aggregates: COUNT, MAX, MIN, AVG, SUM Built in functions: CAST, IF, REGEXP_REPLACE, … Other: EXPLAIN, MAP, REDUCE, DISTRIBUTE BY List and Map operators: array[i], map[k], struct.field
- #18: Hadoop is good for storing and processing large amounts of unstructured or structured data in batch form (i.e. full table scans) Hadoop with HBASE (or Hypertable) can do inserts/updates/deletes with reasonable interactive response times (also see Cassandra).
- #19: Sports car is refined, accelerates very fast, and has a lot of addons/features. But it is pricey on a per bit basis and is expensive to maintain. Cargo train is rough, missing a lot of functionality, slow to start, but once it gets going it can carry a lot of stuff very economically.
- #20: Hadoop is efficient on a cost basis. Security: Need better integration with systems like LDAP or Kerberos. Also need better isolation against malicious users, though auditing can potentially catch those.
- #25: The Data Node slave and the Task Tracker slave can, and should, share the same server instance to leverage data locality whenever possible.